Bimodal artificial intelligence using TabNet for differentiating spinal cord tumors-Integration of patient background information and images.

Autor:	Kita K; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Fujimori T; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Suzuki Y; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Kanie Y; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Takenaka S; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Kaito T; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Taki T; Department of Neurosurgery, Iseikai Hospital, Osaka, Osaka, Japan., Ukon Y; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Furuya M; Osaka Rosai Hospital, Sakai, Osaka, Japan., Saiwai H; Department of Orthopedic Surgery, Graduate School of Medical Sciences, Kyusyu University, Higashi, Fukuoka, Japan., Nakajima N; Japanese Red Cross Society Himeji Hospital, Himeji, Hyogo, Japan., Sugiura T; General Incorporated Foundation Sumitomo Hospital, Osaka, Osaka, Japan., Ishiguro H; National Hospital Organization Osaka National Hospital, Osaka, Osaka, Japan., Kamatani T; Toyonaka Municipal Hospital, Toyonaka, Osaka, Japan., Tsukazaki H; Kansai Rosai Hospital, Amagasaki, Hyogo, Japan., Sakai Y; Suita Municipal Hospital, Suita, Osaka, Japan., Takami H; Osaka International Cancer Institute, Osaka, Osaka, Japan., Tateiwa D; Osaka General Medical Center, Osaka, Osaka, Japan., Hashimoto K; Osaka Police Hospital, Osaka, Osaka, Japan., Wataya T; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Nishigaki D; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Sato J; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Hoshiyama M; JCHO Hoshigaoka Medical Center, Hirakata, Osaka, Japan., Tomiyama N; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan., Okada S; Osaka University Graduate School of Medicine Department of Orthopaedic Surgery, Suita, Osaka, Japan., Kido S; Osaka University School of Medicine Graduate School of Medicine Diagnostic and Interventional Radiology, Suita, Osaka, Japan.
Jazyk:	angličtina
Zdroj:	IScience [iScience] 2023 Sep 14; Vol. 26 (10), pp. 107900. Date of Electronic Publication: 2023 Sep 14 (Print Publication: 2023).
DOI:	10.1016/j.isci.2023.107900
Abstrakt:	We proposed a bimodal artificial intelligence that integrates patient information with images to diagnose spinal cord tumors. Our model combines TabNet, a state-of-the-art deep learning model for tabular data for patient information, and a convolutional neural network for images. As training data, we collected 259 spinal tumor patients (158 for schwannoma and 101 for meningioma). We compared the performance of the image-only unimodal model, table-only unimodal model, bimodal model using a gradient-boosting decision tree, and bimodal model using TabNet. Our proposed bimodal model using TabNet performed best (area under the receiver-operating characteristic curve [AUROC]: 0.91) in the training data and significantly outperformed the physicians' performance. In the external validation using 62 cases from the other two facilities, our bimodal model showed an AUROC of 0.92, proving the robustness of the model. The bimodal analysis using TabNet was effective for differentiating spinal tumors. Competing Interests: Authors declare that they have no competing interests. (© 2023 The Authors.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu