IP Library Granted Patent US 12,733,901
Granted Patent B2
US 12,733,901 · App. 18/603,191 · Granted Sep 15, 2026

Artificial intelligence system for comprehensive medical diagnosis, prognosis, and treatment optimization through medical imaging

Inventor: Robert S Bunn (Highlands Ranch, CO)
Assignee: Ultrasound AI, Inc.
A61B8/0866A61B8/06A61B8/0875A61B8/0883A61B8/467A61B8/488G06T7/0016G06T7/20G16H10/60G16H30/20G16H30/40G16H50/20G06T2207/10132G06T2207/20081G06T2207/30008G06T2207/30044G06T2207/30048G06T2207/30104
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 12,733,901
App. No.
18/603,191
Granted
Sep 15, 2026
Kind
B2
Abstract

Systems and methods for comprehensive medical diagnosis, prognosis, and treatment optimization are provided. A neural network is trained on a large dataset of medical images or raw data from various imaging modalities, such as ultrasound, MRI, CT, and X-ray, which are labeled with ground truth diagnoses of a wide range of medical conditions. The trained neural network can then be provided with medical images of a patient, and the neural network can make predictions and provide insights related to the presence, absence, severity, progression, or risk of various medical conditions. These predictions and insights can support clinical decision-making and enable early intervention, personalized treatment, and improved patient outcomes. The system can be continually updated with new data to improve its performance over time, and can be integrated into healthcare workflows to enhance the accuracy, efficiency, and effectiveness of medical diagnosis and treatment.

Claims (37)

1 . A system for making a comprehensive medical determination, the system comprising:

a medical image generator configured to acquire non-invasive medical images of a plurality of anatomical structures of a patient during an imaging session, the medical image generator further configured to adapt generation of the non-invasive medical images based on feedback received from image analysis logic by fine-tuning at least one of (i) image generation, (ii) focus, or (iii) image processing parameters;

a digital storage storing a plurality of non-invasive medical images of the plurality of anatomical structures of the patient;

a microprocessor in communication with the digital storage and configured to implement the image analysis logic comprising a trained neural network, wherein the image analysis logic is further configured to:

process one or more non-invasive medical images of the plurality of non-invasive medical images of the plurality of anatomical structures of the patient to provide a quantitative prediction or an insight related to a medical condition of the patient; and

determine a confidence score associated with the quantitative prediction; and

a user interface configured to provide the quantitative prediction and the confidence score to a healthcare professional.

2 . The system of claim 1 , wherein the image analysis logic includes first logic configured to process the one or more non-invasive medical images of the plurality of non-invasive medical images to provide the quantitative prediction related to a current state of the medical condition.

3 . The system of claim 1 , wherein the image analysis logic includes second logic configured to process the one or more non-invasive medical images of the plurality of non-invasive medical images to provide the quantitative prediction related to a future state, progression, or risk of the medical condition.

4 . The system of claim 1 , wherein the image analysis logic is configured to employ a regression algorithm to provide the quantitative prediction as a range or confidence interval.

5 . The system of claim 1 , wherein the image analysis logic is configured to employ a classification algorithm to provide the quantitative prediction as one of a plurality of categories or severities.

6 . The system of claim 1 , wherein the image analysis logic is further configured to provide the quantitative prediction based on a combination of the non-invasive medical images and additional clinical data.

7 . The system of claim 1 , wherein the non-invasive medical images are represented by raw image data.

8 . A method for training a neural network to make comprehensive medical predictions, the method comprising:

receiving a dataset of non-invasive medical images of a plurality of anatomical structures of a plurality of patients, the non-invasive medical images labeled with ground truth diagnoses of a plurality of medical conditions;

classifying the non-invasive medical images according to views or features included within the non-invasive medical images;

filtering the non-invasive medical images to remove images:

(i) that lack the views or the features that have been determined to have determinative value; and

(ii) that are of insufficient quality or resolution;

partitioning the dataset into a training set, a validation set, and an independent test set;

training the neural network using the training set to predict the plurality of medical conditions;

fine-tuning the neural network using the validation set to optimize its performance and generalization; and

evaluating final performance characteristics of the neural network using the independent test set, by comparing quantitative predictions based on the independent test set provided by the neural network to ground truth diagnosis labels associated with the independent test set.

