Delta-Like Protein 3 Expression and Targeting in Merkel Cell Carcinoma.

PURPOSE: Delta-like protein 3 (DLL3) is being developed as a predictive biomarker for DLL3-targeting antibody-drug conjugate and other therapies. Given the neuroendocrine features of Merkel cell carcinoma (MCC), we sought to evaluate DLL3 expression and its role in MCC. EXPERIMENTAL DESIGN: Formalin-fixed and paraffin-embedded MCC cases were consecutively selected. Immunohistochemistry was performed for DLL3 (SC16.65 antibody) and polyomavirus large T-antigen (sc-136172 antibody). Slides were read out for percentage of positive tumor cells. Cox proportional hazards model was applied to assess the association between DLL3 expression and overall survival (OS). A patient with a DLL3-expressing MCC was treated with rovalpituzumab tesirine (Rova-T) in the "other tumor" cohort of NCT02709889 and assessed for response. RESULTS: The median H-score of DLL3 expression of 65 patients included was 60 (interquartile range, 30-100). Fifty-eight cases (89%) had ≥1% tumor cells positive for DLL3 expression with any intensity, of which the median DLL3 expression was 50% (interquartile range, 25%-70%). Thirty-four cases (52%) had ≥50% tumor cells positive for DLL3 expression with any intensity. Higher H-score of DLL3 expression was associated with higher polyomavirus nuclear expression (p = .003) when it was dichotomized to negative versus positive. H-score of DLL3 expression did not predict OS of patients with MCC (p = .4) after being adjusted for common clinicopathological factors. A patient treated with Rova-T for refractory metastatic MCC achieved partial response. CONCLUSIONS: DLL3 overexpression is very common in MCC by immunohistochemistry. The response to treatment suggests that DLL3 expression may have predictive relevance for DLL3-targeting therapies in MCC. IMPLICATIONS FOR PRACTICE: Delta-like protein 3 (DLL3) is being developed as a predictive biomarker to identify patients for treatment with DLL3-targeting agents. Merkel cell carcinoma (MCC) is an aggressive neuroendocrine carcinoma of the skin. It was found that DLL3 overexpression is very common in MCC by immunohistochemistry and significantly associated with Merkel cell polyomavirus expression. Despite the lack of prognostic significance in this cohort, DLL3 expression may have predictive relevance for DLL3-targeting therapies in MCC. The high levels of DLL3 expression in a subset of MCC may potentially be used to select patients to receive DLL3-targeting therapies.

Correlation of novel ALKATI with ALK immunohistochemistry and clinical outcomes in metastatic melanoma.

AIMS: Recently, a novel isoform of anaplastic lymphoma kinase, with alternative transcription initiation (ALKATI ), has been described in melanoma and is susceptible to targeted ALK-inhibitor therapy. Clinical outcomes of patients with ALKATI mutated melanoma as well as correlation with immunohistochemical (IHC) methods have not yet been described. METHODS AND RESULTS: Clinicopathological characteristics were abstracted for 324 patients with metastatic melanoma (MM). IHC, fluorescence in-situ hybridisation and RNA-based digital molecular analysis assays were performed on archival tissue from 173 stage III and 192 stage IV tumours. ALKATI was identified in 12.7 and 4.8% stage III and IV tumours, respectively. Discrete presentations of the ALKATI are seen: isolated ALKATI (n = 20) and mixed ALKATI (combined ALKATI and ALKWT ; n = 7). Isolated ALKWT expression (n = 4) was seen with no ALK fusions. Stage III patients showed improved survival with ALKATI expression compared to those with ALKWT or no expression [5-year survival 80, 95% confidence interval (CI) = 57-100% versus 43%, 95% CI = 34-55%, P = 0.013]. Clinicopathological characteristics were not statistically significant. Strong diffuse cytoplasmic staining of ALK IHC (n = 12) has a sensitivity of 52.2%, specificity 100%, PPV of 100% and NPV of 92.5% of detecting isolated ALKATI . CONCLUSION: Presence of ALKATI is a good prognostic indicator in MM. ALK IHC and digital molecular analysis can be incorporated into MM evaluation to identify patients with ALKATI for targeted therapy.

