Deep learning-based decision support system for the diagnosis of neoplastic gallbladder polyps on ultrasonography: Preliminary results

• Published in: Scientific reports 2020-05, Vol.10 (1), p.7700-7700, Article 7700
• Main Authors: Jeong, Younbeom, Kim, Jung Hoon, Chae, Hee-Dong, Park, Sae-Jin, Bae, Jae Seok, Joo, Ijin, Han, Joon Koo
• Format: Article
• Language: English
• Subjects: 692/4020/4021/1328/1498/1499; 692/4020/4021/44/1497; Correlation coefficient; Datasets; Decision support systems; Deep Learning; Differential diagnosis; Female; Gallbladder; Gallbladder - diagnostic imaging; Gallbladder - pathology; Gallbladder Neoplasms - diagnosis; Gallbladder Neoplasms - diagnostic imaging; Gallbladder Neoplasms - pathology; Humanities and Social Sciences; Humans; Male; Middle Aged; multidisciplinary; Neural networks; Polyps; Polyps - diagnosis; Polyps - diagnostic imaging; Polyps - pathology; Precancerous Conditions - diagnosis; Precancerous Conditions - diagnostic imaging; Precancerous Conditions - pathology; Retrospective Studies; Science; Science (multidisciplinary); Transfer learning; Ultrasonic imaging; Ultrasonography
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-020-64205-y

Ultrasonography (US) has been considered image of choice for gallbladder (GB) polyp, however, it had limitations in differentiating between nonneoplastic polyps and neoplastic polyps. We developed and investigated the usefulness of a deep learning-based decision support system (DL-DSS) for the differential diagnosis of GB polyps on US. We retrospectively collected 535 patients, and they were divided into the development dataset (n = 437) and test dataset (n = 98). The binary classification convolutional neural network model was developed by transfer learning. Using the test dataset, three radiologists with different experience levels retrospectively graded the possibility of a neoplastic polyp using a 5-point confidence scale. The reviewers were requested to re-evaluate their grades using the DL-DSS assistant. The areas under the curve (AUCs) of three reviewers were 0.94, 0.78, and 0.87. The DL-DSS alone showed an AUC of 0.92. With the DL-DSS assistant, the AUCs of the reviewer’s improved to 0.95, 0.91, and 0.91. Also, the specificity of the reviewers was improved (65.1–85.7 to 71.4–93.7). The intraclass correlation coefficient (ICC) improved from 0.87 to 0.93. In conclusion, DL-DSS could be used as an assistant tool to decrease the gap between reviewers and to reduce the false positive rate.