IP Library › Granted Patent US 12,749,182
Granted Patent B2
US 12,749,182 · App. 18/302,635 · Granted Sep 29, 2026

Development of medical imaging AI analysis algorithms leveraging image segmentation

Inventor: Murray Aaron Reicher (Rancho Santa Fe, CA)
Assignee: Synthesis Health Inc.
G06T7/0012G06T7/11G16H15/00G16H30/40G16H50/20
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 12,749,182
App. No.
18/302,635
Granted
Sep 29, 2026
Kind
B2
Abstract

A medical image may be anatomically segmented, such as by an automated segmentation model, before presentation to a reading physician, who can then step through the anatomical segments which may have already been associated with an initial estimate of whether there is a finding. Based on indications provided by the reading physician, the system may optimize feature detection algorithms of segment-specific diagnostic models that are configured to identify characteristics of medical images of the specific anatomical segments.

Claims (53)

1 . A computerized method, performed by a computing system having one or more hardware computer processors and one or more non-transitory computer readable storage device storing software instructions executable by the computing system to perform the computerized method comprising:

for each of a plurality of medical images:

accessing the medical image;

applying a segmentation algorithm to the medical image to determine a plurality of anatomical segments indicated in the medical image, wherein each of the anatomical segments is associated with an anatomical component or an anatomical system;

for each of a plurality of users:

displaying the medical image on a display device of a user;

for each of the plurality of anatomical segments, displaying user interface controls usable to indicate whether a finding is observed by the user;

receiving, via the user interface controls, user input indicating that either:

the anatomical segment shows a finding, or

the anatomical segment does not show a finding;

storing, for each anatomical segment, metadata comprising: (i) segment boundaries, (ii) anatomical identifiers, and (iii) user-indicated finding status, in a training data set; and

for each of the plurality of anatomical segments:

training a segment-specific diagnostic model to detect findings in the anatomical segment of medical images not included in the plurality of medical images, wherein the segment-specific diagnostic model:

accesses the training data set to identify a first set of medical images with the anatomical segment identified as no finding and a second set of medical images with the anatomical segment identified as finding detected, and

trains the segment-specific diagnostic model based on differences between the first and second sets of medical images.

2 . The method of claim 1 , further comprising:

accessing a medical image not included in the plurality of medical images;

applying the segmentation algorithm to the medical image to determine the plurality of anatomical segments of patient anatomy indicated in the medical image; and

for each of the anatomical segments identified in the medical image:

selecting a segment-specific diagnostic model associated with the anatomical segment;

applying the segment-specific diagnostic model to at least portions of the medical image associated with the anatomical segment, wherein the segment-specific diagnostic model provides an indication of whether the anatomical segment is more likely normal or abnormal.

3 . The method of claim 2 , further comprising:

displaying, in a user interface, an indication of any anatomical segments with findings.

4 . The method of claim 2 , further comprising:

prepopulating an itemized report with the indications of findings and associated anatomical segments.

5 . The method of claim 4 , wherein the anatomical segments associated with findings are indicated in the report.

6 . The method of claim 4 , wherein the anatomical segments associated with findings include a link or reference to a medical image associated with the finding.

7 . The method of claim 2 , wherein the segment-specific diagnostic model determines indications of finding vs no finding based on one or more of an indication or a clinical question.

8 . The method of claim 1 , wherein the anatomical components include one or more of: lungs, vasculature, cardiac, mediastinum, pleura, or bone.

9 . The method of claim 1 , wherein the anatomical systems include one or more of: digestive system, musculoskeletal system, nervous system, endocrine system, reproductive system, urinary system, or immune system.

10 . The method of claim 1 , wherein the anatomical segments are associated with corresponding sections of a medical report.

11 . The method of claim 1 , wherein the plurality of anatomical segments are stored in data structure in association with a type of the medical image.

12 . The method of claim 1 , further comprising:

wherein the segmentation algorithm accesses a medical report associated with the medical image to determine whether there is a finding or no finding for each of the anatomical segments indicating in the medical report.

13 . The method of claim 12 , wherein said determining whether there is a finding or no finding for each of the anatomical segments indicating in the medical report is based at least partly on natural language processing of textual descriptions associated with respective anatomical segments.

14 . The method of claim 1 , wherein the segment-specific diagnostic models are trained using itemized reports wherein at least one report item corresponds to an anatomical segment defined in an image.

