Convolutional Neural Networks (CNNs) are the prevalent technology in computer vision and have become increasingly popular for medical imaging data classification and analysis. In this field, due to the scarcity of medical data, pretrained ResNets on ImageNet can be considered a suitable first approach. This paper examines the medical imaging classification accuracy of conventional basic custom CNNs compared to ImageNet pretrained ResNets on various medical datasets in an effort to give more information about the importance of medical data and its preprocessing techniques for disease studies. Microscope-extracted cytological images were examined along with chest X-rays, MRI brain scans, and melanoma photographs. The medical images were examined in various sets, class combinations, and resolutions. Augmented image datasets and asymmetrical training and validation splits among the classes were also examined. Models were developed after they were tested and fine-tuned with respect to their network size, parameter values and network methods, image resolution, size of dataset, multitude, and genre of class. Overfitting was also examined, and comparative studies regarding the computational cost of different models were performed. The models achieved high accuracy in image classification that varies depending on the dataset and can be easily incorporated in future over-the-internet medical decision-supporting (telemedicine) environments. In addition, it appeared that conventional basic custom CNN overperformed ImageNet pretrained ResNets. The obtained results indicate the importance of utilizing medical image data as a testbed for improvements in CNN classification performance and the possibility of using CNNs and data preprocessing techniques for disease studies.

Despite the increasing application of machine learning and computational intelligence algorithms in medicine and physiotherapy, accurate classification and prognosis algorithms for postoperative patients in the rehabilitation phase are still lacking. The present study was carried out in two phases. In Phase I, classification performance of simple machine learning algorithms applied on data of patients suffering of reverse total shoulder arthroplasty (RTSA), examining algorithms’ classification accuracy and patients’ rehabilitation prognosis. In Phase II, hybrid computational intelligence algorithms were developed and applied in order to search for the minimum possible training set that achieves the maximum classification and prognostic performance. The data included features like age and gender, passive range of available motion of all movements (preoperative and postoperative), visual analog pain scale (preoperative and postoperative), and total rehabilitation time. In Phase I, K-nearest neighbors (ΚΝΝ) classification algorithm and K-means clustering algorithm (GAKmeans) were applied. Also, a genetic algorithm (GA)-based clustering algorithm (GAClust) was also applied. To achieve 100% performance on the test set, KNN used 80% of the data in the training set, whereas K-means and GAClust used 90% and 53.3%, respectively. In Phase II, additional computational intelligence algorithms were developed, namely, GAKNN (Genetic Algorithm K-nearest neighbors), GAKmeans, and GA2Clust (genetic algorithm-based clustering algorithm 2), for genetic algorithm optimization of the training set. Genetic algorithm optimization of the training set using hybrid algorithms in Phase II resulted in 100% performance on the test set by using only 35% of the available data for training. The proposed hybrid algorithms can reliably be used for patients’ rehabilitation prognosis.

Within the framework of the ongoing development of application of Machine Learning models in Medicine and Physical Therapy, the development of accurate prognosis algorithms for postoperative patients during the rehabilitation phase remains an area requiring further refinement. This paper examines hybrid Deep Learning models that integrate Convolution Neural Networks, Long Short-Term Memory and Gated Recurrent Unit networks, as well as genetic algorithm optimization for feature selection for predicting the time needed for a patient to rehabilitate. Patient data included features like age, passive range of available movements (preoperative and postoperative) and total rehabilitation time. Genetic Algorithm optimization for feature selection indicated that 4 out of the 16 available features are adequate for predicting rehabilitation time. Hybrid Deep Learning models achieved a Root Mean Squared Error (RMSE) of 12 days (less than 0.4 months) in rehabilitation time prediction, demonstrating good performance on a relatively small dataset of 120 patients.

This study introduces a novel approach for optimizing models that reconstruct high-quality full-dose bone scintigraphy images from their 40% low-dose counterparts using optimized attention-based U-Net architectures. We utilized Genetic and Epigenetic Algorithms (epiGA) hyperparameter optimization of two distinct models: a standard Attention U-Net and an Attention U-Net modified with ResNet blocks. Models were trained using a hybrid Mean Squared Error and Structural Similarity (MSE/SSIM) loss function. Obtained results demonstrated superior performance, achieving an average SSIM of 0.9197 and an average Peak Signal-to-Noise ratio (PSNR) of 34.1516 dB, significantly surpassing the baseline low-dose image quality, by gaining ΔSSIM = 0.0333 and ΔPSNR = 3.0729 dB, due to hyperparameter optimization. Comparative benchmarks against Bayesian optimization revealed that epiGA offers superior search efficiency—exploring twice the architecture space in comparable wall-clock time—while consistently identifying more compact, hardware-efficient solutions. These results highlight the effectiveness of integrating epigenetic mechanisms for robust, scalable hyperparameter tuning in medical image reconstruction.