Endoscopic Device Real-Time Gastric Lesion Diagnosis Using AI
Summary
Korean researchers Bum-Joo Cho, Chang Seok Bang, Se Woo Park, Jae-Jun Lee, and Jae-Ho Choi filed USPTO Application US20260108133A1 on April 23, 2026, for an endoscopic device using artificial neural networks to diagnose gastric lesions from real-time gastroendoscopic images. The device builds and trains neural networks on gastric lesion image datasets linked with patient information to provide real-time lesion diagnosis during endoscopy. Medical device manufacturers and healthcare providers performing endoscopic procedures may find this relevant for understanding emerging AI applications in diagnostic endoscopy.
About this source
GovPing monitors USPTO Patent Applications - Health Informatics (G16H) for new healthcare & life sciences regulatory changes. Every update since tracking began is archived, classified, and available as free RSS or email alerts — 169 changes logged to date.
What changed
The published application describes a medical device that uses artificial neural networks to analyze gastroendoscopic images in real-time for gastric lesion diagnosis. The system includes a body part insertable into a patient's body, an operation part for user manipulation, a lesion diagnostic part that trains neural networks on gastric lesion images and diagnostic results, and a display showing real-time diagnostic outputs alongside acquired images. The lesion diagnostic part also generates new datasets by linking real-time gastroendoscopic images with patient information.
Medical device manufacturers developing AI-assisted diagnostic equipment and healthcare providers performing endoscopic procedures may find this relevant for understanding the scope of emerging AI patent claims in diagnostic endoscopy. The filing date of September 25, 2019 indicates this technology has been in development for several years.
Archived snapshot
Apr 24, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
ENDOSCOPIC DEVICE AND METHOD FOR DIAGNOSING GASTRIC LESION BASED ON GASTROENDOSCOPIC IMAGES ACQUIRED IN REAL TIME
Application US20260108133A1 Kind: A1 Apr 23, 2026
Inventors
Bum-Joo CHO, Chang Seok BANG, Se Woo PARK, Jae-Jun LEE, Jae-Ho CHOI
Abstract
An endoscopic device for diagnosing a gastric lesion from gastroendoscopic images acquired in real time is provided. The endoscopic device includes: a body part containing a plurality of units, that is inserted into a patient's body; an operation part provided on the rear end of the body part, for manipulating the body part based on user input information; a lesion diagnostic part that builds an artificial neural network system by training the artificial neural network system by using a plurality of gastric lesion images as input and gastric lesion diagnostic results as output, generates a new dataset by linking new gastroendoscopic images acquired in real time with patient information, and performs a gastric lesion diagnosis through the built artificial neural network system; and a display that shows the diagnostic results of the lesion diagnostic part and the new gastroendoscopic images acquired in real time.
CPC Classifications
A61B 1/000094 A61B 1/00045 G06T 7/0012 G16H 50/20 G06T 2207/20081 G06T 2207/30092
Filing Date
2019-09-25
Application No.
17278983
Mentioned entities
Related changes
Get daily alerts for USPTO Patent Applications - Health Informatics (G16H)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Health Informatics (G16H) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.