IP Library › Granted Patent US 12,738,026
Granted Patent B2
US 12,738,026 · App. 18/570,325 · Granted Sep 15, 2026

Systems, methods, and computer programs for using a network of machine learning models to detect an image depicting an object of interest which can be partially occluded by another object

Inventors: Alan Yuille (Baltimore, MD); Adam Kortylewski (Baltimore, MD)
Assignee: The Johns Hopkins University
G06V10/7715G06T7/74G06V10/40G06V10/764G06V10/82G06T2207/20081G06T2207/20084
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,738,026
App. No.
18/570,325
Granted
Sep 15, 2026
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, used for object detection in an input image that can include at least partial object occlusion. In some implementations, input data representing the image depicting an object can include object-based features and context-based features used for object detection. The feature is processed by a deep convolutional neural network (DCNN) model. First feature data generated by the DCNN is provided to an occlusion model and a generative compositional model. The occlusion model can detect locations where an object depicted in the image is occluded by an object of any other type. The generative compositional model detects the presence of different classes of objects that represent parts or partial components of object depicted in the image. The output of the compositional model and occlusion model is a likelihood map that shows if an object is depicted in the input image.

Claims (79)

1 . A method comprising:

obtaining, by one or more computers, a first feature set that represents a first image that depicts a first type of object, wherein the first feature set preserves spatial features of the first image;

providing, by the one or more computers, the obtained first feature set as an input to a first machine learning model that has been trained to process a feature set that preserves spatial features of an image depicting an object of the same object type as the first type of object and generate output data for each class of a plurality of different classes that each correspond to a particular spatial orientation of an object of the same object type as the first type of object, where first output data for each class represents a likelihood that an image represented by the first feature set depicts an object in a particular spatial orientation that corresponds to the class;

providing, by the one or more computers, the obtained first feature set as an input to a second machine learning model that has been trained to process a feature map corresponding to an image of any object type and generate output data that includes an occlusion likelihood, wherein the occlusion likelihood indicates a likelihood that an object depicted in an image represented by a feature set processed by the second machine learning model is at least partially occluded;

processing, by the one or more computers, the obtained first feature set through the first machine learning model to generate the first output data;

processing, by the one or more computers, the obtained first feature set through the second machine learning model to generate second output data, the second output data comprising an object occlusion map;

converting, by the one or more computers, the object occlusion map into a binary occlusion map, the binary occlusion map representing if an object of any type is occluding an object of the first type, wherein converting the object occlusion map into the binary occlusion map comprises:

comparing a positional occlusion likelihood score of the object occlusion map, representing a likelihood that a particular position is occluded, against a second predetermined threshold;

upon determining that the positional occlusion likelihood score exceeds the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is occluded; and

upon determining that the positional occlusion likelihood score does not exceed the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is not occluded;

determining, by the one or more computers and based on the first output data and the second output data, a score that indicates a likelihood that the first image depicts an object of the first type that is at least partially occluded; and

based on a determination that the determined score satisfies a first predetermined threshold, generating, by the one or more computers, third output data that includes an instruction indicating that an object of the first type that is at least partially occluded has been detected.

2 . The method of claim 1 ,

wherein the first machine learning model is a generative compositional model; and

wherein the generative compositional model processes the first feature set to generate a second feature set as an output of the generative model.

3 . The method of claim 1 ,

wherein the second machine learning model is an object occlusion model; and

wherein the object occlusion model comprises a model, trained by a plurality of input images with known occlusion, that is configured to generate occlusion output data, the occlusion output data indicating a measure of the likelihood that an object of any type is present, the object of any type being different from the object of the first type.

4 . The method of claim 1 ,

wherein the first output data is a likelihood map, the likelihood map including a score that a feature of an object depicted in the first image is represented in the first feature set; and

wherein the object occlusion map comprises a score that represents a likelihood that an object of any type is present and occluding the object of the first type depicted in an input image.

5 . The method of claim 4 ,

wherein the method includes a step of combining the likelihood map with the object occlusion map to generate output score data for each class represented in the first output data.

6 . The method of claim 5 ,

wherein the output score data includes positional output score data on feature occlusion likelihood map, the feature occlusion likelihood map representing a plurality of positional scores that a feature is present and occluded at a corresponding position in the first image.

7 . The method of claim 5 ,

wherein the output score data includes a score value corresponding to each of a plurality of classes represented in a generative compositional model; and

the score value represents the likelihood that each class represented in the generative compositional model is present depicted in the first feature set of the first input image.

8 . The method of claim 7 , the method comprises:

upon computing the score value for each class represented in the generative compositional model, selecting the maximum score value as the class being represented in the first feature set depicted in the first image, wherein the object occlusion map is associated with the maximum score.

9 . A system comprising:

one or more computers; and

one or more computer-readable media storing instructions that, when executed, cause the one or more computers to perform operations comprising:

obtaining, by the one or more computers, a first feature set that represents a first image that depicts a first type of object, wherein the first feature set preserves spatial features of the first image;

providing, by the one or more computers, the obtained first feature set as an input to a first machine learning model that has been trained to process a feature set that preserves spatial features of an image depicting an object of the same object type as the first type of object and generate output data for each class of a plurality of different classes that each correspond to a particular spatial orientation of an object of the same object type as the first type of object, where first output data for each class represents a likelihood that an image represented by the first feature set depicts an object in a particular spatial orientation that corresponds to the class;

providing, by the one or more computers, the obtained first feature set as an input to a second machine learning model that has been trained to process a feature map corresponding to an image of any object type and generate output data that includes an occlusion likelihood, wherein the occlusion likelihood indicates a likelihood that an object depicted in an image represented by a feature set processed by the second machine learning model is at least partially occluded;

processing, by the one or more computers, the obtained first feature set through the first machine learning model to generate the first output data;

processing, by the one or more computers, the obtained first feature set through the second machine learning model to generate second output data, the second output data comprising an object occlusion map;

converting, by one or more computers, the object occlusion map into a binary occlusion map, the binary occlusion map representing if an object of any type is occluding an object of the first type, wherein converting the object occlusion map into the binary occlusion map comprises:

comparing a positional occlusion likelihood score of the object occlusion map, representing a likelihood that a particular position is occluded, against a second predetermined threshold;

upon determining that the positional occlusion likelihood score exceeds the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is occluded; and

upon determining that the positional occlusion likelihood score does not exceed the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is not occluded;

determining, by the one or more computers and based on the first output data and the second output data, a score that indicates a likelihood that the first image depicts an object of the first type that is at least partially occluded; and

based on a determination that the determined score satisfies a first predetermined threshold, generating, by the one or more computers, third output data that includes an instruction indicating that an object of the first type that is at least partially occluded has been detected.

