Article
Oncology
Bin Wang, Preeti Hamal, Xue Meng, Ke Sun, Yang Yang, Yangyang Sun, Xiwen Sun
Summary: The study aimed to develop a prediction model to distinguish atypical adenomatous hyperplasia (AAH) from early lung adenocarcinomas in patients with subcentimeter pulmonary ground-glass nodules (GGNs). The model showed good discrimination performance in both the training and validation sets, potentially helping to avoid aggressive surgical resection for AAH patients.
FRONTIERS IN ONCOLOGY
(2021)
Article
Oncology
Fanyang Meng, Yan Guo, Mingyang Li, Xiaoqian Lu, Shuo Wang, Lei Zhang, Huimao Zhang
Summary: This study established a radiomics nomogram to evaluate the invasiveness of pulmonary adenocarcinomas manifesting as ground-glass nodules (GGNs) noninvasively. The nomogram showed good predictive ability and may assist clinicians in creating personalized treatment strategies.
TRANSLATIONAL ONCOLOGY
(2021)
Article
Oncology
Chengyu Chen, Qun Geng, Gesheng Song, Qian Zhang, Youruo Wang, Dongfeng Sun, Qingshi Zeng, Zhengjun Dai, Gongchao Wang
Summary: The study aimed to establish a nomogram based on radiomics from non-enhanced CT imaging and clinical features for predicting the malignancy of sub-centimeter solid nodules (SCSNs). A retrospective analysis was performed on 198 patients with surgically resected SCSNs. Radiomic features were extracted and used to build predictive models along with clinical features. The best model showed an AUC of 0.905 and was validated to be clinically useful.
FRONTIERS IN ONCOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Chenchen Ma, Shihong Yue, Chang Sun
Summary: This paper presents a novel method for the subtype classification of pulmonary ground glass nodules (GGNs) based on follow-up CTIs. By extracting features and classifying 383 follow-up CTIs, the method accurately predicts the pathological subtypes and improves diagnostic accuracy.
APPLIED SCIENCES-BASEL
(2022)
Article
Multidisciplinary Sciences
Wufei Chen, Ming Li, Dingbiao Mao, Xiaojun Ge, Jiaofeng Wang, Mingyu Tan, Weiling Ma, Xuemei Huang, Jinjuan Lu, Cheng Li, Yanqing Hua, Hao Wu
Summary: This study aimed to develop and validate a radiomics signature to identify the invasiveness of lung adenocarcinoma presented as subcentimeter ground glass nodules. The radiomics signature built on contrast-enhanced CT data showed better predictive performance, with a radiographic-radiomics nomogram demonstrating good clinical utility. Overall, the radiomics signature on CECT could aid in preoperative prediction of invasiveness in patients with subcentimeter lung adenocarcinomas.
SCIENTIFIC REPORTS
(2021)
Article
Oncology
Junjie Zhang, Ligang Hao, MingWei Qi, Qian Xu, Ning Zhang, Hui Feng, Gaofeng Shi
Summary: A combined model incorporating radiomics features and clinical parameters was developed and validated for the preoperative differentiation of PNMA from PTB. The logistic regression method achieved the best performance, showing good predictive value for distinguishing between PNMA and PTB.
Article
Oncology
Wenjun Huang, Heng Deng, Zhaobin Li, Zhanda Xiong, Taohu Zhou, Yanming Ge, Jing Zhang, Wenbin Jing, Yayuan Geng, Xiang Wang, Wenting Tu, Peng Dong, Shiyuan Liu, Li Fan
Summary: This study developed and validated a model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features derived from deep learning and radiomics. The model, CMRI, which integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features, achieved the highest area under the receiver operator characteristic curve (AUC) in multiple test sets, demonstrating its effectiveness in predicting the nature of GGNs.
