Article
Radiology, Nuclear Medicine & Medical Imaging
Hang Li, Xiao-li Chen, Huan Liu, Yi-Sha Liu, Zhen-lin Li, Ming-hui Pang, Hong Pu
Summary: The study aimed to develop a T2WI-based multiregional radiomics model for predicting tumor deposit (TD) and prognosis in patients with resectable rectal cancer. Intra- and peritumoral features were extracted from T2WI images and the most valuable radiomics features were determined. A clinical-radiomics nomogram and a prognostic model for 3-year recurrence-free survival (RFS) were constructed using these features. The models showed good performance in predicting TD and recurrence risk.
EUROPEAN RADIOLOGY
(2023)
Review
Oncology
Lu-Lu Jia, Qing-Yong Zheng, Jin-Hui Tian, Di-Liang He, Jian-Xin Zhao, Lian-Ping Zhao, Gang Huang
Summary: This study evaluated the diagnostic accuracy of AI models with MRI in predicting pCR to nCRT in rectal cancer patients. Results showed that DL models had higher predictive accuracy than radiomics models, and combined models with clinical factors had higher diagnostic accuracy than radiomics models alone.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiao-Li Song, Jia-Liang Ren, Ting-Yu Yao, Dan Zhao, Jinliang Niu
Summary: A radiomics signature based on multisequence MRI is effective in predicting peritoneal metastasis in ovarian cancer patients. Combining clinical predictors, a nomogram can improve the prediction ability for peritoneal metastasis in patients with ovarian cancer.
EUROPEAN RADIOLOGY
(2021)
Article
Oncology
Hang Li, Xiao-li Chen, Huan Liu, Tao Lu, Zhen-lin Li
Summary: This study established and evaluated a clinical-radiomics model based on multiregional T2-weighted imaging for predicting lymph node metastasis and prognosis in patients with resectable rectal cancer. Intra- and peritumoral features were extracted and radiomics signatures were built using selected features. The clinical-radiomic nomogram showed good performance in predicting preoperative lymph node metastasis. The combined clinical-radiomic nomogram based on lymph node metastasis and MRI-reported extramural vascular invasion showed potential for assessing 3-year recurrence-free survival.
FRONTIERS IN ONCOLOGY
(2023)
Article
Oncology
Wenjing Peng, Lijuan Wan, Sicong Wang, Shuangmei Zou, Xinming Zhao, Hongmei Zhang
Summary: This study aimed to compare the utility of radiomics models and traditional clinical models in predicting the therapeutic effect of neoadjuvant chemoradiotherapy for locally advanced rectal cancer. The results showed that MRI-based radiomic models did not provide definite added value compared to clinical models, but they can serve as ancillary tools for tailoring treatment strategies.
FRONTIERS IN ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Loic Duron, Alexandre Heraud, Frederique Charbonneau, Mathieu Zmuda, Julien Savatovsky, Laure Fournier, Augustin Lecler
Summary: An MRI radiomics signature can effectively differentiate between benign and malignant orbital lesions, outperforming expert radiologists. The model had an area under the receiver operating characteristic curve of 0.869 on the test set, with high accuracy, sensitivity, and specificity values. Additional clinical and imaging data did not significantly impact the algorithm's performance.
INVESTIGATIVE RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Niels W. Schurink, Simon R. van Kranen, Joost J. M. van Griethuysen, Sander Roberti, Petur Snaebjornsson, Frans C. H. Bakers, Shira H. de Bie, Gerlof P. T. Bosma, Vincent C. Cappendijk, Remy W. F. Geenen, Peter A. Neijenhuis, Gerald M. Peterson, Cornelis J. Veeken, Roy F. A. Vliegen, Femke P. Peters, Nino Bogveradze, Najim el Khababi, Max J. Lahaye, Monique Maas, Geerard L. Beets, Regina G. H. Beets-Tan, Doenja M. J. Lambregts
Summary: This study aims to develop and validate a multiparametric model to predict neoadjuvant treatment response in rectal cancer using a heterogeneous multicenter MRI dataset.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Xiao-Li Song, Hong-Jian Luo, Jia-Liang Ren, Ping Yin, Ying Liu, Jinliang Niu, Nan Hong
Summary: The performance of multisequence MRI-based radiomics models in assessing MSI status in EC patients was evaluated. The study showed that these models have the potential to predict the MSI status in EC patients.
