Journal article icon

Journal article

Automated detection of cerebral microbleeds on MR images using knowledge distillation framework

Abstract:

Introduction: Cerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections.

Methods: In our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics.

Results: On cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.

Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.3389/fninf.2023.1204186

Authors


More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Clinical Neurosciences
Role:
Author
ORCID:
0000-0002-9451-4779
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Clinical Neurosciences
Role:
Author
ORCID:
0000-0003-1474-9963
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Clinical Neurosciences
Role:
Author
ORCID:
0000-0002-6133-3373
More by this author
Role:
Author
ORCID:
0000-0002-9523-2546


More from this funder
Funder identifier:
https://ror.org/029chgv08
Grant:
203141/Z/16/Z
202788/Z/16/Z
203139/Z/16/Z
215573/Z/19/Z
215573/Z/19/Z
More from this funder
Funder identifier:
https://ror.org/00k4n6c32
Grant:
666881
More from this funder
Funder identifier:
https://ror.org/0439y7842
Grant:
EP/L016052/1


Publisher:
Frontiers Media
Journal:
Frontiers in Neuroinformatics More from this journal
Volume:
17
Article number:
1204186
Place of publication:
Switzerland
Publication date:
2023-07-10
Acceptance date:
2023-06-19
DOI:
EISSN:
1662-5196
Pmid:
37492242


Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP