Ping Yin¹ and Nan Hong^1
1Department of Radiology, Peking University People's Hospital, Beijing, China

Keywords: MSK, Tumor

Early detection and correct diagnosis are key to adequate and successful treatment of PSTs. Based on multi-sequence MRI images, physician’s labeling, segmentation model, and clinical features, six classification models were built. The highest scoring model (model 6) achieved 0.836 AUC, 0.781 ACC in the prospective test set, which was comparable to that of senior residents and junior resident. However, the diagnosing time of DL model is significantly shorter than physicians. Our attention-based two stage DL model allowed the accurate segmentation and classification of benign and malignant PSTs without enhanced MRI and may thus facilitate diagnosis.

View Presentation Video

Dara L Kraitchman^1,2,3, Michele Doucet⁴, Sarah J Powers³, Alainah Bhutta⁵, Emily Kulp⁶, Tina Ehtiati⁷, Cheri Rice¹, Cindy Maranto¹, Kathleen Gabrielson³, Cory Brayton³, and Brian Ladle^4
1Russell H Morgan Department of Radiology and Radiological Science, Johns Hopkins University, Baltimore, MD, United States, ²Center for Image-Guided Animal Therapy, Baltimore, MA, United States, ³Department of Molecular & Comparative Pathobiology, Johns Hopkins University, Baltimore, MD, United States, ⁴Department of Oncology, Johns Hopkins University, Baltimore, MD, United States, ⁵University of Georgia College of Veterinary Medicine, Athens, GA, United States, ⁶Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD, United States, ⁷Siemens Medical Solutions USA, Inc., Baltimore, MD, United States

Keywords: Bone, MR-Guided Interventions, cryoablation

Osteosarcoma (OSA) is the most common bone cancer in young adults and dogs and almost invariably lethal when the cancer spreads.  MR-guided cryoablation offers the potential to cause direct bone necrosis and palliative pain management and has shown the potential to upregulate the immune response in prostate and breast cancer to prevent or shrink metastatic disease.  The current study seeks to determine the immune response of MR-guided cryoablation in spontaneously occurring canine osteosarcoma in comparison to X-ray-guided intratumoral Stimulator of Interferon Gene (STING) immunotherapy as determine by survival time and measurement of inflammatory infilitrates.

View Presentation Video

Timothy JP Bray¹, Alexis JP Jones², Margaret A Hall-Craggs¹, and Hui Zhang^3
1Centre for Medical Imaging, University College London, London, United Kingdom, ²Rheumatology, University College London Hospital, London, United Kingdom, ³Centre for Medical Image Computing, University College London, London, United Kingdom

Keywords: Bone, Inflammation

We present a deep learning workflow which segments and quantifies bone marrow oedema (BMO) in a single deep learning step. Detection and quantification of BMO plays a crucial role in diagnosis and monitoring of patients with inflammatory diseases of the skeleton, including spondyloarthritis (SpA), and various segmentation methods have been developed to facilitate BMO quantification. However, previous attempts have used multiple algorithms in sequence to achieve satisfactory performance. To improve on this, we propose a simplified approach that avoids the need for such sequential algorithms, thus simplifying the workflow, eliminating potential error sources and reducing the need for human input.

Xiangwen Li¹, Qing Li², and chen shuang^3
1Huashan hospital Fudan university, Shang hai, China, ²MR Collaborations, Siemens Healthcare Ltd., Shang hai, China, ³Radiology, Huashan hospital Fudan university, Shang hai, China

Keywords: MSK, Diffusion/other diffusion imaging techniques

In this study, we initially revealed the feasibility of conventional MRI features and whole-tumor histogram features of diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI) parameters in assessing hypoxia-inducible factor 1-alpha (HIF-1α) expression of soft tissue sarcomas (STS). On this basis, we performed a short-term survival analysis of the study population. The findings suggest that MRI morphological features and histogram features of quantitative parameters help predict higher HIF-1α expression and may significantly predict prognosis in patients with STS.

View Presentation Video

Talon Johnson¹, Jimin Ren^1,2, and Anke Henning^1,2
1Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, United States, ²Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX, United States

Keywords: Bone, Fat, Metabolism, diabetes

This study evaluated the sex factor in affecting fat distribution in bone marrow and subcutaneous tissue in human lower extremity. Bone marrow fat (BMF) was characterized by the cross-sectional area in the fibula bone and subcutaneous fat (SF) was measured by the thickness of SF (SFT) in the periphery of calf muscle. It is found that SFT and BMF are statistically significantly correlated to BMI and age, respectively, in women (n = 43), but not in men (n = 59). For a subgroup of subjects with thinner SFT (<15 mm, n = 87), SFT is negatively correlated to BMF.

