arXiv subjects

Jochen Hampe

Publications and source records attributed to Jochen Hampe.

5 recordsLinked to original sources

arXiv2026

Reliable Mislabel Detection for Video Capsule Endoscopy Data

The classification performance of deep neural networks relies strongly on access to large, accurately annotated datasets. In medical imaging, however, obtaining such datasets is particularly challenging since annotations must be provided by specialized physicians, which severely limits the pool of annotators. Furthermore, class boundaries can often be ambiguous or difficult to define which further complicates machine learning-based classification. In this paper, we want to address this problem and introduce a framework for mislabel detection in medical datasets. This is validated on the two largest, publicly available datasets for Video Capsule Endoscopy, an important imaging procedure for examining the gastrointestinal tract based on a video stream of lowresolution images. In addition, potentially mislabeled samples identified by our pipeline were reviewed and re-annotated by three experienced gastroenterologists. Our results show that the proposed framework successfully detects incorrectly labeled data and results in an improved anomaly detection performance after cleaning the datasets compared to current baselines.

cs.CV↗

arXiv2025

Seeing More with Less: Video Capsule Endoscopy with Multi-Task Learning

Video capsule endoscopy has become increasingly important for investigating the small intestine within the gastrointestinal tract. However, a persistent challenge remains the short battery lifetime of such compact sensor edge devices. Integrating artificial intelligence can help overcome this limitation by enabling intelligent real-time decision-making, thereby reducing the energy consumption and prolonging the battery life. However, this remains challenging due to data sparsity and the limited resources of the device restricting the overall model size. In this work, we introduce a multi-task neural network that combines the functionalities of precise self-localization within the gastrointestinal tract with the ability to detect anomalies in the small intestine within a single model. Throughout the development process, we consistently restricted the total number of parameters to ensure the feasibility to deploy such model in a small capsule. We report the first multi-task results using the recently published Galar dataset, integrating established multi-task methods and Viterbi decoding for subsequent time-series analysis. This outperforms current single-task models and represents a significant advance in AI-based approaches in this field. Our model achieves an accuracy of 93.63% on the localization task and an accuracy of 87.48% on the anomaly detection task. The approach requires only 1 million parameters while surpassing the current baselines.

cs.CV↗

arXiv2025

Enhanced Anomaly Detection for Capsule Endoscopy Using Ensemble Learning Strategies

Capsule endoscopy is a method to capture images of the gastrointestinal tract and screen for diseases which might remain hidden if investigated with standard endoscopes. Due to the limited size of a video capsule, embedding AI models directly into the capsule demands careful consideration of the model size and thus complicates anomaly detection in this field. Furthermore, the scarcity of available data in this domain poses an ongoing challenge to achieving effective anomaly detection. Thus, this work introduces an ensemble strategy to address this challenge in anomaly detection tasks in video capsule endoscopies, requiring only a small number of individual neural networks during both the training and inference phases. Ensemble learning combines the predictions of multiple independently trained neural networks. This has shown to be highly effective in enhancing both the accuracy and robustness of machine learning models. However, this comes at the cost of higher memory usage and increased computational effort, which quickly becomes prohibitive in many real-world applications. Instead of applying the same training algorithm to each individual network, we propose using various loss functions, drawn from the anomaly detection field, to train each network. The methods are validated on the two largest publicly available datasets for video capsule endoscopy images, the Galar and the Kvasir-Capsule dataset. We achieve an AUC score of 76.86% on the Kvasir-Capsule and an AUC score of 76.98% on the Galar dataset. Our approach outperforms current baselines with significantly fewer parameters across all models, which is a crucial step towards incorporating artificial intelligence into capsule endoscopies.

cs.CV↗

arXiv2024

Supporting Risk Management for Medical Devices via the Riskman Ontology and Shapes (Preprint)

We propose the Riskman ontology and shapes for representing and analysing information about risk management for medical devices. Risk management is concerned with taking necessary precautions to ensure that a medical device does not cause harms for users or the environment. To date, risk management documentation is submitted to notified bodies (for certification) in the form of semi-structured natural language text. We propose to use terms from the Riskman ontology to provide a formal, logical underpinning for risk management documentation, and to use the included SHACL constraints to check whether the provided data is in accordance with the requirements of the two relevant norms, i.e. ISO 14971 and VDE Spec 90025.

cs.AI↗

arXiv2017

Increased hepatic PDGF-AA signaling mediates liver insulin resistance in obesity associated type 2 diabetes

Type 2 diabetes (T2D) is closely linked with non-alcoholic fatty liver disease (NAFLD) and hepatic insulin resistance, but the involved mechanisms are still elusive. Using DNA methylome and transcriptome analyses of livers from obese individuals, we found that both hypomethylation at a CpG site in PDGFA (encoding platelet derived growth factor alpha) and PDGFA overexpression are associated with increased T2D risk, hyperinsulinemia, increased insulin resistance and increased steatohepatitis risk. Both genetic risk score studies and human cell modeling pointed to a causative impact of high insulin levels on PDGFA CpG site hypomethylation, PDGFA overexpression, and increased PDGF-AA secretion from liver. We found that PDGF-AA secretion further stimulates its own expression through protein kinase C activity and contributes to insulin resistance through decreased expression of both insulin receptor substrate 1 and of insulin receptor. Importantly, hepatocyte insulin sensitivity can be restored by PDGF-AA blocking antibodies, PDGF receptor inhibitors and by metformin opening therapeutic avenues. Conclusion: Therefore, in the liver of obese patients with T2D, the increased PDGF-AA signaling contributes to insulin resistance, opening new therapeutic avenues against T2D and NAFLD.

q-bio.CB↗