Yidi Chen

Yidi Chen


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2023 in Radiology
Verified
Journal Article
Closed access
HJHanyu Jiang
Hanyu Jiang
CYChongtu Yang
Chongtu Yang
YCYidi Chen
Yidi Chen
YWYanshu Wang
Yanshu Wang
YWYuanan Wu
Yuanan Wu
BSBin Song
Bin Song
Background Identifying patients at high risk for advanced-stage hepatocellular carcinoma (HCC) recurrence after liver resection may improve patient survival. Purpose To develop a model including MRI features for predicting postoperative advanced-stage HCC recurrence. Materials and Methods This single-center, retrospective study includes consecutive adult patients who underwent preoperative contrast-enhanced MRI and curative-intent resection for early- to intermediate-stage HCC (from December 2011 to April 2021). Three radiologists evaluated 52 qualitative features on MRI scans. In the training set, Fine-Gray proportional subdistribution hazard analysis was performed to identify clinical, laboratory, imaging, pathologic, and surgical variables to include in the predictive model. In the test set, the concordance index (C-index) was computed to compare the developed model with current staging systems. The Kaplan-Meier survival curves were compared using the log-rank test. Results The study included 532 patients (median age, 54 years; IQR, 46-62 years; 465 male patients), 302 patients from the training set (median age, 54 years; IQR, 46-63 years; 265 male patients), and 128 patients from the test set (median age, 53 years; IQR, 46-63 years; 108 male patients). Advanced-stage recurrence was observed in 38 of 302 (12.6%) and 15 of 128 (11.7%) of patients from the training and test sets, respectively. Serum neutrophil count (109/L), tumor size (in centimeters), and arterial phase hyperenhancement proportion on MRI scans were associated with advanced-stage recurrence (subdistribution hazard ratio range, 1.16-3.83; 95% CI: 1.02, 7.52; P value range, <.001 to .02) and included in the predictive model. The model showed better test set prediction for advanced-stage recurrence than four staging systems (2-year C-indexes, 0.82 [95% CI: 0.74, 0.91] vs 0.63-0.68 [95% CI: 0.52, 0.82]; P value range, .001-.03). Patients at high risk for HCC recurrence (model score, ≥15 points) showed increased advanced-stage recurrence and worse all-stage recurrence-free survival (RFS), advanced-stage RFS, and overall survival than patients at low risk for HCC recurrence (P value range, <.001 to .02). Conclusion A model combining serum neutrophil count, tumor size, and arterial phase hyperenhancement proportion predicted advanced-stage HCC recurrence better than current staging systems and may identify patients at high risk. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tsai and Mellnick in this issue.

1 November 2019 in Journal of Magnetic Resonance Imaging
Verified
Journal Article
Closed access
PDF file
YCYidi Chen
Yidi Chen
XQXiali Qin
Xiali Qin
LLLiling Long
Liling Long
LZLing Zhang
Ling Zhang
ZHZhongkui Huang
Zhongkui Huang
CLChenhui Li
Chenhui Li

24 February 2025 in Liver International
Verified
Journal Article
Open access
TZTianying Zheng
Tianying Zheng
YZYajing Zhu
Yajing Zhu
HJHanyu Jiang
Hanyu Jiang
CYChongtu Yang
Chongtu Yang
YYYuxiang Ye
Yuxiang Ye
YCYidi Chen
Yidi Chen
Background & Aims: Microvascular invasion (MVI) is associated with poor prognosis in hepatocellular carcinoma (HCC). Topology may improve the predictive performance and interpretability of deep learning (DL). We aimed to develop and externally validate an MRI‐based topology DL model for preoperative prediction of MVI. Methods: This dual‐centre retrospective study included consecutive surgically treated HCC patients from two tertiary care hospitals. Automatic liver and tumour segmentations were performed with DL methods. A pure convolutional neural network (CNN) model, a topology‐CNN (TopoCNN) model and a topology‐CNN‐clinical (TopoCNN+Clinic) model were developed and externally validated. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Cox regression analyses were conducted to identify risk factors for recurrence‐free survival within 2 years (early RFS) and overall survival (OS). Results: In total, 589 patients were included (292 [49.6%] with pathologically confirmed MVI). The AUCs of the TopoCNN and TopoCNN+Clinic models were 0.890 and 0.895 for the internal test dataset and 0.871 and 0.879 for the external test dataset, respectively. For tumours ≤ 3.0 cm, the AUCs of the TopoCNN and TopoCNN+Clinic models were 0.879 and 0.929 for the internal test dataset, and 0.763 and 0.758 for the external test dataset. The TopoCNN‐derived MVI prediction probability was an independent risk factor for early RFS (hazard ratio 6.64) and OS (hazard ratio 13.33). Conclusions: The MRI topological DL model based on automatic liver and tumour segmentation could accurately predict MVI and effectively stratify postoperative early RFS and OS, which may assist in personalised treatment decision‐making.

