CDChenchen Dai

Chenchen Dai

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chenchen Dai has a total of 101 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Extreme cardiac MRI analysis under respiratory motion: Results of the CMRxMotion challenge

    by Kang Wang, Chen Qin, Zhang Shi, Haoran Wang, Xiwen Zhang, Chen Chen, Cheng Ouyang, Chengliang Dai, Yuanhan Mo, Chenchen Dai, et al.


  • Open Access

    Node-RADS category on preoperative CT predicts prognosis in patients with papillary renal cell carcinoma

    by Xiaoxia Li, Dengqiang Lin, Ying Xiong, Weifeng Lin, Shaoting Zhang, Shunfa Huang, Jianjun Zhou, Chenchen Dai

    Objectives: This research focused on investigating the relationship between the Node Reporting and Data System (Node-RADS) categories, determined via preoperative CT, and the outcomes of progression-free survival (PFS) and cancer-specific survival (CSS) in individuals diagnosed with papillary renal cell carcinoma (pRCC). Methods: A retrospective multicenter study initially enrolled 454 patients, with 218 eligible for analysis following partial nephrectomy or radical resection for pRCC. Prognostic factors related to PFS and CSS in pRCC patients were identified through univariate and multivariate Cox regression analyses. Subsequently, the prognostic value of Node-RADS was assessed and compared with the existing pRCC risk stratification model. Results: In total, 218 patients (mean age, 58 years; men, 164 [75.2%]) with pRCC (186 Node-rads I tumors (85.3%), 10 Node-rads II tumors (4.6%), and 22 Node-rads III tumors (10.1%)) were included. The Node-RADS category emerged as an independent prognostic factor for PFS (III vs II vs I, hazard ratio (HR) 4.250, p < 0.001) and CSS (III vs II vs I, HR 4.466; p < 0.001). When the Node-RADS category was incorporated into Leibovich’s model, the resulting combined model demonstrated a significant improvement in predictive accuracy (C-index: 0.865 versus 0.755, p = 0.005 for PFS; and 0.921 versus 0.835, p = 0.01 for CSS). Conclusion: The Node-RADS category has been identified as a more accurate predictor of prognosis for pRCC, regardless of pathologic lymph node involvement. These findings need further confirmation in prospective studies. Key Points: Question Lymph node status is important for papillary renal cell carcinoma prognosis, and there is a lack of consensus on radiological evaluation. Findings Node-RADS is an independent predictor of progression-free survival and cancer-specific survival in papillary renal cell carcinoma. Clinical relevance The Node Reporting and Data System category improves the accuracy of the Leibovich model for prognosis, which can help clinical practitioners select individualized treatment plans for each patient. Graphical


  • Diagnostic Performance of Multiparametric Clear Cell Likelihood Score for Characterization of Subcentimeter Solid Renal Lesions: A Multi-institutional Study

    by Run Wang, Fan Meng, Xiaoxia Li, Pingyi Zhu, Jianyi Qu, Jianjun Zhou, Ying Xiong, Shunfa Huang, Chenchen Dai


  • Top Cited Papers
    Open Access

    Artificial intelligence links CT images to pathologic features and survival outcomes of renal masses

    by Ying Xiong, Linpeng Yao, Jinglai Lin, Jiaxi Yao, Qi Bai, Yuan Huang, Xue Zhang, Risheng Huang, Run Wang, Kang Wang, et al.

    Treatment decisions for an incidental renal mass are mostly made with pathologic uncertainty. Improving the diagnosis of benign renal masses and distinguishing aggressive cancers from indolent ones is key to better treatment selection. We analyze 13261 pre-operative computed computed tomography (CT) volumes of 4557 patients. Two multi-phase convolutional neural networks are developed to predict the malignancy and aggressiveness of renal masses. The first diagnostic model designed to predict the malignancy of renal masses achieves area under the curve (AUC) of 0.871 in the prospective test set. This model surpasses the average performance of seven seasoned radiologists. The second diagnostic model differentiating aggressive from indolent tumors has AUC of 0.783 in the prospective test set. Both models outperform corresponding radiomics models and the nephrometry score nomogram. Here we show that the deep learning models can non-invasively predict the likelihood of malignant and aggressive pathology of a renal mass based on preoperative multi-phase CT images.


