IP Library Granted Patent US 12,721,589
Granted Patent B2
US 12,721,589 · App. 18/431,291 · Granted Sep 1, 2026

Artificial intelligence system for determining drug use 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 12,721,589
App. No.
18/431,291
Granted
Sep 1, 2026
Kind
B2
Abstract

Systems and methods for establishing a patient's pharmaceutical use are provided. A neural network is trained on a dataset of medical images, such as ultrasound images, that are tagged with information concerning the use of the pharmaceutical by people who were imaged to produce the medical images. The trained neural network can then be provided with medical images of a patient, and the neural network can then make a determination as to the patient's pharmaceutical use.

Claims (54)

1 . A system configured to make a medical determination, the system comprising:

a medical image generator configured to acquire non-invasive medical images of a body part of a patient during an imaging session, the medical image generator further configured to adapt generation of the 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;

an image storage storing a set of the medical images of the body part of a the patient, the set of medical images having been acquired during the imaging session;

image analysis logic comprising a trained neural network in communication with the image storage and configured to:

(i) process a plurality of the medical images of the set to provide a plurality of image-level determinations indicative of a quantitative estimate of an exposure of the patient to a pharmaceutical,

(ii) generate an aggregate determination regarding the quantitative estimate by aggregating the image-level determinations, wherein the aggregating comprises excluding at least one anatomical view or other information that is determined to be commonly uninformative and/or weighting a plurality of anatomical views in calculating the aggregate determination, and

(iii) determine a confidence score associated with the aggregate determination;

feedback logic configured, based on the confidence score and/or a classification of medical images already acquired during the imaging session, to guide acquisition of at least one additional medical image during the imaging session via a user interface;

the user interface configured to provide at least the aggregate determination and guidance output by the feedback logic to a user; and

a microprocessor configured to execute at least the image analysis logic and the feedback logic.

2 . The system of claim 1 wherein the image analysis logic includes first logic configured to analyze the set of medical images to determine a present exposure to the pharmaceutical at the time the set of medical images were acquired.

3 . The system of claim 1 wherein the image analysis logic includes second logic configured to determine a timeframe for a prior exposure to the pharmaceutical.

4 . The system of claim 1 wherein the image analysis logic is configured to employ a regression algorithm to provide the quantitative estimate as a range.

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

6 . The system of claim 1 , wherein the quantitative estimate comprises an estimated dosage range of the pharmaceutical expressed in dosage units.

7 . The system of claim 1 , wherein the quantitative estimate comprises an estimate of a time period during which the pharmaceutical was used by the patient.

8 . The system of claim 1 wherein the quantitative estimate comprises an estimated dosage expressed as a measure of the pharmaceutical over a time duration.

9 . The system of claim 1 wherein the quantitative estimate is further based on a clinical data set.

10 . The system of claim 1 , wherein image analysis logic is further configured to determine the confidence score satisfies a threshold condition and, in response, identifying the at least one additional medical image.

11 . The system of claim 1 , wherein the feedback logic is further configured to guide acquisition of the at least one additional medical image by at least one of: (i) a recommended anatomical view, (ii) a recommended imaging plane, (iii) a recommended probe position, (iv) a recommended timepoint, or (v) a recommended acquisition setting.

12 . The system of claim 1 , wherein the non-invasive medical images comprise images generated by at least one of ultrasound imaging, magnetic resonance imaging, computed tomography imaging, positron emission tomography imaging, x ray imaging, or optical imaging.

13 . The system of claim 1 , wherein processing the plurality of the medical images further comprises generating a normalized image tensor comprising at least one of: image normalization, image registration, or image resampling into a standardized resolution.

14 . The system of claim 1 , wherein the feedback logic is further configured to generate a region-of-interest representation that identifies a target anatomical structure.

15 . The system of claim 1 , wherein the trained neural network comprises at least one of a convolutional neural network, a transformer network, or an ensemble of neural networks.

16 . The system of claim 1 , wherein the confidence score comprises at least one of a predictive variance, a confidence interval, or an entropy measure.

17 . The system of claim 1 , wherein the image analysis logic is further configured to receive at least one additional medical image identified by the feedback logic, and to compute an updated quantitative estimate using the at least one additional medical image.

18 . The system of claim 1 , wherein the trained neural network was trained using supervised learning on labeled training examples that associate non-invasive medical images with corresponding reference exposure values of the pharmaceutical.

