Background The diameter of congenital melanocytic nevi (CMN) has served as the lone criterion for determining risks of adverse outcomes such as melanoma. A standardized description of additional ...morphologic features is needed. Objective We sought to develop a consensus-based standardized categorization of cutaneous features of CMN and to test agreement among experts on the proposed scheme. Methods An interdisciplinary group of experts in the field of CMN was surveyed using a detailed questionnaire. Applicability of the expert consensus-based scheme was tested for interobserver agreement. Results The principal variable of the consensus-based categorization is CMN size, based on maximal diameter the CMN is projected to attain by adulthood. CMN size categories include: small (<1.5 cm); medium (M1: 1.5-10 cm, M2: >10-20 cm); large (L1: >20-30 cm, L2: >30-40 cm); and giant (G1: >40-60 cm, G2: >60 cm). In addition, number of satellite nevi in the first year of life is categorized into none, 1 to 20, more than 20 to 50, and more than 50 satellites. Additional descriptors of CMN include anatomic localization, color heterogeneity, surface rugousity and presence of hypertrichosis (described as none, moderate, marked), and presence of dermal or subcutaneous nodules (none, scattered, extensive). Assessment of consistency among 3 experts showed moderate to excellent interobserver agreement for categorization of the clinical descriptors (kappa values 0.54-0.93). Limitations Applicability of the proposed scheme was tested in a virtual setting and only among experts. Conclusion The proposed categorization scheme for CMN was agreed upon by experts and showed good interobserver agreement. Such standardized reporting of patients with CMN facilitates the development of an international clinical database for the study of large and giant CMN.
Computer vision may aid in melanoma detection.
We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images.
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.
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).
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.
Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists.
Stage III melanoma is associated with a high risk of relapse and mortality. Nevertheless, follow-up guidelines have largely been empirical rather than evidence-based.
Clinical records of stage III ...patients with no evidence of disease seen at Memorial Sloan-Kettering Cancer Center (MSKCC) between 1992 and 2004, who ultimately relapsed, were reviewed retrospectively to evaluate date of first relapse, time to first relapse, method of first relapse detection, and survival. We also determined overall 5-year relapse-free survival (RFS) of all stage III patients seen at MSKCC during this period.
The overall 5-year RFS for stage IIIA, IIIB, and IIIIC patients was 63%, 32%, and 11%, respectively. Among relapsing patients, 340 had adequate follow-up to be evaluable for all parameters. Site of first relapse was local/in-transit (28%), regional nodal (21%), or systemic (51%). First relapses were detected by the patient or family, physician, or by screening radiologic tests in 47%, 21%, and 32% of patients, respectively. Multivariate analysis revealed that better overall survival was associated with younger age and first relapse being local/in-transit or nodal, asymptomatic, or resectable. For each substage, we estimated site-specific risk of first relapse.
Patients detected almost half of first relapses. Our data suggest that routine physical examinations beyond 3 years for stage IIIA, 2 years for stage IIIB, and 1 year for stage IIIC patients and radiologic imaging beyond 3 years for stages IIIA and IIIB and 2 years for stage IIIC patients would be expected to detect few first systemic relapses.
IMPORTANCE: A neural network-based model (i31-GEP-SLNB) that uses clinicopathologic factors (thickness, mitoses, ulceration, patient age) plus molecular analysis (31-gene expression profiling) has ...become commercially available to guide selection for sentinel lymph node (SLN) biopsy in cutaneous melanoma, but its clinical utility is not well characterized. OBJECTIVE: To determine if use of the i31-GEP-SLNB model is associated with clinical benefit when used to select patients for SLN biopsy. DESIGN, SETTING, AND PARTICIPANTS: This decision-analytic study used data derived from a published external validation study of the i31-GEP-SLNB prediction model. Participants included patients with primary cutaneous melanoma. MAIN OUTCOMES AND MEASURES: The primary outcome was the net benefit associated with using the i31-GEP-SLNB model for SLN biopsy selection compared with other selection strategies (SLN biopsy for all patients and SLN biopsy for no patients) at a 5% risk threshold. Analyses were stratified by American Joint Committee on Cancer (AJCC) T category. The reduction in the number of avoidable SLN biopsies and relative utility were also calculated. RESULTS: Compared with other SLN biopsy selection strategies, use of the i31-GEP-SLNB model had greater net benefit for patients with T1b (+0.012), T2a (+0.002), and T2b melanoma (+0.002) but not for those with high-risk T1a (−0.003) disease. The improvement in relative utility was +22% in patients with T1b, +1% in T2a, and +2% in T2b melanoma. Compared with SLN biopsy for all patients, use of the model would equate to a 23% decrease in SLN biopsies among patients with T1b disease without an SLN metastasis with no increase in the number of patients with an SLN metastasis left untreated; among patients with T2a and T2b melanoma, the net decrease in avoidable biopsies compared with SLN biopsy for all was 3% and 4%, respectively. CONCLUSIONS AND RELEVANCE: The findings of this decision-analytic study suggest that i31-GEP SLNB has significant potential for risk-stratifying patients with T1b melanoma if using a 5% risk threshold; its role among patients with T1a and T2 melanoma or using other risk thresholds requires further study. A prospective validation study confirming the added clinical benefit and cost-effectiveness of i31-GEP-SLNB compared with free clinicopathologic-based prediction models is needed in patients with T1b melanoma.
