Search

Pathologists are responsible for rapidly providing a diagnosis on critical health issues. Challenging cases benefit from additional opinions of pathologist colleagues. In addition to on-site colleagues, there is an active worldwide community of pathologists on social media for complementary opinions. Such access to pathologists worldwide has the capacity to improve diagnostic accuracy and generate broader consensus on next steps in patient care. From Twitter we curate 13,626 images from 6,351 tweets from 25 pathologists from 13 countries. We supplement the Twitter data with 113,161 images from 1,074,484 PubMed articles. We develop machine learning and deep learning models to (i) accurately identify histopathology stains, (ii) discriminate between tissues, and (iii) differentiate disease states. Area Under Receiver Operating Characteristic (AUROC) is 0.805-0.996 for these tasks. We repurpose the disease classifier to search for similar disease states given an image and clinical covariates. We report precision@k = 1 = 0.7618 ± 0.0018 (chance 0.397 ± 0.004, mean ±stdev ). The classifiers find that texture and tissue are important clinico-visual features of disease. Deep features trained only on natural images (e.g., cats and dogs) substantially improved search performance, while pathology-specific deep features and cell nuclei features further improved search to a lesser extent. We implement a social media bot (@pathobot on Twitter) to use the trained classifiers to aid pathologists in obtaining real-time feedback on challenging cases. If a social media post containing pathology text and images mentions the bot, the bot generates quantitative predictions of disease state (normal/artifact/infection/injury/nontumor, preneoplastic/benign/low-grade-malignant-potential, or malignant) and lists similar cases across social media and PubMed. Our project has become a globally distributed expert system that facilitates pathological diagnosis and brings expertise to underserved regions or hospitals with less expertise in a particular disease. This is the first pan-tissue pan-disease (i.e., from infection to malignancy) method for prediction and search on social media, and the first pathology study prospectively tested in public on social media. We will share data through http://pathobotology.org . We expect our project to cultivate a more connected world of physicians and improve patient care worldwide.

The College of American Pathologists (CAP) cancer protocols were first conceived as a resource tool for pathologists to help provide tumor reporting guidelines. The use of synoptic reports provides a [...]

It is well known that some prostate cancers comprise more than 2 grades. (1-5) While most of so-called tertiary grading reported in the literature refers to a higher grade--typically pattern [...], Context.--In prostate cancer, 'tertiary' higher-grade patterns (TPs) have been associated with biochemical recurrence after radical prostatectomy. Objective.--To determine variation regarding definition and application of TPs. Design.--Online survey regarding TPs in a range of grading scenarios circulated to 105 experienced urologic pathologists. Results.--Among 95 respondents, 40 of 95 (42%) defined TPs as 'third most common pattern' and 55 (58%) as 'minor pattern/less than 5% of tumor.' In a tumor with pattern 3 and less than 5% pattern 4, of the 95 respondents, 35 (37%) assigned 3 + 3 = 6 with Tp4, while 56 (59%) assigned 3 + 4 = 7. In a tumor with pattern 4 and less than 5% pattern 5, of the 95 respondents, 51 (54%) assigned 4 + 4 = 8 with TP5, while 43 (45%) assigned 4 + 5 = 9. Six scenarios were presented in which the order of most common patterns was 3, 4, and 5 (Group 1) or 4, 3, and 5 (Group 2) with varying percentages. In both groups, when pattern 5 was less than 5%, we found that 98% and 93% of respondents would assign 3 + 4 = 7 or 4 + 3 = 7 with TP5. In scenarios with 15% or 25% pattern 5, most respondents (70% and 80%, respectively) would include pattern 5 as the secondary grade, that is, 3 + 5 = 8 (Group 1) or 4 + 5 = 9 (Group 2). For 85 of 95 (89%), a TP would not impact Grade Group assignment. Conclusions.--This survey highlights substantial variation in practice patterns regarding definition and application of 'tertiary' grading in radical prostatectomy specimens. High consistency was observed in 3 + 4 = 7/4 + 3 = 7 scenarios with truly minor pattern 5. These findings should inform future studies assessing the standardization and predictive value of 'tertiary' patterns. (Arch Pathol Lab Med. 2020;144:356-360; doi: 10.5858/arpa.2019-0224-OA)

To the Editor.--We read with interest the latest publication from the College of American Pathologists (CAP) on their Electronic Cancer Checklists (eCC) 'Exploring the College of American Pathologists Electronic Cancer [...]

