Explainable Kidney Stone Detection and Localization in CT with U-Net, EfficientNet, and Multi-Method XAI

Explainable and reliable kidney CT image classification using self-supervised DeiT-Tiny transformer

Introduction Kidney-related disorders are one of the global health concerns that require timely detection to prevent severe health complications. The use of computed tomography (CT) images for accurate classification of kidney diseases is important. However, it is challenging to differentiate between classes due to the subtle visual differences. This study introduces a novel two-stage deep learning architecture that integrates self-supervised representation learning with supervised classification for kidney CT image analysis using a publicly available kidney CT image dataset. Methods In the first stage, the DINO framework with a Data-efficient Image Transformer (DeiT-Tiny) backbone is used to learn useful features from kidney CT images independent of labels. In the second stage, the pre-trained model is fine-tuned using labeled data to classify kidney abnormalities. To ensure model transparency and clinical trustworthiness, two explainable AI techniques are applied. Grad-CAM++ is used to highlight important regions contributing to predictions in kidney CT images. In addition, DINO’s inherent multi-head self-attention mechanism is analyzed across all attention heads to capture diverse attention patterns. Results and discussion Experimental findings indicate that the proposed framework achieves strong classification performance, with a test accuracy of 99.16%, AUC-ROC of 99.99%, F1 score of 98.97%, precision of 98.90%, and recall of 99.05%, while also providing clear interpretability for automated kidney disease classification. External validation on a CT dataset from Iraq has yielded 97.03% accuracy, supporting the generalizability of the proposed framework.

Explainable deep learning models for kidney stone classification using axial CT scans

A Deep Learning Approach for Automated Kidney Tumor Classification

A hybrid architecture in which ResNet50 is employed for localized spatial feature extraction, while Vision Transformer enables global contextual learning to automatically classify kidney tumors into multiple classes is proposed.

A deep learning-based study on automated CT diagnosis of kidney stones, hydronephrosis and pyonephrosis.

Laplacian sharpening achieves the best performance within the unified MSF-TEA Net framework, with a test accuracy of 94.40% ± 1.13% and an AUC of 99.30%, outperforming the other enhancement strategies.

A Cascaded Deep Learning Framework for Robust Liver CT Segmentation Using ROI Refinement and Patient-Level Cross-Validation

Accurate liver segmentation from computed tomography (CT) images is essential for computer-aided diagnosis, treatment planning, volumetric assessment, and longitudinal monitoring of patients with hepatocellular carcinoma. However, automated segmentation remains challenging because of variations in liver morphology, low-contrast boundaries, pathological abnormalities, and neighbouring abdominal structures with similar intensity characteristics. This study presents a failure-aware cascaded deep learning framework for automated liver CT segmentation using the publicly available HCC-TACE-Seg dataset. The proposed approach first performs coarse liver localisation on the complete CT image and then extracts a region of interest with an additional safety margin. The cropped region is subsequently processed by a high-resolution U-Net++ model with a ResNet34 encoder. A hybrid Dice and binary cross-entropy loss is used during training, while validation-optimised thresholding, largest-component filtering, and morphological hole filling are applied to improve anatomical consistency. Monte Carlo dropout is further incorporated to estimate predictive uncertainty and support case-level quality assessment. Following annotation verification, 103 liver-positive representative CT images were retained after excluding one image with an empty liver mask. Five-fold cross-validation was performed at the available patient-identifier level to prevent samples from the same patient from being distributed across training and testing partitions. The proposed framework achieved a mean Dice similarity coefficient of 0.8171, Intersection over Union of 0.7442, precision of 0.7993, sensitivity of 0.8737, and specificity of 0.9750. Boundary-based evaluation yielded an HD95 of 48.91 pixels, an average symmetric surface distance of 13.41 pixels, and a surface Dice score of 0.4250. Probability calibration produced a Brier score of 0.0418 and an expected calibration error of 0.0811. Uncertainty estimates were additionally used to flag potentially unreliable segmentations for manual review. These findings indicate that cascaded localisation and region-of-interest refinement can provide robust liver segmentation while reducing background interference and supporting uncertainty-informed quality control.

Attention-Guided Mask R-CNN for Liver Tumor Segmentation and Classification from CT Scans: A Tailored Approach

Computed tomography (CT) images have poor tissue contrasts, irregular appearance of lesions, and unclear tumor borders which limit reliable diagnosis of liver malignancy. This paper introduces an attention-controlled automated liver tumor segmentation and classification based on a customized Mask Region Convolutional Neural Network (tm-RCNN) with an addition of Multi-Scale Attention Gate (MSAG). To increase the local contrast and reduce artifacts caused by acquisition, adaptive histogram equalization is used. The suggested MSAG selectively elevates boundary-sensitive features in a variety of spatial resolutions, which allow accurate delineation of lesions within the tm-RCNN decoder. Deep residual features, geometric form descriptors and enhanced median binary pattern (e-MBP) textures are extracted using segmented areas and then classified using a hybrid SqueezeNet DeepMaxout ensemble with score-level fusion. It has been experimentally validated on two benchmarking CT sets with a higher performance that achieves a Dice coefficient of 0.9587, classification accuracy of 0.936, sensitivity of 0.961 and less computational time of 64.21 s than the state-of-the-art. These findings affirm the usefulness and clinical appropriateness of the suggested framework.