The field of medical imaging and anomaly detection is rapidly evolving, with a focus on developing more accurate and robust models for disease diagnosis and detection. Recent research has highlighted the importance of fairness and generalization in medical imaging AI, with studies exploring the use of disentanglement techniques to mitigate bias in image-trained models. Another key area of development is the creation of more comprehensive and systematic benchmarks for evaluating anomaly detection methods, allowing for more accurate comparisons and advancements in the field. Additionally, there is a growing trend towards integrating multiple omics approaches, such as imaging and lipidomics, to reveal new insights into disease pathogenesis and identify potential biomarkers. Noteworthy papers include: Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams, which evaluates the fairness and performance of image-trained models in diabetic retinopathy prediction. BenchReAD, which introduces a comprehensive benchmark for retinal anomaly detection and proposes a new state-of-the-art method, NFM-DRA.