A Deep Learning Approach for the Identification of the Molecular Subtypes of Pancreatic Ductal Adenocarcinoma Based on Whole Slide Pathology Images.

Delayed diagnosis and treatment resistance result in high pancreatic ductal adenocarcinoma (PDAC) mortality rates. Identifying molecular subtypes can improve treatment, but current methods are costly and time-consuming. In this study, deep learning models were used to identify histologic features that classify PDAC molecular subtypes based on routine hematoxylin-eosin-stained histopathologic slides.

Predictive value and molecular correlates of MYC immunohistochemistry and copy number gain in non-small cell lung carcinomas treated with immunotherapy.

Objectives: Accurately predicting which patients diagnosed with non-small cell lung cancer (NSCLC) will respond to immunotherapy remains a clinical challenge. This study aims to determine the associations between MYC immunoreactivity, MYC copy number gain (CNG), driver mutations and survival following immunotherapy treatment, to provide insight into whether clinical MYC assessment may have predictive value.

Materials And Methods: MYC copy number status was determined in 82 patients with NSCLC treated with immunotherapy, and MYC immunohistochemistry (IHC) was performed on 80 of these cases.

Confirmation of Recurrent Lung Cancer Following Resection Using Liquid Biopsy, a Proof-of-Concept Real-World Study.

Appropriate management requires timely and accurate confirmation of non-small cell lung cancer (NSCLC) recurrence in patients who have had curative-intent surgical resection. We assessed the association between circulating tumor DNA (ctDNA) identified using amplicon sequencing and evidence of recurrence on CT surveillance. A prospective cohort study of NSCLC patients with early-stage disease undergoing curative-intent resection was conducted.

Prognostic Immunohistochemistry for Ki-67 and OTP on Small Biopsies of Pulmonary Carcinoid Tumors: Ki-67 Index Predicts Progression-free Survival and Atypical Histology.

Prognostic stratification of pulmonary carcinoids into "typical" and "atypical" categories requires examination of large tissue volume. However, there is a need for tools that provide similar prognostic information on small biopsy samples. Ki-67 and OTP immunohistochemistry have shown promising prognostic value in studies of resected pulmonary carcinoids, but prognostic value when using biopsy/cytology specimens is unclear.

Pulmonary gangliocytic paraganglioma: An under-recognized mimic of carcinoid tumor.

Gangliocytic paragangliomas are rare neoplasms occurring almost exclusively in the ampullary region of the gastrointestinal tract. Although these tumors are not typically considered in the differential diagnosis of primary pulmonary neoplasia, 5 cases of primary pulmonary gangliocytic paragangliomas have been previously reported. Herein we report our experience with 3 additional examples, all referred to our Anatomic Pathology Consultation service.

Recent developments in the pathology of primary pulmonary salivary gland-type tumours.

Primary pulmonary salivary gland-type tumours are rare neoplasms that are thought to arise from seromucinous glands that are located in the submucosa of large airways. These neoplasms have clinical and pathologic features that are distinct from other pulmonary neoplasms. The majority of primary pulmonary salivary gland-type tumours are malignant, with the most common entities being mucoepidermoid carcinoma, adenoid cystic carcinoma, and epithelial-myoepithelial carcinoma.

Remotely operated robotic microscopy for rapid diagnosis of bronchoscopic cytology specimens.

Background: Obtaining a diagnosis and treating pulmonary malignancies during the same anesthesia requires either an on-site pathologist or a system for remotely evaluating microscopic images. Cytology specimens are challenging to remotely assess given the need to navigate through dispersed and three-dimensional cell clusters. Remote navigation is possible using robotic telepathology, but data are limited on the ease of use of current systems, particularly for pulmonary cytology.

EZH2 and POU2F3 Can Aid in the Distinction of Thymic Carcinoma from Thymoma.

Thymic carcinoma is an aggressive malignancy that can be challenging to distinguish from thymoma using histomorphology. We assessed two emerging markers for these entities, EZH2 and POU2F3, and compared them with conventional immunostains. Whole slide sections of 37 thymic carcinomas, 23 type A thymomas, 13 type B3 thymomas, and 8 micronodular thymomas with lymphoid stroma (MNTLS) were immunostained for EZH2, POU2F3, CD117, CD5, TdT, BAP1, and MTAP.

