Border Detection Method Research Articles

Revisited Otsu Algorithm for Skin Cancer Segmentation

Computer-aided technology can be used to perform a quantitative and objective evaluation of pigmented skin lesions during the clinical assessment procedure. This helps to expedite the procedure. The growing development of non-invasive techniques can be of significant benefit in the early identification of malignant melanoma, which can, in turn, help to minimize the necessity for invasive biopsies. The system is primarily focused on two principal schemes: Establishing an effective lesion border detection method and then creating an efficient classification scheme. We address two primary areas in this work. First, we study skin lesion detection to analyze any sign of malignancy for skin cancer diagnosis. This is followed by the system implementation of a color-based method for all the images from the RGB color space using a revisited OTSU thresholding segmentation scheme. The results proved to be promising with at least an 80% accuracy detection rate for a wide range of clinical skin lesion images.

Using convolutional neural networks for character verification on integrated circuit components of printed circuit boards

Manufacturers of printed circuit boards (PCBs) typically use automated optical inspection (AOI) machines to test their PCBs. However, AOI machines employ conventional image-processing methods. If the integrated circuit (IC) components are not identical to the golden samples, then the AOI machine registers those IC components as flaws. Conventional image-processing methods cause misjudgments and increase the cost of manual reviews. Character-verification and image-classification systems are proposed in this paper for detecting misplaced, missing, and reversed-polarity parts. The regions of IC components can be identified on PCBs by using the contour border-detection method. Through the proposed convolutional neural network (CNN) structure and refinement mechanism, the characters can be successfully recognized. The image-classification system was applied only to images with blurry characters. Different CNN learning structures were used in both systems, and the refinement mechanism was used in both systems to improve the results. The proposed character-verification and image-classification methods achieved 98.84% and 99.48% passing rates, and the amount of required training time was less than that of other methods, demonstrating the proposed methods’ greater effectiveness.

Local edge-enhanced active contour for accurate skin lesion border detection

BackgroundDermoscopy is one of the common and effective imaging techniques in diagnosis of skin cancer, especially for pigmented lesions. Accurate skin lesion border detection is the key to extract important dermoscopic features of the skin lesion. In current clinical settings, border delineation is performed manually by dermatologists. Operator based assessments lead to intra- and inter-observer variations due to its subjective nature. Moreover it is a tedious process. Because of aforementioned hurdles, the automation of lesion boundary detection in dermoscopic images is necessary. In this study, we address this problem by developing a novel skin lesion border detection method with a robust edge indicator function, which is based on a meshless method.ResultOur results are compared with the other image segmentation methods. Our skin lesion border detection algorithm outperforms other state-of-the-art methods. Based on dermatologist drawn ground truth skin lesion borders, the results indicate that our method generates reasonable boundaries than other prominent methods having Dice score of 0.886 ±0.094 and Jaccard score of 0.807 ±0.133.ConclusionWe prove that smoothed particle hydrodynamic (SPH) kernels can be used as edge features in active contours segmentation and probability map can be employed to avoid the evolving contour from leaking into the object of interest.

Fractional-order Darwinian PSO-based feature selection for media-adventitia border detection in intravascular ultrasound images

Media-adventitia (MA) border delineates the outer appearance of arterial wall in intravascular ultrasound (IVUS) image. The detection of MA border is a challenging topic due to many difficulties such as complicated intravascular structures, intrinsic artifacts and image noises. We propose a classification-based MA border detection method with an embedded feature selection technique. The feature selection technique is based on Fractional-order Darwinian particle swarm optimization (FODPSO) algorithm. By employing feature selection, 293-dimension features including multi-scale features, gray-scale features and morphological feature are reducing to 37-dimension. The border detection method with feature selection is tested on a public dataset extracted from in-vivo pullbacks of human coronary arteries, which contains 77 IVUS images. Three indicators, Jaccard (JACC), Hausdorff Distance (HD) and Percentage of Area Difference (PAD), are measured for quantitative evaluation. Detection with 293-dimension features obtains JACC 0.79, HD 1.41 and PAD 0.16, while detection with 37-dimension features obtains JACC 0.83, HD 1.27 and PAD 0.12, indicating that the FODPSO-based feature selection method improves MA border detection by JACC 0.04, HD 0.14 and PAD 0.04. Furthermore, the proposed border detection method acquires better performances compared with two other automatic methods conducted on the same dataset available in literature.

