Information processing in medical imaging : proceedings of the ... conference最新文献

{"title":"Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography.","authors":"Yuexi Du, John A Onofrey, Nicha C Dvornek","doi":"10.1007/978-3-031-96625-5_17","DOIUrl":"10.1007/978-3-031-96625-5_17","url":null,"abstract":"<p><p>Contrastive Language-Image Pre-training (CLIP) demonstrates strong potential in medical image analysis but requires substantial data and computational resources. Due to these restrictions, existing CLIP applications in medical imaging focus mainly on modalities like chest X-rays that have abundant image-report data available, leaving many other important modalities under-explored. Here, we propose one of the first adaptations of the full CLIP model to mammography, which presents significant challenges due to labeled data scarcity, high-resolution images with small regions of interest, and class-wise imbalance. We first develop a specialized supervision framework for mammography that leverages its multi-view nature. Furthermore, we design a symmetric local alignment module to better focus on detailed features in high-resolution images. Lastly, we incorporate a parameter-efficient fine-tuning approach for large language models pre-trained with medical knowledge to address data limitations. Our multi-view and multi-scale alignment (MaMA) method outperforms state-of-the-art baselines for three different tasks on two large real-world mammography datasets, EMBED and RSNA-Mammo, with only 52% model size compared with the largest baseline.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"15830 ","pages":"247-262"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12456755/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145139326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cycle-Consistent Zero-Shot Through-Plane Super-Resolution for Anisotropic Head MRI.","authors":"Samuel W Remedios, Shuwen Wei, Aaron Carass, Blake E Dewey, Jerry L Prince","doi":"10.1007/978-3-031-96628-6_17","DOIUrl":"10.1007/978-3-031-96628-6_17","url":null,"abstract":"<p><p>Magnetic resonance (MR) images are often acquired as anisotropic volumes in clinical settings. Such volumes have a worse through-plane resolution than in-plane resolution, hampering results in many processing pipelines that expect isotropic resolutions. Super-resolution (SR) is a promising methodology to address this problem, but there is concern whether the estimated high-resolution (HR) image suffers from egregious hallucinations, especially with deep learning methods that produce aesthetically pleasing results. One approach to restrict the impact of hallucinations is to guarantee that the estimated HR image is exactly cycle-consistent with the low-resolution observation. The denoising diffusion null space model (DDNM) achieves this through a range null space decomposition, but the specific design of the forward map is left to the application. In this work, we analyze the forward problem in 2D MR acquisition and construct an appropriate linear map <math><mi>A</mi></math> . We train a denoising diffusion probabilistic model on T₁-weighted (T₁-w) head MR images from multiple datasets and implement DDNM using <math><mi>A</mi></math> for the SR task. We show that the approach yields exact cycle-consistent solutions that are also realistic. We evaluated the approach in a wide variety of T₁-w MR datasets, including withheld subjects from training sites and two sites outside of the training domain. We achieve excellent qualitative and quantitative results according to both distortion and perceptual metrics.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"15829 ","pages":"249-264"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12805976/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145999766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brightness-Invariant Tracking Estimation in Tagged MRI.","authors":"Zhangxing Bian, Shuwen Wei, Xiao Liang, Yuan-Chiao Lu, Samuel W Remedios, Fangxu Xing, Jonghye Woo, Dzung L Pham, Aaron Carass, Philip V Bayly, Jiachen Zhuo, Ahmed Alshareef, Jerry L Prince","doi":"10.1007/978-3-031-96625-5_25","DOIUrl":"10.1007/978-3-031-96625-5_25","url":null,"abstract":"<p><p>Magnetic resonance (MR) tagging is an imaging technique for noninvasively tracking tissue motion in vivo by creating a visible pattern of magnetization saturation (tags) that deforms with the tissue. Due to longitudinal relaxation and progression to steady-state, the tags and tissue brightnesses change over time, which makes tracking with optical flow methods error-prone. Although Fourier methods can alleviate these problems, they are also sensitive to brightness changes as well as spectral spreading due to motion. To address these problems, we introduce the brightness-invariant tracking estimation (BRITE) technique for tagged MRI. BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion. The inherent ill-posedness of this problem is addressed by leveraging the expressive power of denoising diffusion probabilistic models to represent the probabilistic distribution of the underlying anatomy and the flexibility of physics-informed neural networks to estimate biologically-plausible motion. A set of tagged MR images of a gel phantom was acquired with various tag periods and imaging flip angles to demonstrate the impact of brightness variations and to validate our method. The results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"15830 ","pages":"375-389"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12720491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145822276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes.","authors":"Yanxi Chen, Mohammad Farazi, Zhangsihao Yang, Yonghui Fan, Nicholas Ashton, Eric M Reiman, Yi Su, Yalin Wang","doi":"10.1007/978-3-031-96625-5_5","DOIUrl":"10.1007/978-3-031-96625-5_5","url":null,"abstract":"<p><p>Alzheimer's disease (AD) is a major neurodegenerative condition that affects millions around the world. As one of the main biomarkers in the AD diagnosis procedure, brain amyloid positivity is typically identified by positron emission tomography (PET), which is costly and invasive. Brain structural magnetic resonance imaging (sMRI) may provide a safer and more convenient solution for the AD diagnosis. Recent advances in geometric deep learning have facilitated sMRI analysis and early diagnosis of AD. However, determining