Updates in pathology and molecular diagnostics to inform the evolving landscape of thoracic surgery and oncology.

The pathologic assessment of lung cancers provides essential guidance to the surgeon and oncologist who are considering the best treatment strategies for patients with both early and advanced-stage disease. The management of patients with lung cancer is predicated first and foremost on access to an accurate diagnosis, even when the sample size is limited, as is often the case with use of modern, minimally invasive sampling techniques. Once the diagnosis and disease stage are established, predictive biomarker testing may be essential, particularly for those patients with nonsmall cell lung carcinoma (NSCLC) being considered for immunotherapy or genomic biomarker-driven targeted therapy.

Hypothesis: HEG1 and claudin-4 staining will allow a diagnosis of epithelioid and biphasic mesothelioma versus non-small-cell lung carcinoma with only two stains in most cases.

Separation of mesothelioma from metastatic carcinoma requires immunohistochemical support, with small batteries of stains recommended as a starting-point, but these numbers commonly expand to 10, 12 or more stains, a process that is not only expensive but frequently generates anomalous or confounding results, leading to even more stains. Here we review data on HEG1 clone SKM9-2, a new (now commercially available) mesothelioma marker and claudin-4, a broad-spectrum carcinoma marker, to ask whether these two stains are sufficient, by themselves, to separate mesotheliomas from non-small-cell lung (NSCLC) as well as other carcinomas. Data for HEG1, derived from four laboratories, showed membrane staining in 393 of 434 (91%) epithelioid/biphasic mesotheliomas and one of 360 (0.

The impact of whole genome and transcriptome analysis (WGTA) on predictive biomarker discovery and diagnostic accuracy of advanced malignancies.

In this study, we evaluate the impact of whole genome and transcriptome analysis (WGTA) on predictive molecular profiling and histologic diagnosis in a cohort of advanced malignancies. WGTA was used to generate reports including molecular alterations and site/tissue of origin prediction. Two reviewers analyzed genomic reports, clinical history, and tumor pathology.

The utility of color normalization for AI-based diagnosis of hematoxylin and eosin-stained pathology images.

The color variation of hematoxylin and eosin (H&E)-stained tissues has presented a challenge for applications of artificial intelligence (AI) in digital pathology. Many color normalization algorithms have been developed in recent years in order to reduce the color variation between H&E images. However, previous efforts in benchmarking these algorithms have produced conflicting results and none have sufficiently assessed the efficacy of the various color normalization methods for improving diagnostic performance of AI systems.

Significance of p53 immunostaining in mesothelial proliferations and correlation with TP53 mutation status.

p53 immunohistochemistry has long been proposed for the separation of benign from malignant mesothelial proliferations, with the older literature suggesting that any degree of positivity supported a diagnosis of mesothelioma. However, using modern immunohistochemistry platforms in other organ systems, notably gynecologic tumors, it has become clear that p53 staining can represent wild-type protein, and only specific staining patterns (absent, overexpression, or cytoplasmic expression) are indicative of a TP53 mutation. We applied these principles to two tissue microarrays containing 94 mesotheliomas and 66 reactive mesothelial proliferations.

Automated PD-L1 Scoring for Non-Small Cell Lung Carcinoma Using Open-Source Software.

PD-L1 expression in non-small cell lung cancer (NSCLC) is predictive of response to immunotherapy, but scoring of PD-L1 immunohistochemistry shows considerable interobserver variability. Automated methods may allow more consistent and expedient PD-L1 scoring. We aimed to assess the technical concordance of PD-L1 scores produced using free open source QuPath software with the manual scores of three pathologists.

Terminal ileum is the most sensitive site for the histologic diagnosis of grade 4 graft-versus-host disease (GvHD) in the lower GI tract and is a harbinger of poor outcome.

The site of the gastrointestinal (GI) tract where biopsies are most likely to be diagnostic of graft-versus-host disease (GvHD) remains controversial. Recent reports have indicated that biopsies from the rectosigmoid have sufficient sensitivity and specificity for diagnosing GI GvHD and can be obtained via a less invasive flexible sigmoidoscopy procedure. While GvHD histologic grades 1-3 have little correlation with patients' symptoms and overall clinical grade, histologic grade 4 GvHD does correlate with severe clinical presentation and a poor prognosis.

