Cargando…

Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs

With the increased reliance on medical imaging, Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipelines. However, training accurate and reliable classification models often require large fine-grained annotated datasets....

Descripción completa

Detalles Bibliográficos
Autores principales: Rajapaksa, Sajith, Khalvati, Farzad
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365288/
https://www.ncbi.nlm.nih.gov/pubmed/37492689
http://dx.doi.org/10.3389/fradi.2022.1061402
_version_ 1785077009913741312
author Rajapaksa, Sajith
Khalvati, Farzad
author_facet Rajapaksa, Sajith
Khalvati, Farzad
author_sort Rajapaksa, Sajith
collection PubMed
description With the increased reliance on medical imaging, Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipelines. However, training accurate and reliable classification models often require large fine-grained annotated datasets. To alleviate this, weakly-supervised methods can be used to obtain local information such as region of interest from global labels. This work proposes a weakly-supervised pipeline to extract Relevance Maps of medical images from pre-trained 3D classification models using localized perturbations. The extracted Relevance Map describes a given region’s importance to the classification model and produces the segmentation for the region. Furthermore, we propose a novel optimal perturbation generation method that exploits 3D superpixels to find the most relevant area for a given classification using U-net architecture. This model is trained with perturbation loss, which maximizes the difference between unperturbed and perturbed predictions. We validated the effectiveness of our methodology by applying it to the segmentation of Glioma brain tumours in MRI scans using only classification labels for glioma type. The proposed method outperforms existing methods in both Dice Similarity Coefficient for segmentation and resolution for visualizations.
format Online
Article
Text
id pubmed-10365288
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-103652882023-07-25 Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs Rajapaksa, Sajith Khalvati, Farzad Front Radiol Radiology With the increased reliance on medical imaging, Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipelines. However, training accurate and reliable classification models often require large fine-grained annotated datasets. To alleviate this, weakly-supervised methods can be used to obtain local information such as region of interest from global labels. This work proposes a weakly-supervised pipeline to extract Relevance Maps of medical images from pre-trained 3D classification models using localized perturbations. The extracted Relevance Map describes a given region’s importance to the classification model and produces the segmentation for the region. Furthermore, we propose a novel optimal perturbation generation method that exploits 3D superpixels to find the most relevant area for a given classification using U-net architecture. This model is trained with perturbation loss, which maximizes the difference between unperturbed and perturbed predictions. We validated the effectiveness of our methodology by applying it to the segmentation of Glioma brain tumours in MRI scans using only classification labels for glioma type. The proposed method outperforms existing methods in both Dice Similarity Coefficient for segmentation and resolution for visualizations. Frontiers Media S.A. 2022-12-21 /pmc/articles/PMC10365288/ /pubmed/37492689 http://dx.doi.org/10.3389/fradi.2022.1061402 Text en © 2022 Rajapaksa and Khalvati. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Radiology
Rajapaksa, Sajith
Khalvati, Farzad
Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title_full Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title_fullStr Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title_full_unstemmed Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title_short Relevance maps: A weakly supervised segmentation method for 3D brain tumours in MRIs
title_sort relevance maps: a weakly supervised segmentation method for 3d brain tumours in mris
topic Radiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10365288/
https://www.ncbi.nlm.nih.gov/pubmed/37492689
http://dx.doi.org/10.3389/fradi.2022.1061402
work_keys_str_mv AT rajapaksasajith relevancemapsaweaklysupervisedsegmentationmethodfor3dbraintumoursinmris
AT khalvatifarzad relevancemapsaweaklysupervisedsegmentationmethodfor3dbraintumoursinmris