Spatiotemporal architecture of immune cells and cancer-associated fibroblasts in high-grade serous ovarian carcinoma.

High-grade serous ovarian carcinoma (HGSOC), the deadliest form of ovarian cancer, is typically diagnosed after it has metastasized and often relapses after standard-of-care platinum-based chemotherapy, likely due to advanced tumor stage, heterogeneity, and immune evasion and tumor-promoting signaling from the tumor microenvironment. To understand how spatial heterogeneity contributes to HGSOC progression and early relapse, we profiled an HGSOC tissue microarray of patient-matched longitudinal samples from 42 patients. We found spatial patterns associated with early relapse, including changes in T cell localization, malformed tertiary lymphoid structure (TLS)-like aggregates, and increased podoplanin-positive cancer-associated fibroblasts (CAFs). Using spatial features to compartmentalize the tissue, we found that plasma cells distribute in two different compartments associated with TLS-like aggregates and CAFs, and these distinct microenvironments may account for the conflicting reports about the role of plasma cells in HGSOC prognosis.

Guidelines for Pathologic Diagnosis of Mesothelioma.

CONTEXT.­: Mesothelioma is an uncommon tumor that can be difficult to diagnose. OBJECTIVE.­: To provide updated, practical guidelines for the pathologic diagnosis of mesothelioma. DATA SOURCES.­: Pathologists involved in the International Mesothelioma Interest Group and others with expertise in mesothelioma contributed to this update. Reference material includes peer-reviewed publications and textbooks. CONCLUSIONS.­: There was consensus opinion regarding guidelines for (1) histomorphologic diagnosis of mesothelial tumors, including distinction of epithelioid, biphasic, and sarcomatoid mesothelioma; recognition of morphologic variants and patterns; and recognition of common morphologic pitfalls; (2) molecular pathogenesis of mesothelioma; (3) application of immunohistochemical markers to establish mesothelial lineage and distinguish mesothelioma from common morphologic differentials; (4) application of ancillary studies to distinguish benign from malignant mesothelial proliferations, including BAP1 and MTAP immunostains; novel immunomarkers such as Merlin and p53; fluorescence in situ hybridization (FISH) for homozygous deletion of CDKN2A; and novel molecular assays; (5) practical recommendations for routine reporting of mesothelioma, including grading epithelioid mesothelioma and other prognostic parameters; (6) diagnosis of mesothelioma in situ; (7) cytologic diagnosis of mesothelioma, including use of immunostains and molecular assays; and (8) features of nonmalignant peritoneal mesothelial lesions.

INHBA(+) cancer-associated fibroblasts generate an immunosuppressive tumor microenvironment in ovarian cancer.

Effective targeting of cancer-associated fibroblasts (CAFs) is hindered by the lack of specific biomarkers and a poor understanding of the mechanisms by which different populations of CAFs contribute to cancer progression. While the role of TGFß in CAFs is well-studied, less attention has been focused on a structurally and functionally similar protein, Activin A (encoded by INHBA). Here, we identified INHBA(+) CAFs as key players in tumor promotion and immunosuppression. Spatiotemporal analyses of patient-matched primary, metastatic, and recurrent ovarian carcinomas revealed that aggressive metastatic tumors enriched in INHBA(+) CAFs were also enriched in regulatory T cells (Tregs). In ovarian cancer mouse models, intraperitoneal injection of the Activin A neutralizing antibody attenuated tumor progression and infiltration with pro-tumorigenic subsets of myofibroblasts and macrophages. Downregulation of INHBA in human ovarian CAFs inhibited pro-tumorigenic CAF functions. Co-culture of human ovarian CAFs and T cells revealed the dependence of Treg differentiation on direct contact with INHBA(+) CAFs. Mechanistically, INHBA/recombinant Activin A in CAFs induced the autocrine expression of PD-L1 through SMAD2-dependent signaling, which promoted Treg differentiation. Collectively, our study identified an INHBA(+) subset of immunomodulatory pro-tumoral CAFs as a potential therapeutic target in advanced ovarian cancers which typically show a poor response to immunotherapy.

