Follow-up imaging and surgical costs associated with different guidelines for management of incidentally detected gallbladder polyps.

RATIONALE AND OBJECTIVES: To compare follow-up imaging and surgical cost implications of the Society of Radiologists in Ultrasound (SRU) guidelines, 2017 and 2022 European (EUR) guidelines, 2020 Canadian Association of Radiologists (CAR) recommendations, and 2013 American College of Radiology (ACR) White Paper for managing incidentally detected gallbladder polyps. MATERIALS AND METHODS: 253 consecutive patients with gallbladder polyps identified on ultrasound were independently reviewed by three radiologists for polyp size and morphology. Electronic medical records were reviewed for patient demographics, cholecystectomy (if performed) pathological findings, or any subsequent diagnosis of gallbladder cancer. For each patient, the following were calculated for each of the 5 guidelines studied: 1) number of recommended follow-up ultrasounds based on initial presentation, 2) number of surgical consultations recommended based on initial presentation, 3) number of surgical consultations recommended based on growth, and 4) associated imaging and surgical costs. Interrater agreement was calculated. RESULTS: The SRU 2022 guidelines suggested significantly fewer follow-up ultrasounds and surgical consultations, leading to a cost reduction of 96.5 % and 96.7 % compared to European 2022 and 2017, respectively; 86.5 % compared to CAR; and 86.2 % compared to ACR guidelines. With SRU Recommendations, the majority of gallbladder polyps would be classified as extremely low risk (68.4 %), 30.8 % low risk, and 0.8 % indeterminate risk. In our cohort, a single case of gallbladder cancer was identified (26 mm) which would be recommended for surgical consult by all guidelines. CONCLUSION: The SRU 2022 guidelines can lead to significant savings for patients, health systems, and society, while reducing unnecessary medical interventions for managing incidentally detected gallbladder polyps.

Critical Advances for Democratizing Ultrasound Diagnostics in Human and Veterinary Medicine.

The democratization of ultrasound imaging refers to the process of making ultrasound technology more accessible. Traditionally, ultrasound imaging has been predominately used in specialized medical facilities by trained professionals. Advancements in technology and changes in the health-care landscape have inspired efforts to broaden the availability of ultrasound imaging to various settings such as remote and resource-limited areas. In this review, we highlight several key factors that have contributed to the ongoing democratization of ultrasound imaging, including portable and handheld devices, recent advancements in technology, and training and education. Examples of diagnostic point-of-care ultrasound (POCUS) imaging used in emergency and critical care, gastroenterology, musculoskeletal applications, and other practices are provided for both human and veterinary medicine. Open challenges and the future of POCUS imaging are presented, including the emerging role of artificial intelligence in technology development.

Validation and tuning of in situ transcriptomics image processing workflows with crowdsourced annotations.

Recent advancements in in situ methods, such as multiplexed in situ RNA hybridization and in situ RNA sequencing, have deepened our understanding of the way biological processes are spatially organized in tissues. Automated image processing and spot-calling algorithms for analyzing in situ transcriptomics images have many parameters which need to be tuned for optimal detection. Having ground truth datasets (images where there is very high confidence on the accuracy of the detected spots) is essential for evaluating these algorithms and tuning their parameters. We present a first-in-kind open-source toolkit and framework for in situ transcriptomics image analysis that incorporates crowdsourced annotations, alongside expert annotations, as a source of ground truth for the analysis of in situ transcriptomics images. The kit includes tools for preparing images for crowdsourcing annotation to optimize crowdsourced workers' ability to annotate these images reliably, performing quality control (QC) on worker annotations, extracting candidate parameters for spot-calling algorithms from sample images, tuning parameters for spot-calling algorithms, and evaluating spot-calling algorithms and worker performance. These tools are wrapped in a modular pipeline with a flexible structure that allows users to take advantage of crowdsourced annotations from any source of their choice. We tested the pipeline using real and synthetic in situ transcriptomics images and annotations from the Amazon Mechanical Turk system obtained via Quanti.us. Using real images from in situ experiments and simulated images produced by one of the tools in the kit, we studied worker sensitivity to spot characteristics and established rules for annotation QC. We explored and demonstrated the use of ground truth generated in this way for validating spot-calling algorithms and tuning their parameters, and confirmed that consensus crowdsourced annotations are a viable substitute for expert-generated ground truth for these purposes.