9 . The method of claim 8 , wherein the non-invasive medical images comprise one or more imaging modalities including ultrasound, radiography, MRI, CT, PET, SPECT, mammography, and optical imaging.

10 . The method of claim 8 , further comprising pre-processing the non-invasive medical images before training the neural network, wherein pre-processing the non-invasive medical images includes one or more of normalization, resizing, cropping, or augmentation.

11 . The method of claim 8 , further comprising employing transfer learning to leverage pre-trained neural networks and adapting the pre-trained neural networks to perform comprehensive medical condition prediction.

12 . The method of claim 8 , wherein the non-invasive medical images are represented by raw image data.

13 . A method for making a comprehensive medical determination using a trained neural network, the method comprising:

acquiring one or more non-invasive medical images of a plurality of anatomical structures of a patient using an image acquisition device, the image acquisition device configured to adapt generation of the one or more non-invasive medical images based on feedback received from image analysis logic by fine-tuning at least one of (i) image generation, (ii) focus, or (iii) image processing parameters;

pre-processing the acquired non-invasive medical images to optimize the acquired non-invasive medical images for input into the trained neural network;

providing the pre-processed non-invasive medical images to the trained neural network, which has been optimized to predict a plurality of medical conditions;

receiving from the trained neural network a quantitative prediction, and a confidence score associated with the quantitative prediction, related to the presence, absence, severity, or risk of a medical condition for the patient; and

presenting the quantitative prediction to a healthcare professional via a user interface to support clinical decision-making.

14 . The method of claim 13 , wherein the trained neural network employs a combination of regression and classification algorithms to provide both continuous and categorical predictions.

15 . The method of claim 13 , wherein the quantitative prediction is accompanied by explanations or visualizations highlighting key anatomical features or abnormalities that contributed to the quantitative prediction.

16 . The method of claim 13 , wherein the trained neural network is continuously updated and refined using new non-invasive medical images and ground truth data.