Multilayer outperforms single-layer slide scanning in AI-based classification of whole slide images with low-burden acid-fast mycobacteria (AFB).

Manual screening of Ziehl-Neelsen (ZN)-stained slides that are negative or contain rare acid-fast mycobacteria (AFB) is labor-intensive and requires repetitive refocusing to visualize AFB candidates under the microscope. Whole slide image (WSI) scanners have enabled implementation of AI to classify digital ZN-stained slides as AFB+ or AFB-. By default, these scanners acquire a single-layer WSI. However, some scanners can acquire a multilayer WSI with a z-stack and an extended focus image layer embedded. We developed a parameterized WSI classification pipeline to assess whether multilayer imaging improves ZN-stained slide classification accuracy. A CNN built into the pipeline classified tiles in each image layer to form an AFB probability score heatmap. Features extracted from the heatmap were then entered into a WSI classifier. 46 AFB+ and 88 AFB- single-layer WSIs were used for the classifier training. 15 AFB+ (with rare microorganisms) and 5 AFB- multilayer WSIs comprised the test set. Parameters in the pipeline included: (a) a WSI representation: z-stack of image layers, middle image layer (a single image layer equivalent) or an extended focus image layer, (b) 4 methods of aggregating AFB probability scores across the z-stack, (c) 3 classifiers, (d) 3 AFB probability thresholds, and (e) 9 feature vector types extracted from the aggregated AFB probability heatmaps. Balanced accuracy (BACC) was used to measure the pipeline performance for all parameter combinations. Analysis of Covariance (ANCOVA) was used to statistically evaluate the effect of each parameter on the BACC. After adjusting for other factors, a significant effect of the WSI representation (p-value < 1.99E-76), classifier type (p-value < 1.73E-21), and AFB threshold (p-value = 0.003) was observed on the BACC. The feature type had no significant effect (p-value = 0.459) on the BACC. WSIs represented by the middle layer, extended focus layer and the z-stack followed by the weighted averaging of AFB probability scores were classified with the average BACC of 58.80%, 68.64%, and 77.28%, respectively. The multilayer WSIs represented by the z-stack with the weighted averaging of AFB probability scores were classified by a Random Forest classifier with the average BACC of 83.32%. Low classification accuracy of WSIs represented by the middle layer suggests that they contain fewer features permitting identification of AFB than the multilayer WSIs. Our results indicate that single-layer acquisition can introduce a bias (sampling error) into the WSI. This bias can be mitigated by the multilayer or the extended focus acquisitions.

Dynamic Changes in the Extracellular Matrix in Primary, Metastatic, and Recurrent Ovarian Cancers.

Cancer-associated fibroblasts (CAFs) and their extracellular matrix are active participants in cancer progression. While it is known that functionally different subpopulations of CAFs co-exist in ovarian cancer, it is unclear whether certain CAF subsets are enriched during metastatic progression and/or chemotherapy. Using computational image analyses of patient-matched primary high-grade serous ovarian carcinomas, synchronous pre-chemotherapy metastases, and metachronous post-chemotherapy metastases from 42 patients, we documented the dynamic spatiotemporal changes in the extracellular matrix, fibroblasts, epithelial cells, immune cells, and CAF subsets expressing different extracellular matrix components. Among the different CAF subsets, COL11A1+ CAFs were associated with linearized collagen fibers and exhibited the greatest enrichment in pre- and post-chemotherapy metastases compared to matched primary tumors. Although pre- and post-chemotherapy metastases were associated with increased CD8+ T cell infiltration, the infiltrate was not always evenly distributed between the stroma and cancer cells, leading to an increased frequency of the immune-excluded phenotype where the majority of CD8+ T cells are present in the tumor stroma but absent from the tumor parenchyma. Overall, most of the differences in the tumor microenvironment were observed between primary tumors and metastases, while fewer differences were observed between pre- and post-treatment metastases. These data suggest that the tumor microenvironment is largely determined by the primary vs. metastatic location of the tumor while chemotherapy does not have a significant impact on the host microenvironment.

