Development and validation of artificial neural networks model for detection of Barrett’s neoplasia: a multicenter pragmatic nonrandomized trial (with video) - 18/02/23
Abstract |
Background and aims |
The aim of this study was to develop and externally validate a computer-aided detection (CAD) system for the detection and localization of Barrett’s neoplasia and assess its performance compared with that of general endoscopists in a statistically powered multicenter study by using real-time video sequences.
Methods |
In phase 1, the hybrid visual geometry group 16-SegNet model was trained by the use of 75,198 images and videos (96 patients) of neoplastic and 1,014,973 images and videos (65 patients) of nonneoplastic Barrett’s esophagus. In phase 2, image-based validation was performed on a separate dataset of 107 images (20 patients) of neoplastic and 364 images (14 patients) of nonneoplastic Barrett’s esophagus. In phase 3 (video-based external validation) we designed a real-time video-based study with 32 videos (32 patients) of neoplastic and 43 videos (43 patients) of nonneoplastic Barrett’s esophagus from 4 European centers to compare the performance of the CAD model with that of 6 nonexpert endoscopists. The primary endpoint was the sensitivity of CAD diagnosis of Barrett’s neoplasia.
Results |
In phase 2, CAD detected Barrett’s neoplasia with sensitivity, specificity, and accuracy of 95.3%, 94.5%, and 94.7%, respectively. In phase 3, the CAD system detected Barrett’s neoplasia with sensitivity, specificity, negative predictive value, and accuracy of 93.8%, 90.7%, 95.1%, and 92.0%, respectively, compared with the endoscopists’ performance of 63.5%, 77.9%, 74.2%, and 71.8%, respectively (P < .05 in all parameters). The CAD system localized neoplastic lesions with accuracy, mean precision, and mean intersection over union of 100%, 0.62, and 0.54, respectively, when compared with at least 1 of the expert markings. The processing speed of the CAD detection and localization were 5 ms/image and 33 ms/image, respectively.
Conclusion |
To our knowledge, this is the first study describing external (multicenter) validation of AI algorithms for the detection of Barrett’s neoplasia on real-time endoscopic videos. The CAD system in this study significantly outperformed nonexpert endoscopists on real-time video-based assessment, achieving >90% sensitivity for neoplasia detection. This result needs to be validated during real-time endoscopic assessment.
Il testo completo di questo articolo è disponibile in PDF.Abbreviations : AI, ASGE, CADe, CNN, HGD, IoU, LGD, NPV, WLI
Mappa
| DISCLOSURE: This investigator-initiated study was funded by NEC Japan. M. Saiko is an AI researcher employed by NEC Japan. N. Maeda is an AI scientist employed by NEC Japan. The remaining authors disclosed no financial relationships. |
Vol 97 - N° 3
P. 422-434 - marzo 2023 Ritorno al numero
Articolo precedente
- Early (<4 weeks) versus standard (≥4 weeks) endoscopic drainage of pancreatic walled-off fluid collections: a systematic review and meta-analysis
- Daryl Ramai, Ikponmwosa Enofe, Smit S. Deliwala, Daniel Mozell, Antonio Facciorusso, Paraskevas Gkolfakis, Babu P. Mohan, Saurabh Chandan, Melissa Previtera, Marcello Maida, Andrea Anderloni, Douglas G. Adler, Andrew Ofosu
- Development and validation of a machine learning–based model for varices screening in compensated cirrhosis (CHESS2001): an international multicenter study
- Yifei Huang, Jia Li, Tianlei Zheng, Dong Ji, Yu Jun Wong, Hong You, Ye Gu, Musong Li, Lili Zhao, Shuang Li, Shi Geng, Na Yang, Guofeng Chen, Yan Wang, Manoj Kumar, Ankur Jindal, Wei Qin, Zhenhuai Chen, Yongning Xin, Zicheng Jiang, Xiaoling Chi, Jilin Cheng, Mingxin Zhang, Huan Liu, Ming Lu, Li Li, Yong Zhang, Chunwen Pu, Deqiang Ma, Qibin He, Shanhong Tang, Chunyan Wang, Shanghao Liu, Jitao Wang, Yanna Liu, Chuan Liu, Hao Liu, Shiv Kumar Sarin
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.
Già abbonato a @@106933@@ rivista ?