PURPOSE:We present a classifier for automatically selecting a lesion border for dermoscopy skin lesion images, to aid in computer-aided diagnosis of melanoma. Variation in photographic technique of dermoscopy images makes segmentation of skin lesions a difficult problem. No single algorithm provides an acceptable lesion border to allow further processing of skin lesions.METHODS:We present a random forests border classifier model to select a lesion border from 12 segmentation algorithm borders, graded on a "good-enough" border basis. Morphology and color features inside and outside the automatic border are used to build the model.RESULTS:For a random forests classifier applied to an 802-lesion test set, the model predicts a satisfactory border in 96.38% of cases, in comparison to the best single border algorithm, which detects a satisfactory border in 85.91% of cases.CONCLUSION:The performance of the classifier-based automatic skin lesion finder is found to be better than any single algorithm used in this research.

This article describes the design, implementation, and results of the latest installment of the dermoscopic image analysis benchmark challenge. The goal is to support research and development of algorithms for automated diagnosis of melanoma, the most lethal skin cancer. The challenge was divided into 3 tasks: lesion segmentation, feature detection, and disease classification. Participation involved 593 registrations, 81 pre-submissions, 46 finalized submissions (including a 4-page manuscript), and approximately 50 attendees, making this the largest standardized and comparative study in this field to date. While the official challenge duration and ranking of participants has concluded, the dataset snapshots remain available for further research and development.

A vision-based measurement approach for pill shape detection is presented along with other applications. Rapid and accurate pill identification is needed by medical and law enforcement personnel during emergencies. But real-world pill identification is challenging due to varied lighting conditions, minor manufacturing defects, and subsequent pill wear. Surmounting these challenges is possible using multiple inputs: pill color, imprint, and shape. Of these different inputs, pill shape is the most important and difficult parameter due to its variations. In this paper, we describe a novel technique to accurately detect the complex pharmaceutical pill shapes using measurements derived from a superimposed adaptable ring centered automatically on either the shape’s centroid or its bounding box midpoint determined based on the measurements from two other rings, namely the inner ring and the outer ring. It is shown that the measurements from the overlays of the adaptable ring suffice to successfully classify the shapes of the pills currently in the Pillbox database (U.S. National Library of Medicine, 2014) with an accuracy of 98.7%. Our method demonstrated higher accuracy when compared with Hu-moments on the same data set. Using logistic regression techniques, Hu-moments provided an accuracy of 96.6%. Though developed for the domain of pharmaceutical pill shapes, we discuss how the measurements from the adaptable ring can also be used in other industrial applications to increase the level of accuracy with the help of this real-time less computationally complex method.

BACKGROUND:Computer vision may aid in melanoma detection. OBJECTIVE:We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images. METHODS:We conducted a cross-sectional study using 100 randomly selected dermoscopic images (50 melanomas, 44 nevi, and 6 lentigines) from an international computer vision melanoma challenge dataset (n = 379), along with individual algorithm results from 25 teams. We used 5 methods (nonlearned and machine learning) to combine individual automated predictions into "fusion" algorithms. In a companion study, 8 dermatologists classified the lesions in the 100 images as either benign or malignant. RESULTS:The average sensitivity and specificity of dermatologists in classification was 82% and 59%. At 82% sensitivity, dermatologist specificity was similar to the top challenge algorithm (59% vs. 62%, P = .68) but lower than the best-performing fusion algorithm (59% vs. 76%, P = .02). Receiver operating characteristic area of the top fusion algorithm was greater than the mean receiver operating characteristic area of dermatologists (0.86 vs. 0.71, P = .001). LIMITATIONS:The dataset lacked the full spectrum of skin lesions encountered in clinical practice, particularly banal lesions. Readers and algorithms were not provided clinical data (eg, age or lesion history/symptoms). Results obtained using our study design cannot be extrapolated to clinical practice. CONCLUSION:Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists.

Basal cell carcinoma (BCC), with an incidence in the US exceeding 2.7 million cases/year, exacts a significant toll in morbidity and financial costs. Earlier BCC detection via automatic analysis of dermoscopy images could reduce the need for advanced surgery. In this paper, automatic diagnostic algorithms are applied to images segmented by five thresholding segmentation routines. Experimental results for five new thresholding routines are compared to expert-determined borders. Logistic regression analysis shows that thresholding segmentation techniques yield diagnostic accuracy that is comparable to that obtained with manual borders. The experimental results obtained with algorithms applied to automatically segmented lesions demonstrate significant potential for the new machine vision techniques.