17 . The method of claim 13 , wherein the one or more non-invasive medical images are represented by raw image data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 14, 2025
From: BUNN, ROBERT S.
To: ULTRASOUND AI INC.
Reel/Frame 070512/0702 →
Continuity (6)
Continuation In Part 17573246 · Jan 11, 2022
Continuation PCTUS2021038164 · Jun 20, 2021
Continuation 17352290 · Jun 19, 2021
Provisional Application 63451844 · Mar 13, 2023
Provisional Application 63041360 · Jun 19, 2020
Related Publication 20240215945A1 · Jul 4, 2024
References Cited (111)
US 8828981B2 · Creasy et al. · 2014 [cited by applicant]
US 10650929B1 · Beck et al. · 2020 [cited by applicant]
US 11266376B2 · Bunn · 2022 [cited by applicant]
US 11969289B2 · Bunn · 2024 [cited by applicant]
US 12318249B2 · Bunn · 2025 [cited by applicant]
US 20040236193A1 · Sharf · 2004 [cited by applicant]
US 20060241510A1 · Halperin et al. · 2006 [cited by applicant]
US 20090093717A1 · Carneiro et al. · 2009 [cited by applicant]
US 20090169074A1 · Avinash et al. · 2009 [cited by applicant]
US 20100312115A1 · Dentinger · 2010 [cited by applicant]
US 20110248818A1 · Hashim-Waris · 2011 [cited by applicant]
US 20120135427A1 · Kypros et al. · 2012 [cited by applicant]
US 20140018678A1 · Donnelly et al. · 2014 [cited by applicant]
US 20140089004A1 · Frey et al. · 2014 [cited by applicant]
US 20150148657A1 · Shashar et al. · 2015 [cited by applicant]
US 20150342560A1 · Davey et al. · 2015 [cited by applicant]
US 20160071266A1 · Srivastava et al. · 2016 [cited by applicant]
US 20160228505A1 · Stossel et al. · 2016 [cited by applicant]
US 20160340407A1 · Hodi et al. · 2016 [cited by applicant]
US 20170000683A1 · Samec et al. · 2017 [cited by applicant]
US 20170086785A1 · Bjaerum · 2017 [cited by applicant]
US 20170091402A1 · Salafia et al. · 2017 [cited by applicant]
US 20170216335A1 · Mangano · 2017 [cited by applicant]
US 20170357844A1 · Comaniciu et al. · 2017 [cited by applicant]
US 20180032666A1 · Sun et al. · 2018 [cited by applicant]
US 20180153504A1 · Herickhoff et al. · 2018 [cited by applicant]
US 20180247410A1 · Madabhushi et al. · 2018 [cited by applicant]
US 20190008674A1 · Myers et al. · 2019 [cited by applicant]
US 20190021698A1 · Raghvan et al. · 2019 [cited by applicant]
US 20190034590A1 · Oren et al. · 2019 [cited by applicant]
US 20190154704A1 · Davis et al. · 2019 [cited by applicant]
US 20190209116A1 · Sjostrand et al. · 2019 [cited by applicant]
US 20190246904A1 · Kim et al. · 2019 [cited by applicant]
US 20190251638A1 · Braz et al. · 2019 [cited by applicant]
US 20190367987A1 · Hamamah et al. · 2019 [cited by applicant]
US 20200005899A1 · Nicula et al. · 2020 [cited by applicant]
US 20200005901A1 · Cohen et al. · 2020 [cited by applicant]
US 20200022674A1 · Egorov · 2020 [cited by applicant]
US 20200035362A1 · Abou Shousha · 2020 [cited by examiner]
US 20200069292A1 · Abolmaesumi et al. · 2020 [cited by applicant]
US 20200077947A1 · Shi et al. · 2020 [cited by applicant]
US 20200147006A1 · Charney et al. · 2020 [cited by applicant]
US 20200149110A1 · Targan et al. · 2020 [cited by applicant]
US 20200168310A1 · Westin et al. · 2020 [cited by applicant]
US 20200170614A1 · Kim et al. · 2020 [cited by applicant]
US 20210068905A1 · Quaid et al. · 2021 [cited by applicant]
US 20210090254A1 · Gong et al. · 2021 [cited by applicant]
US 20210118559A1 · Lefkofsky · 2021 [cited by applicant]
US 20210128115A1 · Mapiye et al. · 2021 [cited by applicant]
US 20210217166A1 · Graule et al. · 2021 [cited by applicant]
US 20210287513A1 · Mazar et al. · 2021 [cited by applicant]
US 20210307702A1 · Moon · 2021 [cited by applicant]
US 20210393235A1 · Bunn · 2021 [cited by applicant]
