Chun-Qiu Su¹, Wentao Hu², Xun-Ning Hong¹, Shan-Shan Lu¹, and Yongming Dai^2
1Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China, ²United Imaging Healthcare, Shanghai, China

Preoperative evaluation of the consistency of pituitary macroadenomas plays a significant role in the determination of the surgical strategy. However, previous studies concerning the assessment of tumor consistency of macroadenomas were controversial^1-4. Diffusion-relaxation correlation spectrum imaging (DR-CSI), which provides a correlation spectrum of both water molecular diffusion and T₂ relaxation, could be used to resolve the information of tissue compositions, compartments, and heterogeneity at a sub-voxel level. The purpose of our study is to evaluate the utility of DR-CSI in assessing the consistency of pituitary macroadenomas.

Wenjun Cui¹, Jing Zhang¹, Kai Ai², Yurong Zheng¹, Yuping Bai¹, Tiejun Gan¹, Rui Wang¹, Tingli Yang¹, Pengfei Wang¹, Jie Zou¹, Haoyuan Li¹, and Yuan Ding^1
1Department of Magnetic Resonance,Lanzhou University Second Hospital, Lan Zhou, China, ²Philips Healthcare, Xi'an, China

Advanced radiological modalities such as Amide Proton Transfer weighted imaging (APTw) may be useful in probing biological tissue properties of pituitary adenomas. The objective of the present study was to examine APTw derived APT value to noninvasively and quantitatively measuring pituitary adenomas. Moreover, the correlation analysis was performed between ATP value and hormone secretion to validate the efficiency of ATP value in differentiate hormone secretion related pituitary adenomas.

Ching-Chung Ko^1,2, Yan-Jen Chen^3,4, Hsun-Ping Hsieh³, and Jeon-Hor Chen^5,6
1Department of Medical Imaging, Chi Mei Medical Center, Tainan, Taiwan, ²Chia Nan University of Pharmacy and Science, Tainan, Taiwan, ³Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, ⁴Graduate Institute of Electronics Engineering, National Taiwan University, Taipei, Taiwan, ⁵Department of Radiological Sciences, University of California, Irvine, CA, United States, ⁶Department of Radiology, E-Da Hospital and I-Shou University, Kaohsiung, Taiwan

A subset of nonfunctioning pituitary macroadenomas (NFMAs) show early progression/recurrence (P/R) after surgery. In clinical practice, one of the main challenges in the treatment of NFMAs is to determine factors that associated with P/R. This study investigated the role of deep learning for the prediction of P/R in NFMAs. 78 patients diagnosed with NFMAs were included. The hybrid CNN-MLP model using both clinical and MRI features showed the best performance for prediction of P/R in NFMAs, with accuracy of 84%, precision of 88%, and AUC of 0.87.

Xin Ge^1,2, Xueying Huang², Kai Zhu², Aijun Wang², Xiaocheng Wei³, Min Li⁴, Ying Shen^1,2, Wenxiao Liu^1,2, Ruirui Lv^1,2, Peng Yong^1,2, Xuhong Yang^1,2, and Xiaodong Wang^2
1Ningxia Medical University, Yinchuan, China, ²General Hospital of Ningxia Medical University, Yinchuan, China, ³GE Healthcare, MR Research, Beijing, China, ⁴GE Healthcare, MR Enhancement Application, Beijing, China

This work sought to identify a new non-invasive means to differentiate high-grade gliomas (HGGs) from solitary brain metastases (SBMs). It was concluded that the T_1native, T_2native, PD_native, and ΔT_1ratio values were measured in peritumoral brain zone from synthetic MRI can be used as quantitative imaging biomarkers for distinguishing between HGGs and SBMs. The ΔT_1ratio values have higher discrimination abilities compared with other parameters, which worth further study.

Yaxuan Wang¹, Lekai Luo¹, Qian Li¹, Wanfang You¹, Yuxia Wang¹, Qian Zhang¹, Su Lui¹, Qiyong Gong¹, and Fei Li^1
1Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu 610041, Sichuan, P.R. China., Chengdu, China

Temporal dynamics in degree centrality (DC) were measured to detect alterations of dynamic topological organization in patients with obsessive-compulsive disorder (OCD) and schizophrenia (SZ). We found both patients with OCD and SZ showed decreased occurrence of a state manifested as the highest centrality in sensory systems. Moreover, we observed common and specific alteration of temporal variability of DC in some brain regions, which correlated with symptom severity of patients, respectively.

