Automatic surveying of cutaneous hemangiomas

Symmetry

Infantile hemangiomas (IHs) are a type of vascular tumors that affect around 10% of newborns. The measurement of the lesion size and the assessment of the evolution is done manually by the physician. This paper presents an algorithm for the automatic computation of the IH lesion surface. The image scale is computed by using the Hough transform and the total variation. As pre-processing, a geometric correction step is included, which ensures that the lesions are viewed as perpendicular to the camera. The image segmentation is based on K-means clustering applied on a five-plane image; the five planes being selected from seven planes with the use of the Karhunen-Loeve transform. Two of the seven planes are 2D total variation filters, based on symmetrical kernels, designed to highlight the IH specific texture. The segmentation performance was assessed on 30 images, and a mean border error of 9.31% was obtained.

Automatic tumor segmentation is a crucial step for diagnosis and surgery planning. This paper presents automatic detection of Hemangioma liver tumor using CT images based on histogram analysis. The proposed methodology consists of three stages. In the first stage, all kind of noises are removed such as speckles using image filtering. The overlap between different peaks is a strong evidence of noisy image. In the second stage, hemangioma tumor candidates are detected using histogram based analysis and K-mean based analysis. Applying histogram based analysis algorithm leads to remove the overlap between liver and the tumor. Suspected area was recognized successfully as the outcome of histogram based analysis. Tumor Pattern shows gradual change from dark to light. The darker tune means worst damage as well as older than the lighter tune. The dark tune indicates severity and old. The light tune indicates new development of the tumor. Quantitative evaluation was done using ANOVA single factor test analysis to test whether there is any significant relation between the classes. Since P < 0.05, there is insignificant relation between all the classes and we reject the null hypothesis. Further, validation between manual and automated segmentation was made and found that the error between manual segmentation and automated segmentation is around 1 % which shows an evidence of success. In the final stage, the performance capability of K-means versus HBAA was made. The error percentage in (HBAA) is (5.1 %), while in (K-mean classifier) the 3.0 %. The estimated area by (K-mean classifier) was almost close to both the estimated area by (HBAA) and the calculated area by the radiologist.

Procedia Computer Science, 2016

In this paper we propose a method for the automatic detection of hemangioma regions, consisting of a cascade of algorithms: a Self Organizing Map (SOM) for clustering the image pixels in 25 classes (using a 5x5 output layer) followed by a morphological method of reducing the number of classes (MMRNC) to only two classes: hemangioma and non-hemangioma. We named this method SOM-MMRNC. To evaluate the performance of the proposed method we have used Fuzzy C-means (FCM) for comparison. The algorithms were tested on 33 images; for most images, the proposed method and FCM obtain similar overall scores, within one percent of each other. However, in about 18% of the cases, there is a significant increase of the overall score for SOM-MMRNC (over 3.5%). On average, the results obtained with the proposed cascade are 1.06% better for each image.

The application of image processing for diagnostics purpose is a non-invasive technique. At present there is a great interest in the prospects of automatic image analysis method for image processing, which provides significant information about a skin lesion, also can be more applicable for the clinical purpose, and as an early warning tool for the detection purpose.. In order to accomplish an efficient way to identify skin cancer at an early stage without performing any unnecessary skin biopsies, digital images of skin lesions have been investigated. To complete this goal, feature extraction is considered as an essential-weapon to analyze an image properly. In this paper, different digital lesion images have been analyzed based on unsupervised image acquisition, pre-processing, and image segmentation techniques. Then the Feature extraction techniques are applied on these segmented images. After this, a graphical user interface has been designed for the lesion probability detection and then a comprehensive discussion has been explored based on the obtained results.

IAEME, 2019

Skin cancer accounts to be a standout amongst the most prevalent types of carcinoma ailments, particularly among Caucasian offspring and pale-skinned persons. Specifically, the melanocytic dermis lesion are conjectured as the most lethal among three pervasive skin carcinoma ailments and the second most communal type amongst youthful grown-ups who are 15-29 years old. These apprehensions have impelled the requirement of automated systems for the diagnosis of skin carcinomas within a limited time frame to reduce unnecessary biopsy, proliferating the momentum of diagnosis and giving reproducibility of indicative outcomes. In this survey paper a brief overview of automated detection and segmentation of vascular structures of skin lesions is presented

2009

The medical diagnosis from images aided by computational solutions has become frequent in the last years, being the automatic extraction of contours, for example, very important to assist the diagnosis of skin lesions. Commonly, some skin lesions are not detected by the clinicians by visual inspection, because they are very small, or sometimes, the clinicians are tired and have some difficulties in their identification. This work presents a study on methods to automatically segment skin lesions from images that can be considered to aware the clinicians' attention on the location of possible skin lesions in images. Moreover, it is presented the comparison of two methods of the most promising ones, analyzing their main characteristics, advantages and disadvantaged.

2009

Abstract: Prompt diagnosis is the most reliable solution for an effective treatment of melanoma. There is an ongoing research for providing computer-aided imaging tools in order to support the early detection and diagnosis of malignant melanomas. The first step towards producing such a diagnosis system is the automated and accurate boundary detection of skin lesion.

Automatic lesion segmentation is an important part of computer-based image analysis of pigmented skin lesions. Currently, there is a great interest in the development of Computer-Aided Diagnosis (CAD) systems for dermoscopic images. The segmentation step is one of the most important ones, since its accuracy determines the eventual success or failure of a CAD system. This study introduced new method of dermoscopic images segmentation. The preprocess was the filtering operation to dermoscopy image to remove most of difficulties facing the efficient segmentations, like a variety of lesion shapes, sizes, color, changes due to different skin types and textures and presence of hairs. Segmentation based mainly on histogram thresholding. The enhancements of image achieved by using mathematical morphology in order to obtain better segmentation with smooth border and without any noise in the lesion region. The proposed method evaluated by using Hammoude Distance (HM) and the True Detection Rate (TDR). Also the proposed method is compared with other skin lesions segmentation methods such as Otsu, adaptive thresholding and fuzzy Cmeans. The accuracy of proposed method was 96.32%, which is highly promised result and dependable.

International Journal of Information, Security and System Management, 2015

Skin cancer has been the most usual and illustrates 50% of all new cancers detected each year. If they detected at an early stage, treatment can become simple and economically. Accurate skin lesion segmentation is important in automated early skin cancer detection and diagnosis systems. The aim of this study is to provide an effective approach to detect the skin lesion border on a purposed image. A novel method based on image processing is proposed that combines the edge detection and the thresholding technique for skin lesions detection from skin region in an image. The distributions of edge and the proposed thresholding method provide a good discrimination of skin lesions. The evaluation of the proposed method is based on the comparison with the Otsu and Rosin segmentation as the most application methods. The performance of the designed system is evaluated with 30 test images, and the experimental results demonstrate the effectiveness of the proposed mole localization scheme.

Skin lesions have consistently had one of the most rapidly increasing incidences of all cancers. Early diagnosis is particularly important. However, even with the help of dermoscopy, differentiating malign and benign lesions is a challenging task. More than that, there are many practical situations where only macroscopic imaging is available. This work focuses on macroscopic imaging segmentation of black skin lesions. We propose a method combining mathematical morphology and edge detection. After the artifacts extraction stage, we refine the skin lesions by using an opening followed by a dilation algorithm. We then proceed to edge detection. We finally make a comparison of our combination method with existing classical methods.