MRI-based radiomic features for identifying recurrent prostate cancer after proton radiation therapy.

PURPOSE: Magnetic Resonance Imaging (MRI) evaluation of recurrent prostate cancer (PCa) following proton beam therapy is challenging due to radiation-induced tissue changes. This study aimed to evaluate MRI-based radiomic features so as to identify the recurrent PCa after proton therapy. METHODS: We retrospectively studied 12 patients with biochemical recurrence (BCR) following proton therapy. Two experienced radiologists identified prostate lesions from multi-parametric MRI (mpMRI) images post-proton therapy and marked control regions of interest (ROIs) on the contralateral side of the prostate gland. A total of 210 radiomic features were extracted from lesions and control regions on the T2-weighted (T2WI) and Apparent Diffusion Coefficient (ADC) image series. Recursive Feature Elimination with Cross-Validation method (RFE-CV) was used for feature selection. A Multilayer Perceptron (MLP) neural network was developed to classify three classes: cancerous, benign, and healthy tissue. The 12-core biopsy results were used as the gold standard for the segmentations. The classifier performance was measured using specificity, sensitivity, the area under receiver operating characteristic curve (AUC), and other statistical indicators. RESULTS: Based on biopsy results, 10 lesions were identified as PCa recurrence while eight lesions were confirmed to be benign. Ten radiomic features (10/210) were selected to build the multi-class classifier. The radiomics classifier gave an accuracy of 0.83 in identifying cancerous, benign, and healthy tissue with a sensitivity of 0.80 and specificity of 0.85. The model yielded an AUC of 0.87, 95% CI [0.72-1.00] in differentiating cancer from the benign and healthy tissues. CONCLUSIONS: Our proof-of-concept study demonstrates the potential of using radiomic features as part of the differential diagnosis of PCa on mpMRI following proton therapy. The results need to be validated in a larger cohort.

MRI-based nomograms and radiomics in presurgical prediction of extraprostatic extension in prostate cancer: a systematic review.

PURPOSE: Prediction of extraprostatic extension (EPE) is essential for accurate surgical planning in prostate cancer (PCa). Radiomics based on magnetic resonance imaging (MRI) has shown potential to predict EPE. We aimed to evaluate studies proposing MRI-based nomograms and radiomics for EPE prediction and assess the quality of current radiomics literature. METHODS: We used PubMed, EMBASE, and SCOPUS databases to find related articles using synonyms for MRI radiomics and nomograms to predict EPE. Two co-authors scored the quality of radiomics literature using the Radiomics Quality Score (RQS). Inter-rater agreement was measured using the intraclass correlation coefficient (ICC) from total RQS scores. We analyzed the characteristic s of the studies and used ANOVAs to associate the area under the curve (AUC) to sample size, clinical and imaging variables, and RQS scores. RESULTS: We identified 33 studies-22 nomograms and 11 radiomics analyses. The mean AUC for nomogram articles was 0.783, and no significant associations were found between AUC and sample size, clinical variables, or number of imaging variables. For radiomics articles, there were significant associations between number of lesions and AUC (p < 0.013). The average RQS total score was 15.91/36 (44%). Through the radiomics operation, segmentation of region-of-interest, selection of features, and model building resulted in a broader range of results. The qualities the studies lacked most were phantom tests for scanner variabilities, temporal variability, external validation datasets, prospective designs, cost-effectiveness analysis, and open science. CONCLUSION: Utilizing MRI-based radiomics to predict EPE in PCa patients demonstrates promising outcomes. However, quality improvement and standardization of radiomics workflow are needed.

Machine learning prediction for COVID-19 disease severity at hospital admission.

