Medical imaging is essential in modern radiotherapy, supporting diagnosis, treatment planning, and monitoring. Synthetic imaging, particularly synthetic computed tomography (sCT), is gaining traction in radiotherapy. The SynthRAD2025 dataset and Grand Challenge promote advancements in sCT generation by providing a benchmarking platform for algorithms using cone-beam CT (CBCT) and magnetic resonance imaging (MRI). The dataset includes 2362 cases: 890 MRI-CT and 1472 CBCT-CT pairs from head-and-neck, thoracic, and abdominal cancer patients treated at five European university medical centers (UMC Groningen, UMC Utrecht, Radboud UMC, LMU University Hospital Munich, and University Hospital of Cologne). Data were acquired with diverse scanners and protocols. Pre-processing, including rigid and deformable image registration, ensures high-quality, modality-aligned images. Extensive quality assurance validates image consistency and usability. All imaging data is provided in MetaImage (.mha) format, ensuring compatibility with medical image processing tools. Metadata, including acquisition parameters and registration details, is available in structured CSV files. To maintain dataset integrity, SynthRAD2025 is divided into training (65%), validation (10%), and test (25%) sets. The dataset is accessible at https://doi.org/10.5281/zenodo.14918089 under the SynthRAD2025 collection. This dataset supports benchmarking and the development of synthetic imaging techniques for radiotherapy applications. Use cases include sCT generation for MRI-only and MR-guided photon/proton therapy, CBCT-based dose calculations, and adaptive radiotherapy workflows. By integrating diverse acquisition settings, SynthRAD2025 fosters robust, generalizable image synthesis algorithms, advancing personalized cancer care and adaptive radiotherapy.

Sharing retrospectively acquired data is essential for both clinical research and training. Synthetic Data Generation (SDG), using Artificial Intelligence (AI) models, can overcome privacy barriers in sharing clinical data, enabling advancements in medical diagnostics. This study focuses on the clinical evaluation of medical SDG, with a proof-of-concept investigation on diagnosing Inflammatory Bowel Disease (IBD) using Wireless Capsule Endoscopy (WCE) images. The paper contributes by a) presenting a protocol for the systematic evaluation of synthetic images by medical experts and b) applying it to assess TIDE-II, a novel variational autoencoder-based model for high-resolution WCE image synthesis, with a comprehensive qualitative evaluation conducted by 10 international WCE specialists, focusing on image quality, diversity, realism, and clinical decision-making. The results show that TIDE-II generates clinically relevant WCE images, helping to address data scarcity and enhance diagnostic tools. The proposed protocol serves as a reference for future research on medical image-generation techniques.

The progression of X-ray technology introduces diverse image styles that need to be adapted to the preferences of radiologists. To support this task, we introduce a novel deep learning-based metric that quantifies style differences of non-matching image pairs. At the heart of our metric is an encoder capable of generating X-ray image style representations. This encoder is trained without any explicit knowledge of style distances by exploiting Simple Siamese learning. During inference, the style representations produced by the encoder are used to calculate a distance metric for non-matching image pairs. Our experiments investigate the proposed concept for a disclosed reproducible and a proprietary image processing pipeline along two dimensions: First, we use a t-distributed stochastic neighbor embedding (t-SNE) analysis to illustrate that the encoder outputs provide meaningful and discriminative style representations. Second, the proposed metric calculated from the encoder outputs is shown to quantify style distances for non-matching pairs in good alignment with the human perception. These results confirm that our proposed method is a promising technique to quantify style differences, which can be used for guided style selection as well as automatic optimization of image pipeline parameters.

Deep learning has shown to have great potential in medical applications. In critical domains as such, it is of high interest to have trustworthy algorithms which are able to tell when reliable assessments cannot be guaranteed. Detecting out-of-distribution (OOD) samples is a crucial step towards building a safe classifier. Following a previous study, showing that it is possible to classify breast cancer in point-of-care ultrasound images, this study investigates OOD detection using three different methods: softmax, energy score and deep ensembles. All methods are tested on three different OOD data sets. The results show that the energy score method outperforms the softmax method, performing well on two of the data sets. The ensemble method is the most robust, performing the best at detecting OOD samples for all three OOD data sets.