Applications for digital pathology (DP) have seen increased growth; however, few departments have successfully implemented a full-scale operation of a DP platform. Digital pathology has tremendous potential to disrupt the [...], Context.--Digital pathology (DP) implementations vary in scale, based on aims of intended operation. Few laboratories have completed a full-scale DP implementation, which may be due to high overhead costs that disrupt the traditional pathology workflow. Neither standardized criteria nor benchmark data have yet been published showing practical return on investment after implementing a DP platform. Objective.--To provide benchmark data and practical metrics to support operational efficiency and cost savings in a large academic center. Design.--Metrics reviewed include archived pathology asset retrieval; ancillary test request for recurrent/meta-static disease; cost analysis and turnaround time (TAT); and DP experience survey. Results.--Glass slide requests from the department slide archive and an off-site surgery center showed a 93% and 97% decrease, respectively. Ancillary immunohistochemical orders, compared in 2014 (52%)--before whole slide images (WSIs) were available in the laboratory information system--and 2017 (21%) showed $114 000/y in anticipated savings. Comprehensive comparative cost analysis showed a 5-year $1.3 million savings. Surgical resection cases with prior WSIs showed a 1-day decrease in TAT. A DP experience survey showed 80% of respondents agreed WSIs improved their clinical sign-out experience. Conclusions.--Implementing a DP operation showed a noteworthy increase in efficiency and operational utility. Digital pathology deployments and operations may be gauged by the following metrics: number of glass slide requests as WSIs become available, decrease in confirmatory testing for patients with metastatic/recurrent disease, long-term decrease in off-site pathology asset costs, and faster TAT. Other departments may use our benchmark data and metrics to enhance patient care and demonstrate return on investment to justify adoption of DP. doi: 10.5858/arpa.2018-0514-OA

Objectives The clinical laboratory workforce plays a crucial role in health care delivery, yet little is known about the unique pressures and challenges this workforce faces. The objective of this study was to identify factors that contribute to burnout, discrimination, exclusion, and inequity in pathology and laboratory medicine. Methods A nationwide survey was conducted in 2 phases. In phase 1, 2391 laboratory professionals were surveyed over a 1-week period about their experiences with burnout, discrimination, and work-related stress. In phase 2, the survey was extended to 1 month and questions were added to elicit more detailed information about diversity, equity, and inclusion (DEI) as well as wellness. Results Results showed a high prevalence of burnout, discrimination, and stress among laboratory professionals, with significant differences among certain demographic groups. Women, Black, indigenous, or people of color individuals and those with disabilities reported higher rates of discrimination. The study also showed a need for mentorship and resources to address educational barriers. Conclusions Findings from this study highlight the urgent need for interventions to address burnout, discrimination, exclusion, and inequity in the laboratory workforce. Initiatives to increase workforce diversity, promote mentorship and diversity training programs, and improve recognition of the laboratory workforce are recommended. The results underscore the pressing need to addressing the challenges and apprehensions laboratory professionals face, including enhancing recognition of their role in patient care, tackling systemic problems related to discrimination and equity, and enhancing the provision of support and resources for managing burnout and fostering well-being. [ABSTRACT FROM AUTHOR]

We evaluated long-term outcomes of small cell carcinoma of the bladder (SCCB), a rare, aggressive disease. Among 199 patients with SCCB treated from 1990 to 2015, those with nonmetastatic disease had excellent longterm survival following neoadjuvant chemotherapy with 5-year disease-free survival rate of 50%. Patients with metastases had poor survival, with median overall survival of 10.3 months. Pathologic downstaging following neoadjuvant chemotherapy was associated with superior survival and ERCC2 mutations conferred increased likelihood of pathologic response. Introduction: Small cell carcinoma of the bladder (SCCB) is a rare variant of bladder cancer with poor outcomes. We evaluated long-term outcomes of nonmetastatic (M0) and metastatic (M1) SCCB and correlated pathologic response with genomic alterations of patients treated with neoadjuvant chemotherapy (NAC). Patients and Methods: Clinical history and pathology samples from SCCB patients diagnosed at our institution were reviewed. Results: One hundred and ninety-nine SCCB patients were identified. (M0: 147 [74%]; M1: 52 [26%]). Among M0 patients, 108 underwent radical cystectomy (RC) (NAC: 71; RC only: 23; adjuvant chemotherapy: 14); 14 received chemoradiotherapy; the rest received chemotherapy alone or no cancer-directed therapy. RC-only patients had a median follow-up of 9.1 years, and median disease-free survival (DFS) and overall survival (OS) were 1.1 and 1.2 years, respectively. NAC patients had pathologic response (< pT2pN0) and pathologic complete response (pT0pN0) rates of 48% and 38%, respectively, with median follow-up of 7.2 years, and median DFS and OS of 5.6 and 14.5 years, respectively. NAC responders (< ypT2N0) had superior median DFS (14.5 vs. 0.6 years, hazard ratio [HR] 0.24, P < .001) and OS (14.5 vs. 2.5 years, HR 0.31, P = .002). DFS rates for responders and nonresponders were 76% and 27% at 5 years, and 71% and 23% at 10 years, respectively. Local and central nervous system recurrences were infrequent. Median progression-free survival (PFS) and OS for M1 disease were 6.9 and 10.3 months, respectively. Genomic profiling was performed on 47 NAC patients. Loss of ERCC2 function was significantly enriched among those with pathologic complete response to NAC (mutations present in 50% of pathologic complete responders vs. 15% nonresponders, P = .045). Conclusion: M0 SCCB is chemosensitive and patients have excellent long-term survival following response to NAC. Patients with M1 disease have poor survival despite systemic therapy. Loss-of-function mutations of ERCC2 were associated with pathologic complete response to NAC. [ABSTRACT FROM AUTHOR]