IMPORTANCE: Early prognostication of patients hospitalized with COVID-19 who may require mechanical ventilation and have worse outcomes within 30 days of admission is useful for delivering appropriate clinical care and optimizing resource allocation. OBJECTIVE: To develop machine learning models to predict COVID-19 severity at the time of the hospital admission based on a single institution data. DESIGN, SETTING, AND PARTICIPANTS: We established a retrospective cohort of patients with COVID-19 from University of Texas Southwestern Medical Center from May 2020 to March 2022. Easily accessible objective markers including basic laboratory variables and initial respiratory status were assessed using Random Forest's feature importance score to create a predictive risk score. Twenty-five significant variables were identified to be used in classification models. The best predictive models were selected with repeated tenfold cross-validation methods. MAIN OUTCOMES AND MEASURES: Among patients with COVID-19 admitted to the hospital, severity was defined by 30-day mortality (30DM) rates and need for mechanical ventilation. RESULTS: This was a large, single institution COVID-19 cohort including total of 1795 patients. The average age was 59.7 years old with diverse heterogeneity. 236 (13%) required mechanical ventilation and 156 patients (8.6%) died within 30 days of hospitalization. Predictive accuracy of each predictive model was validated with the 10-CV method. Random Forest classifier for 30DM model had 192 sub-trees, and obtained 0.72 sensitivity and 0.78 specificity, and 0.82 AUC. The model used to predict MV has 64 sub-trees and returned obtained 0.75 sensitivity and 0.75 specificity, and 0.81 AUC. Our scoring tool can be accessed at https://faculty.tamuc.edu/mmete/covid-risk.html . CONCLUSIONS AND RELEVANCE: In this study, we developed a risk score based on objective variables of COVID-19 patients within six hours of admission to the hospital, therefore helping predict a patient's risk of developing critical illness secondary to COVID-19.

Impact of induction immunosuppression on patient survival in heart transplant recipients treated with tacrolimus and mycophenolic acid in the current allocation era.

BACKGROUND: The practice of induction therapy with either rabbit anti-thymocyte globulin (r-ATG) or interleukin-2 receptor antagonists (IL-2RA) is common among heart transplant recipients. However, its benefits in the setting of contemporary maintenance immunosuppression with tacrolimus/mycophenolic acid (TAC/MPA) are unknown. METHODS: We compared post-transplant mortality among three induction therapy strategies (r-ATG vs IL2-RA vs no induction) in a retrospective cohort analysis of heart transplant recipients maintained on TAC/MPA in the Organ Procurement Transplant Network (OPTN) database between the years 2006 and 2015. We used a multivariable model adjusting for clinically important co-morbidities, and a propensity score analysis using the inverse probability weighted (IPW) method in the final analysis. RESULTS: In multivariable IPW analysis, r-ATG (HR = 1.23; 95% CI = 1.05-1.46, P = 0.01) remained significantly associated with a higher mortality. There was a trend toward having a higher mortality in the IL2-RA (HR = 1.11; 95% CI = 1.00-1.24, P = 0.06) group. Subgroup analyses failed to show a patient survival benefit in using either r-ATG or IL2-RA among any of the subgroups analyzed. CONCLUSION: In this contemporary cohort of heart transplant recipients receiving TAC/MPA, neither r-ATG nor IL2-RA were associated with a survival benefit. On the contrary, adjusted analyses showed a significantly higher mortality in the r-ATG group and a trend toward higher mortality in the IL2-RA group. While caution is needed in interpreting treatment effects in an observational cohort, these data call into question the benefit of induction therapy as a common practice and highlight the need for more studies.

Classification of cocaine-dependent participants with dynamic functional connectivity from functional magnetic resonance imaging data.

Static functional connectivity (FC) analyses based on functional magnetic resonance imaging (fMRI) data have been extensively explored for studying various psychiatric conditions in the brain, including cocaine addiction. A recently emerging, more powerful technique, dynamic functional connectivity (DFC), studies how the FC dynamics change during the course of the fMRI experiments. The aim in this paper was to develop a computational approach, using a machine learning framework, to determine if DFC features were more successful than FC features in the classification of cocaine-dependent patients and healthy controls. fMRI data were obtained from of 25 healthy and 58 cocaine-dependent participants while performing a motor response inhibition task, stop signal task. Group independent component analysis was carried out on all participant data to compute spatially independent components (ICs). Eight ICs were selected manually as relevant brain networks, which were used to classify healthy versus cocaine-dependent participants. FC and DFC measures of the chosen IC pairs were used as features for the classification algorithm. Support Vector Machines were used for both feature selection/reduction and participant classification. Based on DFC with only seven IC pairs, participants were successfully classified with 95% accuracy (and with 90% accuracy with three IC pairs), whereas static FC yielded only 81% accuracy. Visual, sensorimotor, default mode, and executive control networks, amygdala, and insula played the most significant role in the DFC-based classification. These findings support the use of DFC-based classification of fMRI data as a potential biomarker for the identification of cocaine dependence.

