Salvato in:
Dettagli Bibliografici
Autori principali: Isler, Ilkin Sevgi, Mohaisen, David, Lisle, Curtis, Turgut, Damla, Bagci, Ulas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.12215
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911035742486528
author Isler, Ilkin Sevgi
Mohaisen, David
Lisle, Curtis
Turgut, Damla
Bagci, Ulas
author_facet Isler, Ilkin Sevgi
Mohaisen, David
Lisle, Curtis
Turgut, Damla
Bagci, Ulas
contents Reliable tumor segmentation in thoracic computed tomography (CT) remains challenging due to boundary ambiguity, class imbalance, and anatomical variability. We propose an uncertainty-guided, coarse-to-fine segmentation framework that combines full-volume tumor localization with refined region-of-interest (ROI) segmentation, enhanced by anatomically aware post-processing. The first-stage model generates a coarse prediction, followed by anatomically informed filtering based on lung overlap, proximity to lung surfaces, and component size. The resulting ROIs are segmented by a second-stage model trained with uncertainty-aware loss functions to improve accuracy and boundary calibration in ambiguous regions. Experiments on private and public datasets demonstrate improvements in Dice and Hausdorff scores, with fewer false positives and enhanced spatial interpretability. These results highlight the value of combining uncertainty modeling and anatomical priors in cascaded segmentation pipelines for robust and clinically meaningful tumor delineation. On the Orlando dataset, our framework improved Swin UNETR Dice from 0.4690 to 0.6447. Reduction in spurious components was strongly correlated with segmentation gains, underscoring the value of anatomically informed post-processing.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12215
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Uncertainty-Guided Coarse-to-Fine Tumor Segmentation with Anatomy-Aware Post-Processing
Isler, Ilkin Sevgi
Mohaisen, David
Lisle, Curtis
Turgut, Damla
Bagci, Ulas
Computer Vision and Pattern Recognition
Artificial Intelligence
Reliable tumor segmentation in thoracic computed tomography (CT) remains challenging due to boundary ambiguity, class imbalance, and anatomical variability. We propose an uncertainty-guided, coarse-to-fine segmentation framework that combines full-volume tumor localization with refined region-of-interest (ROI) segmentation, enhanced by anatomically aware post-processing. The first-stage model generates a coarse prediction, followed by anatomically informed filtering based on lung overlap, proximity to lung surfaces, and component size. The resulting ROIs are segmented by a second-stage model trained with uncertainty-aware loss functions to improve accuracy and boundary calibration in ambiguous regions. Experiments on private and public datasets demonstrate improvements in Dice and Hausdorff scores, with fewer false positives and enhanced spatial interpretability. These results highlight the value of combining uncertainty modeling and anatomical priors in cascaded segmentation pipelines for robust and clinically meaningful tumor delineation. On the Orlando dataset, our framework improved Swin UNETR Dice from 0.4690 to 0.6447. Reduction in spurious components was strongly correlated with segmentation gains, underscoring the value of anatomically informed post-processing.
title Uncertainty-Guided Coarse-to-Fine Tumor Segmentation with Anatomy-Aware Post-Processing
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.12215