Grad-CAM helps interpret the deep learning models trained to classify multiple sclerosis types using clinical brain magnetic resonance imaging

Zhang, Yunyan; Hong, Daphne; McClement, Daniel G.; Oladosu, Olayinka; Pridham, Glen; Slaney, Garth

doi:10.1016/j.jneumeth.2021.109098

Cited by 64 publications

(29 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Grad-CAM extends this by making CAMs applicable to a variety of CNNs, including those that use fully-connected deep layers, as used here. In recent years, they have been applied to various deep learning MRI classification tasks ( Lee, Lee, Lee, Park, Yoon, 2018 , Zhang, Hong, McClement, Oladosu, Pridham, Slaney, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

Deep learning for sex classification in resting-state and task functional brain networks from the UK Biobank

Leming

Suckling

2021

NeuroImage

View full text Add to dashboard Cite

Highlights Applied deep learning to sex classification in UK BioBank fMRI connectomes. Deep learning classifies sex better in resting-state than in task fMRI. Algorithm to balance out multiple confounds from an fMRI dataset. Adapted two deep learning visualization methods to fMRI connectome classification. Analyzed role of three brain a priori networks in sex classification.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep learning for sex classification in resting-state and task functional brain networks from the UK Biobank

Leming

Suckling

2021

NeuroImage

View full text Add to dashboard Cite

show abstract

“…Chen and colleagues [5] showed that integrating interpretable methods can increase up to 3.5% in the accuracy score of trained models. Zhang and colleagues [34] integrated a Grad-CAM derived heatmap into their deep learning models to develop an effective strategy for identifying the brain areas underlying disease development in multiple sclerosis. A future work could be the inclusion of explainable AI approaches in the training phase to enhance both model classification and localization accuracy.…”

Section: Discussionmentioning

confidence: 99%

Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization

Esmaeili

Vettukattil

Banitalebi

et al. 2021

JPM

View full text Add to dashboard Cite

Primary malignancies in adult brains are globally fatal. Computer vision, especially recent developments in artificial intelligence (AI), have created opportunities to automatically characterize and diagnose tumor lesions in the brain. AI approaches have provided scores of unprecedented accuracy in different image analysis tasks, including differentiating tumor-containing brains from healthy brains. AI models, however, perform as a black box, concealing the rational interpretations that are an essential step towards translating AI imaging tools into clinical routine. An explainable AI approach aims to visualize the high-level features of trained models or integrate into the training process. This study aims to evaluate the performance of selected deep-learning algorithms on localizing tumor lesions and distinguishing the lesion from healthy regions in magnetic resonance imaging contrasts. Despite a significant correlation between classification and lesion localization accuracy (R = 0.46, p = 0.005), the known AI algorithms, examined in this study, classify some tumor brains based on other non-relevant features. The results suggest that explainable AI approaches can develop an intuition for model interpretability and may play an important role in the performance evaluation of deep learning models. Developing explainable AI approaches will be an essential tool to improve human–machine interactions and assist in the selection of optimal training methods.

show abstract

“…The end-to-end gradient-based saliency mapping approach can be readily applied to any black box AI model without knowledge of the network architecture and the weights of the connections. The saliency map obtained with this method can be compared with that obtained by the Grad-CAM method 24 , 27 , 28 . The method can be applied to models for which an interpretation may have not been available 29 , 30 .…”

Section: Discussionmentioning

confidence: 99%

Probing an AI regression model for hand bone age determination using gradient-based saliency mapping

Wang

2021

Sci Rep

View full text Add to dashboard Cite

Understanding how a neural network makes decisions holds significant value for users. For this reason, gradient-based saliency mapping was tested on an artificial intelligence (AI) regression model for determining hand bone age from X-ray radiographs. The partial derivative (PD) of the inferred age with respect to input image intensity at each pixel served as a saliency marker to find sensitive areas contributing to the outcome. The mean of the absolute PD values was calculated for five anatomical regions of interest, and one hundred test images were evaluated with this procedure. The PD maps suggested that the AI model employed a holistic approach in determining hand bone age, with the wrist area being the most important at early ages. However, this importance decreased with increasing age. The middle section of the metacarpal bones was the least important area for bone age determination. The muscular region between the first and second metacarpal bones also exhibited high PD values but contained no bone age information, suggesting a region of vulnerability in age determination. An end-to-end gradient-based saliency map can be obtained from a black box regression AI model and provide insight into how the model makes decisions.

show abstract

Grad-CAM helps interpret the deep learning models trained to classify multiple sclerosis types using clinical brain magnetic resonance imaging

Cited by 64 publications

References 16 publications

Deep learning for sex classification in resting-state and task functional brain networks from the UK Biobank

Deep learning for sex classification in resting-state and task functional brain networks from the UK Biobank

Explainable Artificial Intelligence for Human-Machine Interaction in Brain Tumor Localization

Probing an AI regression model for hand bone age determination using gradient-based saliency mapping

Contact Info

Product

Resources

About