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

BACKGROUND: Dermoscopy 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. RESULT: Our 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. CONCLUSION: We 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.

Induction regimen and survival in simultaneous heart-kidney transplant recipients.

BACKGROUND: Induction therapy in simultaneous heart-kidney transplantation (SHKT) is not well studied in the setting of contemporary maintenance immunosuppression consisting of tacrolimus (TAC), mycophenolic acid (MPA), and prednisone (PRED). METHODS: We analyzed the Organ Procurement and Transplant Network registry from January 1, 2000, to March 3, 2015, for recipients of SHKT (N = 623) maintained on TAC/MPA/PRED at hospital discharge. The study cohort was further stratified into 3 groups by induction choice: induction (n = 232), rabbit anti-thymoglobulin (r-ATG; n = 204), and interleukin-2 receptor-α (n = 187) antagonists. Survival rates were estimated using the Kaplan-Meier estimator. Multivariable inverse probability weighted Cox proportional hazard regression models were used to assess hazard ratios associated with post-transplant mortality as the primary outcome. The study cohort was censored on March 4, 2016, to allow at least 1-year of follow-up. RESULTS: During the study period, the number of SHKTs increased nearly 5-fold. The Kaplan-Meier survival curve showed superior outcomes with r-ATG compared with no induction or interleukin-2 receptor-α induction. Compared with the no-induction group, an inverse probability weighted Cox proportional hazard model showed no independent association of induction therapy with the primary outcome. In sub-group analysis, r-ATG appeared to lower mortality in sensitized patients with panel reactive antibody of 10% or higher (hazard ratio, 0.19; 95% confidence interval, 0.05-0.71). CONCLUSION: r-ATG may provide a survival benefit in SHKT, especially in sensitized patients maintained on TAC/MPA/PRED at hospital discharge.

SIMULTANEOUS LIVER KIDNEY TRANSPLANTATION IN LIVER TRANSPLANT CANDIDATES WITH RENAL DYSFUNCTION: IMPORTANCE OF CREATININE LEVELS, DIALYSIS, AND ORGAN QUALITY IN SURVIVAL.

BACKGROUND: The survival benefit from simultaneous liver-kidney transplantation (SLK) over liver transplant alone (LTA) in recipients with moderate renal dysfunction is not well understood. Moreover, the impact of deceased donor organ quality in SLK transplant survival has not been well described in the literature. METHODS: The Scientific Registry of Transplant Recipients was studied for adult recipients receiving LTA (N=2,700) or SLK (N=1,361) transplantation with moderate renal insufficiency between 2003 and 2013. The study cohort was stratified into four groups based on serum creatinine (Scr< 2 mg/dL versus Scr≥ 2 mg/dL) and dialysis status at listing and at transplant. The patients with end-stage renal disease and requiring acute dialysis more than three months before transplantation were excluded. A propensity score (PS)-matching was performed in each stratified groups to factor out imbalances between the SLK and LTA regarding covariates distribution and to reduce measured confounding. Donor quality was assessed with liver-donor risk index (L-DRI). The primary outcome of interest was post-transplant mortality. RESULTS: On multivariable PS-matched Cox proportional hazard models, SLK led to decrease in post-transplant mortality compared to LTA across all four groups, but only reached statistical significance (HR 0.77; 95% CI, 0.62-0.96) in the recipients not exposed to dialysis and Scr≥ 2 mg/dL at transplant (mortality incidence rate per patient-year 5.7% in SLK vs. 7.6% in LTA, p=0.005). The decrease in mortality was observed among SLK recipients with better quality donors (L-DRI<1.5). CONCLUSIONS: Exposure to pre-transplantation dialysis and donor quality affected overall survival among SLK recipients.

