Eugene Koay | Searcharxiv

arXiv2026

Risk Prediction in Cancer Imaging Using Enriched Radiomics Features

Background: We aim to develop enriched radiomics features that integrate classical structural radiomics with novel functional radiomics derived from liver MRI for diagnosis and risk stratification in liver cancer. The proposed framework leverages enhancement pattern mapping (EPM) images to provide an automated and robust radiomics representation that captures intratumoral heterogeneity through pixel-level functional information. Methods: Pixel-wise EPM data reflecting blood perfusion were extracted from T1-weighted MRI scans. Classical structural radiomics features were extracted via existing software such as PyRadiomics. In addition, empirical quantiles of EPM values over all pixels within the image, and then smoothed using suitable basis. The smoothed quantiles, along with the classical structural quantiles, are used as functional radiomics features for diagnostic classification and tumor grade stratification, using L1-penalized logistic model that automatically downweights the contribution of the irrelevant features. Further, we conducted longitudinal analyses using Bayesian tensor response regression, which enables spatial smoothing and parsimonious modeling of temporally evolving imaging patterns. Results: The enriched radiomics features illustrate higher diagnostic classification performance (AUC=0.96, sensitivity> 0.8) and superior tumor grade stratification accuracy (AUC=0.87, sensitivity=0.8) compared to alternate radiomics features. Moreover, we find that the proportion of lesion pixels with significant reduction in EPM values over time is considerably higher (median = 0.12) in aggressive lesions versus stable or mildly aggressive lesions (median = 0.025). Conclusion: The enriched novel radiomics features can potentially replace classical radiomics analysis and be used for imaging biomarkers in cross-sectional and in longitudinal cancer imaging studies.

stat.AP↗

arXiv2022

Evaluating the Performance of StyleGAN2-ADA on Medical Images

Although generative adversarial networks (GANs) have shown promise in medical imaging, they have four main limitations that impeded their utility: computational cost, data requirements, reliable evaluation measures, and training complexity. Our work investigates each of these obstacles in a novel application of StyleGAN2-ADA to high-resolution medical imaging datasets. Our dataset is comprised of liver-containing axial slices from non-contrast and contrast-enhanced computed tomography (CT) scans. Additionally, we utilized four public datasets composed of various imaging modalities. We trained a StyleGAN2 network with transfer learning (from the Flickr-Faces-HQ dataset) and data augmentation (horizontal flipping and adaptive discriminator augmentation). The network's generative quality was measured quantitatively with the Fréchet Inception Distance (FID) and qualitatively with a visual Turing test given to seven radiologists and radiation oncologists. The StyleGAN2-ADA network achieved a FID of 5.22 ($\pm$ 0.17) on our liver CT dataset. It also set new record FIDs of 10.78, 3.52, 21.17, and 5.39 on the publicly available SLIVER07, ChestX-ray14, ACDC, and Medical Segmentation Decathlon (brain tumors) datasets. In the visual Turing test, the clinicians rated generated images as real 42% of the time, approaching random guessing. Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images. We observed the FID to be consistent with human perceptual evaluation of medical images. Finally, our work found that StyleGAN2-ADA consistently produces high-quality results without hyperparameter searches or retraining.

eess.IV↗