The purpose of this study is to present and compare three denoising diffusion probabilistic models (DDPMs) that generate 3D $T_1$-weighted MRI human brain images. Three DDPMs were trained using 80,675 image volumes from 42,406 subjects spanning 38 publicly available brain MRI datasets. These images had approximately 1 mm isotropic resolution and were manually inspected by three human experts to exclude those with poor quality, field-of-view issues, and excessive pathology. The images were minimally preprocessed to preserve the visual variability of the data. Furthermore, to enable the DDPMs to produce images with natural orientation variations and inhomogeneity, the images were neither registered to a common coordinate system nor bias field corrected. Evaluations included segmentation, Frechet Inception Distance (FID), and qualitative inspection. Regarding results, all three DDPMs generated coherent MR brain volumes. The velocity and flow prediction models achieved lower FIDs than the sample prediction model. However, all three models had higher FIDs compared to real images across multiple cohorts. In a permutation experiment, the generated brain regional volume distributions differed statistically from real data. However, the velocity and flow prediction models had fewer statistically different volume distributions in the thalamus and putamen. In conclusion this work presents and releases the first 3D non-latent diffusion model for brain data without skullstripping or registration. Despite the negative results in statistical testing, the presented DDPMs are capable of generating high-resolution 3D $T_1$-weighted brain images. All model weights and corresponding inference code are publicly available at https://github.com/piksl-research/medforj .

When conducting large-scale studies that collect brain MR images from multiple facilities, the impact of differences in imaging equipment and protocols at each site cannot be ignored, and this domain gap has become a significant issue in recent years. In this study, we propose a new low-dimensional representation (LDR) acquisition method called style encoder adversarial domain adaptation (SE-ADA) to realize content-based image retrieval (CBIR) of brain MR images. SE-ADA reduces domain differences while preserving pathological features by separating domain-specific information from LDR and minimizing domain differences using adversarial learning. In evaluation experiments comparing SE-ADA with recent domain harmonization methods on eight public brain MR datasets (ADNI1/2/3, OASIS1/2/3/4, PPMI), SE-ADA effectively removed domain information while preserving key aspects of the original brain structure and demonstrated the highest disease search accuracy.

The genome sequence contains the blueprint for governing cellular processes. While the availability of genomes has vastly increased over the last decades, experimental annotation of the various functional, non-coding and regulatory elements encoded in the DNA sequence remains both expensive and challenging. This has sparked interest in unsupervised language modeling of genomic DNA, a paradigm that has seen great success for protein sequence data. Although various DNA language models have been proposed, evaluation tasks often differ between individual works, and might not fully recapitulate the fundamental challenges of genome annotation, including the length, scale and sparsity of the data. In this study, we introduce BEND, a Benchmark for DNA language models, featuring a collection of realistic and biologically meaningful downstream tasks defined on the human genome. We find that embeddings from current DNA LMs can approach performance of expert methods on some tasks, but only capture limited information about long-range features. BEND is available at https://github.com/frederikkemarin/BEND.

ELLIS (European Laboratory for Learning and Intelligent Systems) is a European initiative in AI with a focus on scientific excellence, innovation and societal impact. The initiative unites many of the leading machine learning researchers in Europe and aims to create a pan-European AI Lab. The ELLIS Institute Tübingen is sponsored with a 100 Mio EUR endowment from the Hector Foundation. We will be located near Stuttgart in the historic city of Tübingen, a beautiful university town in the southwest of Germany, tucked against a vast nature park. Major cities including Zurich, Munich and Frankfurt are within a few hours by public transportation.

A new study published by experts in Singapore suggests that an artificial intelligence (AI) platform that identifies patient-specific drug combinations can help those whose lymphomas have relapsed. The paper, published in the journal Science Translational Medicine on October 19, is the first study demonstrating the feasibility of personalized drug combination prediction for patients with lymphoma, and utilizes a novel method called QPOP (quadratic phenotypic optimization platform) that is developed in the National University of Singapore (NUS). The method involves collecting a small tumor sample from a patient and incubating this in a laboratory with a set of 12 carefully selected drugs used for lymphoma. After 72 hours, QPOP then ranks the patient's cancer cells' potential response to more than 750 distinct drug combinations of up to four drugs, using these 12 possible drugs. This clinical application study of QPOP, the first-of-its-kind, was a collaboration between clinicians at the National University Cancer Institute, Singapore (NCIS) and scientists from the Cancer Science Institute of Singapore (CSI Singapore) at NUS.

The promise of artificial intelligence to solve problems in drug design, discover how babies learn language, and make progress in many other areas has been stymied by the inability of humans to understand what's going on inside AI systems. Researchers at six universities, including The University of Texas at Austin, are launching a partnership aimed at turning these AI "black boxes" into human-interpretable computer code, allowing them to solve hitherto unsolvable problems. The new partnership, called Understanding the World Through Code, is made possible by a major new grant from the National Science Foundation, through its Expeditions in Computing program. This initiative is focused on "ambitious fundamental research agendas that promise to define the future of computing and information." These grants, given to just three teams every two years, are the largest given by the NSF's Directorate for Computer and Information Science and Engineering.

However, as we grow older, our bodies become less energy efficient, turning simple daily activities like walking around a block into a daunting effort. Although the effect of aging on the energetic costs of walking is well-documented, we do not yet have a complete understanding of what causes the progressive increase in energetic cost. One of the challenges to understanding this phenomenon is that current technologies for assessing metabolic energy consumption require measuring several minutes of breathing. These measurements are too slow to gain insight into the energetic cost of different phases of the gait cycle. The Disability and Rehabilitation Engineering program (DARE) and the Established Program to Stimulate Competitive Research (EPSCoR) from the National Science Foundation (NSF) are funding a collaborative project at the University of Nebraska at Omaha (UNO) and at the University of Nebraska at Lincoln (UNL) aimed at investigating the metabolic cost of different phases of the walking gait cycle. It is expected that this inter-campus collaboration between researchers from different disciplines will enable the development more creative solutions than single-discipline research.

As a step toward improving our ability to identify and manage the harmful effects of bias in artificial intelligence (AI) systems, researchers at the National Institute of Standards and Technology (NIST) recommend widening the scope of where we look for the source of these biases -- beyond the machine learning processes and data used to train AI software to the broader societal factors that influence how technology is developed. The recommendation is a core message of a revised NIST publication, Towards a Standard for Identifying and Managing Bias in Artificial Intelligence (NIST Special Publication 1270), which reflects public comments the agency received on its draft version released last summer. As part of a larger effort to support the development of trustworthy and responsible AI, the document offers guidance connected to the AI Risk Management Framework that NIST is developing. According to NIST's Reva Schwartz, the main distinction between the draft and final versions of the publication is the new emphasis on how bias manifests itself not only in AI algorithms and the data used to train them, but also in the societal context in which AI systems are used. "Context is everything," said Schwartz, principal investigator for AI bias and one of the report's authors.

We are a world class research-intensive university. We deliver teaching and learning of the highest quality. We play a leading role in economic, social and cultural development of the North East of England. Attracting and retaining high-calibre people is fundamental to our continued success. We are delighted to be seeking a motivated individual to join our project, in the School of Computing.

… by imaging from multiple brain sites in a circuit, and using machine learning algorithms (AI) to automatically extract and measure social …