Jun Lu¹, Hailiang Li², and Xiang Li^1
1Department of Radiology, Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China, ²Department of Radiology and Intervention, Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China

  This study aimed to establish and validate a radiomics signature-based nomogram with robust radiomics features from contrast enhanced MRI images. The radiomics features were selected using LASSO regression. A prediction model was constructed with multivariate logistic regression analysis. A nomogram combined radiomics signature and clinical factors were established, showing good performance for predicting the TERT mutation status. The clinical value of radiomics nomogram was further assessed by the prognosis analysis. In conclusion, the radiomics signature-based nomogram is a promising method for preoperatively predicting TERT promoter mutation status and has the potential to assess prognosis noninvasively in glioblastoma patients.

Kiyohisa Kamimura¹, Masanori Nakajo¹, Bohara Manisha¹, Yoshihiko Fukukura¹, Hiroyuki Uchida², Takashi Iwanaga³, Thorsten Feiweier⁴, Hiroshi Imai⁵, and Takashi Yoshiura^1
1Radiology, Kagoshima University, Kagoshima, Japan, ²Neurosurgery, Kagoshima University, Kagoshima, Japan, ³Radiological Technology, Kagoshima University Hospital, Kagoshima, Japan, ⁴Siemens Healthcare GmbH, Erlangen, Germany, ⁵Siemens Healthcare K.K., Tokyo, Japan

To determine whether time-dependent DWI parameters and microscopic diffusion anisotropy (μFA) are useful for differentiating between glioblastoma and primary central nervous system lymphoma (PCNSL), 51 patients with glioblastoma and 13 with PCNSL were examined. In addition to ADC at two different diffusion times, ADC difference (ΔADC) and ADC change ratio (rcADC) were significantly different between the two tumor types, while no difference was shown for μFA. rcADC showed the best diagnostic performance followed by ΔADC.

Suhail Parvaze P¹, Rakesh K Gupta², Rupsa Bhattacharjee³, Anup Singh⁴, Rakesh Kumar Singh⁵, Gaurav Khanna⁶, Amal Roy Chaudhary⁷, Rana Patir⁸, Sandeep Vaishya⁸, Jaladhar Neelavalli ⁹, and Tejas Shah^9
1Philips Innovation Campus, Bangalore, India, ²Department of Radiology and Imaging, Fortis Memorial Research Institute, Gurugram, India, ³Indian Institute of Technology Delhi, Delhi, India, ⁴Department of Biomedical Engineering, Indian Institute of Technology Delhi, Delhi, India, ⁵Fortis Memorial Research Institute, Gurugram, India, ⁶SRL Diagnostics, Fortis Memorial Research Institute, Gurugram, India, ⁷Radiation Oncology, Fortis Memorial Research Institute, Gurugram, India, ⁸Department of Neurosurgery, Fortis Memorial Research Institute, Gurugram, India, ⁹BIU, Philips Innovation Campus, Bangalore, India

Edema in GB is characterized by the presence of tumor cells infiltration as compared to brain metastasis with only pure edema. Radiomics features extracted using FLAIR images in GB and BM are found to be exhibiting variation in some of the entropy and non-uniformity-based features, which could be used as signature to differentiate GB from brain metastasis.

Yao Ge¹, Xianjun Li², Congcong Liu², Miaomiao Wang², Linlin Zhu², Pengxuan Bai², Na Zhang², Yuying Feng², and Jian Yang^2
1Department of Radiology, The First Affiliated Hospital of Xi’an Jiaotong University, xi’an, China, ²Department of Radiology, The First Affiliated Hospital of Xi’an Jiaotong University, xi'an, China

Exploring the asymmetry of the neonatal brain white matter is of great significance for exploring the developmental rules and disease pathogenesis. Virtual MR elastography (VMRE) as a non-invasive technique has also enabled to relate maturation of cerebral structures to neonatal neurodevelopment in addition to conventional techniques.This study aims to explore the capability of diffusion–based VMRE in the characterization of the asymmetric of the neonatal white matter stiffness.The stiffness of neonatal white matter existed asymmetry, and there was a correlation between it and PMA. VMRE may enable to explore the developing brain at several levels.

Jinlong He¹, Jianlin Wu¹, Yang Gao², Qiong Wu², Jing Shen¹, Shaoyu Wang³, Huapeng Zhang³, Jialiang Ren⁴, and Peng Wang^5
1Tianjin Medical University Graduate School, Tianjin, China, ²Department Of Imaging Diagnosis, Affiliated Hospital Of Inner Monglia Medical University, Hohhot, China, ³MR Scientific Marketing, Siemens Healthineers, Shanghai, China, ⁴GE Healthcare, Shanghai, China, ⁵Inner Monglia Medical University, Hohhot, China

Objective:To compare the performance of clinical model, radiomics model, and combined model in predicting biomarker status (IDH, MGMT, TERT, 1p/19q) of glioma.Methods: 81 glioma patients confirmed by histology were enrolled in this study. The predictive performance of each model was validated by receiver operating characteristic curve (ROC) analysis and decision curve analysis (DCA).Results: The mixed model showed the highest performance in each genic phenotype (IDH AUC = 0.93, MGMT AUC=0.88, TERT AUC=0.76, 1p/19q AUC=0.71).Conclusion: The mixed model is an effective tool to distinguish genic phenotype of brain glioma which have highest diagnostic efficiency than other models.

