Accuracy of convolutional neural network-based artificial intelligence in diagnosis of gastrointestinal lesions based on endoscopic images: A systematic review and meta-analysis

Mohan, Babu P.; Khan, Shahab R.; Kassab, Lena L.; Ponnada, Suresh; Dulai, Parambir S.; Kochhar, Gursimran

doi:10.1055/a-1236-3007

Cited by 15 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this meta‐analysis, the application of AI in the diagnosis of OSCC comprehensively achieved pooled AUROC of 97%, pooled sensitivity of 95% and pooled specificity of 92%. These results are in keeping with those of previous meta‐analyses, 9 , 10 , 64 , 65 , 66 in which AI showed good performance in the diagnosis of OSCC, BE‐related or gastric adenocarcinoma and colorectal lesions.…”

Section: Discussionsupporting

confidence: 91%

Systematic review with meta‐analysis: artificial intelligence in the diagnosis of oesophageal diseases

Visaggi

Barberio

Gregori

et al. 2022

Aliment Pharmacol Ther

View full text Add to dashboard Cite

Summary Background Artificial intelligence (AI) has recently been applied to endoscopy and questionnaires for the evaluation of oesophageal diseases (ODs). Aim We performed a systematic review with meta‐analysis to evaluate the performance of AI in the diagnosis of malignant and benign OD. Methods We searched MEDLINE, EMBASE, EMBASE Classic and the Cochrane Library. A bivariate random‐effect model was used to calculate pooled diagnostic efficacy of AI models and endoscopists. The reference tests were histology for neoplasms and the clinical and instrumental diagnosis for gastro‐oesophageal reflux disease (GERD). The pooled area under the summary receiver operating characteristic (AUROC), sensitivity, specificity, positive and negative likelihood ratio (PLR and NLR) and diagnostic odds ratio (DOR) were estimated. Results For the diagnosis of Barrett's neoplasia, AI had AUROC of 0.90, sensitivity 0.89, specificity 0.86, PLR 6.50, NLR 0.13 and DOR 50.53. AI models’ performance was comparable with that of endoscopists (P = 0.35). For the diagnosis of oesophageal squamous cell carcinoma, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.97, 0.95, 0.92, 12.65, 0.05 and DOR 258.36, respectively. In this task, AI performed better than endoscopists although without statistically significant differences. In the detection of abnormal intrapapillary capillary loops, the performance of AI was: AUROC 0.98, sensitivity 0.94, specificity 0.94, PLR 14.75, NLR 0.07 and DOR 225.83. For the diagnosis of GERD based on questionnaires, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.99, 0.97, 0.97, 38.26, 0.03 and 1159.6, respectively. Conclusions AI demonstrated high performance in the clinical and endoscopic diagnosis of OD.

show abstract

Section: Discussionsupporting

confidence: 91%

Systematic review with meta‐analysis: artificial intelligence in the diagnosis of oesophageal diseases

Visaggi

Barberio

Gregori

et al. 2022

Aliment Pharmacol Ther

View full text Add to dashboard Cite

show abstract

“…In recent years, CAD tools are providing an interpretable universal method for endoscopic diagnosis, virtually eliminating variability among observers. Recent metaanalyses [72][73][74][75] confirmed the potential of AI to increase the diagnostic yield and reduce underdiagnosis of upper GI neoplastic lesions, often performing comparably or better than expert endoscopists. However, most studies on CAD tools were retrospective and tested the diagnostic yield of AI on endoscopic images rather than during live EGDS.…”

Section: Discussionmentioning

confidence: 99%

Modern Diagnosis of Early Esophageal Cancer: From Blood Biomarkers to Advanced Endoscopy and Artificial Intelligence