1 November 2024 in Radiology
Verified
Journal Article
Closed access
HJHanyu Jiang
Hanyu Jiang
Roberto CannellaRoberto Cannella
Roberto Cannella
ZWZhenru Wu
Zhenru Wu
ABAurélie Beaufrère
Aurélie Beaufrère
MBMarco Dioguardi Burgio
Marco Dioguardi Burgio
Maxime RonotMaxime Ronot
Maxime Ronot
In general, MRI-assessed intratumoral fat was nonprognostic, but homogeneous intratumoral fat was associated with longer recurrence-free survival and overall survival in an Asian cohort of patients with hepatocellular carcinoma.

7 August 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
KZKe Zou
Ke Zou
YBYang Bai
Yang Bai
BLBo Liu
Bo Liu
YCYidi Chen
Yidi Chen
ZCZhihao Chen
Zhihao Chen
HFHuazhu Fu
Huazhu Fu
Medical phrase grounding is crucial for identifying relevant regions in medical images based on phrase queries, facilitating accurate image analysis and diagnosis. However, current methods rely on manual extraction of key phrases from medical reports, reducing efficiency and increasing the workload for clinicians. Additionally, the lack of model confidence estimation limits clinical trust and usability. In this paper, we introduce a novel task—Medical Report Grounding (MRG)—which aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner. To address this challenge, we propose uMedGround, a a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases by embedding a unique token, < $\mathtt {BOX}$ >, into the vocabulary to enhance detection capabilities. A vision encoder-decoder processes the embedded token and input image to generate grounding boxes. Critically, uMedGround incorporates an uncertainty-aware prediction model, significantly improving the robustness and reliability of grounding predictions. Experimental results demonstrate that uMedGround outperforms state-of-the-art medical phrase grounding methods and fine-tuned large visual-language models, validating its effectiveness and reliability. This study represents a pioneering exploration of the MRG task, marking the first-ever endeavor in this domain. Additionally, we demonstrate the applicability of uMedGround in medical visual question answering and class-based localization tasks, where it highlights visual evidence aligned with key diagnostic phrases, supporting clinicians in interpreting various types of textual inputs, including free-text reports, visual question answering queries, and class labels.

23 September 2025 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
KZKe Zou
Ke Zou
YCYidi Chen
Yidi Chen
LHLing Huang
Ling Huang
NZNan Zhou
Nan Zhou
XYXuedong Yuan
Xuedong Yuan
HFHuazhu Fu
Huazhu Fu
Medical image segmentation is critical for disease diagnosis and treatment assessment. However, concerns regarding the reliability of segmentation regions persist among clinicians, mainly attributed to the absence of confidence assessment, robustness, and calibration to accuracy. To address this, we introduce deep evidential segmentation model (DEviS), an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks. DEviS not only enhances the calibration and robustness of baseline segmentation accuracy but also provides high-efficiency uncertainty estimation for reliable predictions. By leveraging SL theory, we explicitly model probability and uncertainty for medical image segmentation. Here, the Dirichlet distribution parameterizes the distribution of probabilities for different classes of the segmentation results. To generate calibrated predictions and uncertainty, we develop a trainable CUP. Furthermore, DEviS incorporates an uncertainty-aware filtering (UAF) module, which designs the metric of uncertainty-calibrated error to filter out-of-distribution (OOD) data. We conducted validation studies on publicly available datasets, including ISIC2018, KiTS2021, LiTS2017, and BraTS2019, to assess the accuracy and robustness of different backbone segmentation models enhanced by DEviS, as well as the efficiency and reliability of uncertainty estimation. Additionally, two potential clinical trials were conducted using the UAF module. The clinical application conducted on the Johns Hopkins OCT and Duke OCT-DME datasets demonstrated the effectiveness of the model in filtering OOD data. The second trial evaluated its efficacy in filtering high-quality data on the FIVES datasets. At last, the proposed DEviS method was extended to semi-supervised medical image segmentation, where it exhibited strong robustness under noisy conditions. Our code has been released in https://github.com/Cocofeat/DEviS.