Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection

• URL: http://arxiv.org/abs/2507.09294v1
• Date: Sat, 12 Jul 2025 14:07:44 GMT
• Title: Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection
• Abstract summary: Geo-RepNet is a geometry-aware convolutional framework that integrates RGB image and depth information to enhance recognition performance in complex surgical scenes.<n>To evaluate the effectiveness of our approach, we construct a nine-phase ESD dataset with dense frame-level annotations from real-world ESD videos.
• Score: 10.386536115270294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Surgical phase recognition plays a critical role in developing intelligent assistance systems for minimally invasive procedures such as Endoscopic Submucosal Dissection (ESD). However, the high visual similarity across different phases and the lack of structural cues in RGB images pose significant challenges. Depth information offers valuable geometric cues that can complement appearance features by providing insights into spatial relationships and anatomical structures. In this paper, we pioneer the use of depth information for surgical phase recognition and propose Geo-RepNet, a geometry-aware convolutional framework that integrates RGB image and depth information to enhance recognition performance in complex surgical scenes. Built upon a re-parameterizable RepVGG backbone, Geo-RepNet incorporates the Depth-Guided Geometric Prior Generation (DGPG) module that extracts geometry priors from raw depth maps, and the Geometry-Enhanced Multi-scale Attention (GEMA) to inject spatial guidance through geometry-aware cross-attention and efficient multi-scale aggregation. To evaluate the effectiveness of our approach, we construct a nine-phase ESD dataset with dense frame-level annotations from real-world ESD videos. Extensive experiments on the proposed dataset demonstrate that Geo-RepNet achieves state-of-the-art performance while maintaining robustness and high computational efficiency under complex and low-texture surgical environments.

