Artificial intelligence for disease diagnosis: the criterion standard challenge

Mori, Yuichi; Misawa, Masashi; Bernal, Jorge; Bretthauer, Michael; Kudo, Shin‐ei; Rastogi, Amit; Fernández‐Esparrach, Glòria

doi:10.1016/j.gie.2022.04.057

Cited by 6 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We therefore proposed an unsupervised/semisupervised learning process that may solve the number of underlying practical issues for the development of a medical AI model. 28 This study has some limitations. First, our study had a single-center retrospective design, which limits the number of cases and the generalizability of the findings.…”

Section: Discussionmentioning

confidence: 91%

See 1 more Smart Citation

Whole slide image‐based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

Takashina

Kudo

Kouyama

et al. 2023

Digestive Endoscopy

Self Cite

View full text Add to dashboard Cite

ObjectivesLymph node metastasis (LNM) prediction for T1 colorectal cancer (CRC) is critical for determining the need for surgery after endoscopic resection because LNM occurs in 10%. We aimed to develop a novel artificial intelligence (AI) system using whole slide images (WSIs) to predict LNM.MethodsWe conducted a retrospective single center study. To train and test the AI model, we included LNM status‐confirmed T1 and T2 CRC between April 2001 and October 2021. These lesions were divided into two cohorts: training (T1 and T2) and testing (T1). WSIs were cropped into small patches and clustered by unsupervised K‐means. The percentage of patches belonging to each cluster was calculated from each WSI. Each cluster's percentage, sex, and tumor location were extracted and learned using the random forest algorithm. We calculated the areas under the receiver operating characteristic curves (AUCs) to identify the LNM and the rate of over‐surgery of the AI model and the guidelines.ResultsThe training cohort contained 217 T1 and 268 T2 CRCs, while 100 T1 cases (LNM‐positivity 15%) were the test cohort. The AUC of the AI system for the test cohort was 0.74 (95% confidence interval [CI] 0.58–0.86), and 0.52 (95% CI 0.50–0.55) using the guidelines criteria (P = 0.0028). This AI model could reduce the 21% of over‐surgery compared to the guidelines.ConclusionWe developed a pathologist‐independent predictive model for LNM in T1 CRC using WSI for determination of the need for surgery after endoscopic resection.Trial registrationUMIN Clinical Trials Registry (UMIN000046992, https://center6.umin.ac.jp/cgi-open-bin/ctr/ctr_view.cgi?recptno=R000053590).

show abstract

Section: Discussionmentioning

confidence: 91%

“…Second, it does not require any labeling processes to make a training dataset that requires tremendous effort. We therefore proposed an unsupervised/semisupervised learning process that may solve the number of underlying practical issues for the development of a medical AI model 28 …”

Section: Discussionmentioning

confidence: 99%

Whole slide image‐based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

Takashina

Kudo

Kouyama

et al. 2023

Digestive Endoscopy

Self Cite

View full text Add to dashboard Cite

show abstract

“…This complication may be caused by interobserver variability among pathologists. 34 To address this challenge, Mori et al 34 suggested a semisupervised machine-learning approach involving the labeling of polyps by consensus among two or more experts for a pathological diagnosis, whereas difficult polyps could be used in an unlabeled manner. The novel machine-learning approach could be a possible solution.…”

Section: Discussionmentioning

confidence: 99%

“…reported that their developed CADx showed a smaller area under the receiver operating characteristic curve (CADx vs. expert: 55% vs. 68–79%). This complication may be caused by interobserver variability among pathologists 34 . To address this challenge, Mori et al 34 .…”

Section: Discussionmentioning

confidence: 99%

Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study

Kato

Kudo

Minegishi

et al. 2023

Digestive Endoscopy

Self Cite

View full text Add to dashboard Cite

ObjectivesComputer‐aided characterization (CADx) may be used to implement optical biopsy strategies into colonoscopy practice; however, its impact on endoscopic diagnosis remains unknown. We aimed to evaluate the additional diagnostic value of CADx when used by endoscopists for assessing colorectal polyps.MethodsThis was a single‐center, multicase, multireader, image‐reading study using randomly extracted images of pathologically confirmed polyps resected between July 2021 and January 2022. Approved CADx that could predict two‐tier classification (neoplastic or nonneoplastic) by analyzing narrow‐band images of the polyps was used to obtain a CADx diagnosis. Participating endoscopists determined if the polyps were neoplastic or not and noted their confidence level using a computer‐based, image‐reading test. The test was conducted twice with a 4‐week interval: the first test was conducted without CADx prediction and the second test with CADx prediction. Diagnostic performances for neoplasms were calculated using the pathological diagnosis as reference and performances with and without CADx prediction were compared.ResultsFive hundred polyps were randomly extracted from 385 patients and diagnosed by 14 endoscopists (including seven experts). The sensitivity for neoplasia was significantly improved by referring to CADx (89.4% vs. 95.6%). CADx also had incremental effects on the negative predictive value (69.3% vs. 84.3%), overall accuracy (87.2% vs. 91.8%), and high‐confidence diagnosis rate (77.4% vs. 85.8%). However, there was no significant difference in specificity (80.1% vs. 78.9%).ConclusionsComputer‐aided characterization has added diagnostic value for differentiating colorectal neoplasms and may improve the high‐confidence diagnosis rate.

show abstract

Integrating Artificial Intelligence for Enhanced Tuberculosis Diagnosis and Management: A Comprehensive Analysis

Vyas,

Pratap Singh,

Dave

et al. 2024

Smart Healthcare and Machine Learning

View full text Add to dashboard Cite

Artificial intelligence for disease diagnosis: the criterion standard challenge

Cited by 6 publications

References 15 publications

Whole slide image‐based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

Whole slide image‐based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence

Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study

Integrating Artificial Intelligence for Enhanced Tuberculosis Diagnosis and Management: A Comprehensive Analysis

Contact Info

Product

Resources

About