Ciliated Cells in Ovarian Cancer Decrease with Increasing Tumor Grade and Disease Progression.

Ciliated cell markers expressed in epithelial ovarian cancers (EOC) are associated with improved survival. We examined the distribution of cells expressing ciliated cell markers in various EOC histologies and stages. Immunohistochemistry and/or multiplex immunofluorescence were used to determine the expression of FOXJ1 and/or CAPS (ciliated cell markers) in tissue microarrays including 4 normal fallopian tubes, 6 normal endometria, 16 cystadenomas, 25 borderline tumors, 21 low-grade carcinomas, and 118 high-grade carcinomas (HGSOC) (46 serous, 29 endometrioid, 30 clear cell, 13 mucinous). CAPS+ cells were observed in normal fallopian tubes and endometria and in ~85% of serous benign and borderline tumors and low-grade carcinomas but only in <40% of HGSOC. mRNA data from an independent cohort showed higher FOXJ1 and CAPS expression in serous borderline tumors and low-grade carcinomas compared to HGSOC. In HGSOC, ciliated cell-positive markers were observed in 52% primary tumors compared to 26% of patient-matched synchronous metastases, and 24% metachronous metastases (p = 0.009). mRNA data from an independent HGSOC cohort showed lower levels of CAPS in metastases than in primary tumors (p = 0.03). Overall, the study revealed that ciliated cells were less common in mucinous EOC, the percentage of ciliated cell marker-positive cases decreased with increasing grade, and the percentage of ciliated cells decreased in HGSOC metastases compared to patient-matched primary tumors.

FOXC2 Promotes Vasculogenic Mimicry in Ovarian Cancer.

FOXC2 is a forkhead family transcription factor that plays a critical role in specifying mesenchymal cell fate during embryogenesis. FOXC2 expression is associated with increased metastasis and poor survival in various solid malignancies. Using in vitro and in vivo assays in mouse ovarian cancer cell lines, we confirmed the previously reported mechanisms by which FOXC2 could promote cancer growth, metastasis, and drug resistance, including epithelial-mesenchymal transition, stem cell-like differentiation, and resistance to anoikis. In addition, we showed that FOXC2 expression is associated with vasculogenic mimicry in mouse and human ovarian cancers. FOXC2 overexpression increased the ability of human ovarian cancer cells to form vascular-like structures in vitro, while inhibition of FOXC2 had the opposite effect. Thus, we present a novel mechanism by which FOXC2 might contribute to cancer aggressiveness and poor patient survival.

Computational pathology in ovarian cancer.

Histopathologic evaluations of tissue sections are key to diagnosing and managing ovarian cancer. Pathologists empirically assess and integrate visual information, such as cellular density, nuclear atypia, mitotic figures, architectural growth patterns, and higher-order patterns, to determine the tumor type and grade, which guides oncologists in selecting appropriate treatment options. Latent data embedded in pathology slides can be extracted using computational imaging. Computers can analyze digital slide images to simultaneously quantify thousands of features, some of which are visible with a manual microscope, such as nuclear size and shape, while others, such as entropy, eccentricity, and fractal dimensions, are quantitatively beyond the grasp of the human mind. Applications of artificial intelligence and machine learning tools to interpret digital image data provide new opportunities to explore and quantify the spatial organization of tissues, cells, and subcellular structures. In comparison to genomic, epigenomic, transcriptomic, and proteomic patterns, morphologic and spatial patterns are expected to be more informative as quantitative biomarkers of complex and dynamic tumor biology. As computational pathology is not limited to visual data, nuanced subvisual alterations that occur in the seemingly "normal" pre-cancer microenvironment could facilitate research in early cancer detection and prevention. Currently, efforts to maximize the utility of computational pathology are focused on integrating image data with other -omics platforms that lack spatial information, thereby providing a new way to relate the molecular, spatial, and microenvironmental characteristics of cancer. Despite a dire need for improvements in ovarian cancer prevention, early detection, and treatment, the ovarian cancer field has lagged behind other cancers in the application of computational pathology. The intent of this review is to encourage ovarian cancer research teams to apply existing and/or develop additional tools in computational pathology for ovarian cancer and actively contribute to advancing this important field.

