相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Review
Oncology
Erich P. Huang et al.
Summary: Integration of computer-extracted tumour characteristics into medical imaging computer-aided diagnosis (CAD) algorithms has been a long-standing practice. However, the translation of radiomics, an extension of CAD involving quantitative characterization of healthy or pathological structures and processes captured by medical imaging, into clinically useful tools has been limited. This may be due to factors such as varying imaging and radiomic feature extraction protocols, potential pitfalls in radiomic data analysis, and a lack of evidence demonstrating the clinical benefit of radiomic-based tools. The authors provide 16 criteria to guide the clinical translation of radiomics, with the aim of accelerating the use of this technology to improve patient outcomes.
NATURE REVIEWS CLINICAL ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Burak Kocak et al.
Summary: Although radiomics has great potential for supporting clinical decision-making, its current use is mainly limited to academic research, not routine clinical practice. The complex workflow and inadequate reporting and evaluation of radiomics often result in poor reproducibility. A complete radiomics checklist called CLEAR (CheckList for EvaluAtion of Radiomics research) is presented here to address these concerns and improve the quality and reliability of radiomic research. The checklist, consisting of 58 items, serves as a standardization tool for presenting clinical radiomics research and is open for public comments and adaptations in a public repository.
INSIGHTS INTO IMAGING
(2023)
Review
Radiology, Nuclear Medicine & Medical Imaging
Gaia Spadarella et al.
Summary: This systematic review aims to provide a comprehensive overview of Radiomics Quality Score (RQS)-based systematic reviews and evaluate the relationship between RQS and review features. The results indicate that the quality of radiomic articles reported in systematic reviews does not differ significantly between different subgroups, and the overall methodological quality of radiomics research is low.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ying-mei Zheng et al.
Summary: A radiomics nomogram based on contrast-enhanced computed tomography (CECT) was constructed to predict Ki-67 expression level in head and neck squamous cell carcinoma (HNSCC). The radiomics nomogram showed favorable predictive efficacy and clinical utility, providing useful information for prognostic evaluation and clinical decision-making in patients with HNSCC.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jingyu Zhong et al.
Summary: This study compared the image quality between a deep learning image reconstruction (DLIR) algorithm and conventional iterative reconstruction (IR) algorithms in dual-energy CT (DECT) and assessed their impact on radiomics robustness. The results showed that DLIR significantly improved the image quality of DECT, but may alter radiomics features compared to conventional IR. Nine robust DECT radiomics features were identified.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiaoling Ma et al.
Summary: In this study, a DL signature based on the Swin Transformer was developed to predict LN metastasis in patients with lung adenocarcinoma. The DL signature showed promising performance and provided important information for noninvasive mediastinal LN staging and individualized therapeutic options.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Haiyan Zhang et al.
Summary: This study aimed to develop and validate a machine learning model based on radiomics features to detect early brainstem infarction on non-contrast computed tomography (NCCT). The multilayer perceptron (MLP) RMEBI model showed the best performance both in the internal and external validation cohorts. These results suggest that RMEBIs can accurately diagnose early brainstem infarction in routine clinical practice and may help reduce therapeutic decision-making time.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiaobo Zhang et al.
Summary: This study evaluated the predictive value of time-serial CT radiomics features for progression-free survival in lung adenocarcinoma patients treated with EGFR-TKIs. The results showed that the comprehensive radiomics model outperformed baseline clinical characteristics in predicting progression-free survival. This dynamic imaging biomarker holds promise for monitoring treatment response and achieving personalized management.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Die Zhang et al.
Summary: Investigating the value of R2* mapping-based radiomics nomograms in staging liver fibrosis in patients with chronic hepatitis B. The radiomics nomograms combined with R2* mapping-based Radscore, laminin, and platelet have value in staging advanced fibrosis and cirrhosis but limited value for staging significant fibrosis.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Min Lin et al.
