Researchers at Johns Hopkins are developing AI-driven video analysis tools to provide surgeons with unbiased skill assessments and personalized feedback. The system segments surgical procedures, detects instruments, and assesses skill in cataract surgery. Dr. Shameema Sikder is leading the development of technologies to improve ophthalmic surgical care standards internationally. Why it matters: AI-based surgical skill assessment could standardize training and improve patient outcomes in the region and globally.
Researchers from MBZUAI introduced RP-SAM2, a method to improve surgical instrument segmentation by refining point prompts for more stable results. RP-SAM2 uses a novel shift block and compound loss function to reduce sensitivity to point prompt placement, improving segmentation accuracy in data-constrained settings. Experiments on the Cataract1k and CaDIS datasets show that RP-SAM2 enhances segmentation accuracy and reduces variance compared to SAM2, with code available on GitHub.
This paper introduces a method for automatically designing convolutional neural network (CNN) architectures tailored for diabetic retinopathy (DR) diagnosis using fundus images. The approach uses k-medoid clustering, PCA, and inter/intra-class variations to optimize CNN depth and width. Validated on datasets including a local Saudi dataset and Kaggle benchmarks, the custom-designed models outperform pre-trained CNNs with fewer parameters.
Dr. Andrew Bastawrous, CEO/co-founder of Peek, discussed his work on mobile eye clinics at KAUST. He developed Peek Acuity and Peek Retina, which turn smartphones into tools for detecting visual impairment. The technology uses smartphone screens and camera clip-ons to image inside the eye. Why it matters: This low-cost mobile ophthalmic tool has the potential to prevent and treat vision loss in underserved communities.
This paper introduces a domain generalization (DG) method for Diabetic Retinopathy (DR) classification that maximizes mutual information using a large pretrained model. The method aims to address the challenge of domain shift in medical imaging caused by variations in data acquisition. Experiments on public datasets demonstrate that the proposed method outperforms state-of-the-art techniques, achieving a 5.25% improvement in average accuracy.
KAUST hosted the New Challenges in Heterogeneous Catalysis research conference from January 29-31. The conference brought together catalysis researchers from KAUST and abroad to inspire future research and discuss challenges in heterogeneous catalysis. Discussions focused on new chemistry, catalytic materials, understanding catalytic processes, and activation of small molecules like methane and carbon dioxide. Why it matters: Catalysis research is crucial for KAUST's research thrusts in food, water, energy, and environment, contributing to sustainable development and green chemistry in the region.
The study compares deep learning models trained via transfer learning from ImageNet (TII-models) against those trained solely on medical images (LMI-models) for disease segmentation. Results show that combining outputs from both model types can improve segmentation performance by up to 10% in certain scenarios. A repository of models, code, and over 10,000 medical images is available on GitHub to facilitate further research.