Deep metric attention learning for skin lesion classification in dermoscopy images

Currently, convolutional neural networks (CNNs) have made remarkable achievements in skin lesion classification because of their end-to-end feature representation abilities. However, precise skin lesion classification is still challenging because of the following three issues: (1) insufficient training samples, (2) inter-class similarities and intra-class variations, and (3) lack of the ability to focus on discriminative skin lesion parts. To address these issues, we propose a deep metric attention learning CNN (DeMAL-CNN) for skin lesion classification. In DeMAL-CNN, a triplet-based network (TPN) is first designed based on deep metric learning, which consists of three weight-shared embedding extraction networks. TPN adopts a triplet of samples as input and uses the triplet loss to optimize the embeddings, which can not only increase the number of training samples, but also learn the embeddings robust to inter-class similarities and intra-class variations. In addition, a mixed attention mechanism considering both the spatial-wise and channel-wise attention information is designed and integrated into the construction of each embedding extraction network, which can further strengthen the skin lesion localization ability of DeMAL-CNN. After extracting the embeddings, three weight-shared classification layers are used to generate the final predictions. In the training procedure, we combine the triplet loss with the classification loss as a hybrid loss to train DeMAL-CNN. We compare DeMAL-CNN with the baseline method, attention methods, advanced challenge methods, and state-of-the-art skin lesion classification methods on the ISIC 2016 and ISIC 2017 datasets, and test its generalization ability on the PH2 dataset. The results demonstrate its effectiveness.

Efficient structural pseudoinverse learning-based hierarchical representation learning for skin lesion classification

The success of deep learning in skin lesion classification mainly depends on the ultra-deep neural network and the significantly large training data set. Deep learning training is usually time-consuming, and large datasets with labels are hard to obtain, especially skin lesion images. Although pre-training and data augmentation can alleviate these issues, there are still some problems: (1) the data domain is not consistent, resulting in the slow convergence; and (2) low robustness to confusing skin lesions. To solve these problems, we propose an efficient structural pseudoinverse learning-based hierarchical representation learning method. Preliminary feature extraction, shallow network feature extraction and deep learning feature extraction are carried out respectively before the classification of skin lesion images. Gabor filter and pre-trained deep convolutional neural network are used for preliminary feature extraction. The structural pseudoinverse learning (S-PIL) algorithm is used to extract the shallow features. Then, S-PIL preliminarily identifies the skin lesion images that are difficult to be classified to form a new training set for deep learning feature extraction. Through the hierarchical representation learning, we analyze the features of skin lesion images layer by layer to improve the final classification. Our method not only avoid the slow convergence caused by inconsistency of data domain but also enhances the training of confusing examples. Without using additional data, our approach outperforms existing methods in the ISIC 2017 and ISIC 2018 datasets.

A Computer-Aided Diagnosis System Using Deep Learning for Multiclass Skin Lesion Classification

In the USA, each year, almost 5.4 million people are diagnosed with skin cancer. Melanoma is one of the most dangerous types of skin cancer, and its survival rate is 5%. The development of skin cancer has risen over the last couple of years. Early identification of skin cancer can help reduce the human mortality rate. Dermoscopy is a technology used for the acquisition of skin images. However, the manual inspection process consumes more time and required much cost. The recent development in the area of deep learning showed significant performance for classification tasks. In this research work, a new automated framework is proposed for multiclass skin lesion classification. The proposed framework consists of a series of steps. In the first step, augmentation is performed. For the augmentation process, three operations are performed: rotate 90, right-left flip, and up and down flip. In the second step, deep models are fine-tuned. Two models are opted, such as ResNet-50 and ResNet-101, and updated their layers. In the third step, transfer learning is applied to train both fine-tuned deep models on augmented datasets. In the succeeding stage, features are extracted and performed fusion using a modified serial-based approach. Finally, the fused vector is further enhanced by selecting the best features using the skewness-controlled SVR approach. The final selected features are classified using several machine learning algorithms and selected based on the accuracy value. In the experimental process, the augmented HAM10000 dataset is used and achieved an accuracy of 91.7%. Moreover, the performance of the augmented dataset is better as compared to the original imbalanced dataset. In addition, the proposed method is compared with some recent studies and shows improved performance.

The cellular biology of atherosclerosis with atherosclerotic lesion classification and biomarkers

Background Atherosclerosis is a chronic lipid-driven inflammatory disease with infiltration of low-density lipoprotein and is considered as the pivotal step in plaque formation. The aim of the review is to get into the fine details of pathophysiologic mechanisms responsible for atherosclerosis with atherosclerotic lesion classification. It also provides a summary of current biomarkers other than the traditional risk factors so that new treatment modalities can emerge and reduce the morbidity and mortality associated with atherosclerosis. Main body In the classification of atherosclerosis made by American Heart Association (AHA), AHA Type I lesion is the earliest vascular change described microscopically. AHA Type II lesion is primarily composed of abundant macrophages. AHA Type III lesion is the earliest of progressive lesions, while AHA Type IV lesion consists of an acellular necrotic core. Various biomarkers are implicated in different stages of the pathophysiological mechanism of plaque formation and evolution. C Reactive Protein plays a direct role in promoting the inflammatory component of atherosclerosis. Fibrinogen was demonstrated to be elevated among patients with acute thrombosis. Higher leukocyte count is associated with a greater cardiovascular risk. Cytokines have been implicated in atheroma formation and complications. High rates of protease activated receptor expression are also induced by interleukin-6 secretion in atherosclerotic lesions and areas of vascular tissue injury. Cluster of differentiation 40 receptor and its ligand have been also detected in atherosclerotic plaques. Osteopontin, acidic phosphoprotein, and osteoprotegerin have emerged as novel markers of atherosclerotic plaque composition. There are also overproductions of matrix metalloproteinases in the rupture-prone regions and promote lipid-necrotic core formation in the atherosclerotic plaque. Myeloperoxidase has been proposed as a marker of plaque instability. Oxidized low-density lipoprotein receptor 1 provides a route of entry for oxidized low-density lipoprotein into the endothelium. A human atherosclerotic lesion also expresses lipoprotein-associated phospholipase A2. Short conclusion Atherosclerotic plaques are the battlefield between an unbalanced immune response and lipid accumulation in the intima of arteries. Most of the biomarkers associated with atherosclerosis are indicators of inflammatory response and will also be used for medical purposes.

TopoResNet: A Hybrid Deep Learning Architecture and Its Application to Skin Lesion Classification

The application of artificial intelligence (AI) to various medical subfields has been a popular topic of research in recent years. In particular, deep learning has been widely used and has proven effective in many cases. Topological data analysis (TDA)—a rising field at the intersection of mathematics, statistics, and computer science—offers new insights into data. In this work, we develop a novel deep learning architecture that we call TopoResNet that integrates topological information into the residual neural network architecture. To demonstrate TopoResNet, we apply it to a skin lesion classification problem. We find that TopoResNet improves the accuracy and the stability of the training process.