Clinical significance of SLN benign capsular nevi in patients with melanoma.

BACKGROUND: Benign capsular nevi (BCN) are not infrequent in sentinel lymph nodes (SLN) of patients with melanoma. Their prognostic significance is unknown and the literature is limited. This study evaluated the clinical significance of incidentally found BCN in these patients. METHODS: A multi-institutional retrospective review of patients undergoing SLN biopsy for cutaneous melanoma between 2000 and 2016. Patients were divided into the following groups: (a) negative SLN and no BCN, (b) negative SLN and presence of BCN, (c) positive SLN seen only on immunohistochemistry (IHC), and (d) positive SLN via hematoxylin and eosin (H&E). Outcomes measured were overall survival and any recurrence. RESULTS: A total of 1253 patients were identified (group 1 = 978, group 2 = 56, group 3 = 32, and group 4 = 187). Fifty-seven percent were male and the mean age was 59.3 years. BCN was identified in 77 patients (6.2%), of which the majority was in the node-negative group (72%). Multivariable analysis showed that BCN was associated with lower recurrence rates, though not statistically significant (hazard ratio [HR] = 0.5; P = .06). IHC- and H&E-positive SLNs were associated with a higher risk of recurrence (HR = 2.4; P = .02 and 2.0, P < .0001, respectively). CONCLUSION: Patients with BCN and negative SLN had lower recurrence rates than patients with negative SLN and no BCN. Our data suggest a possible protective effect against recurrence.

Mutational Profile in Vulvar, Vaginal, and Urethral Melanomas: Review of 37 Cases With Focus on Primary Tumor Site.

Melanomas of female genital tract are rare tumors with poor prognosis. While BRAF-V600E is the most common pathogenic mutation seen in cutaneous sun-exposed melanomas, mucosal and anogenital melanomas usually lack BRAF mutations and instead they harbor KIT alterations. The American Joint Committee on Cancer staging guideline (AJCC eighth edition) recommends using cutaneous melanoma guidelines for vulvar melanoma staging and does not provide any recommendations for vaginal melanoma staging. The aim of this study is to investigate the mutational status of invasive melanomas arising from different anatomic sites in lower female genital tract (vulvar hair-bearing skin, glabrous skin, vagina and urethra) in a group of 37 patients. Tumors were analyzed using a DNA targeted next-generation sequencing panel covering the 21 most common genes and mutation hotspots in melanomas. The most common genetic alterations in invasive melanomas of lower female genital tract are KIT (32%), TP53 (22%), and NF1 (19%). Overall 66% (21/32) of cases showed a pathogenic alteration in at least one of the MAPK pathway genes. No statistical significance seen between different primary tumor sites and the frequency of the oncogenic mutations, nor were any significant differences found by mutation status. Only one case of urethral melanoma showed a BRAF non-V600E mutation (D594G). Our results suggest a similar molecular pathogenesis and overall survival in melanomas arising from lower female genital tract, irrespective of their exact location in the urogenital area. Future classifications of melanoma should consider grouping vulvar melanomas with mucosal rather than cutaneous melanomas.

CD206-positive myeloid cells bind galectin-9 and promote a tumor-supportive microenvironment.

