Search Results (59)

This paper explores the role of metrology in the assessment of image quality in the field of radiomics. Image Quality Assessment (IQA) is central to ensuring the reliability and reproducibility of radiomic analyses, as it directly affects the accuracy of feature extraction and segmentation, ultimately impacting diagnostic outcomes. From the analysis of approximately 20,000 papers sourced from three databases (PubMed, Scopus, IEEE Xplore), last searched in December 2025, the need for standardized imaging protocols and quality control measures emerges as a critical theme. Studies were included if they involved radiomic feature extraction and evaluated the impact of image quality variations on feature robustness and no formal risk-of-bias assessment was performed. A total of 105 studies were included, covering different medical imaging modalities. Across the included studies, noise, motion, acquisition and reconstruction parameters, and other artifacts consistently emerged as major sources of radiomic feature instability. Indeed, in most papers, IQA is neglected, while the effect of poor-quality images is reported. This research identifies and discusses the relevant issues reported in clinical practice, as well as the main metrics adopted for image quality evaluation. Through a comprehensive review of current literature and an analysis of emerging trends, this paper highlights the urgent need for innovative solutions in image quality metrics tailored to radiomics applications. Full article

Gadolinium-based contrast agents (GBCAs) are vital for glioma imaging yet pose safety, cost, and accessibility issues; predicting contrast enhancement from non-contrast MRI via machine learning (ML) provides a safer, economical alternative, as enhancement indicates tumor aggressiveness and informs treatment planning. However, scanner and population variability hinder robust model selection. To overcome this, a stability-aware framework was developed to identify reproducible ML pipelines for predicting glioma contrast enhancement across multicenter cohorts. A total of 1367 glioma cases from four TCIA datasets (UCSF-PDGM, UPENN-GB, BRATS-Africa, BRATS-TCGA-LGG) were analyzed, using non-contrast T1-weighted images as input and deriving enhancement status from paired post-contrast T1-weighted images; 108 IBSI-standardized radiomics features were extracted via PyRadiomics 3.1, then systematically combined with 48 dimensionality reduction algorithms and 25 classifiers into 1200 pipelines, evaluated through rotational validation (training on three datasets, external testing on the fourth, repeated across rotations) incorporating five-fold cross-validation and a composite score penalizing instability via standard deviation. Cross-validation accuracies spanned 0.91–0.96, with external testing yielding 0.87 (UCSF-PDGM), 0.98 (UPENN-GB), and 0.95 (BRATS-Africa), averaging ~0.93; F1, precision, and recall remained stable (0.87–0.96), while ROC-AUC varied (0.50–0.82) due to cohort heterogeneity, with the MI + ETr pipeline ranking highest for balanced accuracy and stability. This framework enables reliable, generalizable prediction of contrast enhancement from non-contrast glioma MRI, minimizing GBCA dependence and offering a scalable template for reproducible ML in neuro-oncology. Full article

Background: Lung cancer is the leading cause of cancer-related mortality globally. Early detection via low-dose computed tomography (LDCT) can reduce mortality, but its implementation is challenged by the absence of objective diagnostic criteria and the necessity for extensive manual interpretation. Public datasets like the Lung Image Database Consortium often lack pathology-confirmed diagnoses, which can lead to inaccuracies in ground truth labels. Variability in voxel sizes across these datasets also complicates feature extraction, undermining model reliability. Many existing methods for integrating nodule boundary annotations use deep learning models such as generative adversarial networks, which often lack interpretability. Methods: This study assesses the effect of voxel normalization on pulmonary nodule classification and introduces a Fast Fourier Transform-based contour fusion method as a more interpretable alternative. Utilizing pathology-confirmed LDCT data from 415 patients across two medical centers, both machine learning and deep learning models were developed using voxel-normalized images and attention mechanisms, including transformers. Results: The results demonstrated that voxel normalization significantly improved the overlap of features between datasets from two different centers by 64%, resulting in enhanced selection stability. In the ROI-based radiomics analysis, the top-performing machine-learning model achieved an accuracy of 92.6%, whereas the patch-based deep-learning models reached 98.5%. Notably, the FFT-based method provided a clinically interpretable integration of expert annotations, effectively addressing a major limitation of generative adversarial networks. Conclusions: Voxel normalization enhances reliability in pulmonary nodule classification while the FFT-based method offers a viable path toward interpretability in deep learning applications. Future research should explore its implications further in multi-center contexts. Full article

