The development of decision support systems for pathology and their deployment in clinical practice have been hindered by the need for large manually annotated datasets. To overcome this problem, we ...present a multiple instance learning-based deep learning system that uses only the reported diagnoses as labels for training, thereby avoiding expensive and time-consuming pixel-wise manual annotations. We evaluated this framework at scale on a dataset of 44,732 whole slide images from 15,187 patients without any form of data curation. Tests on prostate cancer, basal cell carcinoma and breast cancer metastases to axillary lymph nodes resulted in areas under the curve above 0.98 for all cancer types. Its clinical application would allow pathologists to exclude 65-75% of slides while retaining 100% sensitivity. Our results show that this system has the ability to train accurate classification models at unprecedented scale, laying the foundation for the deployment of computational decision support systems in clinical practice.
High-grade neuroendocrine neoplasms (World Health Organization WHO G3) of the pancreas include both well-differentiated neuroendocrine tumor (WD-NET) and poorly differentiated neuroendocrine ...carcinoma (PD-NEC). According to the WHO classification scheme, the diagnosis of this group of tumors is based on both the histopathology of the tumor and the assessment of proliferation fraction. However, the former can be challenging due to the lack of well-defined histologic criteria, and the latter alone (ie, >20 mitoses/10 high-power fields or Ki67>20%) may not sufficiently distinguish WD-NETs from PD-NECs. Given the considerable differences in treatment strategies and clinical outcome, additional practical modalities are required to facilitate the accurate diagnosis of high-grade pancreatic neuroendocrine neoplasms. We examined 33 cases of WHO G3 neuroendocrine neoplasms of the pancreas and attempted to classify them into WD-NET, small cell PD-NEC (PD-NEC-SCC), and large cell PD-NEC (PD-NEC-LCC) or to designate them as "ambiguous" when an uncertain diagnosis was rendered by any of the observers or there was any disagreement in classification among the 3 observers. To simplify the interpretation, both PD-NEC-SCC and PD-NEC-LCC were considered together as PD-NECs in the final analysis. The initial approach was to assess microscopically a single morphologically challenging hematoxylin and eosin section from each case without the knowledge of Ki67 values, performed independently by 3 pathologists to assess the degree of diagnostic concordance, and then evaluate immunohistochemical staining for surrogate biomarkers of known genotypes of WD-NET and PD-NEC, respectively, and, lastly, complete a clinicopathologic review to establish a final definitive classification. Loss of DAXX or ATRX protein expression defined WD-NET, and abnormal p53, Rb, SMAD4 expression signified PD-NEC. When the chosen section displayed an element of WD histopathology, or other tumor sections contained WHO G1/G2 components, or there had been a prior established diagnosis of a primary WD-NET, the final diagnosis was rendered as a WD-NET with high-grade (G3) progression. If a component of conventional adenocarcinoma was present (in slides not seen in the initial review), the diagnosis was established as a combined adenocarcinoma and PD-NEC. All 3 pathologists agreed on the morphologic classification of 33% of the cases (6 WD-NET, 3 PD-NEC-SCC, and 2 PD-NEC-LCC), were conflicted on 2 cases between PD-NEC-SCC and PD-NEC-LCC, and disagreed or were uncertain on the classification for the remaining 20 cases (61%), which were therefore categorized as ambiguous. In the group of cases in which all pathologists agreed on the classification, the 6 WD-NET cases had either loss of DAXX or ATRX or had evidence of a WD-NET based on additional or prior pathology slides. The 7 PD-NEC cases had abnormal expression of p53, Rb, and/or SMAD4 or a coexisting adenocarcinoma. In the ambiguous group (n=20), 14 cases were established as WD-NETs, based upon loss of DAXX or ATRX in 7 cases and additional pathology evidence of high-grade progression from WD-NET in the other 7 cases; 5 cases were established as PD-NEC based upon abnormal expression of p53, Rb, and/or SMAD4; 1 case remained undetermined with normal expression of all markers and no evidence of entity-defining histologic findings in other slides. On the basis of the final pathologic classifications, the disease-specific survival was 75 and 11 months for the WD-NET and PD-NEC groups, respectively. Thus, we conclude that morphologic diagnosis of high-grade pancreatic neuroendocrine neoplasms is challenging, especially when limited pathologic materials are available, and necessitates better defined criteria. The analysis of both additional sections and prior material, along with an immunohistochemical evaluation, can facilitate accurate diagnosis in the majority of cases and guide the appropriate clinical management and prognosis.
