Optimization of Tumor Dissection Procedures Leads to Measurable Improvement in the Quality of Molecular Testing.

Molecular tests have an inherent limit of detection (LOD) and, therefore, require samples with sufficiently high percentages of neoplastic cells. Many laboratories use tissue dissection; however, optimal procedures for dissection and quality assurance measures have not been established. In this study, several modifications to tissue dissection procedures and workflow were introduced over 4 years. Each modification resulted in a significant improvement in one or more quality assurance measures. The review of materials following dissection resulted in a 90% reduction in KRAS mutations below the stated LOD (P = 0.004). Mutation allele frequencies correlated best with estimated tumor percentages for pathologists with more experience in this process. The direct marking of unstained slides, use of a stereomicroscope, validation of extraction from diagnostic slides, and use of a robust, targeted next-generation sequencing platform all resulted in reduction of quantity not sufficient specimens from 20% to 25% to nearly 0%, without a significant increase in test failures or mutations below the LOD. These data indicate that post-dissection review of unstained slides and monitoring quantity not sufficient rate, test failure rate, and mutation allele frequencies are important tumor dissection quality assurance measures that should be considered by laboratories performing tissue dissections. The amendments to tissue dissection procedures enacted during this study resulted in a measurable improvement in the quality and reliability of this process based on these metrics.

The "Pathology Passport": a redesign of the pathology elective experience to enhance medical student engagement and understanding of pathology as a clinical practice.

Given the trend of condensed preclinical curricula in medical schools nationwide, creating meaningful pathology learning experiences within the clinical and post-clinical curricula is important to both enhance student understanding of how pathology integrates into daily healthcare delivery and spark potential career interest in the field. While pathology electives are a common modality for medical students to explore pathology, they frequently render students passive observers of daily clinical workflows (often in grossing and sign-out rooms of surgical pathology). This can have a negative impact on student engagement with their pathology clinical teams and on their satisfaction with the pathology elective experience. As such, we aim to describe our institutional experience in creating a new pathology elective structure, the "Pathology Passport," which leverages intentional student engagement with existing pathology workflows and introduces a means of criterion-based grading. Data collected from student pre- and post-elective surveys demonstrate the elective's positive impact on students' perceived understanding of pathology and their overall learning experience. We hope that our resources can be leveraged at other institutions and even other non-pathology clerkship/elective rotations to promote active engagement of students in clinical workflows while providing clear expectations for grading.

Utility of Machine Learning to Detect Cytomegalovirus in Digital Hematoxylin and Eosin-Stained Slides.

Rapid and accurate cytomegalovirus (CMV) identification in immunosuppressed or immunocompromised patients presenting with diarrhea is essential for therapeutic management. Due to viral latency, however, the gold standard for CMV diagnosis remains to identify viral cytopathic inclusions on routine hematoxylin and eosin (H&E)-stained tissue sections. Therefore, biopsies may be taken and "rushed" for pathology evaluation. Here, we propose the use of artificial intelligence to detect CMV inclusions on routine H&E-stained whole-slide images to aid pathologists in evaluating these cases. Fifty-eight representative H&E slides from 30 cases with CMV inclusions were identified and scanned. The resulting whole-slide images were manually annotated for CMV inclusions and tiled into 300 × 300 pixel patches. Patches containing annotations were labeled "positive," and these tiles were oversampled with image augmentation to account for class imbalance. The remaining patches were labeled "negative." Data were then divided into training, validation, and holdout sets. Multiple deep learning models were provided with training data, and their performance was analyzed. All tested models showed excellent performance. The highest performance was seen using the EfficientNetV2BO model, which had a test (holdout) accuracy of 99.93%, precision of 100.0%, recall (sensitivity) of 99.85%, and area under the curve of 0.9998. Of 518,941 images in the holdout set, there were only 346 false negatives and 2 false positives. This shows proof of concept for the use of digital tools to assist pathologists in screening "rush" biopsies for CMV infection. Given the high precision, cases screened as "positive" can be quickly confirmed by a pathologist, reducing missed CMV inclusions and improving the confidence of preliminary results. Additionally, this may reduce the need for immunohistochemistry in limited tissue samples, reducing associated costs and turnaround time.

Knowledge-guided analysis of "omics" data using the KnowEnG cloud platform.

We present Knowledge Engine for Genomics (KnowEnG), a free-to-use computational system for analysis of genomics data sets, designed to accelerate biomedical discovery. It includes tools for popular bioinformatics tasks such as gene prioritization, sample clustering, gene set analysis, and expression signature analysis. The system specializes in "knowledge-guided" data mining and machine learning algorithms, in which user-provided data are analyzed in light of prior information about genes, aggregated from numerous knowledge bases and encoded in a massive "Knowledge Network." KnowEnG adheres to "FAIR" principles (findable, accessible, interoperable, and reuseable): its tools are easily portable to diverse computing environments, run on the cloud for scalable and cost-effective execution, and are interoperable with other computing platforms. The analysis tools are made available through multiple access modes, including a web portal with specialized visualization modules. We demonstrate the KnowEnG system's potential value in democratization of advanced tools for the modern genomics era through several case studies that use its tools to recreate and expand upon the published analysis of cancer data sets.