Rapid classification of tumors that are detected in the medical images is of great importance in the early diagnosis of the disease. In this paper, a new liver and brain tumor classification method is proposed by using the power of convolutional neural network (CNN) in feature extraction, the power of discrete wavelet transform (DWT) in signal processing, and the power of long short-term memory (LSTM) in signal classification. A CNN–DWT–LSTM method is proposed to classify the computed tomography (CT) images of livers with tumors and to classify the magnetic resonance (MR) images of brains with tumors. The proposed method classifies liver tumors images as benign or malignant and then classifies brain tumor images as meningioma, glioma, and pituitary. In the hybrid CNN–DWT–LSTM method, the feature vector of the images is obtained from pre-trained AlexNet CNN architecture. The feature vector is reduced but strengthened by applying the single-level one-dimensional discrete wavelet transform (1-D DWT), and it is classified by training with an LSTM network. Under the scope of the study, images of 56 benign and 56 malignant liver tumors that were obtained from Fırat University Research Hospital were used and a publicly available brain tumor dataset were used. The experimental results show that the proposed method had higher performance than classifiers, such as K-nearest neighbors (KNN) and support vector machine (SVM). By using the CNN–DWT–LSTM hybrid method, an accuracy rate of 99.1% was achieved in the liver tumor classification and accuracy rate of 98.6% was achieved in the brain tumor classification. We used two different datasets to demonstrate the performance of the proposed method. Performance measurements show that the proposed method has a satisfactory accuracy rate at the liver tumor and brain tumor classifying.

Steinstrasse is an important complication following extracorporeal shock wave lithotripsy; however, predictive models for risk factors in pediatric populations remain limited. This study aimed to develop and externally validate an explainable machine learning model for predicting steinstrasse formation after ESWL in children. This two-center retrospective study included 807 pediatric patients (< 18 years) who underwent ESWL for renal stones (2015–2025). The internal cohort comprised 685 patients (Adıyaman), while the external validation cohort consisted of 122 patients (Adana). Twenty-six preoperative variables were evaluated. Optimal predictors were identified through consensus-based feature selection using eight algorithms. Thirteen machine learning algorithms were compared using nested cross-validation. Model interpretability was assessed through SHAP, LIME, and partial dependence analyses. The overall steinstrasse incidence was 10.5% (85/807). Nine predictors were selected: S.T.O.N.E. Score, Triple-D Score, age, stone perimeter, stone depth, Hounsfield unit, stone volume, distal ureteral diameter, and skin-to-stone distance. XGBoost demonstrated optimal external validation performance (AUC = 0.949, sensitivity = 90%, specificity = 99.1%, MCC = 0.891) and exhibited excellent generalizability (ΔAUC = 0.001). Explainable artificial intelligence analyses identified age (mean|SHAP|=1.965) and distal ureteral diameter (mean|SHAP|=1.575) as dominant predictors with significant interaction (SHAP = 0.458). Decision curve analysis confirmed clinical utility across a threshold range of 2%–98%. This externally validated model accurately predicts steinstrasse formation using routine preoperative parameters. Integration of patient age, ureteral anatomy, and stone characteristics may guide decisions between ESWL, prophylactic stenting, or alternative endoscopic approaches in pediatric patients.

To evaluate the performance of a hybrid deep learning architecture, MaxViT-T, for fine-grained dental age estimation (DAE) and coarse-grained age-group classification using panoramic radiographs, and to interpret the model's decision-making process through Explainable AI (XAI). A dataset of n = 2,761 panoramic radiographs from patients aged 6-18 years was used. Two classification tasks were performed: a 13-class fine-grained age estimation and a 3-group coarse-grained age classification (age ranges 6-9, 10-13, and 14-18 years, approximating the early mixed, late mixed, and permanent dentition periods). The hybrid MaxViT-T model was compared against ten other architectures, including CNNs and Transformers, using 5-fold stratified cross-validation. Model interpretability was assessed using Grad-CAM and SHAP. MaxViT-T achieved the highest performance in both tasks. For the 13-class age estimation, it reached an accuracy of 0.4980 with a Mean Absolute Error (MAE) of 0.71 years. Tolerance-based accuracy increased to 84.9% and 96.1% within 1 and 2 years, respectively. For the 3-group age classification, the model achieved 91.13% accuracy and an AUC of 0.9669. XAI analyses confirmed that the model's attention shifted from deciduous teeth and erupting permanent teeth in younger ages to third molar development in older ages, predominantly focusing on the mandibular region. The hybrid MaxViT-T architecture achieved the highest accuracy for dental age estimation among the evaluated models, although its advantage over the leading CNN and Transformer architectures was not statistically significant. Its decision behavior aligned with established odontogenic developmental landmarks, supporting the biological plausibility of the learned features.