Activating neurotrophic tyrosine receptor kinase (NTRK) fusions, typically detected using nucleic-acid based assays, are highly targetable and define certain tumors. Here, we explore the utility of ...pan-TRK immunohistochemistry (IHC) to detect NTRK fusions. NTRK rearrangements were detected prospectively using MSK-IMPACT, a DNA-based next-generation sequencing assay. Transcription of novel NTRK rearrangements into potentially functional fusion transcripts was assessed via Archer Dx fusion assay. Pan-Trk IHC testing with mAb EPR17341 was performed on all NTRK rearranged cases and 20 cases negative for NTRK fusions on Archer. Of 23 cases with NTRK rearrangements, 15 had known activating fusions. Archer detected fusion transcripts in 6 of 8 novel NTRK rearrangements of uncertain functional significance. Pan-Trk IHC was positive in 20 of 21 cases with NTRK fusion transcripts confirmed by Archer. The discordant negative case was a mismatch repair- deficient colorectal carcinoma with an ETV6-NTRK3 fusion. All 20 additional Archer-negative cases had concordant pan-TRK IHC results. Pan-Trk IHC sensitivity and specificity for transcribed NTRK fusions was 95.2% and 100%, respectively. All positive IHC cases had cytoplasmic staining while the following fusion partner-specific patterns were discovered: all 5 LMNA-NTRK1 fusions displayed nuclear membrane accentuation, all 4 TPM3/4 fusions displayed cellular membrane accentuation, and half (3/6) of ETV6-NTRK3 fusions displayed nuclear staining. Pan-Trk IHC is a time-efficient and tissue-efficient screen for NTRK fusions, particularly in driver-negative advanced malignancies and potential cases of secretory carcinoma and congenital fibrosarcoma. Pan-Trk IHC can help determine whether translation occurs for novel NTRK rearrangements.
Prior molecular profiling of hepatocellular carcinoma (HCC) has identified actionable findings that may have a role in guiding therapeutic decision-making and clinical trial enrollment. We ...implemented prospective next-generation sequencing (NGS) in the clinic to determine whether such analyses provide predictive and/or prognostic information for HCC patients treated with contemporary systemic therapies.
Matched tumor/normal DNA from patients with HCC (
= 127) were analyzed using a hybridization capture-based NGS assay designed to target 341 or more cancer-associated genes. Demographic and treatment data were prospectively collected with the goal of correlating treatment outcomes and drug response with molecular profiles.
WNT/β-catenin pathway (45%) and
(33%) alterations were frequent and represented mutually exclusive molecular subsets. In sorafenib-treated patients (
= 81), oncogenic PI3K-mTOR pathway alterations were associated with lower disease control rates (DCR, 8.3% vs. 40.2%), shorter median progression-free survival (PFS; 1.9 vs. 5.3 months), and shorter median overall survival (OS; 10.4 vs. 17.9 months). For patients treated with immune checkpoint inhibitors (
= 31), activating alteration WNT/β-catenin signaling were associated with lower DCR (0% vs. 53%), shorter median PFS (2.0 vs. 7.4 months), and shorter median OS (9.1 vs. 15.2 months). Twenty-four percent of patients harbored potentially actionable alterations including
(8.5%) inactivating/truncating mutations,
(6.3%) and
(1.5%) amplifications, and
missense mutations (<1%). Six percent of patients treated with systemic therapy were matched to targeted therapeutics.
Linking NGS to routine clinical care has the potential to identify those patients with HCC likely to benefit from standard systemic therapies and can be used in an investigational context to match patients to genome-directed targeted therapies.
.
Various genetic driver aberrations have been identified among distinct anatomic and clinical subtypes of intrahepatic and extrahepatic cholangiocarcinoma, and these molecular alterations may be ...prognostic biomarkers and/or predictive of drug response.
Tumor samples from patients with cholangiocarcinoma who consented prospectively were analyzed using the MSK-IMPACT platform, a targeted next-generation sequencing assay that analyzes all exons and selected introns of 410 cancer-associated genes. Fisher exact tests were performed to identify associations between clinical characteristics and genetic alterations.
