Endometrial cancer (EC) is the most prevalent cancer within the female reproductive system in developed countries. Despite its high incidence, there is currently no established laboratory screening test for EC, making early detection challenging. This study introduces an innovative, minimally invasive, and cost-effective method utilizing three-dimensional fluorescence analysis combined with machine learning algorithms to enhance early EC detection. Intrinsic fluorescence of blood serum samples was measured using a luminescence spectrophotometer, which captured fluorescence spectra as synchronous excitation spectra and visualized them through wavelength contour matrices. The spectral data were processed using machine learning algorithms, including Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD), along with exploratory techniques such as Principal Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA). Fluorescence ratios R300/330 and R360/490, indicative of altered tryptophan metabolism and redox state changes, were identified as fluorescent spectral markers and represent key metabolic biomarkers. These ratios demonstrated high diagnostic efficacy with AUC values of 0.88 and 0.91, respectively. Among the ML algorithms, LR and RF exhibited high sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), showing significant promise for clinical application. After optimization, LR achieved a sensitivity of 0.94, specificity of 0.89, and an impressive AUC value of 0.94. The application of this novel approach in laboratory diagnostics has the potential to significantly enhance early detection and improve prognosis for EC patients.

Application of machine learning techniques in breast cancer detection has significantly advanced due to the availability of annotated mammography datasets. This paper provides a review of mammography studies using key datasets such as CBIS-DDSM, VinDr-Mammo, and CSAW-CC, which play a critical role in training classification and detection models. The analysis of the studies produces a set of data augmentation techniques in mammography, and their impact and performance improvements in detecting abnormalities in breast tissue are studied. The study discusses the challenges of dataset imbalances and presents methods to address this issue, like synthetic data generation and GAN augmentation as potential solutions. The work underscores the importance of dataset design dedicated for experiments, detailed annotations, and the usage of machine learning models and architectures in improving breast cancer screening models, with a focus on BI-RADS classification. Future directions include refining augmentation methods, addressing class imbalance, and enhancing model interpretability through tools like Grad-CAM.