Updates

Author: mstaring

_bibliography/papers.bib

@@ -87,17 +87,18 @@ @article{Li:2025
   abstract = {Deformable image registration estimates voxel-wise correspondences between images through spatial transformations, and plays a key role in medical imaging. While deep learning methods have significantly reduced runtime, efficiently handling large deformations remains a challenging task. Convolutional networks aggregate local features but lack direct modeling of voxel correspondences, promoting recent works to explore explicit feature matching. Among them, voxel-to-region matching is more efficient for direct correspondence modeling by computing local correlation features within neighbourhoods, while region-to-region matching incurs higher redundancy due to excessive correlation pairs across large regions. However, the inherent locality of voxel-to-region matching hinders the capture of long-range correspondences required for large deformations. To address this, we propose a Recurrent Correlation-based framework that dynamically relocates the matching region toward more promising positions. At each step, local matching is performed with low cost, and the estimated offset guides the next search region, supporting efficient convergence toward large deformations. In addition, we uses a lightweight recurrent update module with memory capacity and decouples motion-related and texture features to suppress semantic redundancy. We conduct extensive experiments on brain MRI and abdominal CT datasets under two settings: with and without affine pre-registration. Results show our method exhibits a strong accuracy-computation trade-off, surpassing or matching the state-of-the-art performance. For example, it achieves comparable performance on the non-affine OASIS dataset, while using only 9.5% of the FLOPs and running 96% faster than RDP, a representative high-performing method.},
 }
 
-@article{Chaves-de-Plaza:2025,
+@article{Chaves-de-Plaza:2026,
   abbr =     {TVCG},
   bibtex_show = {true},
   author =   {Chaves-de-Plaza, Nicolas and Raidou, Renata G. and Mody, Prerak P. and Staring, Marius and van Egmond, Ren{\'e}; and Vilanova, Anna and Hildebrandt, Klaus},
   title =    {LoGCC: Local-to-Global Correlation Clustering for Scalar Field Ensembles},
   journal =  {IEEE Transactions on Visualization and Computer Graphics},
-  volume =   {},
-  number =   {},
-  pages =    {},
-  year =     {2025},
-  pdf =      {2025_j_TVCG.pdf},
+  volume =   {32},
+  number =   {2},
+  pages =    {2260 -- 2271},
+  year =     {2026},
+  month =    {February},
+  pdf =      {2026_j_TVCG.pdf},
   html =     {https://doi.org/10.1109/TVCG.2025.3630550},
   arxiv =    {},
   code =     {},
@@ -128,9 +129,10 @@ @article{VanDerLoo2025
   title =   {Large Language Models for Structured Cardiovascular Data Extraction: A Foundation for Scalable Research and Clinical Applications},
   author =  {van der Loo, Wouter and van der Valk, Viktor and van den Broek, Tim and Atsma, Douwe and Staring, Marius and Scherptong, Roderick},
   journal = {European Heart Journal - Digital Health},
-  volume =  {},
+  volume =  {7},
+  number =  {2},
   pages =   {},
-  month =   {},
+  month =   {March},
   year =    {2025},
   pdf =     {2025_j_EHJ-DH.pdf},
   html =    {https://doi.org/10.1093/ehjdh/ztaf127},

_bibliography/papers_abstracts.bib

@@ -133,7 +133,7 @@ @inproceedings{Gao:2025
   year =      {2025},
   volume =    {206},
   pages =     {S2792 -- S2794},
-  pdf =       {2025_a_ESTRO},
+  pdf =       {2025_a_ESTRO.pdf},
   html =      {https://doi.org/10.1016/S0167-8140(25)00691-7},
   arxiv =     {},
   code =      {},

