Qi, Yunzhe; Zhou, Qinghai; Liu, Boyang; Cui, Can; Zheng, Hua; Suo, Qiuling; Liang, Mingfu; Lov, Kenny; Liu, Xi; Jiang, Shali; Chen, Laming; Chen, Wen-Yen; Jin, Rong; Chang, Shuo; He, Jingrui; Li, Huayu. (2026).��.��Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2-B, 4000–4011.��

Multiple sclerosis (MS) lesions can interfere with automated MRI analysis, while limited labeled data make it difficult to train models that accurately detect these lesions. We developed MSRepaint, an AI-based imaging method that can both fill lesion-affected areas with realistic healthy-appearing tissue and generate synthetic lesions for training purposes. The method preserves surrounding brain anatomy and can work when some MRI inputs are unavailable. In testing, MSRepaint outperformed established lesion-filling methods and achieved accuracy comparable to a recent AI-based approach while processing images more than 20 times faster. Models trained using its synthetic lesions also performed better across multiple lesion-detection datasets than models trained with other synthetic or real training data. MSRepaint therefore provides a fast, flexible approach for improving MRI analysis and generating realistic training data for MS lesion detection.

Fig. 1.��Overview of MSRepaint training and inference. (a) Training data: A 2D multicontrast image��𝑥0��undergoes forward diffusion, generating noisy images��𝑥𝑡−1,��𝑥𝑡, and the final degraded image��𝑥𝑇, paired with its lesion mask��𝑀. (b) Training: The denoiser��𝜙𝑤��is trained to estimate��ˆ𝑥𝑡−1��from��𝑥𝑡��with guidance from mask��𝑀. (c) Inference: The trained denoiser��𝜙𝑤∗��generates outputs guided by��𝑀target, while the repaint mask��𝑀repaint��restricts updates to its region, preserving surrounding tissue. A repainting mechanism iteratively refines update boundaries to ensure seamless integration with the surrounding tissue. (d) Example tasks: Lesion filling sets��𝑀target=0��to replace lesions with healthy tissue, while lesion synthesis sets��𝑀target=𝑀repaint��to generate new lesion patterns.

Artificial intelligence is allowing surgical robots to perform some tasks with limited direct control from surgeons. However, patients’ willingness to undergo surgery involving semi-autonomous robots may influence how widely these technologies are adopted. This study explored patients’ views about the ethical concerns surrounding semi-autonomous robot-assisted surgery and how these concerns affect their willingness to undergo such procedures. Researchers interviewed 50 adults who had undergone surgery within the previous three years, either without a robot or with a robot that was not autonomous. Overall, 56% said they would be willing to undergo semi-autonomous robot-assisted surgery, although willingness depended on which parts of the procedure the robot controlled. Four main factors shaped participants’ views: having enough information to make an informed decision, concerns about new risks introduced by robotic autonomy, trust and the relationship between patients and surgeons, and the potential benefits of robotic technology. Patients also considered the balance of control between the surgeon and robot important. These findings suggest that many patients may be open to semi-autonomous robot-assisted surgery, but acceptance depends on clear informed consent, confidence in safety, trust in surgeons, and understanding the technology’s potential benefits.

Fig 2 . Percent of participants by their willingness to undergo semi-autonomous robot-assisted surgery and by the type of control the robot would have over the different types of surgical processes

Health data are increasingly collected and shared across healthcare, research, and artificial intelligence (AI) applications, creating new opportunities for medical discovery and clinical decision-making. At the same time, these uses raise growing concerns about privacy, security, and trust. This review examines risks and protections throughout the health data life cycle, from their initial collection and use in healthcare to their later use in research and AI development. We discuss how regulations, organizational practices, and technology influence data protection, as well as emerging risks such as unintended disclosure of sensitive information through AI tools. We review methods for protecting health data, including controlling and monitoring access, assessing the risk that individuals could be re-identified, using statistical privacy techniques such as differential privacy, and generating synthetic data that resemble real data without directly representing individual patients. We also discuss approaches that allow organizations to collaborate without directly sharing sensitive data, including federated learning and secure cryptographic methods. These approaches involve important trade-offs between protecting privacy and preserving the usefulness of data. Overall, greater standardization, transparency, and practical guidance are needed to strengthen privacy and trust while supporting responsible use of health data in healthcare, research, and AI.

Figure 1 Simplified representation of different stages in the health data flow with potential risks and mitigation strategies. In the data-generation stage, health data are generated by individuals (e.g., patients). In the primary use stage (pink), data are collected for care by healthcare organizations or third-party systems. In the secondary use stage (yellow), data are shared and analyzed to accelerate knowledge discovery.