Focal Serous Tubal Intra-Epithelial Carcinoma Lesions Are Associated With Global Changes in the Fallopian Tube Epithelia and Stroma.

Objective: Serous tubal intra-epithelial carcinoma (STIC) lesions are thought to be precursors to high-grade serous ovarian cancer (HGSOC), but HGSOC is not always accompanied by STIC. Our study was designed to determine if there are global visual and subvisual microenvironmental differences between fallopian tubes with and without STIC lesions. Methods: Computational image analyses were used to identify potential morphometric and topologic differences in stromal and epithelial cells in samples from three age-matched groups of fallopian tubes. The Benign group comprised normal fallopian tubes from women with benign conditions while the STIC and NoSTIC groups consisted of fallopian tubes from women with HGSOC, with and without STIC lesions, respectively. For the morphometric feature extraction and analysis of the stromal architecture, the image tiles in the STIC group were further divided into the stroma away from the STIC (AwaySTIC) and the stroma near the STIC (NearSTIC). QuPath software was used to identify and quantitate secretory and ciliated epithelial cells. A secretory cell expansion (SCE) or a ciliated cell expansion (CCE) was defined as a monolayered contiguous run of >10 secretory or ciliated cells uninterrupted by the other cell type. Results: Image analyses of the tubal stroma revealed gradual architectural differences from the Benign to NoSTIC to AwaySTIC to NearSTIC groups. In the epithelial topology analysis, the relative number of SCE and the average number of cells within SCE were higher in the STIC group than in the Benign and NoSTIC groups. In addition, aging was associated with an increased relative number of SCE and a decreased relative number of CCE. ROC analysis determined that an average of 15 cells within SCE was the optimal cutoff value indicating the presence of a STIC lesion in the tubal epithelium. Conclusions: Our findings suggest that global stromal alterations and age-associated reorganization of tubal secretory and ciliated cells are associated with STIC lesions. Further studies will need to determine if these alterations precede STIC lesions and provide permissible conditions for the formation of STIC.

Membranous HEG1 expression is a useful marker in the differential diagnosis of epithelioid and biphasic malignant mesothelioma versus carcinomas.

Sialylated HEG1 has been reported as a highly specific and sensitive mesothelioma marker but a comprehensive evaluation of its expression in carcinomas in different organs, various sarcomas and reactive mesothelial proliferations has not been reported. The aim of this study was to evaluate the clinical applicability of HEG1 as a marker in the diagnosis of mesothelioma. HEG1 immunoreactivity was evaluated in whole sections of 122 mesotheliomas, 75 pulmonary carcinomas, 55 other carcinomas, 16 mesenchymal tumors, and 24 reactive mesothelial proliferations and in tissue microarrays containing 70 epithelioid (EM), 36 biphasic (BM), and 2 sarcomatoid mesotheliomas (SM). In whole sections and tissue microarrays, respectively, membranous HEG1 was expressed in 93.0% and 85.5% of EM, 81.3% and 69.4% of BM, 0% and 0% of SM. HEG1 was not expressed in pulmonary adenocarcinomas. HEG1 was expressed as cytoplasmic immunoreactivity in pulmonary squamous cell carcinomas (21.7%). Membranous HEG1 staining was seen in ovarian carcinomas (66.7%), thyroid carcinomas (100%), reactive conditions (16.7%), and mesenchymal tumors (18.8%). The sensitivity of membranous HEG1 expression to distinguish EM/BM from all carcinomas was 88.8%. The specificity for the differential diagnosis between EM/BM and all carcinomas and pulmonary carcinomas was 92.3% and 98.7%, respectively.

