Diagnosis support system, diagnosis support method, and storage medium
Inventors
Kubota, Akihiro • Kanda, Yamato • Taniguchi, Katsuyoshi • TAKABATAKE, Naohisa • Kono, Takashi
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12579795-B2
Publication Date
2026-03-17
Expiration Date
Abstract
A diagnosis support system includes a processor. The processor is connected to a plurality of classifiers that are different in performance. The processor displays performance information of each of the classifiers side by side, receives a user's selection of the performance information displayed side by side, and inputs an input image to the classifier associated with the performance information selected by the user.
Core Innovation
A diagnosis support system includes a processor connected to a plurality of classifier candidates different in performance. The processor applies the plurality of classifier candidates to a first input image that is an in-vivo image to obtain performance information corresponding to each classifier candidate, and the performance information includes comparison information indicating differences in performance among the plurality of classifier candidates based on detection of a region of interest in the in-vivo image.
The system displays the performance information of each of the plurality of classifier candidates side by side and receives a user selection of the displayed performance information. Based on the user's selection, the system inputs a second input image to a corresponding one of the plurality of classifier candidates, where the corresponding classifier candidate is associated with the performance information selected by the user.
The system outputs a detection result of the classifier selected by the user's selection. The disclosed approach also relates to generating classifier candidates including an original classifier candidate and a customized classifier candidate, where classifier candidates can differ in learning data, model architecture, and pre-processing and post-processing. Multiple user interface and performance-information display modes are described, including side-by-side performance presentation and performance information presentation related to regions of interest and detection results.
Claims Coverage
The document provides three independent claims: clm-00001, clm-00024, and clm-00025. Across these independent claims, there are five main inventive feature themes: applying multiple classifier candidates to a first in-vivo image to generate comparison-based performance information, displaying the performance information side by side, receiving a user selection, applying the selected candidate to a second in-vivo image, and outputting a detection result associated with the selected performance.
Multiple classifier candidates with performance comparison on ROI
Applying the plurality of classifier candidates to a first input image to obtain performance information corresponding to each of the plurality of classifier candidates, the first input image being an in-vivo image, wherein the performance information includes comparison information indicating differences in performance among the plurality of classifier candidates based on detection of a region of interest in the in-vivo image.
Side-by-side display of candidate performance information
Displaying the performance information of each of the plurality of classifier candidates side by side.
User selection to choose a classifier output target
Receiving a user's selection of the performance information displayed side by side; and receiving a user's selection for selecting at least one of the plurality of classifier candidates as a classifier serving as an output target.
Apply selected classifier to second in-vivo input and output detection result
Based on the user's selection, input a second input image to a corresponding one of the plurality of classifier candidates, the corresponding one of the plurality of classifier candidates being associated with the performance information selected by the user; and outputting a detection result of the classifier selected by the user's selection.
Tradeoff performance types displayed
The displaying including presenting at least two types of performance that are in a tradeoff relationship as the performance information.
Non-transitory computer-readable storage medium for implementing diagnosis support
A non-transitory computer-readable storage medium storing a diagnosis support program that causes a computer to implement: applying a plurality of classifier candidates to a first input image to obtain performance information corresponding to each of the plurality of classifier candidates, the first input image being an in-vivo image; displaying the performance information of each of the plurality of classifier candidates side by side; receiving a user's selection for selecting at least one of the plurality of classifier candidates as a classifier serving as an output target; based on the user's selection, input a second input image to a corresponding one of the plurality of classifier candidates; and outputting a detection result of the classifier candidate selected by the user's selection.
Across the independent claims, the core coverage is the same interactive workflow: multiple classifier candidates with different performance are evaluated on a first in-vivo image with comparison-based performance information based on detection of a region of interest, the performance information is displayed side by side, a user selection is received, and a corresponding selected classifier is applied to a second input image to output a detection result. One independent claim further specifies that the displayed performance information includes at least two performance types in a tradeoff relationship.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?