Related papers

• GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval [54.741349848771144]
  GeoMamba is a geometry-driven framework for optical-SAR fine-grained retrieval.<n>GFI module enhances cross-modal feature interaction and incorporates structural priors.<n>GeoMamba outperforms existing methods, achieving 63.3% mAP and 77.0% Rank-1 accuracy in all-to-all retrieval setting.
  arXiv  Detail & Related papers  (2026-05-19T12:08:09Z)
• Geometry-Guided Self-Supervision for Ultra-Fine-Grained Recognition with Limited Data [73.20753799870282]
  This paper investigates the intrinsic geometrical features of highly similar objects.<n>It introduces a general self-supervised framework called the Geometric Attribute Exploration Network (GAEor)<n>GAEor generates geometric attributes as novel alternative recognition cues.
  arXiv  Detail & Related papers  (2026-04-21T11:27:33Z)
• Thinking with Geometry: Active Geometry Integration for Spatial Reasoning [68.59084007360615]
  We propose GeoThinker, a framework that shifts paradigm passive fusion to active perception.<n>Instead of feature mixing, GeoThinker enables the model to selectively retrieve geometric evidence conditioned on its internal reasoning demands.<n>Our results indicate that the ability to actively integrate spatial structures is essential for next-generation spatial intelligence.
  arXiv  Detail & Related papers  (2026-02-05T18:59:32Z)
• Depth to Anatomy: Learning Internal Organ Locations from Surface Depth Images [2.2821382245867414]
  We propose a learning-based framework that directly predicts the 3D locations and shapes of multiple internal organs from single 2D depth images of the body surface.<n>Our method accurately localizes a diverse set of anatomical structures, including bones and soft tissues, without requiring explicit surface reconstruction.
  arXiv  Detail & Related papers  (2026-01-26T08:33:11Z)
• AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation [0.0]
  AGENet is a novel framework that incorporates spatial relationships through edge-aware geodesic distance learning.<n>Our key insight is that medical structures follow predictable geometric patterns that can guide prototype extraction.<n>Our method reduces boundary errors compared to existing approaches while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-11-11T09:56:35Z)
• Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery [36.192962258966105]
  Scene graphs (SGs) provide structured representations crucial for decoding complex, dynamic surgical environments.<n>This PRISMA-ScR-guided scoping review systematically maps the evolving landscape of SG research in surgery.<n>Our analysis reveals rapid growth, yet uncovers a critical 'data divide'<n>SGs are maturing into an essential semantic bridge, enabling a new generation of intelligent systems to improve surgical safety, efficiency, and training.
  arXiv  Detail & Related papers  (2025-09-25T09:25:46Z)
• Geometry-Editable and Appearance-Preserving Object Compositon [67.98806888489385]
  General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties.<n>Recent approaches derive semantic embeddings and integrate them into advanced diffusion models to enable geometry-editable generation.<n>We introduce a Disentangled Geometry-editable and Appearance-preserving Diffusion model that first leverages semantic embeddings to implicitly capture desired geometric transformations.
  arXiv  Detail & Related papers  (2025-05-27T09:05:28Z)
• Scribble-Based Interactive Segmentation of Medical Hyperspectral Images [4.675955891956077]
  This work introduces a scribble-based interactive segmentation framework for medical hyperspectral images. The proposed method utilizes deep learning for feature extraction and a geodesic distance map generated from user-provided scribbles.
  arXiv  Detail & Related papers  (2024-08-05T12:33:07Z)
• Depth-Driven Geometric Prompt Learning for Laparoscopic Liver Landmark Detection [43.600236988802465]
  Liver anatomical landmarks serve as important markers for 2D-3D alignment. To facilitate the detection of laparoscopic liver landmarks, we collect a novel dataset called L3D. We propose a depth-driven geometric prompt learning network, namely D2GPLand.
  arXiv  Detail & Related papers  (2024-06-25T18:02:11Z)
• Semantic segmentation of surgical hyperspectral images under geometric domain shifts [69.91792194237212]
  We present the first analysis of state-of-the-art semantic segmentation networks in the presence of geometric out-of-distribution (OOD) data. We also address generalizability with a dedicated augmentation technique termed "Organ Transplantation" Our scheme improves on the SOA DSC by up to 67 % (RGB) and 90 % (HSI) and renders performance on par with in-distribution performance on real OOD test data.
  arXiv  Detail & Related papers  (2023-03-20T09:50:07Z)
• Semantic-SuPer: A Semantic-aware Surgical Perception Framework for Endoscopic Tissue Classification, Reconstruction, and Tracking [21.133420628173067]
  We present a novel surgical perception framework, Semantic-SuPer. It integrates geometric and semantic information to facilitate data association, 3D reconstruction, and tracking of endoscopic scenes.
  arXiv  Detail & Related papers  (2022-10-29T19:33:21Z)
• Recurrent Feature Propagation and Edge Skip-Connections for Automatic Abdominal Organ Segmentation [13.544665065396373]
  We propose a 3D network with four main components trained end-to-end including encoder, edge detector, decoder with edge skip-connections and recurrent feature propagation head. Experimental results show that the proposed network outperforms several state-of-the-art models.
  arXiv  Detail & Related papers  (2022-01-02T08:33:19Z)
• Deep Unrolled Recovery in Sparse Biological Imaging [62.997667081978825]
  Deep algorithm unrolling is a model-based approach to develop deep architectures that combine the interpretability of iterative algorithms with the performance gains of supervised deep learning. This framework is well-suited to applications in biological imaging, where physics-based models exist to describe the measurement process and the information to be recovered is often highly structured.
  arXiv  Detail & Related papers  (2021-09-28T20:22:44Z)
• High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusion [84.24973877109181]
  We propose a novel attention-based hierarchical multi-modal fusion network for guided DSR. We show that our approach outperforms state-of-the-art methods in terms of reconstruction accuracy, running speed and memory efficiency.
  arXiv  Detail & Related papers  (2021-04-04T03:28:33Z)
• Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications [78.63280020581662]
  A novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-03-24T08:16:32Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.