EUVIMEDScopri EUVIMED
Crossref

Towards quality control and harmonization of deep learning CT radiomics: An in‐silico feasibility study with virtual colorectal liver metastases

Mamatha Venugopal, Sathish Ramani, Jacob J Peoples, Richard K G Do, Amber L Simpson, Ge Wang, Bruno De Man

Medical Physics · 2026

DOI: 10.1002/mp.70500 ↗

At a glance

Journal article in Medical Physics, 2026. Written by Mamatha Venugopal and 6 co-authors. Institution: Technology & Innovation Center, GE HealthCare, JFWTC, Bengaluru, Karnataka, India. Major MEDLINE topics: Radiomics, Deep Learning, Liver Neoplasms, Colorectal Neoplasms. 47 references. Funded by: NIH/NCI.

AbstractSubjectsDati bibliograficiCiteRelated studies

Abstract (original language)

Background

Radiomic imaging biomarkers are increasingly studied in oncology as a means to support disease prognosis and personalized treatment planning. While deep learning (DL) offers scalable alternatives to handcrafted radiomic features, DL‐derived biomarkers are sensitive to variations in image acquisition protocols and scanner hardware—even within a single imaging modality. To ensure reliable and reproducible biomarker estimation, it is essential to (1) provide clinicians with quantitative uncertainty estimates associated with biomarker predictions, and (2) address acquisition‐induced variability through harmonization strategies that render consistent performance across diverse imaging conditions.

Purpose

To evaluate uncertainty estimation as a reliability metric for biomarker prediction and to assess the role of image harmonization in improving cross‐scanner inference, we develop deep learning radiomics (DLR) models for joint estimation of biomarkers and associated uncertainties and apply linear harmonization filters to standardize imaging conditions.

Methods

We constructed hybrid digital phantoms by embedding 20,000 virtual colorectal liver metastases into 20 clinical CT liver images to generate metastases‐laden simulated scans. The proposed DLR models jointly estimated a selected set of biomarkers and their associated aleatoric uncertainties from simulated images. Models were trained, validated, and tested using a 70:20:10 data split. Variability in CT image acquisition was modelled using two scanner types, two reconstruction kernels, and three x‐ray tube current settings. DLR performance was evaluated under direct inference (matched training and test scanners), cross‐scanner inference, and harmonized inference using linear harmonization filters. Quantitative evaluation was based on correlation coefficients and root mean squared errors (RMSEs).

Results

The estimated uncertainties were consistently higher for biomarker predictions with larger deviations from ground truth. Excluding high‐uncertainty predictions improved concordance between predictions and ground truth biomarkers. The proportion of uncertain predictions increased under cross‐scanner inference relative to direct inference, indicating reduced biomarker reliability under heterogeneous imaging conditions. Furthermore, application of harmonization filters reduced RMSEs by an average of 43% across biomarkers and experiments during cross‐scanner inference, demonstrating improved cross‐scanner consistency.

Conclusions

In this controlled in‐silico study, uncertainty estimation provided a practical reliability metric for DL‐based radiomic biomarker prediction, while image harmonization improved reproducibility across heterogeneous acquisition conditions. These findings demonstrate methodological feasibility within a simulation‐based framework but have not yet been validated on clinical CT data, motivating future clinical validation and translation.

Subjects

MeSH terms (MEDLINE)

RadiomicsDeep LearningLiver NeoplasmsColorectal NeoplasmsTomography, X-Ray ComputedImage Processing, Computer-AssistedComputer SimulationHumansFeasibility StudiesQuality Control

Author keywords

data harmonizationdeep learningimage biomarkersliver metastasisradiomicsuncertainty estimation

Authors and institutions

  • Technology & Innovation Center, GE HealthCare, JFWTC, Bengaluru, Karnataka, India.
  • Technology & Innovation Center, GE HealthCare, Niskayuna, New York, USA.
  • Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
  • School of Computing/Department of Biomedical and Molecular Sciences, Queen's University, Ontario, Canada.
  • Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, New York, USA.

Funding

  • NIH/NCI

Cite

APA

Venugopal, M., Ramani, S., Peoples, J. J., Do, R. K. G., Simpson, A. L., Wang, G., & De Man, B. (2026). Towards quality control and harmonization of deep learning CT radiomics: An in‐silico feasibility study with virtual colorectal liver metastases. Medical Physics. https://doi.org/10.1002/mp.70500

Vancouver

Venugopal M, Ramani S, Peoples JJ, Do RKG, Simpson AL, Wang G, et al. Towards quality control and harmonization of deep learning CT radiomics: An in‐silico feasibility study with virtual colorectal liver metastases. Medical Physics. 2026. doi:10.1002/mp.70500

BibTeX
@article{Venugopal2026,
  author = {Venugopal, Mamatha and Ramani, Sathish and Peoples, Jacob J and Do, Richard K G and Simpson, Amber L and Wang, Ge and De Man, Bruno},
  title = {Towards quality control and harmonization of deep learning CT radiomics: An in‐silico feasibility study with virtual colorectal liver metastases},
  journal = {Medical Physics},
  year = {2026},
  doi = {10.1002/mp.70500}
}
Start for free →