Area Under News Today

Our roundup of the latest news from metro Detroit and Michigan businesses as well as announcements from government agencies.

Researchers developed Prov-GigaPath, a whole-slide pathology foundation model using a novel vision transformer architecture. The model demonstrates superior performance in mutation prediction, cancer subtyping, and vision-language tasks. It leverages large-scale real-world data from over 30,000 patients to enhance clinical diagnostics.

A study in the Journal of Clinical Endocrinology & Metabolism found that body fat percentage (%BF) thresholds are more accurate than BMI for predicting obesity-related health conditions, suggesting new standards for defining overweight and obesity.

- From research to real-world impact: Lunit demonstrates Lunit INSIGHT's clinical safety, effectiveness, and efficiency in 100 papers

Chronic heart diseases are a leading cause of death worldwide. This paper examines recently published articles on the use of AI and machine-learning to detect chronic heart diseases. The main findings of these papers are summarised to assist researchers in developing new technology using AI and machine learning. The summary includes information on the technologies used in each research paper, the year of publication, the type of heart disease, the machine learning techniques employed and the adv...

AI-based tools enhance early sepsis detection, leveraging EMR data and machine learning for timely treatment and improved outcomes.

Lunit to unveil four oral presentations and three poster presentations at ECR 2024, highlighting Lunit INSIGHT's expansive capability, rang...

Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, today announced the presentation of seven studies at the European Congress of Radiology (ECR) 2024, to be held in Vienna, Austria, from February 28 to March 3. Four will be presented through oral presentations and three as E-posters.

Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, today announced the presentation of seven studies at the European Congress...

[Special thank you to Ian Kivlichan for many useful pointers (E.g. the 100+ year old Nature paper “Vox populi”) and nice feedback. �� ] High-quality data is the fuel for modern data deep learning model training. Most of task-specific labeled data comes from human annotation, such as classification task or RLHF labeling (which can be constructed as classification format) for LLM alignment training. Lots of ML techniques in the post can help with data quality, but fundamentally...