An eXplainable deep learning model for multi-modal MRI grading of IDH-mutant astrocytomas

Hamail Ayaz; Oladosu Oladimeji; Ian Mcloughlin; David Tormey; Thomas c. Booth; Saritha Unnikrishnan

doi:10.1016/j.rineng.2024.103353

An eXplainable deep learning model for multi-modal MRI grading of IDH-mutant astrocytomas

Hamail Ayaz, Oladosu Oladimeji, Ian Mcloughlin, David Tormey, Thomas c. Booth, Saritha Unnikrishnan

Cancer Imaging

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

IDH-Mutant-astrocytomas are malignant brain glioma tumors. They are graded as lower grade (grades 2 and 3) or higher grade (grade 4) according to their rate of growth and molecular features. Conventional IDH grading requires pathology examination, which is invasive, costly, and time-consuming. Advanced MRI modalities are widely used to overcome some of these limitations but require a high level of interpretation for tumor grading. Recent advances in deep learning have shown potential to aid and improve the accuracy and efficiency of tumor classification. This study proposes a novel non-invasive approach for grading IDH-Mutant-astrocytomas using a Light-weight Attention Network (LAN) that integrates multi-modal MRI data, including both conventional and advanced MRI modalities. The study addresses inter-modality heterogeneity using Principal Component Analysis (PCA) while minimizing computational complexity. LAN uses a 3D Convolutional Neural Network (CNN) and a volumetric attention mechanism to extract tumor patterns and classify grades 2 to 4. This is followed by an eXplainable AI approach that uses SHapley Additive exPlanations (SHAP) to interpret model decisions and identify key contributing features. The proposed LAN model outperforms other pre-trained state-of-the-art models, achieving an overall accuracy of 0.84. The SHAP attribution scores demonstrate that advanced MRI modalities such as Arterial Spin Labeling (ASL) and Diffusion-weighted Imaging (DWI), along with conventional MRI sequences such as FLAIR, T1-c and T2, contribute significantly to improving tumor heterogeneity visualization for aggressive grade 2 gliomas. This work demonstrates the feasibility of integrating explainable deep learning with multi-modal MRI data for precise and comprehensible early glioma grading, potentially leading to better clinical decision-making.

Original language	English
Article number	103353
Pages (from-to)	103353
Journal	Results in Engineering
Volume	24
Early online date	20 Nov 2024
DOIs	https://doi.org/10.1016/j.rineng.2024.103353
Publication status	Published - 1 Dec 2024

Access to Document

10.1016/j.rineng.2024.103353Licence: CC BY

https://linkinghub.elsevier.com/retrieve/pii/S2590123024016062

Cite this

@article{f866a79d6a704ae5b966d4994aab53c9,

title = "An eXplainable deep learning model for multi-modal MRI grading of IDH-mutant astrocytomas",

abstract = "IDH-Mutant-astrocytomas are malignant brain glioma tumors. They are graded as lower grade (grades 2 and 3) or higher grade (grade 4) according to their rate of growth and molecular features. Conventional IDH grading requires pathology examination, which is invasive, costly, and time-consuming. Advanced MRI modalities are widely used to overcome some of these limitations but require a high level of interpretation for tumor grading. Recent advances in deep learning have shown potential to aid and improve the accuracy and efficiency of tumor classification. This study proposes a novel non-invasive approach for grading IDH-Mutant-astrocytomas using a Light-weight Attention Network (LAN) that integrates multi-modal MRI data, including both conventional and advanced MRI modalities. The study addresses inter-modality heterogeneity using Principal Component Analysis (PCA) while minimizing computational complexity. LAN uses a 3D Convolutional Neural Network (CNN) and a volumetric attention mechanism to extract tumor patterns and classify grades 2 to 4. This is followed by an eXplainable AI approach that uses SHapley Additive exPlanations (SHAP) to interpret model decisions and identify key contributing features. The proposed LAN model outperforms other pre-trained state-of-the-art models, achieving an overall accuracy of 0.84. The SHAP attribution scores demonstrate that advanced MRI modalities such as Arterial Spin Labeling (ASL) and Diffusion-weighted Imaging (DWI), along with conventional MRI sequences such as FLAIR, T1-c and T2, contribute significantly to improving tumor heterogeneity visualization for aggressive grade 2 gliomas. This work demonstrates the feasibility of integrating explainable deep learning with multi-modal MRI data for precise and comprehensible early glioma grading, potentially leading to better clinical decision-making.",

author = "Hamail Ayaz and Oladosu Oladimeji and Ian Mcloughlin and David Tormey and Booth, {Thomas c.} and Saritha Unnikrishnan",

note = "Publisher Copyright: {\textcopyright} 2024 The Authors",

year = "2024",

month = dec,

day = "1",

doi = "10.1016/j.rineng.2024.103353",

language = "English",

volume = "24",

pages = "103353",

journal = "Results in Engineering",

issn = "2590-1230",

publisher = "Elsevier",

}

TY - JOUR

T1 - An eXplainable deep learning model for multi-modal MRI grading of IDH-mutant astrocytomas

AU - Ayaz, Hamail

AU - Oladimeji, Oladosu

AU - Mcloughlin, Ian

AU - Tormey, David

AU - Booth, Thomas c.

