Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Texture features for image classification and retrieval.

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region's image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

/pdf/classification-of-skin-disease-using-deep-learning-neural-2tijopzkl2.pdf

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Novel coronavirus disease (nCOVID-19) is the most challenging problem for the world. The disease is caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2), leading to high morbidity and mortality worldwide. The study reveals that infected patients exhibit distinct radiographic visual characteristics along with fever, dry cough, fatigue, dyspnea, etc. Chest X-Ray (CXR) is one of the important, non-invasive clinical adjuncts that play an essential role in the detection of such visual responses associated with SARS-COV-2 infection. However, the limited availability of expert radiologists to interpret the CXR images and subtle appearance of disease radiographic responses remains the biggest bottlenecks in manual diagnosis. In this study, we present an automatic COVID screening (ACoS) system that uses radiomic texture descriptors extracted from CXR images to identify the normal, suspected, and nCOVID-19 infected patients. The proposed system uses two-phase classification approach (normal vs. abnormal and nCOVID-19 vs. pneumonia) using majority vote based classifier ensemble of five benchmark supervised classification algorithms. The training-testing and validation of the ACoS system are performed using 2088 (696 normal, 696 pneumonia and 696 nCOVID-19) and 258 (86 images of each category) CXR images, respectively. The obtained validation results for phase-I (accuracy (ACC) = 98.062%, area under curve (AUC) = 0.956) and phase-II (ACC = 91.329% and AUC = 0.831) show the promising performance of the proposed system. Further, the Friedman post-hoc multiple comparisons and z-test statistics reveals that the results of ACoS system are statistically significant. Finally, the obtained performance is compared with the existing state-of-the-art methods.

Coronavirus disease (COVID-19) detection in Chest X-Ray images using majority voting based classifier ensemble

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

Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification.

Extraction of features from cross correlation in space and frequency domains for classification of skin lesions

Optimal selection of features using wavelet fractal descriptors and automatic correlation bias reduction for classifying skin lesions

The development of computer aided diagnosis system has a great impact on early and accurate disease diagnosis. The segmentation of retinal blood vessels aids in identifying the alteration in vessel structure and hence helps to diagnose many diseases such as diabetic retinopathy, glaucoma, hypertension along with some cardiovascular diseases. In this research work, a method is presented for the segmentation of retinal vessel structure from retinal fundus images. 2D wavelet transform assisted morphological gradient operation based ‘Contrast Limited Adaptive Histogram Equalization’ technique has been introduced for the preprocessing of the low contrast fundus images. Morphological gray level hit-or-miss transform with multi-structuring element with varying orientation has been proposed for the separation of blood vessel from its background. Finally a hysteresis thresholding, guided by some morphological operations has been employed to obtain the binary image excluding other unwanted areas. The proposed methodology has been tested on DRIVE database and a maximum accuracy and an average accuracy of 95.65 and 94.31% respectively have been achieved.

Morphological operations with iterative rotation of structuring elements for segmentation of retinal vessel structures

Among the skin cancers, malignant melanoma is of by far the most deadly type. For the early diagnosis of melanoma, computer-aided diagnosis systems for the classification of dermoscopic images have been developed. For accurate image classification, the segmentation of skin lesion area is of prime importance. In this work, mathematical morphology has been used for segmentation for proper identification of skin lesion area. Different shape, texture and color features have been extracted from a set of dermoscopic images and malignant melanomas have been classified using SVM classifier with 85.71% sensitivity.

Saptarshi Chatterjee

Papers

Integration of morphological preprocessing and fractal based feature extraction with recursive feature elimination for skin lesion types classification.

Extraction of features from cross correlation in space and frequency domains for classification of skin lesions

Optimal selection of features using wavelet fractal descriptors and automatic correlation bias reduction for classifying skin lesions

Morphological operations with iterative rotation of structuring elements for segmentation of retinal vessel structures

Mathematical morphology aided shape, texture and colour feature extraction from skin lesion for identification of malignant melanoma