10 . The system of claim 9 ,

wherein the first machine learning model is a generative compositional model; and

wherein the generative compositional model processes the first feature set to generate a second feature set as an output of the generative model.

11 . The system of claim 9 ,

wherein the second machine learning model is an object occlusion model; and

wherein the object occlusion model comprises a model, trained by a plurality of input images with known occlusion, that is configured to generate occlusion output data, the occlusion output data indicating a measure of the likelihood that an object of any type is present, the object of any type being different from the object of the first type.

12 . The system of claim 9 ,

wherein the first output data is a likelihood map, the likelihood map including a score that a feature of an object depicted in the first image is represented in the first feature set; and

wherein the object occlusion map comprises a score that represents a likelihood that an object of any type is present and occluding the object of the first type depicted in an input image.

13 . The system of claim 12 ,

wherein the operations comprise a step of combining the likelihood map with the object occlusion map to generate output score data for each class represented in the first output data.

14 . The system of claim 13 ,

wherein the output score data includes positional output score data on feature occlusion likelihood map, the feature occlusion likelihood map representing a plurality of positional scores that a feature is present and occluded at a corresponding position in the first image.

15 . The system of claim 13 ,

wherein the output score data includes a score value corresponding to each of a plurality of classes represented in a generative compositional model; and

the score value represents the likelihood that each class represented in the generative compositional model is present depicted in the first feature set of the first input image.

16 . The system of claim 15 , the operations further comprise:

upon computing the score value for each class represented in the generative compositional model, selecting the maximum score value as the class being represented in the first feature set depicted in the first image, wherein the object occlusion map is associated with the maximum score.

17 . A non-transitory computer-readable medium storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations, comprising:

obtaining, by the one or more computers, a first feature set that represents a first image that depicts a first type of object, wherein the first feature set preserves spatial features of the first image;

providing, by the one or more computers, the obtained first feature set as an input to a first machine learning model that has been trained to process a feature set that preserves spatial features of an image depicting an object of the same object type as the first type of object and generate output data for each class of a plurality of different classes that each correspond to a particular spatial orientation of an object of the same object type as the first type of object, where first output data for each class represents a likelihood that an image represented by the first feature set depicts an object in a particular spatial orientation that corresponds to the class;

providing, by the one or more computers, the obtained first feature set as an input to a second machine learning model that has been trained to process a feature map corresponding to an image of any object type and generate output data that includes an occlusion likelihood, wherein the occlusion likelihood indicates a likelihood that an object depicted in an image represented by a feature set processed by the second machine learning model is at least partially occluded;

processing, by the one or more computers, the obtained first feature set through the first machine learning model to generate the first output data;

processing, by the one or more computers, the obtained first feature set through the second machine learning model to generate second output data, the second output data comprising an object occlusion map;

converting, by the one or more computers, the object occlusion map into a binary occlusion map, the binary occlusion map representing if an object of any type is occluding an object of the first type, wherein converting the object occlusion map into the binary occlusion map comprises:

comparing a positional occlusion likelihood score of the object occlusion map, representing a likelihood that a particular position is occluded, against a second predetermined threshold;

upon determining that the positional occlusion likelihood score exceeds the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is occluded; and

upon determining that the positional occlusion likelihood score does not exceed the second predetermined threshold, marking the position in the binary occlusion map as a value that represents the position is not occluded;

determining, by the one or more computers and based on the first output data and the second output data, a score that indicates a likelihood that the first image depicts an object of the first type that is at least partially occluded; and

based on a determination that the determined score satisfies a first predetermined threshold, generating, by the one or more computers, third output data that includes an instruction indicating that an object of the first type that is at least partially occluded has been detected.

18 . The computer-readable medium of claim 17 ,

wherein the first machine learning model is a generative compositional model;

wherein the generative compositional model processes the first feature set to generate a second feature set as an output of the generative model;

