1.Research on the application of deep learning based on conventional MRI in differentiating solitary fibrous tumors from schwannomas in the orbit
Jiliang REN ; Zehang NING ; Meng QI ; Zhipeng XIA ; Guoqing WU ; Ying YUAN
Chinese Journal of Radiology 2025;59(2):206-211
Objective:To explore the value of deep learning (DL) models based on conventional MRI in differentiating orbital solitary fibrous tumors (SFT) from schwannomas.Methods:This was a case-control study. A retrospective analysis was conducted on patients with pathologically confirmed orbital SFT and schwannoma admitted to Eye & ENT Hospital, Fudan University (institution 1) from December 2014 to January 2022 and Ninth People′s Hospital, Shanghai Jiao Tong University School of Medicine (institution 2) from July 2015 to May 2022. A total of 140 patients were included, with 104 patients from institution 1 comprising the training cohort for building DL models and 36 patients from institution 2 comprising the external validation cohort for assessing model performance. Based on the preoperative cross-sectional fat-suppressed T 2WI and contrast-enhanced T 1WI (ceT 1WI), tumor contours were outlined on all tumor-containing slices. Six diagnostic models were constructed using residual networks (ResNet) and split-attention residual networks (ResNeSt) with 18 layers (ResNet-18 and ResNeSt-18), based solely on individual T 2WI and ceT 1WI, as well as a combination of both. A radiology resident and an attending radiologist independently reviewed conventional MRI images to determine the tumor type. The performance of the DL models and radiologists in differentiating orbital SFT from schwannoma in the external validation cohort was evaluated using receiver operating characteristic curves, and the areas under the curves (AUC) were compared using the DeLong test. Results:In the external validation cohort, the AUC (95% CI) of the ResNet-18 models based on T 2WI, ceT 1WI, and their combination were 0.861 (0.719-1), 0.896 (0.774-1), and 0.885 (0.755-1), respectively, while the AUC (95% CI) of the ResNeSt-18 models were 0.889 (0.748-1), 0.872 (0.726-1), and 0.910 (0.801-1), respectively. Among these, the ResNeSt-18 model based on the combined sequences achieved the best performance in differentiating the two tumors. The AUC (95% CI) for the individual interpretation of the radiology resident and attending radiologist were 0.729 (0.571-0.887) and 0.771 (0.618-0.923), respectively. The AUC of the ResNeSt-18 model based on the combined sequences was statistically significantly higher than those of the resident and attending radiologist ( Z=1.96, P=0.049; Z=2.00, P=0.045). Conclusion:The ResNeSt-18 model based on conventional MRI can effectively differentiate orbital SFT from schwannoma, demonstrating better performance than those of the radiology resident and the attending radiologist.
2.Development of A High-performance Rectangular Ion Trap for Multi-reflection Time-of-Flight Mass Spectrometer
Xiao-Xia CHEN ; Yi REN ; Qi HUANG ; Da-Jun XIANG ; Chang-Wei LI ; Yi HONG ; Lei LI ; Zheng-Xu HUANG ; Mei LI ; Jing-Wei XU ; Zhen ZHOU
Chinese Journal of Analytical Chemistry 2025;53(1):38-46
As a new generation of time-of-flight mass spectrometry,multiple-reflection time-of-flight mass spectrometry(MR-TOF-MS)has been increasingly applied in the fields such as nuclear physics,chemistry,and biology due to its ultra-high resolution and rapid analysis capabilities.However,the analytical performance of MR-TOF-MS largely depends on the ion bunch state entering the mass analyzer.In this study,a rectangular ion trap(RIT)was developed,designed and processed using printed circuit board technology,as an ion accumulating and focusing device for MR-TOF mass analyzer.Compared to traditional ion traps composed of two sets of planar electrodes,this RIT had higher voltage utilization efficiency,resulting in more efficient ion collection and focusing.The ions were cooled to a sufficiently small bunch for precise mass measurement with MR-TOF-MS mass spectrometry in only 1 ms of cooling time in the RIT,then orthogonally ejected to the MR-TOF mass spectrometer for mass analysis.Experimental results indicated that the working cycle,ion flux,and ion focusing state of the RIT fully met the requirements of the MR-TOF mass analyzer.When coupled with the MR-TOF mass analyzer,the RIT enabled MR-TOF-MS to achieve a mass resolution of 1.5×105.
