Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation

• URL: http://arxiv.org/abs/2607.29509v1
• Date: Fri, 31 Jul 2026 15:13:02 GMT
• Title: Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation
• Abstract summary: We investigate how surgical conceptual knowledge transfers under partially common anatomical representations.<n>Results show that the organ-specific decoder model (CEMD), fully fine-tuned after cross-domain pre-training, achieves the highest segmentation performance.<n>However, we find that class imbalance in surgical data remains a persistent challenge that transfer learning does not fully resolve.
• Score: 2.8921656251272094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Effective multi-organ segmentation in surgical data requires learning the intricate anatomical features and alleviating the challenge of class imbalance, which results from relatively lower proportions of small and limitedly exposed structures. Recent works on laparoscopic multi-organ segmentation focus on learning structure-specific features through class-specific decoder architectures and report favorable results. This work extends the decoder-focused architectures to investigate knowledge sharing in the cross-surgical domain. We utilize two datasets representing different surgical domains, rectal and cholecystectomy surgeries, to explore how surgical conceptual knowledge transfers under partially common anatomical representations. Additionally, we compare the feature adaptation for the encoder and decoder at different training stages to analyse the knowledge adaptation and retention in the network. Our results corroborate previous findings on decoder-specific architectures and demonstrate that the organ-specific decoder model (CEMD), fully fine-tuned after cross-domain pre-training, achieves the highest segmentation performance (62.4\% dice) while converging substantially faster than training from scratch. However, we also find that class imbalance in surgical data remains a persistent challenge that transfer learning does not fully resolve for underrepresented anatomical structures.

Related papers

• What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation [2.6187298376652364]
  We investigate how different encoder--decoder regions influence segmentation performance and forgetting during continual gynecological segmentation.<n>We show that forgetting remains limited when updates are restricted to bottleneck-adjacent regions, but increases sharply once shallower encoders and decoders become trainable.
  arXiv  Detail & Related papers  (2026-08-13T18:02:25Z)
• Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance [50.486523249499115]
  Real-time video understanding is critical to guide procedures in minimally invasive surgery (MIS)<n>We propose Compress-to-Explore (C2E), a novel self-supervised framework to learn compact, informative representations from surgical videos.<n>C2E uses entropy-maximizing decoders to compress images while preserving clinically relevant details, improving encoder performance without labeled data.
  arXiv  Detail & Related papers  (2025-05-16T14:02:24Z)
• Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models [1.9085155846692308]
  We introduce a multi-stage approach to generate multi-class surgical datasets with annotations. Our framework improves anatomy awareness by training organ specific models with an inpainting objective guided by binary segmentation masks. This versatile approach allows the generation of multi-class datasets from real binary datasets and simulated surgical masks.
  arXiv  Detail & Related papers  (2024-10-10T09:29:23Z)
• LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models [59.961172635689664]
  "Knowledge Decomposition" aims to improve the performance on specific medical tasks. We propose a novel framework named Low-Rank Knowledge Decomposition (LoRKD) LoRKD explicitly separates gradients from different tasks by incorporating low-rank expert modules and efficient knowledge separation convolution.
  arXiv  Detail & Related papers  (2024-09-29T03:56:21Z)
• Anatomy-guided Pathology Segmentation [56.883822515800205]
  We develop a generalist segmentation model that combines anatomical and pathological information, aiming to enhance the segmentation accuracy of pathological features. Our Anatomy-Pathology Exchange (APEx) training utilizes a query-based segmentation transformer which decodes a joint feature space into query-representations for human anatomy. In doing so, we are able to report the best results across the board on FDG-PET-CT and Chest X-Ray pathology segmentation tasks with a margin of up to 3.3% as compared to strong baseline methods.
  arXiv  Detail & Related papers  (2024-07-08T11:44:15Z)
• Teaching AI the Anatomy Behind the Scan: Addressing Anatomical Flaws in Medical Image Segmentation with Learnable Prior [34.54360931760496]
  Key anatomical features, such as the number of organs, their shapes and relative positions, are crucial for building a robust multi-organ segmentation model. We introduce a novel architecture called the Anatomy-Informed Network (AIC-Net) AIC-Net incorporates a learnable input termed "Anatomical Prior", which can be adapted to patient-specific anatomy.
  arXiv  Detail & Related papers  (2024-03-27T10:46:24Z)
• K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment [71.27193056354741]
  The problem of how to assess cross-modality medical image synthesis has been largely unexplored. We propose a new metric K-CROSS to spur progress on this challenging problem. K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location.
  arXiv  Detail & Related papers  (2023-07-10T01:26:48Z)
• Towards to Robust and Generalized Medical Image Segmentation Framework [17.24628770042803]
  We propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation. Experiments of lung segmentation on multi chest X-ray datasets are conducted.
  arXiv  Detail & Related papers  (2021-08-09T05:58:49Z)
• Generalized Organ Segmentation by Imitating One-shot Reasoning using Anatomical Correlation [55.1248480381153]
  We propose OrganNet which learns a generalized organ concept from a set of annotated organ classes and then transfer this concept to unseen classes. We show that OrganNet can effectively resist the wide variations in organ morphology and produce state-of-the-art results in one-shot segmentation task.
  arXiv  Detail & Related papers  (2021-03-30T13:41:12Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)

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.