wherein the second machine learning model is an object occlusion model; and

wherein the object occlusion model comprises a model, trained by a plurality of input images with known occlusion, that is configured to generate occlusion output data, the occlusion output data indicating a measure of the likelihood that an object of any type is present, the object of any type being different from the object of the first type.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 23, 2026
From: YUILLE, ALAN; KORTYLEWSKI, ADAM
To: THE JOHNS HOPKINS UNIVERSITY
Reel/Frame 073861/0313 →
Continuity (2)
Provisional Application 63210350 · Jun 14, 2021
Related Publication 20240290075A1 · Aug 29, 2024
References Cited (266)
US 9739783B1 · Kumar et al. · 2017 [cited by applicant]
US 9811906B1 · Vizitiu et al. · 2017 [cited by applicant]
US 9947102B2 · Xu et al. · 2018 [cited by applicant]
US 9965863B2 · Xu et al. · 2018 [cited by applicant]
US 10140544B1 · Zhao et al. · 2018 [cited by applicant]
US 11049250B2 · Nye et al. · 2021 [cited by applicant]
US 11308623B2 · Yuille et al. · 2022 [cited by applicant]
US 12125211B2 · Yuille et al. · 2024 [cited by applicant]
US 12141694B2 · Park et al. · 2024 [cited by applicant]
US 20100067754A1 · Collins et al. · 2010 [cited by applicant]
US 20120230572A1 · Kohlberger · 2012 [cited by applicant]
US 20150003703A1 · Franz et al. · 2015 [cited by applicant]
US 20160098833A1 · Tsadok et al. · 2016 [cited by applicant]
US 20170249744A1 · Wang et al. · 2017 [cited by applicant]
US 20170316578A1 · Fua · 2017 [cited by examiner]
US 20170372505A1 · Bhat · 2017 [cited by examiner]
US 20180042565A1 · Wilson et al. · 2018 [cited by applicant]
US 20180108124A1 · Guo et al. · 2018 [cited by applicant]
US 20180165548A1 · Wang · 2018 [cited by examiner]
US 20180268202A1 · Yu · 2018 [cited by examiner]
US 20190080149A1 · Gernoth · 2019 [cited by examiner]
US 20190105009A1 · Siemionow et al. · 2019 [cited by applicant]
US 20190220975A1 · Hsieh et al. · 2019 [cited by applicant]
US 20190258878A1 · Koivisto et al. · 2019 [cited by applicant]
US 20200005899A1 · Nicula et al. · 2020 [cited by applicant]
US 20200202507A1 · Ceccaldi et al. · 2020 [cited by applicant]
US 20200245960A1 · Richter et al. · 2020 [cited by applicant]
US 20200278681A1 · Gier et al. · 2020 [cited by applicant]
US 20200342600A1 · Sjostrand et al. · 2020 [cited by applicant]
US 20200356899A1 · Rejeb Sfar et al. · 2020 [cited by applicant]
US 20200372626A1 · Dal Mutto · 2020 [cited by examiner]
US 20210012505A1 · Yuille et al. · 2021 [cited by applicant]
US 20220215646A1 · Park et al. · 2022 [cited by applicant]
US 20220277459A1 · Yuille et al. · 2022 [cited by applicant]
US 20220392641A1 · Yuille et al. · 2022 [cited by applicant]
CN 109685809 · 2019 [cited by applicant]
EP 3252671 · 2016 [cited by applicant]
EP 3392832 · 2018 [cited by applicant]
WO WO2016182551 · 2016 [cited by applicant]
WO WO2017210690 · 2017 [cited by applicant]
WO WO2018015080 · 2018 [cited by applicant]
WO WO2018015414 · 2018 [cited by applicant]
WO WO2019005722 · 2019 [cited by applicant]
Abraham et al., “Extracting Brain Regions from Rest fMRI with Total-Variation Constrained Dictionary Learning,”MICCAI., 2013, 16:2:607-15. [cited by applicant]
Ansari et al. “Role of Magnetic Resonance Imaging in the Detection and Characterization of Solid Pancreatic Nodules: An Update,” World Journal of Radiology, 28, 7(11), Nov. 2015, 361-374. [cited by applicant]
Arthur et al., “k-means++: The advantages of careful seeding,” Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, Jan. 2007, 1027-1035. [cited by applicant]
Asman et al., “Formulating spatially varying performance in the statistical fusion framework,” IEEE Trans. on Med, Imaging, 2012, 31:6:1326-1336. [cited by applicant]
Asman et al., “Non-local statistical label fusion for multi-atlas segmentation,” Med. Image Anal., Feb. 2013, 17:2:194-208. [cited by applicant]
Aydogan et al., “Analysis of Trabecular Bone Microstructure Using Contour Tree Connectivity,” MICCAI., 2013, 16:2:428-35. [cited by applicant]
Banerjee et al., “Clustering on the unit hypersphere using von mises-fisher distributions,” Journal of Machine Learning Research, Sep. 2005, 6:1345-1382. [cited by applicant]
Bienenstock et al., “Compositionality, MDL Priors, and Object Recognition,” Proceedings of the 9th International Conference on Neural Information Processing Systems, Dec. 1996, 838-844. [cited by applicant]
Bieth et al., “Atlas Construction for Dynamic (4D) Pet Using Diffeomorphic Transformations,” MICCAI, 2013, 35-42. [cited by applicant]
Boykov et al, “Fast approximate energy minimization via graph cuts,” IEEE Transactions on PAMI, 2001, 23:11:122-1239. [cited by applicant]
Brosch et al., “Manifold Learning of Brain MRIs by Deep Learning,” MICCAI., 2013, 16:2:633-40. [cited by applicant]
Cai et al., “Cascade R-CNN: Delving into High Quality Object Detection,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018, 6154-6162. [cited by applicant]
Carlson et al., “A Sparse Object Coding Scheme in Area V4,” Current Biology, Feb. 22, 2011, 21(4):288-293. [cited by applicant]
Cerrolaza et al., “Multiresolution Hierarchical Shape Models in 3D Subcortical Brain Structures,” MICCAI., 2013, 16:2:641-8. [cited by applicant]
Chang et al., “Characterization of Tissue Histopathology via Predictive Sparse Decomposition and Spatial Pyramid Matching,” MICCAI, 2013, 8150:91-98. [cited by applicant]
Chatelain et al., “Learning from Multiple Experts with Random Forests: Application to the Segmentation of the Midbrain in 3D Ultrasound,” MICCAI, 2013, 16:2:230-7. [cited by applicant]
Chen et al., “Attention to scale: Scale-aware semantic image segmentation,” In proceedings of the IEEE conf. on CCVPR, 2016, 3640-3649. [cited by applicant]
Chen et al., “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 40(4): 834-848. [cited by applicant]
Chen et al., “VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images,” NeuroImage, 2018, 170:446-455. [cited by applicant]
Chu et al., “Multi-organ segmentation based on spatially-divided probabilistic atlas from 3D abdominal CT images,” Lecture Notes in Comp. Sci., 2013, 8150LNCS(part 2) 165-172. [cited by applicant]
Ciompi et al., “Stent Shape Estimation through a Comprehensive Interpretation of Intravascular Ultrasound Images,” MICCAI, 2013, 16:2:345-52. [cited by applicant]
