Association between BRAF V600E mutation and mortality in patients with papillary thyroid cancer.

IMPORTANCE: BRAF V600E is a prominent oncogene in papillary thyroid cancer (PTC), but its role in PTC-related patient mortality has not been established. OBJECTIVE: To investigate the relationship between BRAF V600E mutation and PTC-related mortality. DESIGN, SETTING, AND PARTICIPANTS: Retrospective study of 1849 patients (1411 women and 438 men) with a median age of 46 years (interquartile range, 34-58 years) and an overall median follow-up time of 33 months (interquartile range, 13-67 months) after initial treatment at 13 centers in 7 countries between 1978 and 2011. MAIN OUTCOMES AND MEASURES: Patient deaths specifically caused by PTC. RESULTS: Overall, mortality was 5.3% (45/845; 95% CI, 3.9%-7.1%) vs 1.1% (11/1004; 95% CI, 0.5%-2.0%) (P < .001) in BRAF V600E-positive vs mutation-negative patients. Deaths per 1000 person-years in the analysis of all PTC were 12.87 (95% CI, 9.61-17.24) vs 2.52 (95% CI, 1.40-4.55) in BRAF V600E-positive vs mutation-negative patients; the hazard ratio (HR) was 2.66 (95% CI, 1.30-5.43) after adjustment for age at diagnosis, sex, and medical center. Deaths per 1000 person-years in the analysis of the conventional variant of PTC were 11.80 (95% CI, 8.39-16.60) vs 2.25 (95% CI, 1.01-5.00) in BRAF V600E-positive vs mutation-negative patients; the adjusted HR was 3.53 (95% CI, 1.25-9.98). When lymph node metastasis, extrathyroidal invasion, and distant metastasis were also included in the model, the association of BRAF V600E with mortality for all PTC was no longer significant (HR, 1.21; 95% CI, 0.53-2.76). A higher BRAF V600E-associated patient mortality was also observed in several clinicopathological subcategories, but statistical significance was lost with adjustment for patient age, sex, and medical center. For example, in patients with lymph node metastasis, the deaths per 1000 person-years were 26.26 (95% CI, 19.18-35.94) vs 5.93 (95% CI, 2.96-11.86) in BRAF V600E-positive vs mutation-negative patients (unadjusted HR, 4.43 [95% CI, 2.06-9.51]; adjusted HR, 1.46 [95% CI, 0.62-3.47]). In patients with distant tumor metastasis, deaths per 1000 person-years were 87.72 (95% CI, 62.68-122.77) vs 32.28 (95% CI, 16.14-64.55) in BRAF V600E-positive vs mutation-negative patients (unadjusted HR, 2.63 [95% CI, 1.21-5.72]; adjusted HR, 0.84 [95% CI, 0.27-2.62]). CONCLUSIONS AND RELEVANCE: In this retrospective multicenter study, the presence of the BRAF V600E mutation was significantly associated with increased cancer-related mortality among patients with PTC. Because overall mortality in PTC is low and the association was not independent of tumor features, how to use BRAF V600E to manage mortality risk in patients with PTC is unclear. These findings support further investigation of the prognostic and therapeutic implications of BRAF V600E status in PTC.

A Deep Learning Convolutional Neural Network Can Differentiate Between Helicobacter Pylori Gastritis and Autoimmune Gastritis With Results Comparable to Gastrointestinal Pathologists.

CONTEXT.­: Pathology studies using convolutional neural networks (CNNs) have focused on neoplasms, while studies in inflammatory pathology are rare. We previously demonstrated a CNN that differentiates reactive gastropathy, Helicobacter pylori gastritis (HPG), and normal gastric mucosa. OBJECTIVE.­: To determine whether a CNN can differentiate the following 2 gastric inflammatory patterns: autoimmune gastritis (AG) and HPG. DESIGN.­: Gold standard diagnoses were blindly established by 2 gastrointestinal (GI) pathologists. One hundred eighty-seven cases were scanned for analysis by HALO-AI. All levels and tissue fragments per slide were included for analysis. The cases were randomized, 112 (60%; 60 HPG, 52 AG) in the training set and 75 (40%; 40 HPG, 35 AG) in the test set. A HALO-AI correct area distribution (AD) cutoff of 50% or more was required to credit the CNN with the correct diagnosis. The test set was blindly reviewed by pathologists with different levels of GI pathology expertise as follows: 2 GI pathologists, 2 general surgical pathologists, and 2 residents. Each pathologist rendered their preferred diagnosis, HPG or AG. RESULTS.­: At the HALO-AI AD percentage cutoff of 50% or more, the CNN results were 100% concordant with the gold standard diagnoses. On average, autoimmune gastritis cases had 84.7% HALO-AI autoimmune gastritis AD and HP cases had 87.3% HALO-AI HP AD. The GI pathologists, general anatomic pathologists, and residents were on average, 100%, 86%, and 57% concordant with the gold standard diagnoses, respectively. CONCLUSIONS.­: A CNN can distinguish between cases of HPG and autoimmune gastritis with accuracy equal to GI pathologists.

