Deep Learning in the Classification of Stage of Liver Fibrosis in Chronic Hepatitis B with Magnetic Resonance ADC Images

Abstract

Liver fibrosis in chronic hepatitis B is the pathological repair response of the liver to chronic injury, which is a key step in the development of various chronic liver diseases to cirrhosis and an important link affecting the prognosis of chronic liver diseases. The further development of liver fibrosis in chronic hepatitis B can lead to the disorder of hepatic lobule structure, nodular regeneration of hepatocytes, formation of a pseudolobular structure, namely, cirrhosis, clinical manifestations of liver dysfunction, and portal hypertension. So far, the diagnosis of liver fibrosis in chronic hepatitis B has been made manually by doctors. However, this is very subjective and boring for doctors. Doctors are likely to be interfered with by external factors, such as fatigue and lack of sleep. This paper proposed a 5-layer deep convolution neural network structure for the automatic classification of liver fibrosis in chronic hepatitis B. In the 5-layer deep convolution neural network structure, there were three convolution layers and two fully connected layers, and each convolution layer was connected with a pooling layer. 123 ADC images were collected, and the following results were obtained: the accuracy, sensitivity, specificity, precision, F1, MCC, and FMI were 88.13% ± 1.47%, 81.45% ± 3.69%, 91.12% ± 1.72%, 80.49% ± 2.94%, 80.90% ± 2.39%, 72.36% ± 3.39%, and 80.94% ± 2.37%, respectively.

Fuzzy Logic-Based System for Liver Fibrosis Disease

“…9. Ensemble learning Classification accuracy: 75.5% Zhu et al [60] Artificial neural network Classification accuracy: 86% Zhou et al [61] Deep convolution neural network Classification accuracy: 88% Ayeldeen et al [62] Decision tree Classification accuracy: 93.7% Proposed Work Multilayer fuzzy inference system Classification accuracy: 95% Rather than the classification accuracy, the developed system also takes less computational time as compared to the considered papers. This is because, in the methodology part, the inputs are divided into two layers; as a result of it, the rules of the system are also divided into two parts, i.e., 162 rules for layer 1 and 1458 rules for layer 2.…”

Improved segmentation of overlapping red blood cells on malaria blood smear images with TransUNet architecture

“…Moreover, this improved segmentation of RBCs enables the construction of end-to-end malaria classification algorithms where the segmentation is followed by the classification, and more reliable segmentation enhances the quality of the classification. Therefore, the proposed algorithm can be jointly used with one of the classifiers in the literature [9][10][11][12]25,26 for end-to-end malaria classification. Alternatively, in the case of a low number of samples, feature extraction followed by Fuzzy-SVM might be employed for classification, which was reported to perform well by Chowdhary et al 27 On the other hand, even though the Mask-RCNN algorithm, which was proposed in the literature by Loh et al, 17 is capable of end-to-end classification, its accuracy is not comparable to current classifier algorithms, [9][10][11][12] even with the exclusion of labeling healthy RBCs.…”

Cross-Attention and Deep Supervision UNet for Lesion Segmentation of Chronic Stroke

“…In machine learning methods, in addition to model-based Gaussian Naive Bayes, random forest, and k-neighborhood algorithm, there are also deep learning methods taking convolutional neural network (CNN) as an example. Deep learning methods have many mature and robust methods in the field of medical image classification ( Lyu et al, 2021 ; Zhu et al, 2021a , b ). At the same time, there has been much development in the field of medical image segmentation.…”