87 citations · 115 across the 12 of their papers we have counts for
5 papers · 1 filter
Extremely weakly-supervised blood vessel segmentation with physiologically based synthesis and domain adaptation
Peidi Xu, Olga Sosnovtseva, Charlotte Mehlin Sørensen +2
Accurate analysis and modeling of renal functions require a precise segmentation of the renal blood vessels. Micro-CT scans provide image data at higher resolutions, making more sm…
cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule Diagnosis
Jiahao Lu, Chong Yin, Kenny Erleben +2
Recently, attempts have been made to reduce annotation requirements in feature-based self-explanatory models for lung nodule diagnosis. As a representative, cRedAnno achieves compe…
Auto-segmentation of Hip Joints using MultiPlanar UNet with Transfer learning
Peidi Xu, Faezeh Moshfeghifar, Torkan Gholamalizadeh +3
Accurate geometry representation is essential in developing finite element models. Although generally good, deep-learning segmentation approaches with only few data have difficulti…
Reducing Annotation Need in Self-Explanatory Models for Lung Nodule Diagnosis
Jiahao Lu, Chong Yin, Oswin Krause +3
Feature-based self-explanatory methods explain their classification in terms of human-understandable features. In the medical imaging community, this semantic matching of clinical…
A direct geometry processing cartilage generation method using segmented bone models from datasets with poor cartilage visibility
Faezeh Moshfeghifar, Max Kragballe Nielsen, José D. Tascón-Vidarte +2
We present a method to generate subject-specific cartilage for the hip joint. Given bone geometry, our approach is agnostic to image modality, creates conforming interfaces, and is…