Prospective, comparative evaluation of a deep neural network and dermoscopy in the diagnosis of onychomycosis.
ABSTRACT: BACKGROUND:Onychomycosis is the most common nail disorder and is associated with diagnostic challenges. Emerging non-invasive, real-time techniques such as dermoscopy and deep convolutional neural networks have been proposed for the diagnosis of this condition. However, comparative studies of the two tools in the diagnosis of onychomycosis have not previously been conducted. OBJECTIVES:This study evaluated the diagnostic abilities of a deep neural network (http://nail.modelderm.com) and dermoscopic examination in patients with onychomycosis. METHODS:A prospective observational study was performed in patients presenting with dystrophic features in the toenails. Clinical photographs were taken by research assistants, and the ground truth was determined either by direct microscopy using the potassium hydroxide test or by fungal culture. Five board-certified dermatologists determined a diagnosis of onychomycosis using the clinical photographs. The diagnosis was also made using the algorithm and dermoscopic examination. RESULTS:A total of 90 patients (mean age, 55.3; male, 43.3%) assessed between September 2018 and July 2019 were included in the analysis. The detection of onychomycosis using the algorithm (AUC, 0.751; 95% CI, 0.646-0.856) and that by dermoscopy (AUC, 0.755; 95% CI, 0.654-0.855) were seen to be comparable (Delong's test; P = 0.952). The sensitivity and specificity of the algorithm at the operating point were 70.2% and 72.7%, respectively. The sensitivity and specificity of diagnosis by the five dermatologists were 73.0% and 49.7%, respectively. The Youden index of the algorithm (0.429) was also comparable to that of the dermatologists' diagnosis (0.230±0.176; Wilcoxon rank-sum test; P = 0.667). CONCLUSIONS:As a standalone method, the algorithm analyzed photographs taken by non-physician and showed comparable accuracy for the diagnosis of onychomycosis to that made by experienced dermatologists and by dermoscopic examination. Large sample size and world-wide, multicentered studies should be investigated to prove the performance of the algorithm.
Project description:BACKGROUND:Diagnoses of Skin diseases are frequently delayed in China due to lack of dermatologists. A deep learning-based diagnosis supporting system can facilitate pre-screening patients to prioritize dermatologists' efforts. We aimed to evaluate the classification sensitivity and specificity of deep learning models to classify skin tumors and psoriasis for Chinese population with a modest number of dermoscopic images. METHODS:We developed a convolutional neural network (CNN) based on two datasets from a consecutive series of patients who underwent the dermoscopy in the clinic of the Department of Dermatology, Peking Union Medical College Hospital, between 2016 and 2018, prospectively. In order to evaluate the feasibility of the algorithm, we used two datasets. Dataset I consisted of 7192 dermoscopic images for a multi-class model to differentiate three most common skin tumors and other diseases. Dataset II consisted of 3115 dermoscopic images for a two-class model to classify psoriasis from other inflammatory diseases. We compared the performance of CNN with 164 dermatologists in a reader study with 130 dermoscopic images. The experts' consensus was used as the reference standard except for the cases of basal cell carcinoma (BCC), which were all confirmed by histopathology. RESULTS:The accuracies of multi-class and two-class models were 81.49%?±?0.88% and 77.02%?±?1.81%, respectively. In the reader study, for the multi-class tasks, the diagnosis sensitivity and specificity of 164 dermatologists were 0.770 and 0.962 for BCC, 0.807 and 0.897 for melanocytic nevus, 0.624 and 0.976 for seborrheic keratosis, 0.939 and 0.875 for the "others" group, respectively; the diagnosis sensitivity and specificity of multi-class CNN were 0.800 and 1.000 for BCC, 0.800 and 0.840 for melanocytic nevus, 0.850 and 0.940 for seborrheic keratosis, 0.750 and 0.940 for the "others" group, respectively. For the two-class tasks, the sensitivity and specificity of dermatologists and CNN for classifying psoriasis were 0.872 and 0.838, 1.000 and 0.605, respectively. Both the dermatologists and CNN achieved at least moderate consistency with the reference standard, and there was no significant difference in Kappa coefficients between them (P?>?0.05). CONCLUSIONS:The performance of CNN developed with relatively modest number of dermoscopic images of skin tumors and psoriasis for Chinese population is comparable with 164 dermatologists. These two models could be used for screening in patients suspected with skin tumors and psoriasis respectively in primary care hospital.