Ciresan et al., “Mitosis Detection in Breast Cancer Histology Images with Deep Neural Networks,” MICCAI., 2013, 16:2:411-8. [cited by applicant]
Cisek et al., “3D U-Net: Learning dense volumetric segmentation from sparse annotation,” MICCAI, 2016, 424-432. [cited by applicant]
Cruz-Roa et al., “A Deep Learning Architecture for Image Representation, Visual Interpretability and Automated Basal-Cell Carcinoma Cancer Detection,” MICCAI., 2013, 16:2:403-10. [cited by applicant]
Da Mota et al., “Enhancing the Reproducibility of Group Analysis with Randomized Brain Parcellations,” MICCAI., 2013, 16:2:591-8. [cited by applicant]
Dai et al., “Unsupervised learning of dictionaries of hierarchical compositional models,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2014, 2505-2512. [cited by applicant]
Datar et al., “Geodesic Distances to Landmarks for Dense Correspondence on Ensembles of Complex Shapes,” MICCAI., 2013, 16:19-26. [cited by applicant]
De Silva et al., “Improving 2D-3D Registration Optimization Using Learned Prostate Motion Data,” MICCAI, 2013, 16:2:124-31. [cited by applicant]
Deng et al., “ImageNet: A Large-Scale Hierarchical Image Database,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2009, 248-255. [cited by applicant]
DeVries et al., “Improved regularization of convolutional neural networks with cutout,” CoRR, submitted on Nov. 29, 2017, arXiv:1708.04552v2, 8 pages. [cited by applicant]
Dinse et al., “A Histology-Based Model of Quantitative TI Contrast for In-vivo Cortical Parcellation of High-Resolution 7 Tesla Brain MR Images,” MICCAI, 2013, 16(Pt 2):51-58. [cited by applicant]
Dou et al., “3D deeply supervised network for automatic liver segmentation from CT volumes,” Med. Image Analysis, Oct. 2017, 41:40-54. [cited by applicant]
Dou et al., “Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection”, IEEE Tbe, 2017, 64(7): 1558-1567. [cited by applicant]
Durichen et al., “Respiratory Motion Compensation with Relevance Vector Machines,” MICCAI., 2013, 108-115. [cited by applicant]
Everingham et al., The PASCAL visual object classes challenge 2012 (VOC2012) results. 2012, Pascal2, 24 pages. [cited by applicant]
Extended Search Report in European Appln. No. 20794854.8, dated Apr. 19, 2023, 5 pages. [cited by applicant]
Farag et al., “Automatic pancreas segmentation using coarse to-fine superpixel labeling,” Deep learning and Convolutional Neural Networks for Medical Computing, 2017, 24 pages. [cited by applicant]
Fawzi et al., “Measuring the effect of nuisance variables on classifiers,” Proceedings of the British Machine Vision Conference (BMVC), Sep. 2016, 12 pages. [cited by applicant]
Fidler et al., “Learning a hierarchical compositional shape vocabulary for multiclass object representation,” CoRR, submitted on Aug. 23, 2014, arXiv:1408.5516v1, 17 pages. [cited by applicant]
Fodor et al., “Connectionism and cognitive architecture: A critical analysis,” Cognition, Mar. 1988, 28(1-2):3-71. [cited by applicant]
Forman et al., “Free-Breathing Whole-Heart Coronary MRA: Motion Compensation Integrated into 3D Cartesian Compressed Sensing Reconstruction,” MICCAI., 2013, 16:2:575-82. [cited by applicant]
Gao et al., “Incremental Learning with Selective Memory (ILSM): Towards Fast Prostate Localization for Image Guided Radiotherapy,” MICCAI., 2013, 16:2:378-386. [cited by applicant]
George et al., “A generative vision model that trains with high data efficiency and breaks text-based captchas,” Science, Oct. 26, 2017, 358(6368):eaag2612, 19 pages. [cited by applicant]
Gibson et al., “Automatic multi-organ segmentation on abdominal CT with dense V-networks,” IEEE Trans. Med. Imaging, Aug. 2018, 37:8:1822-1834. [cited by applicant]
Ginsburg et al., “Variable Importance in Nonlinear Kernels (VINK): Classification of Digitized Histopathology,” MICCAI., 2013, 16:2:238-45. [cited by applicant]
Girshick et al., “Rich feature hierarchies for accurate object detection and semantic segmentation,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2014, 580-587. [cited by applicant]
Girshick, “Fast R-CNN,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), Dec. 2015, 1440-1448. [cited by applicant]
Glocker et al., “Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations,” MICCAI., 2013, 16:2:262-70. [cited by applicant]
Gomez et al., “3D Intraventricular Flow Mapping from Colour Doppler Images and Wall Motion,” MICCAI,2013, 16:2:476-83. [cited by applicant]
Grbic et al., “Image-Based Computational Models for TAVI Planning: From CT Images to Implant Deployment,” MICCAI., 2013, 16:2:395-402. [cited by applicant]
Hacihaliloglu et al., “Statistical Shape Model to 3D Ultrasound Registration for Spine Interventions Using Enhanced Local Phase Features,” MICCAI., 2013, 16:2:361-8. [cited by applicant]
Hamy et al., “Respiratory Motion Correction in Dynamic-MRI: Application to Small Bowel Motility Quantification during Free Breathing,” MICCAI, 2013, 16:2:132-40. [cited by applicant]
Havaei et al.,“ Brain tumor segmentation with deep neural networks,” Medical Image analysis, Jan. 2017, 35:18-31. [cited by applicant]
He et al., “Deep Residual Learning for Image Recognition”, 2016, CVPR, 770-778. [cited by applicant]
Heimann et al., “Comparison and evaluation of methods for live segmentation from CT datasets,” IEEE Transactions on Medical Imaging, Aug. 2009, 28:8:1251-1265. [cited by applicant]
Hibar er al., “Genetic Clustering on the Hippocampal Surface for Genome-Wide Association Studies,” MICCAI., 2013, 16:2:690-7. [cited by applicant]
Hu et al. “Brain Tumor Segmentation Using Multi-Cascaded Convolutional Neural Networks and Conditional Random Field,” IEEE Access, Jul. 8, 2019, 7:92615- 92629. [cited by applicant]
Hu et al., “Automated Separation of Binary Overlapping Trees in Low-Contrast Color Retinal Images,” MICCAI., 2013, 16:2:436-43. [cited by applicant]
Huang et al., “A New Sparse Simplex Model for Brain Anatomical and Genetic Network Analysis,” MICCAI., 2013, 16:2:625-632. [cited by applicant]
Huh et al, “Apoptosis Detection for Non-adherent Cells in Time-lapse Phase Contrast Microscopy,” MICCAI, 2013, 8150: 59-66. [cited by applicant]
Hussein et al., “Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches”, IEEE Transactions on Medical Imaging, 2019, 38(8): 1777-1787. [cited by applicant]
