Article
Oncology
Defeng Liu, Linsha Yang, Dan Du, Tao Zheng, Lanxiang Liu, Zhanqiu Wang, Juan Du, Yanchao Dong, Huiling Yi, Yujie Cui
Summary: In this study, a multi-parameter MRI radiomics-based nomogram model was developed to predict 5-year progression-free survival in patients with resected endometrial cancer. The model, incorporating radiomics features, clinical factors, and conventional MR findings, demonstrated good calibration and discrimination ability.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Chunmiao Kang, Pengfeng Sun, Runqin Yang, Changming Zhang, Wenfeng Ning, Hongsheng Liu
Summary: The purpose of this study was to develop a radiomics nomogram to predict pathological response (PR) and overall survival (OS) in patients with advanced laryngeal cancer (LC). A total of 114 LC patients who underwent contrast computerized tomography (CT) were included in this retrospective study. The radiomics score was found to be significantly associated with PR and OS. Multivariate analysis identified volume, N stage, and radiomics score as independent risk factors for OS. A nomogram incorporating these variables was developed and showed better predictive performance for individualized OS estimation.
FRONTIERS IN ONCOLOGY
(2023)
Article
Genetics & Heredity
Bingqing Xia, He Wang, Zhe Wang, Zhaoxia Qian, Qin Xiao, Yin Liu, Zhimin Shao, Shuling Zhou, Weimin Chai, Chao You, Yajia Gu
Summary: The radiomics signature from preoperative MRI images is associated with disease-free survival in triple-negative breast cancer patients. A nomogram based on radiomics signatures, MRI findings, and clinicopathological variables was developed to predict DFS, improving individualized estimation.
FRONTIERS IN GENETICS
(2021)
Article
Oncology
Lang Xiong, Haolin Chen, Xiaofeng Tang, Biyun Chen, Xinhua Jiang, Lizhi Liu, Yanqiu Feng, Longzhong Liu, Li Li
Summary: In this study, a radiomics signature based on preoperative ultrasound was developed to predict disease-free survival in invasive breast cancer patients. The study showed that the radiomics signature had additional value for individualized prediction of disease-free survival.
FRONTIERS IN ONCOLOGY
(2021)
Article
Oncology
Yue Zhou, Lijie Song, Jin Xia, Huan Liu, Jingjing Xing, Jianbo Gao
Summary: This study investigated the prognostic value of CT images and clinical characteristics in predicting the overall survival of esophageal neuroendocrine carcinoma (NEC). The results showed that CT texture features can predict the survival rate of esophageal NEC patients, and the radiomics nomogram based on CT radiomics signature has better prognostic power than the model using combined variables.
FRONTIERS IN ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Qiaoling Chen, JingJing Shao, Ting Xue, Hui Peng, Manman Li, Shaofeng Duan, Feng Feng
Summary: CT-based radiomics nomogram can predict LVI and OS in patients with NSCLC and may help in making personalized treatment strategies before surgery.
EUROPEAN RADIOLOGY
(2023)
Article
Oncology
Mi-Xue Sun, Meng-Jing Zhao, Li-Hao Zhao, Hao-Ran Jiang, Yu-Xia Duan, Gang Li
Summary: This study established a novel model using radiomics analysis of pre-treatment and post-treatment magnetic resonance images to predict progression-free survival in stage II-IVA nasopharyngeal carcinoma patients in South China. The model integrated clinical and radiomics features to build a clinical-and-radiomics nomogram, which showed reliable predictive performance and helped distinguish high-risk patients from low-risk patients.
RADIATION ONCOLOGY
(2023)
Article
Multidisciplinary Sciences
Xiangyang Yu, Feng Wang, Longjun Yang, Kai Ma, Xiaotong Guo, Lixu Wang, Longde Du, Xin Yu, Shengcheng Lin, Hua Xiao, Zhilin Sui, Lanjun Zhang, Zhentao Yu
Summary: In this study, nomograms were developed to predict disease-free survival (DFS) and overall survival (OS) for patients who underwent pneumonectomy for primary lung cancer. The nomograms showed good discrimination accuracy and clinical utility. They can assist in identifying high-risk patients and developing personalized treatment strategies to improve survival.
Article
Oncology
Jiayi Li, Dongyan Cao
Summary: We developed two prognostic nomograms for predicting recurrence and long-term survival in patients with ovarian clear cell carcinoma (OCCC) after primary treatment, and validated them in patients from the same center. This tool, which uses variables specifically related to OCCC, was more accurate than the FIGO system, making it relatively easy to use in clinic for patient counseling, postoperative management, and follow-up for individual patients.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Xihai Wang, Zaiming Lu
Summary: Radiomics features extracted from PET and CT components of F-18-FDG PET/CT images, integrated with clinical factors and metabolic parameters of PET, can predict progression-free survival in patients with advanced high-grade serous ovarian cancer (HGSOC).