Deep-learning based classification distinguishes sarcomatoid malignant mesotheliomas from benign spindle cell mesothelial proliferations.

Sarcomatoid mesothelioma is an aggressive malignancy that can be challenging to distinguish from benign spindle cell mesothelial proliferations based on biopsy, and this distinction is crucial to patient treatment and prognosis. A novel deep learning based classifier may be able to aid pathologists in making this critical diagnostic distinction. SpindleMesoNET was trained on cases of malignant sarcomatoid mesothelioma and benign spindle cell mesothelial proliferations.

Utility of SOX6 and DAB2 for the Diagnosis of Malignant Mesothelioma.

The separation of malignant mesothelioma from non-small cell lung carcinomas can be a difficult problem. Sex-determining region Y box 6 (SOX6) and disabled homolog 2 (DAB2) have recently been proposed as sensitive/specific markers of mesothelial lineage, but have not yet been independently tested for utility in mesothelioma diagnosis. Using tissue microarrays containing mesotheliomas (epithelioid: n=40, sarcomatoid: n=23) and non-small cell lung carcinomas (adenocarcinoma: n=52, squamous cell carcinoma: n=57, large cell carcinoma: n=12) we evaluated the performance of SOX6 and DAB2 by themselves, in conjunction with other established mesothelioma markers (calretinin, WT1, D2-40, CK5/6, HEG1) and combined with 3 broad-spectrum established carcinoma markers: claudin-4, MOC31, and BerEP4.

Discordance in PD-L1 scores on repeat testing of non-small cell lung carcinomas.

Introduction: PD-L1 expression may be used as a biomarker predictive of non-small cell lung carcinoma (NSCLC) response to PD-L1 inhibitor treatment. Spatial and temporal heterogeneity in PD-L1 expression and variation in PD-L1 test interpretation may contribute to differences in PD-L1 test results between samples of the same patient's disease.

Methods: Retrospective chart review identified 77 NSCLC patients with 22C3 PharmDx PD-L1 assays performed on two different tumor samples.

Tumor infiltrating neutrophils and gland formation predict overall survival and molecular subgroups in pancreatic ductal adenocarcinoma.

Background: RNA-sequencing-based classifiers can stratify pancreatic ductal adenocarcinoma (PDAC) into prognostically significant subgroups but are not practical for use in clinical workflows. Here, we assess whether histomorphological features may be used as surrogate markers for predicting molecular subgroup and overall survival in PDAC.

Methods: Ninety-six tissue samples from 50 patients with non-resectable PDAC were scored for gland formation, stromal maturity, mucin, necrosis, and neutrophil infiltration.

Comparability of laboratory-developed and commercial PD-L1 assays in non-small cell lung carcinoma.

PD-L1 expression in non-small cell lung cancer (NSCLC) is predictive of response to treatment with PD-1 and PD-L1 inhibitors. Different inhibitors have been developed with different PD-L1 assays, which use different PD-1 antibody clones on different immunohistochemistry platforms. Depending on instrument and reagent availability, laboratory-developed tests with cross-platform use of PD-L1 antibodies may have practical benefits over commercial assays.

Variability in Synoptic Reporting of Colorectal Cancer pT4a Category and Lymphovascular Invasion.

Context.—: Serosal involvement (pT4a category) and lymphovascular invasion have prognostic significance in colorectal carcinoma, but are subject to interobserver variation in assessment.

Objectives.

The Separation of Benign and Malignant Mesothelial Proliferations: New Markers and How to Use Them.

The separation of benign from malignant mesothelial proliferations is an important clinical but often a difficult morphologic problem. Over the last roughly 10 years a variety of new markers that aid in this separation have been published and some older recommended markers reconsidered. Unlike previous, and largely unusable, empiric immunohistochemical (IHC) stains, these new markers, some using IHC and some using fluourescent in situ hybridization (FISH), are largely based on documented genomic abnormalities in malignant mesotheliomas.