3.Research on the application of deep learning based on conventional MRI in differentiating solitary fibrous tumors from schwannomas in the orbit
Jiliang REN ; Zehang NING ; Meng QI ; Zhipeng XIA ; Guoqing WU ; Ying YUAN
Chinese Journal of Radiology 2025;59(2):206-211
Objective:To explore the value of deep learning (DL) models based on conventional MRI in differentiating orbital solitary fibrous tumors (SFT) from schwannomas.Methods:This was a case-control study. A retrospective analysis was conducted on patients with pathologically confirmed orbital SFT and schwannoma admitted to Eye & ENT Hospital, Fudan University (institution 1) from December 2014 to January 2022 and Ninth People′s Hospital, Shanghai Jiao Tong University School of Medicine (institution 2) from July 2015 to May 2022. A total of 140 patients were included, with 104 patients from institution 1 comprising the training cohort for building DL models and 36 patients from institution 2 comprising the external validation cohort for assessing model performance. Based on the preoperative cross-sectional fat-suppressed T 2WI and contrast-enhanced T 1WI (ceT 1WI), tumor contours were outlined on all tumor-containing slices. Six diagnostic models were constructed using residual networks (ResNet) and split-attention residual networks (ResNeSt) with 18 layers (ResNet-18 and ResNeSt-18), based solely on individual T 2WI and ceT 1WI, as well as a combination of both. A radiology resident and an attending radiologist independently reviewed conventional MRI images to determine the tumor type. The performance of the DL models and radiologists in differentiating orbital SFT from schwannoma in the external validation cohort was evaluated using receiver operating characteristic curves, and the areas under the curves (AUC) were compared using the DeLong test. Results:In the external validation cohort, the AUC (95% CI) of the ResNet-18 models based on T 2WI, ceT 1WI, and their combination were 0.861 (0.719-1), 0.896 (0.774-1), and 0.885 (0.755-1), respectively, while the AUC (95% CI) of the ResNeSt-18 models were 0.889 (0.748-1), 0.872 (0.726-1), and 0.910 (0.801-1), respectively. Among these, the ResNeSt-18 model based on the combined sequences achieved the best performance in differentiating the two tumors. The AUC (95% CI) for the individual interpretation of the radiology resident and attending radiologist were 0.729 (0.571-0.887) and 0.771 (0.618-0.923), respectively. The AUC of the ResNeSt-18 model based on the combined sequences was statistically significantly higher than those of the resident and attending radiologist ( Z=1.96, P=0.049; Z=2.00, P=0.045). Conclusion:The ResNeSt-18 model based on conventional MRI can effectively differentiate orbital SFT from schwannoma, demonstrating better performance than those of the radiology resident and the attending radiologist.
4.Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients (version 2024)