Validation and real-world clinical application of an artificial intelligence algorithm for breast cancer detection in biopsies.

Breast cancer is the most common malignant disease worldwide, with over 2.26 million new cases in 2020. Its diagnosis is determined by a histological review of breast biopsy specimens, which can be labor-intensive, subjective, and error-prone. Artificial Intelligence (AI)-based tools can support cancer detection and classification in breast biopsies ensuring rapid, accurate, and objective diagnosis. We present here the development, external clinical validation, and deployment in routine use of an AI-based quality control solution for breast biopsy review. The underlying AI algorithm is trained to identify 51 different types of clinical and morphological features, and it achieves very high accuracy in a large, multi-site validation study. Specifically, the area under the receiver operating characteristic curves (AUC) for the detection of invasive carcinoma and of ductal carcinoma in situ (DCIS) are 0.99 (specificity and sensitivity of 93.57 and 95.51%, respectively) and 0.98 (specificity and sensitivity of 93.79 and 93.20% respectively), respectively. The AI algorithm differentiates well between subtypes of invasive and different grades of in situ carcinomas with an AUC of 0.97 for invasive ductal carcinoma (IDC) vs. invasive lobular carcinoma (ILC) and AUC of 0.92 for DCIS high grade vs. low grade/atypical ductal hyperplasia, respectively, as well as accurately identifies stromal tumor-infiltrating lymphocytes (TILs) with an AUC of 0.965. Deployment of this AI solution as a real-time quality control solution in clinical routine leads to the identification of cancers initially missed by the reviewing pathologist, demonstrating both clinical utility and accuracy in real-world clinical application.

Biospecimen reporting for improved study quality (BRISQ).

Human biospecimens are subject to a number of different collection, processing, and storage factors that can significantly alter their molecular composition and consistency. These biospecimen preanalytical factors, in turn, influence experimental outcomes and the ability to reproduce scientific results. Currently, the extent and type of information specific to the biospecimen preanalytical conditions reported in scientific publications and regulatory submissions varies widely. To improve the quality of research utilizing human tissues, it is critical that information regarding the handling of biospecimens be reported in a thorough, accurate, and standardized manner. The Biospecimen Reporting for Improved Study Quality (BRISQ) recommendations outlined herein are intended to apply to any study in which human biospecimens are used. The purpose of reporting these details is to supply others, from researchers to regulators, with more consistent and standardized information to better evaluate, interpret, compare, and reproduce the experimental results. The BRISQ guidelines are proposed as an important and timely resource tool to strengthen communication and publications around biospecimen-related research and help reassure patient contributors and the advocacy community that the contributions are valued and respected.

Spectrum of risk of malignancy in subcategories of 'atypia of undetermined significance'.

OBJECTIVE: To determine if focal 'nuclear atypia' or 'microfollicular architecture' portends a higher risk of malignancy than other subcategories of atypia of undetermined significance (AUS) in thyroid fine-needle aspirations (FNAs). STUDY DESIGN: The frequencies of The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) categories were calculated from 3,956 thyroid FNAs interpreted over a 26-month period at The Johns Hopkins Hospital after adoption of TBSRTC. TBSRTC criteria were applied strictly. The risk of malignancy, specifically for AUS subcategories, was analyzed by cyto-histo correlation. RESULTS: Of the 133 cases diagnosed as AUS, 32% were found to have stageable carcinoma (not incidental microcarcinoma) on resection. When the subset of AUS with 'nuclear atypia' (AUS-N) was separated from other AUS cases, 48% (30/62) of them had stageable carcinoma on resection; of the AUS subset with 'microfollicular architecture' (AUS-F), 27% (8/30) were malignant on resection. The 'suspicious for papillary thyroid carcinoma' (SPTC) group maintained a higher risk of malignancy versus AUS-N (relative risk, RR 1.57; 95% CI 1.23-1.81). CONCLUSION: The subcategory of 'nuclear atypia' within AUS indicates a higher risk of malignancy than other subcategories of AUS but has a lower risk of malignancy than SPTC does. Thus, it is an important distinction with potential clinical implications.