US 20220028551A1 · Jordan et al. · 2022 [cited by applicant]
US 20220067922A1 · Yu · 2022 [cited by applicant]
US 20220133260A1 · Bunn · 2022 [cited by applicant]
US 20220133280A1 · Urabe et al. · 2022 [cited by applicant]
US 20220164635A1 · Johansen et al. · 2022 [cited by applicant]
US 20220192501A1 · Shuler · 2022 [cited by applicant]
US 20220328189A1 · Zhou et al. · 2022 [cited by applicant]
US 20220400963A1 · Bucklet et al. · 2022 [cited by applicant]
US 20230172580A1 · Bunn et al. · 2023 [cited by applicant]
US 20240173011A1 · Bunn · 2024 [cited by applicant]
US 20240173012A1 · Bunn · 2024 [cited by applicant]
US 20240197287A1 · Bunn · 2024 [cited by applicant]
US 20250275747A1 · Bunn · 2025 [cited by applicant]
CN 110613480A · 2019 [cited by applicant]
IN 201941040741A · 2021 [cited by applicant]
JP 2018140172A · 2018 [cited by applicant]
KR 1020200013161A · 2020 [cited by applicant]
WO 2020061590A1 · 2020 [cited by applicant]
WO 2020107023A1 · 2020 [cited by applicant]
CN 202180043378.8, Response to first office action issued Dec. 28, 2023, dated May 10, 2024. [cited by applicant]
CN 202180043378.8, Rejection Decision issued May 18, 2024. [cited by applicant]
CN 202180043378.8, Response to Rejection Decision iissued May 18, 2024, dated Aug. 19, 2024. [cited by applicant]
EP 21825348.2 EESR Issued Jun. 18, 2024. [cited by applicant]
Oelze et al., “Review of Quantitative Ultrasound: Envelope Statistics and Backscatter Coefficient Imaging and Contributions to Diagnostic Ultrasound”, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Cont… [cited by applicant]
Suff Natalie et al: “The prediction of preterm delivery: What is new?”, Seminars in Fetal and Neonatal Medicine, Elsevier, GB, vol. 24, No. 1, Sep. 28, 2018 (Sep. 28, 2018), pp. 27-32, XP085591331, ISSN: 1744-165X, DOI:… [cited by applicant]
Pizzella Stephanie et al: “Evolving cervical imaging technologies to predict preterm birth”, Seminars in Immunopathology, Springer Berlin Heidelberg, Berlin/Heidelberg, vol. 42, No. 4, Jun. 10, 2020 (Jun. 10, 2020), pp.… [cited by applicant]
Andrea Campagner, #., Luisa Agnello, #., Carobene, A., Padoan, A., Del Ben, F., Locatelli, M., . . . Marcello Ciaccio, #. (2025). Complete Blood Count and Monocyte Distribution Width-Based Machine Learning Algorithms fo… [cited by applicant]
Beauchamp, N. J., Bryan, R. N., Bui, M. M., Krestin, G. P., McGinty, G. B., Meltzer, C. C., & Neumaier, M. (2023). Integrative diagnostics: the time is now—a report from the International Society for Strategic Studies i… [cited by applicant]
C-AILM https://ifcc.org/ifcc-emerging-technologies-division/etd-committees/wg-aigd/. [cited by applicant]
C-ID https://www.eflm.eu/site/who-we-are/divisions/science-division/fu/c-integrative-diagnostics. [cited by applicant]
Cesselli, D., Ius, T., Isola, M., Del Ben, F., Da Col, G., Bulfoni, M., Skrap, M. (2019). Application of an Artificial Intelligence Algorithm to Prognostically Stratify Grade II Gliomas. Cancers, 31877896. Retrieved fro… [cited by applicant]
Da Col, G., Del Ben, F., Bulfoni, M., Turetta, M., Gerratana, L., Bertozzi, S., . . . Cesselli, D. (2022). Image Analysis of Circulating Tumor Cells and Leukocytes Predicts Survival and Metastatic Pattern in Breast Canc… [cited by applicant]
Del Ben, F. (2025). Beyond test results: the strategic importance of metadata for the integration of AI in laboratory medicine. Clin. Chern. Lab. Med., 39846365. Retrieved from https://pubmed.ncbi.nlm.nih.gov/39846365. [cited by applicant]
Del Ben, F., Biasizzo, J., & Curcio, F. (2019). A fast, nondestructive, low-cost method for the determination of hematocrit of dried blood spots using image analysis. Clin. Chern. Lab. Med., 30179847. Retrieved from htt… [cited by applicant]