View Presentation Video

Ping Yin¹ and Nan Hong^1
1Department of Radiology, Peking University People's Hospital, Beijing, China

Keywords: MSK, Multimodal, Osteosarcoma

In this study, we simultaneously compared the predictive value of ADC, IVIM and semi-quantitative and quantitative DCE-MRI parameters for the efficacy of NACT. We found that D-Bi, D*-Bi, and f-Bi post-NACT and ΔD-Bi had statistical differences between the good response group and the poor response group. ROC curve showed that f-Bi post-NACT had the best performance in all parameters, with AUC of 0.769, sensitivity of 1, and specificity of 0.538. Correlation analysis showed that the efficacy of NACT was negatively correlated with D-Bi, D*-Bi post-NACT and ΔD-Bi, and was significantly positively correlated with f-Bi post-NACT.

 

View Presentation Video

Zhenhong Liao¹ and Xiaoyong Zhang^2
1Deyang People's Hospital, Sichuan, China, ²Philips Healthcare, Chengdu, China

Keywords: Joints, Vessels, osteonecrosis of the femoral head

Dynamic evaluation of retinacular arteries is essential for understanding blood supply changes occurring in osteonecrosis of the femoral head (ONFH). The steady-state (SS) magnetic resonance angiography (MRA) may be an effective method as our previous study suggested, however its feasibility is yet to be determined. Therefore, this study intends to use gadobutrol-based SS MRA to evaluate the blood supply of ONFH.

View Presentation Video

L. Tugan Muftuler¹ and Matthew D. Budde^1
1Medical College of Wisconsin, Milwaukee, WI, United States

Keywords: MSK, Perfusion, lumbar spine, low back pain

Some patients with chronic low back pain (cLBP) do not show any diagnosable conditions in conventional imaging methods. Studies suggested that pain could be associated with the degeneration of vertebral endplate region in those nonspecific cLBP patients. The endplates around degenerating discs experience trauma, which leads to inflammation, angiogenesis, neurogenesis and infection. Currently, there is no established method to diagnose such pathologies. We previously reported associations between increased endplate perfusion and experience of cLBP using DCEMRI. In this study we explored Arterial Spin Labeling to avoid using contrast agents. Results show that FAIR could be used to study endplate perfusion.

View Presentation Video

Xin Mu¹, Meng Tian², Huahui Xu³, Chang Ni¹, Yanbin Li⁴, Xiangwei Kong¹, Xiaoli Gu³, and Jeff L Zhang^1
1Vascular and Physiologic Imaging Research (VPIR) Lab, School of Biomedical Engineering, ShanghaiTech University, Shanghai, China, ²School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China, ³Department of Radiology, Shanghai Guanghua Hospital of Integrative Medicine, Shanghai, China, ⁴Central Research Institute, UIH Group, United Imaging Healthcare, Shanghai, China

Keywords: Skeletal, Muscle

Diffusion tensor imaging (DTI) has been shown to be highly sensitive to subtle pathological alterations caused by multiple diseases. Utilizing this capability of DTI, in this study we characterized post-exercise hyperemic responses of calf muscles. We found that multiple DTI measures, including ADC, λ_1-3, and RD, increased significantly in activated muscles, and more than in those in non-activated muscles. Of particular interest was the significant increase in λ₃ and RD of the activated muscle, indicating a relatively higher degree of increase in water diffusion along the cross-section direction of muscle fibers.

View Presentation Video

Esha Baidya Kayal¹, Devasenathipathy Kandasamy², Kedar Khare¹, Raju Sharma², Sameer Bakhshi², and Amit Mehndiratta^1,2
1Indian Institute of Technology Delhi, New Delhi, India, New Delhi, India, ²All India Institute of Medical Sciences, New Delhi, India, New Delhi, India

Keywords: MSK, Cancer, Intravoxel Incoherent motion, Chemotherapy response prediction, Performance comparison

Predictive performance of penalty-based IVIM analysis methodologies BE+TV and BE+HPF for response to Neoadjuvant Chemotherapy have been evaluated using clinical dataset with osteosarcoma in comparison with existing IVIM analysis methods. IVIM datasets before and after chemotherapy were analyzed using 5 IVIM analysis methods – Bi-exponential model and two of its segmented variants and penalty-based BE+TV and BE+HPF methods. Results showed, IVIM parameters estimated by BE+TV and BE+HPF methods produced improved prediction of response to chemotherapy in osteosarcoma than the existing IVIM analysis methods at both the time-points, before and after chemotherapy.

