DecisionDx® DiffDx™-Melanoma (previously known as ConfirmDx-Melanoma; Castle Biosciences), a diagnostic test designed to aid dermatopathologists in characterizing difficult-to-diagnose melanocytic lesions and help improve cancer treatment decisions, is now commercially available in the United States.
Melanoma is an aggressive type of skin cancer. According to estimates from the American Cancer Society’s in the United States for 2020, about 60,190 men and 40,160 women will be be diagnosed with the disease, and about 4,610 men and 2,240 women are expected to die from the disease.
The majority of patients are diagnosed with stage I or II (localized) disease as defined by the American Joint Committee on Cancer (AJCC) staging system . According to this system, patients with early stage melanoma (i.e., AJCC stage I–II) are regarded as having a good prognosis according to population-based risk estimates. However, evidence shows that due to the greater number of individuals within these earlier stages, more than twice as many people diagnosed with early stage disease will ultimately die of melanoma compared with those diagnosed with stage III melanoma 
Suspicious pigmented lesions
DecisionDx DiffDx-Melanoma is designed for use in patients with suspicious pigmented lesions.
“We are pleased to offer DecisionDx DiffDx-Melanoma, which has been designed to aid dermatopathologists in characterizing difficult-to-diagnose melanocytic lesions as benign or malignant,” said Derek Maetzold, president and chief executive officer of Castle.
“I am particularly proud of our research and development team, who successfully maintained timelines from program initiation to validation. And employing our artificial intelligence tools, we were able to achieve our target product profile goals for DiffDx-Melanoma: improved accuracy metrics with a substantially reduced intermediate-risk zone, to enable dermatopathologists to act upon a test result from DiffDx-Melanoma. This test has been demonstrated to provide a definitive result in more than 96% of the reported cases, which allows for clinicians to have a greater, direct impact on patient care,” Maetzold added.
“Of the approximately 2 million suspicious pigmented lesions biopsied annually in the U.S., approximately 300,000 of those cannot be confidently classified as either benign or malignant through traditional histopathology methods,” noted Sarah I. Estrada, M.D., FCAP, laboratory director of Affiliated Dermatology®.
Prior to the introduction of DecisionDx-Melanoma, almost all treatment plan decisions made around the time of diagnosis relied solely upon traditional clinical and pathologic prognostic factors, including whether to perform the invasive sentinel lymph node (SLN) biopsy surgical procedure to see whether cancer cells were found in lymph nodes.
Per AJCC guidelines, a sentinel lymph node biopsy (SLNB) should be considered for patients with stage T1b melanoma and above as well as for a subset of T1a patients with high-risk features SLNB surgery.
However, the clinical and pathology factors that lead physicians to recommend has limitations and the decision to perform SLNB is not without risk.
While the rates are low (5–10%), the SLNB procedure can be associated with complications including pain, bleeding, allergic reactions to the dye, wound infection, seromas, deep vein thrombosis, nerve damage and edema.
Furthermore, the procedure requires a dedicated team that includes nuclear medicine physicians, surgeons and pathologists. In most cases, the procedure also involves general anesthesia.
Interestingly, approximately 88% of patients who undergo the SLNB surgery are found to have an SLN-negative biopsy result, meaning they remain categorized as lower risk (Stage I or II). But unfortunately, despite being classified as low risk, two out of three patients who develop metastatic disease and die from their primary melanoma tumor were initially classified as Stage I or II, many of whom received an SLN-negative biopsy result following SLNB surgery.
“Undertreatment or delayed identification of melanoma can lead to tumor spread and increased risk of melanoma-specific mortality. On the other hand, overtreatment can impact patient quality of life, potentially resulting in adverse events and increased morbidity. DecisionDx DiffDx-Melanoma is designed to provide diagnostic clarity for dermatopathologists and help dermatologists deliver more informed patient management plans,” Estrada added.
Gene expression profile (GEP) test
DecisionDx DiffDx-Melanoma is a gene expression profile (GEP) test designed to aid dermatopathologists in characterizing difficult-to-diagnose melanocytic lesions and classifies these lesions as: benign (gene expression profile suggestive of benign neoplasm); intermediate-risk (gene expression profile cannot exclude malignancy); or malignant (gene expression profile suggestive of melanoma).
The intent-to-treat analysis of the DiffDx-Melanoma validation study showed that the test accurately diagnosed malignant and benign cases in 96.6% of the cases with 99.1% sensitivity, 94.3% specificity, 93.6% positive predictive value and 99.2% negative predictive value. An intermediate-risk result was identified in 3.6% of the cases.
Castle has three dermatologic cancer gene expression profile tests commercially available in the U.S.: DecisionDx-Melanoma, DecisionDx-SCC and DiffDx-Melanoma. All three tests were developed in-house by Castle and are validated and supported by multiple peer-reviewed publications.
 Key Statistics for Melanoma Skin Cancer. American Cancer Society. Online. last accessed November 2, 2020.
 Gershenwald JE, Scolyer RA, Hess KR et al. Melanoma staging: evidence-based changes in the American Joint Committee on Cancer eighth edition cancer staging manual. CA Cancer J. Clin. 67(6), 472–492 (2017).Crossref, Medline, Google Scholar
 SEER. National Cancer Institute (2017).Google Scholar
 Morton DL, Thompson JF, Cochran AJ et al. Final trial report of sentinel-node biopsy versus nodal observation in melanoma. N. Engl. J. Med. 370(7), 599–609 (2014).
 Vetto JT, Hsueh EC, Gastman BR, Dillon LD, Monzon FA, Cook RW, Keller J, Huang X, Fleming A, Hewgley P, Gerami P, Leachman S, Wayne JD, Berger AC, Fleming MD. Guidance of sentinel lymph node biopsy decisions in patients with T1-T2 melanoma using gene expression profiling. Future Oncol. 2019 Apr;15(11):1207-1217. doi: 10.2217/fon-2018-0912. Epub 2019 Jan 29. PMID: 30691297.
Featured Image: Doctor consulting with a patient, working on diagnostic examination. Photo courtesy: © 2016 – 2020 Fotolia/Adobe. Used with permission.