Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 56 min ago
Peer-reviewedCC BYClinics (Sao Paulo, Brazil)

A multimodal MRI radiomics sonata for differentiating small renal masses: a two-center retrospective study.

  • Chao Fang1
  • Li Tian2
  • Ming Gao3
  • Xiaohui Duan3
  • Qi Liu1
  • Zixin Xu1
  • Junjiong Zheng1
  • Yushu Chen1
  • Ming Huang1
  • Xu Chen1
  • Wei Jiang3
  • Jianqiu Kong4
1 more authors
  • Wen Dong5
5 affiliations
  1. 1Department of Urology, Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China.
  2. 2Department of Medical Imaging, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer Center, Guangzhou, Guangdong, China.
  3. 3Department of Radiology, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, Guangdong, China.
  4. 4Department of Urology, Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China. Electronic address: [email protected].
  5. 5Department of Urology, Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China. Electronic address: [email protected].
Read full textPDFDOICite

Abstract

Background

Accurately distinguishing benign from malignant small renal masses (SRMs) is crucial to avoid unnecessary surgeries, yet reliable preoperative diagnostic tools remain limited.Methods

A total of 189 patients with SRMs from two hospitals (2018-2022) were enrolled. Clinical data and MRI features were analyzed by two radiologists. Radiomics features were automatically extracted from manually segmented ROIs using dedicated software. Significant features were selected via univariate analysis, multivariate regression, and Lasso to develop three models: radiomics, clinical, and combined nomogram. Diagnostic performance was evaluated using the Area Under the receiver operating characteristic Curve (AUC).Results

The radiomics-clinical nomogram was constructed using T2WI signal intensity (p < 0.001), pseudocapsule (p = 0.001), and radiomics score (Rad-score, p = 0.001) via multivariate logistic regression. In the training set, the nomogram achieved an AUC of 0.962 (95% CI: 0.931-0.993), outperforming both the radiomics model (AUC = 0.918, 95% CI: 0.862-0.974) and the clinical model (AUC = 0.856, 95% CI: 0.780-0.933). Favorable performance was observed in the internal validation set (nomogram: AUC = 0.981, 95% CI: 0.944-1.000; radiomics model: AUC = 0.912, 95% CI: 0.750-1.000; clinical model: AUC = 0.844, 95% CI: 0.578-1.000) and external validation set (nomogram: AUC = 0.971, 95% CI: 0.886-1.000; radiomics model: AUC = 0.928, 95% CI: 0.841-0.989; clinical model: AUC = 0.916,95% CI: 0.760-0.976).Conclusion

All three models enable effective and non-invasive preoperative differentiation of benign from malignant SRMs, with the radiomics-clinical nomogram exhibiting the highest diagnostic accuracy, supporting its potential as a valuable clinical tool.

Related

  1. Multiparametric MRI-based radiomics for differentiating HER2-negative, HER2-low, and HER2-positive breast cancer
    Lulu Gai, Shubin Luo, Yudong Yan +9
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. A multimodal deep learning radiomics nomogram integrating clinicopathological features for predicting pathological complete response after neoadjuvant therapy in triple-negative breast cancer: a multicenter retrospective study
    Chuanchuan Qi
    Frontiers in oncologyPeer-reviewedCC BYFull textMedical imaging & radiologyEurope PMCCrossref
  3. Differentiating Xp11.2/TFE3 translocation renal cell carcinoma from clear cell carcinoma: performance of a radiomics model.
    Yi Liu, Kexin Wang, Yaofeng Zhang +5
    BMC cancerPeer-reviewedCC BY-NC-NDFull textMedical imaging & radiologyEurope PMCDOAJ
  4. CT-Based Clinical-Radiomics for Differentiating Talaromyces marneffei Spondylitis From Tuberculous Spondylitis Before Pathogen Confirmation: A Multicentre Diagnostic Study in an Endemic Region.
    Xingqi Zhao, Yilin Teng, Gangyi Wu +6
    MycosesPeer-reviewedCC BY-NC-NDFull textSurgery & anaesthesiaEurope PMC
  5. Computed tomography multi-phase radiomics models for differentiating benign and malignant thyroid nodules
    Ning Li, Jianan Tong, Guozheng Zhang +5
    Frontiers in EndocrinologyPeer-reviewedCC BY 4.0Full textMedical imaging & radiologyCrossrefEurope PMCEurope PMCPMC

Cite

BibTeXRIS
BibTeX
@article{fang2026multimodal,
  title = {{A multimodal MRI radiomics sonata for differentiating small renal masses: a two-center retrospective study.}},
  author = {Chao Fang and Li Tian and Ming Gao and Xiaohui Duan and Qi Liu and Zixin Xu and Junjiong Zheng and Yushu Chen and Ming Huang and Xu Chen and Wei Jiang and Jianqiu Kong and Wen Dong},
  journal = {Clinics (Sao Paulo, Brazil)},
  year = {2026},
  month = oct,
  doi = {10.1016/j.clinsp.2026.101212},
  url = {https://europepmc.org/article/MED/42887293},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - A multimodal MRI radiomics sonata for differentiating small renal masses: a two-center retrospective study.
AU  - Chao Fang
AU  - Li Tian
AU  - Ming Gao
AU  - Xiaohui Duan
AU  - Qi Liu
AU  - Zixin Xu
AU  - Junjiong Zheng
AU  - Yushu Chen
AU  - Ming Huang
AU  - Xu Chen
AU  - Wei Jiang
AU  - Jianqiu Kong
AU  - Wen Dong
PY  - 2026
DA  - 2026/10/16
JO  - Clinics (Sao Paulo, Brazil)
DO  - 10.1016/j.clinsp.2026.101212
UR  - https://europepmc.org/article/MED/42887293
AB  - Background  Accurately distinguishing benign from malignant small renal masses (SRMs) is crucial to avoid unnecessary surgeries, yet reliable preoperative diagnostic tools remain limited.Methods  A total of 189 patients with SRMs from two hospitals (2018-2022) were enrolled. Clinical data and MRI features were analyzed by two radiologists. Radiomics features were automatically extracted from manually segmented ROIs using dedicated software. Significant features were selected via univariate analysis, multivariate regression, and Lasso to develop three models: radiomics, clinical, and combined nomogram. Diagnostic performance was evaluated using the Area Under the receiver operating characteristic Curve (AUC).Results  The radiomics-clinical nomogram was constructed using T2WI signal intensity (p < 0.001), pseudocapsule (p = 0.001), and radiomics score (Rad-score, p = 0.001) via multivariate logistic regression. In the training set, the nomogram achieved an AUC of 0.962 (95% CI: 0.931-0.993), outperforming both the radiomics model (AUC = 0.918, 95% CI: 0.862-0.974) and the clinical model (AUC = 0.856, 95% CI: 0.780-0.933). Favorable performance was observed in the internal validation set (nomogram: AUC = 0.981, 95% CI: 0.944-1.000; radiomics model: AUC = 0.912, 95% CI: 0.750-1.000; clinical model: AUC = 0.844, 95% CI: 0.578-1.000) and external validation set (nomogram: AUC = 0.971, 95% CI: 0.886-1.000; radiomics model: AUC = 0.928, 95% CI: 0.841-0.989; clinical model: AUC = 0.916,95% CI: 0.760-0.976).Conclusion  All three models enable effective and non-invasive preoperative differentiation of benign from malignant SRMs, with the radiomics-clinical nomogram exhibiting the highest diagnostic accuracy, supporting its potential as a valuable clinical tool.
SN  - 1807-5932
SN  - 1980-5322
ER  -