Deep Learning and Capsule Endoscopy: Automatic Panendoscopic Detection of Vascular Lesions

Aims Capsule endoscopy (CE) is commonly used as the initial exam in situations of suspected mid-gastrointestinal bleeding, after normal upper and lower endoscopy. Although the assessment of the small bowel is its primary focus, detection of upstream/downstream of vascular lesions may also be clinically significant. This study aimed to develop and test a Convolutional Neural Network (CNN)-based model for panendoscopic automatic detection of vascular lesions during CE. [1] [2] [3] [4] [5] [6] [7] [8] [9]

Methods A multicentric retrospective study was conducted, based on 1188 CE exams. We used a total of 152312 frames, from seven types of CE devices, of which 14942 had vascular lesions (angiectasia, varices) after triple validation. Data was divided in training/validation (90%) and test (10%) groups, in an exam-split design. We conducted a 5-fold cross validation, during training/validation set. This process was iterated five times. Main outcomes were sensitivity, specificity, accuracy, area under the conventional receiver operating characteristic curve (AUC-ROC) and the precision-recall curve (AUC-PR), from the training/validation phase.

Results Mean sensitivity and specificity were 87.5% (IC95% 81.5 – 93.6%) and 99.5% (IC95% 99.3 – 99.7%), respectively. Mean accuracy was 98.4% (IC95% 97.7 – 99.1%). Mean AUC-ROC value was 0.987 (IC95% 0.980 – 0.995), while AUC-PR value was 0.998 (IC95% 0.997 – 1.000).

Conclusions This is the first proof-of concept AI deep learning model developed for panendoscopic automatic detection of vascular lesions during CE. The high diagnostic performance of this CNN in multibrand devices addresses an important issue of technological interoperability, allowing it to be replicated in multiple technological settings.

Publication History

Article published online:
15 April 2024

• References

• 1 Mascarenhas M, Ribeiro T, Afonso J. et al. Deep learning and colon capsule endoscopy: automatic detection of blood and colonic mucosal lesions using a convolutional neural network. Endosc Int Open 2022; 10: E171-e177
• 2 Mascarenhas Saraiva M, Ferreira JPS, Cardoso H. et al. Artificial intelligence and colon capsule endoscopy: automatic detection of blood in colon capsule endoscopy using a convolutional neural network. Endosc Int Open 2021; 9: E1264-e1268
• 3 Ribeiro T, Saraiva MM, Ferreira JPS. et al. Artificial intelligence and capsule endoscopy: automatic detection of vascular lesions using a convolutional neural network. Ann Gastroenterol 2021; 34: 820-828
• 4 Leenhardt R, Vasseur P, Li C. et al. A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy. Gastrointest Endosc 2019; 89: 189-194
• 5 Cortegoso Valdivia P, Elosua A, Houdeville C. et al. Clinical feasibility of panintestinal (or panenteric) capsule endoscopy: a systematic review. Eur J Gastroenterol Hepatol 2021; 33: 949-955
• 6 Marmo R, Rotondano G, Rondonotti E. et al. Capsule enteroscopy vs. other diagnostic procedures in diagnosing obscure gastrointestinal bleeding: a cost-effectiveness study. Eur J Gastroenterol Hepatol 2007; 19: 535-542
• 7 Teshima CW, Kuipers EJ, van Zanten SV. et al. Double balloon enteroscopy and capsule endoscopy for obscure gastrointestinal bleeding: an updated meta-analysis. J Gastroenterol Hepatol 2011; 26: 796-801
• 8 Liao Z, Gao R, Xu C. et al. Indications and detection, completion, and retention rates of small-bowel capsule endoscopy: a systematic review. Gastrointest Endosc 2010; 71: 280-286
• 9 Triester SL, Leighton JA, Leontiadis GI. et al. A meta-analysis of the yield of capsule endoscopy compared to other diagnostic modalities in patients with obscure gastrointestinal bleeding. Am J Gastroenterol 2005; 100: 2407-2418