arXiv subjects

Christina Bornberg

Publications and source records attributed to Christina Bornberg.

5 recordsLinked to original sources

arXiv2026

Modelling Geographic Atrophy Progression using Implicit Neural Representations

Age-related Macular Degeneration (AMD) is the major cause of blindness in the Western world. Its late dry phase is characterised by irreversible atrophic areas, namely Geographic Atrophy (GA). Longitudinal Fundus Autofluorescence (FAF) image acquisitions are currently the main tool for assessing lesion growth over time at the image level. However, due to its highly individualised progression, the evolution of late AMD remains poorly understood. In this work, we propose using Implicit Neural Representations (INRs) to model GA progression at the individual level in a low-data setting. Our approach generates both FAF and GA segmentation at both past and future time points. Among the comparison models, our method achieves competitive segmentation quality across different scenarios, yielding the lowest Mean Absolute Error (MAE) for the GA lesion area and the highest DICE score, without sacrificing FAF image quality. The code is available at https://github.com/SimoneSarrocco/ga-progression-with-inrs.

cs.CV↗

arXiv2025

GAUDA: Generative Adaptive Uncertainty-guided Diffusion-based Augmentation for Surgical Segmentation

Augmentation by generative modelling yields a promising alternative to the accumulation of surgical data, where ethical, organisational and regulatory aspects must be considered. Yet, the joint synthesis of (image, mask) pairs for segmentation, a major application in surgery, is rather unexplored. We propose to learn semantically comprehensive yet compact latent representations of the (image, mask) space, which we jointly model with a Latent Diffusion Model. We show that our approach can effectively synthesise unseen high-quality paired segmentation data of remarkable semantic coherence. Generative augmentation is typically applied pre-training by synthesising a fixed number of additional training samples to improve downstream task models. To enhance this approach, we further propose Generative Adaptive Uncertainty-guided Diffusion-based Augmentation (GAUDA), leveraging the epistemic uncertainty of a Bayesian downstream model for targeted online synthesis. We condition the generative model on classes with high estimated uncertainty during training to produce additional unseen samples for these classes. By adaptively utilising the generative model online, we can minimise the number of additional training samples and centre them around the currently most uncertain parts of the data distribution. GAUDA effectively improves downstream segmentation results over comparable methods by an average absolute IoU of 1.6% on CaDISv2 and 1.5% on CholecSeg8k, two prominent surgical datasets for semantic segmentation.

cs.CV↗

arXiv2022

Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images

In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a first step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscope. Thus, human fatigue plays a role in error making, making the use of deep learning appealing. Due to the high cost of training data annotation, an approach without manual annotation is needed. We propose Seamless Iterative Semi-Supervised correction of Imperfect labels (SISSI), a new method for training object detection models with noisy and missing annotations in a semi-supervised fashion. Our network learns from noisy labels generated with simple image processing algorithms, which are iteratively corrected during self-training. Due to the nature of missing bounding boxes in the pseudo labels, which would negatively affect the training, we propose to train on dynamically generated synthetic-like images using seamless cloning. Our method successfully provides an adaptive early learning correction technique for object detection. The combination of early learning correction that has been applied in classification and semantic segmentation before and synthetic-like image generation proves to be more effective than the usual semi-supervised approach by > 15% AP and > 20% AR across three different readers. Our code is available at https://github.com/marwankefah/SISSI.

eess.IV↗

arXiv2021

The Arcanum Mission: Scientific Objectives and Instruments for Neptune, Triton and KBOs

The Arcanum mission is a proposed L-class spacecraft that highlights the revolutionary approach which can now be taken to future space mission design. Using the case of the SpaceX Starship vehicle and in particular the high mass and volume characteristics of this launcher, the feasible large size of future missions, even with high delta-V transfer requirements, are analysed. A demonstrator vehicle, designed to support a large and capable science platform with multiple components, is detailed, clearly showing the range and depth of science goals that will be answerable thanks to the current revolution in super heavy-lift launch vehicles.

astro-ph.IM↗

arXiv2021

An L-class Multirole Observatory and Science Platform for Neptune

A coming resurgence of super heavy-lift launch vehicles has precipitated an immense interest in the future of crewed spaceflight and even future colonisation efforts. While it is true that a bright future awaits this sector, driven by commercial ventures and the reignited interest of old space-faring nations, and the joining of new ones, little of this attention has been reserved for the science-centric applications of these launchers. The Arcanum mission is a proposal to use these vehicles to deliver an L-class observatory into a highly eccentric orbit around Neptune, with a wide-ranging suite of science goals and instrumentation tackling Solar System science, planetary science, Kuiper Belt Objects and exoplanet systems.

astro-ph.IM↗