Xu-Sha Wu¹, Yi-Bin Xi¹, and Hong Yin^1
1Xi'an People's Hospital (Xi'an Fourth Hospital), Xi'an, China

Schizophrenia is related to accelerated brain ageing, while individualized biomarkers are scarce. We established a brain age prediction model based on diffusion tensor imaging sequence. The difference between brain age and chronological age of first-episode schizophrenia patients and healthy controls were compared, and the longitudinal studies were performed in follow-up patients after a short-term antipsychotic treatment. The results verified the theory of accelerated brain ageing and medication have an effect on ameliorating it. Structural brain changes in schizophrenia could reveal the accelerated aging and quantification of age discrepancy could contribute to clinical decision-making and find new targeted therapies.

Suhail Parvaze P¹, Tejas Shah², Jaladhar Neelavalli ³, Anup Singh⁴, and Rakesh K Gupta^5
1Philips Innovation Campus, Bangalore, India, ²BIU, Philips Innovation Campus, Bangalore, India, ³BIU, Philips Innovation Campus, Gurugram, India, ⁴Center for Biomedical Engineering, Indian Institute of Technology Delhi, Bangalore, India, ⁵Department of Radiology and Imaging, Fortis Memorial Research Institute, Gurugram, India

Radiomics based feature value analysis and feature maps especially for first order and texture based features are being thoroughly investigated for diagnostic usability and relevance. Radiomics based feature map generation using 2D and 3D modes on different tumor sub-regions of glioblastoma were performed. 2D-based feature maps depicted accurately the texture variation with respect to other images from the slice of interest, whereas in 3D based maps anatomy and pathology of the neighboring slices induced influence resulting in over depiction of pathology. 

Kazuhiro Murayama¹, Yoshiharu Ohno², Kaori Yamamoto³, Takahiro Matsuyama², Seiichiro Ota², Masao Yui³, Masato Ikedo³, Saki Takeda⁴, Akiyoshi Iwase⁴, Satomu Hanamatsu², Hiroyuki Nagata², Takahiro Ueda², Hirotaka Ikeda², and Hiroshi Toyama^2
1Joint Research Laboratory of Advanced Medical Imaging, Fujita Health University School of Medicine, Toyoake, Japan, ²Radiology, Fujita Health University School of Medicine, Toyoake, Japan, ³Canon Medical Systems Corporation, Otawara, Japan, ⁴Radiology, Fujita Health University Hospital, Toyoake, Japan

We hypothesize that the newly developed wheel encoding order (Fast 3D wheel: i.e. Fast 3Dw) method can reduce examination time as well as compressed sensing (CS) with parallel imaging (PI) technique (Compressed SPEEDER) and obtain contrast-enhanced MR examination without any degradation of image quality as compared with conventional PI technique in suspected brain metastases patients.  The purpose of this study was to compare the capability for examination time reduction and image quality and diagnostic performance improvements among conventional PI, CS and Fast 3Dw methods on contrast-enhanced MR examination for brain metastases screening.

Linna Li¹, Zhongping Chen¹, Renjie Lu², Xin He¹, Ying Qiu¹, Dandan Guo¹, Hongkun Shi¹, Dan Tong¹, Yi Zhu³, and Ke Jiang^3
1Radiology, The First Hospital of Jilin Universty, Changchun, China, ²Ultrasound, The First Hospital of Jilin Universty, Changchun, China, ³Philips Healthcare, Beijing, China

Contrast-enhanced (CE) 3D T1-weighted scanning has been used more frequently with better spatial resolution and thinner section than 2D T1-weighted images for early detection and response assessment of brain metastases. To further improve the image scanning sequence, a new reconstruction algorithm, Compressed-SENSE Artificial Intelligence (CS-AI) was applied experimentally to achieve a balance between shortened scan time and improved image quality. This study aims to investigate the feasibility of contrast-enhanced 3D T1-weighted MRI reconstructed with Compressed SENSE Artificial Intelligence (CS-AI) by comparing with 3D T1-weighted images reconstructed with Compressed SENSE(CS), and to find out the optimal acceleration factor(AF).