The MPATH-Dx reporting schema for melanocytic proliferations and melanoma

Digital quantification of Ki67 and PRAME in challenging melanocytic lesions - A novel diagnostic tool

The interpretation of immunohistochemical markers in melanocytic lesions possesses difficulties due to expression in non-melanocytic cells and the time-consuming, non-reproducible nature of manual assessment. A digital tool that accurately quantifies Ki67 and PRAME may valuably aid pathologists in the diagnostic classification of melanocytic lesions. The aim of this study was to assess the diagnostic performance of digitally quantified Ki67 and PRAME in challenging melanocytic lesions utilizing double nuclear staining methods for accurate identification of melanocytic cells. We explored the difference in Ki67 and PRAME expression by WHO-lesion-groups and Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis version 2.0 (MPATH-Dx V2.0). Tissue slides from a cohort of 156 melanocytic lesions were stained with the Ki67/SOX10 double nuclear stain and the PRAME/SOX10 virtual double nuclear stain. Melanocytic cell specific Ki67/SOX10- and PRAME/SOX10-indexes were quantified by AI-driven digital image analysis (DIA) and compared to non-specific Ki67- and PRAME-indexes. The results showed that ROC AUC of the Ki67/SOX10-index was increased compared to the non-specific Ki67-index (p < 0.001), as opposed to the AUC of the PRAME/SOX10-index compared to non-specific PRAME-index (p = 0.090). The medians of digitally quantified Ki67- and PRAME-indexes differed significantly for the overall WHO-groups and MPATH-Dx V2.0 classes (p < 0.001). In conclusion, we found that double nuclear staining improved the diagnostic performance of Ki67, but not PRAME. The combination of digitally quantified Ki67- and PRAME-indexes may potentially serve as a tool for diagnostic classification of challenging melanocytic lesions. The proposed diagnostic tool presents the results visually, graphically, and quantitatively to optimally aid the pathologist.

Robust ROI Detection in Whole Slide Images Guided by Pathologists' Viewing Patterns

Deep learning techniques offer improvements in computer-aided diagnosis systems. However, acquiring image domain annotations is challenging due to the knowledge and commitment required of expert pathologists. Pathologists often identify regions in whole slide images with diagnostic relevance rather than examining the entire slide, with a positive correlation between the time spent on these critical image regions and diagnostic accuracy. In this paper, a heatmap is generated to represent pathologists' viewing patterns during diagnosis and used to guide a deep learning architecture during training. The proposed system outperforms traditional approaches based on color and texture image characteristics, integrating pathologists' domain expertise to enhance region of interest detection without needing individual case annotations. Evaluating our best model, a U-Net model with a pre-trained ResNet-18 encoder, on a skin biopsy whole slide image dataset for melanoma diagnosis, shows its potential in detecting regions of interest, surpassing conventional methods with an increase of 20%, 11%, 22%, and 12% in precision, recall, F1-score, and Intersection over Union, respectively. In a clinical evaluation, three dermatopathologists agreed on the model's effectiveness in replicating pathologists' diagnostic viewing behavior and accurately identifying critical regions. Finally, our study demonstrates that incorporating heatmaps as supplementary signals can enhance the performance of computer-aided diagnosis systems. Without the availability of eye tracking data, identifying precise focus areas is challenging, but our approach shows promise in assisting pathologists in improving diagnostic accuracy and efficiency, streamlining annotation processes, and aiding the training of new pathologists.

Dysplastic Nevi and Superficial Borderline Atypical Melanocytic Lesions: Description of an Algorithmic Clinico-Pathological Classification

The diagnosis, interpretation, and classification of melanocytic tumors is a very complex topic in the pathology and dermatopathology field that lacks standardization and is still subject to discordance and debate. Here, we review the definitions of dysplastic nevus and superficial atypical melanocytic proliferations and provide an overview of some areas still subject to debate and some attempts of standardization. Furthermore, we describe an algorithmic classification, and provide some examples of clinico-pathological correlation. This step-by-step algorithm has an educational purpose and may automatize the work of dermatopathologists. We hope that through further molecular studies, this fine-grained scheme will prove to be related to the biological behavior of these atypical melanocytic lesions.

International Skin Imaging Collaboration-Designated Diagnoses (ISIC-DX): Consensus terminology for lesion diagnostic labeling

BACKGROUND

A common terminology for diagnosis is critically important for clinical communication, education, research and artificial intelligence. Prevailing lexicons are limited in fully representing skin neoplasms.

OBJECTIVES

To achieve expert consensus on diagnostic terms for skin neoplasms and their hierarchical mapping.

METHODS

Diagnostic terms were extracted from textbooks, publications and extant diagnostic codes. Terms were hierarchically mapped to super-categories (e.g. 'benign') and cellular/tissue-differentiation categories (e.g. 'melanocytic'), and appended with pertinent-modifiers and synonyms. These terms were evaluated using a modified-Delphi consensus approach. Experts from the International-Skin-Imaging-Collaboration (ISIC) were surveyed on agreement with terms and their hierarchical mapping; they could suggest modifying, deleting or adding terms. Consensus threshold was >75% for the initial rounds and >50% for the final round.

RESULTS

Eighteen experts completed all Delphi rounds. Of 379 terms, 356 (94%) reached consensus in round one. Eleven of 226 (5%) benign-category terms, 6/140 (4%) malignant-category terms and 6/13 (46%) indeterminate-category terms did not reach initial agreement. Following three rounds, final consensus consisted of 362 terms mapped to 3 super-categories and 41 cellular/tissue-differentiation categories.

CONCLUSIONS

We have created, agreed upon, and made public a taxonomy for skin neoplasms and their hierarchical mapping. Further study will be needed to evaluate the utility and completeness of the lexicon.

Impact of Clinical Information on Melanocytic Skin Lesion Pathology Diagnosis: A Scoping Review

Importance

There is poor accuracy and reproducibility for the histopathologic diagnosis of melanocytic skin lesions, and the provision of clinical information may improve this.

Objective

To examine the impact of clinical information on the histopathologic diagnosis of melanocytic skin lesions.

Evidence Review

PubMed, Embase, and Cochrane Library were searched for new records published from January 2018 to January 2024. References included in the 2018 Cancer Council Australia evidence review were also screened, and forward and backward citation searches were conducted.

Findings

From 2224 records screened, 162 full-text studies were assessed, and 7 studies were included. Studies included pathologists from Austria, Germany, the US, Italy, the UK, and Australia. Patient populations had a mean age of 43 to 55 years and a proportion of female participants of 23% to 63%. The risk of bias assessment demonstrated that all studies had domains at unclear or high risk of bias. Clinical images increased diagnostic certainty (3 studies) and agreement between pathologists (2 studies) led to diagnostic upgrades in 7.6% to 16.7% of interpretations. Clinical diagnosis on the pathology requisition form reduced the odds of missing a melanoma with progression (1 study), while more clinical elements on the form correlated with higher re-excision rates (1 study). Among patients with distant metastases on long-term follow-up, a prior consensus diagnosis of melanoma was established on histopathology alone.

Conclusions and Relevance

Providing clinical information to pathologists may improve diagnostic confidence and interobserver agreement and result in upgrading of the histopathologic diagnosis. While providing the clinical diagnosis may prevent missing a progressive melanoma, more research is needed to determine the appropriateness of histopathology upgrading when clinical images are provided and the impacts on patient outcomes.

Diagnostic discordance among histopathological reviewers of melanocytic lesions

BACKGROUND

Histopathological examination is adequate for the diagnosis of most cutaneous melanocytic neoplasms. However, there is a subset that is either difficult to definitively diagnose or would have diagnostic disagreement upon review by multiple dermatopathologists if a more exhaustive review was performed.

METHODS

Melanocytic lesions underwent an independent, blinded diagnostic histopathological review of hematoxylin and eosin-stained sections. Each lesion was reviewed by three to six dermatopathologists and categorized as benign, malignant, or unknown malignant potential (UMP). Diagnoses were grouped as concordant (all the same designation); opposing (received benign and malignant designations); majority (single designation with the highest number of diagnoses, no benign/malignant opposing designations); and non-definitive (equal number of non-opposing designations [i.e., benign/UMP or malignant/UMP]). Lesions with equivocal designations (concordant or majority UMP, opposing, majority, and non-definitive) were utilized in a patient treatment model of projected surgical treatment discrepancies.

RESULTS

In total, 3317 cases were reviewed, and 23.8% of lesions received equivocal diagnoses. Of these, 7.3% were majority benign, 4.8% were majority malignant, 2.7% were majority UMP, 0.5% were concordant UMP, 6.9% were opposing, and 1.6% were non-definitive. Patient treatment models of those with equivocal lesions (n = 788) revealed a potential of overall surgical treatment variations ranging from 18% to 72%, with the highest variation amongst lesions with opposing, non-definitive, or majority UMP (40%-72%) diagnoses.

