Tilo Niemann | Searcharxiv

arXiv2026

Bowel Obstruction Detection and Localization on Abdominal CT with Deep Learning

Bowel obstruction is a common and potentially life-threatening gastrointestinal condition. In the face of rising diagnostic workloads, the automated diagnosis of bowel obstruction on CT scans supports radiologists by accelerating detection and improving patient outcomes. In this work, we propose a deep learning framework with a multi-task objective that jointly detects bowel obstruction and localizes its transition zone. Additionally, we extend the method with an inherently interpretable classification method that locates the suspected transition point within a slice. It does so by learning a probabilistic selection mask that faithfully bases the classifier's prediction solely on a small image region. The proposed method is evaluated on an internal dataset comprising 1,427 abdominal CTs. Here, the model achieves an obstruction detection test accuracy of 93% and a Hit@10 transition zone localization of 95%. As the first method to reliably localize the transition zone, this marks a significant step towards the automated identification of this critical clinical landmark.

cs.CV↗

arXiv2023

Refraction beats attenuation in breast CT

For a century, clinical X-ray imaging has visualised only the attenuation properties of tissue, which fundamentally limits the contrast, particularly in soft tissues like the breast. Imaging based on refraction can overcome this limitation, but so far has been constrained to high-dose ex-vivo applications or required highly coherent X-ray sources, like synchrotrons. It has been predicted that grating interferometry (GI) could eventually allow computed tomography (CT) to be more dose-efficient. However, the benefit of refraction in clinical CT has not been demonstrated so far. Here we show that GI-CT is more dose-efficient in imaging of breast tissue than conventional CT. Our system, based on a 70kVp X-ray tube source and commercially available gratings, demonstrated superior quality, in terms of adipose-to-glandular tissue contrast-to-noise ratio (CNR), of refraction-contrast compared to the attenuation images. The fusion of the two modes of contrast outperformed conventional CT for spatial resolutions better than 263μm and an average dose to the breast of 16mGy, which is in the clinical breast CT range. Our results show that grating interferometry can significantly reduce the dose, while maintaining the image quality, in diagnostic breast CT. Unlike conventional absorption-based CT, the sensitivity of refraction-based imaging is far from being fully exploited, and further progress will lead to significant improvements of clinical X-ray CT.

physics.med-ph↗