FRONTIERS IN ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Shuyi Yang, Yida Wang, Yuxin Shi, Guang Yang, Qinqin Yan, Jie Shen, Qingle Wang, Haoling Zhang, Shan Yang, Fei Shan, Zhiyong Zhang
Summary: A radiomics nomogram was developed based on manual segmentation of different pulmonary nodules and measurement of signal intensity, nodule size, and other parameters, successfully distinguishing between malignant and benign nodules. The nomogram performed better in both the training and test sets compared to T2-based quantitative parameters.
MAGNETIC RESONANCE IMAGING
(2022)
Article
Oncology
Ling Liang, Haiyan Zhang, Haike Lei, Hong Zhou, Yongzhong Wu, Jiang Shen
Summary: The radiomics model based on low-dose computed tomography (LDCT) has clinical value in diagnosing benign and malignant pulmonary ground-glass nodules. The study found that the combined model had a higher prediction ability and could accurately distinguish between benign and malignant nodules.
TECHNOLOGY IN CANCER RESEARCH & TREATMENT
(2022)
Article
Oncology
Li Yi, Zhiwei Peng, Zhiyong Chen, Yahong Tao, Ze Lin, Anjing He, Mengni Jin, Yun Peng, Yufeng Zhong, Huifeng Yan, Minjing Zuo
Summary: A predictive model based on clinical radiology and radiomics was developed and validated to enhance the ability to distinguish between benign and malignant solitary solid pulmonary nodules. The model showed superior predictive performance compared to other independent models, with an AUC of 0.95, accuracy of 0.89, sensitivity of 0.83, and specificity of 0.96. This nomogram based on clinical radiology, intranodular, and perinodular radiomics features can improve the prediction of benign and malignant solitary pulmonary nodules.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Wenjia Shi, Zhen Yang, Minghui Zhu, Chenxi Zou, Jie Li, Zhixin Liang, Miaoyu Wang, Hang Yu, Bo Yang, Yulin Wang, Chunsun Li, Zirui Wang, Wei Zhao, Liang'an Chen
Summary: Immune therapy could be a promising systemic treatment for early-stage lung adenocarcinomas with ground-glass nodules (GGNs). This study investigated PD-L1 expression in these patients and developed a non-invasive prediction model based on radiomics. The combination of radiomics and clinical features showed better predictive efficacy for PD-L1 expression.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Fen-hua Zhao, Hong-jie Fan, Kang-fei Shan, Long Zhou, Zhen-zhu Pang, Chun-long Fu, Ze-bin Yang, Mei-kang Wu, Ji-hong Sun, Xiao-ming Yang, Zhao-hui Huang
Summary: The radiomics prediction model effectively distinguished between IAC and MIA, providing a non-invasive, low-cost, rapid, and reproducible preoperative prediction method for clinical application.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Yuting Zheng, Xiaoyu Han, Xi Jia, Chengyu Ding, Kailu Zhang, Hanting Li, Xuexiang Cao, Xiaohui Zhang, Xin Zhang, Heshui Shi
Summary: This study explored the value of using Dual-energy CT (DECT) and radiomics to discriminate preinvasive or MIA from IA appearing as GGNs before surgery. The results showed that the DECT-based radiomics model had a higher predictive performance for invasiveness compared to the clinical-DECT model.
FRONTIERS IN ONCOLOGY
(2023)
Article
Oncology
Xingzhi Huang, Zhenghua Wu, Aiyun Zhou, Xiang Min, Qi Qi, Cheng Zhang, Songli Chen, Pan Xu
Summary: The study developed and validated a diagnostic model combining B-mode ultrasound radiomics and ACR TI-RADS for predicting malignant thyroid nodules, showing significantly improved performance compared to the ACR-Score model in both training and validation cohorts. The AUC and net reclassification index (NRI) of the diagnostic model were significantly higher for both senior and junior radiologists.
