Machine-learning-based performance comparison of two-dimensional (2D) and three-dimensional (3D) CT radiomics features for intracerebral haemorrhage …

Q Chen, C Fu, X Qiu, J He, T Zhao, Q Zhang, X Hu… - Clinical Radiology, 2024 - Elsevier
… mortality of 40% and 5-year survival rate of 29%. Haematoma … the clinical and radiological
characteristics between the two … to the interests of preventing further growth in post-ICH care. …

Development and Validation of a Radiomics Nomogram Based on 18F-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography and …

B Yang, J Zhong, J Zhong, L Ma, A Li, H Ji… - Frontiers in …, 2020 - frontiersin.org
… , we developed and validated a radiomics nomogram by combining the radiomic features
extracted … We constructed three rad-scores based on CT features, PET features, and PET/CT

Additional value of metabolic parameters to PET/CT-based radiomics nomogram in predicting lymphovascular invasion and outcome in lung adenocarcinoma

P Nie, G Yang, N Wang, L Yan, W Miao, Y Duan… - … and molecular imaging, 2021 - Springer
… the radiomics nomogram integrating clinical factors, CT features… were finally selected for
RS development. However, the … , and hematological features improved survival prediction in …

Comparison of clinical-computed tomography model with 2D and 3D radiomics models to predict occult peritoneal metastases in advanced gastric cancer

J Huang, Y Chen, Y Zhang, J Xie, Y Liang, W Yuan… - … Radiology, 2022 - Springer
CT findings yet. Meanwhile, several reports have suggested that … , the 2D and 3D radiomics
models were developed with … in terms of predicting survival and chemotherapy benefit in GC …

Preoperative prediction of KRAS mutation status in colorectal cancer using a CT-based radiomics nomogram

T Xue, H Peng, Q Chen, M Li, S Duan… - … Journal of Radiology, 2022 - academic.oup.com
… This study aimed to develop a model to predict KRAS … In this study, it was found that CT
imaging features based on the … study, the 3D radiomics model was slightly better than the 2D

A radiomics nomogram for the prediction of overall survival in patients with hepatocellular carcinoma after hepatectomy

Q Liu, J Li, F Liu, W Yang, J Ding, W Chen, Y Wei, B Li… - Cancer Imaging, 2020 - Springer
… in the 2D analysis and a narrower SD in the 3D analysis were … large number of quantitative
imaging features, which may be … study aimed to develop a radiomics signature to predict the …

2D and 3D CT radiomic features performance comparison in characterization of gastric cancer: a multi-center study

L Meng, D Dong, X Chen, M Fang… - IEEE journal of …, 2020 - ieeexplore.ieee.org
… demonstrated that radiomic features could predict LNM, survival, … in 3D modality, significantly
restricts the development … Dong et al., “Deep learning radiomic nomogram can predict the …

A CT-based radiomics nomogram for predicting the progression-free survival in small cell lung cancer: a multicenter cohort study

X Zheng, K Liu, C Li, C Zhu, Y Gao, J Li, X Wu - La radiologia medica, 2023 - Springer
develop and validate a CT-based radiomics nomogram to estimate the progression-free
survival … This study not only constructed radiomics signature with six CT features associated with …

CT-based radiomics nomogram may predict local recurrence-free survival in esophageal cancer patients receiving definitive chemoradiation or radiotherapy: A …

J Gong, W Zhang, W Huang, Y Liao, Y Yin, M Shi… - Radiotherapy and …, 2022 - Elsevier
… In total, 107 original imaging features were extracted and analyzed from the manually
segmented … In conclusion, we developed and validated a hybrid radiomics nomogram model that …

Development of a nomogram based on 3D CT radiomics signature to predict the mutation status of EGFR molecular subtypes in lung adenocarcinoma: a multicenter …

G Zhang, L Deng, J Zhang, Y Cao, S Li, J Ren… - Frontiers in …, 2022 - frontiersin.org
… The radiological features have been shown to reflect EGFR mutation status in lung … CT,
radiomics converts medical images into mineable data and extracts a large number of features