TY - GEN
T1 - Real-time Barrett's neoplasia characterization in NBI videos using an int8-based quantized neural network
AU - Kusters, Carolus H. J.
AU - Boers, Tim G. W.
AU - Jukema, Jelmer B.
AU - Jong, Martijn R.
AU - Fockens, Kiki N.
AU - de Groof, Albert J.
AU - Bergman, Jacques J.
AU - van der Sommen, Fons
AU - de With, Peter H. N.
N1 - Funding Information: We gratefully acknowledge the research support and equipment provided by Olympus Corp., Tokyo, Japan. Publisher Copyright: © 2023 SPIE.
PY - 2023
Y1 - 2023
N2 - Computer-Aided Diagnosis (CADx) systems for characterization of Narrow-Band Imaging (NBI) videos of suspected lesions in Barrett's Esophagus (BE) can assist endoscopists during endoscopic surveillance. The real clinical value and application of such CADx systems lies in real-time analysis of endoscopic videos inside the endoscopy suite, placing demands on robustness in decision making and insightful classification matching with the clinical opinions. In this paper, we propose a lightweight int8-based quantized neural network architecture supplemented with an efficient stability function on the output for real-time classification of NBI videos. The proposed int8-architecture has low-memory footprint (4.8 MB), enabling operation on a range of edge devices and even existing endoscopy equipment. Moreover, the stability function ensures robust inclusion of temporal information from the video to provide a continuously stable video classification. The algorithm is trained, validated and tested with a total of 3,799 images and 284 videos of in total 598 patients, collected from 7 international centers. Several stability functions are experimented with, some of them being clinically inspired by weighing low-confidence predictions. For the detection of early BE neoplasia, the proposed algorithm achieves a performance of 92.8% accuracy, 95.7% sensitivity, and 91.4% specificity, while only 5.6% of the videos are without a final video classification. This work shows a robust, lightweight and effective deep learning-based CADx system for accurate automated real-time endoscopic video analysis, suited for embedding in endoscopy clinical practice.
AB - Computer-Aided Diagnosis (CADx) systems for characterization of Narrow-Band Imaging (NBI) videos of suspected lesions in Barrett's Esophagus (BE) can assist endoscopists during endoscopic surveillance. The real clinical value and application of such CADx systems lies in real-time analysis of endoscopic videos inside the endoscopy suite, placing demands on robustness in decision making and insightful classification matching with the clinical opinions. In this paper, we propose a lightweight int8-based quantized neural network architecture supplemented with an efficient stability function on the output for real-time classification of NBI videos. The proposed int8-architecture has low-memory footprint (4.8 MB), enabling operation on a range of edge devices and even existing endoscopy equipment. Moreover, the stability function ensures robust inclusion of temporal information from the video to provide a continuously stable video classification. The algorithm is trained, validated and tested with a total of 3,799 images and 284 videos of in total 598 patients, collected from 7 international centers. Several stability functions are experimented with, some of them being clinically inspired by weighing low-confidence predictions. For the detection of early BE neoplasia, the proposed algorithm achieves a performance of 92.8% accuracy, 95.7% sensitivity, and 91.4% specificity, while only 5.6% of the videos are without a final video classification. This work shows a robust, lightweight and effective deep learning-based CADx system for accurate automated real-time endoscopic video analysis, suited for embedding in endoscopy clinical practice.
KW - Barrett's Esophagus
KW - Narrow-Band Imaging
KW - Quantized Neural Networks
KW - Video Analysis
UR - http://www.scopus.com/inward/record.url?scp=85160212367&partnerID=8YFLogxK
U2 - https://doi.org/10.1117/12.2647557
DO - https://doi.org/10.1117/12.2647557
M3 - Conference contribution
VL - 12465
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2023
A2 - Iftekharuddin, Khan M.
A2 - Chen, Weijie
PB - SPIE
T2 - Medical Imaging 2023: Computer-Aided Diagnosis
Y2 - 19 February 2023 through 23 February 2023
ER -