Deep-Learning-Enabled Computer-Aided Diagnosis in the Classification of Pancreatic Cystic Lesions on Confocal Laser Endomicroscopy

Abstract

Accurate classification of pancreatic cystic lesions (PCLs) is important to facilitate proper treatment and to improve patient outcomes. We utilized the convolutional neural network (CNN) of VGG19 to develop a computer-aided diagnosis (CAD) system in the classification of subtypes of PCLs in endoscopic ultrasound-guided needle-based confocal laser endomicroscopy (nCLE). From a retrospectively collected 22,424 nCLE video frames (50 videos) as the training/validation set and 11,047 nCLE video frames (18 videos) as the test set, we developed and compared the diagnostic performance of three CNNs with distinct methods of designating the region of interest. The diagnostic accuracy for subtypes of PCLs by CNNs with manual, maximal rectangular, and U-Net algorithm-designated ROIs was 100%, 38.9%, and 66.7% on a per-video basis and 88.99%, 73.94%, and 76.12% on a per-frame basis, respectively. Our per-frame analysis suggested differential levels of diagnostic accuracy among the five subtypes of PCLs, where non-mucinous PCLs (serous cystic neoplasm: 93.11%, cystic neuroendocrine tumor: 84.31%, and pseudocyst: 98%) had higher diagnostic accuracy than mucinous PCLs (intraductal papillary mucinous neoplasm: 84.43% and mucinous cystic neoplasm: 86.1%). Our CNN demonstrated superior specificity compared to the state-of-the-art for the classification of mucinous PCLs (IPMN and MCN), with high specificity (94.3% and 92.8%, respectively) but low sensitivity (46% and 45.2%, respectively). This suggests the complimentary role of CNN-enabled CAD systems, especially for clinically suspected mucinous PCLs.

The Multifaceted Role of Confocal Laser Endomicroscopy in Head and Neck Surgery: Oncologic and Functional Insights

“…They achieved high diagnostic accuracy for both CLE-based and histopathologic diagnosis of esophageal dysplasia and its precursors, similar to human accuracy [30]. Lee et al also advocate the use of deep learning models in evaluation of pancreatic cystic lesions (PCL) by CLE [31]. Aubreville et al presented a significantly improved overall performance of 94,8% using a model for deep learning-based detection of motion artifacts in CLE images [32].…”

Artificial intelligence assisted endoscopic ultrasound for detection of pancreatic space-occupying lesion: a systematic review and meta-analysis

“…Additionally, there is a lack of studies that perform external validation of the AI models used in the EUS of the pancreas. In the absence of external validation, there is a lack of assurance regarding the model’s generalizability, which may result in the possibility of overestimating the outcomes 27 , 28 , 40 . Efforts are underway to develop techniques and methods that enhance the reliability and interpretability of AI models, allowing technicians and clinicians to understand and trust the results generated by AI algorithms.…”

DenseNet model incorporating hybrid attention mechanisms and clinical features for pancreatic cystic tumor classification

“…In recent years, the development of computer technology and artificial intelligence has facilitated the application of radiomics and deep learning methods in the classification of pancreatic cystic tumors, [6][7][8][9] which provide a basis for detection and diagnosis in the clinic. Xie et al 10 extracted radiomics features based on CT images and demonstrated that the radiomics model had good performance in preoperative identification of MCN and SCN.…”