BackgroundPink blush is a common feature in basal cell carcinoma (BCC). A related feature, semitranslucency, appears as smooth pink or orange regions resembling skin color. We introduce an automatic method for detection of these features based on smoothness and brightness. We also introduce a neighborhood correction method for texture area correction.MethodsSmoothness and brightness were analyzed over four bands: luminance, red, green, and blue, then merged using variance-based dynamic thresholding. Dermoscopic images of 100 biopsy-proven BCCs and 254 competitive benign mimics were used to train the algorithm. Sixteen color and texture features were extracted from the automatically detected areas. The confusion matrix for the algorithm showed 15 classification errors in the training set for the 354 images: three errors in the BCC set and 12 errors in the benign set.ResultsLogistic regression analysis on a separate 1024-image test set was able to achieve good separation of BCC from benign lesions with an area under the receiver operating characteristic curve (ROC) of 0.878 and 0.877 using manually-created and automatically-generated BCC border masks, respectively.ConclusionThis pilot study indicates that automatic detection of semitranslucent and pink blush areas in BCC is feasible using colors and first-order texture statistics.

PURPOSE:Algorithms employed for pigmented lesion segmentation perform poorly on dermoscopy images of basal cell carcinoma (BCC), the most common skin cancer. The main objective was to develop better methods for BCC segmentation.METHODS:Fifteen thresholding methods were implemented for BCC lesion segmentation. We propose two error metrics that better measure the type II error: Relative XOR Error and Lesion Capture Ratio.RESULTS:On training/test sets of 305 and 34 BCC images, respectively, five new techniques outperform two state-of-the-art methods used in segmentation of melanomas, based on the new error metrics.CONCLUSION:The proposed algorithms, which include solutions for image vignetting correction and border expansion to achieve dermatologist-like borders, provide more inclusive and feature-preserving border detection, favoring better BCC classification accuracy, in future work.

To the Editor: The report by Ferris et al1 represents a milestone in comparison of human and computer performance in melanoma detection. The receiver operating characteristic (ROC) curve analysis portrays the sensitivity-specificity tradeoff inherent in any diagnostic system. The study includes nonmelanocytic lesions, representing the clinical situation better than most previous computer-aided diagnostic studies.

The incidence of malignant melanoma continues to increase worldwide. This cancer can strike at any age; it is one of the leading causes of loss of life in young persons. Since this cancer is visible on the skin, it is potentially detectable at a very early stage when it is curable. New developments have converged to make fully automatic early melanoma detection a real possibility. First, the advent of dermoscopy has enabled a dramatic boost in clinical diagnostic ability to the point that melanoma can be detected in the clinic at the very earliest stages. The global adoption of this technology has allowed accumulation of large collections of dermoscopy images of melanomas and benign lesions validated by histopathology. The development of advanced technologies in the areas of image processing and machine learning have given us the ability to allow distinction of malignant melanoma from the many benign mimics that require no biopsy. These new technologies should allow not only earlier detection of melanoma, but also reduction of the large number of needless and costly biopsy procedures. Although some of the new systems reported for these technologies have shown promise in preliminary trials, widespread implementation must await further technical progress in accuracy and reproducibility. In this paper, we provide an overview of computerized detection of melanoma in dermoscopy images. First, we discuss the various aspects of lesion segmentation. Then, we provide a brief overview of clinical feature segmentation. Finally, we discuss the classification stage where machine learning algorithms are applied to the attributes generated from the segmented features to predict the existence of melanoma.

In this article, we describe the design and implementation of a publicly accessible dermatology image analysis benchmark challenge. The goal of the challenge is to sup- port research and development of algorithms for automated diagnosis of melanoma, a lethal form of skin cancer, from dermoscopic images. The challenge was divided into sub-challenges for each task involved in image analysis, including lesion segmentation, dermoscopic feature detection within a lesion, and classification of melanoma. Training data included 900 images. A separate test dataset of 379 images was provided to measure resultant performance of systems developed with the training data. Ground truth for both training and test sets was generated by a panel of dermoscopic experts. In total, there were 79 submissions from a group of 38 participants, making this the largest standardized and comparative study for melanoma diagnosis in dermoscopic images to date. While the official challenge duration and ranking of participants has concluded, the datasets remain available for further research and development.

How far are we away from a Star-Trek-like device that can analyze a lesion and assess its malignancy? We review the main challenges in this field in light of the Blois paradigm of clinical judgment and computers. The research community has failed to adequately address several challenges ripe for the application of digital technology: 1) early detection of changing lesions, 2) detection of non-melanoma skin cancers, and 3) detection of benign melanoma mimics. We highlight a new device and recent image analysis advances in abnormal color and texture detection. Anthropomorphic paradigms can be applied to machine vision. Data fusion has the potential to move automatic diagnosis of skin lesions closer to clinical practice. The fusion of Blois’ high-level clinical information with low-level image data can yield high sensitivity and specificity. Synergy between detection devices and humans can get us closer to this Star-Trek-like device.