Yao LU ; Yang LI ; Leiying ZHANG ; Hao TANG ; Huidan JING ; Yaoli WANG ; Xiangzhi JIA ; Li BA ; Maohong BIAN ; Dan CAI ; Hui CAI ; Xiaohong CAI ; Zhanshan ZHA ; Bingyu CHEN ; Daqing CHEN ; Feng CHEN ; Guoan CHEN ; Haiming CHEN ; Jing CHEN ; Min CHEN ; Qing CHEN ; Shu CHEN ; Xi CHEN ; Jinfeng CHENG ; Xiaoling CHU ; Hongwang CUI ; Xin CUI ; Zhen DA ; Ying DAI ; Surong DENG ; Weiqun DONG ; Weimin FAN ; Ke FENG ; Danhui FU ; Yongshui FU ; Qi FU ; Xuemei FU ; Jia GAN ; Xinyu GAN ; Wei GAO ; Huaizheng GONG ; Rong GUI ; Geng GUO ; Ning HAN ; Yiwen HAO ; Wubing HE ; Qiang HONG ; Ruiqin HOU ; Wei HOU ; Jie HU ; Peiyang HU ; Xi HU ; Xiaoyu HU ; Guangbin HUANG ; Jie HUANG ; Xiangyan HUANG ; Yuanshuai HUANG ; Shouyong HUN ; Xuebing JIANG ; Ping JIN ; Dong LAI ; Aiping LE ; Hongmei LI ; Bijuan LI ; Cuiying LI ; Daihong LI ; Haihong LI ; He LI ; Hui LI ; Jianping LI ; Ning LI ; Xiying LI ; Xiangmin LI ; Xiaofei LI ; Xiaojuan LI ; Zhiqiang LI ; Zhongjun LI ; Zunyan LI ; Huaqin LIANG ; Xiaohua LIANG ; Dongfa LIAO ; Qun LIAO ; Yan LIAO ; Jiajin LIN ; Chunxia LIU ; Fenghua LIU ; Peixian LIU ; Tiemei LIU ; Xiaoxin LIU ; Zhiwei LIU ; Zhongdi LIU ; Hua LU ; Jianfeng LUAN ; Jianjun LUO ; Qun LUO ; Dingfeng LYU ; Qi LYU ; Xianping LYU ; Aijun MA ; Liqiang MA ; Shuxuan MA ; Xainjun MA ; Xiaogang MA ; Xiaoli MA ; Guoqing MAO ; Shijie MU ; Shaolin NIE ; Shujuan OUYANG ; Xilin OUYANG ; Chunqiu PAN ; Jian PAN ; Xiaohua PAN ; Lei PENG ; Tao PENG ; Baohua QIAN ; Shu QIAO ; Li QIN ; Ying REN ; Zhaoqi REN ; Ruiming RONG ; Changshan SU ; Mingwei SUN ; Wenwu SUN ; Zhenwei SUN ; Haiping TANG ; Xiaofeng TANG ; Changjiu TANG ; Cuihua TAO ; Zhibin TIAN ; Juan WANG ; Baoyan WANG ; Chunyan WANG ; Gefei WANG ; Haiyan WANG ; Hongjie WANG ; Peng WANG ; Pengli WANG ; Qiushi WANG ; Xiaoning WANG ; Xinhua WANG ; Xuefeng WANG ; Yong WANG ; Yongjun WANG ; Yuanjie WANG ; Zhihua WANG ; Shaojun WEI ; Yaming WEI ; Jianbo WEN ; Jun WEN ; Jiang WU ; Jufeng WU ; Aijun XIA ; Fei XIA ; Rong XIA ; Jue XIE ; Yanchao XING ; Yan XIONG ; Feng XU ; Yongzhu XU ; Yongan XU ; Yonghe YAN ; Beizhan YAN ; Jiang YANG ; Jiangcun YANG ; Jun YANG ; Xinwen YANG ; Yongyi YANG ; Chunyan YAO ; Mingliang YE ; Changlin YIN ; Ming YIN ; Wen YIN ; Lianling YU ; Shuhong YU ; Zebo YU ; Yigang YU ; Anyong YU ; Hong YUAN ; Yi YUAN ; Chan ZHANG ; Jinjun ZHANG ; Jun ZHANG ; Kai ZHANG ; Leibing ZHANG ; Quan ZHANG ; Rongjiang ZHANG ; Sanming ZHANG ; Shengji ZHANG ; Shuo ZHANG ; Wei ZHANG ; Weidong ZHANG ; Xi ZHANG ; Xingwen ZHANG ; Guixi ZHANG ; Xiaojun ZHANG ; Guoqing ZHAO ; Jianpeng ZHAO ; Shuming ZHAO ; Beibei ZHENG ; Shangen ZHENG ; Huayou ZHOU ; Jicheng ZHOU ; Lihong ZHOU ; Mou ZHOU ; Xiaoyu ZHOU ; Xuelian ZHOU ; Yuan ZHOU ; Zheng ZHOU ; Zuhuang ZHOU ; Haiyan ZHU ; Peiyuan ZHU ; Changju ZHU ; Lili ZHU ; Zhengguo WANG ; Jianxin JIANG ; Deqing WANG ; Jiongcai LAN ; Quanli WANG ; Yang YU ; Lianyang ZHANG ; Aiqing WEN
Chinese Journal of Trauma 2024;40(10):865-881
Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.
5.Associations of genetic variations in pyroptosis related genes with acute adverse events in postoperative rectal cancer patients receiving concurrent chemoradiotherapy.
