End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI

Post time Yesterday 23:07

                              End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI                                                    Ilker Ozgur Koska 1 2, Alper Selver 3 4             [url=https://pubmed.ncbi.nlm.nih.gov/39656236/#full-view-affiliation-5]5             , [url=https://pubmed.ncbi.nlm.nih.gov/?size=20&term=Gelal+F&cauthor_id=39656236]Fazıl Gelal 6, Muhsın Engın Uluc 6, Yusuf Kenan Çetinoğlu 7, Nursel Yurttutan 8             , [url=https://pubmed.ncbi.nlm.nih.gov/?size=20&term=Ser%C4%B1ndere+M&cauthor_id=39656236]Mehmet Serındere 9, Oğuz Dicle 10


                              Affiliations

PMID: 39656236

DOI: [url=https://doi.org/10.1007/s00234-024-03520-x]10.1007/s00234-024-03520-x

                                    Abstract                                                                                                            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.

Post time Yesterday 23:25

: Waiting for confirmation
If the PDF has not been accepted after 72 hours, the system will automatically adopt it.

[Other] End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI

Same Category

Latest Reply

Announcement

Daily Top Contributors

[Other] End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI Copy

Same Category

Latest Reply

Announcement

Daily Top Contributors

[Other] End-to-end deep learning patient level classification of affected territory of ischemic stroke patients in DW-MRI