Artificial Intelligence in Dermatology: A Systematic Review of Its Applications in Melanoma and Keratinocyte Carcinoma Diagnosis.

BACKGROUND: Limited access to dermatologic care may pose an obstacle to the early detection and intervention of cutaneous malignancies. The role of artificial intelligence (AI) in skin cancer diagnosis may alleviate potential care gaps. OBJECTIVE: The aim of this systematic review was to offer an in-depth exploration of published AI algorithms trained on dermoscopic and macroscopic clinical images for the diagnosis of melanoma, basal cell carcinoma, and cutaneous squamous cell carcinoma (cSCC). METHODS: Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a systematic review was conducted on peer-reviewed articles published between January 1, 2000, and January 26, 2023. RESULTS AND DISCUSSION: Among the 232 studies in this review, the overall accuracy, sensitivity, and specificity of AI for tumor detection averaged 90%, 87%, and 91%, respectively. Model performance improved with time. Despite seemingly impressive performance, the paucity of external validation and limited representation of cSCC and skin of color in the data sets limits the generalizability of the current models. In addition, dermatologists coauthored only 12.9% of all studies included in the review. Moving forward, it is imperative to prioritize robustness in data reporting, inclusivity in data collection, and interdisciplinary collaboration to ensure the development of equitable and effective AI tools.

Defining and quantifying histopathologic risk factors for regional and distant metastases in a large cohort of vulvar squamous cell carcinomas.

BACKGROUND: Vulvar squamous cell carcinoma (vSCC) is a rare tumor with a good prognosis when treated at a localized stage. However, once regional/distant metastasis occurs, vSCC can be rapidly fatal. Thus, it is important to identify tumor prognostic features so that high-risk cases can be prioritized for further diagnostic workup and treatment. OBJECTIVE: To estimate the risk of regional/distant metastasis at presentation and sentinel lymph node status for vSCC based on histopathologic characteristics. METHODS: A retrospective cohort study of 15,188 adult vSCC cases from the National Cancer Database diagnosed from 2012 to 2019. RESULTS: We provide specific estimates of the risk of clinically positive nodes and metastatic disease at presentation and sentinel lymph node positivity according to tumor size, moderate/poor tumor differentiation, and lymph-vascular invasion. These histopathologic factors were all significantly associated with the tested clinical outcomes in a multivariable analysis. Moderate (hazard ratio, 1.190; P < .001) and poor differentiation (hazard ratio, 1.204; P < .001) and lymph-vascular invasion (hazard ratio, 1.465; P < .001) were also associated with significantly poorer overall survival. LIMITATIONS: Data on disease-specific survival not available in the data set. CONCLUSIONS: We demonstrate the association of the histopathologic characteristics of vSCC with clinically important outcomes. These data may provide individualized information when discussing diagnostic/treatment recommendations, particularly regarding sentinel lymph node biopsy. These data may also guide future staging and risk stratification efforts for vSCC.

Assessing Rates of Positive Surgical Margins After Standard Excision of Vulvar Melanomas.

BACKGROUND: Vulvar melanoma is a rare malignancy with frequent recurrence and poor prognosis. National guidelines recommend wide local excision of these tumors with allowances for narrower margins for anatomic and functional limitations, which are common on specialty sites. There is presently a lack of data of margin positivity after standard excision of vulvar melanomas. OBJECTIVE: We aim to evaluate the rate of positive margins after standard excision of vulvar melanomas. MATERIALS AND METHODS: Retrospective cohort study of surgically excised vulvar melanomas from the NCDB diagnosed from 2004 to 2019. RESULTS: We identified a total of 2,226 cases. Across surgical approaches and tumor stages, 17.2% (Standard Error [SE]: 0.8%) of cases had positive surgical margins. Among tumor stages, T4 tumors were most commonly excised with positive margins (22.9%, SE: 1.5%). On multivariable survival analysis, excision with positive margins was associated with significantly poorer survival (Hazard Ratio 1.299, p = .015). CONCLUSION: We find that positive margin rates after standard excision of vulvar malignancies are higher than for other specialty site melanomas. Our data suggest that use of surgical approaches with complete margin assessment may improve local control and functional outcomes for patients with vulvar melanoma as they have for patients with other specialty site melanomas.

Evaluating Rates of Positive Margins After Standard Excision of Cutaneous Adnexal Malignancies.

BACKGROUND: It is recommended to excise adnexal neoplasms with standard local excision or Mohs micrographic surgery (MMS), although many occur on high-risk sites such as the head and neck (H&N) and exhibit subclinical extension. Minimal evidence exists on the efficacy of standard excisions for these tumors. OBJECTIVE: To evaluate the rate of positive surgical margins after standard excision of adnexal tumors. METHODS: Retrospective cohort study of cutaneous adnexal malignancies from the National Cancer Database diagnosed from 2004 to 2019. RESULTS: The authors identified a total of 4,402 cases treated with standard excision. Tumors on the H&N were approximately twice as likely as those on the trunk and extremities (T&E) to be excised with positive margins (odds ratio 2.146, p < .001), with the highest estimated rate for eccrine adenocarcinoma (12.1%, SE: 2.3%). The subtype with the highest positive margin rate on the T&E was microcystic adnexal carcinoma (8.0%, SE: 2.9). Positive margins were associated with poorer overall survival on multivariable survival analysis (hazard ratio 1.299, p = .015). CONCLUSION: The authors present subtype- and site-specific positive margin rates for adnexal tumors treated with standard excision, which suggest that tumors on the H&N and some T&E subtypes, should be considered for MMS.

