Diabetic retinopathy (DR) is a major reason for the increased visual loss globally, and it became an important cause of visual impairment among people in 25-74 years of age. The DR significantly affects the economic status in society, particularly in healthcare systems. When timely treatment is provided to the DR patients, approximately 90% of patients can be saved from visual loss. Therefore, it becomes highly essential to classify the stages and severity of DR for the recommendation of required treatments. In this view, this paper introduces a new automated Hyperparameter Tuning Inception-v4 (HPTI-v4) model for the detection and classification of DR from color fundus images. At the preprocessing stage, the contrast level of the fundus image will be improved by the use of contrast limited adaptive histogram equalization (CLAHE) model. Then, the segmentation of the preprocessed image takes place utilizing a histogram-based segmentation model. Afterward, the HPTI-v4 model is applied to extract the required features from the segmented image and it subsequently undergoes classification by the use of a multilayer perceptron (MLP). A series of experiments take place on MESSIDOR (Methods to Evaluate Segmentation and Indexing Techniques in the field of Retinal Ophthalmology) DR dataset to guarantee the goodness of the HPTI-v4 approach and the obtained results clearly exhibited the supremacy of the HPTI-v4 model over the compared methods in a significant way.

Internet of Medical Things (IoMT) is the collection of medical devices and related applications which link the healthcare IT systems through online computer networks. In the field of diagnosis, medical image classification plays an important role in prediction and early diagnosis of critical diseases. Medical images form an indispensable part of a patient's health record which can be applied to control, handle and treat the diseases. But, classification of images is a challenging task in computer-based diagnostics. In this research article, we have introduced a improved classifier i.e., Optimal Deep Learning (DL) for classification of lung cancer, brain image, and Alzheimer’s disease. The researchers proposed the Optimal Feature Selection based Medical Image Classification using DL model by incorporating preprocessing, feature selection and classification. The main goal of the paper is to derive an optimal feature selection model for effective medical image classification. To enhance the performance of the DL classifier, Opposition-based Crow Search (OCS) algorithm is proposed. The OCS algorithm picks the optimal features from pre-processed images, here Multi-texture, grey level features were selected for the analysis. Finally, the optimal features improved the classification result and increased the accuracy, specificity and sensitivity in the diagnosis of medical images. The proposed results were implemented in MATLAB and compared with existing feature selection models and other classification approaches. The proposed model achieved the maximum performance in terms of accuracy, sensitivity and specificity being 95.22%, 86.45 % and 100% for the applied set of images.