Heterogeneity and frequency of BRAF mutations in primary melanoma: Comparison between molecular methods and immunohistochemistry

Bruno, William; Martinuzzi, Claudia; Andreotti, Virginia; Pastorino, Lorenza; Spagnolo, Francesco; Dalmasso, Bruna; Cabiddu, Francesco; Gualco, Marina; Ballestrero, Alberto; Bianchi‐Scarrǎ, Giovanna; Queirolo, Paola; Grillo, Federica; Mastracci, Luca; Ghiorzo, Paola

doi:10.18632/oncotarget.14094

Cited by 36 publications

(32 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, cases that were negative for the BRAFV600E mutation by IHC can be analyzed by deep learning in order to identify false negatives or non-V600E BRAF mutants in patients who would benefit from targeted therapy. As others have advocated using multiple detection methods for challenging samples 41 or to minimize technique-related discordancy 42 , additional rapid and cost-effective mutational screening techniques would be highly valuable. Regarding our NRAS model, additional training with an increased sample size at 40× image magnification can improve overall network performance.…”

Section: Discussionmentioning

confidence: 99%

A Deep Learning Approach for Rapid Mutational Screening in Melanoma

Kim

Nomikou

Coudray³

et al. 2019

Preprint

View full text Add to dashboard Cite

36DNA-based molecular assays for determining mutational status in melanomas are time-37 consuming and costly. As an alternative, we applied a deep convolutional neural network 38 (CNN) to histopathology images of tumors from 257 melanoma patients and developed a 39 fully automated model that first selects for tumor-rich areas (Area under the curve 40 AUC=0.98), and second, predicts for the presence of mutated BRAF or NRAS. Network 41 performance was enhanced on BRAF-mutated melanomas 1.0 mm (AUC=0.83) and on 42 non-ulcerated NRAS-mutated melanomas (AUC=0.92). Applying our models to 43 histological images of primary melanomas from The Cancer Genome Atlas database also 44 demonstrated improved performances on thinner BRAF-mutated melanomas and non-45 ulcerated NRAS-mutated melanomas. We propose that deep learning-based analysis of 46 histological images has the potential to become integrated into clinical decision making 47 for the rapid detection of mutations of interest in melanoma. 48 49 50 Mutations in the BRAF oncogene are found in 50-60% of all melanomas 1 , while NRAS 51 mutations comprise an additional 15-20%. With the development of targeted therapies 2, 52 3 , determining the mutational status of BRAF and NRAS has become an integral 53 component for the management of Stage III/IV melanomas. DNA molecular assays such 54 as Sanger sequencing, pyrosequencing, and next generation sequencing (NGS) are the 55 current gold standard to determine mutational status 4 . However, these methods are costly 56 and time-consuming. Immunohistochemistry, real-time polymerase chain reaction (PCR), 57 and automated platforms 5, 6, 7 are rapid and less expensive alternatives, but are limited to 58 screening for specific mutations, such as BRAF-V600E/K or NRAS-Q61R/L, and may 59 potentially fail to identify rare mutational variants in patients that might have otherwise 60 benefited from adjuvant targeted therapy.61 62 Deep Convolutional Neural Network (CNN) methods to predict mutational status have 63 been demonstrated in other solid tumors. CNNs utilize multiple layers of convolution 64 operations, pooling layers, and fully connected layers to perform classification of images 65 to classes of interest through identification of various image features often not directly 66 detectable by the human eye. Deep CNNs, which utilize non-linear learning algorithms, 67have been successful in manipulating and processing large data sets, particularly for 68 image analysis 8 . Using images from The Cancer Genome Atlas (TCGA), a collaborative 69 cancer genomics database 9 , our group has previously developed a machine learning 70 algorithm that can predict for 6 different genes, including EGFR and STK11, in lung 71 carcinoma 10 . In breast cancer, deep learning applied to tumor microarray images has 72 been shown to predict for ER status with an 84% accuracy 11 . 73 74 In this study, we adapt our previous deep learning algorithm to a different dataset 75 comprised of histopathology images of primary melanomas resected from patients 76 pros...

show abstract

Section: Discussionmentioning

confidence: 99%

A Deep Learning Approach for Rapid Mutational Screening in Melanoma

Kim

Nomikou

Coudray³

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In detail, negative staining was defined as absence of any cytoplasmic labeling either in single interspersed melanoma cells (<10%) or in cells of histiocytic/macrophage lineage; positive staining was classified as homogeneous (staining in >95% of cells) or heterogeneous (staining in <95% of cells) according to the percentage of cytoplasmic staining in melanoma cells, as previous described. 10,28 Intensity of the staining was graded as weak, moderate, or strong. 10…”

