Computer-aided systems for skin lesion diagnosis is a growing area of research. Recently, researchers have shown an increasing interest in developing computer-aided diagnosis systems. This paper aims to review, synthesize and evaluate the quality of evidence for the diagnostic accuracy of computer-aided systems. This study discusses the papers published in the last five years in ScienceDirect, IEEE, and SpringerLink databases. It includes 53 articles using traditional machine learning methods and 49 articles using deep learning methods. The studies are compared based on their contributions, the methods used and the achieved results. The work identified the main challenges of evaluating skin lesion segmentation and classification methods such as small datasets, ad hoc image selection and racial bias.

https://www.mdpi.com/2075-4418/11/8/1390/pdf

Machine Learning and Deep Learning Methods for Skin Lesion Classification and Diagnosis: A Systematic Review

Melanoma remains the most harmful form of skin cancer. Convolutional neural network (CNN) based classifiers have become the best choice for melanoma detection in the recent era. The research has indicated that classifiers based on CNN classify skin cancer images equivalent to dermatologists, which has allowed a quick and life-saving diagnosis. This study provides a systematic literature review of the latest research on melanoma classification using CNN. We restrict our study to the binary classification of melanoma. In particular, this research discusses the CNN classifiers and compares the accuracies of these classifiers when tested on non-published datasets. We conducted a systematic review of existing literature, identifying the literature through a systematic search of the IEEE, Medline, ACM, Springer, Elsevier, and Wiley databases. A total of 5112 studies were identified out of which 55 well-reputed studies were selected. The main objective of this study is to collect state of the art research which identify the recent research trends, challenges and opportunities for melanoma diagnosis and investigate the existing solutions for the diagnosis of melanoma detection using deep learning. Moreover, proposed taxonomy for melanoma detection has been presented that summarizes the broad variety of existing melanoma detection solutions. Lastly, proposed model, challenges and opportunities have been presented which helps the researchers in the domain of melanoma detection.

/pdf/malignant-melanoma-classification-using-deep-learning-1f9b6cq3y0.pdf

Malignant Melanoma Classification Using Deep Learning: Datasets, Performance Measurements, Challenges and Opportunities

Accurate breast cancer detection using automated algorithms remains a problem within the literature. Although a plethora of work has tried to address this issue, an exact solution is yet to be found. This problem is further exacerbated by the fact that most of the existing datasets are imbalanced, i.e., the number of instances of a particular class far exceeds that of the others. In this paper, we propose a framework based on the notion of transfer learning to address this issue and focus our efforts on histopathological and imbalanced image classification. We use the popular VGG-19 as the base model and complement it with several state-of-the-art techniques to improve the overall performance of the system. With the ImageNet dataset taken as the source domain, we apply the learned knowledge in the target domain consisting of histopathological images. With experimentation performed on a large-scale dataset consisting of 277,524 images, we show that the framework proposed in this paper gives superior performance than those available in the existing literature. Through numerical simulations conducted on a supercomputer, we also present guidelines for work in transfer learning and imbalanced image classification.

Imbalanced Breast Cancer Classification Using Transfer Learning

The application of deep learning methods to diagnose diseases has become a new research topic in the medical field. In the field of medicine, skin disease is one of the most common diseases, and its visual representation is more prominent compared with the other types of diseases. Accordingly, the use of deep learning methods for skin disease image recognition is of great significance and has attracted the attention of researchers. In this study, we review 45 research efforts on the identification of skin disease by using deep learning technology since 2016. We analyze these studies from the aspects of disease type, data set, data processing technology, data augmentation technology, model for skin disease image recognition, deep learning framework, evaluation indicators, and model performance. Moreover, we summarize the traditional and machine learning-based skin disease diagnosis and treatment methods. We also analyze the current progress in this field and predict four directions that may become the research topic in the future. Our results show that the skin disease image recognition method based on deep learning is better than those of dermatologists and other computer-aided treatment methods in skin disease diagnosis, especially the multi deep learning model fusion method has the best recognition effect.

/pdf/deep-learning-in-skin-disease-image-recognition-a-review-1kcyd8abr8.pdf

Deep Learning in Skin Disease Image Recognition: A Review

Melanoma is a serious skin disease. Automatic recognition of this lesion by dermoscopic images is a difficult task. Recently, the deep learning paradigm has become a good alternative to detect different types of diseases. In this article, we propose a new deep learning system for melanoma detection. The system consists of three steps: pre-processing, segmentation and classification. The particularity of this work is the introduction of two new deep learning network architectures, W-net and Inception-Resnet, to solve, respectively, the problem of segmentation and the problem of classification. W-net is composed of a ResNet Encoder-Decoder, a ConvNet Encoder-Decoder and a Feature Pyramid network. The use of two concatenated encoder-decoder architectures has significantly improved the segmentation results. Inception-Resnet includes an Inception-Resnet block, which is a fusion of inception with the residual neural network. With this architecture, classification is much more robust. We evaluated the proposed system on the PH2 dataset and on the International Skin Imaging Collaboration datasets (ISIC 2016, ISIC 2017 and ISIC 2018). The results are discussed in terms of accuracy, sensitivity, specificity, dice coefficient and precision. The comparison of the proposed approach with other related work confirmed the advantages of our technique.