Hussein et al., “Supervised and unsupervised tumor characterization in the deep learning era,” ArXiv, 2018, 11 pages. [cited by applicant]
Iglesias et al., Multi-atlas segmentation of biomedical images: A survey, Med Image Anal., Aug. 2015, 24:1:205-219. [cited by applicant]
Imani et al., “Ultrasound-Based Characterization of Prostate Cancer: An in vivo Clinical Feasibility Study,” MICAAI, 2013, 16:2:279-86. [cited by applicant]
International Preliminary Report on Patentability in Appl. No. PCT/US2020/029631, dated Sep. 28, 2021, 6 pages. [cited by applicant]
International Preliminary Report on Patentability in International Application No. PCT/US2020/060061, mailed on May 27, 2022, 9 pages. [cited by applicant]
International Preliminary Report on Patentability in International Appln. No. PCT/US2022/033438, mailed on Dec. 28, 2023, 9 pages. [cited by applicant]
International Search Report and Written Opinion in International Application No. PCT/US2020/060061, mailed on Mar. 1, 2021, 14 pages. [cited by applicant]
International Search Report and Written Opinion in International Appln. No. PCT/US2022/033438, mailed on Oct. 20, 2022, 10 pages. [cited by applicant]
International Search Report in Appl. No. PCT/US2020/029631, dated Jul. 30, 2020, 6 pages. [cited by applicant]
Jiang et al., “Predictive Models of Resting State Networks for Assessment of Altered Functional Connectivity in MCI,” MICCAI, 2013, 16:2:674-81. [cited by applicant]
Jimenez del Toro et al., “Epileptogenic Lesion Quantification in MRI Using Contralateral 3D Texture Comparisons,” MICCAI., 2013, 16:2:353-60. [cited by applicant]
Jin et al., “Context and hierarchy in a probabilistic image model,” Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06), Jun. 2006, 2145-2152. [cited by applicant]
Kamnitsas et al., “Effcient multi-scale 3D Cnn with fully connected CRF for accurate brain lesion segmentation,” Med. Image Analysis, Feb. 2017, 36:61-78. [cited by applicant]
Karasawa e al., “Multi-atlas pancreas segmentation: Atlas selection based on vessel structure,” Med. Image Analysis, 2017, 39:18-28. [cited by applicant]
Kingma et al., “Adam: A method for stochastic optimization,” CoRR, submitted on Dec. 22, 2014, arXiv:1412,6980v1, 9 pages. [cited by applicant]
Kirbas et al., “A review of vessel extraction techniques and algorithms,” ACM Computing Surveys, 2004, 36:2:81-121. [cited by applicant]
Koenig et al., “The Spatial Periodicity of Grid Cells Is Not Sustained During Reduced Theta Oscillations,” Science, 2011, 332:592-595. [cited by applicant]
Kong et al., “RON: Reverse connection with objectness prior networks for object detection,” IEEE Conference on Computer Vision Pattern Recognition, Jul. 2017, 5936-5944. [cited by applicant]
Kortylewski et al., “Compositional Convolutional Networks for Robust Object Classification under Occlusion,” CoRR, submitted on May 29, 2019, arXiv:1905.11826v2, 12 pages. [cited by applicant]
Kortylewski et al., “Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion,” arXiv:2003.04490v3, Apr. 2020, 10 pages. [cited by applicant]
Kortylewski et al., “Greedy structure learning of hierarchical compositional models,” CoRR, submitted on Jan. 22, 2017, arXiv:1701.06171v1, 16 pages. [cited by applicant]
Kortylewski et al., “Probabilistic compositional active basis models for robust pattern recognition,” Proceedings of the British Machine Vision Conference (BMVC), Sep. 2016, 12 pages. [cited by applicant]
Kortylewski, “Model-based image analysis for forensic shoe print recognition,” Dissertation for the Degree of Doctor of Philosophy, University of Basel, Jun. 2017, 124 pages. [cited by applicant]
Krizkevsky et al., “ImageNet Classification with Deep Convolutional Neural Networks”, NIPS, 9 pages, 2012. [cited by applicant]
Kroeger et al., “Learning to Segment Neurons with Non-local Quality Measures,” MICCAI., 2013, 16:2:419-27. [cited by applicant]
Kronman et al., “Image Segmentation Errors Correction by Mesh Segmentation and Deformation,” MICCAI., 2013, 206-213. [cited by applicant]
Kwitt et al., “Studying Cerebral Vasculature Using Structure Proximity and Graph Kernels,” MICCAI., 2013, 16:2:534-541. [cited by applicant]
Lampert et al., “Beyond sliding windows: Object localization by efficient subwindow search,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2008, 8 pages. [cited by applicant]
Lesage et al., “A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes,” SciDirect., 2009, 13:819-845. [cited by applicant]
Li et al., “Automatic liver segmentation based shape constraints and deformable graph cut in CT images,” IEEE tans. on Image Proc., Dec. 2015, 24(12):5315-5329. [cited by applicant]
Li et al., “AOGNets: Compositional Grammatical Architectures for Deep Learning,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019, 6220-6230. [cited by applicant]
Li et al., “SymmNet: A Symmetric Convolutional Neural Network for Occlusion Detection,” Proceedings of the British Machine Vision Conference (BMVC), Sep. 2018, 14 pages. [cited by applicant]
Liao et al., “Learning deep parsimonious representations,” Advances in Neural Information Processing Systems, Dec. 2016, 29:5076-5084. [cited by applicant]
Liao et al., “Representation Learning: A Unified Deep Learning Framework for. Automatic Prostate MR Segmentation,” MICCAI., 2013, 16:2:254-61. [cited by applicant]
Lin et al., “Microsoft COCO: Common Objects in Context,” Computer Vision—ECCV 2014 (LNCS), Sep. 2014, 8693:740-755. [cited by applicant]
Lindner et al., “Accurate Bone Segmentation in 2D Radiographs Using Fully Automatic Shape Model Matching Based on Regression-Voting,” MICCAI., 2013, 181-189. [cited by applicant]
Liu et al., “A Variational Framework for Joint Detection and Segmentation of Ovarian Cancer Metastases,” MICCAI., 2013, 8150:83-90. [cited by applicant]
Liu et al., “Automatic pancreas segmentation via coarse location and ensemble learning,” IEEE Access, 2019, 9 pages. [cited by applicant]
Liu et al., “High-Order Graph Matching Based Feature Selection for Alzheimer's Disease Identification,” MICCAI, 2013, 16:2:311-318. [cited by applicant]
Liu et al., “Joint shape representation and classification for detecting PDAC,” MLMI@MICCAI, 2019, 8 pages. [cited by applicant]
Liu et al., “Longitudinal Modeling of Glaucoma Progression Using 2-Dimensional Continuous-Time Hidden Markov Model,” MICCAI., 2013, 16:2:444-451. [cited by applicant]