Del Ben, F., Da Col. G., Cobarzan, D., Turetta, M., Rubin, D., Buttazzi, P., & Antico, A. (2023). A fully interpretable machine learning model for increasing the effectiveness of urine screening. Am. J. Clin. Pathol., 3… [cited by applicant]
Fabris, M., Del Ben, F., Sozio, E., Beltrami, A. P., Cifii, A., Bertolino, G., . . . Curcio, F. (2022). Cytokines from Bench to Bedside: A Retrospective Study Identifies a Definite Panel of Biomarkers to Early Assess th… [cited by applicant]
Soldati, G., Del Ben, F., Brisotto, G., Biscontin, E., Bulfoni, M., Piruska, A., . . . Mea, V. D. (2018). Microfluidic droplets 1 2 content classification and analysis through convolutional neural networks in a liquid b… [cited by applicant]
Sorace, J., Aberle, D. R., Elimam, D., Lawvere, S., Tawfik, 0., & Wallace, W. D. (2012). Integrating pathology and radiology disciplines: an emerging opportunity? BMC Med., 10(1), 1-6. doi: 10.1186/1741-7015-10-100. [cited by applicant]
Wild, R., Sozio, E., Margiotta, R. G., Dellai, F., Acquasanta, A., Del Ben, F., . . . Laio, A. (2024). Maximally informative feature selection using Information Imbalance: Application to COVID-19 severity prediction. Sc… [cited by applicant]
CN 202180043378.8, Response to Rejection Decision issued May 18, 2024, dated Aug. 19, 2024. [cited by applicant]
International Preliminary Report on Patentability received for PCT Patent Application No. PCT/US2021/038164, mailed on Dec. 29, 2022, 9 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Patent Application No. PCT/US2023/011845, mailed on Aug. 8, 2024, 12 pages. [cited by applicant]
Office Action dated Sep. 3, 2024 regarding Application No. JP2022-574786. [cited by applicant]
Office Action dated Oct. 21, 2024 regarding Application No. KR10-2023-7000075. [cited by applicant]
Response to Office Action dated Nov. 19, 2024 regarding Application No. JP2022-574786. [cited by applicant]
Response to Office Action dated Dec. 23, 2024 regarding Application No. KR10-2023-7000075. [cited by applicant]
Response to Office Action dated Dec. 30, 2024 regarding Application No. EP21825348.2. [cited by applicant]
Office Action dated Feb. 4, 2025 regarding Application No. JP2022-574786. [cited by applicant]
Office Action Issued in related Chinese Patent Application No. 202180043378.8 issued Dec. 28, 2023, 27 pages. [cited by applicant]
PCT/US21/38164 International Search Report and Written Opinion, mailed Sep. 30, 2021. [cited by applicant]
PCT/US23/011845 International Search Report and Written Opinion, mailed Apr. 27, 2023. [cited by applicant]
PCT/US24/014349 International Search Report and Written Opinion, mailed May 7, 2024. [cited by applicant]
PCT/US24/019803 International Search Report and Written Opinion, mailed Jun. 17, 2024. [cited by applicant]
PCT/US24/014353 International Search Report and Written Opinion, mailed May 7, 2024. [cited by applicant]
PCT/US24/014356 International Search Report and Written Opinion, mailed May 9, 2024. [cited by applicant]
Kuo et al., “Automation of the kidney function prediction and classification through ultrasoundbased kidney imaging using deep learning.” In: npj Digital Medicine vol. 2, Article No. 29 (2019), [onlinel [retrieved on Ap… [cited by applicant]
Diniz Pedro H. et al: “Deep Learning Strategies for Ultrasound in Pregnancy”, EMJ Reproductive Health, (Aug. 25, 2020), pp. 73-80, XP093365490, ISSN: 2059-450X, DOI: 10.33590/emjreprohealth/20-00100 Retrieved from the I… [cited by applicant]
Wang Qian et al: “Smart Ultrasound Imaging and Perinatal, Preterm and Paediatric Image Analysis” First International Workshop, SUSI 2019, and 4th International Workshop, PIPPI 2019, Held in Conjunction with MICCAI 2019,… [cited by applicant]