Artificial Intelligence Medical Compendium

Automated treatment planning (ATP) aims to reduce the unwarranted inter-planner variability of manual planning, while improving treatment quality and efficiency. Most ATP pipelines rely on the prediction of the achievable three-dimensional dose distr... read more 

Synthetic data provides the means for more ethical and less biased facial recognition. Nonetheless, the limitations of generative models and the conditioning process they rely on pose a risk of identity leakage, resulting in synthetic samples that ar... read more 

Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image that reflects an intended textual modification while maintaining semantic consistency with a reference image. Existing training-free ZS-CIR methods typically rely on fine-gra... read more 

This work presents a novel open-source toolkit designed for the evaluation of face deidentification techniques with available evaluation models. The framework provides a complete evaluation pipeline, including preprocessing, deidentification, and per... read more 

Video overlay removal aims to recover scenes obscured by subtitles, titles, and logos while preserving surrounding content. Existing methods use temporal propagation or source-conditioned generation, but can leave residual overlays and distort scene ... read more 

Autonomous clinical-modeling agents can optimize predictive performance while violating conditions that make a model usable. We introduce LeakBench, an executable, guideline-derived audit suite that tests agent decisions for prediction-time leakage, ... read more 

Autonomous vehicles must detect objects faster than a frame camera delivers images. Event cameras record brightness changes with microsecond resolution, so RGB--event detectors can decide between frames, at an operating frequency, the rate of decisio... read more 

Disentangled real-image manipulation requires factor-specific semantic control while preserving image fidelity and non-target content. StyleSpace $S$ provides interpretable controls but is limited by GAN inversion, whereas diffusion models offer stro... read more 

Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed the association of 463 radiomic, anatomical and clinical features from pre-trea... read more 

Learning from Demonstration (LfD) allows robots to learn new skills from human examples; however, many vision-based methods require large datasets and resource-intensive end-to-end training. This paper introduces a data-efficient LfD framework for hu... read more