Review
Gastroenterology & Hepatology
Pei-Pei Wang, Chao-Lin Deng, Bin Wu
Summary: In recent years, the use of artificial intelligence, particularly machine learning, in rectal cancer has been increasingly reported, especially in models based on high-resolution MRI. These AI models not only assist in staging diagnosis and localizing radiotherapy, but also have the potential to predict chemotherapy response and patient prognosis.
WORLD JOURNAL OF GASTROENTEROLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Ying-mei Zheng, Jian Li, Song Liu, Jiu-fa Cui, Jin-feng Zhan, Jing Pang, Rui-zhi Zhou, Xiao-li Li, Cheng Dong
Summary: The MRI-based radiomics nomogram showed good performance in differentiating between benign and malignant parotid gland tumors, providing valuable information for clinical decision-making.
EUROPEAN RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Mi Zhou, Tong Gong, Meining Chen, Yuting Wang
Summary: This study investigated the feasibility of high-resolution integrated dynamic shimming echo planar imaging (iEPI) in rectal cancer. The high-resolution iEPI had superior image quality compared to high-resolution sEPI and sEPI, and it had the highest efficacy in differentiating rectal cancer with different degrees of differentiation.
EUROPEAN RADIOLOGY
(2023)
Article
Oncology
Guangwen Zhang, Lei Chen, Aie Liu, Xianpan Pan, Jun Shu, Ye Han, Yi Huan, Jinsong Zhang
Summary: The study examined the feasibility of using deep learning-based segmentation for predicting KRAS/NRAS/BRAF mutations in rectal cancer using MR radiomics. The 3D V-net architecture showed reliable segmentation performance on T2WI and DWI images. Radiomics-based models combined with DL-based segmentation demonstrated comparable gene prediction performance to manual segmentation.
FRONTIERS IN ONCOLOGY
(2021)
Article
Oncology
Yang Zhang, Jiaxuan Peng, Jing Liu, Yanqing Ma, Zhenyu Shu
Summary: The study aimed to compare the predictive performance of different radiomics signatures from mpMRI in predicting PNI in RC patients, and to establish an optimal nomogram for this purpose. The results showed that the fusion radiomics signature outperformed single-sequence radiomics signatures and the clinical model. The nomogram incorporating CEA, tumour stage, and rad-score showed the best predictive performance.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yuxi Ge, Yanlong Jia, Yunzhi Li, Jiankun Dai, Rongping Guan, Shudong Hu
Summary: This study evaluated the imaging quality of a synthetic phase-sensitive inversion recovery (SyPSIR) vessel and its value in detecting extramural venous invasion (EMVI) in patients with rectal cancer using T2-weighted imaging (T2WI). The results showed that combining T2WI and SyPSIR vessels improved the diagnostic performance for EMVI, with increased sensitivity and area under the curve.
EUROPEAN RADIOLOGY
(2023)
Article
Oncology
Juan Li, Liangjie Lin, Xuemei Gao, Shenglei Li, Jingliang Cheng
Summary: This study found that amide proton transfer (APT) weighted and intravoxel incoherent motion (IVIM) imaging have significant value in evaluating prognostic factors for rectal adenocarcinoma. They can help determine histopathological type, tumor grade, and extramural vascular invasion status.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yanfen Cui, Xue'e Cui, Xiaotang Yang, Zhizheng Zhuo, Xiaosong Du, Lei Xin, Zhao Yang, Xintao Cheng
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2019)
Article
Oncology
Yanfen Cui, Wenhui Yang, Jialiang Ren, Dandan Li, Xiaosong Du, Junjie Zhang, Xiaotang Yang
Summary: A radiomics model was developed to predict survival and chemotherapeutic benefits in LARC patients, using pretreatment MR images and clinicopathological features. The model outperformed clinicopathological models, showing better prediction performance and potential for guiding adjuvant chemotherapy. High-risk patients identified by the radiomics model had poorer outcomes and showed a favorable response to adjuvant chemotherapy compared to low-risk patients.