In patients with metastatic melanoma, high blood levels of galectin-9 are correlated with worse overall survival and a bias towards a Th2 inflammatory state supportive of tumor growth. Although galectin-9 signaling through TIM3 on T cells has been described, less is known about the interaction of galectin-9 with macrophages. We aimed to determine whether galectin-9 is a binding partner of CD206 on macrophages and whether the result of this interaction is tumor-supportive. It was determined that incubation of CD68+ macrophages with galectin-9 or anti-CD206 blocked target binding and that both CD206 and galectin-9 were detected by immunoprecipitation of cell lysates. CD206 and galectin-9 had a binding affinity of 2.8 × 10-7  m. Galectin-9 causes CD206+ macrophages to make significantly more FGF2 and monocyte chemoattractant protein (MCP-1), but less macrophage-derived chemokine (MDC). Galectin-9 had no effect on classical monocyte subsets, but caused expansion of the non-classical populations. Lastly, there was a positive correlation between increasing numbers of CD206 macrophages and galectin-9 expression in tumors, and high levels of CD206 macrophages correlated negatively with melanoma survival. These results indicate that galectin-9 binds to CD206 on M2 macrophages, which appear to drive angiogenesis and the production of chemokines that support tumor growth and poor patient prognoses. Targeting this interaction systemically through circulating monocytes may therefore be a novel way to improve local anti-tumor effects by macrophages. Copyright © 2018 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

Histological features and outcome of inverted type-A melanocytic nevi.

The presence of enlarged epithelioid/spindled nests located deep in the reticular dermis of a biphasic melanocytic neoplasm can mimic melanoma arising in a pre-existing nevus, causing over-interpretation of malignancy. We aimed to define the clinicopathologic significance of epithelioid/spindled nests in melanocytic nevi. Retrospectively using clinical and histologic information, we characterized 121 patients with a single lesion showing epithelioid/spindled melanocytes in the reticular dermis or subcutaneous fat, surrounded by melanophages, sometimes blending in with the adnexa. The majority of nevi occurred in women in the ages of 10 to 39 years, where the most frequent presentation was a changing mole. While 78% of the lesions displayed an anatomic (Clark's) level of IV-V, there was no ulceration, significant regression or inflammation. Up to 2 mitoses were found in only 12% of the cases, not correlating with the severity of cytological atypia. No recurrence or metastasis occurred during 45.5 months (mean) of clinical follow up in 26 patients. Notwithstanding the deep dermal extension, these findings suggest a benign histopathology and clinical outcome. Having compared the overlapping histopathology and clinical features between deep penetrating/clonal nevus and combined nevus, we posit that "inverted type-A nevus" might be considered a variant of the two.

Acute cutaneous graft-vs.-host disease compared to drug hypersensitivity reaction with vacuolar interface changes: a blinded study of microscopic and immunohistochemical features.

BACKGROUND: Complications from graft-vs.-host disease (GVHD), a major contributor to morbidity and mortality following hematopoietic cell transplantation, may be mitigated by early diagnosis and intervention. However, differentiation between acute cutaneous GVHD and other common skin eruptions that develop in the post-transplantation period, such as drug hypersensitivity reaction, can be challenging clinically and microscopically. Because recent evidence indicates that CD123, a marker of plasmacytoid dendritic cells, can help to distinguish gastrointestinal GVHD from the clinicopathologic mimic cytomegalovirus colitis, we aimed to determine whether CD123 could aid in the diagnosis of acute cutaneous GVHD. METHODS: We studied 12 skin specimens of patients with grades I-II cutaneous GVHD and 12 from patients who had drug hypersensitivity reaction with vacuolar interface changes on biopsy. RESULTS: No differences were seen between the two groups with regards to density or distribution of CD123 expression. Specimens representing GVHD showed significantly less spongiosis (P < 0.001) and fewer dermal eosinophils (P = 0.03) compared to those representing drug hypersensitivity reaction. CONCLUSIONS: We conclude that CD123 does not appear to be a useful ancillary test in the diagnosis of acute cutaneous GVHD. Careful correlation between clinical findings and features with microscopy remains the cornerstone of accurate diagnosis of acute cutaneous GVHD.

Democratizing Artificial Intelligence in Anatomic Pathology.