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

BACKGROUND: Automated 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. METHODS: This 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. RESULTS: The 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. CONCLUSIONS: The 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.

Successful classification of cocaine dependence using brain imaging: a generalizable machine learning approach.

BACKGROUND: Neuroimaging studies have yielded significant advances in the understanding of neural processes relevant to the development and persistence of addiction. However, these advances have not explored extensively for diagnostic accuracy in human subjects. The aim of this study was to develop a statistical approach, using a machine learning framework, to correctly classify brain images of cocaine-dependent participants and healthy controls. In this study, a framework suitable for educing potential brain regions that differed between the two groups was developed and implemented. Single Photon Emission Computerized Tomography (SPECT) images obtained during rest or a saline infusion in three cohorts of 2-4 week abstinent cocaine-dependent participants (n = 93) and healthy controls (n = 69) were used to develop a classification model. An information theoretic-based feature selection algorithm was first conducted to reduce the number of voxels. A density-based clustering algorithm was then used to form spatially connected voxel clouds in three-dimensional space. A statistical classifier, Support Vectors Machine (SVM), was then used for participant classification. Statistically insignificant voxels of spatially connected brain regions were removed iteratively and classification accuracy was reported through the iterations. RESULTS: The voxel-based analysis identified 1,500 spatially connected voxels in 30 distinct clusters after a grid search in SVM parameters. Participants were successfully classified with 0.88 and 0.89 F-measure accuracies in 10-fold cross validation (10xCV) and leave-one-out (LOO) approaches, respectively. Sensitivity and specificity were 0.90 and 0.89 for LOO; 0.83 and 0.83 for 10xCV. Many of the 30 selected clusters are highly relevant to the addictive process, including regions relevant to cognitive control, default mode network related self-referential thought, behavioral inhibition, and contextual memories. Relative hyperactivity and hypoactivity of regional cerebral blood flow in brain regions in cocaine-dependent participants are presented with corresponding level of significance. CONCLUSIONS: The SVM-based approach successfully classified cocaine-dependent and healthy control participants using voxels selected with information theoretic-based and statistical methods from participants' SPECT data. The regions found in this study align with brain regions reported in the literature. These findings support the future use of brain imaging and SVM-based classifier in the diagnosis of substance use disorders and furthering an understanding of their underlying pathology.

Density-based parallel skin lesion border detection with webCL.

BACKGROUND: Dermoscopy 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. METHODS: Fast 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. RESULTS: Previous 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. CONCLUSIONS: When 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.

Induction Therapies in Live Donor Kidney Transplantation on Tacrolimus and Mycophenolate With or Without Steroid Maintenance.

BACKGROUND AND OBJECTIVES: Induction therapy with IL-2 receptor antagonist (IL2-RA) is recommended as a first line agent in living donor renal transplantation (LRT). However, use of IL2-RA remains controversial in LRT with tacrolimus (TAC)/mycophenolic acid (MPA) with or without steroids. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: The Organ Procurement and Transplantation Network registry was studied for patients receiving LRT from 2000 to 2012 maintained on TAC/MPA at discharge (n=36,153) to compare effectiveness of IL2-RA to other induction options. The cohort was initially divided into two groups based on use of maintenance steroid at time of hospital discharge: steroid (n=25,996) versus no-steroid (n=10,157). Each group was further stratified into three categories according to commonly used antibody induction approach: IL2-RA, rabbit anti-thymocyte globulin (r-ATG), and no-induction in the steroid group versus IL2-RA, r-ATG and alemtuzumab in the no-steroid group. The main outcomes were the risk of acute rejection at 1 year and overall allograft failure (graft failure or death) post-transplantation through the end of follow-up. Propensity score-weighted regression analysis was used to minimize selection bias due to non-random assignment of induction therapies. RESULTS: Multivariable logistic and Cox analysis adjusted for propensity score showed that outcomes in the steroid group were similar between no-induction (odds ratio [OR], 0.96; 95% confidence interval [95% CI], 0.86 to 1.08 for acute rejection; and hazard ratio [HR], 0.99; 95% CI, 0.90 to 1.08 for overall allograft failure) and IL2-RA categories. In the no-steroid group, odds of acute rejection with r-ATG (OR, 0.73; 95% CI, 0.59 to 0.90) and alemtuzumab (OR, 0.53; 95% CI, 0.42 to 0.67) were lower; however, overall allograft failure risk was higher with alemtuzumab (HR, 1.27; 95% CI, 1.03 to 1.56) but not with r-ATG (HR, 1.19; 95% CI, 0.97 to 1.45), compared with IL2-RA induction. CONCLUSIONS: Compared with no-induction therapy, IL2-RA induction was not associated with better outcomes when TAC/MPA/steroids were used in LRT recipients. r-ATG appears to be an acceptable and possibly the preferred induction alternative for IL2-RA in steroid-avoidance protocols.