Comparison of Nuclear Grade, Necrosis, and Histologic Subtype Between Biopsy and Resection in Pleural Malignant Mesothelioma: An International Multi-Institutional Analysis.

OBJECTIVES: Numerous studies on malignant mesothelioma (MM) highlight the prognostic importance of histologic subtype, nuclear grade, and necrosis. This study compares these parameters in paired biopsy and resection specimens of pleural MM. METHODS: Histologic subtype, percentage of epithelioid morphology, nuclear grade, and the presence or absence of necrosis were compared in 429 paired biopsies and resection specimens of pleural MM from 19 institutions. RESULTS: Histologic subtype was concordant in 81% of cases (κ = 0.58). When compared with resection specimens, epithelioid morphology at biopsy had a positive predictive value (PPV) of 78.9% and a negative predictive value (NPV) of 93.5%; sarcomatoid morphology showed high PPV (92.9%) and NPV (99.3%), and biphasic morphology PPV was 89.7% and NPV was 79.7%. Agreement of the percentage of epithelioid morphology was fair (κ = 0.27). Nuclear grade and necrosis were concordant in 75% (κ = 0.59) and 81% (κ = 0.53) of cases, respectively. Nuclear grade showed moderate (κ = 0.53) and substantial (κ = 0.67) agreement from patients with and without neoadjuvant therapy, respectively, and necrosis showed moderate (κ = 0.47 and κ = 0.60) agreement, respectively, in the same subsets of paired specimens. CONCLUSIONS: Paired biopsy-resection specimens from pleural MM show overall moderate agreement in pathologic parameters. These findings may help guide postbiopsy management and triage of patients with MM.

Clinico-pathologic findings in patients with median arcuate ligament syndrome (celiac artery compression syndrome).

Median Arcuate Ligament Syndrome (MALS) is a rare entity characterized by severe post-prandial epigastric pain, nausea, vomiting, and/or weight loss. Symptoms have been attributed to vascular compression (celiac artery compression syndrome, CACS), but it remains controversial whether they could be secondary to neural compression. Literature review identified rare description of pathologic findings in surgery journals. The clinico-pathologic findings of four MALS patients who underwent robotic or laparoscopic surgery in our hospital are described. All our patients were female with a median age of 32.5 (range 25-55 years), and a median BMI of 23.5 kg/m2. They presented with chronic often post-prandial abdominal pain (4/4), nausea (3/4), emesis (2/4), anorexia (1/4), and weight loss (1/4). Two patients had a history of Crohn's disease. At intraoperative exploration, the celiac artery and adjacent nerves and ganglia were encased and partially compressed by fibrotic tissue in each patient. In each case laparoscopic excision of fibrotic tissue, celiac plexus and ligament division and was performed; celiac plexus nerve block was also performed in one patient. After surgical intervention, symptoms improved in three of the patients whose specimens show periganglionic and perineural fibrosis with proliferation of small nerve fibers. Our findings support neurogenic compression as a contributing factor in the development of pain and other MALS symptoms, and favor the use of MALS rather than CACS as diagnostic terminology. To further study the pathogenesis of this unusual syndrome, surgeons should submit all tissues excised during MALS procedures for histopathologic examination.

The concept of mesothelioma in situ, with consideration of its potential impact on cytology diagnosis.

