Deep convolutional neural network-based anomaly detection for organ classification in gastric X-ray examination

• Published in: Computers in biology and medicine Vol. 123; p. 103903
• Main Authors: Togo, Ren, Watanabe, Haruna, Ogawa, Takahiro, Haseyama, Miki
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.08.2020; Elsevier Limited
• Subjects: Anomalies; Anomaly detection; Artificial neural networks; Autoencoder; Classification; Deep learning; Esophagus; Gastric X-ray examination; Internal Medicine; Medical image analysis; Neural networks; Other; Probabilistic models; Stomach; Support vector machines; Deep learning; Stomach; Autoencoder; Medical image analysis; Gastric X-ray examination; Anomaly detection; Esophagus
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2020.103903

The aim of this study was to determine whether our deep convolutional neural network-based anomaly detection model can distinguish differences in esophagus images and stomach images obtained from gastric X-ray examinations. A total of 6012 subjects were analyzed as our study subjects. Since the number of esophagus X-ray images is much smaller than the number of gastric X-ray images taken in X-ray examinations, we took an anomaly detection approach to realize the task of organ classification. We constructed a deep autoencoding gaussian mixture model (DAGMM) with a convolutional autoencoder architecture. The trained model can produce an anomaly score for a given test X-ray image. For comparison, the original DAGMM, AnoGAN, and a One-Class Support Vector Machine (OCSVM) that were trained with features obtained by a pre-trained Inception-v3 network were used. Sensitivity, specificity, and the calculated harmonic mean of the proposed method were 0.956, 0.980, and 0.968, respectively. Those of the original DAGMM were 0.932, 0.883, and 0.907, respectively. Those of AnoGAN were 0.835, 0.833, and 0.834, respectively, and those of OCSVM were 0.932, 0.935, and 0.934, respectively. Experimental results showed the effectiveness of the proposed method for an organ classification task. Our deep convolutional neural network-based anomaly detection model has shown the potential for clinical use in organ classification. [Display omitted] •A method for organ classification was proposed.•Our deep anomaly detection were effective for the organ classification task.•Our method contributes to the construction of datasets for training AI methods.