FRONTIERS IN ONCOLOGY
(2021)
Article
Oncology
Yushan Jia, Shuai Quan, Jialiang Ren, Hui Wu, Aishi Liu, Yang Gao, Fene Hao, Zhenxing Yang, Tong Zhang, He Hu
Summary: This study assessed the predictive value of magnetic resonance imaging (MRI) radiomics for progression-free survival (PFS) in patients with prostate cancer (PCa). The results showed that the hybrid model constructed from radiomics and clinical data performed the best in predicting PFS. This model provides a non-invasive diagnostic tool for risk stratification of clinical patients.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Yixuan Zhai, Jiwei Bai, Yake Xue, Mingxuan Li, Wenbin Mao, Xuezhi Zhang, Yazhuo Zhang
Summary: A MRI-based radiomics nomogram was established and validated to predict the progression-free survival (PFS) of patients with clival chordoma. The nomogram showed a favorable predictive accuracy and provided a novel tool for prognosis prediction and risk stratification. Radiomic analysis proved to be effective in assisting neurosurgeons in evaluating patients with clival chordomas.
FRONTIERS IN ONCOLOGY
(2022)
Article
Medicine, Research & Experimental
Min Liang, Mafeng Chen, Shantanu Singh, Shivank Singh
Summary: Two nomograms were established to predict individual overall survival (OS) among limited stage (LS) and extensive stage (ES) small cell lung cancer (SCLC) patients who received chemotherapy. The nomograms showed good discrimination capacity and calibration with actual observations, and had more benefits in predicting OS than the 7th American Joint Committee on Cancer (AJCC) tumor node metastasis (TNM) staging system. The proposed nomograms may assist clinicians in treatment strategy and design of clinical trials.
ADVANCES IN THERAPY
(2022)
Article
Oncology
Hassan Abdelilah Tafenzi, Farah Choulli, Ganiou Adjade, Anas Baladi, Leila Afani, Mohammed El Fadli, Ismail Essaadi, Rhizlane Belbaraka
Summary: This study developed and validated a nomogram to predict the overall survival of lung cancer patients. The nomogram can provide individual prognosis for patients and assist doctors in making decisions and planning therapeutic trials.
Article
Oncology
Prantesh Jain, Mohammadhadi Khorrami, Amit Gupta, Prabhakar Rajiah, Kaustav Bera, Vidya Sankar Viswanathan, Pingfu Fu, Afshin Dowlati, Anant Madabhushi
Summary: This study explored the role of radiomic features extracted from CT scans in predicting overall survival (OS) and response to chemotherapy in SCLC patients. The study found that radiomic features within and around the lung tumor were both prognostic of OS and predictive of response to chemotherapy.
FRONTIERS IN ONCOLOGY
(2021)
Article
Biology
Qianqian Qi, Shouliang Qi, Yanan Wu, Chen Li, Bin Tian, Shuyue Xia, Jigang Ren, Liming Yang, Hanlin Wang, Hui Yu
Summary: This study proposed a fully automatic deep learning pipeline for rapid and accurate differentiation of COVID-19 from CAP using CT images. The results showed excellent performance of the pipeline in lung segmentation, selection of slices with lesions, and slice-level prediction, achieving a 100% prediction accuracy at the patient level for both datasets.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Kai Zhang, Shouliang Qi, Jiumei Cai, Dan Zhao, Tao Yu, Yong Yue, Yudong Yao, Wei Qian
Summary: This study combines deep learning and CBIR to distinguish lung cancer and tuberculosis in CT images using CSNN, achieving excellent performance at both patch and patient levels. The CBIR-CSNN shows high accuracy and has potential for important clinical applications.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biotechnology & Applied Microbiology
Epimack Michael, He Ma, Hong Li, Shouliang Qi
Summary: This article proposes a computer-aided diagnosis (CAD) system that can automatically generate an optimized algorithm to improve the accuracy of breast cancer diagnosis. The experimental results show that the LightGBM classifier performs better than other classifiers, achieving high accuracy, precision, and recall.
BIOMED RESEARCH INTERNATIONAL
(2022)
Article
Computer Science, Interdisciplinary Applications
Baihua Zhang, Shouliang Qi, Yanan Wu, Xiaohuan Pan, Yudong Yao, Wei Qian, Yubao Guan
Summary: The M-SegSEUNet-CRF model proposes a multi-scale segmentation approach to automatically segment lung tumors from CT images with high accuracy. The model achieves excellent results in delineating tumor boundaries and outperforms other comparative models in the task of lung tumor segmentation.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Biology
Haowen Pang, Yanan Wu, Shouliang Qi, Chen Li, Jing Shen, Yong Yue, Wei Qian, Jianlin Wu
Summary: This study proposes an automatic pipeline for segmenting pulmonary lobes before and after lobectomy from CT images. The pipeline achieved high accuracy and outperformed other counterparts and training strategies. It can be applied to manage patients with lung cancer after lobectomy.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Neuroimaging
Chaoyang Jin, Shouliang Qi, Lei Yang, Yueyang Teng, Chen Li, Yudong Yao, Xiuhang Ruan, Xinhua Wei
Summary: The pathophysiological mechanisms of freezing of gait (FOG) in Parkinson's disease (PD) patients are not well understood. Functional connectivity density (FCD) can be used to analyze connectivity across the brain in an unbiased way. This study found that PD FOG + patients had increased short-range FCD in certain brain regions and decreased long-range FCD in others. Short-range FCD values in the middle temporal gyrus and inferior temporal gyrus were positively correlated with FOG severity, while long-range FCD values in the middle frontal gyrus were negatively correlated. A machine learning model achieved good classification performance using FCD in abnormal regions. Overall, this study demonstrates altered FCD patterns in PD FOG + patients.