Project description: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.
Project description:Background:Accurate medical image interpretation is an essential proficiency for multiple medical specialties, including dermatologists and primary care providers. A dermatoscope, a ×10-×20 magnifying lens paired with a light source, enables enhanced visualization of skin cancer structures beyond standard visual inspection. Skilled interpretation of dermoscopic images improves diagnostic accuracy for skin cancer. Objective:Design and validation of Cutaneous Neoplasm Diagnostic Self-Efficacy Instrument (CNDSEI)-a new tool to assess dermatology residents' confidence in dermoscopic diagnosis of skin tumors. Methods:In the 2018-2019 academic year, the authors administered the CNDSEI and the Long Dermoscopy Assessment (LDA), to measure dermoscopic image interpretation accuracy, to residents in 9 dermatology residency programs prior to dermoscopy educational intervention exposure. The authors conducted CNDSEI item analysis with inspection of response distribution histograms, assessed internal reliability using Cronbach's coefficient alpha (?) and construct validity by comparing baseline CNDSEI and LDA results for corresponding lesions with one-way analysis of variance (ANOVA). Results:At baseline, residents respectively demonstrated significantly higher and lower CNDSEI scores for correctly and incorrectly diagnosed lesions on the LDA (P = 0.001). The internal consistency reliability of CNDSEI responses for the majority (13/15) of the lesion types was excellent (? ? 0.9) or good (0.8? ? <0.9). Conclusions:The CNDSEI pilot established that the tool reliably measures user dermoscopic image interpretation confidence and that self-efficacy correlates with diagnostic accuracy. Precise alignment of medical image diagnostic performance and the self-efficacy instrument content offers opportunity for construct validation of novel medical image interpretation self-efficacy instruments.
Project description:Trichoepitheliomas are uncommon benign adnexal neoplasms that originate from the hair follicles. Multiple familial trichoepithelioma constitute an autosomal dominant disease characterized by the appearance of multiple flesh-colored, symmetrical papules, tumors and/or nodules in the central face and occasionally on the scalp. Although clinical diagnosis is usually straightforward in light of the family history and naked-eye examination, dermoscopy may aid in its confirmation. Dermoscopy of each papule revealed in-focus arborizing vessels, multiple milia-like cysts and rosettes amidst a whitish background. In a patient with multiple facial papules revealing a dermoscopic appearance described above, the diagnosis of sporadic or familial multiple trichoepithelioma should be considered.
Project description:Osseous choristomas are rare benign lesions characterized by ectopic bone formation in the soft tissue of the head and neck region. Dermoscopy visualizes the morphological characteristics that are not observable by the naked eye, and may be used for the evaluation of calcification under the skin. The present study reports a case of an osseous choristoma arising in the tongue, and reveals the dermoscopic features of osseous choristoma from a surgical specimen. A 7-year-old boy was referred to the Department of Dentistry and Oral Surgery, with an asymptomatic pedunculated mass in the tongue. The lesion was removed completely with the adjacent normal tissue under general anesthesia. Dermoscopy of the surgical specimen revealed the hypovascular and homogeneous pattern of the lesion with round extruded whitish material. Based on dermoscopic findings, the presence of calcified hard tissue in the submucosa was verified by the dermatologist. Radiographic examination of the surgical specimen revealed the lesion contained a radiopaque trabeculated mass. Histologically, the lesion contained an osseous tissue, and the pathological diagnosis of osseous choristoma was made following consideration of the ectopic bony tissues that were localized away from the maxillo-mandibular bone. The postoperative course was uneventful with no signs of recurrence during the 36 months following surgery. To the best of the author's knowledge, this is the first report of evaluation of osseous choristoma using dermoscopy. The observation indicates the usefulness of dermoscopy for the diagnosis of oral ossified lesion in oral soft tissue.
