Towards Comprehensive Real-Time Scene Understanding in Ophthalmic Surgery through Multimodal Image Fusion

• URL: http://arxiv.org/abs/2603.25555v1
• Date: Thu, 26 Mar 2026 15:27:27 GMT
• Title: Towards Comprehensive Real-Time Scene Understanding in Ophthalmic Surgery through Multimodal Image Fusion
• Abstract summary: We propose a temporal, real-time capable network architecture to perform joint instrument detection, keypoint localization, and tool-tissue distance estimation.<n>Experiments demonstrate reliable instrument localization and keypoint detection (95.79% mAP50) and show that the incorporation of i OCT significantly improves tool-tissue distance estimation.
• Score: 40.97183044655793
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Purpose: The integration of multimodal imaging into operating rooms paves the way for comprehensive surgical scene understanding. In ophthalmic surgery, by now, two complementary imaging modalities are available: operating microscope (OPMI) imaging and real-time intraoperative optical coherence tomography (iOCT). This first work toward temporal OPMI and iOCT feature fusion demonstrates the potential of multimodal image processing for multi-head prediction through the example of precise instrument tracking in vitreoretinal surgery. Methods: We propose a multimodal, temporal, real-time capable network architecture to perform joint instrument detection, keypoint localization, and tool-tissue distance estimation. Our network design integrates a cross-attention fusion module to merge OPMI and iOCT image features, which are efficiently extracted via a YoloNAS and a CNN encoder, respectively. Furthermore, a region-based recurrent module leverages temporal coherence. Results: Our experiments demonstrate reliable instrument localization and keypoint detection (95.79% mAP50) and show that the incorporation of iOCT significantly improves tool-tissue distance estimation, while achieving real-time processing rates of 22.5 ms per frame. Especially for close distances to the retina (below 1 mm), the distance estimation accuracy improved from 284 $μm$ (OPMI only) to 33 $μm$ (multimodal). Conclusion: Feature fusion of multimodal imaging can enhance multi-task prediction accuracy compared to single-modality processing and real-time processing performance can be achieved through tailored network design. While our results demonstrate the potential of multi-modal processing for image-guided vitreoretinal surgery, they also underline key challenges that motivate future research toward more reliable, consistent, and comprehensive surgical scene understanding.

Related papers

• Unsupervised MRI-US Multimodal Image Registration with Multilevel Correlation Pyramidal Optimization [14.509109797489499]
  We propose an unsupervised multimodal medical image registration method based on multilevel correlation pyramidal optimization (MCPO)<n>Our method achieves the first place in the validation phase and test phase of ReMIND2Reg.<n>This demonstrates the broad applicability of our method in preoperative-to-intraoperative image registration.
  arXiv  Detail & Related papers  (2026-02-06T01:03:57Z)
• A Unified Model for Compressed Sensing MRI Across Undersampling Patterns [69.19631302047569]
  We propose a unified MRI reconstruction model robust to various measurement undersampling patterns and image resolutions.<n>Our model improves SSIM by 11% and PSNR by 4 dB over a state-of-the-art CNN (End-to-End VarNet) with 600$times$ faster inference than diffusion methods.
  arXiv  Detail & Related papers  (2024-10-05T20:03:57Z)
• Multi-sensor Learning Enables Information Transfer across Different Sensory Data and Augments Multi-modality Imaging [21.769547352111957]
  We investigate a data-driven multi-modality imaging (DMI) strategy for synergetic imaging of CT and MRI. We reveal two distinct types of features in multi-modality imaging, namely intra- and inter-modality features, and present a multi-sensor learning (MSL) framework. We showcase the effectiveness of our DMI strategy through synergetic CT-MRI brain imaging.
  arXiv  Detail & Related papers  (2024-09-28T17:40:54Z)
• Friends Across Time: Multi-Scale Action Segmentation Transformer for Surgical Phase Recognition [2.10407185597278]
  We propose the Multi-Scale Action Transformer (MS-AST) for offline surgical phase recognition and the Multi-Scale Action Causal Transformer (MS-ASCT) for online surgical phase recognition. Our method can achieve 95.26% and 96.15% accuracy on the Cholec80 dataset for online and offline surgical phase recognition, respectively.
  arXiv  Detail & Related papers  (2024-01-22T01:34:03Z)
• Phase-Specific Augmented Reality Guidance for Microscopic Cataract Surgery Using Long-Short Spatiotemporal Aggregation Transformer [14.568834378003707]
  Phaemulsification cataract surgery (PCS) is a routine procedure using a surgical microscope. PCS guidance systems extract valuable information from surgical microscopic videos to enhance proficiency. Existing PCS guidance systems suffer from non-phasespecific guidance, leading to redundant visual information. We propose a novel phase-specific augmented reality (AR) guidance system, which offers tailored AR information corresponding to the recognized surgical phase.
  arXiv  Detail & Related papers  (2023-09-11T02:56:56Z)
• LoViT: Long Video Transformer for Surgical Phase Recognition [59.06812739441785]
  We present a two-stage method, called Long Video Transformer (LoViT) for fusing short- and long-term temporal information. Our approach outperforms state-of-the-art methods on the Cholec80 and AutoLaparo datasets consistently.
  arXiv  Detail & Related papers  (2023-05-15T20:06:14Z)
• Multi-modal Aggregation Network for Fast MR Imaging [85.25000133194762]
  We propose a novel Multi-modal Aggregation Network, named MANet, which is capable of discovering complementary representations from a fully sampled auxiliary modality. In our MANet, the representations from the fully sampled auxiliary and undersampled target modalities are learned independently through a specific network. Our MANet follows a hybrid domain learning framework, which allows it to simultaneously recover the frequency signal in the $k$-space domain.
  arXiv  Detail & Related papers  (2021-10-15T13:16:59Z)
• Patch-based field-of-view matching in multi-modal images for electroporation-based ablations [0.6285581681015912]
  Multi-modal imaging sensors are currently involved at different steps of an interventional therapeutic work-flow. Merging this information relies on a correct spatial alignment of the observed anatomy between the acquired images. We show that a regional registration approach using voxel patches provides a good structural compromise between the voxel-wise and "global shifts" approaches.
  arXiv  Detail & Related papers  (2020-11-09T11:27:45Z)
• Searching for Efficient Architecture for Instrument Segmentation in Robotic Surgery [58.63306322525082]
  Most applications rely on accurate real-time segmentation of high-resolution surgical images. We design a light-weight and highly-efficient deep residual architecture which is tuned to perform real-time inference of high-resolution images.
  arXiv  Detail & Related papers  (2020-07-08T21:38:29Z)
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE) [50.65891535040752]
  We propose a diffusion encoding scheme, called Slice-Interleaved Diffusion. SIDE, that interleaves each diffusion-weighted (DW) image volume with slices encoded with different diffusion gradients. We also present a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data.
  arXiv  Detail & Related papers  (2020-02-25T14:48:17Z)

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.