Applying Occam's Razor and Descending the Reconstructive Ladder: The Modified Cheek Advancement Flap for Reconstruction of Nasal Defects.

Nasal reconstruction has important functional and cosmetic considerations, as proper repair of nasal defects is necessary to maintain function of the nasal airway and to recreate the normal appearance of this central facial structure. Cheek advancement flaps provide matched, mobile, and highly vascularized tissue for the reconstruction of nasal defects, allowing for the concealment of incisions within natural creases in a one-stage approach. However, cheek advancement flaps are often underutilized for nasal reconstruction because of their difficulty in restoring nasal contour. We describe reconstruction of 19 nasal dorsal and sidewall defects 0.8 to 3 cm in size. We incorporated a periosteal anchoring suture to maintain/restore nasal contour and additionally removed a half standing cone inferior to the defect to prevent encroachment of the nasal ala or alar crease. All patients were evaluated at least 3 months postoperatively. In all patients, we were able to restore concavity of the nasofacial sulcus, preserve the biconvex nasal tips, prevent alar flaring and retraction, and conserve the alar groove. All patients had excellent functional and cosmetic outcomes. We believe this modified cheek advancement flap provides functionally and aesthetically superior results and can be considered as a first-line approach for repair of nasal dorsal and sidewall defects in subselected patients.

An expert panel consensus on opioid-prescribing guidelines for dermatologic procedures.

BACKGROUND: Opioid overprescribing is a major contributor to the opioid crisis. The lack of procedure-specific guidelines contributes to the vast differences in prescribing practices. OBJECTIVE: To create opioid-prescribing consensus guidelines for common dermatologic procedures. METHODS: We used a 4-step modified Delphi method to conduct a systematic discussion among a panel of dermatologists in the fields of general dermatology, dermatologic surgery, and cosmetics/phlebology to develop opioid prescribing guidelines for some of the most common dermatologic procedural scenarios. Guidelines were developed for opioid-naive patients undergoing routine procedures. Opioid tablets were defined as oxycodone 5-mg oral equivalents. RESULTS: Postoperative pain after most uncomplicated procedures (76%) can be adequately managed with acetaminophen and/or ibuprofen. Group consensus identified no specific dermatologic scenario that routinely requires more than 15 oxycodone 5-mg oral equivalents to manage postoperative pain. Group consensus found that 23% of the procedural scenarios routinely require 1 to 10 opioid tablets, and only 1 routinely requires 1 to 15 opioid tablets. LIMITATIONS: These recommendations are based on expert consensus in lieu of quality evidence-based outcomes research. These recommendations must be individualized to accommodate patients' comorbidities. CONCLUSIONS: Procedure-specific opioid prescribing guidelines may serve as a foundation to produce effective and responsible postoperative pain management strategies after dermatologic interventions.

Current Research in Melanoma and Aggressive Nonmelanoma Skin Cancer.

There have been several significant advances in cancer treatment in the last decade that are applicable to the treatment of melanoma and advanced nonmelanoma skin cancers. Among these are the development of immune checkpoint inhibitors targeting the programmed death protein-1 (PD-1)/programmed death legand-1 (PDL-1) axis, as well as targeted inhibitors of the BRAF/MEK signaling cascade in melanoma, and the hedgehog signaling pathway in basal cell carcinoma (BCC). These immune-based and targeted therapies have dramatically changed the treatment options for locally advanced and metastatic melanoma, Merkel's cell carcinoma, cutaneous squamous cell carcinoma (cSCC), and BCC. In this article, we will briefly review the currently approved targeted and immunotherapy-based treatments for locally advanced and metastatic melanoma, Merkel's cell carcinoma, and cSCC and discuss various combinations of approved therapies, as well as emerging therapeutic candidates that are currently in clinical trials, including novel checkpoint inhibitors in development, intratumoral oncolytic agents (viral and nonviral), and various immune-based therapies such as toll-like receptor (TLR) agonists, adoptive T-cell therapy, T-cell costimulation, and innate immune cell therapy. For advanced BCC, we will discuss trials investigating the currently approved smoothened (SMO) inhibitors for neoadjuvant use, emerging SMO inhibitors in development, topical SMO inhibitors, alternative targets in the hedgehog signaling pathway, and the use of anti-PD-1 agents for advanced BCC both alone and in combination with SMO inhibitors.

Initial skin cancer screening for solid organ transplant recipients in the United States: Delphi method development of expert consensus guidelines.