The Scandinavian leaders of AI in breast imaging presented their research at the ScreenPoint symposium at EUSOBI 2022 in Malmo, Sweden. Dr Kristina Lang presented the MASAI trial, the first prospective randomized controlled trial on the use of AI in breast screening as an alternative for double reading. Based on her previous retrospective studies, she is convinced that AI could lead to a more efficient and more effective screening programme. In the MASAI trial at Unilabs/Skane University Hospital Malmo, women are randomly assigned to a control arm where exams are double read as usual, or to the AI-based intervention arm: Transpara triages screening exams based on risk for malignancy and assigns 90% of all screening cases to single reading, and 10% to double reading. In addition, the top 1% most suspicious cases are automatically recalled.

Artificial intelligence through machine learning is increasingly used in the digital society. Solutions based on machine learning bring both great opportunities, thus coined "Software 2.0," but also great challenges for the engineering community to tackle. Due to the experimental approach used by data scientists when developing machine learning models, agility is an essential characteristic. In this keynote address, we discuss two contemporary development phenomena that are fundamental in machine learning development, i.e., notebook interfaces and MLOps. First, we present a solution that can remedy some of the intrinsic weaknesses of working in notebooks by supporting easy transitions to integrated development environments. Second, we propose reinforced engineering of AI systems by introducing metaphorical buttresses and rebars in the MLOps context. Machine learning-based solutions are dynamic in nature, and we argue that reinforced continuous engineering is required to quality assure the trustworthy AI systems of tomorrow.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. To investigate how an artificial intelligence (AI) system performs on digital mammography (DM) from a screening population with ground truth defined by digital breast tomosynthesis (DBT), and whether AI could detect breast cancers on DM that had originally only been detected on DBT. In this secondary analysis of data from a prospective study, DM examinations from 14768 women (mean age, 57 years), examined with both DM and DBT with independent double reading in the Malmö Breast Tomosynthesis Screening Trial (MBTST; ClinicalTrials.gov

Developed by experts from Sweden's Lund University, the approach has the potential to speed up diagnoses while removing the need for costly, specialist equipment. At present, some 20–30 per cent of patients with Alzheimer's disease are misdiagnosed in specialist care alone, let alone primary care, the team noted. A new tool -- using just a blood test (pictured) and a quick set of cognitive tests -- can predict whether someone will develop Alzheimer's in four years with 90 per cent accuracy'Our algorithm is based on a blood analysis of phosphylated rope and a risk gene for Alzheimer's, as well as testing of memory and executive ability,' said neurologist Sebastian Palmqvist of Lund University and the Skåne University Hospital. 'We have developed an online tool to calculate the risk at the individual level that a person with mild memory difficulties will develop Alzheimer's within four years.' In their study, Professor Palmqvist and colleagues examined 340 people with mild memory difficulties who had been recruited into the Swedish BioFINDER Study into neurodegenerative diseases and 543 people from North America.

Artificial Intelligence (AI) is increasingly used in critical applications. Thus, the need for dependable AI systems is rapidly growing. In 2018, the European Commission appointed experts to a High-Level Expert Group on AI (AI-HLEG). AI-HLEG defined Trustworthy AI as 1) lawful, 2) ethical, and 3) robust and specified seven corresponding key requirements. To help development organizations, AI-HLEG recently published the Assessment List for Trustworthy AI (ALTAI). We present an illustrative case study from applying ALTAI to an ongoing development project of an Advanced Driver-Assistance System (ADAS) that relies on Machine Learning (ML). Our experience shows that ALTAI is largely applicable to ADAS development, but specific parts related to human agency and transparency can be disregarded. Moreover, bigger questions related to societal and environmental impact cannot be tackled by an ADAS supplier in isolation. We present how we plan to develop the ADAS to ensure ALTAI-compliance. Finally, we provide three recommendations for the next revision of ALTAI, i.e., life-cycle variants, domain-specific adaptations, and removed redundancy.

Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated environments such as OpenAI Gym, Atari Learning Environment, or Malmo which allow agents to learn complex tasks through interaction with virtual environments. While RL is also increasingly applied to natural language processing (NLP), there are no simulated textual environments available for researchers to apply and consistently benchmark RL on NLP tasks. With the work reported here, we therefore release NLPGym, an open-source Python toolkit that provides interactive textual environments for standard NLP tasks such as sequence tagging, multi-label classification, and question answering. We also present experimental results for 6 tasks using different RL algorithms which serve as baselines for further research. The toolkit is published at https://github.com/rajcscw/nlp-gym