Genetic and morphologic features for melanoma classification.
Ontology highlight
ABSTRACT:
SUBMITTER: Broekaert SM
PROVIDER: S-EPMC3107973 | biostudies-literature | 2010 Dec
REPOSITORIES: biostudies-literature
Publications
Genetic and morphologic features for melanoma classification.
Broekaert Sigrid M C SM Roy Ritu R Okamoto Ichiro I van den Oord Joost J Bauer Jürgen J Garbe Claus C Barnhill Raymond L RL Busam Klaus J KJ Cochran Alistair J AJ Cook Martin G MG Elder David E DE McCarthy Stanley W SW Mihm Martin C MC Schadendorf Dirk D Scolyer Richard A RA Spatz Alan A Bastian Boris C BC
Pigment cell & melanoma research 20101201 6
Melanoma is comprised of biologically distinct subtypes. The defining clinical, histomorphologic, and molecular features are not fully established. This study sought to validate the association between genetic and histomorphologic features previously described and to determine their reproducibility and association with important clinical variables. Detailed clinical and histomorphologic features of 365 primary cutaneous melanomas were assessed by 11 pathologists and correlated with mutation stat ...[more]
Similar Datasets
Project description:BackgroundIn melanoma, morphology-based classification systems have not been able to provide relevant information for selecting treatments for patients whose tumors have metastasized. The recent identification of causative genetic alterations has revealed mutations in signaling pathways that offer targets for therapy. Identifying morphologic surrogates that can identify patients whose tumors express such alterations (or functionally equivalent alterations) would be clinically useful for therapy stratification and for retrospective analysis of clinical trial data.Methodology/principal findingsWe defined and assessed a panel of histomorphologic measures and correlated them with the mutation status of the oncogenes BRAF and NRAS in a cohort of 302 archival tissues of primary cutaneous melanomas from an academic comprehensive cancer center. Melanomas with BRAF mutations showed distinct morphological features such as increased upward migration and nest formation of intraepidermal melanocytes, thickening of the involved epidermis, and sharper demarcation to the surrounding skin; and they had larger, rounder, and more pigmented tumor cells (all p-values below 0.0001). By contrast, melanomas with NRAS mutations could not be distinguished based on these morphological features. Using simple combinations of features, BRAF mutation status could be predicted with up to 90.8% accuracy in the entire cohort as well as within the categories of the current World Health Organization (WHO) classification. Among the variables routinely recorded in cancer registries, we identified age < 55 y as the single most predictive factor of BRAF mutation in our cohort. Using age < 55 y as a surrogate for BRAF mutation in an independent cohort of 4,785 patients of the Southern German Tumor Registry, we found a significant survival benefit (p < 0.0001) for patients who, based on their age, were predicted to have BRAF mutant melanomas in 69% of the cases. This group also showed a different pattern of metastasis, more frequently involving regional lymph nodes, compared to the patients predicted to have no BRAF mutation and who more frequently displayed satellite, in-transit metastasis, and visceral metastasis (p < 0.0001).ConclusionsRefined morphological classification of primary melanomas can be used to improve existing melanoma classifications by forming subgroups that are genetically more homogeneous and likely to differ in important clinical variables such as outcome and pattern of metastasis. We expect this information to improve classification and facilitate stratification for therapy as well as retrospective analysis of existing trial data.
| S-EPMC2408611 | biostudies-literature
Project description:Despite the similar histologic appearances of high-grade serous ovarian cancers (HGSOCs), clinical observations point to marked differences in their gross appearances. Some patients have numerous small nodules, whereas others have bulkier disease; some patients have widespread disease, whereas others have more localized disease. However, a systematic framework for classifying such gross morphologic differences does not exist. The implementation of a laparoscopic triage algorithm for patients with advanced HGSOC enabled us to prospectively obtain detailed video images of HGSOC that could be analyzed to identify morphologic subtypes. In this study, we aimed to develop and characterize a gross morphologic classification system for HGSOC. Specifically, we assessed whether HGSOC can be reliably divided into distinct gross morphologic subtypes and whether such subtypes have different clinical outcomes and molecular features.