Texture Analysis for Crack Detection in Fracture Mechanics

In the context of the metal-mechanic industry, there is a strong demand for material behavior measuring methods in the presence of cracks under stress conditions. This behavior is usually quantified by means of fracture toughness tests using parameters such as the stress intensity factor K, the CTOD, or the J integral. Regardless of the parameters used to quantify fracture toughness, all tests require knowledge of the correct length of the existing fatigue pre-crack in the sample that generated the failure. Hence, most laboratories have adopted visual measurement methods using a stereoscopic magnifying glass or a profile projector. Additional techniques, such as the use of heat tinting, help users and researchers to visualize the stable crack growth front. With the improvement in image processing and computer vision techniques, the present paper proposes the application of a new method for border detection by texture analysis, in order to get the corresponding contour of the crack front in postmortem analyses of SE(B) samples with high precision. The results suggest that the proposed method could be applied with high precision to images of fracture toughness tests for crack length measurement, having achieved a discrimination rate of 98%. The results also suggest that the method can be applied to samples that have not undergone heat tinting.

Parasite Dispersal From the Ornamental Goldfish Trade.

Goldfish, Carassius auratus Linnaeus, 1758, are immensely popular ornamental cyprinid fish, traded in more than 100 countries. For more than 500 years, human translocation has facilitated the spread of goldfish globally, which has enabled numerous and repeated introductions of parasite taxa that infect them. The parasite fauna assemblage of goldfish is generally well documented, but few studies provide evidence of parasite coinvasion following the release of goldfish. This review provides a comprehensive synopsis of parasites that infect goldfish in farmed, aquarium-held, native, and invasive populations globally and summarises evidence for the cointroduction and coinvasion of goldfish parasites. More than 113 species infect goldfish in their native range, of which 26 species have probably coinvaded with the international trade of goldfish. Of these, Schyzocotyle acheilognathi (Cestoda: Bothriocephalidae), Ichthyophthirius multifiliis (Ciliophora: Ichthyophthiriidae), Argulus japonicus (Crustacea: Argulidae), Lernaea cyprinacea (Crustacea: Ergasilidae), Dactylogyrus anchoratus, Dactylogyrus vastator and Dactylogyrus formosus (Monogenea: Dactylogyridae) are common to invasive goldfish populations in more than four countries and are considered a high risk of continued spread. Coinvasive parasites include species with direct and complex life cycles, which have successfully colonised new environments through utilisation of either new native hosts or suitable invasive hosts. Specifically, I. multifiliis, A. japonicus and L. cyprinacea can cause harm to farmed freshwater fish species and are important parasites to consider for biosecurity. These species may threaten other aquatic animal industries given their low host specificity and adaptable life histories. Future attention to biosecurity, management and border detection methods could limit the continued spread of exotic parasites from the ornamental trade of goldfish.

Semi-automated localization of dermal epidermal junction in optical coherence tomography images of skin.

Identifying the location of the dermal epidermal junction (DEJ) in skin images is essential in several clinical applications of dermatology such as epidermal thickness determination in healthy versus unhealthy skins, such as basal cell carcinoma. Optical coherence tomography (OCT) facilitates the visual detection of DEJ in vivo. However, due to the granular texture of speckle and a low contrast between dermis and epidermis, a skin border detection method is required for DEJ localization. Current DEJ algorithms work well for skins with a visible differentiable epidermal layer but not for the skins of different body sites. In this paper, we present a semi-automated DEJ localization algorithm based on graph theory for OCT images of skin. The proposed algorithm is performed in an interactive framework by a graphical representation of an attenuation coefficient map through a uniform-cost search method. For border thinning, a fuzzy-based nonlinear smoothing technique is used. For evaluation, the DEJ detection method is used by several experts, and the results are compared with manual segmentation. The mean thickness error between the proposed algorithm and the experts' opinion in the Bland-Altman plot is computed as 14 μm; this is comparable to the resolution of the OCT. The results suggest that the proposed image processing method successfully detects DEJ.

