Aug 2026· Tomography· Vol 12, pp. 125· 0 citations· 19 references
Medicine
TL;DR
An open, freely available software pipeline is built that uses deep-learning segmentation to outline each abdominal organ on routine CT images and then derives a patient-specific, organ-level dose index directly from data the scanner already records.
Abstract
Simple Summary CT scanners report a single dose number for the whole scan, yet the dose is delivered unevenly across organs. We built an open, freely available software pipeline that uses deep-learning segmentation to outline each abdominal organ on routine CT images and then derives a patient-specific, organ-level dose index directly from data the scanner already records. Across scans from four manufacturers, we found that this organ-level information can be recovered for some scanners but is entirely absent for others because the values it needs were not kept in the archived scan records. All software, results, and data provenance are fully open, so the work can be reproduced and extended.
Objective. Pediatric pancreas CT segmentation is challenging because developmental anatomy and scan-protocol variability jointly affect organ size, image appearance, and boundary visibility. This study evaluated whether explicitly incorporating anatomy-related and scan-related case-level descriptors could improve pedia...
Wen-Bo Xiong, Nian Liu, Han-Ran Yan et al.· Physics in Medicine and Biol...· 0 citations
One 3D multitask model per modality can rapidly recover patient and acquisition characteristics from heterogeneous CT and MR examinations and outperformed a segmentation-derived XGBoost baseline for all four core targets in both modalities.
J. Wasserthal, Joshy Cyriac, Michael Bach et al.· 0 citations
In comparison to the current state-of-the-art deep learning-based segmentation models, the proposed system surpasses them, highlighting its potential and reliability in precisely segmenting liver regions in CT volumes.
Ahmed Semida, A. Sharafeldeen, Hanan M. Amer et al.· Scientific Reports· 0 citations
Reliable clot-volume quantification and subsequent risk assessment in pulmonary embolism depend on precise segmentation of emboli on computed tomography pulmonary angiography. Deep learning models for this task must be trained on accurate voxel-level labels. The three public datasets that provide such labels were annot...
Qihang Sun, Zhong-Xiao Liu, Bailiang Jian et al.· 0 citations
Visual grounding models can enhance radiology workflows by linking report findings to image regions. This is particularly valuable for 3D CT, where findings often occupy a tiny fraction of the volume. Training 3D grounding models requires large sets of paired phrases and regions, and building such datasets is expensive...
Samuel Church, Danyal Maqbool, Joshua D. Warner et al.· 0 citations
Deep Learning-based analysis of CT topograms with DICOM-derived spatial geometry, enables reliable and reproducible image-based anatomical labelling of CT series, reducing reliance on inconsistent DICOM attributes and improving data consistency and scalability for clinical applications.
Yu-Tong Wen, Judith Kohnke, V. Parmar et al.· European Radiology· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