  • Can multiparametric MRI clear cell likelihood scores differentiate fat-Poor AML from CcRCC in subcentimeter lesions?

    by Ying Xiong, Yinglong Guo, Xiaoxia Li, Pingyi Zhu, Jianyi Qu, Shunfa Huang, Run Wang, Jianjun Zhou, Jianfeng Huang, Chenchen Dai

    Objective To investigate the potential of multiparametric MRI clear cell likelihood scores (ccLS) for differentiating between fat-poor angiomyolipoma (AML) and clear cell renal cell carcinoma (ccRCC) in subcentimeter Lesions (1 cm or smaller). Materials and methods This retrospective study included consecutive patients with subcentimeter renal masses who underwent multiparametric MRI between September 2009 and September 2022 across three hospitals. Clinical and MRI findings were analyzed to differentiate between fat-poor AML and ccRCC. Lesions were categorized using the ccLS and receiver operating characteristic curve analysis was performed to assess ccLS performance. Results Thirty-eight patients (mean age: 52 years ± 12; 19 women) with 39 lesions were included. Of the 39 lesions [mean size: 9.1 mm ± 1.0 (range, 6.0–10.0 mm)], 20 (51%) were ccRCC and 19 (49%) were fat-poor AML. Compared to the ccRCC, subcentimeter fat-poor AMLs were more likely to show hypointensity on T2WI (P < 0.001), homogeneous enhancement (P = 0.010), the presence of microscopic fat (P = 0.036), and the absence of a pseudocapsule (P = 0.020). The diagnostic percentage of fat-poor AML was 47% for a ccLS of 1 or 2, and ccRCC accounted for 75% in the ccLS 4 or 5 category. The AUC for discrimination was 0.846 (95% CI: 0.695–0.941, P < 0.001), with a sensitivity of 75.00% (95% CI: 50.9–91.3) and a specificity of 89.47% (95% CI: 66.9–98.7). Conclusion Multiparametric MRI clear cell likelihood scores can potentially be used to differentiate between fat-poor AML and ccRCC in lesions 1 cm or smaller.


  • Open Access

    Peritumoral Cortex Low-Enhancement Sign on Corticomedullary Phase CT: A Distinctive Indicator of Small Renal Malignancies

    by Jianyi Qu, Xinyan Li, Pingyi Zhu, Wenjie Zhang, Xiaofei Wang, Zhaofeng Zheng, Xinhong Song, Chenchen Dai, Heng Ma, Jianjun Zhou

    Qu J, et al. Korean J Radiol. 2025 Aug;26:e71. https://doi.org/10.3348/kjr.2025.0458


  • Top Cited Papers

    Deep Learning Assessment of Small Renal Masses at Contrast-enhanced Multiphase CT

    by Chenchen Dai, Ying Xiong, Pingyi Zhu, Linpeng Yao, Jinglai Lin, Jiaxi Yao, Xue Zhang, Risheng Huang, Run Wang, Jun Hou, et al.

    A deep learning algorithm based on contrast-enhanced multiphase CT demonstrated good performance for characterizing small (≤3 cm) renal masses as benign lesions.


  • Differentiation of renal cell carcinoma subtypes with different iodine quantification methods using single-phase contrast-enhanced dual-energy CT: areal vs. volumetric analyses

    by Chenchen Dai, Yingli Cao, Yan Jia, Yuqin Ding, Ruofan Sheng, Mengsu Zeng, Jianjun Zhou

    Purpose To investigate the possibility of iodine quantification during a single nephrographic phase in characterizing renal cell carcinoma (RCC) subtypes and if there is a difference between areal and volumetric iodine quantification methods. Materials and methods This retrospective study included 110 patients with 113 histopathologically confirmed RCCs scanned by dual-energy CT at the nephrographic phase before surgeries. For each lesion, an areal measurement of the iodine concentration with maximum enhancement (I max enhan) and the iodine concentration with maximum area among slices (I max area), as well as a volumetric iodine concentration of the whole-tumor (I volume), were evaluated by two independent radiologists. The diagnostic performances in a single nephrographic phase for characterizing RCC subtypes were evaluated, and three iodine quantification methods were compared with each other. Results There were significant differences (clear cell vs. papillary and clear cell vs. chromophobe RCC) and no significant differences (papillary vs. chromophobe RCC) at the nephrographic phase in all three methods. The area under the receiver operating characteristic (ROC) curve (AUC) derived from the I max enhan for discriminating clear cell from papillary RCC was significantly higher than that derived from the I max area (P = 0.0357) and the I volume (P = 0.0206), and no significant differences existed among the three methods in distinguishing clear cell RCC from chromophobe RCC. The reliability of all three parameters was very high with an interclass correlation coefficient (ICC) exceeding 0.8. Conclusions Iodine quantification in a single nephrographic phase can be used to differentiate RCC subtypes preoperatively, and the areal maximum enhancement iodine quantification would probably be the most appropriate approach.