Diffuse malignant mesothelioma (MM) is an incurable tumour of the serosal membranes, which is often caused by exposure to asbestos and commonly diagnosed at advanced stage. Malignant mesothelioma in situ (MMIS) is now included as diagnostic category by the World Health Organization (WHO). However, our international survey of 34 pulmonary pathologists with an interest in MM diagnosis highlights inconsistency regarding how the diagnosis is being made by experts, despite published guidelines. Whilst the WHO restricts the diagnosis to surgical samples, the very concept has implication for cytological diagnosis, which is already regarded as controversial in itself by some. MMIS is currently only applicable as precursor to MM with an epithelioid component, and raises the possibility for different molecular pathways for different histological MM subtypes. The clinical implications of MMIS at this stage are uncertain, but aggressive therapies are being initiated in some instances. Based on the results of the survey we here present a critical appraisal of the concept, its clinical and conceptual implications and provide practice suggestions for diagnosis. A low threshold for ancillary testing is suggested. The designations of 'malignant mesothelioma, cannot exclude MMIS' or 'atypical mesothelial proliferation with molecular indicators of malignancy, so-called MMIS' could be used on cytology samples, adding 'no evidence of invasion in sample provided' for surgical samples. Clinical and radiological correlation are integral to diagnosis and best done at multidisciplinary meetings. Finally, collaborative studies are required to improve our understanding of MMIS.

Malignant peritoneal mesothelioma: prognostic significance of clinical and pathologic parameters and validation of a nuclear-grading system in a multi-institutional series of 225 cases.

Malignant peritoneal mesothelioma historically carried a grim prognosis, but outcomes have improved substantially in recent decades. The prognostic significance of clinical, morphologic, and immunophenotypic features remains ill-defined. This multi-institutional cohort comprises 225 malignant peritoneal mesotheliomas, which were assessed for 21 clinical, morphologic, and immunohistochemical parameters. For epithelioid mesotheliomas, combining nuclear pleomorphism and mitotic index yielded a composite nuclear grade, using a previously standardized grading system. Correlation of clinical, morphologic, and immunohistochemical parameters with overall and disease-free survival was examined by univariate and multivariate analyses. On univariate analysis, longer overall survival was significantly associated with diagnosis after 2000 (P = 0.0001), age <60 years (P = 0.0001), ECOG performance status 0 or 1 (P = 0.01), absence of radiographic lymph-node metastasis (P = 0.04), cytoreduction surgery (P < 0.0001), hyperthermic intraperitoneal chemotherapy (P = 0.0001), peritoneal carcinomatosis index <27 (P = 0.01), absence of necrosis (P = 0.007), and epithelioid histotype (P < 0.0001). Among epithelioid malignant mesotheliomas only, longer overall survival was further associated with female sex (P = 0.03), tubulopapillary architecture (P = 0.005), low nuclear pleomorphism (P < 0.0001), low mitotic index (P = 0.0007), and low composite nuclear grade (P < 0.0001). On multivariate analyses, the low composite nuclear grade was independently associated with longer overall and disease-free survival (P < 0.0001). Our data further clarify the interactions of clinical and pathologic features in peritoneal mesothelioma prognosis and validate the prognostic significance of a standardized nuclear-grading system in epithelioid malignant mesothelioma of the peritoneum.

Challenges in Ki-67 assessments in pulmonary large-cell neuroendocrine carcinomas.

AIMS: To gather the best available evidence regarding Ki-67% values in large-cell neuroendocrine carcinoma (LCNEC) and determine whether certain cut-off values could serve as a prognostic feature in LCNEC. METHODS AND RESULTS: Aperio ScanScope AT Turbo, eSlide Manager and ImageScope software (Leica Biosystems) were used to measure Ki-67% in 77 resected LCNEC diagnosed by World Health Organisation (WHO) criteria. Cases were stratified into six classes by 10% Ki-67 increments. Using the Kaplan-Meier method, overall (OS) and disease-free survivals (DFS) were compared by AJCC stage, by six Ki-67% classes and with Ki-67% cut-points ≥20% and ≥40%. Tumours were from 0.9 to 11.5 cm and pathological stages 1-3. The system measured Ki-67% positivity using 4072-44 533 tumour nuclei per case (mean 16610 ± 8039). Ki-67% ranged from 1 to 64% (mean = 26%; median = 26%). Only 16 (21%) tumours had Ki-67% ≥40%. OS ranged from 1 to 298 months (median follow-up = 25 months). DFS ranged from 1 to 276 months (median follow-up = 9 months). OS and DFS differed across AJCC stage (overall log-rank P = 0.038 and P = 0.037). However, neither OS nor DFS significantly correlated with Ki-67% when six or two classes were used with either ≥20% Ki-67 or ≥40% Ki-67 as cut-point. A literature review identified 14 reports meeting our inclusion criteria with ≥10 LCNEC. Reported Ki-67% ranged from 2% to 100%. Problems contributing to variability in Ki-67% measurements are discussed. CONCLUSION: Our findings caution against a blanket use of 20%, 40% or other Ki-67% cut-points for LCNEC diagnosis or prognostication.