15 . The method of claim 1 , wherein the segment-specific diagnostic models are trained using one or more artificial intelligence algorithms to classify items in a medical report as finding or no finding.

16 . A computing system comprising:

a hardware computer processor; and

a non-transitory computer readable medium having software instructions stored thereon, the software instructions executable by the hardware computer processor to cause the computing system to perform operations comprising:

accessing the medical image;

applying a segmentation algorithm to the medical image to determine a plurality of anatomical segments indicated in the medical image, wherein each of the anatomical segments is associated with an anatomical component or an anatomical system;

for each of a plurality of users:

displaying the medical image on a display device of a user;

for each of the plurality of anatomical segments, displaying user interface controls usable to indicate whether a finding is observed by the user;

receiving, via the user interface controls, user input indicating that either:

the anatomical segment shows a finding, or

the anatomical segment does not show a finding;

storing, for each anatomical segment, metadata comprising: (i) segment boundaries, (ii) anatomical identifiers, and (iii) user-indicated finding status, in a training data set; and

for each of the plurality of anatomical segments:

training a segment-specific diagnostic model to detect findings in the anatomical segment of medical images not included in the plurality of medical images, wherein the segment-specific diagnostic model:

accesses the training data set to identify a first set of medical images with the anatomical segment identified as no finding and a second set of medical images with the anatomical segment identified as finding detected, and