Section: Immunohistochemistrymentioning

confidence: 99%

“…9 Although the somatic BRAF and NRAS mutational status is of great interest for melanoma treatment, there is no consensus so far on the best testing method. 10 Besides BRAF and NRAS, recent studies identified recurrent somatic mutations in the promoter region of the telomerase reverse transcriptase (TERT ) gene occurring in early stages of melanoma development. 11,12 The MC1R (melanocortin-1 receptor) gene is a key determinant of human pigmentation and specific germline allelic variants, defined R variants, show the strongest effect on melanoma susceptibility.…”

mentioning

confidence: 99%

Heterogeneity of BRAF, NRAS, and TERT Promoter Mutational Status in Multiple Melanomas and Association with MC1R Genotype

Pellegrini

Nardo

Cipolloni

et al. 2018

The Journal of Molecular Diagnostics

View full text Add to dashboard Cite

Data on somatic heterogeneity and germline-somatic interaction in multiple primary melanoma (MPM) patients are limited. We investigated the mutational status of BRAF, NRAS, and TERT promoter genes in 97 melanomas of 44 MPM patients and compared molecular and immunohistochemical findings. We further evaluated the association of somatic alterations with the germline MC1R genotype. Mutations in BRAF gene were identified in 41.2% (40/97) of melanomas, in NRAS in 2.1% (2/97), and in TERT promoter in 19.6% (19/97). Distribution of BRAF mutations did not differ across multiple melanomas (P = 0.85), whereas TERT promoter changes decreased from first to subsequent melanomas (P = 0.04). Intrapatient discrepancy of BRAF mutations among multiple tumors was detected in 14 of 44 MPM patients (32%) and of BRAF/NRAS/TERT promoter genes in 20 of 44 (45%). We observed a high rate of agreement between allele-specific TaqMan assay and immunohistochemistry in BRAF detection (κ = 0.83, P < 0.01) with 86 of 97 melanomas (88.7%) presenting similar BRAF status. Germline MC1R variants were identified in 81.4% (35/43) of MPM patients with no association of MC1R genotype with somatic mutations or with intrapatient concordance of somatic mutational profile. Our results support the genetic diversity of multiple melanomas and show that somatic heterogeneity is not influenced by inherited MC1R variants. Immunohistochemistry may be useful as an initial screening test.

show abstract

“…Thus far, thousands of mutational events have been observed in the melanoma genome, and the melanoma genome has been revealed to be characterized by high frequencies of mutations carrying a signature of ultraviolet-B radiation [ 4 – 5 ]. BRAF is the gene most frequently mutated (50-70%) in melanoma, and BRAF v600E is the most common mutation, which is usually found in benign nevi [ 6 ]. Despite the advances in gene targeting therapy, the development of inhibitors of mutant BRAF kinase, for example, as therapeutic agents, is stagnant due to resistance to the therapy [ 7 ].…”

Section: Introductionmentioning

confidence: 99%

DNA methylation/hydroxymethylation in melanoma

Zhang

et al. 2017

Oncotarget

View full text Add to dashboard Cite

Melanoma is a malignant tumor of melanocytes and is considered to be the most aggressive cancer among all skin diseases. The pathogenesis of melanoma has not been well documented, which may restrict the research and development of biomarkers and therapies. To date, several genetic and epigenetic factors have been identified as contributing to the development and progression of melanoma. Besides the findings on genetic susceptibilities, the recent progress in epigenetic studies has revealed that loss of the DNA hydroxymethylation mark, 5-hydroxymethylcytosine (5-hmC), along with high levels of DNA methylation at promoter regions of several tumor suppressor genes in melanoma, may serve as biomarkers for melanoma. Moreover, 5-Aza-2′-deoxycytidine, an epigenetic modifier causing DNA demethylation, and ten-eleven translocation family dioxygenase (TET), which catalyzes the generation of 5-hmC, demonstrate therapeutic potential in melanoma treatment. In this review, we will summarize the latest progress in research on DNA methylation/hydroxymethylation in melanoma, and we will discuss and provide insight for epigenetic biomarkers and therapies for melanoma. Particularly, we will discuss the role of DNA hydroxymethylation in melanoma infiltrating immune cells, which may also serve as a potential target for melanoma treatment.

show abstract

Heterogeneity and frequency of BRAF mutations in primary melanoma: Comparison between molecular methods and immunohistochemistry

Cited by 36 publications

References 44 publications

A Deep Learning Approach for Rapid Mutational Screening in Melanoma

A Deep Learning Approach for Rapid Mutational Screening in Melanoma

Heterogeneity of BRAF, NRAS, and TERT Promoter Mutational Status in Multiple Melanomas and Association with MC1R Genotype

DNA methylation/hydroxymethylation in melanoma

Contact Info

Product

Resources

About