As an analytic tool in medicine, particularly in radiology, deep learning is gaining much attention and opening a new way for disease diagnosis. Nonetheless, it is rather challenging to acquire large‐scale detailed labelled datasets in the field of medical imaging. In fact, transfer learning provides a possible way to resolve this issue to a certain extent such that the parameter learning of a neural network starts with its pre‐trained weights learned from a large‐scale dataset of certain similar task, and fine‐tunes on a small comprehensively annotated dataset for the particular target task. The main aim of this study is to apply the deep learning model to detect the synovial fluid of human knee joint from magnetic resonance images. A specialized convolutional neural network architecture is proposed for automated detection of human knee joint's synovial fluid. Two independent datasets are used in the training, development, and evaluation of the proposed model. It is demonstrated by the experimental results that the proposed model obtains high sensitivity, specificity, precision, and accuracy to the detection of human knee joint's synovial fluid. As a result, this proposed approach provides a novel and feasible way for automating and expediting the synovial fluid analysis.

Human infertility is considered as a serious disease of the reproductive system that affects more than 10% of couples across the globe and over 30% of the reported cases are related to men. The crucial step in the assessment of male infertility and subfertility is semen analysis that strongly depends on the sperm head morphology, i.e., the shape and size of the head of a spermatozoon. However, in medical diagnosis, the morphology of the sperm head is determined manually, and heavily depends on the expertise of the clinician. Moreover, this assessment as well as the morphological classification of human sperm heads are laborious and non-repeatable, and there is also a high degree of inter and intra-laboratory variability in the results. In order to overcome these problems, we propose a specialized convolutional neural network (CNN) architecture to accurately classify human sperm heads based on sperm images. It is carefully designed with several layers, and multiple filter sizes, but fewer filters and parameters to improve efficiency and effectiveness. It is demonstrated that our proposed architecture outperforms state-of-the-art methods, exhibiting 88% recall on the SCIAN dataset in the total agreement setting and 95% recall on the HuSHeM dataset for the classification of human sperm heads. Our proposed method shows the potential of deep learning to surpass embryologists in terms of reliability, throughput, and accuracy.

Increase in popularity of deep learning in various research areas leads to use it in resolving image classification problems. The objective of this research is to compare and to find learning algorithms which perform better for image classification task with small dataset. We have also tuned the hyperparameters associated with optimizers and models to improve performance. First, we performed several experiments using eight learning algorithms to come closer to optimal values of hyperparameters. Then, we executed twenty-four final experiments with near optimum values of hyperparameters to find the best learning algorithm. Experimental results showed that the AdaGrad learning algorithm achieves better accuracy, lesser training time, as well as fewer memory utilization compared to the rest of the learning algorithms.