This paper presents a unified deep learning framework for breast cancer detection that generalizes effectively across mammography and histopathology.Using fine-tuned CNN architectures evaluated under a consistent cross-modal protocol, the method achieves stable, high accuracy on both imaging types, demonstrating robustness to domain shifts and heterogeneous clinical conditions.Another key contribution is the integration of model-agnostic (LIME, SHAP) and model-specific (Grad-CAM) explainability techniques, enabling a balanced trade-off between performance and interpretability.This hybrid XAI strategy provides clinically meaningful visual and feature-level insights, supporting transparent, reliable, and multi-modal diagnostic decision-making.

This paper presents a novel end-to-end framework for automated brain tumor analysis and reporting in Low-Grade Gliomas (LGG). It addresses the challenge of bridging the gap between image analysis and clinical reporting by integrating deep learning-based segmentation with large language models. A VGG19-UNet architecture is used to segment brain tumors from MRI scans, achieving state-of-the-art results (Dice: 0.907 and IoU: 0.829). Then, the segmentation output is processed through a feature extraction module that quantifies tumor size, location, shape, and boundaries. These features are transformed into structured prompts for a generative AI model, which produces detailed medical reports in radiological language. A dual-phase evaluation combining quantitative metrics and expert radiologist review confirms that the generated reports are clinically accurate and well-structured. This framework offers a step toward reducing radiologist workload while maintaining diagnostic quality, with applications in workflow optimization, reporting standardization, and support in resource-limited or high-volume environments.

Automated segmentation of the Corpus Callosum (CC) from brain MRI images is essential for the diagnosis and monitoring of neurological disorders. However, substantial vari- ability in MR intensities across different vendors and protocols, as well as differences in the shape and volume of the CC, pose significant challenges to achieving accurate and reliable segmentation. In this study, we propose an efficient segmentation approach using a novel Vector Quantization-based U-Net (VQ-UNet). Our architecture builds upon the traditional U-Net model by integrating a Vector Quantization (VQ) memory module within the bottleneck layer. This enhancement enriches feature representation while reducing the model’s dependency on large annotated datasets. Additionally, by incorporating saliency map techniques, our model improves interpretability, enabling more trustworthy volumetric quantification of the CC. Experimental results demonstrate that the proposed VQ-UNet significantly outperforms state-of-the-art methods, achieving up to 2% higher Dice scores compared to U-Net variants. We believe this approach paves the way for more reliable CC analysis in clinical settings.

Accurate segmentation of the Corpus Callosum (CC) plays a crucial role in studying brain connectivity and understanding neurological disorders. However, limited availability of annotated data poses a significant challenge for developing robust segmentation models. In order to deal with this issue, we propose in the study an effective approach that combines one-shot learning and a modified multiclass U-Net architecture. The proposed approach represents the first attempt in this context, to the best of our knowledge. We begin by generating additional Ground Truth (GT) data using one-shot learning, effectively expanding the limited annotated dataset. This approach leverages the inherent generalization capability of one-shot learning to predict segmentation for unlabeled data, which are then validated and refined by domain experts. The refined segmentation serves as new GT data, enhancing the training process. To further improve parcellation accuracy, we modify the U-Net architecture to handle the complex task of multiclass CC parcellation. The modified multiclass U-Net effectively captures the intricate features and spatial dependencies within the CC, enabling precise parcellation into distinct sub-regions. The framework has been tested and evaluated on two challenging datasets that are publicly available. The obtained results are promising and show the performance of the proposed solution against geometric methods from the state of the art.

In this paper, a multi-stage deep learning model is proposed for brain glioma tumor detection and segmentation from MRI scans. The model consists of two stages: object detection using YOLOv7 with EfficientNet-B0 backbone, and active contour snake model for boundary refinement and segmentation. The proposed method also includes a customized CNN with feature selection and GRU layer for accurate class label prediction. The proposed model has been trained on the BraTS 2020 dataset and has achieved state-of-the-art performance in terms of accuracy and effectiveness. This proposed method can potentially assist radiologists and clinicians in detecting and segmenting brain tumors in medical images, leading to better diagnosis and treatment planning for patients.

In this paper, we introduce an unsupervised method for the parcellation of the Corpus Callosum (CC) from MRI images. Since there are no visible landmarks within the structure that explicit its parcels, non-geometric CC parcellation is a challenging task especially that almost of proposed methods are geometric or data-based. In fact, in order to subdivide the CC from brain sagittal MRI scans, we adopt the probabilistic neural network as a clustering technique. Then, we use a cluster validity measure based on the maximum entropy (Vmep) to obtain the optimal number of classes. After that, we obtain the isolated CC that we parcel automatically using SLIC (Simple Linear Iterative Clustering) as superpixel segmentation technique. The obtained results on two challenging public datasets prove the performance of the proposed method against geometric methods from the state of the art. Indeed, as best as we know, it is the first work that investigates the validation of a CC parcellation method on ground-truth datasets using many objective metrics.