Aug 2026· 2026 International Conference on Modern Sustainable Systems (CMSS)· pp. 1367-1373· 0 citations· 24 references
Abstract
Despite the impressive diagnostic accuracy achieved by deep convolutional neural networks (CNNs), their decisionmaking processes are often challenging to interpret, which hinders clinical trust and widespread adoption. This paper introduces an interpretability framework based on activation patching for classifying brain tumor MRIs, which identifies critical feature channels that influence decisions within a trained CNN. The indirect impact of each channel is assessed by observing the changes in classifier logits after substituting the activation of a chosen channel between a clean MRI slice and a contrasting slice at the third rectified convolutional stage. The resulting indirect-effect scores for each channel are utilized to re-weight globally pooled feature representations, which are then classified using a ridge-regularized logistic regression model. To enhance decision transparency while maintaining predictive performance, a convex combination of the CNN classifier and the logistic model is employed. The proposed framework is tested on two publicly accessible benchmark datasets: Br35H for binary tumor detection and the Nackara dataset for four-class brain tumor classification. Experimental outcomes from a deterministic training run yielded classification accuracies of 97.0% and 94.6% for the binary and four-class datasets, respectively The proposed framework provides an interpretable and auditable approach for brain tumor MRI classification. However, further validation using patient-independent, multi-center datasets acquired from different MRI scanners is required before clinical deployment.”,
Brain tumors are a leading cause of cancer-related mortality, and their early and accurate classification from magnetic resonance imaging (MRI) is critical for treatment planning. Manual interpretation is time-consuming and subject to inter-observer variability. This paper presents an automated four-class brain-tumor c...
Jun-Yao Zhang· Applied and Computational En...· 0 citations
This research systematically benchmarks five CNN architectures (VGG19, DenseNet201, ResNet50, Inception-v3, and MobileNet) on balanced and naturally imbalanced MRI datasets, suggesting that VGG19 is particularly good at discriminative performance.
Tegar Anugrah Firdaus, B. Rais, Marcelinus Jonathan Salim et al.· 0 citations
An advanced modularized Convolutional Neural Network that incorporates ConvDAtt block, Complementary Information (CI) downsampling block, and Spatial Pyramid Pooling (SPP) block is introduced that can effectively extract the information features and discriminant features of brain tumor MRI images.
Jin-Can Zhang, Chuan-Qi Cai, Xing-Hua Tan et al.· PLoS ONE· 0 citations
A neurotumor multiclass classifier is presented, which has a probabilistic soft voting ensemble as the classification method, based on the transfer learning model using pre-trained Convolutional Neural Networks (CNNs), using VGG16, ResNet50 and fine-tuned EfficientNetB0 as the basic classifiers.
Anuj Gupta, Anita, Manish Gupta· international journal of eng...· 0 citations
The findings demonstrate the potential of combining complementary transfer-learning models with preprocessing, ensemble fusion, and explainable artificial intelligence for automated brain tumor classification from MRI images.
Ahmed Thijeel· Alkadhim Journal for Compute...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.