A Comprehensive Review on Kidney Stone Detection using Machine Learning and Deep Learning Techniques

Kidney Stone Detection Using Medical Imagingand Computational Intelligence - A Review

Nephrolithiasis (kidney stone disease) is a common urological disease that has a high clinical and economic impact. The early diagnosis is needed to avoid complications like obstruction of the ureter, infection, impaired kidney functioning. Traditional imaging modalities, such as ultrasonography, kidney-ureter-bladder radiography, and non-contrast computed tomography, are common but have a number of limitations, specifically their operator dependence, radiation, and low sensitivity to small or radiolucent stones. This review follows a PRISMA-based methodology to conduct a systematic review of studies published between 2015 and 2025 on the topic of computational intelligence methods such as artificial intelligence, machine learning, and deep learning to detect kidney stones based on medical images. Major scientific databases were considered in studies according to imaging modality, preprocessing method, model architecture and performance measures. Deep learning models, especially, Convolutional Neural Networks and U-Net-based frameworks, are highly effective in detection and segmentation tasks and have been reported to have accuracy of 86 to 99.9 percent, Dice coefficients over 0.85 and AUC of up to 0.99 in controlled data. Hybridization to combine ML classifiers, including Support Vector Machines, further improves the performance of classification. Yet, these outcomes are commonly limited through small datasets, class imbalance, external validation, and overfitting, which have an impact on real-life generalization. The use of computational intelligence has greatly improved the detection of kidney stones by enhancing automation, precision, and reproducibility. However, there are still major issues, such as the standardization of the dataset, interpretability of the models, and limitations to the clinical implementation. Explainable AI, federated learning, and 3D volumetric analysis should be prioritized in future research to create diagnostic systems.

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.

Deep Learning-Based Detection of Renal Abnormalities from CT Images: A Study on a Bangladeshi Cohort

An AI-driven computed tomography diagnostic system for the automated detection and classification of renal abnormalities in the Bangladeshi population is presented and Xception showed the best overall performance, indicating its strong capability for reliable renal abnormality classification from CT images.

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

Chronic renal disease classification using the AL-5-ENeT-B4 model from CT images.

Chronic Renal Disease (CRD) is an increasing global health burden, largely driven by the rising prevalence of diabetes and hypertension. Early and accurate identification of renal abnormalities from computed tomography (CT) images is clinically important, yet manual interpretation is time-consuming and conventional machine learning methods often have limited scalability for complex multiclass medical image classification. This study proposes AL-5-ENeT-B4, a modified EfficientNet-B4 architecture enhanc d with five additional layers for automated CRD classification from CT images. The proposed framework is integrated an image preprocessing, data augmentation, stratified 5-fold cross-validation, and deep learning of pre-trained features to classify renal CT scans into one of the four categories: cyst, normal, stone, or tumour. The results of this model were evaluated using 5-fold cross-validation. The proposed model achieved an average K-fold accuracy (99.18%), precision (99.18%), and recall score (99.19%), with an F1-score (99.18%). Furthermore, Grad-CAM visualisation used to provide better interpretability by highlights those renal areas that had clinical significance in relation to the model's decisions. The proposed AL-5-ENeT-B4 model is compared with ResNet50, VGG16, DenseNet121, and ViT-B/16 and demonstrated significantly improved performance achieving an average MCC of 0.9912 and Cohen's Kappa of 0.9912(p < 0.001).

A new approach for lung cancer diagnosis: parallel feature learning

Lung cancer, one of the most common types of cancer worldwide, can be fatal. Early diagnosis saves lives. Computed tomography (CT) is used in the diagnosis of the disease. Since the radiology specialist evaluates this X-ray result, the specialist's interpretation can vary. Furthermore, the analysis by the radiologist is both time-consuming and costly. However, a cancer diagnosis approach based on deep learning models supports the radiologist's decision. In this study, a parallel feature learning architecture developed for lung CT images was designed. This architecture focuses on learning different features from each parallel path by using deformable and dilated convolution layers together. Dilated convolution captures semantic features in images with different dilated rates ratios by expanding receptive field, while deformable convolution better captures structural changes. This mechanism allows for more flexible and distinctive feature extraction without significantly increasing computational complexity. The proposed architecture was tested on three different lung cancer datasets: the Public Lung Cancer Dataset, IQ-OTH/NCCD, and LIDC-IDRI. Experimental findings demonstrate robust and consistent classification performance, achieving accuracy rates of 99.44%, 98.75%, and 98.62%, respectively. This shows that the proposed architecture offers a reliable solution for lung cancer diagnosis.