Developments in AI and Machine Learning for Neuroimaging

O’Sullivan, Shane; Jeanquartier, Fleur; Jean-Quartier, Claire; Holzinger, Andreas; Shiebler, Dan; Moon, Pradip; Angione, Claudio

doi:10.1007/978-3-030-50402-1_18

Cited by 3 publications

(3 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A cloud-based healthcare framework for COVID-19 like pandemics combined imaging data such as CXR, CT, PET with blood pressure, cough sound, and body temperature, for training a DNN model [287]. Hybrid imaging provides additional information from the different image modalities that can significantly increase the investigation and identification of a disease [35]. Two significant issues faced for multimodal imaging are the class imbalances and lack of sufficient labelled data [35].…”

Section: Hybrid/fusion Imaging For Xaimentioning

confidence: 99%

“…Hybrid imaging provides additional information from the different image modalities that can significantly increase the investigation and identification of a disease [35]. Two significant issues faced for multimodal imaging are the class imbalances and lack of sufficient labelled data [35]. The black box and opaque nature of deep neural networks precludes their usefulness despite excellent performance of multimodal methods [288].…”

Section: Hybrid/fusion Imaging For Xaimentioning

confidence: 99%

“…Some of the XAI surveys address the applications in healthcare sector. A survey of XAI in machine learning based clinical decision support system (CDSS) [27], medical image analysis [28,29], interpretable methods for neural networks [30], AI interpretability in radiology [31], trustworthy AI for healthcare [32], AI techniques for COVID-19 [33,34] neuroimaging [35], and oncological radiomics, feature extraction basics and major interpretability methods [36].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Nazir¹,

Dickson²,

Akram³

2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

Section: Hybrid/fusion Imaging For Xaimentioning

confidence: 99%

Section: Hybrid/fusion Imaging For Xaimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Nazir¹,

Dickson²,

Akram³

2023

Computers in Biology and Medicine

View full text Add to dashboard Cite

Bridging Imaging and Clinical Scores in Parkinson’s Progression via Multimodal Self-Supervised Deep Learning

Martinez-Murcia,

Arco,

Jimenez-Mesa

et al. 2024

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Neurodegenerative diseases pose a formidable challenge to medical research, demanding a nuanced understanding of their progressive nature. In this regard, latent generative models can effectively be used in a data-driven modeling of different dimensions of neurodegeneration, framed within the context of the manifold hypothesis. This paper proposes a joint framework for a multi-modal, common latent generative model to address the need for a more comprehensive understanding of the neurodegenerative landscape in the context of Parkinson’s disease (PD). The proposed architecture uses coupled variational autoencoders (VAEs) to joint model a common latent space to both neuroimaging and clinical data from the Parkinson’s Progression Markers Initiative (PPMI). Alternative loss functions, different normalization procedures, and the interpretability and explainability of latent generative models are addressed, leading to a model that was able to predict clinical symptomatology in the test set, as measured by the unified Parkinson’s disease rating scale (UPDRS), with R2 up to 0.86 for same-modality and 0.441 cross-modality (using solely neuroimaging). The findings provide a foundation for further advancements in the field of clinical research and practice, with potential applications in decision-making processes for PD. The study also highlights the limitations and capabilities of the proposed model, emphasizing its direct interpretability and potential impact on understanding and interpreting neuroimaging patterns associated with PD symptomatology.

show abstract

Interpretable Machine Learning with Brain Image and Survival Data

et al. 2022

View full text Add to dashboard Cite

Recent developments in research on artificial intelligence (AI) in medicine deal with the analysis of image data such as Magnetic Resonance Imaging (MRI) scans to support the of decision-making of medical personnel. For this purpose, machine learning (ML) algorithms are often used, which do not explain the internal decision-making process at all. Thus, it is often difficult to validate or interpret the results of the applied AI methods. This manuscript aims to overcome this problem by using methods of explainable AI (XAI) to interpret the decision-making of an ML algorithm in the use case of predicting the survival rate of patients with brain tumors based on MRI scans. Therefore, we explore the analysis of brain images together with survival data to predict survival in gliomas with a focus on improving the interpretability of the results. Using the Brain Tumor Segmentation dataset BraTS 2020, we used a well-validated dataset for evaluation and relied on a convolutional neural network structure to improve the explainability of important features by adding Shapley overlays. The trained network models were used to evaluate SHapley Additive exPlanations (SHAP) directly and were not optimized for accuracy. The resulting overfitting of some network structures is therefore seen as a use case of the presented interpretation method. It is shown that the network structure can be validated by experts using visualizations, thus making the decision-making of the method interpretable. Our study highlights the feasibility of combining explainers with 3D voxels and also the fact that the interpretation of prediction results significantly supports the evaluation of results. The implementation in python is available on gitlab as “XAIforBrainImgSurv”.

show abstract

Developments in AI and Machine Learning for Neuroimaging

Cited by 3 publications

References 62 publications

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Bridging Imaging and Clinical Scores in Parkinson’s Progression via Multimodal Self-Supervised Deep Learning

Interpretable Machine Learning with Brain Image and Survival Data

Contact Info

Product

Resources

About