2023-01-27 | PXD031518 | Pride
Project description:Bacterial vaginosis (BV) is caused by the excessive and imbalanced growth of bacteria in vagina, affecting 30 to 50% of women. Gram staining followed by Nugent scoring based on bacterial morphotypes under the microscope is considered the gold standard for BV diagnosis; this method is often labor-intensive and time-consuming, and results vary from person to person. We developed and optimized a convolutional neural network (CNN) model and evaluated its ability to automatically identify and classify three categories of Nugent scores from microscope images. The CNN model was first established with a panel of microscopic images with Nugent scores determined by experts. The model was trained by minimizing the cross-entropy loss function and optimized by using a momentum optimizer. The separate test sets of images collected from three hospitals were evaluated by the CNN model. The CNN model consisted of 25 convolutional layers, 2 pooling layers, and a fully connected layer. The model obtained 82.4% sensitivity and 96.6% specificity with the 5,815 validation images when altered vaginal flora and BV were considered the positive samples, which was better than the rates achieved by top-level technologists and obstetricians in China. The capability of our model for generalization was so strong that it exhibited 75.1% accuracy in three categories of Nugent scores on the independent test set of 1,082 images, which was 6.6% higher than the average of three technologists, who are hold bachelor's degrees in medicine and are qualified to make diagnostic decisions. When three technologists ran one specimen in triplicate, the precision of three categories of Nugent scores was 54.0%. One hundred three samples diagnosed by two technologists on different days showed a repeatability of 90.3%. The CNN model outperformed human health care practitioners in terms of accuracy and stability for three categories of Nugent score diagnosis. The deep learning model may offer translational applications in automating diagnosis of bacterial vaginosis with proper supporting hardware.
| S-EPMC8111127 | biostudies-literature
Project description:BackgroundFor over 150 years, pathologists have relied on histomorphology to classify and diagnose neoplasms. Their success has been stunning, permitting the accurate diagnosis of thousands of different types of neoplasms using only a microscope and a trained eye. In the past two decades, cancer genomics has challenged the supremacy of histomorphology by identifying genetic alterations shared by morphologically diverse tumors and by finding genetic features that distinguish subgroups of morphologically homogeneous tumors.DiscussionThe Developmental Lineage Classification and Taxonomy of Neoplasms groups neoplasms by their embryologic origin. The putative value of this classification is based on the expectation that tumors of a common developmental lineage will share common metabolic pathways and common responses to drugs that target these pathways. The purpose of this manuscript is to show that grouping tumors according to their developmental lineage can reconcile certain fundamental discrepancies resulting from morphologic and molecular approaches to neoplasm classification. In this study, six issues in tumor classification are described that exemplify the growing rift between morphologic and molecular approaches to tumor classification: 1) the morphologic separation between epithelial and non-epithelial tumors; 2) the grouping of tumors based on shared cellular functions; 3) the distinction between germ cell tumors and pluripotent tumors of non-germ cell origin; 4) the distinction between tumors that have lost their differentiation and tumors that arise from uncommitted stem cells; 5) the molecular properties shared by morphologically disparate tumors that have a common developmental lineage, and 6) the problem of re-classifying morphologically identical but clinically distinct subsets of tumors. The discussion of these issues in the context of describing different methods of tumor classification is intended to underscore the clinical value of a robust tumor classification.SummaryA classification of neoplasms should guide the rational design and selection of a new generation of cancer medications targeted to metabolic pathways. Without a scientifically sound neoplasm classification, biological measurements on individual tumor samples cannot be generalized to class-related tumors, and constitutive properties common to a class of tumors cannot be distinguished from uninformative data in complex and chaotic biological systems. This paper discusses the importance of biological classification and examines several different approaches to the specific problem of tumor classification.