CONCLUSION

Histopathologic review in this large cohort demonstrated substantial diagnostic variation, with 23.8% of cases receiving equivocal diagnoses. We identified diagnostic ambiguity even in lesions where a definitive diagnosis was previously rendered by a single real-world dermatopathologist. The combined clinical impact of diagnostic discordance or a final diagnosis of UMP is highlighted by high diagnosis-dependent treatment variation in the patient treatment model, which could be underreported in a real-world setting, where review by more than one to two dermatopathologists is relatively rare.

Pathologist Characteristics Associated With Rendering Higher-Grade Diagnoses for Melanocytic Lesions

Importance

The incidence of melanoma diagnoses has been increasing in recent decades, and controlled studies have indicated high histopathologic discordance across the intermediate range of melanocytic lesions. The respective causes for these phenomena remain incompletely understood.

Objective

To identify pathologist characteristics associated with tendencies to diagnose melanocytic lesions as higher grade vs lower grade or to diagnose invasive melanoma vs any less severe diagnosis.

Design, Setting, and Participants

This exploratory study used data from 2 nationwide studies (the Melanoma Pathology [M-Path] study, conducted from July 2013 to May 2016, and the Reducing Errors in Melanocytic Interpretations [REMI] study, conducted from August 2018 to March 2021) in which participating pathologists who interpreted melanocytic lesions in their clinical practices interpreted study cases in glass slide format. Each pathologist was randomly assigned to interpret a set of study cases from a repository of skin biopsy samples of melanocytic lesions; each case was independently interpreted by multiple pathologists. Data were analyzed from July 2022 to February 2023.

Main Outcomes and Measures

The association of pathologist characteristics with diagnosis of a study case as higher grade (including severely dysplastic and melanoma in situ) vs lower grade (including mild to moderately dysplastic nevi) and diagnosis of invasive melanoma vs any less severe diagnosis was assessed using logistic regression. Characteristics included demographics (age, gender, and geographic region), years of experience, academic affiliation, caseload of melanocytic lesions in their practice, specialty training, and history of malpractice suits.

Results

A total of 338 pathologists were included: 113 general pathologists and 74 dermatopathologists from M-Path and 151 dermatopathologists from REMI. The predominant factor associated with rendering more severe diagnoses was specialist training in dermatopathology (board certification and/or fellowship training). Pathologists with this training were more likely to render higher-grade diagnoses (odds ratio [OR], 2.63; 95% CI, 2.10-3.30; P < .001) and to diagnose invasive melanoma (OR, 1.95; 95% CI, 1.53-2.49; P < .001) than pathologists without this training interpreting the same case. Nonmitogenic pT1a diagnoses (stage pT1a melanomas with no mitotic activity) accounted for the observed difference in diagnosis of invasive melanoma; when these lesions, which carry a low risk of metastasis, were grouped with the less severe diagnoses, there was no observed association (OR, 0.95; 95% CI, 0.74-1.23; P = .71). Among dermatopathologists, those with a higher caseload of melanocytic lesions in their practice were more likely to assign higher-grade diagnoses (OR for trend, 1.27; 95% CI, 1.04-1.56; P = .02).

Conclusions and Relevance

The findings suggest that specialty training in dermatopathology is associated with a greater tendency to diagnose atypical melanocytic proliferations as pT1a melanomas. These low-risk melanomas constitute a growing proportion of melanomas diagnosed in the US.

Advances in melanoma: epidemiology, diagnosis, and prognosis

Unraveling the multidimensional complexities of melanoma has required concerted efforts by dedicated community of researchers and clinicians battling against this deadly form of skin cancer. Remarkable advances have been made in the realm of epidemiology, classification, diagnosis, and therapy of melanoma. The treatment of advanced melanomas has entered the golden era as targeted personalized therapies have emerged that have significantly altered the mortality rate. A paradigm shift in the approach to melanoma classification, diagnosis, prognosis, and staging is underway, fueled by discoveries of genetic alterations in melanocytic neoplasms. A morphologic clinicopathologic classification of melanoma is expected to be replaced by a more precise molecular based one. As validated, convenient, and cost-effective molecular-based tests emerge, molecular diagnostics will play a greater role in the clinical and histologic diagnosis of melanoma. Artificial intelligence augmented clinical and histologic diagnosis of melanoma is expected to make the process more streamlined and efficient. A more accurate model of prognosis and staging of melanoma is emerging based on molecular understanding melanoma. This contribution summarizes the recent advances in melanoma epidemiology, classification, diagnosis, and prognosis.

Assessment of lipid and pigment content in suspicious melanocytic lesions to improve melanoma detection

Melanoma is a highly aggressive form of skin cancer and the most frequent lethal malignancy diagnosed by dermatologists. Although there have been advances for predicting melanoma prognosis, there are few highly sensitive and specific diagnostic tools for clinically evaluating suspicious melanocytic lesions prior to biopsy. We have recently determined that alterations in cellular lipid and pigment content are associated with tumor progression and melanoma metastasis. Here, we seek to determine if lipid droplet and pigment content assessments near the skin's surface are able to distinguish benign from malignant melanocytic lesions. We obtained 14 benign melanocytic lesions, classified as Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MPATH-Dx) class 1, and 22 malignant melanomas, classified as MPATH-Dx class 4 or 5, from Boston Medical Center. The malignant melanomas had an average greatest thickness of 1.8 ± 2.1 mm with 7/22 biopsies showing the presence of ulceration. Tissues were stained with the Fontana Masson stain to detect pigment or immunohistochemically stained for adipophilin, the main protein component of lipid droplets, to detect lipid droplets. Pigment and lipid droplets were quantified using ImageJ and CellProfiler, respectively. We found no significant difference in total pigment area between benign melanocytic lesions and malignant melanoma, and a 66% decrease in lipid content and 68% reduction in lipid/pigment content between benign melanocytic lesions and malignant melanoma ( P  < 0.05). Our results suggest that lipid content and lipid/pigment content ratios may distinguish benign and malignant melanocytic lesions, which may be useful as a diagnostic tool for histopathologically challenging pigmented lesions.

Differences in nomenclature usage and preference among dermatopathologists for "dysplastic" nevi: A national survey

BACKGROUND

Ongoing controversy exists regarding terminology used to describe atypical melanocytic nevi. Efforts to standardize nomenclature, including the 1992 NIH consensus conference, have been largely unsuccessful. Significant advances have revealed an increasingly detailed genetic picture of melanocytic neoplasms, including strong evidence for the existence of those with "intermediate" behavior.

METHODS

We sent an electronic survey to dermatopathologists (n = 846) to assess trends in nomenclature usage and attitudes toward developing new consensus nomenclature for atypical melanocytic nevi.

RESULTS

There were 229 complete responses (27.1% response rate). The most used/preferred nomenclature was "dysplastic nevus" (43%/39%, respectively), followed by the NIH-recommended terminology (28%/26%). Three-tier grading systems were most heavily used/preferred (79%/63%). Dermatopathologists based in New England were most likely to use the NIH terminology; on the other hand, "dysplastic nevus" or "other" were most used elsewhere (p = 0.029). Most (76%) expressed at least "moderate" enthusiasm for developing consensus nomenclature, with 47% "very" or "extremely" enthusiastic.

CONCLUSION

Little has changed with the wide variation in terminology for atypical melanocytic nevi. There continues to be no one dominant terminology in use. However, there is enthusiasm for standardization. A new attempt at updated consensus nomenclature may be fruitful.

Diagnostic error, uncertainty, and overdiagnosis in melanoma

Diagnostic error can be defined as deviation from a gold standard diagnosis, typically defined in terms of expert opinion, although sometimes in terms of unexpected events that might occur in follow-up (such as progression and death from disease). Although diagnostic error does exist for melanoma, deviations from gold standard diagnosis, certainly among appropriately trained and experienced practitioners, are likely to be the result of uncertainty and lack of specific criteria, and differences of opinion, rather than lack of diagnostic skills. In this review, the concept of diagnostic error will be considered in relation to diagnostic uncertainty, and the concept of overdiagnosis in melanoma will be presented and discussed.

Are Pathologists Self-Aware of Their Diagnostic Accuracy? Metacognition and the Diagnostic Process in Pathology

BACKGROUND

Metacognition is a cognitive process that involves self-awareness of thinking, understanding, and performance. This study assesses pathologists' metacognition by examining the association between their diagnostic accuracy and self-reported confidence levels while interpreting skin and breast biopsies.

DESIGN

We studied 187 pathologists from the Melanoma Pathology Study (M-Path) and 115 pathologists from the Breast Pathology Study (B-Path). We measured pathologists' metacognitive ability by examining the area under the curve (AUC), the area under each pathologist's receiver operating characteristic (ROC) curve summarizing the association between confidence and diagnostic accuracy. We investigated possible relationships between this AUC measure, referred to as metacognitive sensitivity, and pathologist attributes. We also assessed whether higher metacognitive sensitivity affected the association between diagnostic accuracy and a secondary diagnostic action such as requesting a second opinion.