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.
With melanoma incidence rising and mortality stable, some question whether the melanoma epidemic is real. Melanoma thickness and survival trends may provide insights, but previous studies have been ...limited because of missing data on thickness.
With a validated imputation method for missing thickness data, we characterized melanoma thickness and survival trends among men and women in the Surveillance, Epidemiology, and End Results (SEER)-9 registries between 1989 and 2009. A total of 98,498 cases of invasive melanoma were identified. All statistical tests were two-sided.
Incidence per 100 000 person-years increased (13.94, 95% confidence interval CI = 13.65 to 14.23, to 21.87, 95% CI = 21.56 to 22.19, P < .001) between 1989 to 1991 and 2007 to 2009, fatal incidence remained stable (2.32, 95% CI = 2.2 to 2.4, to 2.08, 95% CI = 2.0 to 2.2, P = .20) between 1989 to 1991 and 1998 to 2000, and five-year survival increased (88.29%, 95% CI = 87.60% to 88.95%, to 91.68%, 95% CI = 91.22% to 92.12%, P < .001) between 1989 to 1991 and 2001 to 2003. Increase in incidence occurred across all thickness groups. Median thickness decreased (0.73 to 0.58mm). Geometric mean thickness decreased (0.77 to 0.65mm) 4.6% (95% CI = 4.2% to 5.0%) every three years in multivariable analysis. Thickness decreased among T1/T2 tumors (0.01-1.00 and 1.01-2.00mm) and among all age and sex groups, whites, non-Hispanics, and all body sites. However, thickness increased among T3/T4 tumors (2.01-4.00 and > 4.00mm) and nodular melanomas; acral lentiginous melanomas approached statistical significance. Thickness remained unchanged among some racial minorities. Melanoma-specific survival improved (hazard ratio HR = 0.89, 95% CI = 0.88 to 0.91) every three years in multivariable analysis. Improvements in survival occurred across all subgroups except nonblack minorities, and nodular and acral lentiginous subtypes.
Increasing incidence across all thickness groups coupled with T3/T4 lesions becoming thicker suggests that the melanoma epidemic is real and not simply an artifact of increased detection pressure of earlier-stage T1/T2 lesions. Survival is generally improving independent of thickness, but improvements in survival have not been experienced by certain minorities, and nodular and acral lentiginous subtypes.
On the basis of the clinical impression and current knowledge, acquired melanocytic nevi and melanomas may not occur in random localizations. The goal of this study was to identify whether their ...distribution on the back is random and whether the location of melanoma correlates with its adjacent lesions. Therefore, patient-level and lesion-level spatial analyses were performed using the Clark‒Evans test for complete spatial randomness. A total of 311 patients with three-dimensional total body photography (average age of 40.08 30‒49 years; male/female ratio: 128/183) with 5,108 eligible lesions in total were included in the study (mean sum of eligible lesions per patient of 16.42 3‒199). The patient-level analysis revealed that the distributions of acquired melanocytic neoplasms were more likely to deviate toward clustering than dispersion (average z-score of ‒0.55 95% confidence interval = ‒0.69 to ‒0.41; P < 0.001). The lesion-level analysis indicated a higher portion of melanomas (n = 57 of 72, 79.2% 95% confidence interval = 69.4‒88.9%) appearing in proximity to neighboring melanocytic neoplasms than to nevi (n = 2,281 of 5,036, 45.3% 95% confidence interval = 43.9‒46.7%). In conclusion, the nevi and melanomas’ distribution on the back tends toward clustering as opposed to dispersion. Furthermore, melanomas are more likely to appear proximally to their neighboring neoplasms than to nevi. These findings may justify various oncogenic theories and improve diagnostic methodology.