CT-based habitat imaging integrated with radiomics and clinicopathology for noninvasive prediction of microvascular invasion in hepatocellular carcinoma - Takeaways - MDSpire

CT-based habitat imaging integrated with radiomics and clinicopathology for noninvasive prediction of microvascular invasion in hepatocellular carcinoma

  • By

  • Shuangxi Chen

  • Xushuang Qin

  • Shanni Dong

  • Xiaoshu Zhu

  • Yang Liu

  • Jun Chen

  • Ruizhong Ye

  • Li Zhu

  • May 22, 2026

  • 0 min

Share

  • 1

    A CT-based habitat imaging model was developed to predict microvascular invasion (MVI) in hepatocellular carcinoma (HCC) noninvasively.

  • 2

    The study included 216 patients with confirmed HCC, utilizing preoperative CT and postoperative histopathologic MVI status.

  • 3

    The combined model achieved an AUC of 0.862 in the training set and 0.814 in the validation set, outperforming individual models.

  • 4

    Calibration curves indicated good agreement, and decision curve analysis showed net benefit for the combined model at specific thresholds.

  • 5

    This model quantifies intratumoral heterogeneity and offers a reliable tool for preoperative MVI risk stratification in HCC.

Original Source(s)

CT-based habitat imaging integrated with radiomics and clinicopathology for noninvasive prediction of microvascular invasion in hepatocellular carcinoma

  • by Shuangxi Chen, Xushuang Qin, Shanni Dong, Xiaoshu Zhu, Yang Liu, Jun Chen, Ruizhong Ye, Li Zhu

  • May 22, 2026

Related Content

Bilateral renal metastasis following radical prostatectomy for prostate cancer: a case report

Characteristics and risk factors of immune-related adverse events in patients receiving immune checkpoint inhibitor combination therapy

The role of NAD+ metabolic reprogramming in colorectal cancer chemoresistance: mechanistic insights, clinical translation challenges and opportunities