19 . A method for training a neural network to make a medical determination, the method comprising:

receiving a set of non-invasive medical images of body parts of a plurality of patients, the medical images tagged with information concerning exposure by the respective patients to a pharmaceutical;

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

filtering the medical images to remove images that lack features or views that have been determined to have little or no determinative value and/or to remove medical images filtered according to quality or resolution;

dividing the set of medical images into a training set and a validation set;

providing the medical images of the training set, and their tags, to a neural network to train the neural network to determine a quantitative exposure of the plurality of patients to the pharmaceutical based on images of the body parts; and

providing medical images of a single patient from the validation set to the neural network to make a determination, and comparing the determination to the tags associated with the medical images.

20 . The method of claim 19 wherein the non-invasive medical images are ultrasound images.

21 . The method of claim 19 further comprising classifying the medical images before providing the medical images of the training set to the neural network.

22 . The method of claim 19 further comprising resizing the medical images before providing the medical images of the training set to the neural network.

23 . A method for making a medical determination, the method comprising:

during a medical imaging session, generating, using an image generator comprising a source and a detector, a set of non-invasive medical images of a body part of a patient;

storing the set of medical images;

providing a plurality of medical images of the set to a neural network that has been trained to determine, from medical images of the body part, a quantitative estimate of an exposure of the patient to a pharmaceutical;

receiving, from the neural network, a plurality of image-level determinations and a confidence score associated with the determinations;

generating an aggregate determination regarding the quantitative estimate by aggregating the image-level determinations, wherein the aggregating comprises excluding at least one anatomical view or other information that is determined to be commonly uninformative and/or weighting a plurality of anatomical views in calculating the aggregate determination;

when the confidence score indicates inadequate precision, accuracy, and/or reliability, providing feedback during the imaging session via a user interface to guide acquisition of at least one additional medical image and/or to adapt generation of medical images by fine-tuning at least one of (i) image generation, (ii) focus, or (iii) image processing parameters; and

providing the aggregate determination regarding the quantitative estimate.

24 . The method of claim 23 wherein the non-invasive medical images are ultrasound images.

25 . The method of claim 23 wherein the neural network employs a regression algorithm and receiving the plurality of image-level determinations further includes receiving one or more ranges.

26 . The method of claim 23 wherein the neural network employs a classification algorithm and receiving the plurality of image-level determinations further includes receiving one of a plurality of categories.

27 . The method of claim 23 wherein the quantitative estimate of exposure to the pharmaceutical further comprises an estimate of an effective dosage of the pharmaceutical.

28 . The method of claim 23 wherein the quantitative estimate of exposure to the pharmaceutical further comprises a time the pharmaceutical should be used by the patient.

29 . The method of claim 23 , wherein the quantitative estimate comprises an estimated dosage range of the pharmaceutical expressed in dosage units.

30 . The method of claim 23 , wherein the quantitative estimate comprises an estimate of a time period during which the pharmaceutical was used by the patient.

31 . The method of claim 23 wherein the quantitative estimate comprises an estimated dosage expressed as a measure of the pharmaceutical over a time duration.

32 . The method of claim 23 wherein the quantitative estimate is further based on a clinical data set.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 7, 2025
From: BUNN, ROBERT S.
To: ULTRASOUND AI INC.
Reel/Frame 070437/0263 →
Continuity (6)
Continuation In Part 17573246 · Jan 11, 2022
Continuation PCTUS2021038164 · Jun 20, 2021
Continuation 17352290 · Jun 19, 2021
Provisional Application 63443169 · Feb 3, 2023
Provisional Application 63041360 · Jun 19, 2020
Related Publication 20240197287A1 · Jun 20, 2024
References Cited (112)
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 12369883B2 · 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 · 2016 [cited by examiner]
US 20160228505A1 · Stossel et al. · 2016 [cited by applicant]
US 20160340407A1 · Hodi · 2016 [cited by examiner]
US 20170000683A1 · Samec · 2017 [cited by examiner]
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 · 2018 [cited by examiner]
US 20180247410A1 · Madabhushi · 2018 [cited by examiner]
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 et al. · 2020 [cited by applicant]
US 20200069292A1 · Abolmaesumi · 2020 [cited by examiner]
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 20240215945A1 · 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]
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]
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]
JP 2022-574786, Notice of Reasons for Refusal, Issued Sep. 3, 2024. [cited by applicant]
KR 10-2023-7000075, Office Action, Issued Oct. 21, 2024. [cited by applicant]
EP 21825348.2, Response to EESR, filed Dec. 30, 2024. [cited by applicant]
JP 2022-574786, Response to Notice of Reasons for Refusal, Issued Sep. 3, 2024, filed Nov. 19, 2024. [cited by applicant]
KR 10-2023-7000075, Response to Office Action, Issued Oct. 21, 2024, filed Dec. 23, 2024. [cited by applicant]
Office Action dated Feb. 4, 2025 regarding JP2022-574786. [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]
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]
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 … [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]