RESULTS

We found no significant associations between pathologist clinical attributes and metacognitive AUC. However, we found that pathologists with higher AUC showed a stronger trend to request secondary diagnostic action for inaccurate diagnoses and not for accurate diagnoses compared with pathologists with lower AUC.

LIMITATIONS

Pathologists reported confidence in specific diagnostic terms, rather than the broader classes into which the diagnostic terms were later grouped to determine accuracy. In addition, while there is no gold standard for the correct diagnosis to determine the accuracy of pathologists' interpretations, our studies achieved a high-quality reference diagnosis by using the consensus diagnosis of 3 experienced pathologists.

CONCLUSIONS

Metacognition can affect clinical decisions. If pathologists have self-awareness that their diagnosis may be inaccurate, they can request additional tests or second opinions, providing the opportunity to correct inaccurate diagnoses.

HIGHLIGHTS

Metacognitive sensitivity varied across pathologists, with most showing higher sensitivity than expected by chance.None of the demographic or clinical characteristics we examined was significantly associated with metacognitive sensitivity.Pathologists with higher metacognitive sensitivity were more likely to request additional tests or second opinions for their inaccurate diagnoses.

Revision of the Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis Classification Schema for Melanocytic Lesions: A Consensus Statement

IMPORTANCE

A standardized pathology classification system for melanocytic lesions is needed to aid both pathologists and clinicians in cataloging currently existing diverse terminologies and in the diagnosis and treatment of patients. The Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MPATH-Dx) has been developed for this purpose.

OBJECTIVE

To revise the MPATH-Dx version 1.0 classification tool, using feedback from dermatopathologists participating in the National Institutes of Health-funded Reducing Errors in Melanocytic Interpretations (REMI) Study and from members of the International Melanoma Pathology Study Group (IMPSG).

EVIDENCE REVIEW

Practicing dermatopathologists recruited from 40 US states participated in the 2-year REMI study and provided feedback on the MPATH-Dx version 1.0 tool. Independently, member dermatopathologists participating in an IMPSG workshop dedicated to the MPATH-Dx schema provided additional input for refining the MPATH-Dx tool. A reference panel of 3 dermatopathologists, the original authors of the MPATH-Dx version 1.0 tool, integrated all feedback into an updated and refined MPATH-Dx version 2.0.

FINDINGS

The new MPATH-Dx version 2.0 schema simplifies the original 5-class hierarchy into 4 classes to improve diagnostic concordance and to provide more explicit guidance in the treatment of patients. This new version also has clearly defined histopathological criteria for classification of classes I and II lesions; has specific provisions for the most frequently encountered low-cumulative sun damage pathway of melanoma progression, as well as other, less common World Health Organization pathways to melanoma; provides guidance for classifying intermediate class II tumors vs melanoma; and recognizes a subset of pT1a melanomas with very low risk and possible eventual reclassification as neoplasms lacking criteria for melanoma.

CONCLUSIONS AND RELEVANCE

The implementation of the newly revised MPATH-Dx version 2.0 schema into clinical practice is anticipated to provide a robust tool and adjunct for standardized diagnostic reporting of melanocytic lesions and management of patients to the benefit of both health care practitioners and patients.

VSGD-Net: Virtual Staining Guided Melanocyte Detection on Histopathological Images

Detection of melanocytes serves as a critical prerequisite in assessing melanocytic growth patterns when diagnosing melanoma and its precursor lesions on skin biopsy specimens. However, this detection is challenging due to the visual similarity of melanocytes to other cells in routine Hematoxylin and Eosin (H&E) stained images, leading to the failure of current nuclei detection methods. Stains such as Sox10 can mark melanocytes, but they require an additional step and expense and thus are not regularly used in clinical practice. To address these limitations, we introduce VSGD-Net, a novel detection network that learns melanocyte identification through virtual staining from H&E to Sox10. The method takes only routine H&E images during inference, resulting in a promising approach to support pathologists in the diagnosis of melanoma. To the best of our knowledge, this is the first study that investigates the detection problem using image synthesis features between two distinct pathology stainings. Extensive experimental results show that our proposed model outperforms state-of-the-art nuclei detection methods for melanocyte detection. The source code and pre-trained model are available at: https://github.com/kechunl/VSGD-Net.

Dysplastic nevus part I: Historical perspective, classification, and epidemiology

Since the late 1970s, the diagnosis and management of dysplastic nevi have been areas fraught with controversy in the fields of dermatology and dermatopathology. Diagnostic uncertainty and lack of standardized nomenclature continue to propagate confusion among clinicians, dermatopathologists, and patients. In part I of this CME review article, we summarize the historical context that gave rise to the debate surrounding dysplastic nevi and review key features for diagnosis, classification, and management, as well as epidemiology. We discuss essentials of clinical criteria, dermoscopic features, histopathologic features, and the diagnostic utility of total body photography and reflectance confocal microscopy in evaluating dysplastic nevi, with emphasis on information available since the last comprehensive review a decade ago.

Deep Learning for Skin Melanocytic Tumors in Whole-Slide Images: A Systematic Review

The rise of Artificial Intelligence (AI) has shown promising performance as a support tool in clinical pathology workflows. In addition to the well-known interobserver variability between dermatopathologists, melanomas present a significant challenge in their histological interpretation. This study aims to analyze all previously published studies on whole-slide images of melanocytic tumors that rely on deep learning techniques for automatic image analysis. Embase, Pubmed, Web of Science, and Virtual Health Library were used to search for relevant studies for the systematic review, in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Articles from 2015 to July 2022 were included, with an emphasis placed on the used artificial intelligence methods. Twenty-eight studies that fulfilled the inclusion criteria were grouped into four groups based on their clinical objectives, including pathologists versus deep learning models (n = 10), diagnostic prediction (n = 7); prognosis (n = 5), and histological features (n = 6). These were then analyzed to draw conclusions on the general parameters and conditions of AI in pathology, as well as the necessary factors for better performance in real scenarios.

[Deep learning-based fully automated intelligent and precise diagnosis for melanocytic lesions]

Melanocytic lesions occur on the surface of the skin, in which the malignant type is melanoma with a high fatality rate, seriously endangering human health. The histopathological analysis is the gold standard for diagnosis of melanocytic lesions. In this study, a fully automated intelligent diagnosis method based on deep learning was proposed to classify the pathological whole slide images (WSI) of melanocytic lesions. Firstly, the color normalization based on CycleGAN neural network was performed on multi-center pathological WSI; Secondly, ResNet-152 neural network-based deep convolutional network prediction model was built using 745 WSI; Then, a decision fusion model was cascaded, which calculates the average prediction probability of each WSI; Finally, the diagnostic performance of the proposed method was verified by internal and external test sets containing 182 and 54 WSI, respectively. Experimental results showed that the overall diagnostic accuracy of the proposed method reached 94.12% in the internal test set and exceeded 90% in the external test set. Furthermore, the color normalization method adopted was superior to the traditional color statistics-based and staining separation-based methods in terms of structure preservation and artifact suppression. The results demonstrate that the proposed method can achieve high precision and strong robustness in pathological WSI classification of melanocytic lesions, which has the potential in promoting the clinical application of computer-aided pathological diagnosis.

Segmenting Skin Biopsy Images with Coarse and Sparse Annotations using U-Net

The number of melanoma diagnoses has increased dramatically over the past three decades, outpacing almost all other cancers. Nearly 1 in 4 skin biopsies is of melanocytic lesions, highlighting the clinical and public health importance of correct diagnosis. Deep learning image analysis methods may improve and complement current diagnostic and prognostic capabilities. The histologic evaluation of melanocytic lesions, including melanoma and its precursors, involves determining whether the melanocytic population involves the epidermis, dermis, or both. Semantic segmentation of clinically important structures in skin biopsies is a crucial step towards an accurate diagnosis. While training a segmentation model requires ground-truth labels, annotation of large images is a labor-intensive task. This issue becomes especially pronounced in a medical image dataset in which expert annotation is the gold standard. In this paper, we propose a two-stage segmentation pipeline using coarse and sparse annotations on a small region of the whole slide image as the training set. Segmentation results on whole slide images show promising performance for the proposed pipeline.

Histopathological diagnosis of cutaneous melanocytic lesions: blinded and nonblinded second opinions offer similar improvement in diagnostic accuracy

BACKGROUND

Previous studies of second opinions in the diagnosis of melanocytic skin lesions have examined blinded second opinions, which do not reflect usual clinical practice. The current study, conducted in the USA, investigated both blinded and nonblinded second opinions for their impact on diagnostic accuracy.

METHODS

In total, 100 melanocytic skin biopsy cases, ranging from benign to invasive melanoma, were interpreted by 74 dermatopathologists. Subsequently, 151 dermatopathologists performed nonblinded second and third reviews. We compared the accuracy of single reviewers, second opinions obtained from independent, blinded reviewers and second opinions obtained from sequential, nonblinded reviewers. Accuracy was defined with respect to a consensus reference diagnosis.