Project description:Melanomas that clinically mimic seborrheic keratosis (SK) can delay diagnosis and adequate treatment. However, little is known about the value of dermoscopy in recognizing these difficult-to-diagnose melanomas.To describe the dermoscopic features of SK-like melanomas to understand their clinical morphology.This observational retrospective study used 134 clinical and dermoscopic images of histopathologically proven melanomas in 134 patients treated in 9 skin cancer centers in Spain, France, Italy, and Austria. Without knowledge that the definite diagnosis for all the lesions was melanoma, 2 dermoscopy-trained observers evaluated the clinical descriptions and 48 dermoscopic features (including all melanocytic and nonmelanocytic criteria) of all 134 images and classified each dermoscopically as SK or not SK. The total dermoscopy score and the 7-point checklist score were assessed. Images of the lesions and patient data were collected from July 15, 2013, through July 31, 2014.Frequencies of specific morphologic patterns of (clinically and dermoscopically) SK-like melanomas, patient demographics, and interobserver agreement of criteria were evaluated.Of the 134 cases collected from 72 men and 61 women, all of whom were white and who had a mean (SD) age of 55.6 (17.5) years, 110 (82.1%) revealed dermoscopic features suggestive of melanoma, including pigment network (74 [55.2%]), blue-white veil (72 [53.7%]), globules and dots (68 [50.7%]), pseudopods or streaks (47 [35.1%]), and blue-black sign (43 [32.3%]). The remaining 24 cases (17.9%) were considered likely SKs, even by dermoscopy. Overall, lesions showed a scaly and hyperkeratotic surface (45 [33.6%]), yellowish keratin (42 [31.3%]), comedo-like openings (41 [30.5%]), and milia-like cysts (30 [22.4%]). The entire sample achieved a mean (SD) total dermoscopy score of 4.7 (1.6) and a 7-point checklist score of 4.4 (2.3), while dermoscopically SK-like melanomas achieved a total dermoscopy score of only 4.2 (1.3) and a 7-point checklist score of 2.0 (1.9), both in the range of benignity. The most helpful criteria in correctly diagnosing SK-like melanomas were the presence of blue-white veil, pseudopods or streaks, and pigment network. Multivariate analysis found only the blue-black sign to be significantly associated with a correct diagnosis, while hyperkeratosis and fissures and ridges were independent risk markers of dermoscopically SK-like melanomas.Seborrheic keratosis-like melanomas can be dermoscopically challenging, but the presence of the blue-black sign, pigment network, pseudopods or streaks, and/or blue-white veil, despite the presence of other SK features, allows the correct diagnosis of most of the difficult melanoma cases.
Project description:BACKGROUND:The benign and malignant patterns of acral melanocytic naevi (AMN) and acral melanomas (AM) have been defined in a series of retrospective studies. A three-step algorithm was developed to determine when to biopsy acral melanocytic lesions. This algorithm has only been applied to a Japanese population. OBJECTIVES:Our study aimed to review the current management strategy of acral melanocytic lesions and to investigate the utility of the three-step algorithm in a predominately Caucasian cohort. METHODS:A retrospective search of the pathology and image databases at Mayo Clinic was performed between the years 2006 and 2016. Only cases located on a volar surface with dermoscopic images were included. Two dermatologists reviewed all dermoscopic images and assigned a global dermoscopic pattern. Clinical and follow-up data were gathered by chart review. All lesions with known diameter and pathological diagnosis were used for the three-step algorithm. RESULTS:Regular fibrillar and ridge patterns were more likely to be biopsied (P = 0.01). The majority of AMN (58.1%) and AM (60%) biopsied were due to physician-deemed concerning dermoscopic patterns. 39.2% of these cases were parallel furrow, lattice-like or regular fibrillar. When patients were asked to follow-up within a 3- to 6-month period, only 16.7% of the patients returned within that interval. The three-step algorithm would have correctly identified four of five AM for biopsy, missing a 6 mm, multicomponent, invasive melanoma. CONCLUSION:We found one major educational gap in the recognition of low-risk lesions with high rates of biopsy of the fibrillary pattern. Recognizing low-risk dermoscopic patterns could reduce the rate of biopsy of AMN by 23.3%. We identified two major practice gaps, poor patient compliance with follow-up and the potential insensitivity of the three-step algorithm to small multicomponent acral melanocytic lesions.