GPU accelerated dynamic functional connectivity analysis for functional MRI data.

Recent advances in multi-core processors and graphics card based computational technologies have paved the way for an improved and dynamic utilization of parallel computing techniques. Numerous applications have been implemented for the acceleration of computationally-intensive problems in various computational science fields including bioinformatics, in which big data problems are prevalent. In neuroimaging, dynamic functional connectivity (DFC) analysis is a computationally demanding method used to investigate dynamic functional interactions among different brain regions or networks identified with functional magnetic resonance imaging (fMRI) data. In this study, we implemented and analyzed a parallel DFC algorithm based on thread-based and block-based approaches. The thread-based approach was designed to parallelize DFC computations and was implemented in both Open Multi-Processing (OpenMP) and Compute Unified Device Architecture (CUDA) programming platforms. Another approach developed in this study to better utilize CUDA architecture is the block-based approach, where parallelization involves smaller parts of fMRI time-courses obtained by sliding-windows. Experimental results showed that the proposed parallel design solutions enabled by the GPUs significantly reduce the computation time for DFC analysis. Multicore implementation using OpenMP on 8-core processor provides up to 7.7× speed-up. GPU implementation using CUDA yielded substantial accelerations ranging from 18.5× to 157× speed-up once thread-based and block-based approaches were combined in the analysis. Proposed parallel programming solutions showed that multi-core processor and CUDA-supported GPU implementations accelerated the DFC analyses significantly. Developed algorithms make the DFC analyses more practical for multi-subject studies with more dynamic analyses.

Dermoscopic diagnosis of melanoma in a 4D space constructed by active contour extracted features.

Dermoscopy, also known as epiluminescence microscopy, is a major imaging technique used in the assessment of melanoma and other diseases of skin. In this study we propose a computer aided method and tools for fast and automated diagnosis of malignant skin lesions using non-linear classifiers. The method consists of three main stages: (1) skin lesion features extraction from images; (2) features measurement and digitization; and (3) skin lesion binary diagnosis (classification), using the extracted features. A shrinking active contour (S-ACES) extracts color regions boundaries, the number of colors, and lesion's boundary, which is used to calculate the abrupt boundary. Quantification methods for measurements of asymmetry and abrupt endings in skin lesions are elaborated to approach the second stage of the method. The total dermoscopy score (TDS) formula of the ABCD rule is modeled as linear support vector machines (SVM). Further a polynomial SVM classifier is developed. To validate the proposed framework a dataset of 64 lesion images were selected from a collection with a ground truth. The lesions were classified as benign or malignant by the TDS based model and the SVM polynomial classifier. Comparing the results, we showed that the latter model has a better f-measure then the TDS-based model (linear classifier) in the classification of skin lesions into two groups, malignant and benign.

