Alberta Stroke Program Early CT Score Calculation Using the Deep Learning-Based Brain Hemisphere Comparison Algorithm |
| |
| Authors: | Masaki Naganuma Atsushi Tachibana Takuya Fuchigami Sadato Akahori Shuichiro Okumura Kenichiro Yi Yoshimasa Matsuo Koichi Ikeno Toshiro Yonehara |
| |
| Affiliation: | 2. Fujifilm Corporation, Japan;3. Department of Radiology, Saiseikai Kumamoto Hospital, Kumamoto, Japan;2. School of Medicine, New York Medical College, Valhalla, NY, USA;2. Department of Neurology, Asklepios Hospital St. Georg, Hamburg, Germany;3. Department of Internal Medicine I, University Medical Center of the Johannes Gutenberg-University, Mainz, Germany;4. Epidemiology, IQVIA, Frankfurt am Main, Germany;2. Department of Neurology, Stroke and Cerebrovascular Diseases Division, Tufts Medical Center, Boston, MA, USA;3. Department of Neurology, Neuroscience Critical Care Division, University of Mississippi Medical Center, Jackson, MS, USA;4. Department of Neurology, University of Miami Miller School of Medicine, Miami, FL, USA;5. Department of Neurology, Saint David''s Round Rock Medical Center, Round Rock, TX, USA;6. NHLBI''s Framingham Heart Study, Framingham, Massachusetts, USA;2. Neurology, California Hospital Medical Center, Los Angeles, CA USA;3. Pharmacy Services, Adventist Health White Memorial, Los Angeles, CA USA |
| |
| Abstract: | ![]()
ObjectivesThe Alberta Stroke Program Early Computed Tomography Score (ASPECTS) is a promising tool for the evaluation of stroke expansion to determine suitability for reperfusion therapy. The aim of this study was to validate deep learning-based ASPECTS calculation software that utilizes a three-dimensional fully convolutional network-based brain hemisphere comparison algorithm (3D-BHCA).Materials and MethodsWe retrospectively collected head non-contrast computed tomography (CT) data from 71 patients with acute ischemic stroke and 80 non-stroke patients. The results for ASPECTS on CT assessed by 5 stroke neurologists and by the 3D-BHCA model were compared with the ground truth by means of region-based and score-based analyses.ResultsIn total, 151 patients and 3020 (151 × 20) ASPECTS regions were investigated. Median time from onset to CT was 195 min in the stroke patients. In region-based analysis, the sensitivity (0.80), specificity (0.97), and accuracy (0.96) of the 3D-BHCA model were superior to those of stroke neurologists. The sensitivity (0.98), specificity (0.92), and accuracy (0.97) of dichotomized ASPECTS > 5 analysis and the intraclass correlation coefficient (0.90) in total score-based analysis of the 3D-BHCA model were superior to those of stroke neurologists overall. When patients with stroke were stratified by onset-to-CT time, the 3D-BHCA model exhibited the highest performance to calculate ASPECTS, even in the earliest time period.ConclusionsThe automated ASPECTS calculation software we developed using a deep learning-based algorithm was superior or equal to stroke neurologists in performing ASPECTS calculation in patients with acute stroke and non-stroke patients. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