CONTEXT.­: Artificial intelligence is a transforming technology for anatomic pathology. Involvement within the workforce will foster support for algorithm development and implementation. OBJECTIVE.­: To develop a supportive ecosystem that enables pathologists with variable expertise in artificial intelligence to create algorithms in a development environment with seamless transition to a production environment. RESULTS.­: The development team considered internal development and vended solutions. Because of the extended timeline and resource requirements for internal development, a decision was made to use a vended solution. Vendor proposals were solicited and reviewed by pathologists, IT, and security groups. A vendor was selected and pipelines for development and production were established. Proposals for development were solicited from the pathology department. Eighty-four investigators were selected for the initial cohort, receiving training and access to dedicated subject matter experts. A total of 30 of 31 projects progressed through the model development process of annotating, training, and validation. Based on these projects, 15 abstracts were submitted to national meetings. CONCLUSIONS.­: Democratizing artificial intelligence by creating an ecosystem to support pathologists with varying levels of expertise can break down entry barriers, reduce overall cost of algorithm development, improve algorithm quality, and enhance the speed of adoption.

Neoadjuvant cobimetinib and atezolizumab with or without vemurafenib for high-risk operable Stage III melanoma: the Phase II NeoACTIVATE trial.

Both targeted therapies and immunotherapies provide benefit in resected Stage III melanoma. We hypothesized that the combination of targeted and immunotherapy given prior to therapeutic lymph node dissection (TLND) would be tolerable and drive robust pathologic responses. In NeoACTIVATE (NCT03554083), a Phase II trial, patients with clinically evident resectable Stage III melanoma received either 12 weeks of neoadjuvant vemurafenib, cobimetinib, and atezolizumab (BRAF-mutated, Cohort A, n = 15), or cobimetinib and atezolizumab (BRAF-wild-type, Cohort B, n = 15) followed by TLND and 24 weeks of adjuvant atezolizumab. Here, we report outcomes from the neoadjuvant portion of the trial. Based on intent to treat analysis, pathologic response (≤50% viable tumor) and major pathologic response (complete or near-complete, ≤10% viable tumor) were observed in 86.7% and 66.7% of BRAF-mutated and 53.3% and 33.3% of BRAF-wild-type patients, respectively (primary outcome); these exceeded pre-specified benchmarks of 50% and 30% for major pathologic response. Grade 3 and higher toxicities, primarily dermatologic, occurred in 63% during neoadjuvant treatment (secondary outcome). No surgical delays nor progression to regional unresectability occurred (secondary outcome). Peripheral blood CD8 + TCM cell expansion associated with favorable pathologic responses (exploratory outcome).

Researching COVID to enhance recovery (RECOVER) tissue pathology study protocol: Rationale, objectives, and design.

IMPORTANCE: SARS-CoV-2 infection can result in ongoing, relapsing, or new symptoms or organ dysfunction after the acute phase of infection, termed Post-Acute Sequelae of SARS-CoV-2 (PASC), or long COVID. The characteristics, prevalence, trajectory and mechanisms of PASC are poorly understood. The objectives of the Researching COVID to Enhance Recovery (RECOVER) tissue pathology study (RECOVER-Pathology) are to: (1) characterize prevalence and types of organ injury/disease and pathology occurring with PASC; (2) characterize the association of pathologic findings with clinical and other characteristics; (3) define the pathophysiology and mechanisms of PASC, and possible mediation via viral persistence; and (4) establish a post-mortem tissue biobank and post-mortem brain imaging biorepository. METHODS: RECOVER-Pathology is a cross-sectional study of decedents dying at least 15 days following initial SARS-CoV-2 infection. Eligible decedents must meet WHO criteria for suspected, probable, or confirmed infection and must be aged 18 years or more at the time of death. Enrollment occurs at 7 sites in four U.S. states and Washington, DC. Comprehensive autopsies are conducted according to a standardized protocol within 24 hours of death; tissue samples are sent to the PASC Biorepository for later analyses. Data on clinical history are collected from the medical records and/or next of kin. The primary study outcomes include an array of pathologic features organized by organ system. Causal inference methods will be employed to investigate associations between risk factors and pathologic outcomes. DISCUSSION: RECOVER-Pathology is the largest autopsy study addressing PASC among US adults. Results of this study are intended to elucidate mechanisms of organ injury and disease and enhance our understanding of the pathophysiology of PASC.