FRONTIERS IN ONCOLOGY
(2021)
Article
Medicine, General & Internal
Wang-Jia Li, Fa-Jin Lv, Yi-Wen Tan, Bin-Jie Fu, Zhi-Gang Chu
Summary: This study investigated the CT features and pathological findings of pulmonary benign ground-glass nodules (GGNs), and found that different types of nodules have distinct CT characteristics, which can help improve diagnostic accuracy. Follow-up should be considered for subsolid nodules with CT features manifested in type I or II GGNs for further management.
INTERNATIONAL JOURNAL OF GENERAL MEDICINE
(2021)
Article
Oncology
Wei Zhao, Yingli Sun, Kaiming Kuang, Jiancheng Yang, Ge Li, Bingbing Ni, Yingjia Jiang, Bo Jiang, Jun Liu, Ming Li
Summary: Evaluating lung nodules’ invasiveness using irregularly sampled follow-up CT images is crucial in clinical practice. The ViSTA deep learning framework provides a solution for this, offering superior performance and potential applicability in predicting invasiveness of early lung adenocarcinoma. ViSTA outperforms other models and even approaches the performance of senior radiologists, showing promising accuracy in clinical evaluation.
Article
Radiology, Nuclear Medicine & Medical Imaging
Liang Jin, Kun Wang, Ming Li
Summary: CACS scan with Sn100 kVp prior to CCTA imaging on dual-source CT could reduce overall radiation dose. Compared with routine CCTA imaging, CACS scan shows advantages in reducing the number of scans, shortening the scan length, and decreasing the dose.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2022)
Article
Medicine, General & Internal
Kun Wang, Xiaodong Wang, Shaoqiang Zheng, Cheng Li, Liang Jin, Ming Li
Summary: Comparing dedicated coronary computed tomography angiography (CCTA) followed by high-pitch scanning with triple-rule-out computed tomography angiography (TRO-CTA), it was found that the former showed significantly lower radiation doses and contrast media volume, while maintaining good image quality in pulmonary arteries, thoracic aortae, and coronary arteries scans.
Article
Cardiac & Cardiovascular Systems
Liang Jin, Pan Gao, Kun Wang, Jianying Li, Ming Li
Summary: This study evaluated whether applying image filters improves image quality in CCTA. The results showed that using image filters significantly improved the image quality of coronary arteries and increased diagnostic accuracy. This is important for radiologists' diagnostic confidence.
FRONTIERS IN CARDIOVASCULAR MEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yingli Sun, Zongjing Ma, Wei Zhao, Liang Jin, Pan Gao, Kun Wang, Xuemei Huang, Shaofeng Duan, Ming Li
Summary: This study developed a model based on radiomics and clinical features to predict the long-term stability or growth of pulmonary ground-glass nodules (GGNs). The model, which combines radiographic features, size, age, and location, can effectively improve the follow-up management of GGNs through predictive analysis.
EUROPEAN JOURNAL OF RADIOLOGY
(2023)
Article
Virology
Xiao Li, Wei Yin, Ao Li, Danni Li, Xiaolong Gao, Ruizhi Wang, Bin Cui, Shuang Qiu, Rou Li, Lina Jia, Changjing Zuo, Lan Zhang, Ming Li
Summary: Due to the COVID-19 pandemic, long COVID patients experienced sequelae, but the underlying pathology was uncertain. Targeted radiopharmaceuticals, such as Ga-68-cyc-DX600, enable the systemic and dynamic tracking of pathological changes. ACE2 PET imaging with Ga-68-cyc-DX600 revealed the functional ACE2 recovery patterns in organs and provided a more comprehensive understanding of post-infection dysfunction.
JOURNAL OF MEDICAL VIROLOGY
(2023)
Article
Polymer Science
Ruizhi Wang, Nan Du, Liang Jin, Wufei Chen, Zhuangxuan Ma, Tianyu Zhang, Jie Xu, Wei Zhang, Xiaolin Wang, Ming Li
Summary: This study prepared fluorescent gold nanoparticles (NPs) and achieved photothermal conversion by depositing gold nanoclusters on their surface. Hyaluronic acid was attached to the NPs surface to target cancer cells. The results showed that these NPs had high photothermal conversion efficiency and good photostability, rapidly increasing temperature and ablating cancer cells in a short time.
