Akinori Hata1, Masahiro Yanagawa2, Kazuki Yamagata3, Yuuki Suzuki3, Shoji Kido3, Atsushi Kawata2, Shuhei Doi2, Yuriko Yoshida2, Tomo Miyata2, Mitsuko Tsubamoto4, Noriko Kikuchi2, Noriyuki Tomiyama2. 1. Department of Future Diagnostic Radiology, Graduate School of Medicine, Osaka University, 2-2 Yamadaoka, Suita, Osaka, 565-0871, Japan. a-hata@radiol.med.osaka-u.ac.jp. 2. Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka University, 2-2 Yamadaoka, Suita, Osaka, 565-0871, Japan. 3. Department of Artificial Intelligence Diagnostic Radiology, Graduate School of Medicine, Osaka University, 2-2 Yamadaoka, Suita, Osaka, 565-0871, Japan. 4. Department of Future Diagnostic Radiology, Graduate School of Medicine, Osaka University, 2-2 Yamadaoka, Suita, Osaka, 565-0871, Japan.
Abstract
OBJECTIVES: To develop a deep learning-based algorithm to detect aortic dissection (AD) and evaluate the diagnostic ability of the algorithm compared with those of radiologists. METHODS: Included in the study were 170 patients (85 with AD and 85 without AD). An AD detection algorithm was developed using a convolutional neural network with Xception architecture. Of the patient data, 80% were used for training and validation and 20% were used for testing. Fivefold cross-validation was performed to evaluate the method. An average of 6688 non-contrast-enhanced CT images (slice thickness, 5 mm) were used for training. A radiologist reviewed both contrast-enhanced and non-contrast-enhanced images and identified the slices of AD. The identified slices were used as ground truth. Receiver operating characteristic curve and area under the curve (AUC) analysis was performed. Five radiologists independently evaluated the images. The accuracy, sensitivity, and specificity of the algorithm and those of the radiologists were compared. RESULTS: The AUC of the developed algorithm was 0.940, and a cutoff value of 0.400 provided accuracy of 90.0%, sensitivity of 91.8%, and specificity of 88.2%. For the radiologists, median (range) accuracy, sensitivity, and specificity were 88.8 (83.5-94.1)%, 90.6 (83.5-94.1)%, and 94.1 (72.9-97.6)%, respectively. There was no significant difference in performance in terms of accuracy, sensitivity, or specificity between the algorithm and the average performance of the radiologists (p > 0.05). CONCLUSIONS: The developed algorithm showed comparable diagnostic performance to radiologists for detecting AD, which suggests the potential of the proposed method to support clinical practice by reducing missed ADs. KEY POINTS: • A deep learning-based algorithm for detecting aortic dissection was developed using the non-contrast-enhanced CT images of 170 patients. • The algorithm had an AUC of 0.940 for detecting aortic dissection. • The accuracy, sensitivity, and specificity of the algorithm were comparable to those of radiologists.
OBJECTIVES: To develop a deep learning-based algorithm to detect aortic dissection (AD) and evaluate the diagnostic ability of the algorithm compared with those of radiologists. METHODS: Included in the study were 170 patients (85 with AD and 85 without AD). An AD detection algorithm was developed using a convolutional neural network with Xception architecture. Of the patient data, 80% were used for training and validation and 20% were used for testing. Fivefold cross-validation was performed to evaluate the method. An average of 6688 non-contrast-enhanced CT images (slice thickness, 5 mm) were used for training. A radiologist reviewed both contrast-enhanced and non-contrast-enhanced images and identified the slices of AD. The identified slices were used as ground truth. Receiver operating characteristic curve and area under the curve (AUC) analysis was performed. Five radiologists independently evaluated the images. The accuracy, sensitivity, and specificity of the algorithm and those of the radiologists were compared. RESULTS: The AUC of the developed algorithm was 0.940, and a cutoff value of 0.400 provided accuracy of 90.0%, sensitivity of 91.8%, and specificity of 88.2%. For the radiologists, median (range) accuracy, sensitivity, and specificity were 88.8 (83.5-94.1)%, 90.6 (83.5-94.1)%, and 94.1 (72.9-97.6)%, respectively. There was no significant difference in performance in terms of accuracy, sensitivity, or specificity between the algorithm and the average performance of the radiologists (p > 0.05). CONCLUSIONS: The developed algorithm showed comparable diagnostic performance to radiologists for detecting AD, which suggests the potential of the proposed method to support clinical practice by reducing missed ADs. KEY POINTS: • A deep learning-based algorithm for detecting aortic dissection was developed using the non-contrast-enhanced CT images of 170 patients. • The algorithm had an AUC of 0.940 for detecting aortic dissection. • The accuracy, sensitivity, and specificity of the algorithm were comparable to those of radiologists.
Authors: Louis-Mathieu Stevens; Joren C Madsen; Eric M Isselbacher; Paul Khairy; Thomas E MacGillivray; Alan D Hilgenberg; Arvind K Agnihotri Journal: J Thorac Cardiovasc Surg Date: 2009-05-31 Impact factor: 5.209
Authors: Andre Esteva; Brett Kuprel; Roberto A Novoa; Justin Ko; Susan M Swetter; Helen M Blau; Sebastian Thrun Journal: Nature Date: 2017-01-25 Impact factor: 49.962
Authors: Yan Gao; Min Wang; Guogang Zhang; Lingjun Zhou; Jingming Luo; Lijue Liu Journal: Int J Environ Res Public Health Date: 2022-05-06 Impact factor: 4.614
Authors: Ben Li; Tiam Feridooni; Cesar Cuen-Ojeda; Teruko Kishibe; Charles de Mestral; Muhammad Mamdani; Mohammed Al-Omran Journal: NPJ Digit Med Date: 2022-01-19