Background and Objectives: Breast cancer accounts for 12.5% of all new cancer cases in women worldwide. Early detection significantly improves survival rates, but traditional biomarkers like CA 15-3 and HER2 lack sensitivity and specificity, particularly for early-stage disease. Advances in metabolomics and machine learning, particularly explainable artificial intelligence (XAI), offer new opportunities for identifying robust biomarkers and improving diagnostic accuracy. This study aimed to identify and validate serum-based metabolic biomarkers for breast cancer using advanced metabolomic profiling techniques and a Light Gradient Boosting Machine (LightGBM) model. Additionally, SHapley Additive exPlanations (SHAP) were applied to enhance model interpretability and biological insight. Materials and Methods: The study included 103 breast cancer patients and 31 healthy controls. Serum samples underwent liquid and gas chromatography–time-of-flight mass spectrometry (LC-TOFMS and GC-TOFMS). Mutual Information (MI), Sparse Partial Least Squares (sPLS), Boruta, and Multi-Objective Feature Selection (MOFS) approaches were applied to the data for biomarker discovery. LightGBM, AdaBoost, and Random Forest were employed for classification and to identify class imbalance with the Synthetic Minority Oversampling Technique (SMOTE). SHAP analysis ranked metabolites based on their contribution to model predictions. Results: Compared to other feature selection approaches, the MOFS approach was more robust in terms of predictive performance, and metabolites identified by this method were used in subsequent analyses for biomarker discovery. LightGBM outperformed the AdaBoost and Random Forest models, achieving 86.6% accuracy, 89.1% sensitivity, 84.2% specificity, and an F1-score of 87.0%. SHAP analysis identified 2-Aminobutyric acid, choline, and coproporphyrin as the most influential metabolites, with dysregulation of these markers associated with breast cancer risk. Conclusions: This study is among the first to integrate SHAP explainability with metabolomic profiling, bridging computational predictions and biological insights for improved clinical adoption. This study demonstrates the effectiveness of combining metabolomics with XAI-driven machine learning for breast cancer diagnostics. The identified biomarkers not only improve diagnostic accuracy but also reveal critical metabolic dysregulations associated with disease progression.

Objective: One of the most significant cancers impacting the health of women is breast cancer. This study aimed to provide breast cancer classification (benign and malignant) using the transfer learning method on the ultrasound images.Methods: In the present study, a public imaging dataset was used for the breast cancer classification. Transfer learning technique was implemented for the detection and classification of breast cancer (benign or malignant) based on the ultrasound images. The current research includes data of 150 cases of malignant and 100 normal cases obtained from the Mendeley data. The relevant dataset was partitioned into training (85% of the images) and validation (15% of the images) sets. The present study implemented Teachable Machine (teachablemachine.withgoogle.com) for predicting the benign or malignant of breast cancer tumor based on the ultrasound images.Results: According to the experimental results, accuracy, sensitivity and specificity with 95% confidence intervals were 0.974 (0.923-1.0), 0.957 (0.781-0.999) and 1 (0.782-1.0), respectively.Conclusion: The model proposed in this study gave predictions that could be useful to clinicians in classifying breast cancer based on ultrasound images. Thus, this system can be developed in mobile, web, or alternative environments and offered as a computer-aided system for the use of radiologists, pathologists or other healthcare professionals in hospitals.

Ovarian cancer’s high mortality is primarily due to late-stage diagnosis, underscoring the critical need for improved early detection tools. This study develops and validates explainable artificial intelligence (XAI) models to discriminate malignant from benign ovarian masses using readily available demographic and laboratory data. A dataset of 309 patients (140 malignant, 169 benign) with 47 clinical parameters was analyzed. The Boruta algorithm selected 19 significant features, including tumor markers (CA125, HE4, CEA, CA19-9, AFP), hematological indices, liver function tests, and electrolytes. Five ensemble machine learning algorithms were optimized and evaluated using repeated stratified 5-fold cross-validation. The Gradient Boosting model achieved the highest performance with 88.99% (±3.2%) accuracy, 0.934 AUC-ROC, and 0.782 Matthews correlation coefficient. SHAP analysis identified HE4, CEA, globulin, CA125, and age as the most globally important features. Unlike black-box approaches, our XAI framework provides clinically interpretable decision pathways through LIME and SHAP visualizations, revealing how feature values push predictions toward malignancy or benignity. Partial dependence plots illustrated non-linear risk relationships, such as a sharp increase in malignancy probability with CA125 > 35 U/mL. This explainable approach demonstrates that ensemble models can achieve high diagnostic accuracy using routine lab data alone, performing comparably to established clinical indices while ensuring transparency and clinical plausibility. The integration of state-of-the-art XAI techniques highlights established biomarkers and reveals potential novel contributors like inflammatory and hepatic indices, offering a pragmatic, scalable triage tool to augment existing diagnostic pathways, particularly in resource-constrained settings.