RESULTS

The mean case-level diagnostic accuracy of single reviewers was 65.3% (95% CI 63.4-67.2%). Second opinions arising from sequential, nonblinded reviewers significantly improved accuracy to 69.9% (95% CI 68.0-71.7%; P < 0.001). Similarly, second opinions arising from blinded reviewers improved upon the accuracy of single reviewers (69.2%; 95% CI 68.0-71.7%). Nonblinded reviewers were more likely than blinded reviewers to give diagnoses in the same diagnostic classes as the first diagnosis. Nonblinded reviewers tended to be more confident when they agreed with previous reviewers, even with inaccurate diagnoses.

CONCLUSION

We found that both blinded and nonblinded second reviewers offered a similar modest improvement in diagnostic accuracy compared with single reviewers. Obtaining second opinions with knowledge of previous reviews tends to generate agreement among reviews, and may generate unwarranted confidence in an inaccurate diagnosis. Combining aspects of both blinded and nonblinded review in practice may leverage the advantages while mitigating the disadvantages of each approach. Specifically, a second pathologist could give an initial diagnosis blinded to the results of the first pathologist, with subsequent nonblinded discussion between the two pathologists if their diagnoses differ.

Effect of Prior Diagnoses on Dermatopathologists' Interpretations of Melanocytic Lesions: A Randomized Controlled Trial

Importance

Medical second opinions are common, although little is known about the best processes for obtaining them. This study assesses whether knowledge of a prior physician's diagnosis influences consulting physicians' diagnoses.

Objective

To measure the extent to which dermatopathologists' diagnoses are influenced by prior diagnostic information from another dermatopathologist.

Design, Setting, and Participants

Dermatopathologists were randomly assigned to interpret 1 slide set of 18 melanocytic skin biopsy specimens in 2 phases (5 slide sets totaling 90 cases). Phase 1 interpretations were conducted without prior diagnostic information. After a washout period of 12 or more months, dermatopathologists' phase 2 interpretations were conducted with their identical slide set; for a random subset of cases in phase 2, participants were shown prior diagnoses by other dermatopathologists that were either more or less severe than their own phase 1 diagnosis of the case. Using the Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis tool, cases ranged from class I (benign) to class V (≥pT1b invasive melanoma). Data collection took place from August 2018 to March 2021, and data analysis was performed from March to December 2021.

Intervention

Prior diagnoses were actual diagnoses from board-certified and/or fellowship-trained dermatopathologists. A prior diagnosis was always in a more severe or less severe diagnostic class than the participant's phase 1 interpretation; more or less severe was determined by the randomization scheme. In the control condition of no prior diagnostic information, the participants were told that a prior diagnosis was not available.

Main Outcomes and Measures

When exposure was to a prior diagnosis in a higher diagnostic class, the primary study outcome was whether a participant's diagnosis in phase 2 was in a higher diagnostic class than the participant's diagnosis in phase 1. When exposure was to a prior diagnosis in a lower diagnostic class, the primary study outcome was whether a participant's diagnosis in phase 2 was in a lower diagnostic class than the participant's diagnosis in phase 1. The effect of prior diagnostic information was measured using the relative risk (RR) of each outcome relative to the control condition of no prior diagnostic information, adjusted for the diagnostic class of the phase 1 diagnosis. Prior to data collection, it was hypothesized that participants would be swayed in the direction of prior diagnostic information.

Results

A total of 149 dermatopathologists (median [range] age, 47 years [34-76] years; 101 [68%] were male) provided 5322 interpretations of study cases. Participants were more likely to increase the severity of their diagnosis when the prior diagnosis was of greater severity compared with when no prior diagnosis was provided (RR, 1.52; 95% CI, 1.34-1.73); likewise, participants gave less severe diagnoses when prior diagnoses were of lesser severity (RR, 1.38; 95% CI, 1.19-1.59). Trends were similar among dermatopathologists who had previously stated they were "not at all influenced" by prior diagnoses. Prior diagnoses also swayed dermatopathologists away from correct diagnoses.

Conclusions and Relevance

In this randomized controlled trial, despite the preference of most dermatopathologists to receive prior diagnoses when providing second opinions, this information swayed them away from a correct diagnosis to an incorrect diagnosis.

Improving the Diagnosis of Skin Biopsies Using Tissue Segmentation

Invasive melanoma, a common type of skin cancer, is considered one of the deadliest. Pathologists routinely evaluate melanocytic lesions to determine the amount of atypia, and if the lesion represents an invasive melanoma, its stage. However, due to the complicated nature of these assessments, inter- and intra-observer variability among pathologists in their interpretation are very common. Machine-learning techniques have shown impressive and robust performance on various tasks including healthcare. In this work, we study the potential of including semantic segmentation of clinically important tissue structure in improving the diagnosis of skin biopsy images. Our experimental results show a 6% improvement in F-score when using whole slide images along with epidermal nests and cancerous dermal nest segmentation masks compared to using whole-slide images alone in training and testing the diagnosis pipeline.

Dermatopathologist Perceptions of Overdiagnosis of Melanocytic Skin Lesions and Association With Diagnostic Behaviors

Importance

Despite evidence of overdiagnosis of in situ and invasive melanoma, neither the perceptions of practicing dermatopathologists about overdiagnosis nor possible associations between perceptions of overdiagnosis and diagnostic practices have been studied.

Objective

To examine practicing US dermatopathologists' perceptions of melanoma overdiagnosis as a public health issue, and to associate diagnostic behaviors of dermatopathologists with perceptions of melanoma overdiagnosis.

Design, Setting, and Participants

This survey study included 115 board-certified and/or fellowship-trained dermatopathologists and their diagnostic interpretations on a set of 18 skin biopsy cases (5 slide sets comprising 90 melanocytic skin lesions). Participants interpreted cases remotely using their own microscopes. Survey invitations occurred during 2018 to 2019, with data collection completed 2021. Data analysis was performed from June to September 2021.

Main Outcomes and Measures

Agreement vs disagreement that overdiagnosis is a public health issue for atypical nevi, melanoma in situ, and invasive melanoma. Associations between perceptions regarding overdiagnosis and interpretive behavior on study cases.

Results

Of 115 dermatopathologists, 68% (95% CI, 59%-76%) agreed that overdiagnosis is a public health issue for atypical nevi; 47% (95% CI, 38%-56%) for melanoma in situ; and 35% (95% CI, 26%-43%) for invasive melanoma. Dermatopathologists with more years in practice were significantly less likely to perceive that atypical nevi are overdiagnosed, eg, 46% of dermatopathologists with 20 or more years of experience agreed that atypical nevi are overdiagnosed compared with 93% of dermatopathologists with 1 to 4 years of experience. Compared with other dermatopathologists, those who agreed that all 3 conditions are overdiagnosed were slightly more likely to diagnose study cases as mild to moderately dysplastic nevi (odds ratio, 1.26; 95% CI, 0.97-1.64; P = .08), but the difference was not statistically significant. Dermatopathologists who agreed that invasive melanoma is overdiagnosed did not significantly differ in diagnosing invasive melanoma for study cases compared with those who disagreed (odds ratio, 1.10; 95% CI, 0.86-1.41; P = .44).

Conclusions and Relevance

In this survey study, about two-thirds of dermatopathologists thought that atypical nevi are overdiagnosed, half thought that melanoma in situ is overdiagnosed, and one-third thought that invasive melanoma is overdiagnosed. No statistically significant associations were found between perceptions about overdiagnosis and interpretive behavior when diagnosing skin biopsy cases.

An analysis of pathologists' viewing processes as they diagnose whole slide digital images

Although pathologists have their own viewing habits while diagnosing, viewing behaviors leading to the most accurate diagnoses are under-investigated. Digital whole slide imaging has enabled investigators to analyze pathologists' visual interpretation of histopathological features using mouse and viewport tracking techniques. In this study, we provide definitions for basic viewing behavior variables and investigate the association of pathologists' characteristics and viewing behaviors, and how they relate to diagnostic accuracy when interpreting whole slide images. We use recordings of 32 pathologists' actions while interpreting a set of 36 digital whole slide skin biopsy images (5 sets of 36 cases; 180 cases total). These viewport tracking data include the coordinates of a viewport scene on pathologists' screens, the magnification level at which that viewport was viewed, as well as a timestamp. We define a set of variables to quantify pathologists' viewing behaviors such as zooming, panning, and interacting with a consensus reference panel's selected region of interest (ROI). We examine the association of these viewing behaviors with pathologists' demographics, clinical characteristics, and diagnostic accuracy using cross-classified multilevel models. Viewing behaviors differ based on clinical experience of the pathologists. Pathologists with a higher caseload of melanocytic skin biopsy cases and pathologists with board certification and/or fellowship training in dermatopathology have lower average zoom and lower variance of zoom levels. Viewing behaviors associated with higher diagnostic accuracy include higher average and variance of zoom levels, a lower magnification percentage (a measure of consecutive zooming behavior), higher total interpretation time, and higher amount of time spent viewing ROIs. Scanning behavior, which refers to panning with a fixed zoom level, has marginally significant positive association with accuracy. Pathologists' training, clinical experience, and their exposure to a range of cases are associated with their viewing behaviors, which may contribute to their diagnostic accuracy. Research in computational pathology integrating digital imaging and clinical informatics opens up new avenues for leveraging viewing behaviors in medical education and training, potentially improving patient care and the effectiveness of clinical workflow.

