Deep Learning Approaches Towards Skin Lesion Segmentation and Classification from Dermoscopic Images - A Review.

BACKGROUND: Automated intelligent systems for unbiased diagnosis are primary requirement for the pigment lesion analysis. It has gained the attention of researchers in the last few decades. These systems involve multiple phases such as pre-processing, feature extraction, segmentation, classification and post processing. It is crucial to accurately localize and segment the skin lesion. It is observed that recent enhancements in machine learning algorithms and dermoscopic techniques reduced the misclassification rate therefore, the focus towards computer aided systems increased exponentially in recent years. Computer aided diagnostic systems are reliable source for dermatologists to analyze the type of cancer, but it is widely acknowledged that even higher accuracy is needed for computer aided diagnostic systems to be adopted practically in the diagnostic process of life threatening diseases. INTRODUCTION: Skin cancer is one of the most threatening cancers. It occurs by the abnormal multiplication of cells. The core three types of skin cells are: Squamous, Basal and Melanocytes. There are two wide classes of skin cancer; Melanocytic and non-Melanocytic. It is difficult to differentiate between benign and malignant melanoma, therefore dermatologists sometimes misclassify the benign and malignant melanoma. Melanoma is estimated as 19th most frequent cancer, it is riskier than the Basel and Squamous carcinoma because it rapidly spreads throughout the body. Hence, to lower the death risk, it is critical to diagnose the correct type of cancer in early rudimentary phases. It can occur on any part of body, but it has higher probability to occur on chest, back and legs. METHODS: The paper presents a review of segmentation and classification techniques for skin lesion detection. Dermoscopy and its features are discussed briefly. After that Image pre-processing techniques are described. A thorough review of segmentation and classification phases of skin lesion detection using deep learning techniques is presented Literature is discussed and a comparative analysis of discussed methods is presented. CONCLUSION: In this paper, we have presented the survey of more than 100 papers and comparative analysis of state of the art techniques, model and methodologies. Malignant melanoma is one of the most threating and deadliest cancers. Since the last few decades, researchers are putting extra attention and effort in accurate diagnosis of melanoma. The main challenges of dermoscopic skin lesion images are: low contrasts, multiple lesions, irregular and fuzzy borders, blood vessels, regression, hairs, bubbles, variegated coloring and other kinds of distortions. The lack of large training dataset makes these problems even more challenging. Due to recent advancement in the paradigm of deep learning, and specially the outstanding performance in medical imaging, it has become important to review the deep learning algorithms performance in skin lesion segmentation. Here, we have discussed the results of different techniques on the basis of different evaluation parameters such as Jaccard coefficient, sensitivity, specificity and accuracy. And the paper listed down the major achievements in this domain with the detailed discussion of the techniques. In future, it is expected to improve results by utilizing the capabilities of deep learning frameworks with other pre and post processing techniques so reliable and accurate diagnostic systems can be built.

Opacity and transport measurements reveal that dilute plasma models of sonoluminescence are not valid.

A strong interaction between a nanosecond laser and a 70 µm radius sonoluminescing plasma is achieved. The overall response of the system results in a factor of 2 increase in temperature as determined by its spectrum. Images of the interaction reveal that light energy is absorbed and trapped in a region smaller than the sonoluminescence emitting region of the bubble for over 100 ns. We interpret this opacity and transport measurement as demonstrating that sonoluminescencing bubbles can be 1000 times more opaque than what follows from the Saha equation of statistical mechanics in the ideal plasma limit. To address this discrepancy, we suggest that the effects of strong Coulomb interactions are an essential component of a first principles theory of sonoluminescence.

100-Watt sonoluminescence generated by 2.5-atmosphere-pressure pulses.

A Xenon gas bubble introduced into a vertically suspended steel cylinder is driven to sonoluminescence by impacting the apparatus against a solid steel base. This produces a 150-ns flash of broadband light that exceeds 100-W peak intensity and has a spectral temperature of 10,200 K. This bubble system, which yields light with a single shot, emits very powerful sonoluminescence. A jet is visible following bubble collapse, which demonstrates that spherical symmetry is not necessary to produce sonoluminescence.

Phase transition to an opaque plasma in a sonoluminescing bubble.

Time-resolved spectrum measurements of a sonoluminescing Xe bubble reveal a transition from transparency to an opaque Planck blackbody. As the temperature is <10 000 K and the density is below liquid density, the photon scattering length is 10 000 times too large to explain its opacity. We resolve this issue with a model that reduces the ionization potential. According to this model, sonoluminescence originates in a new phase of matter with high ionization. Analysis of line emission from Xe* also yields evidence of phase segregation for this first-order transition inside a bubble.