Objective: Since COVID-19 is a worldwide pandemic, COVID-19 detection using a convolutional neural network (CNN) has been an extraordinary research technique. In the reported studies, many models that can predict COVID-19 based on deep learning methods using various medical images have been created; however, clinical decision support systems have been limited. The aim of this study is to develop a successful deep learning model based on X-ray images and a computer-assisted, fast, free and web-based diagnostic tool for accurate detection of COVID-19. Method: In this study a 15-layer CNN model was used to detect COVID-19 using X-ray images, which outperformed many previously published CNN models in terms of classification. The model performance is evaluated according to Accuracy, Matthews Correlation Coefficient (MCC), F1 Score, Specificity, Sensitivity (Recall), Youden’s Index, Precision (Positive Predictive Value: PPV), Negative Predictive Value (NPV), and Confusion Matrix (Classification matrix). In the second phase of the study, the computer-aided diagnostic tool for COVID-19 disease was developed using Python Flask library, JavaScript and Html codes. Results: The model to diagnose COVID-19 has an average accuracy of 98.68 % in the training set and 96.98 % in the testing set. Among the evaluation metrics, the minimum value is 93.4 % for MCC and Youden’s index, and the maximum value is 97.8 for sensitivity and NPV. A higher sensitivity value means a lower false negative (FN) value, and a low FN value is an encouraging outcome for COVID-19 cases. This conclusion is crucial because minimizing the overlooked cases of COVID-19 (false negatives) is one of the main goals of this research. Conclusion: In this period when COVID-19 is spreading rapidly around the world, it is thought that the free and web-based COVID-19 X-Ray clinical decision support tool can be a very effective and fast diagnostic tool. The computer-aided system can assist physicians and radiologists in making clinical decisions about the disease, as well as provide support in diagnosis, follow-up, and prognosis. The developed computer-assisted diagnosis tool can be publicly accessed at http://biostatapps.inonu.edu.tr/CSYX/.

Aim: Breast cancer is the leading cause of death among women around the world. Because of its low cost and the fact that it does not emit hazardous radiation, infrared thermography has emerged as a viable approach for diagnosing the condition in young women. This study aims to create a computer-aided diagnostic system that can process thermographic breast cancer images and classify breast cancer with pre-trained networks in order to use thermography as a diagnostic method. Materials and Methods: In this study, an open-access data set consisting of thermographic breast cancer images was used for diagnostic purposes. The data set consists of 179 healthy images and 101 images from patients. The images were converted from .txt format to .jpeg format. The data set is acquired from http://visual.ic.uff.br/dmi/. In this study, various pre-trained networks were used to reduce the training time. Different metrics were employed to assess the performance of the models. Results: The images obtained during the modeling phase were used to display both breasts in the image without distinguishing the right and left breasts, that is, without fragmenting the images. According to the results of the different pre-trained network models after the data preprocessing stages, the best classification performance was achieved for the ResNet50V2 model with an accuracy value of 0.996. Conclusion: In this study, a computer-aided diagnosis system was created by developing an interface for breast cancer classification from thermographic images in addition to experimental findings. The web software based on the proposed models has provided promising predictions of breast cancer from thermographic images. The developed software can help medical and other healthcare professionals easily spot breast cancer.

Aim: The goal of this study is to produce user-friendly software for healthcare professionals with various approaches such as detection, identification, classification, and tracking of polyps contained in endoscopic images utilizing appropriate video/image processing techniques and CNN architecture. Material and Method: There were 345 photos in total in the study. These photographs are images depicting anatomical milestones, clinical findings, or gastrointestinal procedures in the digestive tract that have been documented and validated by medical specialists (skilled endoscopists). Each class has hundreds of images. The photos were downloaded from https://datasets.simula.no/kvasir, which is a free source for educational and research purposes. In the modeling phase, CNN and the Max-Margin object detection technique (MMOD), one of the deep neural network designs in the Dlib package, were employed. The data set was separated as 80% training and 20% test dataset using the simple cross-validation method (hold-out). Precision, recall, F1-score, average precision (AP), mean average precision (mAP), ideal localization recall precision (oLRP), mean optimal LRP (moLRP), and intersection over union (IoU) were used to evaluate model performance. Results: When the previously described steps were performed on the open-access video image dataset of endoscopic polyps in the current study, all performance metrics examined in the training dataset received a value of 1, whereas, in the test dataset precision, sensitivity, F1-score, AP, mAP, oLRP, and moLRP were 98%, 90%, 94%, 89%, 89%, 48%, and 48% respectively. Conclusion: The proposed approach was found to make accurate predictions in the diagnosis of gastrointestinal polyps based on the values of the calculated performance criteria.