Wanting Gan¹, Shuang Meng¹, Lihua Chen¹, Nan Wang¹, Yunsong Liu¹, and Ailian Liu^1
1Department of Radiology，the First Affiliated Hospital of Dalian Medical University, Dalian, China

Positive surgical margins(PSMs) are associated with local recurrence and distant metastasis of prostate cancer which affect the long-term survival rate of patients^1-3. IVIM can simultaneously observe microcirculatory perfusion of blood and intracellular and extracellular water molecules diffusion⁴. The results of our study show that f-Bi can be used to predict positive margins of radical prostatectomy.

Na Song¹, Zhiqiang Chen¹, Xiaohua Chen¹, Zhuo Wang¹, Shaoru Zhang¹, Xiaocheng Wei², Dan Zhang¹, and Kai Zhu^1
1Radiology, The Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan, China, ²GE Healthcare, MR Research China, Beijing, Beijing, China

In this retrospective study, we aim to investigate the application value of quantitative relaxation time obtained from synthetic MRI in the diagnosis and assessment of aggressiveness of transition zone prostate cancer. It was concluded that quantitative relaxation T1 and T2 values of synthetic MRI are useful parameters for discriminate TZ PCa from BPH, and T1 value demonstrated the similar diagnostic performance as ADC value. Gleason staging could be preliminarily assessed by T2 value of SyMRI in patients who cannot be punctured.

 

QiuRong Wei¹, WeiCui Chen², LiTing Mao², Kan Deng³, WeiKang Huang², Bo Liu², Xian Liu², and ZhaoXian Yan^2
1The Second Clinical College of Guangzhou University of Chinese Medicine, Guangzhou, China, ²the Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, China, ³Philips Healthcare, Guangzhou, China

The extramural venous invasion (EMVI) is considered as the potential prognostic factor for patients with rectal carcinoma. We tried to investigate the diagnostic ability of diffusion kurtosis imaging (DKI) - derived parameters as risk factors for EMVI’s involvement status.Our results showed that the Kmean values, lymph node involvement, and an advanced tumor stage (T3) were independent risk factors for the prediction of EMVI status, which may suggest that the DKI as a potential biomarker for evaluating the EMVI status of rectal cancer is feasible.

Yuxi Ge^1,2 and Weiqiang Dou^3
1Affiliated Hospital of Jiangnan University, Wuxi, China, ²MR Research, GE Healthcare, Nanjing, China, ³GE Healthcare, Nanjing, China

This study aimed to investigate the feasibility of T2 mapping in predicting the response to chemoradiation (CRT) for patients with local advanced rectal cancer (LARC). Thirty-five LARC patients were measured with T2 mapping before-, during- and after-CRT. Resultant T2 values during- and after-CRT, and the T2 decrease ratio of before- to during-CRT were correlated significantly with tumor regression grade. Compared to poor responders, good responders showed lower T2 during- and after-CRT and higher T2 decrease ratio of before- to during-CRT. Therefore, quantitative T2 mapping may be useful for predicting the response to CRT for LARC patients.

Shuang Meng¹, Lihua Chen², Nan Wang², Yunsong Liu², and Ailian Liu^2
1Radiology, The First Affiliated Hospital of Dalian Medical University, Dalian, China, ²The First Affiliated Hospital of Dalian Medical University, Dalian, China

PSMs are an independent risk factor for biochemical recurrence in patients after radical prostatectomy. DKI quantifies the non-Gaussian nature of the real water molecule diffusion, and accurately reveals the changes in the microstructure of the tissue. Results of this study indicate that MD, Da , Dr, MK, Ka and Kr can be used to predict predicts positive margins after radical resection of localized prostate cancer.

Cheng Xueqing¹, Li Haixia², and Chen Yuntian^1
1Department of radiology, West China Hospital, Chengdu, China, ²Philips Healthcare, Guangzhou, China

In this study, we applied the radiomics features of both suspected lesion and prostate gland on bi-parametric MRI (bpMRI) (T2W and ADC) to predict whether targeted biopsy alone is enough in detecting clinically significant prostate cancer (csPCa) in biopsy naïve men and compare their value with PI-RADS category.

