Deep learning-based prediction of mortality using brain midline shift and clinical information
Brain midline shift (MLS) indicates the severity of mass effect from intracranial lesions such as traumatic brain injury, stroke, brain tumor, or hematoma. Brain MLS can be used to determine whether patients require emergency surgery and to predict patients' prognosis. Since brain MLS is usuall...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024173021 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573121207468032 |
|---|---|
| author | An-Rong Wu Sun-Yuan Hsieh Hsin-Hung Chou Cheng-Shih Lai Jo-Ying Hung Bow Wang Yi-Shan Tsai |
| author_facet | An-Rong Wu Sun-Yuan Hsieh Hsin-Hung Chou Cheng-Shih Lai Jo-Ying Hung Bow Wang Yi-Shan Tsai |
| author_sort | An-Rong Wu |
| collection | DOAJ |
| description | Brain midline shift (MLS) indicates the severity of mass effect from intracranial lesions such as traumatic brain injury, stroke, brain tumor, or hematoma. Brain MLS can be used to determine whether patients require emergency surgery and to predict patients' prognosis. Since brain MLS is usually emergent, it must be diagnosed immediately. Therefore, this study presents a computer-aided deep-learning method for detecting MLS, aiming to predict mortality in a prognosis-predicting cohort using brain MLS and clinical in-formation. The brain midline is a 3-dimensional structure, but computed tomography (CT) slices are 2-dimensional which limits brain MLS detection. Here we propose a keypoint detection method to detect brain midline on each CT slice, acquiring brain MLS distance and area in each slice. Combined with clinical information, patient mortality can be predicted using the multilayer perceptron (MLP) model. The accuracy, precision, sensitivity, specificity, and F1-score for slice selection with the proposed model are 0.966, 0.952, 0.991, 0.932, and 0.971, respectively. Both MLS distance and volume were precisely predicted at slice-level and case-level with only the slightest error. The detected midlines were clearly separated into left and right brain with a dice coefficient of 0.98. The accuracy and AUC of the MLP model were both above 0.8. The model detected large brain MLS cases well in the prediction of outcomes in the prognosis-predicting cohort. The method performs well on slice selection and brain MLS detection, and predictions of MLS distance and volume combined with clinical information predicts the patient's prognosis well. |
| format | Article |
| id | doaj-art-014ba1264a324abbaa5e5d1a464a5a2b |
| institution | Kabale University |
| issn | 2405-8440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj-art-014ba1264a324abbaa5e5d1a464a5a2b2025-02-02T05:27:46ZengElsevierHeliyon2405-84402025-01-01112e41271Deep learning-based prediction of mortality using brain midline shift and clinical informationAn-Rong Wu0Sun-Yuan Hsieh1Hsin-Hung Chou2Cheng-Shih Lai3Jo-Ying Hung4Bow Wang5Yi-Shan Tsai6Department of Computer Science and Engineering, National Cheng Kung University, Tainan, TaiwanDepartment of Computer Science and Engineering, National Cheng Kung University, Tainan, Taiwan; Department of Computer Science and Engineering, National Chi Nan University, Nantou, TaiwanDepartment of Computer Science and Engineering, National Chi Nan University, Nantou, Taiwan; Corresponding author.Department of Medical Imaging, National Cheng Kung University Hospital, Tainan, TaiwanDepartment of Statistics, National Cheng Kung University, Tainan, TaiwanDepartment of Medical Imaging, National Cheng Kung University Hospital, Tainan, TaiwanDepartment of Medical Imaging, National Cheng Kung University Hospital, Tainan, Taiwan; Corresponding author.Brain midline shift (MLS) indicates the severity of mass effect from intracranial lesions such as traumatic brain injury, stroke, brain tumor, or hematoma. Brain MLS can be used to determine whether patients require emergency surgery and to predict patients' prognosis. Since brain MLS is usually emergent, it must be diagnosed immediately. Therefore, this study presents a computer-aided deep-learning method for detecting MLS, aiming to predict mortality in a prognosis-predicting cohort using brain MLS and clinical in-formation. The brain midline is a 3-dimensional structure, but computed tomography (CT) slices are 2-dimensional which limits brain MLS detection. Here we propose a keypoint detection method to detect brain midline on each CT slice, acquiring brain MLS distance and area in each slice. Combined with clinical information, patient mortality can be predicted using the multilayer perceptron (MLP) model. The accuracy, precision, sensitivity, specificity, and F1-score for slice selection with the proposed model are 0.966, 0.952, 0.991, 0.932, and 0.971, respectively. Both MLS distance and volume were precisely predicted at slice-level and case-level with only the slightest error. The detected midlines were clearly separated into left and right brain with a dice coefficient of 0.98. The accuracy and AUC of the MLP model were both above 0.8. The model detected large brain MLS cases well in the prediction of outcomes in the prognosis-predicting cohort. The method performs well on slice selection and brain MLS detection, and predictions of MLS distance and volume combined with clinical information predicts the patient's prognosis well.http://www.sciencedirect.com/science/article/pii/S2405844024173021Artificial intelligenceMedical intelligenceBrain midline shiftMidline detectionKeypoint detection networkDeep learning |
| spellingShingle | An-Rong Wu Sun-Yuan Hsieh Hsin-Hung Chou Cheng-Shih Lai Jo-Ying Hung Bow Wang Yi-Shan Tsai Deep learning-based prediction of mortality using brain midline shift and clinical information Heliyon Artificial intelligence Medical intelligence Brain midline shift Midline detection Keypoint detection network Deep learning |
| title | Deep learning-based prediction of mortality using brain midline shift and clinical information |
| title_full | Deep learning-based prediction of mortality using brain midline shift and clinical information |
| title_fullStr | Deep learning-based prediction of mortality using brain midline shift and clinical information |
| title_full_unstemmed | Deep learning-based prediction of mortality using brain midline shift and clinical information |
| title_short | Deep learning-based prediction of mortality using brain midline shift and clinical information |
| title_sort | deep learning based prediction of mortality using brain midline shift and clinical information |
| topic | Artificial intelligence Medical intelligence Brain midline shift Midline detection Keypoint detection network Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024173021 |
| work_keys_str_mv | AT anrongwu deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT sunyuanhsieh deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT hsinhungchou deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT chengshihlai deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT joyinghung deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT bowwang deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation AT yishantsai deeplearningbasedpredictionofmortalityusingbrainmidlineshiftandclinicalinformation |