Summary: This study aimed to explore the clinical value of ultrasound radiomics analysis in the diagnosis of cervical lymph node metastasis in patients with nasopharyngeal carcinoma. The results showed that ultrasound radiomics analysis has the potential to screen meaningful ultrasound features and improve diagnostic efficiency.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jingxuan Jiang et al.
Summary: The study aims to develop a clot-based radiomics model using CT imaging radiomic features and machine learning to identify cardioembolic (CE) stroke before mechanical thrombectomy (MTB) in patients with acute ischemic stroke (AIS). The results show that the radiomics model performs better than the routine radiological method in predicting CE stroke.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Qiaoling Chen et al.
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
Radiology, Nuclear Medicine & Medical Imaging
Wyanne A. Noortman et al.
Summary: This study investigates the use of [F-18]FDG-PET/CT radiomics, SUVmax, and biochemical profiles for identifying the genetic clusters of PPGLs. The results show that PET radiomics performs better in identifying PPGLs compared to biochemistry, SUVmax, and CT radiomics, especially in the differentiation of sporadic PPGLs.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Russell Frood et al.
Summary: This study evaluated the ability of machine learning models derived from pre-treatment FDG PET/CT to predict outcomes in cHL patients. The results showed that a ridge regression model using a 1.5 x mean liver SUV segmentation had the highest performance, with a high AUC when evaluated on training, validation, and test datasets.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Qiang Zheng et al.
Summary: This study investigates how different hippocampal segmentation methods affect the accuracy of hippocampal radiomic features (HRFs) in Alzheimer's disease (AD) analysis. The results show that HRFs exhibit high consistency across different segmentation methods and the best performance in AD classification is obtained when HRFs are extracted using the naive majority voting method with a more sufficient segmentation and relatively low hippocampal segmentation accuracy.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Emmanuel Salinas-Miranda et al.
Summary: This study investigated the association between transcriptional subtypes and an externally validated preoperative CT-based radiomic prognostic score (Rad-score). The results showed that high Rad-scores were correlated with the squamous subtype, while low Rad-scores were associated with less lethal subtypes.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Meixin Zhao et al.
Summary: This study investigates the ability of machine learning models trained on clinical data and positron emission tomography/computed tomography (PET/CT) radiomics to predict survival outcomes and risk factors in lung adenocarcinoma patients. The results demonstrate that machine learning models can accurately predict long-term survival and risk factors in lung adenocarcinoma patients.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Chao Zhu et al.
Summary: This study suggests that a CTE-based radiomics model has potential value in predicting mucosal healing in CD patients. A nomogram constructed by combining radiomics signatures and clinical features can help clinicians select appropriate therapeutic strategies for CD patients.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ying Fan et al.
Summary: This study explores the value of multi-parametric MRI-based radiomics in detecting EGFR mutation and resistance (T790M) mutation in lung adenocarcinoma patients with spinal metastasis. The study found that radiomics features from spinal metastasis can predict EGFR and T790M mutations, and the constructed nomogram models have potential as new markers for guiding treatment management in these patients.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Shucheng Bi et al.
Summary: This study assessed the predictive ability of a multi-parametric MRI-based radiomics signature (RS) for the preoperative evaluation of Ki-67 proliferation status in sinonasal malignancies. The results showed that the RS can be used as a non-invasive and accurate tool for evaluating the proliferation status of patients.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiaoyang Xie et al.
Summary: This study demonstrates the value of deep learning in combining multimodal radiomics and clinical and imaging features for differentiating ocular adnexal lymphoma (OAL) from idiopathic orbital inflammation (IOI). The DL model using combined features outperformed those using only multimodal radiomics features or clinical and imaging features, indicating the benefit of combining multiple modalities for more accurate diagnosis.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Dan Bao et al.
Summary: A radiomics-based model developed from pretreatment MRI of the temporal lobe showed persuasive performance in predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Fei Xiang et al.