_bibliography/papers_conf.bib

@@ -17,7 +17,7 @@ @inproceedings{Gao:2026
   year =      {2026},
   pdf =       {2026_c_CARS.pdf},
   html =      {},
-  arxiv =     {},
+  arxiv =     {2603.29670},
   code =      {},
   abstract =  {
 <b>Purpose</b> Deep-learning-based three-dimensional (3D) dose prediction has become an important component of automated radiotherapy workflows. However, most existing models are trained using voxel-wise regression losses, which are poorly aligned with clinical plan evaluation criteria that rely on dose-volume histogram (DVH)-derived metrics. This study aims to develop a clinically guided loss formulation that directly optimizes clinically used DVH metrics while remaining computationally efficient for head and neck (H&N) dose prediction.<br><b>Methods</b> We propose a clinical DVH metric loss (CDM loss) that jointly incorporates differentiable formulations of common D-metrics and differentiable surrogates of V--metrics. The loss is driven by a JSON-based clinical plan evaluation template to ensure alignment with clinic planning criteria. In addition, we introduce a lossless bit-mask encoding scheme to efficiently represent a large number of overlapping ROIs, substantially improving training efficiency. The method was evaluated on a retrospective cohort of 174 H&N patients treated with VMAT, using a temporal split for training (n = 137) and testing (n = 37).<br><b>Results</b> Compared with MAE- and DVH-based losses, the proposed CDM loss substantially improved clinical target coverage, and satisfied all predefined clinical constraints. Using a standard 3D U-Net, the PTV Score was reduced from 1.544 (MAE) to 0.491 (MAE+CDM), while consistently satisfying all PTV clinical constraints. OAR sparing remained comparable or improved. Bit-mask ROI encoding reduced average training epoch time from 241s to 43s (83.2% reduction) and lowered peak GPU memory usage. Notably, with the CDM loss, a standard 3D U-Net achieved performance comparable to or better than more complex state-of-the-art architectures.<br><b>Conclusion</b> Directly optimizing clinically used DVH metrics enables 3D dose predictions that are better aligned with clinical treatment planning criteria than conventional only voxel-wise or DVH-curve supervision. The proposed CDM loss, combined with efficient ROI bit-mask encoding, provides a practical and scalable framework for H&N dose prediction.},
@@ -37,7 +37,7 @@ @inproceedings{Ilicak:2026
   year =      {2026},
   pdf =       {2026_c_ISBI.pdf},
   html =      {},
-  arxiv =     {},
+  arxiv =     {2602.19829},
   code =      {},
   abstract =  {Portable low-field magnetic resonance imaging (MRI) systems have gained renewed interest owing to their cost effectiveness and point-of-care imaging capabilities. Yet, portable MRI systems suffer from relatively low signal-to-noise ratio and limited hardware capabilities. While previous works have proposed the use of deep learning based reconstruction methods to improve low-field image quality, these operated only in the image-domain. Unlike other imaging modalities, MRI directly acquires data in the Fourier-domain (k-space), and exploiting both k-space and image-domain information can improve reconstruction quality. Here, we introduce DUN-DD, a novel physics-guided 3D network for portable MRI reconstruction, with parallel dual-domain branches whose outputs are combined together via an attention-based fusion network. To demonstrate the performance of the proposed method, we present in vivo reconstructions obtained from both emulated datasets as well as images acquired with a 47mT Halbach-based portable MRI system. Our results show that DUN-DD outperforms state-of-the-art classical, data-driven, and physics-guided methods on both emulated and real portable MRI acquisitions.},
 }
@@ -51,11 +51,11 @@ @inproceedings{Zheng:2025b
   address =   {Wuhan, China},
   series =    {},
   volume =    {},
-  pages =     {},
+  pages =     {4517 -- 4520},
   month =     {December},
   year =      {2025},
-  pdf =       {},
-  html =      {},
+  pdf =       {2025_c_BIBM.pdf},
+  html =      {https://doi.org/10.1109/BIBM66473.2025.11356999},
   arxiv =     {2509.20073},
   code =      {},