An artificial neural network method for lumen and media-adventitia border detection in IVUS

Intravascular ultrasound (IVUS) has been well recognized as one powerful imaging technique to evaluate the stenosis inside the coronary arteries. The detection of lumen border and media-adventitia (MA) border in IVUS images is the key procedure to determine the plaque burden inside the coronary arteries, but this detection could be burdensome to the doctor because of large volume of the IVUS images. In this paper, we use the artificial neural network (ANN) method as the feature learning algorithm for the detection of the lumen and MA borders in IVUS images. Two types of imaging information including spatial, neighboring features were used as the input data to the ANN method, and then the different vascular layers were distinguished accordingly through two sparse auto-encoders and one softmax classifier. Another ANN was used to optimize the result of the first network. In the end, the active contour model was applied to smooth the lumen and MA borders detected by the ANN method. The performance of our approach was compared with the manual drawing method performed by two IVUS experts on 461 IVUS images from four subjects. Results showed that our approach had a high correlation and good agreement with the manual drawing results. The detection error of the ANN method close to the error between two groups of manual drawing result. All these results indicated that our proposed approach could efficiently and accurately handle the detection of lumen and MA borders in the IVUS images.

Abrupt skin lesion border cutoff measurement for malignancy detection in dermoscopy images.

BackgroundAutomated skin lesion border examination and analysis techniques have become an important field of research for distinguishing malignant pigmented lesions from benign lesions. An abrupt pigment pattern cutoff at the periphery of a skin lesion is one of the most important dermoscopic features for detection of neoplastic behavior. In current clinical setting, the lesion is divided into a virtual pie with eight sections. Each section is examined by a dermatologist for abrupt cutoff and scored accordingly, which can be tedious and subjective.MethodsThis study introduces a novel approach to objectively quantify abruptness of pigment patterns along the lesion periphery. In the proposed approach, first, the skin lesion border is detected by the density based lesion border detection method. Second, the detected border is gradually scaled through vector operations. Then, along gradually scaled borders, pigment pattern homogeneities are calculated at different scales. Through this process, statistical texture features are extracted. Moreover, different color spaces are examined for the efficacy of texture analysis.ResultsThe proposed method has been tested and validated on 100 (31 melanoma, 69 benign) dermoscopy images. Analyzed results indicate that proposed method is efficient on malignancy detection. More specifically, we obtained specificity of 0.96 and sensitivity of 0.86 for malignancy detection in a certain color space. The F-measure, harmonic mean of recall and precision, of the framework is reported as 0.87.ConclusionsThe use of texture homogeneity along the periphery of the lesion border is an effective method to detect malignancy of the skin lesion in dermoscopy images. Among different color spaces tested, RGB color space’s blue color channel is the most informative color channel to detect malignancy for skin lesions. That is followed by YCbCr color spaces Cr channel, and Cr is closely followed by the green color channel of RGB color space.

Robust semi-automated quantification of cardiac MR perfusion using level set: Application to hypertrophic cardiomyopathy patient data

BackgroundRecently there have been several clinical MR perfusion studies in patients with hypertrophic cardiomyopathy (HCM) who may suffer from myocardial ischemia due to coronary microvascular dysfunction. In these studies, data analysis relied on a manual procedure of tracing epicardial and endocardial borders. The goal of this work is to develop and validate a robust semi-automated analysis method for myocardial perfusion quantification in clinical HCM data. MethodDynamic multi-slice stress perfusion MRI data were acquired from 18 HCM patients. The proposed semi-automated method required user input of two landmark selections: LV center point and RV insertion point. Automated segmentations of the endocardial and epicardial borders were performed in three short-axis slices using distance regularized level set evolution on RV, LV, and myocardial enhancement frames. ResultsThe proposed automated epicardial border detection method resulted in average radial distance errors of 7.5%, 9.5%, and 11.6% in basal, mid, and apical slices, respectively, when compared to manual tracing of the borders as a reference. In linear regression analysis, the highest correlation of myocardial upslope measurements was observed between the manual method and the proposed method in the anterolateral section (r=0.964), and the lowest correlation was observed in the inferoseptal section (r=0.866). ConclusionThe proposed semi-automated method for myocardial MR perfusion quantification is feasible in HCM patients who typically show (1) irregular myocardial shape and (2) low image contrast between the myocardium and its surrounding regions due to coronary microvascular disease.

