13:30 | 0874.
| Deep learning enabled MRI general denoising at 0.55T Zheren Zhu1, Azaan Rehman2, Michael Ohliger1, Yoo Jin Lee1, Hui Xue2,3, and Yang Yang1 1Radiology and Biomedical Imaging, University of California, San Francisco, CA, United States, 2National Institutes of Health, Bethesda, MD, United States, 3National Heart Lung and Blood Institute, Bethesda, MD, United States Keywords: AI/ML Image Reconstruction, Visualization, Mid-Field MRI, Denoising Motivation: Recent advancements in 0.55T MRI systems present promising opportunities for affordable and accessible MRI. Enhancing SNR to mitigate the inherent limitations of mid field strength is a crucial step in advancing this technology. Goal(s): In this study, we aim to advance 0.55T MRI for speed and quality through a deep-learning-driven general denoise method processing low-SNR scans of various body parts and sequences. Approach: We constructed a model with a spatial-temporal attention mechanism and employed massive complex image data for training. Results: The proposed method significantly improves low SNR single-repetition images at 0.55T, making the results comparable or superior to the averages of multi-repetitions. Impact: With robust denoising on mid-field systems, enhanced image quality and quicker scans can be expected for more accurate diagnoses and improved patient experience. New sequences can be developed and paired to further advance the system. |
13:42 | 0875.
| Accelerating Low-Field Prostate DWI: Self-Supervised Denoising for Rapid Scan Acquisition Laura Pfaff1,2, Omar Darwish2, Cornelius Eichner2, Fabian Wagner1, Mareike Thies1, Nastassia Vysotskaya1, Elisabeth Weiland2, Thomas Benkert2, Marcel Dominik Nickel2, Tobias Wuerfl2, and Andreas Maier1 1Pattern Recognition Lab, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany, 2Magnetic Resonance, Siemens Healthineers AG, Erlangen, Germany Keywords: Analysis/Processing, Low-Field MRI, Diffusion-Weighted Imaging Motivation: Diffusion-weighted imaging (DWI) is crucial for lesion detection but suffers from inherently low signal-to-noise ratio (SNR), especially in low-field settings. Goal(s): The goal of this work is to accelerate low-field prostate DWI, reducing the number of image repetitions and scan time while maintaining image quality. Approach: We present a self-supervised denoising method employing Stein's unbiased risk estimator (SURE) and a physics-based noise model and evaluate the denoising results without relying on ground-truth data. Results: Our method excels in preserving image content, outperforming other denoising techniques. This allows a substantial reduction in scan time, making it a promising advancement in low-field DWI. Impact: Our proposed denoising approach accelerates low-field
prostate DWI via self-supervised denoising, improving scan efficiency without
compromising image quality. We further demonstrate how to employ a
physics-based noise model to evaluate denoising performance in the absence of noise-free
ground-truth data. |
13:54 | 0876.
| Multi-Atlas Segmentation of MR Brain Images with Lesions Using Subspace-Assisted-GAN Based Image Recovery Yi Ding1, Huixiang Zhuang1, Yue Guan1, Yunpeng Zhang1, Ziyu Meng1, Zhi-Pei Liang2,3, and Yao Li1 1School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China, 2Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL, United States, 3Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, United States Keywords: Analysis/Processing, Machine Learning/Artificial Intelligence, Multi-Atlas Segmentation Motivation: Multi-atlas segmentation (MAS) of MR brain images with lesions is of great clinical significance but remains challenging due to registration inaccuracy caused by pathologies. Goal(s): Our goal was to improve the MAS performance of pathological brain images by restoring more accurate normal images form lesion data. Approach: We integrate a novel subspace-assisted generative model into the MAS framework for estimation of subject-specific posterior normative distribution, which can effectively extract a “hypothetical” normal image from the lesion data, thus enhancing the accuracy of lesion segmentation. Results: Our method produced significantly improved results in normal recovery and MAS compared to the state-of-the-art methods. Impact: The proposed method significantly improves the performance of segmentation of MR brain images with lesions, which may provide a useful tool for tissue segmentation in pathological brain images. |
14:06 | 0877.
| LESEN: Label-Efficient Self-Ensembling Network for Multi-Parametric MRI-based Visual Pathway Identification Alou Diakite1,2, Cheng Li1, Lei Xie3, Yuanjing Feng3, Hua Han1, Hairong Zheng1, and Shanshan Wang1,4,5 1Paul C Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 2University of Chinese Academy of Science, Beijing, China, 3Zhejiang University of Technology, Hangzhou, China, 4Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China, 5Peng Cheng Laboratory, Shenzhen, China Keywords: Analysis/Processing, Brain, Semi-supervised learning Motivation: Obtaining labeled data for visual pathway (VP) segmentation can be laborious and time-consuming. Therefore, it is crucial to develop algorithms with good performance in situations with limited labeled samples. Goal(s): The goal is to propose a label-efficient self-ensembling network (LESEN) for VP segmentation. Approach: We first introduce the LESEN model which consists of a student model and a teacher model that learn from each other using supervised and unsupervised losses. Additionally, a novel reliable unlabeled sample selection (RUSS) method is introduced to enhance the effectiveness of the LESEN model. Results: The LESEN model surpasses existing techniques on the human connectome project (HCP) dataset. Impact: The
proposed LESEN model can improve visual pathway segmentation accuracy and
reliability with limited labeled data, advancing multi-parametric MRI analysis
in clinical and research settings. |
14:18 | 0878.