   abstract =  {Encoder-Decoder architectures are widely used in deep learning-based Deformable Image Registration (DIR), where the encoder extracts multi-scale features and the decoder predicts deformation fields by recovering spatial locations. However, current methods lack specialized extraction of features (that are useful for registration) and predict deformation jointly and homogeneously in all three directions. In this paper, we propose a novel expert-guided DIR network with Mixture of Experts (MoE) mechanism applied in both encoder and decoder, named SHMoAReg. Specifically, we incorporate Mixture of Attention heads (MoA) into encoder layers, while Spatial Heterogeneous Mixture of Experts (SHMoE) into the decoder layers. The MoA enhances the specialization of feature extraction by dynamically selecting the optimal combination of attention heads for each image token. Meanwhile, the SHMoE predicts deformation fields heterogeneously in three directions for each voxel using experts with varying kernel sizes. Extensive experiments conducted on two publicly available datasets show consistent improvements over various methods, with a notable increase from 60.58% to 65.58% in Dice score for the abdominal CT dataset. Furthermore, SHMoAReg enhances model interpretability by differentiating experts' utilities across/within different resolution layers. To the best of our knowledge, we are the first to introduce MoE mechanism into DIR tasks. The code will be released soon.},
@@ -94,7 +94,7 @@ @inproceedings{Lyu:2025b
   year =      {2025},
   pdf =       {2025_c_STACOMb.pdf},
   html =      {},
-  arxiv =     {},
+  arxiv =     {2601.04428},
   code =      {},
   abstract =  {In recent years, deep learning has attracted increasing attention in the field of Cardiac MRI (CMR) reconstruction due to its superior performance over traditional methods, particularly in handling higher acceleration factors, highlighting its potential for real-world clinical applications. However, current deep learning methods remain limited in generalizability. CMR scans exhibit wide variability in image contrast, sampling patterns, scanner vendors, anatomical structures, and disease types. Most existing models are designed to handle only a single or narrow subset of these variations, leading to performance degradation when faced with distribution shifts. Therefore, it is beneficial to develop a unified model capable of generalizing across diverse CMR scenarios. To this end, we propose CRUNet-MR-Univ, a foundation model that leverages spatio-temporal correlations and prompt-based priors to effectively handle the full diversity of CMR scans. Our approach consistently outperforms baseline methods across a wide range of settings, highlighting its effectiveness and promise.},
 }
@@ -137,6 +137,25 @@ @inproceedings{Gao:2025
   abstract =  {Medical imaging is essential for the diagnosis and treatment of diseases, with medical image segmentation as a subtask receiving high attention. However, automatic medical image segmentation models are typically task-specific and struggle to handle multiple scenarios, such as different imaging modalities and regions of interest. With the introduction of the Segment Anything Model (SAM), training a universal model for various clinical scenarios has become feasible. Recently, several Medical SAM (MedSAM) methods have been proposed, but these models often rely on heavy image encoders to achieve high performance, which may not be practical for real-world applications due to their high computational demands and slow inference speed. To address this issue, a lightweight version of the MedSAM (LiteMedSAM) can provide a viable solution, achieving high performance while requiring fewer resources and less time. In this work, we introduce Swin-LiteMedSAM, a new variant of LiteMedSAM. This model integrates the tiny Swin Transformer as the image encoder, incorporates multiple types of prompts, including box-based points and scribble generated from a given bounding box, and establishes skip connections between the image encoder and the mask decoder. In the <i>Segment Anything in Medical Images on Laptop</i> challenge (CVPR 2024), our approach strikes a good balance between segmentation performance and speed, demonstrating significantly improved overall results across multiple modalities compared to the LiteMedSAM baseline provided by the challenge organizers. Our proposed model achieved a DSC score of 0.8678 and an NSD score of 0.8844 on the validation set. On the final test set, it attained a DSC score of 0.8193 and an NSD score of 0.8461, securing fourth place in the challenge. The code and trained model are available at https://github.com/RuochenGao/Swin_LiteMedSAM.},
 }
 
+@inproceedings{Ma:2024,
+  abbr =    {},
+  bibtex_show = {true},
+  author =    {Ma, Jun and et al},
+  title =     {Efficient MedSAMs: Segment Anything in Medical Images on Laptop},
+  booktitle = {CVPR 2024 MedSAM on Laptop Competition},
+  address =   {},
+  series =    {},
+  volume =    {},
+  pages =     {},
+  month =     {},
+  year =      {2024},
+  pdf =       {2024_c_CVPR.pdf},
+  html =      {},
+  arxiv =     {2412.16085},
+  code =      {},
+  abstract =  {Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications.},
+}
+
 @inproceedings{Lyu:2024,
   abbr =    {},
   bibtex_show = {true},