Retinal fundus images play a crucial role in the early detection of eye diseases. However, the impact of technical factors on these images can pose challenges for reliable AI applications in ophthalmology. For example, large fundus cohorts are often confounded by factors such as camera type, bearing the risk of learning shortcuts rather than the causal relationships behind the image generation process. Here, we introduce a population model for retinal fundus images that effectively disentangles patient attributes from camera effects, enabling controllable and highly realistic image generation. To achieve this, we propose a disentanglement loss based on distance correlation. Through qualitative and quantitative analyses, we show that our models encode desired information in disentangled subspaces and enable controllable image generation based on the learned subspaces, demonstrating the effectiveness of our disentanglement loss. The project code is publicly available at https://github.com/berenslab/disentangling-retinal-images.

The Fundus Image Toolbox is an open source Python suite of tools for working with retinal fundus images. It includes quality prediction, fovea and optic disc center localization, blood vessel segmentation, image registration, and fundus cropping functions. It also provides a collection of useful utilities for image manipulation and image-based PyTorch models. The toolbox is designed to be flexible and easy to use, thus helping to speed up research workflows. It is available as a PyPI package and at https://github.com/berenslab/fundus_image_toolbox. Statement of need In ophthalmic research, retinal fundus images are often used as a resource for studying various eye diseases such as diabetic retinopathy, glaucoma and age-related macular degeneration. Consequently, there is a large amount of research on machine learning for fundus image analysis. However, many of the works do not publish their source code, and very few of them provide ready-to-use open source preprocessing tools to the community.

Automated organ segmentation is a prerequisite for efficient analysis of MR data in large cohorts with thousands of participants. The feasibility and generalizability of previously proposed methods has mostly been demonstrated in smaller cohorts. The aim of this work is to implement and validate automated semantic 3D segmentation of liver and spleen on multi-contrast MR data of the body trunk which were acquired in a large epidemiological imaging study with the objective to provide a robust and general setup in a setting of limited training data. Liver and spleen were manually segmented in 173 MR images by an experienced radiologist, providing labeled ground-truth. Varying amount of training datasets were randomly chosen to train a convolutional neural network (CNN)-based segmentation with 4-fold patient-leave-out cross-validation and compared against a Random Forest (RF)-based segmentation. Validation amongst participants revealed high accuracies of 99.7%/99.9% for liver/spleen-segmentation with superiority of CNN to RF. In conclusion, automated semantic organ segmentation is feasible in a robust and general setup.

Osteoporosis may alter mandibular bone structure and peri-implant remodeling, but it remains unclear whether such changes are detectable on dental radiographs using deep learning. This retrospective study evaluated whether osteoporosis can be discriminated in two mandibular regions of interest: peri-implant bone and the mental foramen region. Digital periapical radiographs acquired between November 2012 and October 2024 were analyzed in 51 women, including 25 patients with osteoporosis and 26 non-osteoporotic controls without a documented history or diagnosis of osteoporosis; the osteoporosis group was significantly older than the control group. Two binary classification experiments were performed using patient-level fivefold grouped cross-validation. The peri-implant experiment included 1682 cropped images and used an image-plus-metadata ResNet-18 model incorporating the time interval between implant placement and radiograph acquisition. The mental foramen experiment included 102 cropped images and used an image-only ResNet-18 model. Mean accuracy, F1 score, and area under the receiver operating characteristic curve were 0.613, 0.628, and 0.713 for the peri-implant region of interest (ROI) and 0.701, 0.713, and 0.744 for the mental foramen ROI, respectively. Both experiments showed substantial fold-to-fold variability. These findings suggest that ROI selection influences model behavior, but neither approach yielded sufficiently stable ROI-level classification performance under patient-level grouped validation to support individual patient-level screening claims. Nondiscriminatory AI results should therefore be interpreted as limited evidence under the present experimental conditions rather than as proof of radiographic equivalence.