arXiv subjects

Helia Abedini

Publications and source records attributed to Helia Abedini.

2 recordsLinked to original sources

arXiv2026

Robust Multicenter CT Radiogenomics for Dual EGFR and KRAS Prediction in Lung Cancer with Stability-Aware Modeling and SHAP Interpretation

Accurate identification of EGFR and KRAS mutations is essential for precision therapy in non-small cell lung cancer (NSCLC), but tissue genotyping is invasive and may not capture tumor heterogeneity. CT-based radiogenomics offers a noninvasive alternative, although generalization across centers remains challenging. We benchmarked handcrafted radiomics features (HRF), deep feature representations (DFR), and their fusion for three-class mutation prediction (wild-type, KRAS-mutant, and EGFR-mutant) with external testing. We curated 1,023 thoracic CT scans from 12 public datasets across more than 20 centers, including 136 patients with EGFR/KRAS labels. IBSI-compliant HRFs were extracted with standardized preprocessing, and DFRs were derived using PySERA. HRF-only, DFR-only, and fused HRF+DFR pipelines were evaluated using five-fold cross-validation and external testing. A semi-supervised pseudo-labeling strategy leveraged unlabeled CT scans, and SHAP supported interpretability. In external testing, HRF-based models generalized best, achieving AUC 0.77 +/- 0.07 and accuracy 0.77 +/- 0.00. DFR-based models showed a larger drop from cross-validation to external testing, with best external AUC around 0.57 +/- 0.05. Fusion improved robustness over DFR-only models but did not consistently outperform HRFs. SHAP identified morphology- and heterogeneity-related radiomic phenotypes as key predictors. Standardized handcrafted radiomics within a multicenter semi-supervised framework may provide a generalizable and interpretable approach for CT-based EGFR/KRAS stratification.

physics.med-ph↗

arXiv2025

General vs Domain-Specific CNNs: Understanding Pretraining Effects on Brain MRI Tumor Classification

The accurate identification of brain tumors from magnetic resonance imaging (MRI) is essential for timely diagnosis and effective therapeutic intervention. While deep convolutional neural networks (CNNs), particularly those pre-trained on extensive datasets, have shown considerable promise in medical image analysis, a key question arises when working with limited data: do models pre-trained on specialized medical image repositories outperform those pre-trained on diverse, general-domain datasets? This research presents a comparative analysis of three distinct pre-trained CNN architectures for brain tumor classification: RadImageNet DenseNet121, which leverages pre-training on medical-domain data, alongside two modern general-purpose networks, EfficientNetV2S and ConvNeXt-Tiny. All models were trained and fine-tuned under uniform experimental conditions using a modestly sized brain MRI dataset to maintain consistency in evaluation. The experimental outcomes indicate that ConvNeXt-Tiny delivered the best performance, achieving 93% test accuracy, followed by EfficientNetV2S at 85%. In contrast, RadImageNet DenseNet121 attained only 68% accuracy and exhibited higher loss, indicating limited generalization capability despite its domain-specific pre-training. These observations imply that pre-training on medical-domain data does not necessarily guarantee superior performance in data-scarce scenarios. Conversely, contemporary general-purpose CNNs with deeper architectures, pre-trained on large-scale diverse datasets, may offer more effective transfer learning for specialized diagnostic tasks in medical imaging.

cs.CV↗