Computer-assisted diagnostic systems have been developed to aid doctors in diagnosing thyroid-related abnormalities. The aim of this research is to improve the diagnosis accuracy of thyroid abnormality detection models that can be utilized to alleviate undue pressure on healthcare professionals. In this research, we proposed deep learning, metaheuristics, and a MCDM algorithms-based framework to detect thyroid-related abnormalities from ultrasound and histopathological images. The proposed method uses three recently developed deep learning techniques (DeiT, Swin Transformer, and Mixer-MLP) to extract features from the thyroid image datasets. The feature extraction techniques are based on the Image Transformer and MLP models. There is a large number of redundant features that can overfit the classifiers and reduce the generalization capabilities of the classifiers. In order to avoid the overfitting problem, six feature transformation techniques (PCA, TSVD, FastICA, ISOMAP, LLE, and UMP) are analyzed to reduce the dimensionality of the data. There are five different classifiers (LR, NB, SVC, KNN, and RF) evaluated using the 5-fold stratified cross-validation technique on the transformed dataset. Both datasets exhibit large class imbalances and hence, the stratified cross-validation technique is used to evaluate the performance. The MEREC-TOPSIS MCDM technique is used for ranking the evaluated models at different analysis stages. In the first stage, the best feature extraction and classification techniques are chosen, whereas, in the second stage, the best dimensionality reduction method is evaluated in wrapper feature selection mode. Two best-ranked models are further selected for the weighted average ensemble learning and features selection using the recently proposed meta-heuristics FOX-optimization algorithm. The PCA+FOX optimization-based feature selection + random forest model achieved the highest TOPSIS score and performed exceptionally well with an accuracy of 99.13%, F2-score of 98.82%, and AUC-ROC score of 99.13% on the ultrasound dataset. Similarly, the model achieved an accuracy score of 90.65%, an F2-score of 92.01%, and an AUC-ROC score of 95.48% on the histopathological dataset. This study exploits the combination novelty of different algorithms in order to improve the thyroid cancer diagnosis capabilities. This proposed framework outperforms the current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly aid medical professionals by reducing the excessive burden on the medical fraternity.

Approximately 26 million individuals globally struggle with cardiac disease, and the incidence is increasing by 2% each year. To reduce the healthcare burden, the researchers propose various CAD models. Feature extraction and Feature selection are essential in reducing the model complexity and memory requirement. In the proposed research, we investigate the performance of different feature extraction and selection methods using two heart sound datasets. The features are extracted using MFCC and DWT methods from heart sounds. Four feature selection methods (Fisher’s Score, mRMR, ReliefF, and Gini Index) are analyzed and ranked using the D-CRITIC TOPSIS technique. The two best models based on feature selection are utilized in the weighted average ensemble. The weights in ensemble learning are optimized using the Dwarf Mongoose optimization algorithm. The feature fusion model combining DWT and MFCC with mRMR for feature selection achieved the highest performance on the PhysioNet dataset, with an accuracy of 82.70%, an F1-Score of 0.8369, and an AUC-ROC score of 0.9092. The best accuracy, F1-Score, and AUC-ROC score on the PASCAL CHSC dataset are 79.64%, 0.7826, and 0.8116, respectively. The study compared four feature selection methods. The mRMR-based model achieved the highest TOPSIS score and ranked first in the performance table. The findings demonstrate that the mRMR feature selection performed better than other feature selection for both feature extraction methods evaluated in this study. The ensemble model using mRMR and ReliefF outperformed all base models and achieved the highest performance metrics. This study highlighted the enhanced detection of cardiac disorders through the combined effectiveness of feature extraction, feature selection, classification models, and ensemble strategies.