Density-based parallel skin lesion border detection with webCL

BackgroundDermoscopy is a highly effective and noninvasive imaging technique used in diagnosis of melanoma and other pigmented skin lesions. Many aspects of the lesion under consideration are defined in relation to the lesion border. This makes border detection one of the most important steps in dermoscopic image analysis. In current practice, dermatologists often delineate borders through a hand drawn representation based upon visual inspection. Due to the subjective nature of this technique, intra- and inter-observer variations are common. Because of this, the automated assessment of lesion borders in dermoscopic images has become an important area of study.MethodsFast density based skin lesion border detection method has been implemented in parallel with a new parallel technology called WebCL. WebCL utilizes client side computing capabilities to use available hardware resources such as multi cores and GPUs. Developed WebCL-parallel density based skin lesion border detection method runs efficiently from internet browsers.ResultsPrevious research indicates that one of the highest accuracy rates can be achieved using density based clustering techniques for skin lesion border detection. While these algorithms do have unfavorable time complexities, this effect could be mitigated when implemented in parallel. In this study, density based clustering technique for skin lesion border detection is parallelized and redesigned to run very efficiently on the heterogeneous platforms (e.g. tablets, SmartPhones, multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units) by transforming the technique into a series of independent concurrent operations. Heterogeneous computing is adopted to support accessibility, portability and multi-device use in the clinical settings. For this, we used WebCL, an emerging technology that enables a HTML5 Web browser to execute code in parallel for heterogeneous platforms. We depicted WebCL and our parallel algorithm design. In addition, we tested parallel code on 100 dermoscopy images and showed the execution speedups with respect to the serial version. Results indicate that parallel (WebCL) version and serial version of density based lesion border detection methods generate the same accuracy rates for 100 dermoscopy images, in which mean of border error is 6.94%, mean of recall is 76.66%, and mean of precision is 99.29% respectively. Moreover, WebCL version's speedup factor for 100 dermoscopy images' lesion border detection averages around ~491.2.ConclusionsWhen large amount of high resolution dermoscopy images considered in a usual clinical setting along with the critical importance of early detection and diagnosis of melanoma before metastasis, the importance of fast processing dermoscopy images become obvious. In this paper, we introduce WebCL and the use of it for biomedical image processing applications. WebCL is a javascript binding of OpenCL, which takes advantage of GPU computing from a web browser. Therefore, WebCL parallel version of density based skin lesion border detection introduced in this study can supplement expert dermatologist, and aid them in early diagnosis of skin lesions. While WebCL is currently an emerging technology, a full adoption of WebCL into the HTML5 standard would allow for this implementation to run on a very large set of hardware and software systems. WebCL takes full advantage of parallel computational resources including multi-cores and GPUs on a local machine, and allows for compiled code to run directly from the Web Browser.

A New fuzzy level set method for lesion border detection in dermoscopy images

Accurate segmentation plays a vital role in automated analysis of dermoscopy images. A new method based on fuzzy level set method is introduced here for lesion detection in dermoscopy images. In this method, a hypothesis testing framework is defined first to separate lesions from skin and artifacts. Then the boundary of lesion is estimated by a decision function based on the level set energy minimization method which is driven by fuzzy connectedness concept. Performance is evaluated on real dermoscopy images which are captured from various lesions with different sizes and colors. Parameters for performance evaluation are presented and obtained results are compared with some other state-of-the-art lesion detection methods. Increased true positive rate in parallel with simultaneous decrease in false positive rate, Hammoude distance and Hausdorff distance confirm the effectiveness of proposed method for skin cancer detection.

An empirical strategy to detect bacterial transcript structure from directional RNA-seq transcriptome data.