Correlation of FISH and PRAME Immunohistochemistry in Ambiguous Superficial Cutaneous Melanocytic Proliferations

ABSTRACT

Preferentially expressed antigen in melanoma (PRAME) is a tumor-associated repressor of retinoic acid signaling which is expressed in melanoma and has emerged as a potential biomarker for malignant behavior in melanocytic neoplasms. Although ancillary molecular techniques such as fluorescence in situ hybridization (FISH) are established techniques in the diagnosis of problematic cutaneous melanocytic proliferations, they are expensive, time-consuming, and require appropriate infrastructure, which places them out of reach of some laboratories. The advent of readily available commercial antibodies to PRAME has the potential to provide a more accessible alternative. The aim of this study was to determine whether immunohistochemistry for PRAME could serve as a surrogate for FISH analysis in a subgroup of challenging superficial melanocytic proliferations. Cases which had previously been submitted for FISH analysis were stained for PRAME and interpreted by a panel of at least 3 dermatopathologists is a blinded fashion. Of a study set of 55 cases, 42 (76%) showed a pattern of PRAME immunostaining which was concordant with the cytogenetic interpretation, with an unweighted kappa of 0.42 (representing mild-to-moderate agreement). Thus, although there was a correlation between positive immunohistochemistry for PRAME and abnormal findings on FISH analysis, in our view, the concordance was not sufficient to enable PRAME immunohistochemistry to act as a surrogate for FISH testing. Our findings reiterate the principle that interpretation of problematic superficial melanocytic proliferations requires a synthesis of all the available data, including clinical scenario, morphological features, immunohistochemistry, and ancillary molecular investigations.

Rate of Immunohistochemistry Utilization in the Diagnosis of Cutaneous Melanocytic Lesions

ABSTRACT

Melanocytic lesions represent a large portion of the workload in many laboratories. Although many melanocytic nevi can be confidently diagnosed based on routine hematoxylin and eosin light microscopy, ancillary testing is often warranted. Various immunohistochemical (IHC) stains are routinely used in the diagnosis of melanocytic lesions. Because melanocytic lesions are frequently encountered in skin specimens, the use of IHC is likely to represent a significant area of resource utilization in dermatopathology laboratories. Our study investigates the rate of IHC utilization in the diagnosis of melanocytic lesions in a high-volume, government-funded, not-for-profit laboratory. Of the 1230 cases of melanocytic lesions investigated, including benign as well as malignant entities, 300 cases involved the utilization of IHC. IHC was used in a larger percentage of melanomas than nevi and in a larger percentage of melanoma in situ cases than invasive melanomas. SOX10 was overwhelmingly the most frequently used IHC.

Assessment of a Diagnostic Classification System for Management of Lesions to Exclude Melanoma

Importance

The proposed MOLEM (Management of Lesion to Exclude Melanoma) schema is more clinically relevant than Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MATH-Dx) for the management classification of melanocytic and nonmelanocytic lesions excised to exclude melanoma. A more standardized way of establishing diagnostic criteria will be crucial in the training of artificial intelligence (AI) algorithms.

Objective

To examine pathologists' variability, reliability, and confidence in reporting melanocytic and nonmelanocytic lesions excised to exclude melanoma using the MOLEM schema in a population of higher-risk patients.

Design, Setting, and Participants

This cohort study enrolled higher-risk patients referred to a primary care skin clinic in New South Wales, Australia, between April 2019 and December 2019. Baseline demographic characteristics including age, sex, and related clinical details (eg, history of melanoma) were collected. Patients with lesions suspicious for melanoma assessed by a primary care physician underwent clinical evaluation, dermoscopy imaging, and subsequent excision biopsy of the suspected lesion(s). A total of 217 lesions removed and prepared by conventional histologic method and stained with hematoxylin-eosin were reviewed by up to 9 independent pathologists for diagnosis using the MOLEM reporting schema. Pathologists evaluating for MOLEM schema were masked to the original histopathologic diagnosis.

Main Outcomes and Measures

Characteristics of the lesions were described and the concordance of cases per MOLEM class was assessed. Interrater agreement and the agreement between pathologists' ratings and the majority MOLEM diagnosis were calculated by Gwet AC1 with quadratic weighting applied. The diagnostic confidence of pathologists was then assessed.

Results

A total of 197 patients were included in the study (102 [51.8%] male; 95 [48.2%] female); mean (SD) age was 64.2 (15.8) years (range, 24-93 years). Overall, 217 index lesions were assessed with a total of 1516 histological diagnoses. Of 1516 diagnoses, 677 (44.7%) were classified as MOLEM class I; 120 (7.9%) as MOLEM class II; 564 (37.2%) as MOLEM class III; 114 (7.5%) as MOLEM class IV; and 55 (3.6%) as MOLEM class V. Concordance rates per MOLEM class were 88.6% (class I), 50.8% (class II), 76.2% (class III), 77.2% (class IV), and 74.2% (class V). The quadratic weighted interrater agreement was 91.3%, with a Gwet AC1 coefficient of 0.76 (95% CI, 0.72-0.81). The quadratic weighted agreement between pathologists' ratings and majority MOLEM was 94.7%, with a Gwet AC1 coefficient of 0.86 (95% CI, 0.84-0.88). The confidence in diagnosis data showed a relatively high level of confidence (between 1.0 and 1.5) when diagnosing classes I (mean [SD], 1.3 [0.3]), IV (1.3 [0.3]) and V (1.1 [0.1]); while classes II (1.8 [0.2]) and III (1.5 [0.4]) were diagnosed with a lower level of pathologist confidence (≥1.5). The quadratic weighted interrater confidence rating agreement was 95.2%, with a Gwet AC1 coefficient of 0.92 (95% CI, 0.90-0.94) for the 1314 confidence ratings collected. The confidence agreement for each MOLEM class was 95.0% (class I), 93.5% (class II), 95.3% (class III), 96.5% (class IV), and 97.5% (class V).

Conclusions and Relevance

The proposed MOLEM schema better reflects clinical practice than the MPATH-Dx schema in lesions excised to exclude melanoma by combining diagnoses with similar prognostic outcomes for melanocytic and nonmelanocytic lesions into standardized classification categories. Pathologists' level of confidence appeared to follow the MOLEM schema diagnostic concordance trend, ie, atypical naevi and melanoma in situ diagnoses were the least agreed upon and the most challenging for pathologists to confidently diagnose.

Relevance of BRAF Subcellular Localization and Its Interaction with KRAS and KIT Mutations in Skin Melanoma

Although skin melanoma (SKM) represents only one-quarter of newly diagnosed skin malignant tumors, it presents a high mortality rate. Hence, new prognostic and therapeutic tools need to be developed. This study focused on investigating the prognostic value of the subcellular expression of BRAF, KRAS, and KIT in SKM in correlation with their gene-encoding interactions. In silico analysis of the abovementioned gene interactions, along with their mRNA expression, was conducted, and the results were validated at the protein level using immunohistochemical (IHC) stains. For IHC expression, the encoded protein expressions were checked on 96 consecutive SKMs and 30 nevi. The UALCAN database showed no prognostic value for the mRNA expression level of KRAS and BRAF and demonstrated a longer survival for patients with low mRNA expression of KIT in SKMs. IHC examinations of SKMs confirmed the UALCAN data and showed that KIT expression was inversely correlated with ulceration, Breslow index, mitotic rate, and pT stage. KRAS expression was also found to be inversely correlated with ulceration and perineural invasion. When the subcellular expression of BRAF protein was recorded (nuclear vs. cytoplasmatic vs. mixed nucleus + cytoplasm), a direct correlation was emphasized between nuclear positivity and lymphovascular or perineural invasion. The independent prognostic value was demonstrated for mixed expression of the BRAF protein in SKM. BRAF cytoplasmic predominance, in association with KIT's IHC positivity, was more frequently observed in early-stage nonulcerated SKMs, which displayed a low mitotic rate and a late death event. The present study firstly verified the possible prognostic value of BRAF subcellular localization in SKMs. A low mRNA expression or IHC cytoplasmic positivity for KIT and BRAF might be used as a positive prognostic parameter of SKM. SKM's BRAF nuclear positivity needs to be evaluated in further studies as a possible indicator of perineural and lymphovascular invasion.