Analysis of nondiagnostic results after image-guided needle biopsies of musculoskeletal lesions.

BACKGROUND/RATIONALE: Image-guided needle biopsies are commonly used to diagnose musculoskeletal tumors, but nondiagnostic (ND) results can delay diagnosis and treatment. It is important to understand which factors or diagnoses predispose to a ND result so that appropriate patient education or a possible change in the clinical plan can be made. Currently it is unclear which factors or specific lesions are more likely to lead to a ND result after image-guided needle biopsy. QUESTIONS/PURPOSES: We therefore identified specific factors and diagnoses most likely to yield ND results. We also asked whether an image-guided needle biopsy of bone and soft tissue lesions is an accurate and clinically useful tool. METHODS: We retrospectively reviewed data from a prospectively collected database for a case-control study of 508 image-guided needle biopsies of patients with suspected musculoskeletal tumors between 2003 and 2008. RESULTS: The interpretations of 453 of the 508 (89%) needle biopsies were accurate and clinically useful. Forty-five biopsies (9%) were ND and 10 (2%) were incorrect (IC). Bone lesions had a higher ND rate than soft tissue lesions (13% vs. 4%). The specific diagnosis with the highest ND rate was histiocytosis. Elbow and forearm locations had higher ND rates than average. Malignant tumors had a higher IC rate than benign tumors (5% vs. 0%); fibromyxoid sarcoma and rare subtypes of osteosarcoma had higher IC rates than other diagnoses. Repeat needle or open biopsies were performed in 71 (14%) patients. Bone lesions were more likely than soft tissue lesions to require repeat biopsies (18% vs. 9%). CONCLUSIONS: A high rate of accuracy and clinical usefulness is possible with image-guided needle biopsies of musculoskeletal lesions. We believe these biopsies appropriate in selected circumstances but a key factor for appropriate use is an experienced musculoskeletal tumor team with frequent communication to correlate clinical, radiographic, and histologic information for each patient.

A Deep Learning Convolutional Neural Network Can Recognize Common Patterns of Injury in Gastric Pathology.

CONTEXT.­: Most deep learning (DL) studies have focused on neoplastic pathology, with the realm of inflammatory pathology remaining largely untouched. OBJECTIVE.­: To investigate the use of DL for nonneoplastic gastric biopsies. DESIGN.­: Gold standard diagnoses were blindly established by 2 gastrointestinal pathologists. For phase 1, 300 classic cases (100 normal, 100 Helicobacter pylori, 100 reactive gastropathy) that best displayed the desired pathology were scanned and annotated for DL analysis. A total of 70% of the cases for each group were selected for the training set, and 30% were included in the test set. The software assigned colored labels to the test biopsies, which corresponded to the area of the tissue assigned a diagnosis by the DL algorithm, termed area distribution (AD). For Phase 2, an additional 106 consecutive nonclassical gastric biopsies from our archives were tested in the same fashion. RESULTS.­: For Phase 1, receiver operating curves showed near perfect agreement with the gold standard diagnoses at an AD percentage cutoff of 50% for normal (area under the curve [AUC] = 99.7%) and H pylori (AUC = 100%), and 40% for reactive gastropathy (AUC = 99.9%). Sensitivity/specificity pairings were as follows: normal (96.7%, 86.7%), H pylori (100%, 98.3%), and reactive gastropathy (96.7%, 96.7%). For phase 2, receiver operating curves were slightly less discriminatory, with optimal AD cutoffs reduced to 40% across diagnostic groups. The AUCs were 91.9% for normal, 100% for H pylori, and 94.0% for reactive gastropathy. Sensitivity/specificity parings were as follows: normal (73.7%, 79.6%), H pylori (95.7%, 100%), reactive gastropathy (100%, 62.5%). CONCLUSIONS.­: A convolutional neural network can serve as an effective screening tool/diagnostic aid for H pylori gastritis.

Comparing Deep Learning and Immunohistochemistry in Determining the Site of Origin for Well-Differentiated Neuroendocrine Tumors.