BackgroundAs sequencing costs are being lowered continuously, RNA-seq has gradually been adopted as the first choice for comparative transcriptome studies with bacteria. Unlike microarrays, RNA-seq can directly detect cDNA derived from mRNA transcripts at a single nucleotide resolution. Not only does this allow researchers to determine the absolute expression level of genes, but it also conveys information about transcript structure. Few automatic software tools have yet been established to investigate large-scale RNA-seq data for bacterial transcript structure analysis.ResultsIn this study, 54 directional RNA-seq libraries from Salmonella serovar Typhimurium (S. Typhimurium) 14028s were examined for potential relationships between read mapping patterns and transcript structure. We developed an empirical method, combined with statistical tests, to automatically detect key transcript features, including transcriptional start sites (TSSs), transcriptional termination sites (TTSs) and operon organization. Using our method, we obtained 2,764 TSSs and 1,467 TTSs for 1331 and 844 different genes, respectively. Identification of TSSs facilitated further discrimination of 215 putative sigma 38 regulons and 863 potential sigma 70 regulons. Combining the TSSs and TTSs with intergenic distance and co-expression information, we comprehensively annotated the operon organization in S. Typhimurium 14028s.ConclusionsOur results show that directional RNA-seq can be used to detect transcriptional borders at an acceptable resolution of ±10-20 nucleotides. Technical limitations of the RNA-seq procedure may prevent single nucleotide resolution. The automatic transcript border detection methods, statistical models and operon organization pipeline that we have described could be widely applied to RNA-seq studies in other bacteria. Furthermore, the TSSs, TTSs, operons, promoters and unstranslated regions that we have defined for S. Typhimurium 14028s may constitute valuable resources that can be used for comparative analyses with other Salmonella serotypes.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-015-1555-8) contains supplementary material, which is available to authorized users.

ICMA: an integrated cardiac modeling and analysis platform.

Summary: ICMA, a software framework to create 3D finite element models of the left ventricle from cardiac ultrasound or magnetic resonance imaging (MRI) data, has been made available as an open-source code. The framework is hardware vendor independent and uses speckle tracking (endocardial border detection) on ultrasound (MRI) imaging data in the form of DICOM. Standard American Heart Association segment-based strain analysis can be performed using a browser-based interface. The speckle tracking, border detection and model fitting methods are implemented in C++ using open-source tools. They are wrapped as web services and orchestrated via a JBOSS-based application server.Availability and implementation: The source code for ICMA is freely available under MPL 1.1 or GPL 2.0 or LGPL 2.1 license at https://github.com/ABI-Software-Laboratory/ICMA and a standalone virtual machine at http://goo.gl/M4lJKH for download.Contact: r.jagir@auckland.ac.nzSupplementary information: Supplementary materials are available at Bioinformatics online.

Spatial fuzzy c-means algorithm with adaptive fuzzy exponent selection for robust vermilion border detection in healthy and diseased lower lips

IntroductionAccurate lip contour identification is demanding since variations in color, form and surface texture, even in normal lips, introduce artifacts in non-adapted segmentation algorithms. Herein, a method for vermilion border detection and quantification in healthy and diseased lower lips is presented. AimTo quantify the morphological irregularities of lower lip border, to validate its discriminative power in solar cheilosis diagnosis and to provide supportive tools toward, cost effective, non invasive, disease monitoring. MaterialsSegmentation algorithm for lower lip border was based on spatial fuzzy c-means clustering algorithm with adaptive selection of fuzzy exponent m. Lip features measuring morphological lip border deviations were estimated. The method of lip border extraction and quantitative description was evaluated in a gold standard set of 25 young volunteers without onset of lip diseases. Quantitative descriptors were evaluated in terms of correct classification rates in differentiating 30 healthy control cases from 41 patients with solar cheilosis and were further applied to quantify the therapeutic outcome after immunocryosurgery in eight patients with solar cheilosis. ResultsAdaptive estimation of fuzzy exponent m substantially boosted the segmentation quality in gold standard cases yielding quite smooth lip contours and uniformly low values of lip irregularity features. Discriminant analysis highlighted the distance between the extracted and modeled vermilion border as a feature with excellent diagnostic accuracy (sensitivity and specificity 98% and 93% respectively). Results on patients with solar cheilosis followed up after treatment with immunocryosurgery showed that proposed quantitative lip marker was able to trace the improvement of disease after treatment. ConclusionCorrect lip border recognition is the prerequisite for extracting essential morphological descriptors from lips with epithelial diseases like solar cheilosis. In this paper we presented an efficient method for the automatic identification and quantitative description of lower lip vermilion border morphology in health and disease using digital photography and image analysis techniques.

