Keisuke Kawauchi1, Sho Furuya2,3, Kenji Hirata4,5, Chietsugu Katoh1,6, Osamu Manabe2,3, Kentaro Kobayashi2, Shiro Watanabe2, Tohru Shiga2,3. 1. Graduate School of Biomedical Science and Engineering, School of Medicine, Hokkaido University, N15 W7, Kita-ku, Sapporo, 0608638, Japan. 2. Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, N15 W7, Kita-ku, Sapporo, 0608638, Japan. 3. Department of Nuclear Medicine, Hokkaido University Hospital, N15 W7, Kita-ku, Sapporo, Hokkaido, 0608638, Japan. 4. Department of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, N15 W7, Kita-ku, Sapporo, 0608638, Japan. khirata@med.hokudai.ac.jp. 5. Department of Nuclear Medicine, Hokkaido University Hospital, N15 W7, Kita-ku, Sapporo, Hokkaido, 0608638, Japan. khirata@med.hokudai.ac.jp. 6. Faculty of Health Sciences Biomedical Science and Engineering, Hokkaido University, N15 W7, Kita-ku, Sapporo, 0608638, Japan.
Abstract
BACKGROUND: As the number of PET/CT scanners increases and FDG PET/CT becomes a common imaging modality for oncology, the demands for automated detection systems on artificial intelligence (AI) to prevent human oversight and misdiagnosis are rapidly growing. We aimed to develop a convolutional neural network (CNN)-based system that can classify whole-body FDG PET as 1) benign, 2) malignant or 3) equivocal. METHODS: This retrospective study investigated 3485 sequential patients with malignant or suspected malignant disease, who underwent whole-body FDG PET/CT at our institute. All the cases were classified into the 3 categories by a nuclear medicine physician. A residual network (ResNet)-based CNN architecture was built for classifying patients into the 3 categories. In addition, we performed a region-based analysis of CNN (head-and-neck, chest, abdomen, and pelvic region). RESULTS: There were 1280 (37%), 1450 (42%), and 755 (22%) patients classified as benign, malignant and equivocal, respectively. In the patient-based analysis, CNN predicted benign, malignant and equivocal images with 99.4, 99.4, and 87.5% accuracy, respectively. In region-based analysis, the prediction was correct with the probability of 97.3% (head-and-neck), 96.6% (chest), 92.8% (abdomen) and 99.6% (pelvic region), respectively. CONCLUSION: The CNN-based system reliably classified FDG PET images into 3 categories, indicating that it could be helpful for physicians as a double-checking system to prevent oversight and misdiagnosis.
BACKGROUND: As the number of PET/CT scanners increases and FDG PET/CT becomes a common imaging modality for oncology, the demands for automated detection systems on artificial intelligence (AI) to prevent human oversight and misdiagnosis are rapidly growing. We aimed to develop a convolutional neural network (CNN)-based system that can classify whole-body FDG PET as 1) benign, 2) malignant or 3) equivocal. METHODS: This retrospective study investigated 3485 sequential patients with malignant or suspected malignant disease, who underwent whole-body FDG PET/CT at our institute. All the cases were classified into the 3 categories by a nuclear medicine physician. A residual network (ResNet)-based CNN architecture was built for classifying patients into the 3 categories. In addition, we performed a region-based analysis of CNN (head-and-neck, chest, abdomen, and pelvic region). RESULTS: There were 1280 (37%), 1450 (42%), and 755 (22%) patients classified as benign, malignant and equivocal, respectively. In the patient-based analysis, CNN predicted benign, malignant and equivocal images with 99.4, 99.4, and 87.5% accuracy, respectively. In region-based analysis, the prediction was correct with the probability of 97.3% (head-and-neck), 96.6% (chest), 92.8% (abdomen) and 99.6% (pelvic region), respectively. CONCLUSION: The CNN-based system reliably classified FDG PET images into 3 categories, indicating that it could be helpful for physicians as a double-checking system to prevent oversight and misdiagnosis.
Entities:
Keywords:
Convolutional neural network; Deep learning; FDG; PET
Authors: Clifford Silver Tarimo; Soumitra S Bhuyan; Quanman Li; Michael Johnson J Mahande; Jian Wu; Xiaoli Fu Journal: BMJ Open Date: 2021-12-02 Impact factor: 3.006