A total of 195 patients were studied: 78% intrahepatic and 22% extrahepatic cholangiocarcinoma. The most commonly altered genes in intrahepatic cholangiocarcinoma were
(30%),
(23%),
(20%),
(20%), and
gene fusions (14%). A tendency toward mutual exclusivity was seen between multiple genes in intrahepatic cholangiocarcinoma including
, and
Alterations in CDKN2A/B and ERBB2 were associated with reduced survival and time to progression on chemotherapy in patients with locally advanced or metastatic disease. Genetic alterations with potential therapeutic implications were identified in 47% of patients, leading to biomarker-directed therapy or clinical trial enrollment in 16% of patients.
Cholangiocarcinoma is a genetically diverse cancer. Alterations in
and
are associated with negative prognostic implications in patients with advanced disease. Somatic alterations with therapeutic implications were identified in almost half of patients. These prospective data provide a contemporary benchmark for guiding the development of targeted therapies in molecularly profiled cholangiocarcinoma, and support to the use of molecular profiling to guide therapy selection in patients with advanced biliary cancers.
.
Much recent debate has focused on the optimal classification of epithelial neuroendocrine tumors (NETs). Multiple different systems of terminology, grading, and staging have been proposed, and some ...systems combine elements of grade and stage into a single prognostic classification. Recently, national and international consensus groups have attempted to standardize the classification of NETs, especially for those arising in the gastrointestinal tract and pancreas. Furthermore, the recognition that common classification criteria (such as proliferative rate) span multiple different systems allows the basic data necessary to predict outcome and tailor therapy to be included in pathology reports, even though a single uniform system of terminology may remain elusive. Formal tumor-node-metastasis (TNM)-based staging systems also have been developed recently, and advances in the treatment of some NETs (pancreatic in particular) are pointing towards the need to assess therapeutic biomarkers in routine practice. This review will present the most widely used systems for classifying, grading, and staging NETs and will summarize the recommendations for the data to be included in standard pathology reports of these uncommon tumors.
In this review, we detail the changes and the relevant features that are applied to neuroendocrine neoplasms (NENs) in the 2022 WHO Classification of Endocrine and Neuroendocrine Tumors. Using a ...question-and-answer approach, we discuss the consolidation of the nomenclature that distinguishes neuronal paragangliomas from epithelial neoplasms, which are divided into well-differentiated neuroendocrine tumors (NETs) and poorly differentiated neuroendocrine carcinomas (NECs). The criteria for these distinctions based on differentiation are outlined. NETs are generally (but not always) graded as G1, G2, and G3 based on proliferation, whereas NECs are by definition high grade; the importance of Ki67 as a tool for classification and grading is emphasized. The clinical relevance of proper classification is explained, and the importance of hormonal function is examined, including eutopic and ectopic hormone production. The tools available to pathologists for accurate classification include the conventional biomarkers of neuroendocrine lineage and differentiation, INSM1, synaptophysin, chromogranins, and somatostatin receptors (SSTRs), but also include transcription factors that can identify the site of origin of a metastatic lesion of unknown primary site, as well as hormones, enzymes, and keratins that play a role in functional and structural correlation. The recognition of highly proliferative, well-differentiated NETs has resulted in the need for biomarkers that can distinguish these G3 NETs from NECs, including stains to determine expression of SSTRs and those that can indicate the unique molecular pathogenetic alterations that underlie the distinction, for example, global loss of RB and aberrant p53 in pancreatic NECs compared with loss of ATRX, DAXX, and menin in pancreatic NETs. Other differential diagnoses are discussed with recommendations for biomarkers that can assist in correct classification, including the distinctions between epithelial and non-epithelial NENs that have allowed reclassification of epithelial NETs in the spine, in the duodenum, and in the middle ear; the first two may be composite tumors with neuronal and glial elements, and as this feature is integral to the duodenal lesion, it is now classified as composite gangliocytoma/neuroma and neuroendocrine tumor (CoGNET). The many other aspects of differential diagnosis are detailed with recommendations for biomarkers that can distinguish NENs from non-neuroendocrine lesions that can mimic their morphology. The concepts of mixed neuroendocrine and non-neuroendocrine (MiNEN) and amphicrine tumors are clarified with information about how to approach such lesions in routine practice. Theranostic biomarkers that assist patient management are reviewed. Given the significant proportion of NENs that are associated with germline mutations that predispose to this disease, we explain the role of the pathologist in identifying precursor lesions and applying molecular immunohistochemistry to guide genetic testing.