Hong Xia CHEN ; Ning Xin REN ; Jie YANG ; Jin Na CHEN ; Qi Xuan LU ; Yan Ru FENG ; Ying HUANG ; Lu Qian YIN ; Dong Xi LIN ; Ye Xiong LI ; Jing JIN ; Wen TAN
Chinese Journal of Oncology 2023;45(2):146-152
Objective: This study aims to investigate the associations between genetic variations of pyroptosis pathway related key genes and adverse events (AEs) of postoperative chemoradiotherapy (CRT) in patients with rectal cancer. Methods: DNA was extracted from the peripheral blood which was collected from 347 patients before CRT. Sequenom MassARRAY was used to detect the genotypes of 43 haplotype-tagging single nucleotide polymorphisms (htSNPs) in eight pyroptosis genes, including absent in melanoma 2 (AIM2), caspase-1 (CASP1), caspase-4(CASP4), caspase-5 (CASP5), caspase-11 (CASP11), gasdermin D (GSDMD), gasdermin E (GSDME) and NLR family pyrin domain containing 3 (NLRP3). The associations between 43 htSNPs and AEs were evaluated by the odd ratios (ORs) and 95% confidence intervals (CIs) by unconditional logistic regression models, adjusted for sex, age, clinical stage, tumor grade, Karnofsky performance status (KPS), surgical procedure, and tumor location. Results: Among the 347 patients with rectal cancer underwent concurrent CRT with capecitabine after surgery, a total of 101(29.1%) occurred grade ≥ 2 leukopenia. rs11226565 (OR=0.41, 95% CI: 0.21-0.79, P=0.008), rs579408(OR=1.54, 95% CI: 1.03-2.29, P=0.034) and rs543923 (OR=0.63, 95% CI: 0.41-0.98, P=0.040) were significantly associated with the occurrence of grade ≥ 2 leukopenia. One hundred and fifty-six (45.0%) had grade ≥ 2 diarrhea, two SNPs were significantly associated with the occurrence of grade ≥ diarrhea, including CASP11 rs10880868 (OR=0.55, 95% CI: 0.33-0.91, P=0.020) and GSDME rs2954558 (OR=1.52, 95% CI: 1.01-2.31, P=0.050). In addition, sixty-six cases (19.0%) developed grade ≥2 dermatitis, three SNPs that significantly associated with the risk of grade ≥2 dermatitis included GSDME rs2237314 (OR=0.36, 95% CI: 0.16-0.83, P=0.017), GSDME rs12540919 (OR=0.52, 95% CI: 0.27-0.99, P=0.045) and NLRP3 rs3806268 (OR=1.51, 95% CI: 1.03-2.22, P=0.037). There was no significant difference in the association between other genetic variations and AEs of rectal cancer patients (all P>0.05). Surgical procedure and tumor location had great impacts on the occurrence of grade ≥2 diarrhea and dermatitis (all P<0.01). Conclusion: The genetic variants of CASP4, CASP11, GSDME and NLRP3 are associated with the occurrence of AEs in patients with rectal cancer who received postoperative CRT, suggesting they may be potential genetic markers in predicting the grade of AEs to achieve individualized treatment of rectal cancer.
Humans
;
Pyroptosis
;
NLR Family, Pyrin Domain-Containing 3 Protein/metabolism*
;
Gasdermins
;
Chemoradiotherapy/adverse effects*
;
Rectal Neoplasms/surgery*
;
Caspases/metabolism*
;
Diarrhea/chemically induced*
;
Leukopenia/genetics*
;
Genetic Variation
;
Dermatitis
8.Short-course radiotherapy combined with CAPOX and PD-1 inhibitor for the total neoadjuvant therapy of locally advanced rectal cancer: the preliminary single-center findings of a prospective, multicentre, randomized phase II trial (TORCH).