Yu Guo¹, Yu Fu¹, Jiansen Li², Lei Zhang¹, Zhuo Wang¹, and Huimao Zhang^1
1The First Hospital of Jilin University, Changchun, China, ²United Imaging Healthcare, Shanghai, China

2D T2WI obtained in multi plane is recommend in preoperative assessment of rectal cancer, but 2D acquisition suffers from heavy partial volume effects. As a result, 2D T2WI cannot assess early rectal cancer stages accurately. Comparing with 2D T2WI, 3D T2WI could provide higher spatial resolution, especially the thin slice thickness, with highly reduced partial volume effects in rectal MRI. The purpose of the study was to compare the local-regional staging accuracy of the conventional 2D T2WI protocol and the 3D T2WI protocol for preoperative MR imaging in early rectal cancer patients.

Zhuo Wang¹, Zhiqiang Chen¹, Shaoru Zhang¹, Xiaohua Chen¹, Dan Zhang¹, Na Song¹, Yuhui Xiong², Lei Cai³, and Bing Chen^3
1The Department of Radiology, General Hospital of Ningxia Medical University,, YinChuan, China, ²GE Healthcare, Beijing, China, ³The Department of Radiology, General Hospital of Ningxia Medical University,, Yinchuan, China

In this study, we aim to evaluate the diagnostic performance of diffusion tensor imaging (DTI) in detecting prostatic peripheral zone cancer and to deduce its clinical utility. The area under curve (AUC) of the receiver operating characteristic (ROC) curves was used to evaluate the diagnostic efficiency of ADC value, FA value and their combination. The diagnostic threshold values of ADC and FA were also determined. It was concluded that DTI quantitative indexes has moderately high diagnostic accuracy in detecting prostate cancer , while the ADC value had higher diagnostic efficiency than the FA value.

yuhui liu^1,2, anliang chen¹, Wan Dong¹, and Ailian Liu^1
1The First Affiliated Hospital of Dalian Medical University, Dalian, China, ²Dalian Medical University, Dalian, China

The purpose of this study is to use IVIM（intravoxel incoherent motion）and DCE（dynamic contrast-enhanced）imaging techniques to identify the value of rectal mucinous adenocarcinoma and tubular adenocarcinoma, and to provide rich information and help for clinical decision-making. 

Yan Lin¹, Huanian Zhang¹, Ting Ouyang¹, Rongzhi Cai¹, Peie Zheng¹, yao Fu¹, and Renhua Wu^1
1Radiology Department, Second Affiliated Hospital of Shantou University Medical College, Shantou City, China

This study aimed to profile the metabolic differences of colorectal cancer tissues (CCT) in different stages and sites, as compared with their adjacent noncancerous tissues (ANT), to investigate the temporal and spatial heterogeneities of metabolic characterization. Our NMR-based metabonomics fingerprinting revealed that many of the metabolite levels were significantly altered in CCT as compared with ANT, indicating deregulations of glucose metabolism, one-carbon metabolism, glutamine metabolism, amino acid metabolism, fatty acid metabolism, TCA cycle, choline metabolism, ect. Significant metabolic differences were found in CRC tissues at different pathological stages and sites, suggesting temporal and spatial heterogeneities of metabolic characterization in CCT. 

Jiao Qu¹, Xin Shu², Wenjing Zhang¹, Mengyuan Xu¹, Ying Wang¹, Lituan Wang², Lei Zhang², and Su Lui^1
1Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu, China, ²College of Computer Science, Sichuan University, Chengdu, China

Brain metastases detection and segmentation on magnetic resonance images is laborious, error-prone and often irreproducible for radiologists and radiation oncologist. We present a specific deep slice-crossed network with local weighted loss to automatically detect and segment brain metastases on contrast-enhanced T1WI images. The results demonstrated the good performance, high robustness and generalizability of the model. In addition, compared with radiologists, the model showed higher sensitivity and increased efficiency in identifying and segmenting brain metastases. The results jointly suggested that the proposed model is a promising tool to assist the workflow in the clinical practice.