View Presentation Video

Peng Gao¹, Weisheng Zhang¹, and Hexin Feng^2
1Dalian Medical University, Dalian, China, ²China Medical University, Shenyang, China

Keywords: Muscle, Tumor

区分不同亚型的纤维化肿瘤仍然具有挑战性，但具有重要的临床意义。本研究的目的是评估基于常规 MRI 序列的影像组学在区分惰性纤维化肿瘤和躯干和四肢浸润性纤维化肿瘤的价值。预测模型基于 T1 图像的逻辑回归在区分惰性纤维瘤和侵袭性纤维瘤方面具有最好的预测效率，对 T1 和 T2 预测模型贡献最大的特征分别是 idn 和最小轴长。病变的大小和深度对判断肿瘤的性质有一定的参考价值。

Linzhe Li¹, Junhong Duan¹, Muqi Liu¹, Yunjie Liao¹, Pengzhi Hu¹, and Chen Thomas Zhao^2
1Department of Medical Imaging, the Third Xiangya Hospital, Central South University, Changsha, China, ²Philips Healthcare, Guangzhou, China

Keywords: MSK, Fat, CS AI, Bone Marrow Fat, mDIXON-quant

Compressed SENSE (CS) has been suggested to speed up MRI acquisition in clinical studies, while reducing artefacts and improving image quality. To date, the optimal acceleration factor (AF) for Compressed SENSE AI (CS AI) versus conventional compressed SENSE (CS) on lumber spine images remains unclear. In this study, the impact of CS AI technique with different acceleration factors compared with conventional CS on the utility of measuring lumber spine fat was investigated. Results of this study showed that CS AI not only shortened MRI acquisition time, but also ensured image quality, as well as clinical diagnostic accuracy and clinical throughput.

View Presentation Video

Alfredo Liubomir Lopez Kolkovsky¹, Béatrice Matot¹, Harmen Reyngoudt¹, Benjamin Marty¹, Ericky Caldas de Almeida Araujo¹, and Yves Fromes^1
1NMR Laboratory , Neuromuscular Investigation Center, Institute of Myology, Paris Cedex 13, France

Keywords: Muscle, Aging, Multi-contrast, Metabolism, Non-proton, Spectroscopy

The age-related loss of muscle mass, strength and quality is a multifactorial process whose mechanisms are incompletely understood. NMR allows investigating numerous physiological and biochemical variables in vivo dynamically. Here, 51 physically active subjects performed a normalized plantar flexion exercise to evaluate vascular response (blood flow, T₂*, water compartmentalization), tissue oxygenation and oxidative energy metabolism (pH, mitochondrial oxidative capacity, work to [ADP] ratio). Results showed that the vascular and metabolic function was preserved in old subjects relative to young and middle-aged participants. We conclude that vascular and oxidative metabolism impairments are not a necessary condition of old age.

View Presentation Video

Seok Hahn¹, Jisook Yi², Ho-Joon Lee², Sunggun Lee³, Sekyoung Park⁴, Joonsung Lee⁵, Jose de Arcos⁶, and Maggie Fung^7
1Department of Radiology, Haeundae Paik Hospital, Inje University College of Medicine, Busan, Korea, Republic of, ²Department of Radiology, IHaeundae Paik Hospital, Inje University College of Medicine, Busan, Korea, Republic of, ³Division of Rheumatology, Department of Internal Medicine, Haeundae Paik Hospital, Inje University College of Medicine, Busan, Korea, Republic of, ⁴Department of Radiology, Kosin University Gospel Hospital, Kosin University College of Medicine, Busan, Korea, Republic of, ⁵GE Healthcare, Seoul, Korea, Republic of, ⁶GE Healthcare, Little Chalfont, United Kingdom, ⁷GE Healthcare, New York, NJ, United States

Keywords: Joints, MSK, sacroiliac joint, zero echo time imaging, deep learning reconstruction

The aim of this study was to compare the diagnostic performance of DLR of ZTE imaging for bone erosion in axial spondyloarthritis, using CT as the reference standard. Twenty-three patients with suspicion of sacroiliitis underwent both CT and MR scans of sacroiliac joints included for analysis. ZTE with or with DLR showed higher correlation coefficients than T1WI for two readers. Inter-reader agreements showed moderate to substantial agreement. ZTE DLR improves diagnostic performance in the detection of SIJ bone erosion in patients with axial spondyloarthritis compared with T1WI and ZTE without DLR.

Jianfeng Bao¹, Xiao Wang², Yuchuan Zhuang³, Liangjie Lin⁴, Yong Zhang², and Jingliang Cheng^2
1Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, zhengzhou, China, ²Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China, ³Department of Electronic Science, University of Rochester, ROCHESTER, NY, United States, ⁴Philips Healthcare, Beijing, China

Keywords: Bone, Fat, intermolecular double-quantum coherence,fat composition,magnetic resonance spectroscopy

Unsaturated fatty acids in the bone marrow may play a critical role in bone metabolism, however, these peaks cannot be well resolved by conventional MRS techniques due to local intensive B0 inhomogeneities. We introduced intermolecular double-quantum coherence to enhance the spectrum resolution on clinical 3.0 T within one minute and more unsaturated peaks can be identified.  

