Performance of a deep learning-based identification system for esophageal cancer from CT images

• Published in: Esophagus : official journal of the Japan Esophageal Society 2021-07, Vol.18 (3), p.612-620
• Main Authors: Takeuchi, Masashi, Seto, Takumi, Hashimoto, Masahiro, Ichihara, Nao, Morimoto, Yosuke, Kawakubo, Hirofumi, Suzuki, Tatsuya, Jinzaki, Masahiro, Kitagawa, Yuko, Miyata, Hiroaki, Sakakibara, Yasubumi
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial Intelligence; Deep Learning; Esophageal cancer; Esophageal Neoplasms - diagnostic imaging; Esophagus; Gastroenterology; Humans; Medical diagnosis; Medicine; Medicine & Public Health; Neural networks; Original Article; Retrospective Studies; Surgical Oncology; Thoracic Surgery; Tomography, X-Ray Computed - methods
• ISSN: 1612-9059; 1612-9067
• DOI: 10.1007/s10388-021-00826-0

Background Because cancers of hollow organs such as the esophagus are hard to detect even by the expert physician, it is important to establish diagnostic systems to support physicians and increase the accuracy of diagnosis. In recent years, deep learning-based artificial intelligence (AI) technology has been employed for medical image recognition. However, no optimal CT diagnostic system employing deep learning technology has been attempted and established for esophageal cancer so far. Purpose To establish an AI-based diagnostic system for esophageal cancer from CT images. Materials and methods In this single-center, retrospective cohort study, 457 patients with primary esophageal cancer referred to our division between 2005 and 2018 were enrolled. We fine-tuned VGG16, an image recognition model of deep learning convolutional neural network (CNN), for the detection of esophageal cancer. We evaluated the diagnostic accuracy of the CNN using a test data set including 46 cancerous CT images and 100 non-cancerous images and compared it to that of two radiologists. Results Pre-treatment esophageal cancer stages of the patients included in the test data set were clinical T1 (12 patients), clinical T2 (9 patients), clinical T3 (20 patients), and clinical T4 (5 patients). The CNN-based system showed a diagnostic accuracy of 84.2%, F value of 0.742, sensitivity of 71.7%, and specificity of 90.0%. Conclusions Our AI-based diagnostic system succeeded in detecting esophageal cancer with high accuracy. More training with vast datasets collected from multiples centers would lead to even higher diagnostic accuracy and aid better decision making.