Liu et al., “Multifold Bayesian Kernelization in Alzheimer's Diagnosis,” MICCAI., 2013, 16:2:303-10. [cited by applicant]
Liu et al., “Tracking of Carotid Arteries in Ultrasound Images,” MICCAI., 2013, 16:2:526-33. [cited by applicant]
Lombaert et al., “Joint Statistics on Cardiac Shape and Fiber Architecture,” MICCAI., 2013, 16:2:492-500. [cited by applicant]
Long et al., “Fully Convolutional Networks for Semantic Segmentation,” CVPR, 2015, 3431-3440. [cited by applicant]
Lorenzi et al., “Sparse Scale-Space Decomposition of Volume Changes in Deformations Fields,” MICCAI., 2013, 16:2:328-35. [cited by applicant]
Lorza et al., “Carotid Artery Lumen Segmentation in 3D Free-Hand Ultrasound Images Using Surface Graph Cuts,” MICCAI., 2013, 16:2: 542-9. [cited by applicant]
Lugo-Fagundo et al., “Deep learning in radiology: Now the real work begins,” J. Am, Coll. Radiol., Feb. 2018, 15:2:364-367. [cited by applicant]
Lundervold et al., “An overview of deep learning in medical imaging focusing on MRI,” Zeitschrift für Medizinische Physik, May 2019, 29:2:102-127. [cited by applicant]
Lv et al., “Group-Wise FMRI Activation Detection on Corresponding Cortical Landmarks,” MICCAI., 2013, 16:2:665-73. [cited by applicant]
Lv et al., “Modeling Dynamic Functional Information Flows on Large-Scale Brain Networks,” MICCAI., 2013, 698-705. [cited by applicant]
Mahapatra et al., “Semi-Supervised and Active Learning for Automatic Segmentation of Crohn's Disease,” MICCAI., 2013, 16:2:214-21. [cited by applicant]
Mahrooghy et al., “Heterogeneity Wavelet Kinetics from DCE-MRI for Classifying Gene Expression Based Breast Cancer Recurrence Risk,” MICCA., 2013, 16:2:295-302. [cited by applicant]
Maier et al, “A gentle introduction to deep learning in medical imaging processing,” J. of Med. Physics, Dec. 2018, 31 pages. [cited by applicant]
Marreiros et al., “Non-rigid Deformation Pipeline for Compensation of Superficial Brain Shift,” MICCAI., 2013, 16:2:141-8. [cited by applicant]
McLeod et al., “Spatio-temporal Dimension Reduction of Cardiac Motion for Group-Wise Analysis and Statistical Testing,” MICCAI., 2013, 16:2:501-8. [cited by applicant]
Melbourne et al., “Measurement of Myelin in the Preterm Brain: Multi-compartment Diffusion Imaging and Multi-component T2 Relaxometry,” MICCAI,, 2013, 16:2:336-44. [cited by applicant]
Mharib et al., “Survey on liver CT image segmentation methods,” Artif Intell Rev., 2012, 37:83-95. [cited by applicant]
Milletari et al., “V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation”, 2016 Fourth International Conference on 3D Vision,2016, 565-571. [cited by applicant]
Mori et al., Medical Image computing and computer-assisted intervention—MICCAI 2013, 16th Int. Conf., Sep. 2013, 36 pages. [cited by applicant]
Nascimento et al., Multi-atlas segmentation using manifold learning with deep belief neworks, IEE, 2016, 4 pages. [cited by applicant]
NCBI.gov [online], “Pancreatic cancer treatment (adult) (PDQ),” May 15, 2020, retrieved on Oct. 5, 2020, retrieved from URL<https://www.ncbi.nlm.nih.gov/books/NBK65957/?report-printable. 37 pages. [cited by applicant]
Nouranian et al., “An Automatic Multi-atlas Segmentation of the Prostate in Transrectal Ultrasound Images Using Pairwise Atlas Shape Similarity,” MICCAI, 2013, 16:2:173-80. [cited by applicant]
Okada et al., “Abdominal multi-organ segmentation from CT images using conditional shape-location and unsupervised intensity priors,” Med. Image Anal., Dec. 2015, 26:1:1-18. [cited by applicant]
Oktay et al., “Biomechanically driven registration of pre- to intra-operative 3D images for laparoscopic surgery,” MICCAI., 2013, 16:2:1-9. [cited by applicant]
Ospina et al., “A Tensor-Based Population Value Decomposition to Explain Rectal Toxicity after Prostate Cancer Radiotherapy,” MICCAI., 2013, 16:2:387-94. [cited by applicant]
Petersen et al., “Quantitative Airway Analysis in Longitudinal Studies Using Groupwise Registration and 4D Optimal Surfaces,” MICCAI., 2013, 16:2:287-94. [cited by applicant]
Piuze et al., “Cardiac Fiber Inpainting Using Cartan Forms,” MICCAI, 2013, 16:2:509-17. [cited by applicant]
Porras et al., “Myocardial Motion Estimation Combining Tissue Doppler and B-mode Echocardiographic Images,” MICCAI., 2013, 16:2:484-91. [cited by applicant]
Prasoon et al., “Deep Feature Learning for Knee Cartilage Segmentation Using a Triplanar Convolutional Neural Network,” MICCAI., 2013, 16:2:246-53. [cited by applicant]
Prevost et al., “Registration of Free-Breathing 3D+t Abdominal Perfusion CT Images via Co-segmentation,” MICCAI., 2013, 16:2:99-107. [cited by applicant]
Qiu et al., “Fast Globally Optimal Segmentation of 3D Prostate MRI with Axial Symmetry Prior,” MICCAI., 2013, 16:2:198-205. [cited by applicant]
Rafii-Tari et al., “Learning-Based Modeling of Endovascular Navigation for Collaborative Robotic Catheterization,” MICCAI., 2013, 16:2:369-77. [cited by applicant]
Rajchl et al., “Deepcut: Object segmentation from bounding box annotations using convulutional neural networks,” IEE Trans. Med. Imaging., 2016, 10 pages. [cited by applicant]
Reddy et al., “Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2019, 7326-7335. [cited by applicant]
Ren et al., “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” Advances in Neural Information Processing Systems, Dec. 2015, vol. 28, 9 pages. [cited by applicant]
Roe et al., “Toward a Unified Theory of Visual Area V4,” Neuron, Apr. 12, 2012, 74(1):12-29. [cited by applicant]
Romain et al., “A Multi-task Learning Approach for Compartmental Model Parameter Estimation in DCE-CT Sequences, ”MICAA., 2013, 16:2:271-8. [cited by applicant]
Ronneberger et al., “U-Net: Convolutional Networks for Biomedical Image Segmentation”, MICCAR, 234-241, 2015. [cited by applicant]
Roth et al., “Deep convolutional networks for pancreas segmentation in CT imaging,” SPIE Med., Imaging, 2015, 9413-94131G. [cited by applicant]
Roth et al., “DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation”, MICCAI, 556-564, 2015. [cited by applicant]
Roth et al., “Hierarchical 3D fully convolutional networks for multi-organ segmentation,” ARXIV., Apr. 2017, arXiv:1704.06382, 11 pages. [cited by applicant]
Roth et al., Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation, Medical Image Analysis, Apr. 2018, 45:94-107. [cited by applicant]