Ashwin, T. S.; Sanda, Nihar; Coursey, Austin; Gupta, Vaibhav; Biswas, Gautam. (2026).��.��Proceedings of the ACM Symposium on Applied Computing, 87–94.��

Franklin, Jacob; Chu, Ling; McDonald, Samuel A.; Turer, Robert W.; Webb, Janet; Steitz, Bryan D.; Yi, Haoyang; Chen, Qingxia; McCoy, Allison B.; Nall, Carolynn; Chen, Catherine; Rousseau, Justin F.; Lehmann, Christoph U.; Willett, Duwayne L.; Kumah-Crystal, Yaa A.; Mize, Dara E. (2026).��.��Discover Artificial Intelligence, 6(1), 550.��

This study addresses the challenge of��automatic polyp segmentation, the process of identifying and outlining polyps in colonoscopy images. While many artificial intelligence (AI) models perform well on the data they were trained on, they often struggle when tested on images from different hospitals or datasets because polyps can vary widely in size, shape, color, and appearance. Differences in image quality, such as glare from reflected light, blur, fluid, and changes in lighting during colonoscopy, add to this challenge. To improve performance across different datasets, the researchers developed��HAT-SAM3, an adaptation of the��Segment Anything Model 3 (SAM 3), a large pre-trained AI model originally designed for image segmentation. HAT-SAM3 uses a training technique called��highlight-aware training (HAT), which helps the model better handle bright reflections commonly seen in endoscopy images without changing how the model operates during testing. When evaluated on five publicly available datasets, HAT-SAM3 achieved an average��Dice score(a measure of how closely the model’s predicted outlines match the true polyp boundaries) of 0.884 and produced the best reported results on four of the five datasets. In additional testing, where the model was trained on one dataset and evaluated on three completely separate datasets without further training, HAT-SAM3 consistently outperformed the strongest previously reported method. These results suggest that adapting a pre-trained foundation model with endoscopy-specific training techniques can improve the accuracy and reliability of automated polyp segmentation across a wide range of clinical datasets. The researchers have also made their code publicly available to support future research.

Fig 1: Motivation of HAT-SAM3. A task-specific polyp segmenter can perform well when training and test images come from the same visual distribution, but degrade under cross-domain changes in illumination, blur, specular reflection, and polyp appearance. HAT-SAM3 uses a broad segmentation prior with endoscopy-aware adaptation to improve cross-domain polyp segmentation

Research on artificial intelligence tools that help clinicians make decisions has had mixed results: sometimes these tools improve decision-making, and sometimes they do not, and it is not always clear why. This review looked at what factors affect how well AI-based clinical decision-support systems, or AI-CDS, work in medicine. The authors searched three medical databases and found 45 relevant studies out of 5,850 screened articles. They focused on how both clinician factors and technology design features influenced three things: how clinicians feel about AI, whether they accept AI recommendations, and how well they perform when using AI. The review found that experienced clinicians may gain less from AI support than less experienced clinicians, although the results were not consistent across studies. It also found that explainable AI, meaning AI that gives reasons for its suggestions, can increase trust, but it may also lead clinicians to trust incorrect recommendations too much, which can hurt performance when humans and AI work together. Clinicians’ existing attitudes toward AI also influenced whether they accepted its advice. Overall, the review suggests that future research should focus on “appropriate trust,” meaning clinicians should rely on AI only when the advice is actually trustworthy, rather than simply trying to increase trust in AI overall.

Figure 1.

PRISMA diagram for study inclusion.

Agentic AI��refers to systems that can set their own goals, adapt to new situations, and improve over time through experience. This study explores how such systems can learn more efficiently by sharing knowledge with one another, instead of learning everything from scratch. In particular, it looks at how an AI agent can decide��what knowledge to reuse, which other agents to learn from, and how to incorporate that knowledge��into its own decision-making process (often called a��policy, or strategy for choosing actions).

The researchers introduce a new method called��MOSAIC (Modular Sharing and Composition in Collective Learning). This approach allows agents to compare tasks using mathematical representations, select useful knowledge from others based on performance and similarity, and integrate it using flexible, modular neural network components. In simple terms, agents can “borrow” and adapt pieces of what others have already learned.

The results show that agents using MOSAIC learn faster and perform better than those learning alone or sharing information indiscriminately. In some cases, they can even solve problems that individual agents cannot. The study also finds that targeted, selective sharing reduces confusion between tasks and leads to a kind of��self-organization, where agents working on easier problems help others tackle more complex ones. Overall, this work highlights the potential of collaborative learning strategies to make AI systems more efficient and adaptable.

Skyler Grandel; Scott Thomas Andersen; Yu Huang; Kevin Leach (2026).��.��ACM Transactions on Software Engineering and Methodology, 35(3), Article 82.��