Scholarlink

Background <p>This study aimed to develop and validate an interpretable radiomics model using quantitative features from B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) for predicting macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC).</p> Methods <p>From October 2020 to September 2023, 344 patients (mean age: 58.20 ± 10.70 years; 275 men) with surgically resected HCC were retrospectively enrolled from three medical centers. Radiomics features were extracted from BMUS and CEUS, followed by a multiple-step feature selection process. BMUS<sub>R</sub> model (based on BMUS radiomics features), BM + CEUS<sub>R</sub> model (based on BMUS and CEUS radiomics features) and hybrid<sub>R+C</sub> model (integrated clinical indicators and radiomic features) were established. These radiomics models’ performance was compared with conventional clinic-radiological (C<sub>C+R</sub>) model using area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) method was used to interpret model performance. The model’s potential for predicting recurrence-free survival (RFS) was further analyzed.</p> Results <p>Among ten distinct machine learning classifiers evaluated, the AdaBoost algorithm demonstrated the highest classification performance. The AUCs of the BM + CEUS<sub>R</sub> model for identifying MTM-HCC were higher than the BMUS<sub>R</sub> model and the conventional clinic-radiological model in both validation (0.880 vs. 0.720 and 0.658, both <i>p</i> &lt; 0.05) and test sets (0.878 vs. 0.605 and 0.594, both <i>p</i> &lt; 0.05). No statistical differences were observed between the BM + CEUS<sub>R</sub> model and the hybrid<sub>R+C</sub> model in either set (<i>p</i> &gt; 0.05). Additionally, the AdaBoost-based BM + CEUS<sub>R</sub> model showed promising in stratifying early recurrence-free survival, with <i>p</i> &lt; 0.001.</p> Conclusion <p>The AdaBoost-based BM + CEUS<sub>R</sub> model shows promise as a tool for preoperatively identifying MTM-HCC and may also be beneficial in predicting prognosis.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

B-mode ultrasound and contrast-enhanced ultrasound-based radiomics interpretable analysis for the prediction of macrotrabecular-massive subtype of hepatocellular carcinoma

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月17日

查看全文
  • Dan Lu,
  • Cheng Qin,
  • Li-Fan Wang,
  • Ling-Ling Li,
  • Yu Li,
  • Li-Ping Sun,
  • Hui Shi,
  • Bo-Yang Zhou,
  • Xin Guan,
  • Yao Miao,
  • Hong Han,
  • Jian-Hua Zhou,
  • Hui-Xiong Xu,
  • Chong-Ke Zhao

摘要

Background

This study aimed to develop and validate an interpretable radiomics model using quantitative features from B-mode ultrasound (BMUS) and contrast-enhanced ultrasound (CEUS) for predicting macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC).

Methods

From October 2020 to September 2023, 344 patients (mean age: 58.20 ± 10.70 years; 275 men) with surgically resected HCC were retrospectively enrolled from three medical centers. Radiomics features were extracted from BMUS and CEUS, followed by a multiple-step feature selection process. BMUSR model (based on BMUS radiomics features), BM + CEUSR model (based on BMUS and CEUS radiomics features) and hybridR+C model (integrated clinical indicators and radiomic features) were established. These radiomics models’ performance was compared with conventional clinic-radiological (CC+R) model using area under the receiver operating characteristic curve (AUC). SHapley Additive exPlanations (SHAP) method was used to interpret model performance. The model’s potential for predicting recurrence-free survival (RFS) was further analyzed.

Results

Among ten distinct machine learning classifiers evaluated, the AdaBoost algorithm demonstrated the highest classification performance. The AUCs of the BM + CEUSR model for identifying MTM-HCC were higher than the BMUSR model and the conventional clinic-radiological model in both validation (0.880 vs. 0.720 and 0.658, both p < 0.05) and test sets (0.878 vs. 0.605 and 0.594, both p < 0.05). No statistical differences were observed between the BM + CEUSR model and the hybridR+C model in either set (p > 0.05). Additionally, the AdaBoost-based BM + CEUSR model showed promising in stratifying early recurrence-free survival, with p < 0.001.

Conclusion

The AdaBoost-based BM + CEUSR model shows promise as a tool for preoperatively identifying MTM-HCC and may also be beneficial in predicting prognosis.