trains the segment-specific diagnostic model based on differences between the first and second sets of medical images.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 7, 2023
From: REICHER, MURRAY AARON
To: SYNTHESIS HEALTH INC.
Reel/Frame 064189/0028 →
Continuity (2)
Provisional Application 63332534 · Apr 19, 2022
Related Publication 20230334663A1 · Oct 19, 2023
References Cited (91)
US 7646898B1 · Nowinski et al. · 2010 [cited by applicant]
US 10210310B2 · Carolus et al. · 2019 [cited by applicant]
US 10580528B2 · Mclaughlin et al. · 2020 [cited by applicant]
US 10937164B2 · Steigauf et al. · 2021 [cited by applicant]
US 11263749B1 · Purushottam et al. · 2022 [cited by applicant]
US 11540794B2 · Boddington et al. · 2023 [cited by applicant]
US 11574112B2 · Song et al. · 2023 [cited by applicant]
US 11664114B2 · Lyman et al. · 2023 [cited by applicant]
US 12548660B2 · Reicher et al. · 2026 [cited by applicant]
US 20070282824A1 · Ellingsworth · 2007 [cited by applicant]
US 20080146923A1 · Mejla et al. · 2008 [cited by applicant]
US 20080205721A1 · Udupa et al. · 2008 [cited by applicant]
US 20090092300A1 · Jerebko · 2009 [cited by examiner]
US 20100095340A1 · Ei et al. · 2010 [cited by applicant]
US 20130251233A1 · Yang et al. · 2013 [cited by applicant]
US 20140115020A1 · Colaco et al. · 2014 [cited by applicant]
US 20150310358A1 · Khabazian · 2015 [cited by applicant]
US 20160121142A1 · Zhang et al. · 2016 [cited by applicant]
US 20160154933A1 · Ramanathan · 2016 [cited by applicant]
US 20170069084A1 · Kubo et al. · 2017 [cited by applicant]
US 20180326149A1 · Lipschultz et al. · 2018 [cited by applicant]
US 20180342060A1 · Yao · 2018 [cited by examiner]
US 20190042703A1 · Reicher et al. · 2019 [cited by applicant]
US 20190096060A1 · Zhang et al. · 2019 [cited by applicant]
US 20190139218A1 · Song et al. · 2019 [cited by applicant]
US 20190139238A1 · Wyeth · 2019 [cited by applicant]
US 20190171714A1 · Gale et al. · 2019 [cited by applicant]
US 20190188870A1 · Park et al. · 2019 [cited by applicant]
US 20190237184A1 · Sharma et al. · 2019 [cited by applicant]
US 20190290215A1 · Gilbert · 2019 [cited by applicant]
US 20190325249A1 · Maraghoosh et al. · 2019 [cited by applicant]
US 20200043600A1 · Glottmann et al. · 2020 [cited by applicant]
US 20200178794A1 · El-Baz et al. · 2020 [cited by applicant]
US 20200321100A1 · Glottmann et al. · 2020 [cited by applicant]
US 20210020303A1 · Accomazzi et al. · 2021 [cited by applicant]
US 20210065859A1 · McKinney et al. · 2021 [cited by applicant]
US 20210134465A1 · Gooßen et al. · 2021 [cited by applicant]
US 20210216822A1 · Paik et al. · 2021 [cited by applicant]
US 20210264212A1 · Paik et al. · 2021 [cited by applicant]
US 20210282730A1 · Singh et al. · 2021 [cited by applicant]
US 20210375435A1 · O'Connor et al. · 2021 [cited by applicant]
US 20220037019A1 · Covington · 2022 [cited by examiner]
US 20220084209A1 · Wang · 2022 [cited by examiner]
US 20220265233A1 · Boddington et al. · 2022 [cited by applicant]
US 20230070444A1 · Kartmann et al. · 2023 [cited by applicant]
US 20230108955A1 · Weissman et al. · 2023 [cited by applicant]
US 20230334763A1 · Reicher · 2023 [cited by applicant]
US 20230335261A1 · Reicher et al. · 2023 [cited by applicant]
US 20230343454A1 · Chang et al. · 2023 [cited by applicant]
US 20240087724A1 · Sawarkar · 2024 [cited by examiner]
US 20240153094A1 · Liu · 2024 [cited by examiner]
US 20240177836A1 · Paik · 2024 [cited by examiner]
US 20240312583A1 · Amarasingham et al. · 2024 [cited by applicant]
US 20240331354A1 · Azad et al. · 2024 [cited by applicant]
US 20240347156A1 · Paulett et al. · 2024 [cited by applicant]
US 20250078970A1 · Reicher et al. · 2025 [cited by applicant]
US 20250078987A1 · Reicher et al. · 2025 [cited by applicant]
CN 112309528 · 2021 [cited by applicant]
CN 115035089 · 2022 [cited by applicant]
EP 2561458 · 2021 [cited by applicant]
JP 2020523711 · 2020 [cited by applicant]
KR 1020180040287 · 2018 [cited by applicant]
KR 20180040287A · 2018 [cited by examiner]
KR 1020190102399 · 2019 [cited by applicant]
KR 102374278 · 2022 [cited by applicant]
WO WO2014085918 · 2014 [cited by applicant]
WO WO2018129094 · 2018 [cited by applicant]
WO WO20208026033 · 2020 [cited by applicant]
WO WO2020056086 · 2020 [cited by applicant]
WO WO2022144360 · 2022 [cited by applicant]
WO WO2022212771 · 2022 [cited by applicant]
WO WO2023205177 · 2023 [cited by applicant]
WO WO2023205179 · 2023 [cited by applicant]
WO WO2023205181 · 2023 [cited by applicant]
WO WO2024102765 · 2024 [cited by applicant]
WO WO2024102832 · 2024 [cited by applicant]
WO WO2025048865 · 2025 [cited by applicant]
WO WO2025155564 · 2025 [cited by applicant]
Kim Sung Hyun, KR-20180040287-A (English Translation), System for Interpreting Medical Images Through Machine Learnings (Year: 2018). [cited by examiner]
International Search Report and Written Opinion for International Application No. PCT/US2023/018991 dated Aug. 8, 2023; 10 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2023/018985 dated Aug. 16, 2023; 10 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2023/018987 dated Aug. 1, 2023; 11 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2023/079001 dated Feb. 29, 2024; 11 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2023/079117 dated Mar. 6, 2024; 12 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2023/078010 dated May 20, 2024; 8 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2025/011591 dated Jul. 2, 2025, 10 pages. [cited by applicant]
Sugimoto et al., “Extracting clinical terms from radiology reports with deep learning,” Journal of Biomedical Informatics 116; In 7 pages (2021). [cited by applicant]
International Preliminay Report on Patentability for International Application No. PCT/US2023/078010 issued Mar. 4, 2026; 4 pages. [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2025/046841 mailed Jan. 16, 2026. [cited by applicant]
Fraunhofer: Analyzing documents faster using artificial intelligence from Fraunhofer. Fraunhofer. (Sep. 1, 2020). Https://www.farunhofer.de/en/press/research-news/2020/september/analyzing-documents-faster-using-artifici… [cited by applicant]
Kalaria et al.: “Comparison-Bot: An Automated Preliminary-Final Report Comparison System,” J Digit Imaging (2016) 29:325-330. [cited by applicant]