Summary: This study aimed to develop and validate a radiomics signature to estimate recurrence-free survival in GBC patients. The results showed that the radiomics signature and combined nomogram could assist in predicting RFS in GBC patients, demonstrating good prediction performance.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Nuo Si et al.
Summary: The radiomics analysis of PCAT captured by CCTA showed superior performance in discriminating acute MI from UA, indicating its potential clinical value.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yunlin Zheng et al.
Summary: The combined model incorporating radiomics and clinical features demonstrated an excellent ability to distinguish between benign and malignant parotid tumors, providing a noninvasive and efficient method for clinical decision making.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jin Juan Kang et al.
Summary: The magnetic susceptibility value and radiomics features of the nigrostriatal system could play a crucial role in diagnosing Parkinson's disease and its related cognitive impairment.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jeroen Bleker et al.
Summary: The deep learning masked auto-fixed volume of interest (DLM) segmentation method provides a more accurate radiomics diagnosis of clinically significant prostate cancer (CS PCa) compared to manual segmentation, while significantly reducing expert time investment.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Haolin Chen et al.
Summary: This study developed and evaluated a deep learning-based automatic meningioma segmentation method for preoperative meningioma differentiation using radiomic features. The results showed that the developed method enables automatic and accurate extraction of meningioma from multiparametric MR images, which can help deploy radiomics for preoperative meningioma differentiation in clinical practice.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hao Zhang et al.
Summary: This study developed and validated CT and radiomics nomograms to differentiate mass-forming chronic pancreatitis (MFCP) from pancreatic ductal adenocarcinoma (PDAC). The nomograms showed good differentiation ability in patients with chronic pancreatitis and have the potential to refine the management of pancreatic masses in these patients.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Funing Chu et al.
Summary: This study developed and validated an optimized model for predicting the survival of patients with esophageal squamous cell carcinoma (ESCC) based on the 1-mm-isotropic-3D contrast-enhanced StarVIBE MRI sequence and clinical risk factors. The combined model, which incorporated radiomics features and clinical factors, showed better predictive efficacy compared to radiomics models alone.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Michal Eifer et al.
Summary: The study aimed to differentiate between FDG-avid breast cancer metastatic lymphadenopathy and FDG-avid COVID-19 mRNA vaccine-related axillary lymphadenopathy using machine learning and radiomics. The results demonstrated that radiomics features can effectively differentiate between the two conditions, which may have clinical significance in distinguishing between benign and malignant lymph nodes.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yeshaswini Nagaraj et al.
Summary: An automatic COVID-19 Reporting and Data System (CO-RADS)-based classification was developed in a multi-demographic setting. The study achieved clinically acceptable performance and can serve as a standardized tool for automated COVID-19 assessment. Inter-observer agreement for CO-RADS scoring was significant, and suspected COVID-19 CT scans were identified with an accuracy of 84%.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jingyu Zhong et al.
Summary: This study implemented a pipeline to automatically segment the ROI and used a nomogram integrating the MRI-based radiomics score and clinical variables to predict responses to neoadjuvant chemotherapy (NAC) in osteosarcoma patients. The results showed that this automated approach could aid radiologists in identifying pathological good responders to NAC.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Bo Cheng et al.
Summary: This study established a non-invasive radiomics model based on computed tomography (CT) to predict EGFR mutation status in GGO-featured lung adenocarcinoma, subsequently guiding the administration of targeted therapy with favorable sensitivity and specificity.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Claudio E. von Schacky et al.
Summary: This study developed a machine learning model to distinguish between benign and malignant bone lesions and compared its performance to radiologists. The results showed that an artificial neural network model combining radiomic features and demographic information achieved good accuracy, sensitivity, and AUC in different test sets.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ming-De Li et al.
Summary: The study systematically assessed the reproducibility of radiomics features from ultrasound images, finding that wavelet and shearlet features showed the best reproducibility across all procedures.
EUROPEAN RADIOLOGY
(2022)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Daniel Pinto dos Santos et al.