Eryuan Gao¹, Guohua Zhao¹, Huiting Zhang², Ankang Gao¹, Xiaoyue Ma¹, Jie Bai¹, Xu Yan², Yusong Lin³, Guang Yang⁴, and Jingliang Cheng^1
1department of magnetic resonance imaging, the First Affiliated Hospital of Zhengzhou University, Zhengzhou, China, ²MR Scientific Marketing, Siemens Healthcare, Shanghai, China, ³the School of Software, Zhengzhou University, Zhengzhou, China, ⁴Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China

The differentiation of glioblastomas from solitary brain metastases by using routine magnetic resonance imaging (MRI) alone presents a challenge. As a representative of diffusion MRI technology, diffusion kurtosis imaging (DKI) can closely reflect the real situation of water molecule movement in tumor tissues. We speculate that DKI radiomics is superior to routine MRI radiomics in distinguishing GBMs from SBMs. We developed a series of radiomics models of DKI parameter maps and routine MRI to compare their performance. Finally, several independent parameters models perform well in distinguishing two tumors. The combined DKI radiomics model obtained the best performance.

Chien-Yi Liao¹, Cheng-Chia Lee^2,3,4, Huai-Che Yang^2,3, Wen-Yuh Chung^2,3, Hsiu-Mei Wu^3,5, Wan-Yuo Guo^3,5, Ren-Shyan Liu⁶, and Chia-Feng Lu^1,7
1Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, ²Department of Neurosurgery, Neurological Institute, Taipei Veteran General Hospital, Taipei, Taiwan, ³School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan, ⁴Brain Research Center, National Yang Ming Chiao Tung University, Taipei, Taiwan, ⁵Department of Radiology, Taipei Veteran General Hospital, Taipei, Taiwan, ⁶Department of Medical Imaging, Cheng-Hsin General Hospital, Taipei, Taiwan, ⁷Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei, Taiwan

About 30% of Non-small cell lung cancer (NSCLC) patients develop brain metastases (BMs) during the course of the disease. MR radiomics and EGFR mutation status were reported with the potential to predict the local tumor control of Gamma Knife stereotactic radiosurgery (GKRS). The prediction of overall survival after GKRS can further benefit the management of BM patients. We proposed a deep learning-based model using the clinical information, EGFR mutation status, and MR radiomic features to predict the overall survival after GKRS. We suggested that pre-GKRS MRI characteristics combined with gene and clinical information can improve the prediction of overall survival.

Chengxiu Zhang¹, Yang Song², Lin Lin³, Rufei Zhang³, Minxiong Zhou⁴, Xu Yan², and Guang Yang^1
1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, ²MR Scientific Marketing, Siemens Healthineers, Shanghai, China, ³Department of Radiology, Fujian Medical University Union Hospital, Fuzhou, China, ⁴Shanghai University of Medicine & Health Sciences, Shanghai, China

We used multi-parametric MRI to predict the postoperative recurrence of meningioma. Compared to the usual radiomics on analyzing the whole tumor, we used an unsupervised clustering method to explore the tumor habitats. Interpretable features were extracted from subregions of the lesion and used to build a habitat radiomic model. The habitat model achieved an AUC of 0.711 compared with 0.569 achieved by whole tumor analysis. The split subregions of the tumor also have clear biological meanings to the radiologists.

Ting Fang^1,2, Nan Meng¹, Zhun Huang², Pengyang Feng², Ziqiang Li², Yang Yang³, Jianmin Yuan⁴, and Meiyun Wang^2
1Zhengzhou University People's hospital, Zhengzhou, China, ²Henan Provincial People's Hospital, Zhengzhou, China, ³Beijing United Imaging Research Institute of Intelligent Imaging, Beijing, China, ⁴Central Research Institute, Shanghai, China

Intra-Voxel Incoherent Motion (IVIM), PET imaging, and Amide Proton Transfer weighted imaging (APTw) are all effective tools for distinguishing the pathological types of solitary pulmonary lesions. The difference between their ability to distinguish the Ki-67 high expression (HE) and low expression (LE) group is still unclear. Our study shows IVIM and PET imaging are better methods than APTw for distinguishing Ki-67 HE and LE groups of non-small cell cancer.