CST: A Multitask Learning Framework for Colorectal Cancer Region Mining Based on Transformer

Colorectal cancer is a high death rate cancer until now; from the clinical view, the diagnosis of the tumour region is critical for the doctors. But with data accumulation, this task takes lots of time and labor with large variances between different doctors. With the development of computer vision, detection and segmentation of the colorectal cancer region from CT or MRI image series are a great challenge in the past decades, and there still have great demands on automatic diagnosis. In this paper, we proposed a novel transfer learning protocol, called CST, that is, a union framework for colorectal cancer region detection and segmentation task based on the transformer model, which effectively constructs the cancer region detection and its segmentation jointly. To make a higher detection accuracy, we incorporate an autoencoder-based image-level decision approach that leverages the image-level decision of a cancer slice. We also compared our framework with one-stage and two-stage object detection methods; the results show that our proposed method achieves better results on detection and segmentation tasks. And this proposed framework will give another pathway for colorectal cancer screen by way of artificial intelligence.

Cost effectiveness of DPYD genotyping to screen for dihydropyrimidine dehydrogenase (DPD) deficiency prior to adjuvant chemotherapy for colon cancer.

55 Background: Fluoropyrimidine chemotherapy agents, including 5-fluorouracil and capecitabine, are the backbone of adjuvant treatment for colon cancer, and adjuvant chemotherapy substantially reduces recurrence and mortality after surgical resection of stage 3 colon cancer. While fluoropyrimidine chemotherapy is generally safe, the risk of severe, potentially fatal chemotherapy toxicity is substantially increased for the 2-3% of U.S. patients with DPD deficiency caused by pathogenic variants in the DPYD gene. DPYD genotype testing is readily available in the U.S. but has not been widely adopted. We evaluated the cost effectiveness of DPYD genotyping prior to adjuvant chemotherapy for colon cancer in the U.S. Methods: We constructed a Markov model to simulate screening for DPD deficiency with DPYD genotyping (versus no screening) among patients receiving fluoropyrimidine-based adjuvant chemotherapy for stage 3 colon cancer. Screen-positive patients were modeled to receive dose-reduced fluoropyrimidine chemotherapy. Model transition probabilities for treatment-related toxicities were derived from published clinical trial data with annotation of DPYD genotype and chemotherapy dosing strategy. Our analysis is from the healthcare perspective, with a time horizon of five years and an annual discount rate of 3% for future costs and benefits. Direct healthcare costs and health utilities were estimated from published sources and converted to 2020 US dollars, and post-treatment survival was modeled from SEER data. The primary outcome was the incremental cost-effectiveness ratio (ICER), defined as dollars per quality-adjusted life year (QALY). We used a value of $100,000/QALY as the cost-effectiveness threshold. One-way sensitivity analyses were used to examine model uncertainty. Results: Compared with no screening, screening for DPD deficiency with DPYD genotyping increased per-patient costs by $106 and improved quality-adjusted survival by 0.0028 QALYs, leading to an ICER of $37,300/QALY. In one-way sensitivity analyses, the ICER exceeded $100,000/QALY when the carrier frequency of pathogenic DPYD gene variants was less than 1.17%, and when the specificity of DPYD genotyping was less than 98.9%. Cost-effectiveness estimates were not sensitive to the cost of DPYD genotyping, the cost of toxicity-related hospitalizations, or the health utility associated with grade 3-4 toxicity. Conclusions: Among patients receiving adjuvant chemotherapy for stage 3 colon cancer, screening for DPD deficiency with DPYD genotyping is a cost-effective strategy for preventing infrequent but severe, sometimes fatal toxicities of fluoropyrimidine chemotherapy.

From potential to practice: how accelerating access to HPV tests and screen and treat programmes can help eliminate cervical cancer

Human papillomavirus (HPV) vaccination campaigns to prevent cervical cancer are being considered and implemented in countries around the world. While vaccination will protect future generations, it will not help the millions of women currently infected, leading to an estimated 311 000 deaths per year globally. This paper examines a selection of strategies that when applied to both existing and new technologies, could accelerate access to HPV testing. Authors from the US Agency for International Development, the National Institutes of Health, and the Bridge to Health Medical and Dental, a non-governmental organisation, joined forces to propose a scalable and country-directed solution for preventing cervical cancer using an end-to-end approach. Collectively, the authors offer seven evidence-based strategies, that when used alone or in combination have the ability to reduce HPV-caused cervical cancer deaths and disability. These strategies include (1) consistent HPV test intervals to decrease HPV DNA test costs; (2) exploring market shaping opportunities; (3) employing iterative user research methodologies like human-centred design; (4) target product profiles for new HPV tests; (5) encouraging innovation around cervical cancer screen and treat programmes; (6) developing national cancer control plans; and (7) integrating cervical cancer screen and treat services into existing infrastructure. By using the strategies outlined here, in combination with HPV vaccination campaigns, national governments will be able to scale and expand cervical cancer screening programmes and provide evidence-based treatment programmes for HPV-infected women.

2020 The clinical implications of a positive prostate cancer screen in patients undergoing a cardiac transplant evaluation

OBJECTIVES/SPECIFIC AIMS: Screening the general population for prostate cancer with prostate specific antigen (PSA) continues to be controversial. Patients with advanced heart failure undergoing evaluation for suitability for cardiac transplantation are often requested to undergo prostate cancer screening, with guiding evidence generated from the general population. The objective of this study is to determine the clinical implications of a positive prostate cancer screen result in this patient population. METHODS/STUDY POPULATION: A retrospective cohort study was performed on all men that were referred to a tertiary care cardiac transplant center between January 2000 and December 2015. Patients were classified as having either a “positive screen” (PSA≥4 ng/mL) or a “negative screen” (PSA<4 ng/mL) at the point of evaluation. The primary outcome of time to listing for cardiac transplant (days) was calculated from the date of referral to the date of listing. A multivariable Cox proportional hazards model was developed to assess the association between a positive prostate cancer test result and listing for cardiac transplantation. RESULTS/ANTICIPATED RESULTS: Among the 704 patients included in this study, 66 men (9.4%) had a positive prostate cancer screen result. Men with a positive prostate cancer screen were approximately 4 year older (mean 58.5 vs. 54.1 years), more likely to have a diagnosis of Ischemic Cardiomyopathy (74% vs. 53%) and require continuous mechanical support (61% vs. 16%) at the point of transplant evaluation. The median time for listing for cardiac transplant was greater in patients with a positive PSA (119 vs. 48 days, p<0.05). After adjusting for age, renal function, clinical status at evaluation, history of COPD, and year of referral, patients with a positive prostate cancer screen had a reduced hazards ratio (HR) for progressing to cardiac transplant listing compared with those with a negative screen (HR 0.58, 95%CI: 0.38–0.91). DISCUSSION/SIGNIFICANCE OF IMPACT: Screening patients undergoing cardiac transplant evaluation for prostate cancer with PSA has a low diagnostic yield. An individual’s PSA value is influenced by their age and clinical status at the time of screening, with a positive screen being associated with a reduced likelihood for progressing to listing for cardiac transplant.