Characterization of multiple diagnostic terms in melanocytic skin lesion pathology reports

BACKGROUND

Histopathologically ambiguous melanocytic lesions lead some pathologists to list multiple diagnostic considerations in the pathology report. The frequency and circumstance of multiple diagnostic considerations remain poorly characterized.

METHODS

Two hundred and forty skin biopsy samples were interpreted by 187 pathologists (8976 independent diagnoses) and classified according to a diagnostic/treatment stratification (MPATH-Dx).

RESULTS

Multiple diagnoses in different MPATH-Dx classes were used in n = 1320 (14.7%) interpretations, with 97% of pathologists and 91% of cases having at least one such interpretation. Multiple diagnoses were more common for intermediate risk lesions and are associated with greater subjective difficulty and lower confidence. We estimate that 6% of pathology reports for melanocytic lesions in the United States contain two diagnoses of different MPATH-Dx prognostic classes, and 2% of cases are given two diagnoses with significant treatment implications.

CONCLUSIONS

Difficult melanocytic diagnoses in skin may necessitate multiple diagnostic considerations; however, as patients increasingly access their health records and retrieve pathology reports (as mandated by US law), uncertainty should be expressed unambiguously.

Association of Second-Opinion Strategies in the Histopathologic Diagnosis of Cutaneous Melanocytic Lesions With Diagnostic Accuracy and Population-Level Costs

IMPORTANCE

Diagnostic variation among pathologists interpreting cutaneous melanocytic lesions could lead to suboptimal care.

OBJECTIVE

To estimate the potential association of second-opinion strategies in the histopathologic diagnosis of cutaneous melanocytic lesions with diagnostic accuracy and 1-year population-level costs in the US.

DESIGN, SETTING, AND PARTICIPANTS

Decision analysis with 1-year time horizon including melanocytic lesion diagnoses available from US pathologists participating in the Melanoma Pathology Study (M-Path) and from the study panel of reference pathologists who classified cases using the MPATH-Dx classification tool. M-Path data collection occurred from July 2013 through March 2015; analyses for the present study were performed between April 2015 and January 2021.

EXPOSURES

Various second-opinion strategies for interpretation of melanocytic cutaneous lesions.

MAIN OUTCOMES AND MEASURES

Estimated accuracy of pathologists' diagnoses, defined as concordance with the reference panel diagnoses, and 1-year postbiopsy medical costs under various second-opinion strategies. Expected percentage of concordant diagnoses, including percentages of overinterpretation and underinterpretation, and 1-year costs of medical care per 100 000 in the US population.

RESULTS

Decision-analytic model parameters were based on diagnostic interpretations for 240 cases by 187 pathologists compared with reference panel diagnoses. Without second opinions, 83.2% of diagnoses in the US were estimated to be accurate-ie, concordant with the reference diagnosis; with overinterpretation (8.0%) or underinterpretation (8.8%), and 16 850 misclassified diagnoses per 100 000 biopsies. Accuracy increased under all second-opinion strategies. Accuracy (87.4% concordance with 3.6% overinterpretation and 9.1% underinterpretation) and cost (an increase of more than $10 million per 100 000 biopsies per year) were highest when second opinions were universal (eg, performed on all biopsies), relative to no second opinions. A selective second-opinion strategy based on pathologists' desire or institutional requirements for a second opinion was most accurate (86.5% concordance; 4.4% overinterpretation; 9.1% underinterpretation) and would reduce costs by more than $1.9 million per 100 000 skin biopsies relative to no second opinions. Improvements in diagnostic accuracy with all second-opinion strategies were associated with reductions in overinterpretation but not underinterpretation.

CONCLUSIONS AND RELEVANCE

In this decision-analytic model, selective second-opinion strategies for interpretation of melanocytic skin lesions showed the potential to improve diagnostic accuracy and decrease costs relative to no second opinions or universal second opinions.

The WHO 2018 Classification of Cutaneous Melanocytic Neoplasms: Suggestions From Routine Practice

The "multidimensional" World Health Organization (WHO) classification 2018 of melanocytic tumors encompasses nine melanoma pathways (seven of which for cutaneous melanoma) according to a progression model in which morphologically intermediate melanocytic tumors are cosidered as simulators and/or precursors to melanoma. These "intermediates" can be subclassified into: i) a "classical" subgroup (superficial/thin compound: dysplastic nevus), which is placed within the morphologic and molecular progression spectrum of classical (Clark's and McGovern's) melanoma subtypes (superficial spreading and, possibly, nodular); and ii) a "non-classical" subgroup (thick compound/dermal: "melanocytomas") whose genetic pathways diverge from classical melanoma subtypes. Such a progression model is aimed at giving a conceptual framework for a histopathological classification; however, routine clinicopathological practice strongly suggests that most melanomas arise de novo and that the vast majority of nevi are clinically stable or even involuting over time. Clinicopathological correlation can help identify some severely atypical but benign tumors (e.g.: sclerosing nevus with pseudomelanomatous features) as well as some deceptively bland melanomas (e.g.: lentiginous melanoma; nested melanoma), thereby addressing some ambiguous cases to a correct clinical management. The recently available adjuvant therapy regimens for melanoma raise the problem of a careful distinction between severely atypical (high grade) melanocytoma and "classical" melanoma: conventional morphology can guide an algorithmic approach based on an antibody panel (anti-mutated BRAF, BAP1, PRAME, ALK, TRKA, MET, HRAS-WT, ROS; beta catenin; R1alpha; p16; HMB45; Ki67), a first-line molecular study (identification of hot spot mutations of BRAF and NRAS) and an advanced molecular study (sequencing of NF1, KIT, BRAF, MAP2K1, GNAQ, GNA11, PLCB4, CYSLTR2, HRAS; fusions studies of BRAF, RET, MAP3K8, PRKCA); as a final step, next-generation sequencing can identify melanocytic tumors with rare genetic signatures and melanocytic tumors with a high tumor mutation burden which should be definitely ascribed to the category of classical melanoma with the respective therapeutic options.

Translation of a circulating miRNA signature of melanoma into a solid tissue assay to improve diagnostic accuracy and precision

Aim: Successful treatment of cutaneous melanoma depends on early and accurate diagnosis of clinically suspicious melanocytic skin lesions. Multiple international studies have described the challenge of providing accurate and reproducible histopathological assessments of melanocytic lesions, highlighting the need for new diagnostic tools including disease-specific biomarkers. Previously, a 38-miRNA signature (MEL38) was identified in melanoma patient plasma and validated as a novel biomarker. In this study, MEL38 expression in solid tissue biopsies representing the benign nevi to metastatic melanoma spectrum is examined. Patients & methods: Nanostring digital gene expression assessment of the MEL38 signature was performed on 308 formalin-fixed paraffin-embedded biopsies of nevi, melanoma in situ and invasive melanoma. Genomic data were interrogated using hierarchical clustering, univariate and multivariate statistical approaches. Classification scores computed from the MEL38 signature were analyzed for their association with demographic data and histopathology results, including MPATH-DX class, AJCC disease stage and tissue subtype. Results: The MEL38 score can stratify higher-risk melanomas (MPATH-Dx class V or more advanced) from lower-risk skin lesions (class I-IV) with an area under the curve of 0.97 (p < 0.001). The genomic score ranges from 0 to 10 and is positively correlated with melanoma progression, with an intraclass correlation coefficient of 0.85 with stage 0-IV disease. Using an optimized classification threshold of ≥2.7 accurately identifies higher-risk melanomas with 89% sensitivity and 94% specificity. Multivariate analysis showed the score to be a significant predictor of malignancy, independent of technical and clinical covariates. Application of the MEL38 signature to Spitz nevi reveals an intrasubtype profile, with elements in common to both nevi and melanoma. Conclusion: Melanoma-specific circulating miRNAs maintain their association with malignancy when measured in the hypothesized tissue of origin. The MEL38 signature is an accurate and reproducible metric of melanoma status, based on changes in miRNA expression that occur as the disease develops and spreads. Inclusion of the MEL38 score into routine practice would provide physicians with previously unavailable, personalized genomic information about their patient's skin lesions. Combining molecular biomarker data with conventional histopathology data may improve diagnostic accuracy, healthcare resource utilization and patient outcomes.

Diagnostic assessment of deep learning for melanocytic lesions using whole-slide pathological images

•

The performance of the deep learning algorithm was on par with that of 7 expert pathologists in discriminating melanoma from nevus using whole-slide pathological images (WSIs).

•

Deep learning algorithm might function as a supplemental tool to assist pathologist by automatically pre-screening and highlighting interest regions prior to review.

Background

Deep learning has the potential to improve diagnostic accuracy and efficiency in medical image recognition. In the current study, we developed a deep learning algorithm and assessed its performance in discriminating melanoma from nevus using whole-slide pathological images (WSIs).

Methods

The deep learning algorithm was trained and validated using a set of 781 WSIs (86 melanomas, 695 nevi) from PLA General Hospital. The diagnostic performance of the algorithm was tested on an independent test set of 104 WSIs (29 melanomas, 75 nevi) from Tianjin Chang Zheng Hospital. The same test set was also diagnostically classified by 7 expert dermatopathologists.

