# Exploring Cycle Consistency Learning in Interactive Volume Segmentation

arXiv: https://arxiv.org/abs/2303.06493 · HTML: https://mlsanity.com/paper/2303.06493/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [Learning Correspondence from the Cycle-Consistency of Time](https://mlsanity.com/paper/1903.07593/) (2019)
- [AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?](https://mlsanity.com/paper/2010.14808/) (2020)
- [Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation](https://mlsanity.com/paper/2106.05210/) (2021)
- [Temporal Cycle-Consistency Learning](https://mlsanity.com/paper/1904.07846/) (2019)
- [Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion](https://mlsanity.com/paper/2103.07941/) (2021)
- [Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning](https://mlsanity.com/paper/1710.04043/) (2017)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration](https://mlsanity.com/paper/2008.05772/) (2020)
- [SwiftNet: Real-time Video Object Segmentation](https://mlsanity.com/paper/2102.04604/) (2021)
- [Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1911.10334/) (2019)
- [textttGradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency](https://mlsanity.com/paper/2206.05897/) (2022)
- [iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images](https://mlsanity.com/paper/2112.11325/) (2021)
- [ICON: Learning Regular Maps Through Inverse Consistency](https://mlsanity.com/paper/2105.04459/) (2021)
- [Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation](https://mlsanity.com/paper/2010.12176/) (2020)
- [Unsupervised learning for cross-domain medical image synthesis using deformation invariant cycle consistency networks](https://mlsanity.com/paper/1808.03944/) (2018)

## Built on by (most cited first, 4 of 4)

- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [Clustering Propagation for Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.16646/) (2024)
- [Lightweight Method for Interactive 3D Medical Image Segmentation with Multi-Round Result Fusion](https://mlsanity.com/paper/2412.08315/) (2024)
- [ImplicitCell: Resolution Cell Modeling of Joint Implicit Volume Reconstruction and Pose Refinement in Freehand 3D Ultrasound](https://mlsanity.com/paper/2503.06686/) (2025)

## Abstract (arXiv)

Automatic medical volume segmentation often lacks clinical accuracy, necessitating further refinement. In this work, we interactively approach medical volume segmentation via two decoupled modules: interaction-to-segmentation and segmentation propagation. Given a medical volume, a user first segments a slice (or several slices) via the interaction module and then propagates the segmentation(s) to the remaining slices. The user may repeat this process multiple times until a sufficiently high volume segmentation quality is achieved. However, due to the lack of human correction during propagation, segmentation errors are prone to accumulate in the intermediate slices and may lead to sub-optimal performance. To alleviate this issue, we propose a simple yet effective cycle consistency loss that regularizes an intermediate segmentation by referencing the accurate segmentation in the starting slice. To this end, we introduce a backward segmentation path that propagates the intermediate segmentation back to the starting slice using the same propagation network. With cycle consistency training, the propagation network is better regularized than in standard forward-only training approaches. Evaluation results on challenging AbdomenCT-1K and OAI-ZIB datasets demonstrate the effectiveness of our method.