| S-EPMC1208861 | biostudies-literature
Project description:ImportanceDespite similar histologic appearance among high-grade serous ovarian cancers (HGSOCs), clinical observations suggest vast differences in gross appearance. There is currently no systematic framework by which to classify HGSOCs according to their gross morphologic characteristics.ObjectiveTo develop and characterize a gross morphologic classification system for HGSOC.Design, setting, and participantsThis cohort study included patients with suspected advanced-stage ovarian cancer who presented between April 1, 2013, and August 5, 2016, to the University of Texas MD Anderson Cancer Center, a large referral center. Patients underwent laparoscopic assessment of disease burden before treatment and received a histopathologic diagnosis of HGSOC. Researchers assigning morphologic subtype and performing molecular analyses were blinded to clinical outcomes. Data analysis was performed between April 2020 and November 2021.ExposuresGross tumor morphologic characteristics.Main outcomes and measuresClinical outcomes and multiomic profiles of representative tumor samples of type I or type II morphologic subtypes were compared.ResultsOf 112 women (mean [SD] age 62.7 [9.7] years) included in the study, most patients (84% [94]) exhibited a predominant morphologic subtype and many (63% [71]) had a uniform morphologic subtype at all involved sites. Compared with those with uniform type I morphologic subtype, patients with uniform type II morphologic subtype were more likely to have a favorable Fagotti score (83% [19 of 23] vs 46% [22 of 48]; P = .004) and thus to be triaged to primary tumor reductive surgery. Similarly, patients with uniform type II morphologic subtype also had significantly higher mean (SD) estimated blood loss (639 [559; 95% CI, 391-887] mL vs 415 [527; 95% CI, 253-577] mL; P = .006) and longer mean (SD) operative time (408 [130; 95% CI, 350-466] minutes vs 333 [113; 95% CI, 298-367] minutes; P = .03) during tumor reductive surgery. Type I tumors had enrichment of epithelial-mesenchymal transition (false discovery rate [FDR] q-value, 3.10 × 10-24), hypoxia (FDR q-value, 1.52 × 10-5), and angiogenesis pathways (FDR q-value, 2.11 × 10-2), whereas type II tumors had enrichment of pathways related to MYC signaling (FDR q-value, 2.04 × 10-9) and cell cycle progression (FDR q-value, 1.10 × 10-5) by integrated proteomic and transcriptomic analysis. Abundances of metabolites and lipids also differed between the 2 morphologic subtypes.Conclusions and relevanceThis study identified 2 novel, gross morphologic subtypes of HGSOC, each with unique clinical features and molecular signatures. The findings may have implications for triaging patients to surgery or chemotherapy, identifying outcomes, and developing tailored therapeutic strategies.
| S-EPMC9568802 | biostudies-literature
Project description:Progressive renal dysfunction is a major complication of type 1 diabetes. Studying relationships between evolution of diabetic nephropathy lesions and renal functional alterations (structural-functional relationships) helps to better understand the natural history of diabetic nephropathy. The focus of this review is our current understanding of the interplay between morphologic changes of diabetic nephropathy and glomerular filtration rate (GFR) loss. These morphologic changes often may not progress in parallel to each other or to the decline in GFR or increase in albumin excretion rate (AER). Quantitative measures of renal (mainly glomerular) structural changes can predict a substantially larger fraction of AER variability compared with that of GFR, especially using linear correlation analyses. However, nonlinear models better fit the structural-functional relationships across a wide range of GFRs and AERs. Currently, there are insufficient longitudinal data to show which structural changes predict the slope of GFR decline in type 1 diabetic patients. Based on cross-sectional studies, however, such a predictor would be about 10% more robust in patients whose GFR was 45 mL/min/1.73 m(2) or greater if comprised of a composite of glomerular, tubular, and interstitial parameters versus glomerular changes alone. For a slowly progressive disease, such as diabetic nephropathy, in which, especially in the earlier stages, it takes a long time for GFR to decline substantially, such predictors are much needed and, if sufficiently precise, could potentially serve as a surrogate of renal functional decline in clinical trials.
| S-EPMC3622555 | biostudies-literature
Project description:Data transformations prior to analysis may be beneficial in classification tasks. In this article we investigate a set of such transformations on 2D graph-data derived from facial images and their effect on classification accuracy in a high-dimensional setting. These transformations are low-variance in the sense that each involves only a fixed small number of input features. We show that classification accuracy can be improved when penalized regression techniques are employed, as compared to a principal component analysis (PCA) pre-processing step. In our data example classification accuracy improves from 47% to 62% when switching from PCA to penalized regression. A second goal is to visualize the resulting classifiers. We develop importance plots highlighting the influence of coordinates in the original 2D space. Features used for classification are mapped to coordinates in the original images and combined into an importance measure for each pixel. These plots assist in assessing plausibility of classifiers, interpretation of classifiers, and determination of the relative importance of different features.
