Joanna Jaworek-Korjakowska

Determination of border irregularity in dermoscopic color images of pigmented skin lesions

Malignant melanoma, which is the most dangerous type of skin cancer, is commonly diagnosed in all people, regardless of age, gender, or race. In the last several years an increasing melanoma incidence and mortality rate has been observed worldwide. In this research we present a new approach to the detection and classification of border irregularity, one of the major parameter in a widely used diagnostic algorithm ABCD rule of dermoscopy. Accurate assessment of irregular borders is clinically important due to a significantly different occurrence in benign and malignant skin lesions. In this paper we describe a complex algorithm containing following steps: image enhancement, lesion segmentation, border irregularity detection as well as classification. The algorithm has been tested on 300 dermoscopic images and achieved a detection of 79% and classification accuracy of 90%. Compared to state-of-the-art, we obtain improved classification accuracy.

Assessment of dots and globules in dermoscopic color images as one of the 7-point check list criteria

Skin cancer is the most commonly diagnosed type of cancer in all people, regardless of age, gender, or race. One of the most common malignant skin cancer is melanoma which is a dangerous proliferation of melanocytes. In the last several years an increasing melanoma incidence rate has been observed worldwide, and the diagnosis and deaths are increasing faster than those of any other skin cancer. The presence or absence of irregular dots and globules is one of the most important dermoscopic criteria for the diagnosis of malignant melanoma. In this paper we propose a new approach to the assessment of dots and globules irregularity of the pigmented skin lesion. We describe a complex algorithm containing following steps: image enhancement, hair removal, lesion segmentation, dots and globules detection as well as irregularity calculation. The algorithm has been tested on a database of 100 dermoscopic images. Compared to state-of-the-art, we obtain improved detection and classification accuracy.

Hair removal from dermoscopic color images

Abstract Skin cancer is the most commonly diagnosed type of cancer in people, regardless of age, gender, or race. One of the most common malignant skin cancers is melanoma, which is a dangerous proliferation of melanocytes. It is a well-known fact that early diagnosis of skin cancer is crucial and allows for successful treatment. Treatment of melanoma is not effective when melanoma is at an advanced stage. A widely used tool for the examination of skin lesions is a dermatoscope, which uses optic magnification to visualize features that are invisible to the naked eye. For a precise and objective diagnosis, there is a need for a computerized method for the removal and inpainting of hairs in image processing. In this study, we present an algorithm for the detection and inpainting of hairs in color dermoscopic images.

Automatic detection of melanomas: an application based on the ABCD criteria

This paper proposes and describes an automatic software system to detect and diagnose malignant melanomas. Skin melanoma is the most serious type of skin cancer and one of the most malignant tumors in humans. In the last several years increasing melanoma incidence has been observed worldwide. The aim of the present research project was to design, implement and test an application for early diagnosis of malignant melanomas. The system is based on the commonly used dermoscopic criteria scheme called the ABCD rule of dermoscopy (A stands for Asymmetry, B for border irregularity, C for color and D for diameter) and has been tested on a database of 50 lesions (20 benign lesions and 30 malignant lesions). The results of the preliminary experiments show that the image analysis with computer assistance has the potential of more accurately identifying the dermoscopic lesions.

Computer-Aided Diagnosis of Micro-Malignant Melanoma Lesions Applying Support Vector Machines

Background. One of the fatal disorders causing death is malignant melanoma, the deadliest form of skin cancer. The aim of the modern dermatology is the early detection of skin cancer, which usually results in reducing the mortality rate and less extensive treatment. This paper presents a study on classification of melanoma in the early stage of development using SVMs as a useful technique for data classification. Method. In this paper an automatic algorithm for the classification of melanomas in their early stage, with a diameter under 5 mm, has been presented. The system contains the following steps: image enhancement, lesion segmentation, feature calculation and selection, and classification stage using SVMs. Results. The algorithm has been tested on 200 images including 70 melanomas and 130 benign lesions. The SVM classifier achieved sensitivity of 90% and specificity of 96%. The results indicate that the proposed approach captured most of the malignant cases and could provide reliable information for effective skin mole examination. Conclusions. Micro-melanomas due to the small size and low advancement of development create enormous difficulties during the diagnosis even for experts. The use of advanced equipment and sophisticated computer systems can help in the early diagnosis of skin lesions.