Are Epithelial Ovarian Cancers of the Mesenchymal Subtype Actually Intraperitoneal Metastases to the Ovary?

Primary ovarian high-grade serous carcinoma (HGSC) has been classified into 4 molecular subtypes: Immunoreactive, Proliferative, Differentiated, and Mesenchymal (Mes), of which the Mes subtype (Mes-HGSC) is associated with the worst clinical outcomes. We propose that Mes-HGSC comprise clusters of cancer and associated stromal cells that detached from tumors in the upper abdomen/omentum and disseminated in the peritoneal cavity, including to the ovary. Using comparative analyses of multiple transcriptomic data sets, we provide the following evidence that the phenotype of Mes-HGSC matches the phenotype of tumors in the upper abdomen/omentum: (1) irrespective of the primary ovarian HGSC molecular subtype, matched upper abdominal/omental metastases were typically of the Mes subtype, (2) the Mes subtype was present at the ovarian site only in patients with concurrent upper abdominal/omental metastases and not in those with HGSC confined to the ovary, and (3) ovarian Mes-HGSC had an expression profile characteristic of stromal cells in the upper abdominal/omental metastases. We suggest that ovarian Mes-HGSC signifies advanced intraperitoneal tumor dissemination to the ovary rather than a subtype of primary ovarian HGSC. This is consistent with the presence of upper abdominal/omental disease, suboptimal debulking, and worst survival previously reported in patients with ovarian Mes-HGSC compared to other molecular subtypes.

Multiplatform molecular test performance in indeterminate thyroid nodules.

BACKGROUND: Approximately 25% of thyroid nodule fine-needle aspirates (FNAs) have cytology that is indeterminate for malignant disease. Accurate risk stratification of these FNAs with ancillary testing would reduce unnecessary thyroid surgery. METHODS: We evaluated the performance of an ancillary multiplatform test (MPTX) that has three diagnostic categories (negative, moderate, and positive). MPTX includes the combination of a mutation panel (ThyGeNEXT®) and a microRNA risk classifier (ThyraMIR®). A blinded, multicenter study was performed using consensus histopathology diagnosis among three pathologists to validate test performance. RESULTS: Unanimous consensus diagnosis was reached in 197 subjects with indeterminate thyroid nodules; 36% had disease. MPTX had 95% sensitivity (95% CI,86%-99%) and 90% specificity (95% CI,84%-95%) for disease in prevalence adjusted nodules with Bethesda III and IV cytology. Negative MPTX results ruledout disease with 97% negative predictive value (NPV; 95% CI,91%-99%) at a 30% disease prevalence, while positive MPTX results ruledin high risk disease with 75% positive predictive value (PPV; 95% CI,60%-86%). Such results are expected in four out of five Bethesda III and IV nodules tested, including RAS positive nodules in which the microRNA classifier was useful in rulingin disease. 90% of mutation panel false positives were due to analytically verified RAS mutations detected in benign adenomas. Moderate MPTX results had a moderate rate of disease (39%, 95% CI,23%-54%), primarily due to RAS mutations, wherein the possibility of disease could not be excluded. CONCLUSIONS: Our results emphasize that decisions for surgery should not solely be based on RAS or RAS-like mutations. MPTX informs management decisions while accounting for these challenges.