Results

The deep learning algorithm receiver operating characteristic (ROC) curve achieved a sensitivity 100% at the specificity of 94.7% in the classification of melanoma and nevus on the test set. The area under ROC curve was 0.99. Dermatopathologists achieved a mean sensitivity and specificity of 95.1% (95% confidence interval [CI]: 92.0%-98.2%) and 96.0% (95% CI: 94.2%-97.8%), respectively. At the operating point of sensitivity of 95.1%, the algorithm revealed a comparable specificity with 7 dermatopathologists (97.3% vs. 96.0%, P = 0.11). At the operating point of specificity of 96.0%, the algorithm also achieved a comparable sensitivity with 7 dermatopathologists (96.5% vs. 95.1%, P = 0.30). A more transparent and interpretable diagnosis could be generated by highlighting the regions of interest recognized by the algorithm in WSIs.

Conclusion

The performance of the deep learning algorithm was on par with that of 7 expert dermatopathologists in interpreting WSIs with melanocytic lesions. By pre-screening the suspicious melanoma regions, it might serve as a supplemental diagnostic tool to improve working efficiency of pathologists.

Melanoma in the Blink of an Eye: Pathologists' Rapid Detection, Classification, and Localization of Skin Abnormalities

Expert radiologists can quickly extract a basic "gist" understanding of a medical image following less than a second exposure, leading to above-chance diagnostic classification of images. Most of this work has focused on radiology tasks (such as screening mammography), and it is currently unclear whether this pattern of results and the nature of visual expertise underlying this ability are applicable to pathology, another medical imaging domain demanding visual diagnostic interpretation. To further characterize the detection, localization, and diagnosis of medical images, this study examined eye movements and diagnostic decision-making when pathologists were briefly exposed to digital whole slide images of melanocytic skin biopsies. Twelve resident (N = 5), fellow (N = 5), and attending pathologists (N = 2) with experience interpreting dermatopathology briefly viewed 48 cases presented for 500 ms each, and we tracked their eye movements towards histological abnormalities, their ability to classify images as containing or not containing invasive melanoma, and their ability to localize critical image regions. Results demonstrated rapid shifts of the eyes towards critical abnormalities during image viewing, high diagnostic sensitivity and specificity, and a surprisingly accurate ability to localize critical diagnostic image regions. Furthermore, when pathologists fixated critical regions with their eyes, they were subsequently much more likely to successfully localize that region on an outline of the image. Results are discussed relative to models of medical image interpretation and innovative methods for monitoring and assessing expertise development during medical education and training.

Histopathologic synoptic reporting of invasive melanoma: How reliable are the data?

BACKGROUND

Synoptic reporting is recommended by many guideline committees to encourage the thorough histologic documentation necessary for optimal management of patients with melanoma.

METHODS

One hundred fifty-one pathologists from 40 US states interpreted 41 invasive melanoma cases. For each synoptic reporting factor, the authors identified cases with "complete agreement" (all participants recorded the same value) versus any disagreement. Pairwise agreement was calculated for each case as the proportion of pairs of responses that agreed, where paired responses were generated by the comparison of each reviewer's response with all others.

RESULTS

There was complete agreement among all reviewers for 22 of the 41 cases (54%) on Breslow thickness dichotomized at 0.8 mm, with pairwise agreement ranging from 49% to 100% across the 41 cases. There was complete agreement for "no ulceration" in 24 of the 41 cases (59%), with pairwise agreement ranging from 42% to 100%. Tumor transected at base had complete agreement for 26 of the 41 cases (63%), with pairwise agreement ranging from 31% to 100%. Mitotic rate, categorized as 0/mm² , 1/mm² , or 2/mm² , had complete agreement for 17 of the 41 cases (41%), with pairwise agreement ranging from 36% to 100%. Regression saw complete agreement for 14 of 41 cases (34%), with pairwise agreement ranging from 40% to 100%. Lymphovascular invasion, perineural invasion, and microscopic satellites were rarely reported as present. Respectively, these prognostic factors had complete agreement for 32 (78%), 37 (90%), and 18 (44%) of the 41 cases, and the ranges of pairwise agreement were 47% to 100%, 70% to 100%, and 53% to 100%, respectively.

CONCLUSIONS

These findings alert pathologists and clinicians to the problem of interobserver variability in recording critical prognostic factors.

LAY SUMMARY

This study addresses variability in the assessment and reporting of critical characteristics of invasive melanomas that are used by clinicians to guide patient care. The authors characterize the diagnostic variability among pathologists and their reporting methods in light of recently updated national guidelines. Results demonstrate considerable variability in the diagnostic reporting of melanoma with regard to the following: Breslow thickness, mitotic rate, ulceration, regression, and microscopic satellites. This work serves to alert pathologists and clinicians to the existence of variability in reporting these prognostic factors.

Molecular Biomarkers for Melanoma Screening, Diagnosis and Prognosis: Current State and Future Prospects

Despite significant progress in the development of treatment options, melanoma remains a leading cause of death due to skin cancer. Advances in our understanding of the genetic, transcriptomic, and morphologic spectrum of benign and malignant melanocytic neoplasia have enabled the field to propose biomarkers with potential diagnostic, prognostic, and predictive value. While these proposed biomarkers have the potential to improve clinical decision making at multiple critical intervention points, most remain unvalidated. Clinical validation of even the most commonly assessed biomarkers will require substantial resources, including limited clinical specimens. It is therefore important to consider the properties that constitute a relevant and clinically-useful biomarker-based test prior to engaging in large validation studies. In this review article we adapt an established framework for determining minimally-useful biomarker test characteristics, and apply this framework to a discussion of currently used and proposed biomarkers designed to aid melanoma detection, staging, prognosis, and choice of treatment.

Estimating the potential impact of interventions to reduce over-calling and under-calling of melanoma

BACKGROUND

Pathologists sometimes disagree over the histopathologic diagnosis of melanoma. 'Over-calling' and 'under-calling' of melanoma may harm individuals and healthcare systems.

OBJECTIVES

To estimate the extent of 'over-calling' and 'under-calling' of melanoma for a population undergoing one excision per person and to model the impact of potential solutions.

METHODS

In this epidemiological modelling study, we undertook simulations using published data on the prevalence and diagnostic accuracy of melanocytic histopathology in the U.S.

POPULATION

We simulated results for 10 000 patients each undergoing excision of one melanocytic lesion, interpreted by one community pathologist. We repeated the simulation using a hypothetical intervention that improves diagnostic agreement between community pathologist and a specialist dermatopathologist. We then evaluated four scenarios for how melanocytic lesions judged to be neither clearly benign (post-test probability of melanoma < 5%), nor clearly malignant (post-test probability of melanoma > 90%) might be handled, before sending for expert dermatopathologist review to decide the final diagnosis. These were (1) no intervention before expert review, (2) formal second community pathologist review, (3) intervention to increase diagnostic agreement and (4) both the intervention and formal second community pathologist review. The main outcomes were the probability of 'over-calling' and 'under-calling' melanoma, and number of lesions requiring expert referral for each scenario.

RESULTS

For 10 000 individuals undergoing excision of one melanocytic lesion, interpreted by a community pathologist, a hypothetical intervention to improve histopathology agreement reduced the number of benign lesions 'over-called' as melanoma from 308 to 164 and the number of melanomas 'under-called' from 289 to 240. If all uncertain diagnoses were sent for expert review, the number of referrals would decrease from 1500 to 737 cases if formal second community pathologist review was used, and to 701 cases if the hypothetical intervention was additionally used.

CONCLUSIONS

Interventions to improve histopathology agreement may reduce melanoma 'over-calling' and 'under-calling'.

A standardized approach to classifying melanocytic neoplasms? Comments on the MPATH-Dx system

The potential benefits and limitations of the MPATH-Dx classification system for melanocytic neoplasms are presented and discussed.

A patient-centric dataset of images and metadata for identifying melanomas using clinical context

Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.

Machine learning techniques for mitoses classification

BACKGROUND

Pathologists analyze biopsy material at both the cellular and structural level to determine diagnosis and cancer stage. Mitotic figures are surrogate biomarkers of cellular proliferation that can provide prognostic information; thus, their precise detection is an important factor for clinical care. Convolutional Neural Networks (CNNs) have shown remarkable performance on several recognition tasks. Utilizing CNNs for mitosis classification may aid pathologists to improve the detection accuracy.

METHODS

We studied two state-of-the-art CNN-based models, ESPNet and DenseNet, for mitosis classification on six whole slide images of skin biopsies and compared their quantitative performance in terms of sensitivity, specificity, and F-score. We used raw RGB images of mitosis and non-mitosis samples with their corresponding labels as training input. In order to compare with other work, we studied the performance of these classifiers and two other architectures, ResNet and ShuffleNet, on the publicly available MITOS breast biopsy dataset and compared the performance of all four in terms of precision, recall, and F-score (which are standard for this data set), architecture, training time and inference time.

