IP Library › Granted Patent US 12,299,886
Granted Patent B2
US 12,299,886 · App. 18/603,460 · Granted May 13, 2025

Systems and methods for detecting potential malignancies

Inventors: Jonathan Ng (Cambridge, MA); Sloane Allebes Phillips (Cambridge, MA); Amit Ranade (Cambridge, MA); Daniel Wang (Cambridge, MA); Perikumar Mukundbhai Javia (Cambridge, MA); Avi Walden (Cambridge, MA); Austin Wang (Cambridge, MA); Evan Wlodkowski (Cambridge, MA); Samriddhi Dhakal (Cambridge, MA)
Assignee: Iterative Scopes, Inc.
G06T7/0012A61B1/00004A61B1/00016A61B1/0005A61B1/31G06T2207/10016G06T2207/10068G06T2207/20084G06T2207/30096G06T2210/12
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 12,299,886
App. No.
18/603,460
Granted
May 13, 2025
Kind
B2
Abstract

One or more machine learning techniques can be used to identify locations of potential malignancies within images (e.g., video images) captured during a medical procedure, such as an endoscopic procedure. The images can be displayed, in real-time, on a display unit. The images can be displayed with a graphical overlay that isolates the identified locations of potential malignancies.

Claims (48)

1. A data processing system comprising:

a display unit;

a memory; and

at least one processor configured to execute one or more instructions stored in the memory to perform operations comprising:

receiving spatially arranged image data associated with a plurality of images from an imaging device;

generating a plurality of processed images by processing the spatially arranged image data to identify one or more pixels of the spatially arranged image data representing, a set of processed images of the plurality of processed images, a location of a potential malignancy in an individual;

causing the display unit to display the set of processed images, wherein the set of processed images include at least one graphical overlay generated by the at least one processor;

detecting that a surgical tool is present in at least one of the processed images while the surgical tool is present in a surgical space associated with the potential malignancy; and

in response to the detecting,

altering the at least one graphical overlay from the at least one of the processed images, wherein the altering of at least one graphical overlay enables the at least one graphical overlay to be removed while the surgical tool is being detected, and

displaying an indicator when the at least one graphical overlay is displayed for less than a threshold amount of time.

2. The data processing system of claim 1 , wherein an amount of time between receiving the spatially arranged image data and causing the display unit to display the set of processed images is less than 60 milliseconds.

3. The data processing system of claim 1 , wherein the spatially arranged image data is received through a video capture card that is communicatively coupled to an endoscopic processing unit that comprises the imaging device.

4. The data processing system of claim 1 , wherein the set of processed images that are displayed include at least one visual indicator that indicates the set of processed images correspond to spatially arranged image data that has been processed by the at least one processor.

5. The data processing system of claim 1 , wherein the operations further comprise causing the display unit to display an indicator that indicates a potential malignancy has been identified in a previously displayed processed image that did not include a graphical overlay isolating one or more image locations corresponding to that potential malignancy.

6. The data processing system of claim 1 , wherein the at least one graphical overlay comprises a bounding box.

7. The data processing system of claim 1 , wherein the potential malignancy includes a polyp.

8. The data processing system of claim 1 , wherein the imaging device includes an endoscopic imaging device.

9. The data processing system of claim 1 , wherein the at least one processor is further configured to be communicatively coupled to a cloud-computing environment and to transmit the spatially arranged image data to the cloud-computing environment.

10. The data processing system of claim 1 , wherein the at least one graphical overlay represents the location of the potential malignancy in the individual, wherein the indicator is configured for being displayed in at least one of the set of processed images after the at least one graphical overlay representing the location of the potential malignancy in the individual are no longer being displayed.

11. The data processing system of claim 1 , the operations further comprising:

detecting, from the spatially arranged image data associated with a plurality of images from an imaging device, patient identifying information; and

obscuring, from the spatially arranged image data associated with a plurality of images from an imaging device, the patient identifying information.

12. The data processing system of claim 1 , the operations further comprising:

padding an input volume that includes the one or more pixels of the spatially arranged image data representing a location of a potential malignancy in an individual; and

controlling, based on padding the input volume, a spatial size of an object included in a graphical overlay of the one or graphic overlays, the object being associated with the location of a potential malignancy in an individual.

13. The data processing system of claim 1 , the operations further comprising:

causing the at least one graphical overlay to be displayed for at least a threshold amount of time for smoothing display of the graphical overlay.