View Presentation Video

Michael Mills¹, Greta Brezgyte¹, Bernard Ho², Julian Pearce², Kristiana Gordon^1,2, Peter S Mortimer^1,2, Pia Ostergaard¹, and Franklyn A Howe^1
1St George's University of London, London, United Kingdom, ²St George's University Hospitals NHS Foundation Trust, London, United Kingdom

Keywords: Vessels, Genetic Diseases, lymphatic

MRI can investigate lymphatic dysfunction and lymphoedema (a chronic swelling of interstitial fluid), however little quantitative research has been published. Dynamic Contrast-Enhanced Magnetic Resonance Lymphangiography (DCE-MRL) allows identification of lymph vessels in both healthy and lymphoedematous limbs, and was used to study the oedematous limbs of patients where the lymphoedema was associated with a mutation of the FOXC2 gene. Signal measured in leg lymphatics of these patients (n=6) peaked significantly earlier than in non-oedematous limbs (n=6) and demonstrated higher peak signals, despite an impaired lymphatic system and therefore an expectation of more sluggish drainage.

View Presentation Video

Qizheng Wang¹, Meiyi Yao², Yandong Liu³, Xinhang Song², Xiaoying Xing¹, Yongye Chen¹, Ke Liu¹, Weili Zhao¹, Xiaoguang Cheng³, Shuqiang Jiang², and Ning Lang^1
1Peking University Third Hospital, Beijing, China, ²Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China, ³Department of Radiology, Beijing Jishuitan Hospital, Beijing, China

Keywords: Joints, Segmentation

Segmentation of synovial-related structures in MRI images can help assess synovitis-effusion,  infrapatellar fat pad (IPFP) changes, and response to treatment, which is important for the clinical diagnosis of knee disease. However, segmenting images manually, which depends on the skill and experience of the physician; furthermore, it is time-consuming for radiologists. In this study, a deep learning pipeline for the 3D segmentation of the suprapatellar capsule (SC) and IPFP and knee synovitis classification were developed using proton density (PD)-weighted images of sagittal fat-suppressed knees, the most commonly used sequence in clinical practice, to support clinical decision-making. 

View Presentation Video

Jinling Mao¹, Zhongqi Zhu¹, Yinghao Li¹, Hongzhi Wang¹, and Jie Shi^2
1East China Normal University, Shanghai, China, ²Shanghai Guanghua Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai, China

Keywords: Vessels, Inflammation, synovitis;Pannus;Wrist joint

In this paper, 18 cases of wrist magnetic resonance enhancement were collected, a pixel-by-pixel time-intensity curves (TIC) analysis method was proposed, four types of enhancement curves were customized, and compared with the synovitis score, the results showed that the area of the rapidly rising and descending pixel area was extremely correlated with the synovitis score (r=0.812).

View Presentation Video

Ziwei Zhang¹, Lingling Song¹, Weixin He¹, Qi Zeng¹, Lisha Nie², Xiaocheng Wei², Jiawei Wang¹, He Sui¹, Zhaoshu Huang¹, Xia Zhu¹, Chen Liang¹, and Yu Li^1
1The Affiliated Hospital of Guizhou Medical University, GuiYang, China, ²GE Healthcare, MR Research China, BeiJing, China

Keywords: Skeletal, Skeletal

The current study aims to compare the detection ability of zero echo time(ZTE) MRI and CT in presenting bony change of sacroiliac joint in ankylosing spondylitis. It was concluded that the ankylosing spondylitis detection rate was comparable between ZTE MRI and CT, where the detection rate of bony erosions by ZTE MRI was higher than that by CT. Our observations indicated that in the future, the ZTE MRI may potentially replace the ionization-related CT method by providing a more comprehensive evaluation of sacroiliitis in ankylosing spondylitis patients.

Siyu Liu¹, Yishi Wang², and Songtao Ai^1
1Shanghai Ninth People's Hospital, Shanghai, China, ²Philips Healthcare, Beijing, China, Beijing, China

Keywords: Muscle, Cancer

Dermatofibrosarcoma protuberans （DFSP） is a rare low to intermediate grade soft tissue sarcoma of skin, but the fibrosarcomatous DFSP （FS-DFSP） is a clearly malignant pathological subtype. The identification of malignant pathological subtypes by radiomics plays an important role preoperatively. The non-invasive machine learning method based on T1WI and FS-T2WI imaging is potential prognostic tool by distinguishing different levels of DFSP pathological subtypes before operation in this study to provide a new idea for the diagnosis and treatment of DFSP.