39
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Artificial Intelligence Trained by Deep Learning Can Improve Computed Tomography Diagnosis of Nontraumatic Subarachnoid Hemorrhage by Nonspecialists

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Subarachnoid hemorrhage (SAH) is a serious cerebrovascular disease with a high mortality rate and is known as a disease that is hard to diagnose because it may be overlooked by noncontrast computed tomography (NCCT) examinations that are most frequently used for diagnosis. To create a system preventing this oversight of SAH, we trained artificial intelligence (AI) with NCCT images obtained from 419 patients with nontraumatic SAH and 338 healthy subjects and created an AI system capable of diagnosing the presence and location of SAH. Then, we conducted experiments in which five neurosurgery specialists, five nonspecialists, and the AI system interpreted NCCT images obtained from 135 patients with SAH and 196 normal subjects. The AI system was capable of performing a diagnosis of SAH with equal accuracy to that of five neurosurgery specialists, and the accuracy was higher than that of nonspecialists. Furthermore, the diagnostic accuracy of four out of five nonspecialists improved by interpreting NCCT images using the diagnostic results of the AI system as a reference, and the number of oversight cases was significantly reduced by the support of the AI system. This is the first report demonstrating that an AI system improved the diagnostic accuracy of SAH by nonspecialists.

          Related collections

          Most cited references37

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The International Cooperative Study on the Timing of Aneurysm Surgery. Part 1: Overall management results.

              The International Cooperative Study on the Timing of Aneurysm Surgery evaluated the results of surgical and medical management in 3521 patients between December, 1980, and July, 1983. At admission, 75% of patients were in good neurological condition and surgery was performed in 83%. At the 6-month evaluation, 26% of the patients had died and 58% exhibited a complete recovery. Vasospasm and rebleeding were the leading causes of morbidity and mortality in addition to the initial bleed. Predictors for mortality included the patient's decreased level of consciousness and increased age, thickness of the subarachnoid hemorrhage clot on computerized tomography, elevated blood pressure, preexisting medical illnesses, and basilar aneurysms. The results presented here document the status of management in the 1980's.
                Bookmark

                Author and article information

                Journal
                Neurol Med Chir (Tokyo)
                Neurol Med Chir (Tokyo)
                NMC
                Neurologia medico-chirurgica
                The Japan Neurosurgical Society
                0470-8105
                1349-8029
                November 2021
                16 September 2021
                : 61
                : 11
                : 652-660
                Affiliations
                [1 ]Department of Neurosurgery, Saiseikai Kumamoto Hospital, Stroke Center, Kumamoto, Kumamoto, Japan
                [2 ]Department of Radiology, Saiseikai Kumamoto Hospital, Kumamoto, Kumamoto, Japan
                [3 ]Research & Development Management Headquarters, FUJIFILM Corporation, Tokyo, Japan
                Author notes
                Corresponding author: Toru Nishi, MD, PhD Department of Neurosurgery, Sakurajyuji Yatsushiro Rehabilitation Hospital, 2-4-31 Honmachi, Yatsushiro, Kumamoto 866-0861, Japan. email: tyasu37@ 123456cc.okayama-u.ac.jp
                Article
                nmc-61-652
                10.2176/nmc.oa.2021-0124
                8592812
                34526447
                37c4f7f3-83b1-436f-a271-07e099ea9139
                © 2021 The Japan Neurosurgical Society

                This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc-nd/4.0/

                History
                : 8 May 2021
                : 5 August 2021
                Categories
                Original Article

                subarachnoid hemorrhage,misdiagnosis,diagnosis,deep learning,artificial intelligence

                Comments

                Comment on this article