W-net and inception residual network for skin lesion segmentation and classification

Melanoma is one of the four major types of skin cancers caused by malignant growth in the melanocyte cells. It is the rarest one, accounting to only 1% of all skin cancer cases. However, it is the deadliest among all the skin cancer types. Owing to its rarity, efficient diagnosis of the disease becomes rather difficult. Here, a deep depthwise separable residual convolutional algorithm is introduced to perform binary melanoma classification on a dermoscopic skin lesion image dataset. Prior to training the model with the dataset noise removal from the images using non-local means filter is performed followed by enhancement using contrast-limited adaptive histogram equilisation over discrete wavelet transform algorithm. Images are fed to the model as multi-channel image matrices with channels chosen across multiple color spaces based on their ability to optimize the performance of the model. Proper lesion detection and classification ability of the model are tested by monitoring the gradient weighted class activation maps and saliency maps, respectively. Dynamic effectiveness of the model is shown through its performance in multiple skin lesion image datasets. The proposed model achieved an ACC of 99.50% on international skin imaging collaboration (ISIC), 96.77% on PH2, 94.44% on DermIS and 95.23% on MED-NODE datasets.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-ipr.2018.6669

Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network

In this paper we propose a Transposed Convolutional Recurrent Neural Network (TCRNN) architecture for polyphonic sound event recognition. Transposed convolution layer, which caries out a regular convolution operation but reverts the spatial transformation and it is combined with a bidirectional Recurrent Neural Network (RNN) to get TCRNN. Instead of the traditional mel spectrogram features, the proposed methodology incorporates mel-IFgram (Instantaneous Frequency spectrogram) features. The performance of the proposed approach is evaluated on sound events of publicly available TUT-SED 2016 and Joint sound scene and polyphonic sound event recognition datasets. Results show that the proposed approach outperforms state-of-the-art methods.

Polyphonic Sound Event Detection Using Transposed Convolutional Recurrent Neural Network

Genes are parts of a DNA sequence responsible for protein synthesis. Splicing more specifically refers to a post-transcriptional modification that is responsible for multiple protein synthesis from a single gene. The classification of the splice junction has remained quite a challenging task in the field of bioinformatics and is equally important as the synthesized proteins are responsible for the unique characteristics observed in different living organisms. In this study, we propose a state of the art algorithm in splice junction prediction from DNA sequence using a multilayered stacked RNN model, which achieves an overall accuracy of 99.95% and an AUROC score of 1.0 for exon-intron, intron-exon as well as no-junction classification.

Splice Junction Prediction in DNA Sequence Using Multilayered RNN Model

Basal cell carcinoma and squamous cell carcinoma are known to be the two most widespread variety of skin cancer. In this study, we introduce a novel state of the art deep neural network for skin carcinoma detection. The proposed network requires training two identical subnetworks to perform extensive feature extraction for accurate classification. These subnetworks are designed following the deep residual learning paradigm to boost up the loss optimization. The units in each convolution layer use the separable convolution algorithm in order to conserve parameter space, which in turn allows us to design the costly classification network architecture described in this study. Our model achieved an AUROC score of \(0.997\), \(1.000\) and \(0.998\) for basal cell carcinoma, squamous cell carcinoma, and benign skin lesion classification respectively. Here, we explain the working of the aforementioned network and discuss in details the state of the art performance achieved by it.

A Novel Approach for Automatic Diagnosis of Skin Carcinoma from Dermoscopic Images Using Parallel Deep Residual Networks

Invasive ductal carcinoma (IDC), which is also sometimes known as the infiltrating ductal carcinoma, is the most regular form of breast cancer. It accounts to about 80% of all breast cancers. According to American Cancer Society [1], more than 180, 000 women in the United States are diagnosed with invasive breast cancer each year. The survival rate associated with this form of cancer is about 77% to 93% depending on the stage at which they are being diagnosed. The invasiveness and the frequency of the occurrence of these disease makes it one of the difficult cancers to be diagnosed. Our proposed methodology involves diagnosing the invasive ductal carcinoma with a deep residual convolution network to classify the IDC affected histopathological images from the normal images. The dataset for the purpose used is a benchmark dataset known as the Breast Histopathology Images [2]. The microscopic RGB images are converted into a seven channel image matrix, which are then fed to the network. The proposed model produces a 99.29% accurate approach towards prediction of IDC in the histopathology images with an AUROC score of 0.9996. Classification ability of the model is tested using standard performance metrics. The following methodology has been described in the next sections. Index Terms–Residual learning, CIELAB color space, Grad-CAM, Contrast adaptive histogram equalization (CLAHE), Gaussian filtering

Chandra Churh Chatterjee

Papers

Diagnosis of melanoma from dermoscopic images using a deep depthwise separable residual convolutional network

Polyphonic Sound Event Detection Using Transposed Convolutional Recurrent Neural Network

Splice Junction Prediction in DNA Sequence Using Multilayered RNN Model

A Novel Approach for Automatic Diagnosis of Skin Carcinoma from Dermoscopic Images Using Parallel Deep Residual Networks

A Novel method for IDC Prediction in Breast Cancer Histopathology images using Deep Residual Neural Networks