Roth et al., “Spatial Aggregation of Holistically-Nested Networks for Automated Pancreas Segmentation”, 2016, MICCAI, 451-459. [cited by applicant]
Roth et al., “Towards dense volumetric pancreas segmentation in CT using 3D fully conventional networks,” Medical Imaging, 2018, 6 pages. [cited by applicant]
Sabuncu et al., “A generative model for image segmentation based on label fusion,” IEE Trans. on Med. Imaging, Oct. 2010, 29:10:1714-1729. [cited by applicant]
Saito et al., “Joint optimization of segmentation and shape prior from level-set-based statistical shape model, and its application to the automated segmentation of abdominal organs,” Med. Image Analysis, 2016, 28:46-65. [cited by applicant]
Sasikumar et al., “First-pass processing of value cues in the ventral visual pathway,” Current Biology, Feb. 8, 2018, 28(4):538-548. [cited by applicant]
Seito et al., “Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks,” IEE Trans. on Med. Imag., May 2016, 35:5:1160-1169. [cited by applicant]
Shen et al., “A Spatial Mixture Approach to Inferring Sub-ROI Spatio-temporal Patterns from Rapid Event-Related fMRI Data,” MICCAI., 2013, 16:2:657-64. [cited by applicant]
Shen et al., Deep learning in medical image analysis, Annu rev.Biomed. En., 2017, 19:221-248. [cited by applicant]
Simonyan et al., “Very deep convolutional networks for large-scale image recognition,” CoRR, submitted on Dec. 23, 2014, arXiv:1409.1556v5, 13 pages. [cited by applicant]
Simpson et al., “A bayesian approach for spatially adaptive regularisation in Non-rigid registration,” MICCAI., 2013, 10-18. [cited by applicant]
Song et al., “Discriminative Data Transform for Image Feature Extraction and Classification,” MICCAI., 2013, 16:2:452-9. [cited by applicant]
Stone et al., “Teaching Compositionality to CNNs,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, 5058-5067. [cited by applicant]
Suk et al., “Deep Learning-Based Feature Representation for AD/MCI Classification,” MICCAI., 2013, 16:2:583-90. [cited by applicant]
Sun et al., “Symmetric stereo matching for occlusion handling,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2005, 399-406. [cited by applicant]
Tabernik et al., “Towards deep compositional networks,” Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), Dec. 2016, 3470-3475. [cited by applicant]
Tang et al., “Deeply Learned Compositional Models for Human Pose Estimation,” Computer Vision—ECCV 2018 (LNCS), Sep. 2018, 11207:190-206. [cited by applicant]
Tang et al., “Random Walks with Efficient Search and Contextually Adapted Image Similarity for Deformable Registration,” MICCAI, 2013, 43-50. [cited by applicant]
Tang et al., “Towards a unified compositional model for visual pattern modeling,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), Oct. 2017, 2784-2793. [cited by applicant]
The Handbook of Brain Theory and Neural Networks, 2nd ed., Arbib (ed.), 2003, pp. 244-248. [cited by applicant]
Tong et al., “Multiple Instance Learning for Classification of Dementia in Brain MRI,” Med. Image Anal., Jul. 2014, 18:5:808-18. [cited by applicant]
Uzunbas et al., “Collaborative Multi Organ Segmentation by Integrating Deformable and Graphical Models,” MICCAI, 2013, 157-164. [cited by applicant]
Vaziri et al., “A channel for 3d environmental shape in anterior inferotemporal cortex,” Neuron, Oct. 2014, 84(1):55-62. [cited by applicant]
Vincent et al., “Bayesian Joint Detection-Estimation of Cerebral Vasoreactivity from ASL fMRI Data,” MICCAI, 2013, 616-624. [cited by applicant]
Wang et al., “Abdominal Multi-organ Segmentation with Organ-Attention Networks and Statistical Fusion,” CoRR, submitted on Apr. 23, 2018, arXiv:1804.08414v1, 21 pages. [cited by applicant]
Wang et al., “Abdominal multi-organ segmentation with organ-attention networks and statistical fusion,” Medical Image Analysis, 2019, 55:88-102. [cited by applicant]
Wang et al., “Automated Embryo Stage Classification in Time-Lapse Microscopy Video of Early Human Embryo Development,” MICCAI., 2013, 16:2:460-7. [cited by applicant]
Wang et al., “Detecting semantic parts on partially occluded objects,” Proceedings of the British Machine Vision Conference (BMVC), Sep. 2017, 13 pages. [cited by applicant]
Wang et al., “Discovering Internal Representations from Object-CNNs Using Population Encoding,” CoRR, submitted on Nov. 21, 2015, arXiv:1511.06855v1, 12 pages. [cited by applicant]
Wang et al., “Image quality assessment: Form error visibility to structural similarity,” IEE. Trans. on Image. Proces., Apr. 2004, 13:4:600-612. [cited by applicant]
Wang et al., “Image Quality Assessment: From Error Visibility to Structural Similarity,” IEEE Transactions on Image Processing, Apr. 2004, 13:4:600-612. [cited by applicant]
Wang et al., “Interactive Retinal Vessel Extraction by Integrating Vessel Tracing and Graph Search,” MICCAI., 2013, 16:2:567-74. [cited by applicant]
Wang et al., “Robust Object Detection under Occlusion with Context-Aware CompositionalNets,” 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2020, pp. 12642-12651. [cited by applicant]
Wang et al., “Sequential Monte Carlo Tracking for Marginal Artery Segmentation on CT Angiography by Multiple Cue Fusion,” MICCAI., 2013, 16:2:518-525. [cited by applicant]
Wang et al., “Visual concepts and compositional voting,” CoRR, submitted on Nov. 13, 2017, arXiv:1711.04451v1, 37 pages. [cited by applicant]
Wang et al., English translation of CN 109685809 A, published on Apr. 26, 2019, 14 pages. [cited by applicant]
Warfield et al., “Simultaneous truth and performance level estimation (STAPLE): An algorithm for the validation of image segmentation,” IEE Trans. Med. Imaging., Jul. 2004, 23:7:903-921. [cited by applicant]
Wasza et al., “Real-Time Respiratory Motion Analysis Using Manifold Ray Casting of Volumetrically Fused Multi-view Range Imaging,” MICCAI., 2013, 16:2:116-23. [cited by applicant]
Wee et al., “Identification of MCI Using Optimal Sparse MAR Modeled Effective Connectivity Networks,” MICCAI., 2013, 16:2:319-327. [cited by applicant]
Wolz et al., “Automated abdominal multi-organ segmentation with subject-specific atlas generation,” IEE Trans. on Med. Imaging, Sep. 2013, 32:9:1723-1730. [cited by applicant]
