Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 14;151(2):84.
doi: 10.1007/s00432-025-06119-8.

An interpretable ensemble model combining handcrafted radiomics and deep learning for predicting the overall survival of hepatocellular carcinoma patients after stereotactic body radiation therapy

Yi Chen #  1   2 , David Pasquier #  3   4   5 , Damon Verstappen  1 , Henry C Woodruff  1   6 , Philippe Lambin  1   6
Affiliations

An interpretable ensemble model combining handcrafted radiomics and deep learning for predicting the overall survival of hepatocellular carcinoma patients after stereotactic body radiation therapy

Yi Chen et al. J Cancer Res Clin Oncol. .

Abstract

Purpose: Hepatocellular carcinoma (HCC) remains a global health concern, marked by increasing incidence rates and poor outcomes. This study seeks to develop a robust predictive model by integrating radiomics and deep learning features with clinical data to predict 2-year survival in HCC patients treated with stereotactic body radiation therapy (SBRT).

Methods: This study analyzed a cohort of 186 HCC patients who underwent SBRT. Radiomics features were extracted from CT scans, complemented by collection of clinical data. Training and validation of machine learning models were conducted using nested cross-validation techniques. Deep learning models, leveraging various convolutional neural networks (CNNs), were employed to effectively integrate both image and clinical data. Post-hoc explainability techniques were applied to elucidate the contribution of imaging data to predictive outcomes.

Results: Handcrafted radiomics features demonstrated moderate predictive performance, with area under the receiver operating characteristic curve (AUC) values ranging from 0.59 to 0.72. Deep learning models, harnessing the fusion of image and clinical data, exhibited improved predictive accuracy, with AUC values ranging from 0.71 to 0.81. Notably, the ensemble model, amalgamating handcrafted radiomics and deep learning features with clinical data, demonstrated the most robust predictive capability, achieving an AUC of 0.86 (95% CI: 0.80-0.93).

Conclusion: The ensemble model represents a significant advancement, providing a comprehensive tool for predicting survival outcomes in HCC patients undergoing SBRT. The inclusion of interpretability methods such as Grad-CAM enhances transparency and understanding of these complex predictive models.

Keywords: Deep learning; Handcrafted features; Hepatocellular carcinoma; Radiomics; Stereotactic body radiation therapy.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: This research study was conducted retrospectively from data obtained for clinical purposes. The study protocols were in compliance with the French Regulation for retrospective studies (MR004). Consent for publication: Not applicable. Consent to participate: Consent for participation was obtained in compliance with the French Regulation for retrospective studies. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Representation of the workflow of constructing models
Fig. 2
Fig. 2
Boxplot of the ROC AUC for handcrafted radiomics and clinical features
Fig. 3
Fig. 3
ROC AUC curves for deep learning (DL) based on radiomics, images (Img) +/- clinical features, and ensemble models
Fig. 4
Fig. 4
Gradient-Class Activation Maps in the whole liver of a patient using deep learning model (red and green: negative and positive contribution respectively). White contour: gross tumour volume
See this image and copyright information in PMC

References

    1. Adebayo J, Gilmer J, Muelly M, Goodfellow I, Hardt M, Kim B (2018) Sanity Checks for Saliency Maps. 32nd Conference on Neural Information Processing Systems (NeurIPS), Montréal, Canada https://arxiv.org/pdf/1810.03292
    1. Affo S, Yu LX, Schwabe RF (2017) The role of Cancer-Associated fibroblasts and fibrosis in Liver Cancer. Annu Rev Pathol 12:153–186 - PMC - PubMed
    1. Beuque MPL, Lobbes MBI, van Wijk Y, Widaatalla Y, Primakov S, Majer M, Balleyguier C, Woodruff HC, Lambin P (2023) Combining Deep Learning and Handcrafted Radiomics for classification of suspicious lesions on contrast-enhanced mammograms. Radiology 307:e221843 - PubMed
    1. Cozzi L, Dinapoli N, Fogliata A, Hsu WC, Reggiori G, Lobefalo F, Kirienko M, Sollini M, Franceschini D, Comito T, Franzese C, Scorsetti M, Wang PM (2017) Radiomics based analysis to predict local control and survival in hepatocellular carcinoma patients treated with volumetric modulated arc therapy. BMC Cancer 17:829 - PMC - PubMed
    1. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577 - PMC - PubMed

MeSH terms

LinkOut - more resources