AD pathology, such as brain amyloid deposition, in preclinical stage remains challenging, as less significant morphological changes can be observed. As a result, few AD classification models are generalizable to the brain amyloid positivity classification task. Blood-based biomarkers (BBBMs), on the other hand, have recently achieved remarkable success in predicting brain amyloid positivity and identifying individuals with high risk of being brain amyloid positive. However, individuals in medium risk group still require gold standard tests such as Amyloid PET for further evaluation. Inspired by the recent success of transformer architectures, we propose a geometric deep learning model based on transformer that is both scalable and robust to variations in input volumetric mesh size. Our work introduced a novel tokenization scheme for tetrahedral meshes, incorporating anatomical landmarks generated by a pre-trained Gaussian process model. Our model achieved superior classification performance in AD classification task. In addition, we showed that the model was also generalizable to the brain amyloid positivity prediction with individuals in the medium risk class, where BM alone cannot achieve a clear classification. Our work may enrich geometric deep learning research and improve AD diagnosis accuracy without using expensive and invasive PET scans.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"15830 ","pages":"65-78"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12965764/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147379855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation","authors":"Y. Huang, Wanqing Xie, Mingzhen Li, Mingmei Cheng, Jinzhou Wu, Weixiao Wang, Jane You, Xiaofeng Liu","doi":"10.1007/978-3-031-34048-2_28","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_28","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"5 1","pages":"360-371"},"PeriodicalIF":0.0,"publicationDate":"2023-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78747201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Better Generalization of White Matter Tract Segmentation to Arbitrary Datasets with Scaled Residual Bootstrap","authors":"Wan Liu, Chuyang Ye","doi":"10.1007/978-3-031-34048-2_48","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_48","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"39 1","pages":"629-640"},"PeriodicalIF":0.0,"publicationDate":"2023-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79474426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision","authors":"Jiexiang Wang, Chaoqi Chen","doi":"10.1007/978-3-031-34048-2_20","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_20","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"6 1","pages":"250-262"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82819634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Weakly Semi-supervised Detection in Lung Ultrasound Videos","authors":"J. Ouyang, Li Chen, Gary Y. Li, Naveen Balaraju, Shubham Patil, C. Mehanian, Sourabh Kulhare, R. Millin, K. Gregory, Cynthia Gregory, Meihua Zhu, David O. Kessler, L. Malia, Almaz S. Dessie, J. Rabiner, D. Coneybeare, B. Shopsin, A. Hersh, C. Madar, J. Shupp, L. Johnson, Jacob Avila, K. Dwyer, P. Weimersheimer, B. Raju, J. Kruecker, A. Chen","doi":"10.1007/978-3-031-34048-2_16","DOIUrl":"https://doi.org/10.1007/978-3-031-34048-2_16","url":null,"abstract":"","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"39 1","pages":"195-207"},"PeriodicalIF":0.0,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76189144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds.","authors":"Niharika S D'Souza, Archana Venkataraman","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Connectomics has emerged as a powerful tool in neuroimaging and has spurred recent advancements in statistical and machine learning methods for connectivity data. Despite connectomes inhabiting a matrix manifold, most analytical frameworks ignore the underlying data geometry. This is largely because simple operations, such as mean estimation, do not have easily computable closed-form solutions. We propose a geometrically aware neural framework for connectomes, i.e., the mSPD-NN, designed to estimate the geodesic mean of a collections of symmetric positive definite (SPD) matrices. The mSPD-NN is comprised of bilinear fully connected layers with tied weights and utilizes a novel loss function to optimize the matrix-normal equation arising from Fréchet mean estimation. Via experiments on synthetic data, we demonstrate the efficacy of our mSPD-NN against common alternatives for SPD mean estimation, providing competitive performance in terms of scalability and robustness to noise. We illustrate the real-world flexibility of the mSPD-NN in multiple experiments on rs-fMRI data and demonstrate that it uncovers stable biomarkers associated with subtle network differences among patients with ADHD-ASD comorbidities and healthy controls.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"2023 ","pages":"53-65"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11513587/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142523786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using Multiple Instance Learning to Build Multimodal Representations.","authors":"Peiqi Wang, William M Wells, Seth Berkowitz, Steven Horng, Polina Golland","doi":"10.1007/978-3-031-34048-2_35","DOIUrl":"10.1007/978-3-031-34048-2_35","url":null,"abstract":"<p><p>Image-text multimodal representation learning aligns data across modalities and enables important medical applications, e.g., image classification, visual grounding, and cross-modal retrieval. In this work, we establish a connection between multimodal representation learning and multiple instance learning. Based on this connection, we propose a generic framework for constructing permutation-invariant score functions with many existing multimodal representation learning approaches as special cases. Furthermore, we use the framework to derive a novel contrastive learning approach and demonstrate that our method achieves state-of-the-art results in several downstream tasks.</p>","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"397 1","pages":"457-470"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12456966/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88972802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}