A CNN-based active learning framework to identify mycobacteria in digitized Ziehl-Neelsen stained human tissues.

Tuberculosis is the most common mycobacterial disease that affects humans worldwide. Rapid and reliable diagnosis of mycobacteria is crucial to identify infected individuals, to initiate and monitor treatment and to minimize or prevent transmission. Microscopic identification of acid-fast mycobacteria (AFB) in tissue sections is usually accomplished by examining Ziehl-Neelsen (ZN) stained slides in which AFB appear bright red against the blue background. Because the ZN-stained slides require time consuming and meticulous screening by an experienced pathologist, our team developed a machine learning pipeline to classify digitized ZN-stained slides as AFB-positive or AFB-negative. The pipeline includes two convolutional neural network (CNN) models to recognize tiles containing AFB, and a logistic regression (LR) model to classify slides based on features from AFB-probability maps assembled from the CNN tile-based classification results. The first CNN was trained using tiles from 6 AFB-positive and 8 AFB-negative slides, and the second CNN was trained using the initial tile set expanded by additional tiles from 19 AFB-negative slides selected within an active learning framework. When evaluated on a separate set of tiles, the two CNNs yielded F1 scores of 99.03% and 98.75%, respectively, and were used to classify tiles in a separate set of 134 slides (46 AFB-positive and 88 AFB-negative). The classification yielded two AFB-probability maps, one for each CNN. The LR model was then 10-fold cross-validated using the average of feature vectors extracted from the AFB-probability maps generated by each CNN. The feature vector consisted of seven features of the AFB-probability map histogram and the positive tile rate (PTR). The sensitivity (87.13%), specificity (87.62%) and F1 (80.18%) achieved by this model were superior to the baseline performance of PTR-based separation of slides that yielded F1 scores of 73.13% and 66.67% in the AFB-probability maps outputted by the CNN trained within the active learning framework and the CNN trained only on the initial set of slides, respectively. Our CNNs outperformed several recently published models for AFB detection. Active learning induced robust learning of features by the CNN and led to improved LR classification performance of slides. In the 52 AFB-positive slides used in the pipeline development, the AFB were infrequent, predominantly single and only rarely found in small clusters. Our pipeline can classify slides and visualize suspected AFB-positive areas in each slide, and thus potentially facilitate evaluation of ZN-stained tissue sections for AFB.

Pathologists should probably forget about kappa. Percent agreement, diagnostic specificity and related metrics provide more clinically applicable measures of interobserver variability.

Kappa statistics have been widely used in the pathology literature to compare interobserver diagnostic variability (IOV) among different pathologists but there has been limited discussion about the clinical significance of kappa scores. Five representative and recent pathology papers were queried using clinically relevant specific questions to learn how IOV was evaluated and how the clinical applicability of results was interpreted. The papers supported our anecdotal impression that pathologists usually assess IOV using Cohen's or Fleiss' kappa statistics and interpret the results using some variation of the scale proposed by Landis and Koch. The papers did not cite or propose specific guidelines to comment on the clinical applicability of results. The solutions proposed to decrease IOV included the development of better diagnostic criteria and additional educational efforts, but the possibility that the entities themselves represented a continuum of morphologic findings rather than distinct diagnostic categories was not considered in any of the studies. A dataset from a previous study of IOV reported by Thunnissen et al. was recalculated to estimate percent agreement among 19 international lung pathologists for the diagnosis of 74 challenging lung neuroendocrine neoplasms. Kappa scores and diagnostic sensitivity, specificity, positive and negative predictive values were calculated using the majority consensus diagnosis for each case as the gold reference diagnosis for that case. Diagnostic specificity estimates among multiple pathologists were > 90%, although kappa scores were considerably more variable. We explain why kappa scores are of limited clinical applicability in pathology and propose the use of positive and negative percent agreement and diagnostic specificity against a gold reference diagnosis to evaluate IOV among two and multiple raters, respectively.