Performance of artificial intelligence in the characterization of colorectal lesions
Background: Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Medknow Publications
2023-01-01
|
| Series: | The Saudi Journal of Gastroenterology |
| Subjects: | |
| Online Access: | http://www.saudijgastro.com/article.asp?issn=1319-3767;year=2023;volume=29;issue=4;spage=219;epage=224;aulast= |
| _version_ | 1797738480915185664 |
|---|---|
| author | Carlos E. O. Dos Santos Daniele Malaman Ivan D. Arciniegas Sanmartin Ari B. S. Leão Gabriel S Leão Júlio C Pereira-Lima |
| author_facet | Carlos E. O. Dos Santos Daniele Malaman Ivan D. Arciniegas Sanmartin Ari B. S. Leão Gabriel S Leão Júlio C Pereira-Lima |
| author_sort | Carlos E. O. Dos Santos |
| collection | DOAJ |
| description | Background: Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorectal lesions and compare it with the performance of an expert, in addition to evaluating the computer-aided detection (CADe) mode in terms of polyp detection rate (PDR) and adenoma detection rate (ADR).
Methods: A prospective study was conducted to evaluate the performance of CAD EYE using blue light imaging (BLI), dichotomizing lesions into hyperplastic and neoplastic, and of an expert based on the Japan Narrow-Band Imaging Expert Team (JNET) classification for the characterization of lesions. After white light imaging (WLI) diagnosis, magnification was used on all lesions, which were removed and examined histologically. Diagnostic criteria were evaluated, and PDR and ADR were calculated.
Results: A total of 110 lesions (80 (72.7%) dysplastic lesions and 30 (27.3%) nondysplastic lesions) were evaluated in 52 patients, with a mean lesion size of 4.3 mm. Artificial intelligence (AI) analysis showed 81.8% accuracy, 76.3% sensitivity, 96.7% specificity, 98.5% positive predictive value (PPV), and 60.4% negative predictive value (NPV). The kappa value was 0.61, and the area under the receiver operating characteristic curve (AUC) was 0.87. Expert analysis showed 93.6% accuracy, 92.5% sensitivity, 96.7% specificity, 98.7% PPV, and 82.9% NPV. The kappa value was 0.85, and the AUC was 0.95. Overall, PDR was 67.6% and ADR was 45.9%.
Conclusions: The CADx mode showed good accuracy in characterizing colorectal lesions, but the expert assessment was superior in almost all diagnostic criteria. PDR and ADR were high. |
| first_indexed | 2024-03-12T13:43:27Z |
| format | Article |
| id | doaj.art-beb2d4608fc140beb05fadcf7e17d4e9 |
| institution | Directory Open Access Journal |
| issn | 1319-3767 1998-4049 |
| language | English |
| last_indexed | 2024-03-12T13:43:27Z |
| publishDate | 2023-01-01 |
| publisher | Wolters Kluwer Medknow Publications |
| record_format | Article |
| series | The Saudi Journal of Gastroenterology |
| spelling | doaj.art-beb2d4608fc140beb05fadcf7e17d4e92023-08-23T09:49:10ZengWolters Kluwer Medknow PublicationsThe Saudi Journal of Gastroenterology1319-37671998-40492023-01-0129421922410.4103/sjg.sjg_316_22Performance of artificial intelligence in the characterization of colorectal lesionsCarlos E. O. Dos SantosDaniele MalamanIvan D. Arciniegas SanmartinAri B. S. LeãoGabriel S LeãoJúlio C Pereira-LimaBackground: Image-enhanced endoscopy (IEE) has been used in the differentiation between neoplastic and non-neoplastic colorectal lesions through microvasculature analysis. This study aimed to evaluate the computer-aided diagnosis (CADx) mode of the CAD EYE system for the optical diagnosis of colorectal lesions and compare it with the performance of an expert, in addition to evaluating the computer-aided detection (CADe) mode in terms of polyp detection rate (PDR) and adenoma detection rate (ADR). Methods: A prospective study was conducted to evaluate the performance of CAD EYE using blue light imaging (BLI), dichotomizing lesions into hyperplastic and neoplastic, and of an expert based on the Japan Narrow-Band Imaging Expert Team (JNET) classification for the characterization of lesions. After white light imaging (WLI) diagnosis, magnification was used on all lesions, which were removed and examined histologically. Diagnostic criteria were evaluated, and PDR and ADR were calculated. Results: A total of 110 lesions (80 (72.7%) dysplastic lesions and 30 (27.3%) nondysplastic lesions) were evaluated in 52 patients, with a mean lesion size of 4.3 mm. Artificial intelligence (AI) analysis showed 81.8% accuracy, 76.3% sensitivity, 96.7% specificity, 98.5% positive predictive value (PPV), and 60.4% negative predictive value (NPV). The kappa value was 0.61, and the area under the receiver operating characteristic curve (AUC) was 0.87. Expert analysis showed 93.6% accuracy, 92.5% sensitivity, 96.7% specificity, 98.7% PPV, and 82.9% NPV. The kappa value was 0.85, and the AUC was 0.95. Overall, PDR was 67.6% and ADR was 45.9%. Conclusions: The CADx mode showed good accuracy in characterizing colorectal lesions, but the expert assessment was superior in almost all diagnostic criteria. PDR and ADR were high.http://www.saudijgastro.com/article.asp?issn=1319-3767;year=2023;volume=29;issue=4;spage=219;epage=224;aulast=adenomasartificial intelligencecolonic polypscolonoscopycomputer-assisted diagnosis |
| spellingShingle | Carlos E. O. Dos Santos Daniele Malaman Ivan D. Arciniegas Sanmartin Ari B. S. Leão Gabriel S Leão Júlio C Pereira-Lima Performance of artificial intelligence in the characterization of colorectal lesions The Saudi Journal of Gastroenterology adenomas artificial intelligence colonic polyps colonoscopy computer-assisted diagnosis |
| title | Performance of artificial intelligence in the characterization of colorectal lesions |
| title_full | Performance of artificial intelligence in the characterization of colorectal lesions |
| title_fullStr | Performance of artificial intelligence in the characterization of colorectal lesions |
| title_full_unstemmed | Performance of artificial intelligence in the characterization of colorectal lesions |
| title_short | Performance of artificial intelligence in the characterization of colorectal lesions |
| title_sort | performance of artificial intelligence in the characterization of colorectal lesions |
| topic | adenomas artificial intelligence colonic polyps colonoscopy computer-assisted diagnosis |
| url | http://www.saudijgastro.com/article.asp?issn=1319-3767;year=2023;volume=29;issue=4;spage=219;epage=224;aulast= |
| work_keys_str_mv | AT carloseodossantos performanceofartificialintelligenceinthecharacterizationofcolorectallesions AT danielemalaman performanceofartificialintelligenceinthecharacterizationofcolorectallesions AT ivandarciniegassanmartin performanceofartificialintelligenceinthecharacterizationofcolorectallesions AT aribsleao performanceofartificialintelligenceinthecharacterizationofcolorectallesions AT gabrielsleao performanceofartificialintelligenceinthecharacterizationofcolorectallesions AT juliocpereiralima performanceofartificialintelligenceinthecharacterizationofcolorectallesions |