An improved border detection in dermoscopy images for density based clustering.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. In current practice, dermatologists determine lesion area by manually drawing lesion borders. Therefore, automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is automated detection of lesion borders. To our knowledge, in our 2010 study we achieved one of the highest accuracy rates in the automated lesion border detection field by using modified density based clustering algorithm. In the previous study, we proposed a novel method which removes redundant computations in well-known spatial density based clustering algorithm, DBSCAN; thus, in turn it speeds up clustering process considerably. FINDINGS: Our previous study was heavily dependent on the pre-processing step which creates a binary image from original image. In this study, we embed a new distance measure to the existing algorithm. This provides twofold benefits. First, since new approach removes pre-processing step, it directly works on color images instead of binary ones. Thus, very important color information is not lost. Second, accuracy of delineated lesion borders is improved on 75% of 100 dermoscopy image dataset. CONCLUSION: Previous and improved methods are tested within the same dermoscopy dataset along with the same set of dermatologist drawn ground truth images. Results revealed that the improved method directly works on color images without any pre-processing and generates more accurate results than existing method.

Fast density-based lesion detection in dermoscopy images.

Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is automated detection of lesion borders. In this study, we introduce a border-driven density-based framework to identify skin lesion(s) in dermoscopy images. Unlike the conventional density-based clustering algorithms, proposed algorithm expands regions only at borders of a cluster that in turn speeds up the process without losing precision or recall. In our method, border regions are represented with one or more simple polygons at any time. We tested our algorithm on a dataset of 100 dermoscopy cases with multiple physicians' drawn ground truth borders. The results show that border error and f-measure of assessment averages out at 6.9% and 0.86 respectively.

Lesion detection in demoscopy images with novel density-based and active contour approaches.

BACKGROUND: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Automated assessment tools for dermoscopy images have become an important field of research mainly because of inter- and intra-observer variations in human interpretation. One of the most important steps in dermoscopy image analysis is the detection of lesion borders, since many other features, such as asymmetry, border irregularity, and abrupt border cutoff, rely on the boundary of the lesion. RESULTS: To automate the process of delineating the lesions, we employed Active Contour Model (ACM) and boundary-driven density-based clustering (BD-DBSCAN) algorithms on 50 dermoscopy images, which also have ground truths to be used for quantitative comparison. We have observed that ACM and BD-DBSCAN have the same border error of 6.6% on all images. To address noisy images, BD-DBSCAN can perform better delineation than ACM. However, when used with optimum parameters, ACM outperforms BD-DBSCAN, since ACM has a higher recall ratio. CONCLUSION: We successfully proposed two new frameworks to delineate suspicious lesions with i) an ACM integrated approach with sharpening and ii) a fast boundary-driven density-based clustering technique. ACM shrinks a curve toward the boundary of the lesion. To guide the evolution, the model employs the exact solution 27 of a specific form of the Geometric Heat Partial Differential Equation 28. To make ACM advance through noisy images, an improvement of the model's boundary condition is under consideration. BD-DBSCAN improves regular density-based algorithm to select query points intelligently.

Analysis of density based and fuzzy c-means clustering methods on lesion border extraction in dermoscopy images.

BACKGROUND: Computer-aided segmentation and border detection in dermoscopic images is one of the core components of diagnostic procedures and therapeutic interventions for skin cancer. Automated assessment tools for dermoscopy images have become an important research field mainly because of inter- and intra-observer variations in human interpretation. In this study, we compare two approaches for automatic border detection in dermoscopy images: density based clustering (DBSCAN) and Fuzzy C-Means (FCM) clustering algorithms. In the first approach, if there exists enough density--greater than certain number of points--around a point, then either a new cluster is formed around the point or an existing cluster grows by including the point and its neighbors. In the second approach FCM clustering is used. This approach has the ability to assign one data point into more than one cluster. RESULTS: Each approach is examined on a set of 100 dermoscopy images whose manually drawn borders by a dermatologist are used as the ground truth. Error rates; false positives and false negatives along with true positives and true negatives are quantified by comparing results with manually determined borders from a dermatologist. The assessments obtained from both methods are quantitatively analyzed over three accuracy measures: border error, precision, and recall. CONCLUSION: As well as low border error, high precision and recall, visual outcome showed that the DBSCAN effectively delineated targeted lesion, and has bright future; however, the FCM had poor performance especially in border error metric.