End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI.
Purpose: To develop an end-to-end DL model for automated classification of affected territory in DWI of stroke patients. Materials and methods: In this retrospective multicenter study, brain DWI studies from January 2017 to April 2020 from Center 1, from June 2020 to December 2020 from Center 2, and...
| Publicado en: | Neuroradiology Vol. 67; no. 1; pp. 137 - 152 |
|---|---|
| Autores principales: | , , , , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
Springer Nature
Jan2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=182843953&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 182843953 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 00283940 NYZ jtl: Neuroradiology issn: 00283940 maglogo: N pubinfo: dt: Jan2025 vid: 67 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 182843953 181536557 182843953 182843953 10.1007/s00234-024-03520-x 182843953 ppf: 137 ppct: 15 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI. aug: au: Koska, Ilker Ozgur Selver, Alper Gelal, Fazıl Uluc, Muhsın Engın Çetinoğlu, Yusuf Kenan Yurttutan, Nursel Serındere, Mehmet Dicle, Oğuz affil: Department of Radiology, Behçet Uz Children's Hospital, Izmir, Turkey sug: subj: Ischemic Stroke Radiography Magnetic Resonance Imaging Methods Deep Learning Image Interpretation, Computer Assisted Human Retrospective Design Multicenter Studies Anterior Cerebral Artery Middle Cerebral Artery Convolutional Neural Networks Male Female Adult Middle Age Aged Aged, 80 and Over Support Vector Machine Stroke Patients Cerebrovascular Circulation Patient Classification Adult: 19-44 years Middle Aged: 45-64 years Aged: 65+ years Aged, 80 & over Male Female ab: Purpose: To develop an end-to-end DL model for automated classification of affected territory in DWI of stroke patients. Materials and methods: In this retrospective multicenter study, brain DWI studies from January 2017 to April 2020 from Center 1, from June 2020 to December 2020 from Center 2, and from November 2019 to April 2020 from Center 3 were included. Four radiologists labeled images into five classes: anterior cerebral artery (ACA), middle cerebral artery (MCA), posterior circulation (PC), and watershed (WS) regions, as well as normal images. Additionally, for Center 1, clinical information was encoded as a domain knowledge vector to incorporate into image embeddings. 3D convolutional neural network (CNN) and attention gate integrated versions for direct 3D encoding, long short-term memory (LSTM-CNN), and time-distributed layer for slice-based encoding were employed. Balanced classification accuracy, macro averaged f1 score, AUC, and interrater Cohen's kappa were calculated. Results: Overall, 624 DWI MRIs from 3 centers were utilized (mean age, interval: 66.89 years, 29–95 years; 345 male) with 439 patients in the training, 103 in the validation, and 82 in the test sets. The best model was a slice-based parallel encoding model with 0.88 balanced accuracy, 0.80 macro-f1 score, and an AUC of 0.98. Clinical domain knowledge integration improved the performance with 0.93 best overall accuracy with parallel stream model embeddings and support vector machine classifiers. The mean kappa value for interrater agreement was 0.87. Conclusion: Developed end-to-end deep learning models performed well in classifying affected regions from stroke in DWI. Clinical relevance statement: The end-to-end deep learning model with a parallel stream encoding strategy for classifying stroke regions in DWI has performed comparably with radiologists. Key results: • Parallel encoding of slices followed by application of convolutional block attention module was the best performing image-based deep learning approach with 0.88 balanced accuracy, 0.80 macro-f1 score, and 0.98 AUC. • Integration of clinical domain knowledge to the image embeddings and support vector machine-based training increased the classification accuracy to 0.93. • Ablation studies with reduced class number and pocket algorithm with image embeddings from different encoding strategies yielded different winner strategies, which was interpreted as evidence of the strong requirement for dataset and training methodology matching. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|