Trustworthy multi-phase liver tumor segmentation via evidence-based uncertainty

Biomedical imaging is a driver of scientific discovery and a core component of medical care and is being stimulated by the field of deep learning. While semantic segmentation algorithms enable image analysis and quantification in many applications, the design of respective specialized solutions is non-trivial and highly dependent on dataset properties and hardware conditions. We developed nnU-Net, a deep learning-based segmentation method that automatically configures itself, including preprocessing, network architecture, training and post-processing for any new task. The key design choices in this process are modeled as a set of fixed parameters, interdependent rules and empirical decisions. Without manual intervention, nnU-Net surpasses most existing approaches, including highly specialized solutions on 23 public datasets used in international biomedical segmentation competitions. We make nnU-Net publicly available as an out-of-the-box tool, rendering state-of-the-art segmentation accessible to a broad audience by requiring neither expert knowledge nor computing resources beyond standard network training. Show more

Background & Aims The burden of liver cancer varies across the world. Herein, we present updated estimates of the current global burden of liver cancer (incidence and mortality) and provide predictions of the number of cases/deaths to 2040. Methods We extracted data on primary liver cancer cases and deaths from the GLOBOCAN 2020 database, which includes 185 countries. Age-standardised incidence and mortality rates (ASRs) per 100,000 person-years were calculated. Cases and deaths up to the year 2040 were predicted based on incidence and mortality rates for 2020 and global demographic projections to 2040. Results In 2020, an estimated 905,700 people were diagnosed with, and 830,200 people died from, liver cancer globally. Global ASRs for liver cancer were 9.5 and 8.7 for new cases and deaths, respectively, per 100,000 people and were highest in Eastern Asia (17.8 new cases, 16.1 deaths), Northern Africa (15.2 new cases, 14.5 deaths), and South-Eastern Asia (13.7 new cases, 13.2 deaths). Liver cancer was among the top three causes of cancer death in 46 countries and was among the top five causes of cancer death in 90 countries. ASRs of both incidence and mortality were higher among males than females in all world regions (male:female ASR ratio ranged between 1.2–3.6). The number of new cases of liver cancer per year is predicted to increase by 55.0% between 2020 and 2040, with a possible 1.4 million people diagnosed in 2040. A predicted 1.3 million people could die from liver cancer in 2040 (56.4% more than in 2020). Conclusions Liver cancer is a major cause of death in many countries, and the number of people diagnosed with liver cancer is predicted to rise. Efforts to reduce the incidence of preventable liver cancer should be prioritised. Lay summary The burden of liver cancer varies across the world. Liver cancer was among the top three causes of cancer death in 46 countries and was among the top five causes of cancer death in 90 countries worldwide. We predict the number of cases and deaths will rise over the next 20 years as the world population grows. Primary liver cancer due to some causes is preventable if control efforts are prioritised and the predicted rise in cases may increase the need for resources to manage care of patients with liver cancer. • 905,700 people were diagnosed with and 830,200 people died from liver cancer globally in 2020. • Liver cancer was among the top three causes of cancer death in 46 countries. • The number of new cases and deaths from liver cancer could rise by >55% by 2040. Show more

The Liver Imaging Reporting and Data System (LI-RADS) is composed of four individual algorithms intended to standardize the lexicon, as well as reporting and care, in patients with or at risk for hepatocellular carcinoma in the context of surveillance with US; diagnosis with CT, MRI, or contrast material-enhanced US; and assessment of treatment response with CT or MRI. This report provides a broad overview of LI-RADS, including its historic development, relationship to other imaging guidelines, composition, aims, and future directions. In addition, readers will understand the motivation for and key components of the 2018 update. Show more