Design of a teledermatology system to support the consultation of dermoscopic cases using mobile technologies and cloud platform

Abstract Skin cancer is the most commonly diagnosed type of cancer in humans regardless of age, gender, or race. One of the most common malignant skin cancers is melanoma, which is a dangerous proliferation of melanocytes. In the last several years, an increasing melanoma incidence has been observed worldwide, and the incidence rate is increasing faster than those of any other skin cancer. The correct identification and diagnosis of moles still creates problems to inexperienced dermatologists and family physicians. In this paper, we present a new approach to the problem of assessing difficult cases in dermatology. We propose a teledermatology system to support the consultation process between family physicians and experts in the field of dermoscopic images. The system consists of a desktop monitoring application and a special smartphone application implemented for experts. If necessary, the physician can send the dermoscopic image to two dermatologists for further examination. This cloud-based architecture provides an interesting system for a fast and efficient exchange of dermatological information. Initial results and assessment of doctors are promising and indicate that the application can be used as a decision support system for dermoscopic images.

Automated epidermis segmentation in histopathological images of human skin stained with hematoxylin and eosin

Background: Epidermis area is an important observation area for the diagnosis of inflammatory skin diseases and skin cancers. Therefore, in order to develop a computer-aided diagnosis system, segmentation of the epidermis area is usually an essential, initial step. This study presents an automated and robust method for epidermis segmentation in whole slide histopathological images of human skin, stained with hematoxylin and eosin. Methods: The proposed method performs epidermis segmentation based on the information about shape and distribution of transparent regions in a slide image and information about distribution and concentration of hematoxylin and eosin stains. It utilizes domain-specific knowledge of morphometric and biochemical properties of skin tissue elements to segment the relevant histopathological structures in human skin. Results: Experimental results on 88 skin histopathological images from three different sources show that the proposed method segments the epidermis with a mean sensitivity of 87 %, a mean specificity of 95% and a mean precision of 57%. It is robust to inter- and intra-image variations in both staining and illumination, and makes no assumptions about the type of skin disorder. The proposed method provides a superior performance compared to the existing techniques.

ASSESSMENT OF ASYMMETRY IN DERMOSCOPIC COLOUR IMAGES OF PIGMENTED SKIN LESIONS

Skin cancer is the most commonly diagnosed type of cancer in all people, regardless of age, gender, or race. One of the most common malignant skin cancer is melanoma which is a dangerous proliferation of melanocytes. In the last several years an increasing melanoma incidence has been observed worldwide, and thediagnosis and deaths are increasing faster than those of any other skin cancer. Only in UK around 12,800 new cases of malignant melanoma were diagnosed in 2010. This paper presents a new approach to the assessment of asymmetry of the pigmented skin lesion. Asymmetry is one of the most important indicator andit contributes substantially to the diagnosis of melanoma in the commonly used diagnostic algorithm, ABCD rule.This paper describes a complex algorithm containing following steps: image enhancement, border detection, lesion segmentation,positioning of axes, and calculation of the asymmetry parameters. The automated asymmetry assessment is based on definition and calculationof the geometry parameters and colour variation (pigmentation, texture) of the lesion. The algorithm has been tested on a database of 100 images (30 malignant lesions and 70 benign lesions). The effectiveness of the proposed method is shown through experiments and compared to diagnosis results by clinical experts. The sensitivity and accuracy have improved significantly.

Automatic Detection of Blue-Whitish Veil as the Primary Dermoscopic Feature

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Owing to the difficulty and subjectivity of human interpretation, dermoscopy image analysis has become an important research area. One of the most important local structure that is likely to appear in malignant melanoma is the blue-whitish veil. In this article, we present an unsupervised approach to the blue-whitish veil detection in dermoscopy images of pigmented skin lesions based on the analysis of HSV color space. The method is tested on a set of 179 dermoscopy images and the detection error rate is lower than 15%. The results demonstrate that the presented method achieves both fast and accurate blue structure segmentation in dermoscopy images.

The Accuracy of H&E Stain Unmixing Techniques When Estimating Relative Stain Concentrations

The hematoxylin and eosin stain (H&E stain) is one of the most popular, routine stain in histology. It allows to observe an overall cellular architecture of tissue and is more versatile than such stainings as immunohistochemistry. In this paper, we evaluate performance of state-of-the-art methods for stain unmixing in H&E-stained images. The aim of our study is to measure the degree of conformity of relative stain concentration maps obtained automatically to ground truth, to examine their robustness to variations in staining and illumination between images, and to assess their usefulness for routine usage.