14. A method comprising:

receiving spatially arranged image data associated with a plurality of images from an imaging device;

generating a plurality of processed images by processing the spatially arranged image data to identify one or more pixels of the spatially arranged image data representing, a set of processed images of the plurality of processed images, a location of a potential malignancy in an individual;

causing a display unit to display the set of processed images, wherein the set of processed images include at least one graphical overlay;

detecting that a surgical tool is present in at least one of the processed images while the surgical tool is present in a surgical space associated with the potential malignancy; and

in response to the detecting,

altering the at least one graphical overlay from the at least one of the processed images, wherein the altering of at least one graphical overlay enables the at least one graphical overlay to be removed while the surgical tool is being detected, and

displaying an indicator when the at least one graphical overlay is displayed for less than a threshold amount of time.

15. The method of claim 14 , wherein the set of processed images that are displayed include at least one visual indicator that indicates the set of processed images correspond to spatially arranged image data that has been processed by at least one processor.

16. The method of claim 14 , further comprising:

causing the display unit to display an indicator that indicates a potential malignancy has been identified in a previously displayed processed image that did not include a graphical overlay isolating one or more image locations corresponding to that potential malignancy.

17. The method of claim 14 , wherein the at least one graphical overlay represents the location of the potential malignancy in the individual, wherein the indicator is configured for being displayed in at least one of the set of processed images after the at least one graphical overlay representing the location of the potential malignancy in the individual are no longer being displayed.

18. The method of claim 14 , further comprising:

detecting, from the spatially arranged image data associated with a plurality of images from an imaging device, patient identifying information; and

obscuring, from the spatially arranged image data associated with a plurality of images from an imaging device, the patient identifying information.

19. The method of claim 14 , further comprising:

padding an input volume that includes the one or more pixels of the spatially arranged image data representing a location of a potential malignancy in an individual; and

controlling, based on padding the input volume, a spatial size of an object included in a graphical overlay of the one or graphic overlays, the object being associated with the location of a potential malignancy in an individual.

20. The method of claim 14 , further comprising:

causing the at least one graphical overlay to be displayed for at least a threshold amount of time for smoothing display of the graphical overlay.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 29, 2024
From: NG, JONATHAN; PHILLIPS, SLOANE ALLEBES; RANADE, AMIT; WANG, DANIEL; JAVIA, PERIKUMAR MUKUNDBHAI; WALDEN, AVI; WANG, AUSTIN; WLODKOWSKI, EVAN; DHAKAL, SAMRIDDHI
To: ITERATIVE SCOPES, INC.
Reel/Frame 066945/0879 →
Continuity (2)
Continuation 16934777 · Jul 21, 2020
Related Publication 20240296561A1 · Sep 5, 2024
References Cited (18)
US 10510144B2 · Zur · 2019 [cited by applicant]
US 10639104B1 · Barral et al. · 2020 [cited by applicant]
US 10810460B2 · Dinh et al. · 2020 [cited by applicant]
US 11100633B2 · Dinh et al. · 2021 [cited by applicant]
US 11195052B2 · Dinh et al. · 2021 [cited by applicant]
US 11961225B2 · Ng et al. · 2024 [cited by applicant]
US 20180253839A1 · Zur · 2018 [cited by applicant]
US 20180353244A1 · Kashima · 2018 [cited by examiner]
US 20190026608A1 · Hsieh et al. · 2019 [cited by applicant]
US 20190200977A1 · Shelton et al. · 2019 [cited by applicant]
US 20190297276A1 · Sachdev · 2019 [cited by examiner]
US 20200380675A1 · Golden et al. · 2020 [cited by applicant]
US 20210012868A1 · Wolf et al. · 2021 [cited by applicant]
US 20210274999A1 · Kubota · 2021 [cited by examiner]
US 20220028059A1 · Ng et al. · 2022 [cited by applicant]
Klare et al., “Automated polyp detection in the colorectum: a prospective study (with videos),” Gastrointestinal Endoscopy, Mar. 2019, 89(3):576-582. [cited by applicant]
Stidham et al., “Performance of a Deep Learning Model vs Human Reviewers in Grading Endoscopic Disease Severity of Patients With Ulcerative Colitis,” JAMA Network Open, May 2019, 2(5):e193963, 10 pages. [cited by applicant]
Takenaka et al., “Development and Validation of a Deep Neural Network for Accurate Evaluation of Endoscopic Images From Patients with Ulcerative Colitis,” Gastroenterology, Jun. 2020, 158(8):2150-2157. [cited by applicant]