Wu et al., “Unsupervised Deep Feature Learning for Deformable Registration of MR Brain Images,” MICCAI., 2013, 16:2:649-56. [cited by applicant]
Xia et al., “Bridging the Gap Between 2D and 3D Organ Segmentation with Volumetric Fusion Net”, MICCAI, 445-453, 2018. [cited by applicant]
Xiang et al., “Beyond PASCAL: A benchmark for 3D object detection in the wild,” IEEE Winter Conference on Applications of Computer Vision, Mar. 2014, 75-82. [cited by applicant]
Xiang et al., “Object Detection by 3D Aspectlets and Occlusion Reasoning,” IEEE International Conference on Computer Vision Workshops, Dec. 2013, 530-537. [cited by applicant]
Xiao et al., “Tdapnet: Prototype network with recurrent top-down attention for robust object classification under partial occlusion,” CoRR, submitted on Sep. 9, 2019, arXiv:1909.03879v1, 11 pages. [cited by applicant]
Xie et al., “Holistically-Nested Edge Detection”, Proceedings of the IEEE International Conference on Computer Vision, 2015, 1395-1403. [cited by applicant]
Xu et al., “A Symmetric 4D Registration Algorithm for Respiratory Motion Modeling,” MICCAI., 2013, 16:2:149-56. [cited by applicant]
Xu et al., “Automatic Grading of Nuclear Cataracts from Slit-Lamp Lens Images Using Group Sparsity Regression,” MICCAI., 2013, 16:2:468-75. [cited by applicant]
Xu et al., “Spatially Constrained Random Walk Approach for Accurate Estimation of Airway Wall Surfaces,” MICCAI., 2013, 16:2:559-566. [cited by applicant]
Yamane et al., “A neural code for three-dimensional object shape in macaque inferotemporal cortex,” Nature Neuroscience, Oct. 5, 2008, 11(11):1352-1360. [cited by applicant]
Yan et al., “Inferring occluded features for fast object detection,” Signal Processing, May 2015, 110:188-198. [cited by applicant]
Ye et al., “Pathological Site Retargeting under Tissue Deformation Using Geometrical Association and Tracking,” MICCAI., 2013, 16:2:67-74. [cited by applicant]
Yokota et al., “Automated CT Segmentation of Diseased Hip Using Hierarchical and Conditional Statistical Shape Models,” MICCAI, 2013 190-197. [cited by applicant]
Yoldemir et al., “Overlapping Replicator Dynamics for Functional Subnetwork Identification,” MICCAI., 2013, 16:2:682-9. [cited by applicant]
Yu et al., “Recurrent saliency transformation network: incorporating multi-stage visual cues for small organ segmentation,” Arxiv, 2017, 10 pages. [cited by applicant]
Yuille et al., “Abdominal multi-organ segmentation with organ-attention networks and statistical fusion,” Med., Image Anal., Jul. 2019, 55:88-102. [cited by applicant]
Yun et al., “CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features,” CoRR, submitted on May 13, 2019, arXiv:1905.04899v1, 14 pages. [cited by applicant]
Zhang et al., “Deepvoting: A robust and explainable deep network for semantic part detection under partial occlusion,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018,… [cited by applicant]
Zhang et al., “Interpretable convolutional neural networks,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018, 8827-8836. [cited by applicant]
Zhang et al., “Large Deformation Diffeomorphic Registration of Diffusion-Weighted Images with Explicit Orientation Optimization,” MICCAI, 2013, 16(Pt 2):27-34. [cited by applicant]
Zhang et al., “Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd,” CoRR, submitted on Jul. 23, 2018, arXiv:1807.08407v1, 17 pages. [cited by applicant]
Zhang et al., “Personalized Pancreatic Tumor Growth Prediction via Group Learning”, MICCAI, 2017, 424-432. [cited by applicant]
Zhao et al., “Hierarchical Constrained Local Model Using ICA and Its Application to Down Syndrome Detection,” MICCAI., 2013, 16:2:222-9. [cited by applicant]
Zheng et al., “Optic disc and cup segmentation from color fundus photograph using graph cut with priors,” MICCAI., 2013, 16:75-82. [cited by applicant]
Zhou et al., “A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans”, MICCAI,2017, 693-701. [cited by applicant]
Zhou et al., “Deep Supervision for Pancreatic Cyst Segmentation in Abdominal CT Scans”, MICCAI, 2017, 222-230. [cited by applicant]
Zhou et al., “Pancreas Segmentation in Abdominal CT Scan: A Coarse-to-Fine Approach.” arXiv:1612.08230v1, Dec. 2016, pp. 1-13. [cited by applicant]
Zhu et al., “A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation”, International Conference on 3D Vision, 682-690, 2018. [cited by applicant]
Zhu et al., “Deep Learning Representation using Autoencoder for 3D Shape Retrieval”, Neurocomputing 204: 41-50, 2016. [cited by applicant]
Zhu et al., “Multi-scale coarse-to-fine segmentation for screening pancreatic ductal adenocarcinoma,” ArXiv, 2019, 9 pages. [cited by applicant]
Zhu et al., “Random Walks with Adaptive Cylinder Flux Based Connectivity for Vessel Segmentation,” MICCAI., 2013, 16:2:550-8. [cited by applicant]
Zhu et al., “Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models,” Proceedings of the 41st Annual Meeting of the Cognitive Science Society: Creativity + Cognition + Computation, J… [cited by applicant]
Zhu et al., “Unsupervised Structure Learning: Hierarchical Recursive Composition, Suspicious Coincidence and Competitive Exclusion,” Computer Vision—ECCV 2008 (LNCS), Oct. 2008, 5303:759-773. [cited by applicant]
Zhuang et al., Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI, Med Image Analysis, 2016, 31:77-87. [cited by applicant]
Zu et al., “Robust multi-atlas propagation by deep sparse representation,” Pattern Recognition, 2017, 63:511-517. [cited by applicant]
Cen et al., “Boosting occluded image classification via subspace decomposition- based estimation of deep features,” IEEE Transactions on Cybernetics, Aug. 12, 2019, 50(7):3409-22. [cited by applicant]
Cen et al., “Deep feature augmentation for occluded image classification,” Pattern Recognition, Mar. 1, 2021, 111:107737. [cited by applicant]
Enzweiler et al., “Multi-cue pedestrian classification with partial occlusion handling,” In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun. 13, 2010, 990-997. [cited by applicant]
Kortylewski et al., “Combining compositional models and deep networks for robust object classification under occlusion,” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2020, 1333-13… [cited by applicant]
Yoo, “Deep convolution neural networks in computer vision: a review,” IEIE Transactions on Smart Processing and Computing, Feb. 2015, 4(1):35-43. [cited by applicant]