| Single Generalized Convolutional Neural Network for Automatic Liver Extraction and R2* Estimation for Iron Overload Assessment Utsav Shrestha1,2, Cara Morin3, Zachary R. Abramson2, and Aaryani Tipirneni-Sajja1,2 1University of Memphis, Memphis, TN, United States, 2St. Jude Children’s Research Hospital, Memphis, TN, United States, 3Cincinnati Children’s Hospital Medical Center, Cincinnati, OH, United States Keywords: Analysis/Processing, Quantitative Imaging, Deep Learning, Generalized CNN, R2*, HIC Motivation: Although R2*-MRI is extensively validated to assess hepatic iron content(HIC), different MRI sequences are used, hence multiple sequence-specific convolutional neural networks(CNNs) have been proposed for automated liver segmentation and HIC estimation. Goal(s): Assess feasibility of generalized CNN with limited training datasets to automate liver segmentation across various MRI sequences used to quantify HIC in clinical practice. Approach: Data of twenty-nine patients scanned using multi-echo 2D/3D breath-hold and free-breathing Cartesian and radial GRE sequences were used to train U-Net CNN using incremental learning. Results: Excellent agreement was obtained between manual and single generalized U-Net for liver segmentation and R2* estimation across multiple MRI sequences. Impact: Generalized CNN using
incremental learning minimizes the need for extensive training datasets to
segment liver across multiple MRI sequences. With additional fine-tuning and
validation, this approach can be widely applicable for sequence-independent
liver segmentation and assessment of hepatic iron content. |
14:30 | 0879.
| A deep multimodal fusion framework for MRI-based segmentation of intracranial arterial calcification Xin Wang1,2, Gador Canton2, Yin Guo2,3, Kaiyu Zhang2,3, Thomas S. Hatsukami2,4, Jin Zhang5, Beibei Sun5, Huilin Zhao5, Yan Zhou5, Mahmud Mossa-Basha2, Chun Yuan2,6, and Niranjan Balu2 1Department of Electrical and Computer Engineering, University of Washington, Seattle, WA, United States, 2Vascular Imaging Lab, Department of Radiology, University of Washington, Seattle, WA, United States, 3Department of Bioengineering, University of Washington, Seattle, WA, United States, 4Department of Surgery, University of Washington, Seattle, WA, United States, 5Department of Radiology, Ren Ji Hospital, Shanghai Jiao Tong University, Shanghai, China, 6Department of Radiology and Imaging Sciences, University of Utah, Salt Lake City, UT, United States Keywords: Analysis/Processing, Segmentation, Vessel wall imaging, intracranial calcification, multimodal fusion Motivation: Recently, MRI-based intracranial arterial calcification segmentation has got increasing interest due to its clinical value, but current approaches to this challenging problem suffer from poor performance. Goal(s): To develop a deep learning model for enhancing calcification segmentation on MRI by using CT as additional training resource. Approach: A dissimilarity loss is proposed to align the latent features learned from MRI and CT of the same subject, thus making MR feature simpler and it easier for segmentation. Results: Compared with several commonly used segmentation networks, our model demonstrates superior performance in calcification segmentation. The ablation study further shows the effectiveness of the dissimilarity loss. Impact: The proposed model could be applied in clinical scenarios to automatically segment calcification on cerebral MR scans and it does not require CT imaging. Radiologists could leverage the segmentation result in the analysis of various vessel plaque components. |
14:42 | 0880.
| AtlasSeg: Atlas Prior Guided Dual-UNet for Cortical Segmentation in Fetal Brain MRI Haoan Xu1, Tianshu Zheng1, Xinyi Xu1, Yao Shen1, Jiwei Sun1, Cong Sun2, Guangbin Wang3, and Dan Wu1 1Department of Biomedical Engineering, Zhejiang University, Hangzhou, China, 2Department of Radiology, Beijing Hospital, Beijing, China, 3Department of Radiology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China Keywords: Analysis/Processing, Segmentation, Fetal Brain MRI; Artificial Intelligence Motivation: Automatic segmentation of fetal brain remains challenging partially due to the dynamically changing anatomical structures during fetal brain development. Goal(s): To enhance segmentation accuracy through incorporating gestational age-specific information as a guidance, we introduce AtlasSeg, a dual-U-shape network with dense attentive interactions. Approach: By providing atlas volume and segmentation label at the corresponding gestational age, AtlasSeg effectively extracts the contextual features of age-specific patterns and structures that assist segmentations. Results: AtlasSeg demonstrated superior performance against six other segmentation networks in both standard and out-of-distribution experiments, in two fetal MRI datasets. Ablation tests further demonstrated the role of atlas guidance. Impact: Through gestational age-specific
atlas-guided information, AtlasSeg can serve as
an accurate and robust automatic segmentation tool for its superior performance
in both in-distribution and out-of-distribution tests, which is useful for quantitative
analysis in large-scale fetal brain studies. |
14:54 | 0881.