Project description:This article refers to the Computer Aided Diagnosis of the melanoma skin cancer. We derive wavelet-based features of melanoma from the dermoscopic images of pigmental skin lesions and apply binary C-SVM classifiers to discriminate malignant melanoma from dysplastic nevus. The aim of this research is to select the most efficient model of the SVM classifier for various image resolutions and to search for the best resolution-invariant wavelet bases. We show AUC as a function of the wavelet number and SVM kernels optimized by the Bayesian search for two independent data sets. Our results are compatible with the previous experiments to discriminate melanoma in dermoscopy images with ensembling and feed-forward neural networks.
Project description:Introduction The incidence and mortality of melanoma are rising rapidly. Despite ongoing research and the introduction of new therapeutic methods, advanced melanoma is still considered incurable. Early detection and surgical excision of the tumor increases patients’ survival. Since the diagnostic protocol includes surgical excision of all suspicious lesions, it is burdened with a high rate of unnecessary excisions that cause unwanted scarring. This is why the development of accurate diagnostic techniques is crucial. The most common diagnostic tool in early diagnosis of cutaneous melanoma is dermoscopy, though there are emerging new techniques, such as reflectance confocal microscopy and optical coherence tomography. Aim To evaluate diagnostic accuracy of reflectance confocal microscopy as a secondary examination in melanocytic lesions previously diagnosed as melanomas by means of dermoscopy. Material and methods Forty-six melanocytic lesions presenting dermoscopic features of cutaneous malignant melanoma were examined by means of reflectance confocal microscopy. Results The RCM evaluation showed sensitivity at the level of 100% and specificity at 62%. Conclusions It can be estimated that double evaluation of melanocytic lesions by dermoscopy and reflectance confocal microscopy may allow up to 62% of unnecessary excisions to be avoided.
Project description:Importance:Deep learning convolutional neural networks (CNNs) have shown a performance at the level of dermatologists in the diagnosis of melanoma. Accordingly, further exploring the potential limitations of CNN technology before broadly applying it is of special interest. Objective:To investigate the association between gentian violet surgical skin markings in dermoscopic images and the diagnostic performance of a CNN approved for use as a medical device in the European market. Design and Setting:A cross-sectional analysis was conducted from August 1, 2018, to November 30, 2018, using a CNN architecture trained with more than 120 000 dermoscopic images of skin neoplasms and corresponding diagnoses. The association of gentian violet skin markings in dermoscopic images with the performance of the CNN was investigated in 3 image sets of 130 melanocytic lesions each (107 benign nevi, 23 melanomas). Exposures:The same lesions were sequentially imaged with and without the application of a gentian violet surgical skin marker and then evaluated by the CNN for their probability of being a melanoma. In addition, the markings were removed by manually cropping the dermoscopic images to focus on the melanocytic lesion. Main Outcomes and Measures:Sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve for the CNN's diagnostic classification in unmarked, marked, and cropped images. Results:In all, 130 melanocytic lesions (107 benign nevi and 23 melanomas) were imaged. In unmarked lesions, the CNN achieved a sensitivity of 95.7% (95% CI, 79%-99.2%) and a specificity of 84.1% (95% CI, 76.0%-89.8%). The ROC AUC was 0.969. In marked lesions, an increase in melanoma probability scores was observed that resulted in a sensitivity of 100% (95% CI, 85.7%-100%) and a significantly reduced specificity of 45.8% (95% CI, 36.7%-55.2%, P?<?.001). The ROC AUC was 0.922. Cropping images led to the highest sensitivity of 100% (95% CI, 85.7%-100%), specificity of 97.2% (95% CI, 92.1%-99.0%), and ROC AUC of 0.993. Heat maps created by vanilla gradient descent backpropagation indicated that the blue markings were associated with the increased false-positive rate. Conclusions and Relevance:This study's findings suggest that skin markings significantly interfered with the CNN's correct diagnosis of nevi by increasing the melanoma probability scores and consequently the false-positive rate. A predominance of skin markings in melanoma training images may have induced the CNN's association of markings with a melanoma diagnosis. Accordingly, these findings suggest that skin markings should be avoided in dermoscopic images intended for analysis by a CNN. Trial Registration:German Clinical Trial Register (DRKS) Identifier: DRKS00013570.