Using Artificial Intelligence as a Melanoma Screening Tool in Self-Referred Patients.

INTRODUCTION: Early detection of melanoma requires timely access to medical care. In this study, we examined the feasibility of using artificial intelligence (AI) to flag possible melanomas in self-referred patients concerned that a skin lesion might be cancerous. METHODS: Patients were recruited for the study through advertisements in 2 hospitals in Halifax, Nova Scotia, Canada. Lesions of concern were initially examined by a trained medical student and if the study criteria were met, the lesions were then scanned using the FotoFinder System®. The images were analyzed using their proprietary computer software. Macroscopic and dermoscopic images were evaluated by 3 experienced dermatologists and a senior dermatology resident, all blinded to the AI results. Suspicious lesions identified by the AI or any of the 3 dermatologists were then excised. RESULTS: Seventeen confirmed malignancies were found, including 10 melanomas. Six melanomas were not flagged by the AI. These lesions showed ambiguous atypical melanocytic proliferations, and all were diagnostically challenging to the dermatologists and to the dermatopathologists. Eight malignancies were seen in patients with a family history of melanoma. The AI's ability to diagnose malignancy is not inferior to the dermatologists examining dermoscopic images. CONCLUSION: AI, used in this study, may serve as a practical skin cancer screening aid. While it does have technical and diagnostic limitations, its inclusion in a melanoma screening program, directed at those with a concern about a particular lesion would be valuable in providing timely access to the diagnosis of skin cancer.

Merkel cell carcinoma: an update.

Merkel cell carcinoma (MCC) is an uncommon primary cutaneous neuroendocrine carcinoma associated with an adverse prognosis. In recent years, our understanding of MCC biology has markedly progressed. Since the discovery of the Merkel cell polyomavirus, it has become clear that MCC represents an ontogenetically dichotomous group of neoplasms with overlapping histopathology. Specifically, most MCCs arise secondary to viral oncogenesis, while a smaller subset is the direct result of UV-associated mutations. The distinction of these groups bears relevance in their immunohistochemical and molecular characterization, as well as in disease prognosis. Further recent developments relate to the landmark utilization of immunotherapeutics in MCC, providing optimistic options for the management of this aggressive disease. In this review, we discuss both fundamental and emerging concepts in MCC, with a particular focus on topics of practical relevance to the surgical or dermatopathologist.

Morphological patterns of metastases from combined Merkel cell carcinomas: study of an eastern Canadian cohort of cases.

Combined Merkel cell carcinomas are hybrid tumors composed of neuroendocrine and other phenotypic (usually squamous) elements. They form a minority of Merkel cell carcinomas (MCCs) as a whole, are usually Merkel cell polyomavirus-negative, and have rarely been segregated for specific study. Sporadic reports have indicated that metastases from these tumors can show a combined phenotype. We retrospectively studied 38 cases (24 men [63%], 14 women [37%], mean age 78 years [range, 46-99 years]) of combined MCC. Metastases occurred in 20 patients (53%) (at presentation and/or in follow-up [mean 38 months (range, 0.6-185 months)]). Those from 17 individuals (45%) were examined microscopically. These were mainly nodal in distribution. In 12 patients (71%), the secondary deposits were of pure neuroendocrine type, whereas in 5 (29%), combined deposits were identified. Squamous elements were the most common divergent component, in the primary and secondary tumors. The combined metastases varied from obvious squamous nests in a neuroendocrine background to scattered bizarre tumor giant cells expressing CK5/6 on immunohistochemistry. In one case, individual nodes within a single basin displayed purely squamous or purely neuroendocrine deposits. The mean overall survival in the cohort was 48 months (range, 30-67 months) and the mortality was 82%. Our work sheds light on the frequency and patterns of metastases in combined MCCs. In concert with the poor outcome data documented by others, it also raises a question as to the potential prognostic significance of a combined phenotype per se, independent of a virus-negative status and other variables. This issue deserves further study.

CytoLyt® fixation and decalcification pretreatments alter antigenicity in normal tissues compared with standard formalin fixation.

Immunohistochemistry is used on cell blocks constructed from cytopathology samples fixed in methanol-based fixatives, such as CytoLyt (Cytyc Corp), and on surgical pathology tissues exposed to decalcifying agents, often without technical validation. We evaluated a panel of commonly utilized antibodies in normal tissues exposed to differing preanalytic conditions as follows: CytoLyt fixation, formalin fixation followed by exposure to decalcifying agents (Leica Decalcifier I-10% formic acid or Leica Decalcifier II-5% hydrochloric acid), or standard formalin fixation. Altered expression was observed with several antibodies compared with standard formalin fixation. Specifically, there was absent or near absent expression of thyroid transcription factor 1 (TTF-1), D2-40, and CD20 in CytoLyt-fixed tissues, whereas reduced expression was observed for p63, estrogen receptor, S100 protein, CD3, calretinin, chromogranin, and synaptophysin. Absent or near absent expression of TTF-1 was also observed with exposure to hydrochloric acid, whereas reduced expression was observed for CK5/6, CK7, p63, estrogen receptor, leukocyte common antigen, CD3, CD20, and synaptophysin. Exposure to formic acid had less impact with reduced expression observed for only 3 antibodies (CK8/18, CK7, and TTF-1). The results of this study demonstrate the need to validate immunohistochemical protocols on control tissue treated in the same manner as test tissue, including CytoLyt fixation and exposure of tissue to decalcifying agents.

Microsatellite instability status does not predict total lymph node or negative lymph node retrieval in stage III colon cancer.

The relationship between higher total lymph node resection number in colorectal cancer resection specimens and improved overall survival is well known. Recent studies describe an association between a high rate of microsatellite instability and a high total lymph node count in colorectal cancer. Higher lymph node retrieval may potentially explain the improved survival seen in cancers with microsatellite instability. We investigate whether these associations can be validated in a cohort of American Joint Committee on Cancer stage III colon cancers. Medical records from 200 cases of stage III colon cancer resection specimens were reviewed, and sufficient tissue was available for 168. Expression of DNA mismatch repair proteins was determined by immunohistochemistry, and microsatellite status, by polymerase chain reaction. The mean total lymph node count in cases with microsatellite instability versus microsatellite stable tumors (15.9 versus 16.9; P = .664) and the mean number of negative lymph nodes in each respective category (12.2 versus 13.6; P = .522) were not significantly different. There was no difference between microsatellite stable cases and cases with microsatellite instability when total lymph node counts (P = .953) or negative lymph node counts (P = .381) were analyzed with respect to percentage of cases above and below the medians. This cohort of stage III colon cancers does not support a significant relationship between microsatellite status and a higher retrieval of total or negative lymph nodes. Although microsatellite instability is associated with improved overall survival in our cohort (P = .026), the reason for this does not appear to be related to higher numbers of retrieved lymph nodes.