Implementation of model explainability for a basic brain tumor detection using convolutional neural networks on MRI slices

Windisch, Paul; Weber, Pascal; Fürweger, Christoph; Ehret, Felix; Kufeld, Markus; Zwahlen, Daniel R.; Muacevic, Alexander

doi:10.1007/s00234-020-02465-1

Cited by 49 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of Grad-CAM in this study provided important information and led us to evaluate the performance of the model on non-contrast-enhanced slices. Explainable AI has seen increased use in machine learning in general as well as machine learning in medicine in particular and has been shown to benefit the development of models in various ways [30]. Furthermore, understanding the decisions of a model is important to enable the adoption of a model by clinicians as they are less likely to use something that is deemed a "black box" [31].…”

Section: Discussionmentioning

confidence: 99%

Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices—A Feasibility Study

Sager

Näf

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

Introduction: Many proposed algorithms for tumor detection rely on 2.5/3D convolutional neural networks (CNNs) and the input of segmentations for training. The purpose of this study is therefore to assess the performance of tumor detection on single MRI slices containing vestibular schwannomas (VS) as a computationally inexpensive alternative that does not require the creation of segmentations. Methods: A total of 2992 T1-weighted contrast-enhanced axial slices containing VS from the MRIs of 633 patients were labeled according to tumor location, of which 2538 slices from 539 patients were used for training a CNN (ResNet-34) to classify them according to the side of the tumor as a surrogate for detection and 454 slices from 94 patients were used for internal validation. The model was then externally validated on contrast-enhanced and non-contrast-enhanced slices from a different institution. Categorical accuracy was noted, and the results of the predictions for the validation set are provided with confusion matrices. Results: The model achieved an accuracy of 0.928 (95% CI: 0.869–0.987) on contrast-enhanced slices and 0.795 (95% CI: 0.702–0.888) on non-contrast-enhanced slices from the external validation cohorts. The implementation of Gradient-weighted Class Activation Mapping (Grad-CAM) revealed that the focus of the model was not limited to the contrast-enhancing tumor but to a larger area of the cerebellum and the cerebellopontine angle. Conclusions: Single-slice predictions might constitute a computationally inexpensive alternative to training 2.5/3D-CNNs for certain detection tasks in medical imaging even without the use of segmentations. Head-to-head comparisons between 2D and more sophisticated architectures could help to determine the difference in accuracy, especially for more difficult tasks.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices—A Feasibility Study

Sager

Näf

et al. 2021

Diagnostics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The interpretability was evaluated with Grad-CAM and Guided Backpropagation for validating the trustworthiness [150]. A pre-trained ResNet50 model was used on IXI dataset of MRI slices for a multiclass classification into a glioblastoma, vestibular schwannoma, or no tumor [152]. Grad-CAM was used for visualisations and helped to identify the tumor location.…”

Section: Magnetic Resonance Imaging (Mri)mentioning

confidence: 99%

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

“…Several XAI methods have been previously proposed for natural image tasks, while little attention has been paid to explain brain imaging applications [ 18 ]. For brain cancer classification, Windisch et al [ 28 ] applied 2D Grad-CAM to generate heatmaps indicating which areas of the input MRI made the classifier decide on the category of the existence of a brain tumor. Similarly, 2D Grad-CAM was used in [ 29 ] to evaluate the performance of three DL models in brain tumor classification.…”

Section: Related Workmentioning

confidence: 99%

Explainability of deep neural networks for MRI analysis of brain tumors

et al. 2022

View full text Add to dashboard Cite

Purpose Artificial intelligence (AI), in particular deep neural networks, has achieved remarkable results for medical image analysis in several applications. Yet the lack of explainability of deep neural models is considered the principal restriction before applying these methods in clinical practice. Methods In this study, we propose a NeuroXAI framework for explainable AI of deep learning networks to increase the trust of medical experts. NeuroXAI implements seven state-of-the-art explanation methods providing visualization maps to help make deep learning models transparent. Results NeuroXAI has been applied to two applications of the most widely investigated problems in brain imaging analysis, i.e., image classification and segmentation using magnetic resonance (MR) modality. Visual attention maps of multiple XAI methods have been generated and compared for both applications. Another experiment demonstrated that NeuroXAI can provide information flow visualization on internal layers of a segmentation CNN. Conclusion Due to its open architecture, ease of implementation, and scalability to new XAI methods, NeuroXAI could be utilized to assist radiologists and medical professionals in the detection and diagnosis of brain tumors in the clinical routine of cancer patients. The code of NeuroXAI is publicly accessible at https://github.com/razeineldin/NeuroXAI.

show abstract

Implementation of model explainability for a basic brain tumor detection using convolutional neural networks on MRI slices

Cited by 49 publications

References 9 publications

Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices—A Feasibility Study

Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices—A Feasibility Study

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

Explainability of deep neural networks for MRI analysis of brain tumors

Contact Info

Product

Resources

About