Measurement of Left and Right Atrial Volume in Patients Undergoing Ablation for Atrial Arrhythmias: Comparison of a Manual versus Semiautomatic Algorithm of Real Time 3D Echocardiography

Real time full-volume 3D echocardiography (3DE) allows rapid and noninvasive measurement of left (LA) and right atrial (RA) volume without geometric assumptions. Different algorithms from different commercial providers are available. Older software requires manual tracing of endocardial contours. Recently, software with semiautomatic endocardial contour-finding algorithms has become available, which considerably speeds up the procedure. Our aim was to compare, in the same dataset, both LA and RA volumes determined by an algorithm involving manual tracing to the corresponding volumes obtained by an algorithm with semiautomatic contour detection. Maximal atrial volumes were measured in 88 patients using a multiplane interpolation method algorithm based on manual planimetry of 8 slices. These volumes were compared with volumes determined by the QLAB 8.1 software using semiautomatic border detection. Linear regression showed excellent correlation between volumes determined by manual and by semiautomatic software for both LA and RA (r(2) = 0.90 and 0.89, respectively, P < 0.001). Bland-Altman analysis of manual versus semiautomatic volume determination showed narrow 95% limits of agreement (-15.9 to +12.0 mL for LA volume and -13.9 to +12.2 mL for RA volume) with a minimal bias of -1.9 ± 7.0 mL and -0.8 ± 6.5 mL, respectively, by the semiautomatic method. The semiautomatic border detection method shows excellent correlation for maximal LA and RA volume determination compared to the more time-consuming, multiplane interpolation method, with only slight underestimation. The results indicate that values of LA and RA volumes obtained by either algorithm can be compared, for example, during follow-up examinations.

Association of age with left ventricular volumes, ejection fraction and concentricity: the Framingham heart study

Background Left ventricular (LV) parameters may vary with aging, but concomitant disease can obscure relationships between age and LV size, mass and function. CMR provides reproducible measures of LV volumes, mass, and ejection fraction (EF), but manual analyses are time consuming. Automated border detection (ABD) methods may decrease analytical burden. We sought to examine the effect of greater age on LV volumes, mass, EF and concentricity in a large cohort of healthy adults free of clinical cardiovascular disease and hypertension using ABDassisted methods.

Real-Time Image-Identification-Based Anti-Manmade Misoperation System for Substations

A novel antimisoperation system is proposed to prevent manmade misoperations using real-time signboard image identification technology. A portable video capture device is employed to capture real-time images of the current working bay's substation signboard. These images, with the aid of image identification, are used to determine whether the operations staff has accessed a wrong bay. The framework and workflow of the system are provided, and the implementation of the signboard image border detection, character partition, and image-matching methods are also introduced in detail. The effectiveness and engineering applicability of the proposed system are demonstrated through lab results and in-field tests. The proposed system can be used in conjunction with an active five-prevention system to further improve the validity and safety of substation operations.

Optimized Weighted Performance Index for Objective Evaluation of Border-Detection Methods in Dermoscopy Images

Quantitative evaluation of the existing border-detection methods is commonly performed by using different metrics. This is inherently problematic due to the different characteristics of each metric. This paper presents a novel approach for objective evaluation of border-detection methods in dermoscopy images by introducing a comprehensive evaluation metric: optimized weighted performance index. The index is formed as a nonlinear weighted function of the six commonly used metrics of sensitivity, specificity, accuracy, precision, border error, and similarity. Constrained nonlinear multivariable optimization techniques are applied to determine the optimal set of weights that result in the maximum value of the index. This index is used as an effective measure of the value of a given border-detection method and, thus, provides a basis for comparison with other methods. To demonstrate the effectiveness of the proposed index, it is used to evaluate five recent border-detection methods applied on a set of 55 high-resolution dermoscopy images.

Three‐phase general border detection method for dermoscopy images using non‐uniform illumination correction

Computer-aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is lesion segmentation. Many studies have been successful in segmenting melanocytic skin lesions (MSLs), but few have focused on non-melanocytic skin lesions (NoMSLs), as the wide variety of lesions makes accurate segmentation difficult. We developed an automatic segmentation program for detecting borders of skin lesions in dermoscopy images. The method consists of a pre-processing phase, general lesion segmentation phase, including illumination correction, and bright region segmentation phase. We tested our method on a set of 107 NoMSLs and a set of 319 MSLs. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, and 93.9% and 93.8% for MSLs, in comparison with manual extractions from four or five dermatologists. The accuracy of our method was competitive or better than five recently published methods. Our new method is the first method for detecting borders of both non-melanocytic and melanocytic skin lesions.