Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning
Abstract Alzheimer’s disease (AD) is a neurological disorder that predominantly affects the brain. In the coming years, it is expected to spread rapidly, with limited progress in diagnostic techniques. Various machine learning (ML) and artificial intelligence (AI) algorithms have been employed to de...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2024-02-01
|
| Series: | Visual Computing for Industry, Biomedicine, and Art |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s42492-024-00154-x |
| _version_ | 1797276008904130560 |
|---|---|
| author | Sazia Parvin Sonia Farhana Nimmy Md Sarwar Kamal |
| author_facet | Sazia Parvin Sonia Farhana Nimmy Md Sarwar Kamal |
| author_sort | Sazia Parvin |
| collection | DOAJ |
| description | Abstract Alzheimer’s disease (AD) is a neurological disorder that predominantly affects the brain. In the coming years, it is expected to spread rapidly, with limited progress in diagnostic techniques. Various machine learning (ML) and artificial intelligence (AI) algorithms have been employed to detect AD using single-modality data. However, recent developments in ML have enabled the application of these methods to multiple data sources and input modalities for AD prediction. In this study, we developed a framework that utilizes multimodal data (tabular data, magnetic resonance imaging (MRI) images, and genetic information) to classify AD. As part of the pre-processing phase, we generated a knowledge graph from the tabular data and MRI images. We employed graph neural networks for knowledge graph creation, and region-based convolutional neural network approach for image-to-knowledge graph generation. Additionally, we integrated various explainable AI (XAI) techniques to interpret and elucidate the prediction outcomes derived from multimodal data. Layer-wise relevance propagation was used to explain the layer-wise outcomes in the MRI images. We also incorporated submodular pick local interpretable model-agnostic explanations to interpret the decision-making process based on the tabular data provided. Genetic expression values play a crucial role in AD analysis. We used a graphical gene tree to identify genes associated with the disease. Moreover, a dashboard was designed to display XAI outcomes, enabling experts and medical professionals to easily comprehend the prediction results. |
| first_indexed | 2024-03-07T15:22:10Z |
| format | Article |
| id | doaj.art-a8218f0d05a34f4db043132c16b520be |
| institution | Directory Open Access Journal |
| issn | 2524-4442 |
| language | English |
| last_indexed | 2024-03-07T15:22:10Z |
| publishDate | 2024-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Visual Computing for Industry, Biomedicine, and Art |
| spelling | doaj.art-a8218f0d05a34f4db043132c16b520be2024-03-05T17:35:45ZengSpringerOpenVisual Computing for Industry, Biomedicine, and Art2524-44422024-02-017111210.1186/s42492-024-00154-xConvolutional neural network based data interpretable framework for Alzheimer’s treatment planningSazia Parvin0Sonia Farhana Nimmy1Md Sarwar Kamal2Information Technology, Melbourne PolytechnicFaculty of Economics and Business, University of New South WalesSchool of Computer Science, Faculty of Engineering and IT, University of Technology SydneyAbstract Alzheimer’s disease (AD) is a neurological disorder that predominantly affects the brain. In the coming years, it is expected to spread rapidly, with limited progress in diagnostic techniques. Various machine learning (ML) and artificial intelligence (AI) algorithms have been employed to detect AD using single-modality data. However, recent developments in ML have enabled the application of these methods to multiple data sources and input modalities for AD prediction. In this study, we developed a framework that utilizes multimodal data (tabular data, magnetic resonance imaging (MRI) images, and genetic information) to classify AD. As part of the pre-processing phase, we generated a knowledge graph from the tabular data and MRI images. We employed graph neural networks for knowledge graph creation, and region-based convolutional neural network approach for image-to-knowledge graph generation. Additionally, we integrated various explainable AI (XAI) techniques to interpret and elucidate the prediction outcomes derived from multimodal data. Layer-wise relevance propagation was used to explain the layer-wise outcomes in the MRI images. We also incorporated submodular pick local interpretable model-agnostic explanations to interpret the decision-making process based on the tabular data provided. Genetic expression values play a crucial role in AD analysis. We used a graphical gene tree to identify genes associated with the disease. Moreover, a dashboard was designed to display XAI outcomes, enabling experts and medical professionals to easily comprehend the prediction results.https://doi.org/10.1186/s42492-024-00154-xMultimodalRegion-based convolutional neural networkLayer-wise relevance propagationSubmodular pick local interpretable model-agnostic explanationsGraphical genes treeAlzheimer’s disease |
| spellingShingle | Sazia Parvin Sonia Farhana Nimmy Md Sarwar Kamal Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning Visual Computing for Industry, Biomedicine, and Art Multimodal Region-based convolutional neural network Layer-wise relevance propagation Submodular pick local interpretable model-agnostic explanations Graphical genes tree Alzheimer’s disease |
| title | Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning |
| title_full | Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning |
| title_fullStr | Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning |
| title_full_unstemmed | Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning |
| title_short | Convolutional neural network based data interpretable framework for Alzheimer’s treatment planning |
| title_sort | convolutional neural network based data interpretable framework for alzheimer s treatment planning |
| topic | Multimodal Region-based convolutional neural network Layer-wise relevance propagation Submodular pick local interpretable model-agnostic explanations Graphical genes tree Alzheimer’s disease |
| url | https://doi.org/10.1186/s42492-024-00154-x |
| work_keys_str_mv | AT saziaparvin convolutionalneuralnetworkbaseddatainterpretableframeworkforalzheimerstreatmentplanning AT soniafarhananimmy convolutionalneuralnetworkbaseddatainterpretableframeworkforalzheimerstreatmentplanning AT mdsarwarkamal convolutionalneuralnetworkbaseddatainterpretableframeworkforalzheimerstreatmentplanning |