The 2010 World Health Organization (WHO) classification recommends that pancreatic neuroendocrine tumors (PanNETs) be graded on the basis of the mitotic rate and Ki67 index, with grade 2 (G2) PanNETs ...defined as having a mitotic rate of 2 to 20 mitotic figures/10 high-power fields or a Ki67 index of 3% to 20%. Grade 3 (G3) pancreatic neuroendocrine carcinoma (NEC) is defined as having >20 mitotic figures/10 high-power fields or a Ki67 index of >20%. However, some PanNETs show discordance between the mitotic rate and Ki67 index, usually having a Ki67 index in the G3 range but a mitotic rate suggesting G2, prompting us to examine the clinical significance of the Ki67 index in a large series of clinically well-characterized mitotic G2 PanNETs. Mitotic G2 well differentiated PanNETs, surgically resected at our institutions were reviewed. Of those, 19 cases had a Ki67>20% and were selected as the study group of grade-discordant (mitotic count G2/Ki67 index G3) PanNETs. For comparison, 53 grade-concordant (both mitotic count and Ki67 index G2) PanNETs matched for presenting stage with the discordant group as well as 43 morphologically poorly differentiated (either small cell or large cell type) pancreatic NECs were also included. The percentage of Ki67-positive neoplastic cells was quantified by manual counting of at least 500 cells on printed photographic images of "hot spots." The mean Ki67 index for grade-concordant and grade-discordant PanNETs and poorly differentiated NECs were 8.1% (range, 3% to 20%), 40% (range, 24% to 80%), and 70% (range, 40% to 98%), respectively. Overall, patients with grade-discordant PanNETs had significantly longer survival time compared with the patients with poorly differentiated NEC (median survival of 54.1 vs. 11 mo and 5 y survival of 29.1% vs. 16.1%; P=0.002). In addition, the survival time of the patients with grade-discordant PanNETs was shorter than that of the patients with grade-concordant PanNETs (median survival of 67.8 mo and 5 y survival of 62.4%); however, the difference was not statistically significant (P=0.2). Our data support the notion that the mitotic rate and Ki67 index-based grades of PanNETs can be discordant, and when the Ki67 index indicates G3, the clinical outcome is slightly worse. More importantly, we demonstrate that well differentiated PanNETs that are G3 by Ki67 are significantly less aggressive than bona fide poorly differentiated NECs, suggesting that the current WHO G3 category is heterogenous, contains 2 distinct neoplasms, and can be further separated into well differentiated PanNET with an elevated proliferation rate and poorly differentiated NEC.
Immune checkpoint inhibition has been shown to generate profound and durable responses in mismatch repair deficient (MMR-D) solid tumors and has elicited interest in detection tools and strategies to ...guide therapeutic decision-making. Herein we address questions on the appropriate screening, detection methods, patient selection, and initiation of therapy for MMR-D pancreatic ductal adenocarcinoma (PDAC) and assess the utility of next-generation sequencing (NGS) in providing additional prognostic and predictive information for MMR-D PDAC.
Archival and prospectively acquired samples and matched normal DNA from
= 833 PDAC cases were analyzed using a hybridization capture-based, NGS assay designed to perform targeted deep sequencing of all exons and selected introns of 341 to 468 cancer-associated genes. A computational program using NGS data derived the MSI status from the tumor-normal paired genome sequencing data. Available germline testing, IHC, and microsatellite instability (MSI) PCR results were reviewed to assess and confirm MMR-D and MSI status.
MMR-D in PDAC is a rare event among PDAC patients (7/833), occurring at a frequency of 0.8%. Loss of MMR protein expression by IHC, high mutational load, and elevated MSIsensor scores were correlated with MMR-D PDAC. All 7 MMR-D PDAC patients in the study were found to have Lynch syndrome. Four (57%) of the MMR-D patients treated with immune checkpoint blockade had treatment benefit (1 complete response, 2 partial responses, 1 stable disease).
An integrated approach of germline testing and somatic analyses of tumor tissues in advanced PDAC using NGS may help guide future development of immune and molecularly directed therapies in PDAC patients.
.