Edge2Prompt: Modality-Agnostic Model for Out-of-Distribution Liver Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hollet, Nathan, Cherkaoui, Oumeymah, Cattin, Philippe C., Hadramy, Sidaty El
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918121997074432
author Hollet, Nathan
Cherkaoui, Oumeymah
Cattin, Philippe C.
Hadramy, Sidaty El
author_facet Hollet, Nathan
Cherkaoui, Oumeymah
Cattin, Philippe C.
Hadramy, Sidaty El
contents Liver segmentation is essential for preoperative planning in interventions like tumor resection or transplantation, but implementation in clinical workflows faces challenges due to modality-specific tools and data scarcity. We propose Edge2Prompt, a novel pipeline for modality-agnostic liver segmentation that generalizes to out-of-distribution (OOD) data. Our method integrates classical edge detection with foundation models. Modality-agnostic edge maps are first extracted from input images, then processed by a U-Net to generate logit-based prompts. These prompts condition the Segment Anything Model 2 (SAM-2) to generate 2D liver segmentations, which can then be reconstructed into 3D volumes. Evaluated on the multi-modal CHAOS dataset, Edge2Prompt achieves competitive results compared to classical segmentation methods when trained and tested in-distribution (ID), and outperforms them in data-scarce scenarios due to the SAM-2 module. Furthermore, it achieves a mean Dice Score of 86.4% on OOD tasks, outperforming U-Net baselines by 27.4% and other self-prompting methods by 9.1%, demonstrating its effectiveness. This work bridges classical and foundation models for clinically adaptable, data-efficient segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04305
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Edge2Prompt: Modality-Agnostic Model for Out-of-Distribution Liver Segmentation
Hollet, Nathan
Cherkaoui, Oumeymah
Cattin, Philippe C.
Hadramy, Sidaty El
Image and Video Processing
Liver segmentation is essential for preoperative planning in interventions like tumor resection or transplantation, but implementation in clinical workflows faces challenges due to modality-specific tools and data scarcity. We propose Edge2Prompt, a novel pipeline for modality-agnostic liver segmentation that generalizes to out-of-distribution (OOD) data. Our method integrates classical edge detection with foundation models. Modality-agnostic edge maps are first extracted from input images, then processed by a U-Net to generate logit-based prompts. These prompts condition the Segment Anything Model 2 (SAM-2) to generate 2D liver segmentations, which can then be reconstructed into 3D volumes. Evaluated on the multi-modal CHAOS dataset, Edge2Prompt achieves competitive results compared to classical segmentation methods when trained and tested in-distribution (ID), and outperforms them in data-scarce scenarios due to the SAM-2 module. Furthermore, it achieves a mean Dice Score of 86.4% on OOD tasks, outperforming U-Net baselines by 27.4% and other self-prompting methods by 9.1%, demonstrating its effectiveness. This work bridges classical and foundation models for clinically adaptable, data-efficient segmentation.
title Edge2Prompt: Modality-Agnostic Model for Out-of-Distribution Liver Segmentation
topic Image and Video Processing
url https://arxiv.org/abs/2508.04305