What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation

• URL: http://arxiv.org/abs/2608.13660v1
• Date: Thu, 13 Aug 2026 18:02:25 GMT
• Title: What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation
• Abstract summary: 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.
• Score: 2.6187298376652364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical image segmentation models are typically trained under the assumption that all data are available simultaneously. However, in clinical practice, datasets often arrive sequentially, requiring models to adapt continuously to evolving data distributions. We study this problem in gynecological image segmentation, where substantial heterogeneity across imaging modalities, anatomical structures, and annotation protocols creates a particularly challenging continual learning setting. Under these large distribution shifts, existing continual learning methods struggle to preserve previously learned knowledge, leading to catastrophic forgetting. To better understand forgetting in this setting, we investigate how different encoder--decoder regions influence segmentation performance and forgetting during continual gynecological segmentation. Through block-wise ablation analysis, we observe that ablating early encoder and late decoder regions results in the largest performance degradation, indicating that segmentation performance depends unevenly across the network hierarchy. Using controlled adaptation experiments, we further show that forgetting remains limited when updates are restricted to bottleneck-adjacent regions, but increases sharply once shallower encoders and decoders become trainable, even when only a small subset of parameters is updated. These findings suggest that forgetting in the encoder-decoder architecture is strongly influenced by where updates occur across network depth during continual learning. Full code and analysis pipelines will be made publicly available upon acceptance.

Related papers

• Leveraging Transfer Learning with Class-Specific Decoders for Laparoscopic Segmentation [2.8921656251272094]
  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.
  arXiv  Detail & Related papers  (2026-07-31T15:13:02Z)
• Towards Voxel Spacing Consistency for Medical Image Segmentation [56.992050146446495]
  We study the correlation between image resampling and segmentation, and propose Consispace, a semantic-aware resampling framework.<n> Consispace achieves consistent voxel spacing in the axial direction while preserving anatomical and semantic consistency.
  arXiv  Detail & Related papers  (2026-06-30T15:42:23Z)
• MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification [60.41879345743941]
  We propose MedMamba, an end-to-end architecture that integrates state space models with domain-specific inductive biases.<n>MedMamba achieves state-of-the-art performance while maintaining linear computational complexity.
  arXiv  Detail & Related papers  (2026-05-24T09:23:39Z)
• Resource-efficient Automatic Refinement of Segmentations via Weak Supervision from Light Feedback [1.8082075562656847]
  We present SCORE, a weakly supervised framework that learns to refine mask predictions only using light feedback during training.<n>We demonstrate SCORE on humerus CT scans, where it considerably improves initial predictions and achieves performance on par with existing refinement methods.
  arXiv  Detail & Related papers  (2025-11-04T13:53:10Z)
• Rethinking the Nested U-Net Approach: Enhancing Biomarker Segmentation with Attention Mechanisms and Multiscale Feature Fusion [2.0799865428691393]
  We introduce a nested UNet architecture that captures both local and global context through Multiscale Feature Fusion and Attention Mechanisms.<n>This design improves feature integration from encoders, highlights key channels and regions, and restores spatial details to enhance segmentation performance.
  arXiv  Detail & Related papers  (2025-04-08T15:53:46Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• 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)
• Deep Co-Attention Network for Multi-View Subspace Learning [73.3450258002607]
  We propose a deep co-attention network for multi-view subspace learning. It aims to extract both the common information and the complementary information in an adversarial setting. In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation.
  arXiv  Detail & Related papers  (2021-02-15T18:46:44Z)
• A survey on shape-constraint deep learning for medical image segmentation [0.46023882211671957]
  convolutional deep neural networks and its many variants have completely changed the modern landscape of deep learning based medical image segmentation. The over dependence of these methods on pixel level classification and regression has been identified early on as a problem. To ensure the segmentation result is anatomically consistent, approaches based on Markov/ Conditional Random Fields, Statistical Shape Models are becoming increasingly popular.
  arXiv  Detail & Related papers  (2021-01-19T16:52:10Z)
• 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)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)
• Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization [59.5104563755095]
  We introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding.
  arXiv  Detail & Related papers  (2020-09-27T12:30:30Z)

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.