Increased diagnosis of thin superficial spreading melanomas: A 20-year study.

BACKGROUND: Diagnostic practice by dermatopathologists evaluating pigmented lesions may have evolved over time. OBJECTIVES: We sought to investigate diagnostic drift among a group of dermatopathologists asked to re-evaluate cases initially diagnosed 20 years ago. METHODS: Twenty nine cases of dysplastic nevi with severe atypia and 11 cases of thin radial growth-phase melanoma from 1988 through 1990 were retrieved from the pathology files of the Massachusetts General Hospital. All dermatopathologists who had rendered an original diagnosis for any of the 40 slides and the current faculty in the Massachusetts General Hospital Dermatopathology Unit were invited to evaluate the slide set in 2008 through 2009. RESULTS: The mean number of melanoma diagnoses by the 9 study participants was 18, an increase from the original 11 melanoma diagnoses. A majority agreed with the original diagnosis of melanoma in all 11 cases. In contrast, a majority of current raters diagnosed melanoma in 4 of the 29 cases originally reported as dysplastic nevus with severe atypia. Interrater agreement over time was excellent (kappa 0.88) and fair (kappa 0.47) for cases originally diagnosed as melanoma and severely atypical dysplastic nevus, respectively. LIMITATIONS: The unbalanced composition of the slide set, lack of access to clinical or demographic information, access to only one diagnostic slide, and imposed dichotomous categorization of tumors were limitations. CONCLUSIONS: A selected cohort of dermatopathologists demonstrated a general trend toward the reclassification of prior nonmalignant diagnoses of severely atypical dysplastic nevi as malignant but did not tend to revise prior diagnoses of cutaneous melanoma as benign.

Color Vision Deficiency Survey in Anatomic Pathology.

OBJECTIVES: To learn what color vision-deficient pathologists and cytotechnologists consider their most significant problems and advantages as well as any accommodations. METHODS: An anonymous online survey developed for practicing pathologists and cytotechnologists regarding their experiences with stains was sent to the members of 4 national societies. RESULTS: We received 377 responses. Twenty-three people, all men, identified themselves as color vision deficient, with 22 reporting red-green color vision deficiency and 1 reporting uncertain type. Eight pathologists and cytotechnologists indicated that they thought that their color vision deficiency conferred advantages to them, including a greater appreciation of morphology, with less confusion resulting from variations in stain quality or intensity. Nineteen pathologists and cytotechnologists thought that their color vision deficiency conferred disadvantages; the most common disadvantages stated were the identification of eosinophils and acid-fast bacilli. Other difficulties included interpretation of RBCs and nucleoli and sometimes Alcian blue, Brown and Brenn, Congo red, crystal violet, Fite, Giemsa, mucicarmine, periodic acid-Schiff, and fluorescence in situ hybridization stains. Only 2 of the color vision-deficient pathologists and cytotechnologists found digital slides more difficult than glass slides. CONCLUSIONS: Color vision-deficient pathologists and cytotechnologists report that they have developed approaches to viewing slides that do not compromise their interpretations. Digital pathology may provide several approaches for aiding color vision-deficient pathologists with the interpretation of certain stains.

Resolving the heterogeneous tumor-centric cellular neighborhood through multiplexed, spatial paracrine interactions in the setting of immune checkpoint blockade.

