XFlow improves lesion segmentation in chest X-rays with stepwise refinement
XFlow: A Workflow Model for Instruction-Guided Lesion Segmentation in Chest X-rays
Computer Vision and Pattern Recognition
Summary
Segmenting lesions in chest X-rays is hard because many models only detect a fixed set of features and assume those features are always present. The authors highlight that current models often produce noisy segmentations and do everything in one step, unlike radiologists who first locate then refine lesion boundaries. They introduce XFlow, which mimics this by combining lung detection, presence checking, and iteratively improving the lesion mask. Tests show that XFlow produces better and clearer lesion outlines than earlier methods.
What this means in practice
- •For medical imaging software developers: Integrate XFlow to enhance lesion outlining accuracy in chest X-ray analysis tools by mimicking radiologists' stepwise review process.
- •For healthcare ai service providers: Offer more reliable and interpretable lesion segmentation services for chest X-rays by adopting XFlow’s iterative refinement workflow.$Commercial implications: XFlow enables improved lesion segmentation products for hospitals and clinics, increasing diagnostic accuracy and confidence.
Authors
Geon Choi, Hangyul Yoon, Hyunki Park, Sang Hoon Seo, Edward Choi
Abstract
Existing text-guided segmentation models in the medical domain cover only a narrow set of anatomical structures and lesions in chest X-rays (CXRs), and most of them assume that the queried target is always present in the image. Instruction-guided lesion segmentation (ILS) was introduced to overcome these limitations by segmenting diverse lesion types from simple user instructions while also recognizing when the queried lesion is absent, and ROSALIA was proposed as the first model for this task. However, the masks produced by ROSALIA remain of limited quality, often carrying scattered noise. Moreover, ROSALIA predicts the mask in a single shot, which differs fundamentally from how radiologists perceive and delineate lesions in practice. A radiologist first surveys the entire thorax, then localizes the approximate region of abnormality, and only then refines the lesion contour. Motivated by this coarse-to-fine, multi-level perception process, we present XFlow, a workflow model for ILS that combines box-based localization with multi-turn point refinement. XFlow detects the lungs, decides whether the queried finding is present in each of them, and prompts a fine-tuned SAM with the lesion box for an initial mask. It then corrects that mask through point prompts until its boundary follows the lesion, leaving every intermediate decision visible. Our experiments show that XFlow achieves the best segmentation quality on both internal and external evaluation. Notably, it surpasses ROSALIA in segmentation quality even when the two are trained on the same lesion annotations. Code and model weights will be made publicly available.