Summary: Although radiomics shows promise in analyzing medical image data, there are pitfalls to avoid for reproducibility. There is a gap in translating radiomics research into clinical practice, and more high-evidence studies focusing on prospective research with clinical impact are needed going forward.
EUROPEAN RADIOLOGY
(2021)
Review
Radiology, Nuclear Medicine & Medical Imaging
Jingyu Zhong et al.
Summary: This systematic review evaluated the methodological quality and risk of bias in radiomics studies on osteosarcoma. Despite insufficient overall scientific quality, radiomics shows promise in predicting treatment response, guiding therapeutic decisions, and impacting prognosis. Improvements in study design, validation, and open science are needed for clinical applications.
EUROPEAN RADIOLOGY
(2021)
Review
Clinical Neurology
Lorenzo Ugga et al.
Summary: This study systematically reviewed studies using radiomics and machine learning in patients with intracranial meningioma for diagnostic and predictive purposes. Promising results were found for preoperative meningioma grading using machine learning, but more high-quality studies are needed before clinical implementation.
Review
Radiology, Nuclear Medicine & Medical Imaging
Meilinuer Abdurixiti et al.
Summary: This study assessed the methodological quality of radiomic studies based on PET/CT images predicting EGFR mutation status in NSCLC patients. The methodologies in the radiomic workflow varied greatly, with first-order statistics being the most reproducible features. The quality of the studies needs improvement before application to the clinical setting.
BRITISH JOURNAL OF RADIOLOGY
(2021)
Review
Radiology, Nuclear Medicine & Medical Imaging
Gaia Spadarella et al.
Summary: The methodological quality of MRI-based radiomics studies in nasopharyngeal cancer patients is generally low, with significant limitations in external validation, biological correlation, prospective design, and open science. More efforts are needed to improve the quality and rigor of radiomic studies in this area.
EUROPEAN JOURNAL OF RADIOLOGY
(2021)
Article
Multidisciplinary Sciences
Chansik An et al.
Summary: The study conducted two classification tasks using real-world brain tumor radiomics data and found significant variability in AUCs between training and testing sets, especially with undersampled datasets and difficult tasks. When there was a large discrepancy in AUC between training and test sets, none of the validation methods helped reduce the generalization gap sufficiently.
Article
Medicine, General & Internal
Yung-Shuo Kao et al.
Summary: This study highlights the potential of CT-based radiomics feature models in successfully distinguishing COVID-19 from other viral pneumonia infections, providing valuable insights for diagnostic accuracy in the field.
Editorial Material
Oncology
Kenneth Miles
BRITISH JOURNAL OF CANCER
(2020)
Review
Radiology, Nuclear Medicine & Medical Imaging
Stephan Ursprung et al.
EUROPEAN RADIOLOGY
(2020)
Review
Radiology, Nuclear Medicine & Medical Imaging
Arnaldo Stanzione et al.
EUROPEAN JOURNAL OF RADIOLOGY
(2020)
Review
Radiology, Nuclear Medicine & Medical Imaging
Hongxi Wang et al.
EUROPEAN RADIOLOGY
(2020)
Article
Radiology, Nuclear Medicine & Medical Imaging
Dongsheng Gu et al.
EUROPEAN RADIOLOGY
(2019)
Review
Oncology
Philippe Lambin et al.
NATURE REVIEWS CLINICAL ONCOLOGY
(2017)
Article
Psychology, Social
Daniel Lakens
SOCIAL PSYCHOLOGICAL AND PERSONALITY SCIENCE
(2017)
Article
Radiology, Nuclear Medicine & Medical Imaging
Robert J. Gillies et al.
Article
Rehabilitation
Terry K. Koo et al.
JOURNAL OF CHIROPRACTIC MEDICINE
(2016)
Article
Medical Laboratory Technology
Mary L. McHugh
Article
Health Care Sciences & Services
Jan Kottner et al.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2011)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Alexander A. Bankier et al.