RADIOTHERAPY AND ONCOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Junjie Zhang, Guanghui Wang, Jialiang Ren, Zhao Yang, Dandan Li, Yanfen Cui, Xiaotang Yang
Summary: By analyzing multiparametric MRI images, we developed a radiomics model that can predict the lymphovascular invasion (LVI) status and clinical outcomes in patients with breast invasive ductal carcinoma (IDC). The model combines different sequences of MRI images and achieves improved accuracy in predicting LVI.
EUROPEAN RADIOLOGY
(2022)
Article
Oncology
Ruirui Song, Yanfen Cui, Jialiang Ren, Junjie Zhang, Zhao Yang, Dandan Li, Zhenhui Li, Xiaotang Yang
Summary: The CT-based radiomics models constructed in this study demonstrated good performance in predicting the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer, which is of great clinical significance.
RADIOTHERAPY AND ONCOLOGY
(2022)
Article
Oncology
Jiayi Zhang, Yanfen Cui, Kaikai Wei, Zhenhui Li, Dandan Li, Ruirui Song, Jialiang Ren, Xin Gao, Xiaotang Yang
Summary: This study developed a model using deep learning algorithm and computed tomography (CT) images to predict neoadjuvant chemotherapy (NACT) resistance in patients with locally advanced gastric cancer (LAGC). The model showed promising performance in both internal and external validation cohorts, outperforming the clinical model.
Article
Medicine, Research & Experimental
Yumeng Wang, Xipeng Pan, Huan Lin, Chu Han, Yajun An, Bingjiang Qiu, Zhengyun Feng, Xiaomei Huang, Zeyan Xu, Zhenwei Shi, Xin Chen, Bingbing Li, Lixu Yan, Cheng Lu, Zhenhui Li, Yanfen Cui, Zaiyi Liu, Zhenbing Liu
Summary: In this study, a computerized method was developed to extract texture features from tumor tissue in patients with resectable lung adenocarcinoma (LUAD). The extracted features were used to construct a prognostic model that could predict overall survival. The model, which integrated texture features with clinicopathological variables, showed improved prognostic stratification compared to using clinicopathological variables alone. The identified texture features were also associated with biological pathways.
JOURNAL OF TRANSLATIONAL MEDICINE
(2022)
Article
Multidisciplinary Sciences
Xipeng Pan, Huan Lin, Chu Han, Zhengyun Feng, Yumeng Wang, Jiatai Lin, Bingjiang Qiu, Lixu Yan, Bingbing Li, Zeyan Xu, Zhizhen Wang, Ke Zhao, Zhenbing Liu, Changhong Liang, Xin Chen, Zhenhui Li, Yanfen Cui, Cheng Lu, Zaiyi Liu
Summary: This study aimed to develop and validate an artificial intelligence-driven pathological scoring system for assessing tumor-infiltrating lymphocytes (TILs) in lung adenocarcinoma (LUAD) patients. The scoring system, based on deep learning methods, showed a correlation between risk score and patient outcomes, outperforming the clinicopathologic model in predicting prognosis.
Article
Medicine, General & Internal
Yanfen Cui, Jiayi Zhang, Zhenhui Li, Kaikai Wei, Ye Lei, Jialiang Ren, Lei Wu, Zhenwei Shi, Xiaochun Meng, Xiaotang Yang, Xin Gao
Summary: An accurate prediction model for the response to neoadjuvant chemotherapy in patients with locally advanced gastric cancer (LAGC) was developed using a deep learning radiomics nomogram. The model exhibited satisfactory performance in both internal and external validation cohorts, providing valuable information for personalized treatment.