# Distilling Temporal Coherence into 2D Networks for Transrectal Ultrasound Prostate Video Segmentation

arXiv: https://arxiv.org/abs/2606.31198 · HTML: https://mlsanity.com/paper/2606.31198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 30 Jun 2026.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [MedNeXt: Transformer-driven Scaling of ConvNets for Medical Image Segmentation](https://mlsanity.com/paper/2303.09975/) (2023)
- [Video Polyp Segmentation: A Deep Learning Perspective](https://mlsanity.com/paper/2203.14291/) (2022)
- [Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformations](https://mlsanity.com/paper/1911.01218/) (2019)
- [MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation](https://mlsanity.com/paper/2105.07451/) (2021)
- [Adaptive Context Selection for Polyp Segmentation](https://mlsanity.com/paper/2301.04799/) (2023)
- [TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing](https://mlsanity.com/paper/2303.07428/) (2023)
- [Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound](https://mlsanity.com/paper/1907.01743/) (2019)
- [SALI: Short-term Alignment and Long-term Interaction Network for Colonoscopy Video Polyp Segmentation](https://mlsanity.com/paper/2406.13532/) (2024)
- [Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos](https://mlsanity.com/paper/2310.01861/) (2023)
- [Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images](https://mlsanity.com/paper/1612.01655/) (2016)

## Abstract (arXiv)

Real-time video segmentation of the prostate in Transrectal Ultrasound (TRUS) is essential for image-guided interventions. While conventional 2D methods suffer from inter-frame inconsistencies by disregarding temporal context, 3D architectures incur prohibitive latency. To resolve this dilemma, we present a Temporally Consistent Learning Framework that distills temporal coherence into a 2D network during training, preserving single-frame inference efficiency. Our design is driven by a key clinical observation: the prostate exhibits geometric stability, whereas the surrounding acoustic environment fluctuates due to physiological motion and transducer pressure. Because conventional temporal constraints propagate erroneous gradients from these unstable regions, we introduce a Confidence-Weighted Temporal Consistency objective derived from optical flow warping residuals, selectively attenuating contributions from unreliable regions. Complementing this pixel-wise constraint, a Dual-scale Prototype Alignment Module enforces semantic coherence through contrastive optimization of local boundary and global semantic features. Furthermore, to eliminate the need for dense per-frame video annotations, we employ geometric equivariance-based pseudo-labeling with knowledge distillation from a pretrained teacher. Extensive experiments on SUN-SEG and our newly introduced TRUS-V benchmark (2,679 frames) demonstrate state-of-the-art accuracy and temporal consistency at real-time speed. Code and dataset are available at https://github.com/DYDevelop/DTC-TRUS.