BRAIN IMAGING AND BEHAVIOR
(2023)
Article
Computer Science, Interdisciplinary Applications
Haowen Pang, Shouliang Qi, Yanan Wu, Meihuan Wang, Chen Li, Yu Sun, Wei Qian, Guoyan Tang, Jiaxuan Xu, Zhenyu Liang, Rongchang Chen
Summary: In this study, two synthesizers were developed to achieve mutual synthesis between non-contrast CT (NCCT) and contrast-enhanced CT (CECT) using generative adversarial networks. The results demonstrated the effectiveness of the synthesizers in high-quality synthesis of NCCT and CECT images, with the training process being crucial to their performance.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Article
Biology
Yanan Wu, Qianqian Qi, Shouliang Qi, Liming Yang, Hanlin Wang, Hui Yu, Jianpeng Li, Gang Wang, Ping Zhang, Zhenyu Liang, Rongchang Chen
Summary: The study proposes a method for accurately distinguishing COVID-19 from CAP using MIP images from CT scans and a capsule network. The method achieves high accuracy and sensitivity in COVID-19 diagnosis and prediction.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Artificial Intelligence
Yanan Wu, Shuiqing Zhao, Shouliang Qi, Jie Feng, Haowen Pang, Runsheng Chang, Long Bai, Mengqi Li, Shuyue Xia, Wei Qian, Hongliang Ren
Summary: Accurate airway segmentation from CT images is critical for diagnosing and evaluating COPD. Existing methods face challenges in segmenting small branches of the airway. This study proposes a two-stage framework with a novel 3D contextual transformer to address these challenges. Experimental results show that the proposed method outperforms existing methods in extracting airway branches and achieving state-of-the-art segmentation performance.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Biology
Shannan Chen, Jinfeng Duan, Nan Zhang, Miao Qi, Jinze Li, Hong Wang, Rongqiang Wang, Ronghui Ju, Yang Duan, Shouliang Qi
Summary: This study proposed a Multi-Scale Attention-based YOLOv5 (MSA-YOLOv5) model for effectively detecting acute ischemic stroke lesions in multimodal images, particularly for small lesions and artifacts. The model achieved high detection performance on both in-house AIS dataset and the ISLES 2022 dataset, outperforming other network models.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Interdisciplinary Applications
Yanan Wu, Shouliang Qi, Meihuan Wang, Shuiqing Zhao, Haowen Pang, Jiaxuan Xu, Long Bai, Hongliang Ren
Summary: Transformer-based network with a channel-enhanced attention module is proposed for pulmonary vessel segmentation and artery-vein separation in non-contrast and contrast-enhanced CT images. The network utilizes a 3D contextual transformer module and a double attention module to achieve high-quality segmentation. Experimental results on in-house and challenge datasets demonstrate the effectiveness of the proposed method. The code is available at https://github.com/wuyanan513/Pulmonary-Vessel-Segmentation-and-Artery-vein-Separation.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Article
Computer Science, Interdisciplinary Applications
Yanan Wu, Haowen Pang, Jing Shen, Shouliang Qi, Jie Feng, Yong Yue, Wei Qian, Jianlin Wu
Summary: Lobectomy is an effective therapy for lung cancer, and this study assessed the changes in lung and lobe volume after lobectomy and predicted postoperative lung volume. The study found that lung volume decreased after lobectomy, but the attenuation distribution changed little. Machine learning models were used to predict postoperative lung volume, which can help with surgical planning and improve prognosis.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Jiao Wei, Can Tong, Bingxue Wu, Qiang He, Shouliang Qi, Yudong Yao, Yueyang Teng
Summary: This article presents a new type of nonnegative matrix factorization (NMF) called entropy weighted NMF (EWNMF), which assigns an optimizable weight to each attribute of each data point to emphasize their importance. Experimental results demonstrate the feasibility and effectiveness of the proposed method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Caiwen Xu, Jie Feng, Yong Yue, Wanjun Cheng, Dianning He, Shouliang Qi, Guojun Zhang
Summary: A hybrid few-shot multiple-instance learning model was developed to successfully predict lymphoma aggressiveness in PET/CT images, showcasing the potential of artificial intelligence in medical applications with limited samples.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2024)