RESULTS

The ESPNet and DenseNet results on our primary melanoma dataset had a sensitivity of 0.976 and 0.968, and a specificity of 0.987 and 0.995, respectively, with F-scores of .968 and .976, respectively. On the MITOS dataset, ESPNet and DenseNet showed a sensitivity of 0.866 and 0.916, and a specificity of 0.973 and 0.980, respectively. The MITOS results using DenseNet had a precision of 0.939, recall of 0.916, and F-score of 0.927. The best published result on MITOS (Saha et al. 2018) reported precision of 0.92, recall of 0.88, and F-score of 0.90. In our architecture comparisons on MITOS, we found that DenseNet beats the others in terms of F-Score (DenseNet 0.927, ESPNet 0.890, ResNet 0.865, ShuffleNet 0.847) and especially Recall (DenseNet 0.916, ESPNet 0.866, ResNet 0.807, ShuffleNet 0.753), while ResNet and ESPNet have much faster inference times (ResNet 6 s, ESPNet 8 s, DenseNet 31 s). ResNet is faster than ESPNet, but ESPNet has a higher F-Score and Recall than ResNet, making it a good compromise solution.

CONCLUSION

We studied several state-of-the-art CNNs for detecting mitotic figures in whole slide biopsy images. We evaluated two CNNs on a melanoma cancer dataset and then compared four CNNs on a public breast cancer data set, using the same methodology on both. Our methodology and architecture for mitosis finding in both melanoma and breast cancer whole slide images has been thoroughly tested and is likely to be useful for finding mitoses in any whole slide biopsy images.

Scale-Aware Transformers for Diagnosing Melanocytic Lesions

Diagnosing melanocytic lesions is one of the most challenging areas of pathology with extensive intra- and inter-observer variability. The gold standard for a diagnosis of invasive melanoma is the examination of histopathological whole slide skin biopsy images by an experienced dermatopathologist. Digitized whole slide images offer novel opportunities for computer programs to improve the diagnostic performance of pathologists. In order to automatically classify such images, representations that reflect the content and context of the input images are needed. In this paper, we introduce a novel self-attention-based network to learn representations from digital whole slide images of melanocytic skin lesions at multiple scales. Our model softly weighs representations from multiple scales, allowing it to discriminate between diagnosis-relevant and -irrelevant information automatically. Our experiments show that our method outperforms five other state-of-the-art whole slide image classification methods by a significant margin. Our method also achieves comparable performance to 187 practicing U.S. pathologists who interpreted the same cases in an independent study. To facilitate relevant research, full training and inference code is made publicly available at https://github.com/meredith-wenjunwu/ScATNet.

Terminology for melanocytic skin lesions and the MPATH-Dx classification schema: A survey of dermatopathologists

BACKGROUND

Diagnostic terms used in histopathology reports of cutaneous melanocytic lesions are not standardized. We describe dermatopathologists' views regarding diverse diagnostic terminology and the utility of the Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MPATH-Dx) for categorizing melanocytic lesions.

METHODS

July 2018-2019 survey of board-certified and/or fellowship-trained dermatopathologists with experience interpreting melanocytic lesions.

RESULTS

Among 160 participants, 99% reported witnessing different terminology being used for the same melanocytic lesion. Most viewed diverse terminology as confusing to primary care physicians (98%), frustrating to pathologists (83%), requiring more of their time as a consultant (64%), and providing necessary clinical information (52%). Most perceived that adoption of the MPATH-Dx would: improve communication with other pathologists and treating physicians (87%), generally be a change for the better (80%), improve patient care (79%), be acceptable to clinical colleagues (68%), save time in pathology report documentation (53%), and protect from malpractice (51%).

CONCLUSIONS

Most dermatopathologists view diverse terminology as contributing to miscommunication with clinicians and patients, adversely impacting patient care. They view the MPATH-Dx as a promising tool to standardize terminology and improve communication. The MPATH-Dx may be a useful supplement to conventional pathology reports. Further revision and refinement are necessary for widespread clinical use.

Dermatopathologists' Experience With and Perceptions of Patient Online Access to Pathologic Test Result Reports

Importance

Many patients presently have access to their pathologic test result reports via online patient portals, yet little is known about pathologists' perspective on this topic.

Objective

To examine dermatopathologists' experience and perceptions of patient online access to pathology reports.

Design, Setting, and Participants

A survey of 160 dermatopathologists currently practicing in the United States who are board certified and/or fellowship trained in dermatopathology was conducted between July 15, 2018, and September 23, 2019. Those who reported interpreting skin biopsies of melanocytic lesions within the previous year and expected to continue interpreting them for the next 2 years were included.

Main Outcomes and Measures

Dermatopathologists' demographic and clinical characteristics, experiences with patient online access to pathologic test result reports, potential behaviors and reactions to patient online access to those reports, and effects on patients who read their pathologic test result reports online.

Results

Of the 160 participating dermatopathologists from the 226 eligible for participation (71% response rate), 107 were men (67%); mean (SD) age was 49 (9.7) years (range, 34-77 years). Ninety-one participants (57%) reported that patients have contacted them directly about pathologic test reports they had written. Some participants noted that they would decrease their use of abbreviations and/or specialized terminology (57 [36%]), change the way they describe lesions suspicious for cancer (29 [18%]), and need specialized training in communicating with patients (39 [24%]) if patients were reading their reports. Most respondents perceived that patient understanding would increase (97 [61%]) and the quality of patient-physician communication would increase (98 [61%]) owing to the availability of online reports. Slightly higher proportions perceived increased patient worry (114 [71%]) and confusion (116 [73%]). However, on balance, most participants (114 [71%]) agreed that making pathologic test result reports available to patients online is a good idea.

Conclusions and Relevance

Dermatopathologists in this survey study perceived both positive and negative consequences of patient online access to pathologic test result reports written by the respondents. Most participants believe that making pathologic test result reports available to patients online is a good idea; however, they also report concerns about patient worry and confusion increasing as a result. Further research regarding best practices and the effect on both patients and clinicians is warranted.

The Emperor's New Clothes: A Critique of the Current WHO Classification of Malignant Melanoma

The World Health Organization's classification of skin tumors of 2018 presents melanoma as a loose assembly of independent biologic entities, each of which is characterized by a distinctive constellation of clinical, histopathologic, and molecular findings that evolve through different pathways of lesional progression from a benign to an intermediate and, ultimately, malignant tumor. The alleged pathways, however, are based on vague correlations and fail to take into account the common occurrence of lesions that cannot be assigned to either of them. Moreover, there is no such thing as a lesional progression. The evolvement of neoplasms is always a clonal and, therefore, initially focal event. In the majority of melanomas, there is no evidence of a juxtaposition of a benign, intermediate, and malignant portion. Occasionally, a melanoma may develop within the confines of a melanocytic nevus, but a nevus cannot transform into melanoma. The concept of lesional progression merely serves to handle problems of differential diagnosis because it obscures and, in fact, denies the difference between benign and malignant neoplasms. In the current classification of the World Health Organization, every lesion is said to bear some risk of malignant progression, intermediate categories are recognized for all alleged pathways, and no distinction is made between "high-grade dysplasia" and melanoma in situ. Differentiation between benign and malignant neoplasms of melanocytes may be difficult, but the concept of lesional progression does not address those problems; it merely offers evasions under the disguise of diagnoses.

Factors associated with use of immunohistochemical markers in the histopathological diagnosis of cutaneous melanocytic lesions

BACKGROUND

Melanocytic tumors are often challenging and constitute almost one in four skin biopsies. Immunohistochemical (IHC) studies may assist diagnosis; however, indications for their use are not standardized.

METHODS

A test set of 240 skin biopsies of melanocytic tumors was examined by 187 pathologists from 10 US states, interpreting 48 cases in Phase I and either 36 or 48 cases in Phase II. Participant and diagnosis characteristics were compared between those who reported they would have ordered, or who would have not ordered IHC on individual cases. Intraobserver analysis examined consistency in the intent to order when pathologists interpreted the same cases on two occasions.

RESULTS

Of 187 participants interpreting 48 cases each, 21 (11%) did not request IHC tests for any case, 85 (45%) requested testing for 1 to 6 cases, and 81 (43%) requested testing for ≥6 cases. Of 240 cases, 229 had at least one participant requesting testing. Only 2 out of 240 cases had more than 50% of participants requesting testing. Increased utilization of testing was associated with younger age of pathologist, board-certification in dermatopathology, low confidence in diagnosis, and lesions in intermediate MPATH-Dx classes 2 to 4. The median intraobserver concordance for requesting tests among 72 participants interpreting the same 48 cases in Phases I and II was 81% (IQR 73%-90%) and the median Kappa statistic was 0.20 (IQR 0.00, 0.39).

CONCLUSION

Substantial variability exists among pathologists in utilizing IHC.