1. Y. Lyu, H. Liao, H. Zhu, and S. Kevin Zhou, “A3DSegNet: Anatomy-aware artifact disentanglement and segmentation network for unpaired segmentation, artifact reduction, and modality translation,” Information Processing in Medical Imaging (IPMI), 2021. (accepted)
Introduction to IPMI: The full name of IPMI is Information Processing in Medical Imaging. The IPMI conference series focuses on novel developments in the acquisition, formation, analysis and display of medical images. IPMI places the highest importance on high-quality submissions coupled with presentations and thorough discussions of the presented contributions. IPMI is held every two years. The 27th international conference on Information Processing in Medical Imaging (IPMI) will be held in Rønne at the island of Bornholm in Denmark from Sunday June 27th to Friday July 2nd, 2021.
2. R. Gao, Z. Hou, J. Li, H. Han, B. Lu, and S. Kevin Zhou, “Joint Coronary Centerline Extraction and Lumen Segmentation from CCTA using CNNTracker and Vascular Graph Convolutional Network,” IEEE International Symposium on Biomedical Imaging (ISBI), 2021. (accepted)
Abstract: Automatic analysis of coronary artery in coronary computed tomography angiography (CCTA) is important for clinicians to diagnose and evaluate coronary artery disease (CAD). Often there are two analysis tasks involved: centerline extraction and lumen segmentation, which are related yet often treated separately in the literature. In this work, we leverage their mutual relationship and propose an automatic approach for joint centerline extraction and lumen segmentation from CCTA using a hybrid of deep learning models. Our approach features the following designs, including: (i) the use of CNNTracker that traces out the centerline from seeds to detected ostia or the end of vessels, which fixes the breakage issue commonly found in previous pixel-based segmentation methods; (ii) a vascular Graph Convolutional Network (GCN) that leverages the geometric shape prior for accurate mesh-based lumen segmentation; (iii) the alternation between CNNTracker and GCN that refines the centerline and reduces the drift in tracking.
Introduction to ISBI: The IEEE International Symposium on Biomedical Imaging (ISBI) is a scientific conference dedicated to mathematical, algorithmic, and computational aspects of biological and biomedical imaging, across all scales of observation. It fosters knowledge transfer among different imaging communities and contributes to an integrative approach to biomedical imaging. ISBI is a joint initiative from the IEEE Signal Processing Society (SPS) and the IEEE Engineering in Medicine and Biology Society (EMBS).
3. P. Liu, et al. S. Kevin Zhou, “Deep learning to segment pelvic bones: large-scale CT datasets and baseline models,” Information Processing in Computer-Assisted Interventions (IPCAI), 2021. (accepted)
Purpose: Pelvic bone segmentation in CT has always been an essential step in clinical diagnosis and surgery planning of pelvic bone diseases. Existing methods for pelvic bone segmentation are either hand-crafted or semi-automatic and achieve limited accuracy when dealing with image appearance variations due to the multi-site domain shift, the presence of contrasted vessels, coprolith and chyme, bone fractures, low dose, metal artifacts, etc. Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored. Methods: In this paper, we aim to bridge the data gap by curating a large pelvic CT dataset pooled from multiple sources, including 1184 CT volumes with a variety of appearance variations. Then we propose for the first time, to the best of our knowledge, to learn a deep multi-class network for segmenting lumbar spine, sacrum, left hip, and right hip, from multiple-domain images simultaneously to obtain more effective and robust feature representations. Finally, we introduce a post-processor based on the signed distance function (SDF). Results: Extensive experiments on our dataset demonstrate the effectiveness of our automatic method, achieving an average Dice of 0.987 for a metal-free volume. SDF post-processor yields a decrease of 15.1% in Hausdorff distance compared with traditional post-processor. Conclusion: We believe this large-scale dataset will promote the development of the whole community and open source the images, annotations, codes, and trained baseline models at https://github.com/ICT-MIRACLE-lab/CTPelvic1K.
Introduction to IPCAI: The Information Processing in Computer-Assisted Interventions (IPCAI) is one of the most important forums for innovation in the domain of computer-assisted surgery. The IPCAI conference is a truly international interdisciplinary conference bringing clinicians, computer scientists, engineers, and other researchers at a unique setting. The format of the meeting is designed specifically for active engagement from the attendees. The 12th IPCAI meeting is intended to be on June 22-23, 2021, in conjunction with the Computer-Assisted Radiology and Surgery (CARS) Congress 2021, Munich, Germany.
4. R. Gao, Y. Gao, H. Han, S. Kevin Zhou, and Bin Lu, “Cardiac event prediction by evaluating variation of perivascular adipose tissue in serial coronary CT angiography,” European Congress of Radiology (ECR), 2021. (accepted)
Abstract: The study uses an automated algorithm to extract the perivascular adipose tissue(PVAT), which proves that the variation of PVAT from serial CCTA is a novel indicator to predict cardiac events. With the increase of PVAT, the risk of cardiac event also grows.
Introduction to ECR: The European Congress of Radiology (ECR) is not only the largest and most important medical imaging conference in Europe, it is also the official annual meeting of the European Society of Radiology, which is one of the largest and most influential radiology societies in the world, with more than 75,500 members from more than 157 countries. Every year more than 30,000 participants span all areas of the radiology arena including: radiology professionals, radiographers, physicists, and industry representatives attend the ECR at the Austria Center Vienna.
5. P. Cheng, H. Liao, G. Wong, J. Luo, S. Kevin Zhou and R. Chellappa, “XraySyn: Realistic view synthesis from a single radiograph through CT priors,” The 35th AAAI Conference on Artificial Intelligence, February 2021. (accepted)
Abstract: A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane. Hence, radiograph analysis naturally requires physicians to relate the prior about 3D human anatomy to 2D radiographs. Synthesizing novel radiographic views in a small range can assist physicians in interpreting anatomy more reliably; however, radiograph view synthesis is heavily ill-posed, lacking in paired data, and lacking in differentiable operations to leverage learning-based approaches. To address these problems, we use Computed Tomography (CT) for radiograph simulation and design a differentiable projection algorithm, which enables us to achieve geometrically consistent transformations between the radiography and CT domains. Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs. To the best of our knowledge, this is the first work on radiograph view synthesis. We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without groundtruth bone labels.
Introduction to AAAI: The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) will be held virtually February 2-9, 2021.