No abstract

In 2011, Food and Drug Administration (FDA or USFDA) certified the automated cell morphology (ACM) systems for medical use in USA. The brightness, contrast and color appearance are all factors that play a major role in the diagnosis of many blood diseases. Accordingly, enhancement of pathological microscopic image (PMI) is a crucial step to increase the efficiency of computer assisted software. Some of the previous PMI enhancement methods neglected the illumination information and others used a reference image for template matching. These methods worked under strictly controlled conditions. In this paper, a robust technique is proposed for pathological images enhancement based on neutrosophic similarity score scaling. The color image is separated into three channels, and then each channel is represented in the neutrosophic domain into three subsets T, I and F. Neutrosophic similarity score (NSS) under multi-criteria are computed and used to scale the input image. The main contribution of this paper is that red, green and blue coefficients derived from the neutrosophic calculations lead directly to an adaptive pathology image enhancement and take into consideration many color image quality (IQ) parameters like illumination, contrast and color balance where it does not focus on a single IQ parameter like previous methods. In the experiments, several microscopic image quality measurements are utilized to evaluate the proposed method's performance versus the previous enhancement techniques. The experimental results demonstrate that our proposed system is promising with low complexity, adaptive with different resolution and lighting conditions. This provides the basis for automatic medical diagnosis and further processing of medical images.

A lot of studies confirmed the seriousness of breast cancer as the most tumors lethal to women worldwide. Early detection and diagnosis of breast cancer are of great importance to increase treatment options and patients' survival rate. Ultrasound is one of the most frequently used methods to detect and diagnosis breast tumor due to its harmlessness and inexpensiveness. However, problems were found in the tumor diagnosis and classification as benign and malign on ultrasound image for its vagueness, such as speckle noise and low contrast. In this paper, we propose a novel breast tumor classification algorithm that combines texture and morphologic features based on neutrosophic similarity score. Then, a supervised feature selection technique is employed to reduce feature space. Finally, a support vector machine (SVM) classifier is employed to prove the discrimination power of the proposed features set. The proposed system is validated by 112 cases (58 malign, 54 benign). The experimental results show that such features set is promising and 99.1% classification accuracy is achieved.

Echocardiography is an ultrasound-based imaging modality that helps the physician to visualize heart chambers and valves motion activity. Recently, deep learning plays an important role in several clinical computer-assisted diagnostic systems. There is a real need to employ deep learning methodologies to increase such systems. In this paper, we proposed a deep learning system to classify several echocardiography views and identify its physiological location. Firstly, the spatial CNN features are extracted from each frame in the echo-motion. Secondly, we proposed novel temporal features based on neutrosophic sets. The neutrosophic temporal motion features are extracted from echo-motion activity. To extract the deep CNN features, we activated a pre-trained deep ResNet model. Then, both spatial and neutrosophic temporal CNN features were fused based on features concatenation technique. Finally, the fused CNN features were fed into deep long short-term memory network to classify echo-cardio views and identify their location. During our experiments, we employed a public echocardiography dataset that consisted of 432 videos for eight cardio-views. We have investigated several pre-trained network activation performances. ResNet architecture activation achieved the best accuracy score among several pre-trained networks. The Proposed system based on fused spatial neutrosophic temporal deep features achieved 96.3% accuracy and 95.75% sensitivity. For the classification of cardio-views location, the proposed system achieved 99.1% accuracy. The proposed system achieved more accuracy than previous deep learning methods with a significant decrease in the training time cost. The experimental results showed promising results for our proposed approach.

In this paper, a method based on adaptive neutrosphic sets similarity score is proposed in order to detect WBCs from a blood smear microscopic image and segment its components (nucleus and the cytoplasm). The proposed segmentation algorithm can be utilized for fully-automated classification systems, such systems can be either for the healthy WBCs or even for non-healthy WBCs specially the leukemia cells.