Article
Biotechnology & Applied Microbiology
Liang Jin, Yingli Sun, Zongjing Ma, Ming Li
Summary: This retrospective study aimed to predict the injury time of rib fractures in distinguishing fresh or old rib fractures. The radiomics-based model displayed good accuracy in differentiating between the injury time of rib fractures at 30 and 90 days, and the human-model collaboration generated more accurate outcomes, which may help to add value to clinical practice and distinguish artificial injury in forensic medicine.
BIOENGINEERING-BASEL
(2023)
Article
Biology
Zhuangxuan Ma, Liang Jin, Lukai Zhang, Yuling Yang, Yilin Tang, Pan Gao, Yingli Sun, Ming Li
Summary: We established an acute aortic syndrome recognition model based on the radiological features of non-contrast CT images. This model can effectively detect acute aortic syndrome on non-contrast CT images with high sensitivity and accuracy, and it has important clinical applications for the screening of acute aortic syndrome, especially in the emergency department.
Review
Neurosciences
Yanjing Chen, Wei Zhao, Sijie Yi, Jun Liu
Summary: Through a meta-analysis of machine learning in diagnosing major depressive disorder based on neuroimaging data, it was found that machine learning showed high accuracy for automatic diagnosis of MDD, and certain factors may contribute to heterogeneity in the diagnostic results.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Multidisciplinary Sciences
Yumeng Wang, Huan Lin, Ningning Yao, Xiaobo Chen, Bingjiang Qiu, Yanfen Cui, Yu Liu, Bingbing Li, Chu Han, Zhenhui Li, Wei Zhao, Zimin Wang, Xipeng Pan, Cheng Lu, Jun Liu, Zhenbing Liu, Zaiyi Liu
Summary: In this study, an automated computational workflow was developed to evaluate the density of tertiary lymphoid structures (TLSs) in the tumor region of lung adenocarcinoma patients. The computerized TLS density was found to be associated with disease-free survival (DFS) and could improve prognostic stratification when combined with clinicopathological variables.
Article
Engineering, Biomedical
Zuowei Jiang, Xiaoyan Cai, Libin Yang, Dehong Gao, Wei Zhao, Junwei Han, Jun Liu, Dinggang Shen, Tianming Liu
Summary: Researchers propose an abstractive summarization approach for Chinese chest radiology reports, which achieves outstanding results through the construction of pre-training and fine-tuning corpora. This approach offers a promising solution to alleviate physicians' workload in computer-aided diagnosis.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Youlan Shang, Weidao Chen, Ge Li, Yijie Huang, Yisong Wang, Xiaoyan Kui, Ming Li, Hairong Zheng, Wei Zhao, Jun Liu
Summary: Radiomics extracted from the peritumoral region can provide additional value in predicting the EGFR mutation status of lung adenocarcinoma patients, with the optimal peritumoral range being 4 mm.