Ya Qi WANG ; Li Jun SHEN ; Jue Feng WAN ; Hui ZHANG ; Yan WANG ; Xian WU ; Jing Wen WANG ; Ren Jie WANG ; Yi Qun SUN ; Tong TONG ; Dan HUANG ; Lei WANG ; Wei Qi SHENG ; Xun ZHANG ; Guo Xiang CAI ; Ye XU ; San Jun CAI ; Zhen ZHANG ; Fan XIA
Chinese Journal of Gastrointestinal Surgery 2023;26(5):448-458
Objective: Total neoadjuvant therapy has been used to improve tumor responses and prevent distant metastases in patients with locally advanced rectal cancer (LARC). Patients with complete clinical responses (cCR) then have the option of choosing a watch and wait (W&W) strategy and organ preservation. It has recently been shown that hypofractionated radiotherapy has better synergistic effects with PD-1/PD-L1 inhibitors than does conventionally fractionated radiotherapy, increasing the sensitivity of microsatellite stable (MSS) colorectal cancer to immunotherapy. Thus, in this trial we aimed to determine whether total neoadjuvant therapy comprising short-course radiotherapy (SCRT) combined with a PD-1 inhibitor improves the degree of tumor regression in patients with LARC. Methods: TORCH is a prospective, multicenter, randomized, phase II trial (TORCH Registration No. NCT04518280). Patients with LARC (T3-4/N+M0, distance from anus ≤10 cm) are eligible and are randomly assigned to consolidation or induction arms. Those in the consolidation arm receive SCRT (25Gy/5 Fx), followed by six cycles of toripalimab plus capecitabine and oxaliplatin (ToriCAPOX). Those in the induction arm receive two cycles of ToriCAPOX, then undergo SCRT, followed by four cycles of ToriCAPOX. Patients in both groups undergo total mesorectal excision (TME) or can choose a W&W strategy if cCR has been achieved. The primary endpoint is the complete response rate (CR, pathological complete response [pCR] plus continuous cCR for more than 1 year). The secondary endpoints include rates of Grade 3-4 acute adverse effects (AEs) etc. Results: Up to 30 September 2022, 62 patients attending our center were enrolled (Consolidation arm: 34, Induction arm:28). Their median age was 53 (27-69) years. Fifty-nine of them had MSS/pMMR type cancer (95.2%), and only three MSI-H/dMMR. Additionally, 55 patients (88.7%) had Stage III disease. The following important characteristics were distributed as follows: lower location (≤5 cm from anus, 48/62, 77.4%), deeper invasion by primary lesion (cT4 7/62, 11.3%; mesorectal fascia involved 17/62, 27.4%), and high risk of distant metastasis (cN2 26/62, 41.9%; EMVI+ 11/62, 17.7%). All 62 patients completed the SCRT and at least five cycles of ToriCAPOX, 52/62 (83.9%) completing six cycles of ToriCAPOX. Finally, 29 patients achieved cCR (46.8%, 29/62), 18 of whom decided to adopt a W&W strategy. TME was performed on 32 patients. Pathological examination showed 18 had achieved pCR, four TRG 1, and 10 TRG 2-3. The three patients with MSI-H disease all achieved cCR. One of these patients was found to have pCR after surgery whereas the other two adopted a W&W strategy. Thus, the pCR and CR rates were 56.2% (18/32) and 58.1% (36/62), respectively. The TRG 0-1 rate was 68.8% (22/32). The most common non-hematologic AEs were poor appetite (49/60, 81.7%), numbness (49/60, 81.7%), nausea (47/60, 78.3%) and asthenia (43/60, 71.7%); two patients did not complete this survey. The most common hematologic AEs were thrombocytopenia (48/62, 77.4%), anemia (47/62, 75.8%), leukopenia/neutropenia (44/62, 71.0%) and high transaminase (39/62, 62.9%). The main Grade III-IV AE was thrombocytopenia (22/62, 35.5%), with three patients (3/62, 4.8%) having Grade IV thrombocytopenia. No Grade V AEs were noted. Conclusions: SCRT-based total neoadjuvant therapy combined with toripalimab can achieve a surprisingly good CR rate in patients with LARC and thus has the potential to offer new treatment options for organ preservation in patients with MSS and lower-location rectal cancer. Meanwhile, the preliminary findings of a single center show good tolerability, the main Grade III-IV AE being thrombocytopenia. The significant efficacy and long-term prognostic benefit need to be determined by further follow-up.
Humans
;
Middle Aged
;
Antineoplastic Combined Chemotherapy Protocols/therapeutic use*
;
Chemoradiotherapy
;
Immune Checkpoint Inhibitors/therapeutic use*
;
Neoadjuvant Therapy
;
Prospective Studies
;
Rectal Neoplasms/pathology*
;
Thrombocytopenia/drug therapy*
;
Treatment Outcome
;
Adult
;
Aged

Result Analysis
Print
Save
E-mail