Direct interactions between tumor and immune cells mediate the antitumor effect of all modern cancer immunotherapeutic agents. Simultaneously, tumor cells have evolved mechanisms of evasion including the downregulation of HLA-I potentially disrupting the mechanism of action employed by many immune checkpoint inhibitors. And yet the in situ interplay between these cells within the tumor immune microenvironment (TIME) remains elusive. Recent advances in histologic multiplex bioimaging platforms have enabled in-depth molecular characterization of single cells within spatially-preserved and clinically archived tumor tissues. Herein, we applied multiplex immunofluorescence (MxIF) to excisional lymph node biopsies from 14 patients with metastatic melanoma who experienced clear objective responses to immunotherapy (7 complete response; 7 progressive disease) to determine distinguishing features of the TIME in the pretreatment setting. Distinct regions of the TIME were evaluated using 35 proteins probing tumor, immune and vasculature components across 323 fields of view. Single cell compositional analysis confirmed established prognostic immune cell types including increased prevalence of cytotoxic T cells within the tumor core FOVs of responders. Integrating single cell quantification with the spatial arrangement of cellular neighborhoods surrounding tumor cells revealed novel, spatial immune signatures capable of stratifying TIME based on clinical response. Our analysis revealed dynamic cellular composition of the TCCN based on anatomical subregion, functional expression of HLA-I by the index tumor cell and ultimately clinical response to immunotherapy. Overall, this study provides an analytical framework to resolve the cellular complexity of the TIME, increasingly relevant to the outcomes of modern cancer immunotherapy.

Single-Nucleotide Polymorphism Array for Histologically Ambiguous Melanocytic Tumors.

Genome-wide copy number profiling by single-nucleotide polymorphism (SNP) array is increasingly employed in the clinical diagnostic workup of melanocytic tumors. We present our SNP array results on 675 melanocytic tumors, including 615 histologically ambiguous tumors evaluated by our institution's dermatopathology consultation service and a separate validation cohort of 26 known benign nevi and 34 known malignant melanomas. The total number of somatic copy number abnormalities, sub-chromosomal copy number abnormalities, regions of homozygosity, and abnormalities at disease-associated regions was significantly associated with a diagnosis of malignancy across disease categories. In our study, the number of copy number abnormalities was the factor that best discriminated between benign versus malignant diagnoses, confirming recent published research. Histologically ambiguous tumors had a range and spectrum of abnormalities, including recurrent 11p gains, copy state transitions over kinase genes, and 3p deletions overlapping BAP1 in neoplasms with Spitzoid morphology. Our data suggest that histologically ambiguous melanocytic neoplasms and early primary melanomas have a range of abnormalities that is intermediate between unambiguous benign or malignant melanocytic neoplasms. Careful technical review and an integrated diagnostic approach are essential for the accurate interpretation of SNP array results on histologically ambiguous melanocytic tumors.

Distinctive eosinophilic cytoplasmic inclusion bodies in melanocytic nevi: an immunohistochemical and ultrastructural study.

BACKGROUND: We sought to further determine the histochemical, immunohistochemical and ultrastructural properties of eosinophilic cytoplasmic inclusion bodies in melanocytic nevi. METHODS: Skin specimens from four patients with a known diagnosis of conventional melanocytic nevus (3) or Spitz nevus (1) and containing intracytoplasmic eosinophilic inclusion bodies were selected. In addition, melanomas (25), Spitz nevi (10) and blue nevi (4) were examined to determine the frequency of the inclusions. RESULTS: Inclusions tended to be located in multinucleated melanocytes with abundant vacuolated cytoplasm. In conventional (hematoxylin and eosin-stained) sections, the degree of density and eosinophilia of intracytoplasmic inclusions varied with size. Periodic acid-Schiff, Fontana and Congo red stains showed no reactivity. All bodies were immunoreactive for ubiquitin but negative for tyrosinase, keratin and vimentin. Ultrastructurally, inclusion bodies were non-membrane bound, ranged from 4 to 7 µm, and were comprised of radiating filamentous structures with or without an electron-dense core. Electron probe x-ray microanalysis revealed no significant peaks. None of additional melanomas, Spitz nevi and blue nevi that were evaluated showed similar inclusions. CONCLUSIONS: The inclusion bodies described herein bear no resemblance to other cytoplasmic inclusion bodies previously described in melanocytic lesions. There is no discernible relationship to melanosomes by ultrastructural analysis. We postulate a relationship with dysfunction of ubiquitin-mediated protein degradation occurring in melanocytes.

