Yoshiyuki Watanabe1,2, Takahiro Tanaka3, Atsushi Nishida3, Hiroto Takahashi4, Masahiro Fujiwara4, Takuya Fujiwara4, Atsuko Arisawa4, Hiroki Yano4, Noriyuki Tomiyama4, Hajime Nakamura5, Kenichi Todo6, Kazuhisa Yoshiya7. 1. Department of Future Diagnostic Radiology, Osaka University Graduate School of Medicine, Osaka, Japan. ywatanab@belle.shiga-med.ac.jp. 2. Department of Radiology, Shiga University of Medical Science, Tsukiwacho Seta Otsu, Shiga, 520-2102, Japan. ywatanab@belle.shiga-med.ac.jp. 3. Dai Nippon Printing Co., Ltd., Tokyo, Japan. 4. Department of Diagnostic and Interventional Radiology, Osaka University Graduate School of Medicine, Osaka, Japan. 5. Department of Neurosurgery, Osaka University Graduate School of Medicine, Osaka, Japan. 6. Department of Neurology, Osaka University Graduate School of Medicine, Osaka, Japan. 7. Department of Traumatology and Acute Critical Medicine, Osaka University Graduate School of Medicine, Osaka, Japan.
Abstract
PURPOSE: To elucidate the effect of deep learning-based computer-assisted detection (CAD) on the performance of different-level physicians in detecting intracranial haemorrhage using CT. METHODS: A total of 40 head CT datasets (normal, 16; haemorrhagic, 24) were evaluated by 15 physicians (5 board-certificated radiologists, 5 radiology residents, and 5 medical interns). The physicians attended 2 reading sessions without and with CAD. All physicians annotated the haemorrhagic regions with a degree of confidence, and the reading time was recorded in each case. Our CAD system was developed using 433 patients' head CT images (normal, 203; haemorrhagic, 230), and haemorrhage rates were displayed as corresponding probability heat maps using U-Net and a machine learning-based false-positive removal method. Sensitivity, specificity, accuracy, and figure of merit (FOM) were calculated based on the annotations and confidence levels. RESULTS: In patient-based evaluation, the mean accuracy of all physicians significantly increased from 83.7 to 89.7% (p < 0.001) after using CAD. Additionally, accuracies of board-certificated radiologists, radiology residents, and interns were 92.5, 82.5, and 76.0% without CAD and 97.5, 90.5, and 81.0% with CAD, respectively. The mean FOM of all physicians increased from 0.78 to 0.82 (p = 0.004) after using CAD. The reading time was significantly lower when CAD (43 s) was used than when it was not (68 s, p < 0.001) for all physicians. CONCLUSION: The CAD system developed using deep learning significantly improved the diagnostic performance and reduced the reading time among all physicians in detecting intracranial haemorrhage.
PURPOSE: To elucidate the effect of deep learning-based computer-assisted detection (CAD) on the performance of different-level physicians in detecting intracranial haemorrhage using CT. METHODS: A total of 40 head CT datasets (normal, 16; haemorrhagic, 24) were evaluated by 15 physicians (5 board-certificated radiologists, 5 radiology residents, and 5 medical interns). The physicians attended 2 reading sessions without and with CAD. All physicians annotated the haemorrhagic regions with a degree of confidence, and the reading time was recorded in each case. Our CAD system was developed using 433 patients' head CT images (normal, 203; haemorrhagic, 230), and haemorrhage rates were displayed as corresponding probability heat maps using U-Net and a machine learning-based false-positive removal method. Sensitivity, specificity, accuracy, and figure of merit (FOM) were calculated based on the annotations and confidence levels. RESULTS: In patient-based evaluation, the mean accuracy of all physicians significantly increased from 83.7 to 89.7% (p < 0.001) after using CAD. Additionally, accuracies of board-certificated radiologists, radiology residents, and interns were 92.5, 82.5, and 76.0% without CAD and 97.5, 90.5, and 81.0% with CAD, respectively. The mean FOM of all physicians increased from 0.78 to 0.82 (p = 0.004) after using CAD. The reading time was significantly lower when CAD (43 s) was used than when it was not (68 s, p < 0.001) for all physicians. CONCLUSION: The CAD system developed using deep learning significantly improved the diagnostic performance and reduced the reading time among all physicians in detecting intracranial haemorrhage.
Entities:
Keywords:
Computed tomography; Deep learning; Diagnosis; Efficacy; Intracranial haemorrhage; Retrospective
Authors: Almut Kundisch; Alexander Hönning; Sven Mutze; Lutz Kreissl; Frederik Spohn; Johannes Lemcke; Maximilian Sitz; Paul Sparenberg; Leonie Goelz Journal: PLoS One Date: 2021-11-29 Impact factor: 3.240
Authors: B Nageswara Rao; Sudhansu Mohanty; Kamal Sen; U Rajendra Acharya; Kang Hao Cheong; Sukanta Sabut Journal: Comput Math Methods Med Date: 2022-04-16 Impact factor: 2.809
Authors: Vidhya V; Anjan Gudigar; U Raghavendra; Ajay Hegde; Girish R Menon; Filippo Molinari; Edward J Ciaccio; U Rajendra Acharya Journal: Int J Environ Res Public Health Date: 2021-06-16 Impact factor: 3.390