Visaggi

Barberio

Ghisa

et al. 2021

Cancers

View full text Add to dashboard Cite

Esophageal cancer (EC) is the seventh most common cancer and the sixth cause of cancer death worldwide. Histologically, esophageal squamous cell carcinoma (ESCC) and esophageal adenocarcinoma (EAC) account for up to 90% and 20% of all ECs, respectively. Clinical symptoms such as dysphagia, odynophagia, and bolus impaction occur late in the natural history of the disease, and the diagnosis is often delayed. The prognosis of ESCC and EAC is poor in advanced stages, being survival rates less than 20% at five years. However, when the diagnosis is achieved early, curative treatment is possible, and survival exceeds 80%. For these reasons, mass screening strategies for EC are highly desirable, and several options are currently under investigation. Blood biomarkers offer an inexpensive, non-invasive screening strategy for cancers, and novel technologies have allowed the identification of candidate markers for EC. The esophagus is easily accessible via endoscopy, and endoscopic imaging represents the gold standard for cancer surveillance. However, lesion recognition during endoscopic procedures is hampered by interobserver variability. To fill this gap, artificial intelligence (AI) has recently been explored and provided encouraging results. In this review, we provide a summary of currently available options to achieve early diagnosis of EC, focusing on blood biomarkers, advanced endoscopy, and AI.

show abstract

“…However, due to insufficient data they could not compare the effectiveness of computer‐aided algorithms with that of endoscopic physicians. In another meta‐analysis 36 the metrics of pooled sensitivity, specificity, PLR, NLR, DOR and AUROC for AI could not be obtained due to significant heterogeneity of the included studies and those based on SVM were excluded. One study 34 concluded that the use of NBI resulted in a higher AUROC of the AI models than the use of WLI in the diagnosis of ESCC, while in our study we found no statistical difference in AUROC between the use of WLI and NBI.…”

Section: Discussionmentioning

confidence: 99%

Accuracy of artificial intelligence‐assisted detection of esophageal cancer and neoplasms on endoscopic images: A systematic review and meta‐analysis

Zhang

Wang

Zhang

2021

J of Digest Diseases

View full text Add to dashboard Cite

To investigate systematically previous studies on the accuracy of artificial intelligence (AI)-assisted diagnostic models in detecting esophageal neoplasms on endoscopic images so as to provide scientific evidence for the effectiveness of these models.Methods: A literature search was conducted on the PubMed, EMBASE and Cochrane Library databases for studies on the AI-assisted detection of esophageal neoplasms on endoscopic images published up to December 2020. A bivariate mixed-effects regression model was used to calculate the pooled diagnostic efficacy of AI-assisted system. Subgroup analyses and meta-regression analyses were performed to explore the sources of heterogeneity. The effectiveness of AI-assisted models was also compared with that of the endoscopists.Results: Sixteen studies were included in the systematic review and meta-analysis.The pooled sensitivity, specificity, positive and negative likelihood ratios, diagnostic odds ratio and area under the summary receiver operating characteristic curve regarding AI-assisted detection of esophageal neoplasms were 94% (95% confidence interval [CI] 92%-96%), 85% (95% CI 73%-92%), 6.40 (95% CI 3.38-12.11), 0.06 (95% CI 0.04-0.10), 98.88 (95% CI 39.45-247.87) and 0.97 (95% CI 0.95-0.98), respectively. AI-based models performed better than endoscopists in terms of the pooled sensitivity (94% [95% CI 84%-98%] vs 82% [95% CI 77%-86%, P < 0.01). Conclusions:The use of AI results in increased accuracy in detecting early esophageal cancer. However, most of the included studies have a retrospective study design, thus further validation with prospective trials is required.

show abstract

Accuracy of convolutional neural network-based artificial intelligence in diagnosis of gastrointestinal lesions based on endoscopic images: A systematic review and meta-analysis

Cited by 15 publications

References 29 publications

Systematic review with meta‐analysis: artificial intelligence in the diagnosis of oesophageal diseases

Systematic review with meta‐analysis: artificial intelligence in the diagnosis of oesophageal diseases

Modern Diagnosis of Early Esophageal Cancer: From Blood Biomarkers to Advanced Endoscopy and Artificial Intelligence

Accuracy of artificial intelligence‐assisted detection of esophageal cancer and neoplasms on endoscopic images: A systematic review and meta‐analysis

Contact Info

Product

Resources

About