Article
Radiology, Nuclear Medicine & Medical Imaging
Hila Tal Tamir, Dana Stav, Yitzhac Hadad, Rivka Kessner
Summary: This study aimed to characterize thyroid nodules seen on Spectral Detector computed tomography (SDCT) and compare them with their Thyroid Imaging Reporting and Data System (TI-RADS) category on Ultrasound (US). The results showed that the spectral results of SDCT can assist in differentiating thyroid nodules of different risk levels.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Volha Nizhnikava, Ursula Reiter, Gabor Kovacs, Clemens Reiter, Corina Kraeuter, Horst Olschewski, Michael Fuchsjaeger, Gert Reiter
Summary: The purpose of this study was to investigate the associations between cardiac magnetic resonance feature-tracking-derived myocardial strain parameters and volumetric function and hemodynamic parameters in patients with pulmonary hypertension. The results showed that impairment of myocardial strains was more strongly associated with alterations in ventricular function parameters than elevated pulmonary arterial pressure, limiting the diagnostic information of myocardial strain parameters in pulmonary hypertension.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yu-ling Qian, Rui-lin Quan, Xiao-xi Chen, Yang-yi Lin, Xiao-li Jing, Qing Gu, Chang-ming Xiong, Jian-guo He, Ai-hua Zhi
Summary: The purpose of this study was to investigate the imaging characteristics and prognostic factors for the long-term survival of Behcet's disease (BD) with arterial involvement. The results showed that arterial lesions associated with BD usually involve multiple arteries and manifest differently in different types of arteries. Cardiac involvement and pulmonary artery aneurysm/dilation were independent prognostic factors for the survival of BD patients with arterial involvement.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Letter
Radiology, Nuclear Medicine & Medical Imaging
Yong Xie, Jian Wang, Yinghua Zou
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Daria Kifjak, Maximilian Hochmair, Daniel Sobotka, Alexander R. Haug, Raphael Ambros, Florian Prayer, Benedikt H. Heidinger, Sebastian Roehrich, Ruxandra-Iulia Milos, Wolfgang Wadsak, Thorsten Fuereder, Dagmar Krenbek, Andreas Fazekas, Michael Meilinger, Marius E. Mayerhoefer, Georg Langs, Christian Herold, Helmut Prosch, Lucian Beer
Summary: The ability of pretreatment PET parameters and peripheral blood biomarkers to predict PFS and OS in NSCLC patients treated with ICIT was assessed. The study found that MTV and the number of SOI were independent risk factors for progression and overall survival, and the combination of these factors improved risk stratification.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Theresa Sophie Patzer, Jan-Peter Grunz, Henner Huflage, Jan-Lucca Hennes, Pauline Pannenbecker, Philipp Gruschwitz, Saif Afat, Judith Herrmann, Thorsten Alexander Bley, Andreas Steven Kunz
Summary: This study investigated the potential of tin prefiltration and virtual monoenergetic imaging (VMI) in suppressing metal artifacts in high-resolution CT images of the lower extremities. The results showed that VMI reconstructions had better artifact reduction compared to T3D. VMI110keV had the least image noise. In terms of image quality, interpretability of bone-metal interface, and overall image quality, VMI110keV performed the best.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yue Li, Huan Zhang, Lei Yue, Caixia Fu, Robert Grimm, Wenhua Li, Weijian Guo, Tong Tong
Summary: This study evaluated and compared the diagnostic value of diffusion-related texture analysis parameters from different magnetic resonance diffusion models in predicting the clinical response to chemotherapy in patients with colorectal liver metastases. Among the models, DKI-derived parameters showed the best performance for early prediction, followed by IVIM-derived parameters and DWI baseline features.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lu Wang, ShiXiong Zhang, Jun Xin
Summary: This study aimed to determine if sex differences in abdominal visceral fat composition and metabolism can help predict the prognosis of DLBCL patients. The results showed that females with certain fat composition and metabolism characteristics had worse progression-free survival, while no significant differences were found in males with DLBCL.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yu-ping Wu, Lan Wu, Jing Ou, Jin-ming Cao, Mao-yong Fu, Tian-wu Chen, Erika Ouchi, Jiani Hu
Summary: This study aimed to develop CT radiomics models to preoperatively identify lymph node (LN) status in resectable esophageal squamous cell carcinoma (ESCC) patients. The results showed that the combined model, integrating ESCC and LN radiomics features with clinical features, had the highest predictive ability among the three models. The combined model's predictive ability was validated in both the test and external validation cohorts.
EUROPEAN JOURNAL OF RADIOLOGY
(2024)