ICL-NoiseUNet - A Novel In-Context Learning Based Framework For Ultrasound Segmentation With Adaptive Noise Modulation

Ioannis Charisiadis, Ilyass el Allali, Richard G. P. Lopata, Clara I. Sánchez, Navchetan Awasthi
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:801-826, 2026.

Abstract

The complex patterns, artifacts and speckle noise that are present in ultrasound images make precise segmentation very challenging. Existing approaches, such as convolutional neural network architectures and foundation models, have shown promising results across a wide range of tasks. However, they struggle to adapt to the unique characteristics of ultrasound data, leading to poor delineation of anatomical boundaries. For that reason, we propose ICL-NoiseUNet, an in-context-learning segmentation framework that combines guidance from a set of input-output pairs, called the context set, with analytic noise descriptors. More specifically, the model leverages an In-Context Feature Conditioning (ICFC) module to incorporate context examples and a Noise Modulation Block (NMB) that adapts feature representation to ultrasound characteristics. After extensive evaluation across several datasets, ICL-NoiseUNet consistently outperforms state-of-the-art methods, enhancing the segmentation quality. Moreover, ablation studies confirm the synergy effect of contextual conditioning and noise modulation. Overall, these findings pave the way for noise-guided ultrasound segmentation. The code will be open-source at .

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-charisiadis26a, title = {ICL-NoiseUNet - A Novel In-Context Learning Based Framework For Ultrasound Segmentation With Adaptive Noise Modulation}, author = {Charisiadis, Ioannis and el Allali, Ilyass and Lopata, Richard G. P. and S{\'a}nchez, Clara I. and Awasthi, Navchetan}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {801--826}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/charisiadis26a/charisiadis26a.pdf}, url = {https://proceedings.mlr.press/v315/charisiadis26a.html}, abstract = {The complex patterns, artifacts and speckle noise that are present in ultrasound images make precise segmentation very challenging. Existing approaches, such as convolutional neural network architectures and foundation models, have shown promising results across a wide range of tasks. However, they struggle to adapt to the unique characteristics of ultrasound data, leading to poor delineation of anatomical boundaries. For that reason, we propose ICL-NoiseUNet, an in-context-learning segmentation framework that combines guidance from a set of input-output pairs, called the context set, with analytic noise descriptors. More specifically, the model leverages an In-Context Feature Conditioning (ICFC) module to incorporate context examples and a Noise Modulation Block (NMB) that adapts feature representation to ultrasound characteristics. After extensive evaluation across several datasets, ICL-NoiseUNet consistently outperforms state-of-the-art methods, enhancing the segmentation quality. Moreover, ablation studies confirm the synergy effect of contextual conditioning and noise modulation. Overall, these findings pave the way for noise-guided ultrasound segmentation. The code will be open-source at .} }
Endnote
%0 Conference Paper %T ICL-NoiseUNet - A Novel In-Context Learning Based Framework For Ultrasound Segmentation With Adaptive Noise Modulation %A Ioannis Charisiadis %A Ilyass el Allali %A Richard G. P. Lopata %A Clara I. Sánchez %A Navchetan Awasthi %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-charisiadis26a %I PMLR %P 801--826 %U https://proceedings.mlr.press/v315/charisiadis26a.html %V 315 %X The complex patterns, artifacts and speckle noise that are present in ultrasound images make precise segmentation very challenging. Existing approaches, such as convolutional neural network architectures and foundation models, have shown promising results across a wide range of tasks. However, they struggle to adapt to the unique characteristics of ultrasound data, leading to poor delineation of anatomical boundaries. For that reason, we propose ICL-NoiseUNet, an in-context-learning segmentation framework that combines guidance from a set of input-output pairs, called the context set, with analytic noise descriptors. More specifically, the model leverages an In-Context Feature Conditioning (ICFC) module to incorporate context examples and a Noise Modulation Block (NMB) that adapts feature representation to ultrasound characteristics. After extensive evaluation across several datasets, ICL-NoiseUNet consistently outperforms state-of-the-art methods, enhancing the segmentation quality. Moreover, ablation studies confirm the synergy effect of contextual conditioning and noise modulation. Overall, these findings pave the way for noise-guided ultrasound segmentation. The code will be open-source at .
APA
Charisiadis, I., el Allali, I., Lopata, R.G.P., Sánchez, C.I. & Awasthi, N.. (2026). ICL-NoiseUNet - A Novel In-Context Learning Based Framework For Ultrasound Segmentation With Adaptive Noise Modulation. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:801-826 Available from https://proceedings.mlr.press/v315/charisiadis26a.html.

Related Material