File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3389/fninf.2019.00033
- Scopus: eid_2-s2.0-85068467425
- PMID: 31191282
- WOS: WOS:000469458500001
Supplementary
- Citations:
- Appears in Collections:
Article: Evaluation of enhanced learning techniques for segmenting ischaemic stroke lesions in brain magnetic resonance perfusion images using a convolutional neural network scheme
Title | Evaluation of enhanced learning techniques for segmenting ischaemic stroke lesions in brain magnetic resonance perfusion images using a convolutional neural network scheme |
---|---|
Authors | |
Keywords | Computer vision Ischaemic stroke Segmentation Deepmedic Medical image analysis Deep learning Convolutional neural networks |
Issue Date | 2019 |
Citation | Frontiers in Neuroinformatics, 2019, v. 13, article no. 33 How to Cite? |
Abstract | © 2019 Pérez Malla, Valdés Hernández, Rachmadi and Komura. Magnetic resonance (MR) perfusion imaging non-invasively measures cerebral perfusion, which describes the blood's passage through the brain's vascular network. Therefore, it is widely used to assess cerebral ischaemia. Convolutional Neural Networks (CNN) constitute the state-of-the-art method in automatic pattern recognition and hence, in segmentation tasks. But none of the CNN architectures developed to date have achieved high accuracy when segmenting ischaemic stroke lesions, being the main reasons their heterogeneity in location, shape, size, image intensity and texture, especially in this imaging modality. We use a freely available CNN framework, developed for MR imaging lesion segmentation, as core algorithm to evaluate the impact of enhanced machine learning techniques, namely data augmentation, transfer learning and post-processing, in the segmentation of stroke lesions using the ISLES 2017 dataset, which contains expert annotated diffusion-weighted perfusion and diffusion brain MRI of 43 stroke patients. Of all the techniques evaluated, data augmentation with binary closing achieved the best results, improving the mean Dice score in 17% over the baseline model. Consistent with previous works, better performance was obtained in the presence of large lesions. |
Persistent Identifier | http://hdl.handle.net/10722/288948 |
PubMed Central ID | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pérez Malla, Carlos Uziel | - |
dc.contributor.author | Valdés Hernández, Maria del C. | - |
dc.contributor.author | Rachmadi, Muhammad Febrian | - |
dc.contributor.author | Komura, Taku | - |
dc.date.accessioned | 2020-10-12T08:06:17Z | - |
dc.date.available | 2020-10-12T08:06:17Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Frontiers in Neuroinformatics, 2019, v. 13, article no. 33 | - |
dc.identifier.uri | http://hdl.handle.net/10722/288948 | - |
dc.description.abstract | © 2019 Pérez Malla, Valdés Hernández, Rachmadi and Komura. Magnetic resonance (MR) perfusion imaging non-invasively measures cerebral perfusion, which describes the blood's passage through the brain's vascular network. Therefore, it is widely used to assess cerebral ischaemia. Convolutional Neural Networks (CNN) constitute the state-of-the-art method in automatic pattern recognition and hence, in segmentation tasks. But none of the CNN architectures developed to date have achieved high accuracy when segmenting ischaemic stroke lesions, being the main reasons their heterogeneity in location, shape, size, image intensity and texture, especially in this imaging modality. We use a freely available CNN framework, developed for MR imaging lesion segmentation, as core algorithm to evaluate the impact of enhanced machine learning techniques, namely data augmentation, transfer learning and post-processing, in the segmentation of stroke lesions using the ISLES 2017 dataset, which contains expert annotated diffusion-weighted perfusion and diffusion brain MRI of 43 stroke patients. Of all the techniques evaluated, data augmentation with binary closing achieved the best results, improving the mean Dice score in 17% over the baseline model. Consistent with previous works, better performance was obtained in the presence of large lesions. | - |
dc.language | eng | - |
dc.relation.ispartof | Frontiers in Neuroinformatics | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | Computer vision | - |
dc.subject | Ischaemic stroke | - |
dc.subject | Segmentation | - |
dc.subject | Deepmedic | - |
dc.subject | Medical image analysis | - |
dc.subject | Deep learning | - |
dc.subject | Convolutional neural networks | - |
dc.title | Evaluation of enhanced learning techniques for segmenting ischaemic stroke lesions in brain magnetic resonance perfusion images using a convolutional neural network scheme | - |
dc.type | Article | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.3389/fninf.2019.00033 | - |
dc.identifier.pmid | 31191282 | - |
dc.identifier.pmcid | PMC6548861 | - |
dc.identifier.scopus | eid_2-s2.0-85068467425 | - |
dc.identifier.volume | 13 | - |
dc.identifier.spage | article no. 33 | - |
dc.identifier.epage | article no. 33 | - |
dc.identifier.eissn | 1662-5196 | - |
dc.identifier.isi | WOS:000469458500001 | - |
dc.identifier.issnl | 1662-5196 | - |