| Enhancing transcranial focused ultrasound treatment planning with synthetic ct from ultra-short echo time (UTE) MRI: a deep learning approach Dong Liu1, Zhuoyao Xin2, Robin Ji3, Fotis Tsitsos3, Sergio Jiménez-Gambín3, Vincent P Ferrera3, Elisa E. Konofagou3, and Jia Guo3 1Department of Neuroscience, Columbia University, New York City, NY, United States, 2F.M. Kirby Research Center for Functional Brain Imaging, Kennedy Krieger Institute, Baltimore, MD, United States, 3Department of Biomedical Engineering, Columbia University, New York City, NY, United States Keywords: Analysis/Processing, Focused Ultrasound, UTE MRI, image guided therapy Motivation: There’s a clinical interest in exploring an alternative option using ultrashort-time-echo MRI to replace CT imaging for accurate transcranial FUS treatment planning. Goal(s): To employ a deep learning approach to generate synthetic CT images from a limited UTE-MRI dataset. Approach: A deep learning framework based on 3D Transformer U-net is applied to the paired UTE-CT dataset and acoustic simulation is performed to validate the results. Results: Utilizing UTE MRI can offer synthetic CT as an alternative to traditional CT imaging. The simulations showed a minimal maximum acoustic pressure difference of less than8% and a focus shift of less than1.5mm compared to CT-based simulations. Impact: This study introduces a novel multi-task deep learning approach that enables accurate synthetic CT generation from limited UTE-MRI data. This innovation provides a cost-effective and radiation-free alternative to traditional CT imaging, significantly enhancing transcranial focused ultrasound treatment planning. |
15:06 | 0882.
| Hepatobiliary Phase Synthesis Using Multi-Task Learning GAN: Application to Liver Fibrosis Classification Rencheng Zheng1, Nannan Shi2, Yuxin Shi2, Zidong Yang3, Xueqin Xia1, Hing-Chiu Chang4, Weibo Chen5, Ying-Hua Chu6, Chengyan Wang7, and He Wang1 1Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China, 2Department of Radiology, Shanghai Public Health Clinical Center, Shanghai, China, 3USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA, United States, 4Department of Biomedical Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong, 5Philips Healthcare, Shanghai, China, 6Siemens Healthineers, Shanghai, China, 7Human Phenome Institute, Fudan University, Shanghai, China Keywords: AI/ML Image Reconstruction, Liver Motivation: Hepatobiliary phase (HBP) has important clinical diagnostic value for liver diseases, but its long acquisition time can pose issues with scanning resources and patient cooperation. Goal(s): Our goal was to design a generative model for HBP synthesis based on early phases in hepatobiliary-specific contrast-enhanced MRI. Approach: We proposed a multi-task learning deep learning model and evaluated its performance on a multi-center dataset. Results: The proposed model exhibited superior HBP synthesis performance compared to the classic Pix2Pix model. The synthetic HBP was comparable to the real HBP, and significantly outperformed early phases in subsequent liver fibrosis grading tasks. Impact: The proposed approach has the potential to accurately synthesize HBP, which is expected to be extended to clinical practice for rapid acquisition of HBP in hepatobiliary-specific contrast-enhanced MRI, thereby significantly reducing scanning time and alleviating clinical stress. |
15:18 | 0883.
| Metal artifact synthesis: Enabling inclusive Deep learning for patients with implants Vanika Singhal1, Deepa Anand1, Florintina C1, Harshit Dubey1, RAdhika Madhavan2, Chitresh Bhushan2, and Dattesh Shanbhag1 1GE HealthCare, Bangalore, India, 2GE HealthCare, Niskayuna, NY, United States Keywords: Analysis/Processing, Artifacts, Metal implants, simulation, augmentation Motivation: AI medical imaging solutions are impacted by the presence metal implants and a design of appropriate synthesis method can improve robustness of DL models. Goal(s): Simulation of patient medical condition like metal artifacts in MRI medical images. Approach: The proposed method blends regions from template images containing metal artifacts into target images by using metal segmentation mask for selection, blending this region into a chosen target image RoI . Results: Improvement in knee classification accuracy of 8% and decrease in spine plane distance error by 25-40% and plane angle error by 4-30% using the proposed approach. Impact: A data adaptive metal simulation method in
semantically relevant regions in anatomy ensures robust of DL models in
patients with metal implants who hitherto would not have benefitted from AI
driven tasks . |