AU - Unnikrishnan, Saritha

PY - 2024/12/1

Y1 - 2024/12/1

N2 - IDH-Mutant-astrocytomas are malignant brain glioma tumors. They are graded as lower grade (grades 2 and 3) or higher grade (grade 4) according to their rate of growth and molecular features. Conventional IDH grading requires pathology examination, which is invasive, costly, and time-consuming. Advanced MRI modalities are widely used to overcome some of these limitations but require a high level of interpretation for tumor grading. Recent advances in deep learning have shown potential to aid and improve the accuracy and efficiency of tumor classification. This study proposes a novel non-invasive approach for grading IDH-Mutant-astrocytomas using a Light-weight Attention Network (LAN) that integrates multi-modal MRI data, including both conventional and advanced MRI modalities. The study addresses inter-modality heterogeneity using Principal Component Analysis (PCA) while minimizing computational complexity. LAN uses a 3D Convolutional Neural Network (CNN) and a volumetric attention mechanism to extract tumor patterns and classify grades 2 to 4. This is followed by an eXplainable AI approach that uses SHapley Additive exPlanations (SHAP) to interpret model decisions and identify key contributing features. The proposed LAN model outperforms other pre-trained state-of-the-art models, achieving an overall accuracy of 0.84. The SHAP attribution scores demonstrate that advanced MRI modalities such as Arterial Spin Labeling (ASL) and Diffusion-weighted Imaging (DWI), along with conventional MRI sequences such as FLAIR, T1-c and T2, contribute significantly to improving tumor heterogeneity visualization for aggressive grade 2 gliomas. This work demonstrates the feasibility of integrating explainable deep learning with multi-modal MRI data for precise and comprehensible early glioma grading, potentially leading to better clinical decision-making.

AB - IDH-Mutant-astrocytomas are malignant brain glioma tumors. They are graded as lower grade (grades 2 and 3) or higher grade (grade 4) according to their rate of growth and molecular features. Conventional IDH grading requires pathology examination, which is invasive, costly, and time-consuming. Advanced MRI modalities are widely used to overcome some of these limitations but require a high level of interpretation for tumor grading. Recent advances in deep learning have shown potential to aid and improve the accuracy and efficiency of tumor classification. This study proposes a novel non-invasive approach for grading IDH-Mutant-astrocytomas using a Light-weight Attention Network (LAN) that integrates multi-modal MRI data, including both conventional and advanced MRI modalities. The study addresses inter-modality heterogeneity using Principal Component Analysis (PCA) while minimizing computational complexity. LAN uses a 3D Convolutional Neural Network (CNN) and a volumetric attention mechanism to extract tumor patterns and classify grades 2 to 4. This is followed by an eXplainable AI approach that uses SHapley Additive exPlanations (SHAP) to interpret model decisions and identify key contributing features. The proposed LAN model outperforms other pre-trained state-of-the-art models, achieving an overall accuracy of 0.84. The SHAP attribution scores demonstrate that advanced MRI modalities such as Arterial Spin Labeling (ASL) and Diffusion-weighted Imaging (DWI), along with conventional MRI sequences such as FLAIR, T1-c and T2, contribute significantly to improving tumor heterogeneity visualization for aggressive grade 2 gliomas. This work demonstrates the feasibility of integrating explainable deep learning with multi-modal MRI data for precise and comprehensible early glioma grading, potentially leading to better clinical decision-making.

UR - http://www.scopus.com/inward/record.url?scp=85209410199&partnerID=8YFLogxK

U2 - 10.1016/j.rineng.2024.103353

DO - 10.1016/j.rineng.2024.103353

M3 - Article

SN - 2590-1230

VL - 24

SP - 103353

JO - Results in Engineering

JF - Results in Engineering

M1 - 103353

ER -

An eXplainable deep learning model for multi-modal MRI grading of IDH-mutant astrocytomas

Abstract

Access to Document

Other files and links

Fingerprint

Cite this