| S-EPMC4236018 | biostudies-literature
Project description:Studies that have attempted to validate the staging systems and the predictors of survival for patients with primary malignant melanoma of the esophagus (PMME) have been underpowered given their scarcity and small scale. We aimed to review a large number of PMME cases to know more about its clinicopathological features, TNM staging systems, and survival predictors of PMME. Case reports on PMME were extracted from PubMed/Medline through bibliography search and our center. A total of 287 PMME cases were identified. The majority of the patient population was male (72.08%). The most common location of PMME was the lower esophagus (50.62%) and middle esophagus (35.39%). Among the patients, 82.28% received surgical intervention. The median overall survival (OS) duration was 15 months (0.5-244). The American Joint Commission on Cancer staging classification (AJCC) for the mucosal melanoma of the upper aerodigestive tract with stage IVB and IVC integrated in stage IVA showed better distribution of OS than that for esophageal carcinoma. T stage, N stage, and surgery had significant impacts on OS duration in univariate analysis. However, only T stage and N stage were identified as independent factors for OS duration in the multivariate Cox models. PMME is an aggressive tumor with poor prognosis. The AJCC staging system for mucosal melanoma with stage IVB and IVC integrated in stage IVA may be a better option for staging PMME patients. T stage and N stage are independent factors for OS.
| S-EPMC9283823 | biostudies-literature
Project description:Purpose:To investigate the feasibility of pediatric cataract monitoring and morphologic classification using slit lamp-adapted anterior segmental photography in a large cohort that included uncooperative children. Methods:Patients registered in the Childhood Cataract Program of the Chinese Ministry of Health were prospectively selected. Eligible patients underwent slit-lamp adapted anterior segmental photography to record and monitor the morphology of their cataractous lenses. A set of assistance techniques for slit lamp-adapted photography was developed to instruct the parents of uncooperative children how to help maintain the child's head position and keep the eyes open after sleep aid administration. Results:Briefly, slit lamp-adapted photography was completed for all 438 children, including 260 (59.4%) uncooperative children with our assistance techniques. All 746 images of 438 patients successfully confirmed the diagnoses and classifications. Considering the lesion location, pediatric cataract morphologies could be objectively classified into the seven following types: total; nuclear; polar, including two subtypes (anterior and posterior); lamellar; nuclear combined with cortical, including three subtypes (coral-like, dust-like, and blue-dot); cortical; and Y suture. The top three types of unilateral cataracts were polar (55, 42.3%), total (42, 32.3%), and nuclear (23, 17.7%); and the top three types of bilateral cataracts were nuclear (110, 35.8%), total (102, 33.2%), and lamellar (34, 11.1%). Conclusions:Slit lamp-adapted anterior segmental photography is applicable for monitoring and classifying the morphologies of pediatric cataracts and is even safe and feasible for uncooperative children with assistance techniques and sleep aid administration. Translational Relevance:This study proposes a novel strategy for the preoperative evaluation and evidence-based management of pediatric ophthalmology (Clinical Trials.gov, NCT02748031).
| S-EPMC5678553 | biostudies-literature
Project description:Spitz tumors represent a distinct subtype of melanocytic lesions with characteristic histopathologic features, some of which are overlapping with melanoma. More common in the pediatric and younger population, they can be clinically suspected by recognizing specific patterns on dermatoscopic examination, and several subtypes have been described. We now classify these lesions into benign Spitz nevi, intermediate lesions identified as "atypical Spitz tumors" (or Spitz melanocytoma) and malignant Spitz melanoma. More recently a large body of work has uncovered the molecular underpinning of Spitz tumors, including mutations in the HRAS gene and several gene fusions involving several protein kinases. Here we present an overarching view of our current knowledge and understanding of Spitz tumors, detailing clinical, histopathological and molecular features characteristic of these lesions.
| S-EPMC9209745 | biostudies-literature