Dicom_wsi: A Python Implementation for Converting Whole-Slide Images to Digital Imaging and Communications in Medicine Compliant Files.

BACKGROUND: Adoption of the Digital Imaging and Communications in Medicine (DICOM) standard for whole slide images (WSIs) has been slow, despite significant time and effort by standards curators. One reason for the lack of adoption is that there are few tools which exist that can meet the requirements of WSIs, given an evolving ecosystem of best practices for implementation. Eventually, vendors will conform to the specification to ensure enterprise interoperability, but what about archived slides? Millions of slides have been scanned in various proprietary formats, many with examples of rare histologies. Our hypothesis is that if users and developers had access to easy to use tools for migrating proprietary formats to the open DICOM standard, then more tools would be developed as DICOM first implementations. METHODS: The technology we present here is dicom_wsi, a Python based toolkit for converting any slide capable of being read by the OpenSlide library into DICOM conformant and validated implementations. Moreover, additional postprocessing such as background removal, digital transformations (e.g., ink removal), and annotation storage are also described. dicom_wsi is a free and open source implementation that anyone can use or modify to meet their specific purposes. RESULTS: We compare the output of dicom_wsi to two other existing implementations of WSI to DICOM converters and also validate the images using DICOM capable image viewers. CONCLUSION: dicom_wsi represents the first step in a long process of DICOM adoption for WSI. It is the first open source implementation released in the developer friendly Python programming language and can be freely downloaded at .

Robust hierarchical density estimation and regression for re-stained histological whole slide image co-registration.

For many disease conditions, tissue samples are colored with multiple dyes and stains to add contrast and location information for specific proteins to accurately identify and diagnose disease. This presents a computational challenge for digital pathology, as whole-slide images (WSIs) need to be properly overlaid (i.e. registered) to identify co-localized features. Traditional image registration methods sometimes fail due to the high variation of cell density and insufficient texture information in WSIs-particularly at high magnifications. In this paper, we proposed a robust image registration strategy to align re-stained WSIs precisely and efficiently. This method is applied to 30 pairs of immunohistochemical (IHC) stains and their hematoxylin and eosin (H&E) counterparts. Our approach advances the existing methods in three key ways. First, we introduce refinements to existing image registration methods. Second, we present an effective weighting strategy using kernel density estimation to mitigate registration errors. Third, we account for the linear relationship across WSI levels to improve accuracy. Our experiments show significant decreases in registration errors when matching IHC and H&E pairs, enabling subcellular-level analysis on stained and re-stained histological images. We also provide a tool to allow users to develop their own registration benchmarking experiments.

Classification of Melanocytic Lesions in Selected and Whole-Slide Images via Convolutional Neural Networks.

Whole-slide images (WSIs) are a rich new source of biomedical imaging data. The use of automated systems to classify and segment WSIs has recently come to forefront of the pathology research community. While digital slides have obvious educational and clinical uses, their most exciting potential lies in the application of quantitative computational tools to automate search tasks, assist in classic diagnostic classification tasks, and improve prognosis and theranostics. An essential step in enabling these advancements is to apply advances in machine learning and artificial intelligence from other fields to previously inaccessible pathology datasets, thereby enabling the application of new technologies to solve persistent diagnostic challenges in pathology. Here, we applied convolutional neural networks to differentiate between two forms of melanocytic lesions (Spitz and conventional). Classification accuracy at the patch level was 99.0%-2% when applied to WSI. Importantly, when the model was trained without careful image curation by a pathologist, the training took significantly longer and had lower overall performance. These results highlight the utility of augmented human intelligence in digital pathology applications, and the critical role pathologists will play in the evolution of computational pathology algorithms.