BACKGROUND: Determining the site of origin for metastatic well-differentiated neuroendocrine tumors (WDNETs) is challenging, and immunohistochemical (IHC) profiles do not always lead to a definitive diagnosis. We sought to determine if a deep-learning convolutional neural network (CNN) could improve upon established IHC profiles in predicting the site of origin in a cohort of WDNETs from the common primary sites. MATERIALS AND METHODS: Hematoxylin and eosin (H&E)-stained tissue microarrays (TMAs) were created using 215 WDNETs arising from the known primary sites. A CNN trained and tested on 60% (n = 130) and 40% (n = 85) of these cases, respectively. One hundred and seventy-nine cases had TMA tissue remaining for the IHC analysis. These cases were stained with IHC markers pPAX8, CDX2, SATB2, and thyroid transcription factor-1 (markers of pancreas/duodenum, ileum/jejunum/duodenum, colorectum/appendix, and lung WDNET sites of origin, respectively). The CNN diagnosis was deemed correct if it designated a majority or plurality of the tumor area as the known site of origin. The IHC diagnosis was deemed correct if the most specific marker for a particular site of origin met an H-score threshold determined by two pathologists. RESULTS: When all cases were considered, the CNN correctly identified the site of origin at a lower rate compared to IHC (72% vs. 82%, respectively). Of the 85 cases in the CNN test set, 66 had sufficient TMA material for IHC stains, thus 66 cases were available for a direct case-by-case comparison of IHC versus CNN. The CNN correctly identified 70% of these cases, while IHC correctly identified 76%, a finding that was not statistically significant (P = 0.56). CONCLUSION: A CNN can identify WDNET site of origin at an accuracy rate close to the current gold standard IHC methods.

Identification of genes differentially expressed in benign versus malignant thyroid tumors.

PURPOSE: Although fine-needle aspiration biopsy is the most useful diagnostic tool in evaluating a thyroid nodule, preoperative diagnosis of thyroid nodules is frequently imprecise, with up to 30% of fine-needle aspiration biopsy cytology samples reported as "suspicious" or "indeterminate." Therefore, other adjuncts, such as molecular-based diagnostic approaches are needed in the preoperative distinction of these lesions. EXPERIMENTAL DESIGN: In an attempt to identify diagnostic markers for the preoperative distinction of these lesions, we chose to study by microarray analysis the eight different thyroid tumor subtypes that can present a diagnostic challenge to the clinician. RESULTS: Our microarray-based analysis of 94 thyroid tumors identified 75 genes that are differentially expressed between benign and malignant tumor subtypes. Of these, 33 were overexpressed and 42 were underexpressed in malignant compared with benign thyroid tumors. Statistical analysis of these genes, using nearest-neighbor classification, showed a 73% sensitivity and 82% specificity in predicting malignancy. Real-time reverse transcription-PCR validation for 12 of these genes was confirmatory. Western blot and immunohistochemical analyses of one of the genes, high mobility group AT-hook 2, further validated the microarray and real-time reverse transcription-PCR data. CONCLUSIONS: Our results suggest that these 12 genes could be useful in the development of a panel of markers to differentiate benign from malignant tumors and thus serve as an important first step in solving the clinical problem associated with suspicious thyroid lesions.

Identification of immunohistochemical biomarkers for papillary thyroid carcinoma using gene expression profiling.

We report the successful validation of a combined gene expression profiling and tissue microarray approach to papillary thyroid carcinoma (PTC) biomarker identification. Our ultimate goal is the identification of protein biomarkers that can be effectively used in immunocytochemical assays applied to thyroid fine needle aspiration biopsy (FNAB) samples. To that end, we designed our approach to prioritize molecules that were minimally expressed in normal thyroid and highly expressed in PTC. We first generated gene expression profiles from 11 normal thyroid tissue samples and 9 samples of classic PTC. The results were segregated to rank most highly those molecules not expressed in normal thyroid and up-regulated at least 6-fold in PTC. From this list, we chose 2 molecules (P-cadherin and Bax) for immunohistochemical analysis for which commercial antibodies were available. These were compared with 2 other molecules that have been previously studied in thyroid cancer (cytokeratin-19 and galectin-3). For immunohistochemistry, a tissue microarray was generated that contained the following tissues: classic PTC (n = 20), follicular variant of PTC (n = 9), normal thyroid (n = 19), Hashimoto thyroiditis (n = 11), follicular adenoma (n = 15), and follicular carcinoma (n = 14). Immunohistochemical staining was scored and compared with the gene expression profiling. As anticipated, cytokeratin-19 and galectin-3 were highly expressed in PTC and less expressed in other tissues. Bax and P-cadherin were also expressed in PTC, but to a lower level than cytokeratin-19 and galectin-3; however, Bax and P-cadherin demonstrated virtually no staining of normal thyroid, unlike cytokeratin-19 and galectin-3. These results validate our approach for PTC biomarker discovery and identify several candidate biomarkers for further development.