Background: Automated pathology techniques for detecting cervical cancer at the premalignant stage have advantages for women in areas with limited medical resources. Methods: This article presents EpithNet, a deep learning approach for the critical step of automated epithelium segmentation in digitized cervical histology images. EpithNet employs three regression networks of varying dimensions of image input blocks (patches) surrounding a given pixel, with all blocks at a fixed resolution, using varying network depth. Results: The proposed model was evaluated on 311 digitized histology epithelial images and the results indicate that the technique maximizes region-based information to improve pixel-wise probability estimates. EpithNet-mc model, formed by intermediate concatenation of the convolutional layers of the three models, was observed to achieve 94% Jaccard index (intersection over union) which is 26.4% higher than the benchmark model. Conclusions: EpithNet yields better epithelial segmentation results than state-of-the-art benchmark methods.

Background: Cervical screening could potentially be improved by better stratifying individual risk for the development of cervical cancer or precancer, possibly even allowing follow-up of individual patients differently than proposed under current guidelines that focus primarily on recent screening test results. We explore the use of a Bayesian decision science model to quantitatively stratify individual risk for the development of cervical squamous neoplasia. Materials and Methods: We previously developed a dynamic multivariate Bayesian network model that uses cervical screening and histopathologic data collected over 13 years in our system to quantitatively estimate the risk of individuals for the development of cervical precancer or invasive cervical cancer. The database includes 1,126,048 liquid-based cytology test results belonging to 389,929 women. From-the-vial, high risk human papilloma virus (HPV) test results and follow-up gynecological surgical procedures were available on 33.6% and 12% of these results (378,896 and 134,727), respectively. Results: Historical data impacted 5-year cumulative risk for both histopathologic cervical intraepithelial neoplasia 3 (CIN3) and squamous cell carcinoma (SCC) diagnoses. The risk was highest in patients with prior high grade squamous intraepithelial lesion cytology results. Persistent abnormal cervical screening test results, either cytologic or HPV results, were associated with variable increasing risk for squamous neoplasia. Risk also increased with prior histopathologic diagnoses of precancer, including CIN2, CIN3, and adenocarcinoma in situ. Conclusions: Bayesian modeling allows for individualized quantitative risk assessments of system patients for histopathologic diagnoses of significant cervical squamous neoplasia, including very rare outcomes such as SCC.

Background: Laboratory tests are among the most ordered tests and account for a large portion of wasted health-care spending. Meta-analyses suggest that the most promising interventions at improving health-care value and reducing cost are low investment strategies involving simple changes to ordering systems. The veterans affairs (VA) has a 2018–2024 strategic objective to reduce wasted spending through data- and performance-focused decision-making. Methods: VA Palo Alto Healthcare System laboratory utilization data were obtained from multiple sources, including the VA Corporate Data Warehouse and utilization reports from reference laboratory. Ordering volume, test results, and follow-up clinical impact data were collected and evaluated in partnership with the treating physicians and hospital informatics in order to optimize ordering sets. Results: Dextromethorphan (Dext) and synthetic cannabinoid testing were identified as the lowest value tests based on a three-tier score of negativity rate, volume, and cost. In partnership with the ordering physicians and hospital informatics, reflexive testing was eliminated, resulting in persistent decreases in the volume of Dext (162–10 tests/month) and synthetic cannabinoid tests (155–19 tests/month) ordered. The proportion of unnecessary repeat tests also dropped from 71.5% to 5.5%, the test positivity rate increased from 0.87% to 3.49%, and the approximate monthly cost of both tests decreased ten-fold from $21,250 to $2087 for a yearly savings of $229,000 at a single VA. Conclusions: Improved laboratory utilization is central to the VA' strategic objective to reduce waste. A relatively simple intervention involving partnership with the treating physicians and hospital informatics in combination with data- and performance-focused decision-making can yield substantial reductions in health-care waste.