Skin cancer is the most common malignancy affecting solid organ transplant recipients (SOTR), and SOTR experience increased skin cancer-associated morbidity and mortality. There are no formal multidisciplinary guidelines for skin cancer screening after transplant, and current practices are widely variable. We conducted three rounds of Delphi method surveys with a panel of 84 U.S. dermatologists and transplant physicians to establish skin cancer screening recommendations for SOTR. The transplant team should risk stratify SOTR for screening, and dermatologists should perform skin cancer screening by full-body skin examination. SOTR with a history of skin cancer should continue regular follow-up with dermatology for skin cancer surveillance. High-risk transplant patients include thoracic organ recipients, SOTR age 50 and above, and male SOTR. High-risk Caucasian patients should be screened within 2 years after transplant, all Caucasian, Asian, Hispanic, and high-risk African American patients should be screened within 5 years after transplant. No consensus was reached regarding screening for low-risk African American SOTR. We propose a standardized approach to skin cancer screening in SOTR based on multidisciplinary expert consensus. These guidelines prioritize and emphasize the need for screening for SOTR at greatest risk for skin cancer.

Stratification of Poor Outcomes for Cutaneous Squamous Cell Carcinoma in Immunosuppressed Patients Using the American Joint Committee on Cancer Eighth Edition and Brigham and Women's Hospital Staging Systems.

BACKGROUND: Staging systems for cutaneous squamous cell carcinoma (CSCC) include Brigham and Women's Hospital (BWH) and American Joint Committee on Cancer staging system, eighth edition (AJCC-8). OBJECTIVE: To evaluate and compare AJCC-8 and BWH staging systems for CSCC in immunosuppressed patients. MATERIALS AND METHODS: A retrospective cohort study of immunosuppressed patients diagnosed with primary CSCC from 2012 to 2016. The main end point was any poor outcome (PO), which included local recurrence, nodal metastasis, and disease-specific death. RESULTS: Fifty-eight immunosuppressed patients had 263 CSCCs. Fifty percent of tumors were AJCC-8 T1, 44.7% T2, and 4.8% T3. Fifty percent of tumors were BWH T1, 48.5% T2a, 1.3% T2b, and 0.4% T3. Risk of PO for AJCC-8 was 1.7%, 8.8%, and 36.4% for T1, T2, and T3, respectively (p < .01). Risk of PO for BWH was 1.8%, 9.9%, 33.3%, and 100.0% for T1, T2a, T2b, and T3, respectively (p < .01). Thirty-six percent of AJCC-8 T3/T4 tumors had POs compared with 5.1% in low T1/T2 stages (p = .002). Fifty percent of BWH T2b/T3 tumors had POs compared with 5.3% in low T1/T2a stages (p = .01). CONCLUSION: AJCC-8 and BWH staging systems stratify CSCC with similar distinctiveness, homogeneity, and monotonicity for immunosuppressed patients.

Expertise in Head and Neck Cutaneous Reconstructive Surgery.

BACKGROUND: The management of skin cancers has evolved with the development of Mohs micrographic surgery and a greater emphasis on surgical training within dermatology. It is unclear whether these changes have translated into innovations and contributions to the reconstructive literature. OBJECTIVE: To assess contributions from each medical specialty to the cutaneous head and neck oncologic reconstructive literature. METHODS: The authors conducted a systematic review of the head and neck reconstructive literature from 2000 through 2015 based on a priori search terms relating to suture technique, linear closure, advancement, rotation, transposition and interpolation flaps, and identified the specialty of the senior authors. RESULTS: The authors identified 74,871 articles, of which 1,319 were relevant. Under suture technique articles, the senior authors were primarily dermatologists (58.2%) and plastic surgeons (20.3%). Under linear closure, the authors were dermatologists (48.1%), plastic surgeons (22.2%), and otolaryngologists (20.4%). Under advancement and rotation flaps, the senior authors were plastic surgeons (40.5%, 38.9%), dermatologists (38.1%, 34.2%), and otolaryngologists (14.4%, 21.6%). Under transposition and interpolation flaps, the senior authors were plastic surgeons (47.3%, 39.4%), dermatologists (32.3%, 27.0%), and otolaryngologists (15.3%, 23.4%). CONCLUSION: The primary specialties contributing to the cutaneous head and neck reconstructive literature are plastic surgery, dermatology, and otolaryngology.

Digital imaging biomarkers feed machine learning for melanoma screening.

We developed an automated approach for generating quantitative image analysis metrics (imaging biomarkers) that are then analysed with a set of 13 machine learning algorithms to generate an overall risk score that is called a Q-score. These methods were applied to a set of 120 "difficult" dermoscopy images of dysplastic nevi and melanomas that were subsequently excised/classified. This approach yielded 98% sensitivity and 36% specificity for melanoma detection, approaching sensitivity/specificity of expert lesion evaluation. Importantly, we found strong spectral dependence of many imaging biomarkers in blue or red colour channels, suggesting the need to optimize spectral evaluation of pigmented lesions.