Background/Objectives: Glioblastoma (GBM) exhibits heterogeneous, nonlinear invasion patterns that challenge conventional modeling and radiomic prediction. Most deep learning approaches describe the morphology but rarely capture the dynamical stability of tumor evolution. We propose an AI framework that approximates a latent attractor landscape of GBM morphodynamics—stable basins in a continuous manifold that are consistent with reproducible morphologic regimes. Methods: Multimodal MRI scans from BraTS 2020 (n = 494) were standardized and embedded with a 3D autoencoder to obtain 128-D latent representations. Unsupervised clustering identified latent basins (“attractors”). A neural ordinary differential equation (neural-ODE) approximated latent dynamics. All dynamics were inferred from cross-sectional population variability rather than longitudinal follow-up, serving as a proof-of-concept approximation of morphologic continuity. Voxel-level perturbation quantified local morphodynamic sensitivity, and proof-of-concept control was explored by adding small inputs to the neural-ODE using both a deterministic controller and a reinforcement learning agent based on soft actor–critic (SAC). Survival analyses (Kaplan–Meier, log-rank, ridge-regularized Cox) assessed associations with outcomes. Results: The learned latent manifold was smooth and clinically organized. Three dominant attractor basins were identified with significant survival stratification (χ² = 31.8, p = 1.3 × 10⁻⁷) in the static model. Dynamic attractor basins derived from neural-ODE endpoints showed modest and non-significant survival differences, confirming that these dynamic labels primarily encode the morphodynamic structure rather than fixed prognostic strata. Dynamic basins inferred from neural-ODE flows were not independently prognostic, indicating that the inferred morphodynamic field captures geometric organization rather than additional clinical risk information. The latent stability index showed a weak but borderline significant negative association with survival (ρ = −0.13 [−0.26, −0.01]; p = 0.0499). In multivariable Cox models, age remained the dominant covariate (HR = 1.30 [1.16–1.45]; p = 5 × 10⁻⁶), with overall C-indices of 0.61–0.64. Voxel-level sensitivity maps highlighted enhancing rims and peri-necrotic interfaces as influential regions. In simulation, deterministic control redirected trajectories toward lower-risk basins (≈57% success; ≈96% terminal distance reduction), while a soft actor–critic (SAC) agent produced smoother trajectories and modest additional reductions in terminal distance, albeit without matching the deterministic controller’s success rate. The learned attractor classes were internally consistent and clinically distinct. Conclusions: Learning a latent attractor landscape links generative AI, dynamical systems theory, and clinical outcomes in GBM. Although limited by the cross-sectional nature of BraTS and modest prognostic gains beyond age, these results provide a mechanistic, controllable framework for tumor morphology in which inferred dynamic attractor-like flows describe latent organization rather than a clinically predictive temporal model, motivating prospective radiogenomic validation and adaptive therapy studies. Full article

Background: Glioblastoma (GBM) is among the most aggressive and morphologically heterogeneous brain tumors. Beyond static imaging biomarkers, its structural organization can be viewed as a nonlinear dynamical system. Characterizing morphodynamic attractors within such a system may reveal latent stability patterns of morphological change and potential indicators of morphodynamic organization. Methods: We analyzed 494 subjects from the multi-institutional BraTS 2020 dataset using a fully automated computational pipeline. Each multimodal MRI volume was encoded into a 16-dimensional latent space using a 3D convolutional autoencoder. Synthetic morphological trajectories, generated through bidirectional growth–shrinkage transformations of tumor masks, enabled training of a contraction-regularized Neural Ordinary Differential Equation (Neural ODE) to model continuous-time latent morphodynamics. Morphological complexity was quantified using fractal dimension (DF), and local dynamical stability was measured via a Lyapunov-like exponent (λ). Robustness analyses assessed the stability of DF–λ regimes under multi-scale perturbations, synthetic-order reversal (directionality; sign-aware comparison) and stochastic noise, including cross-generator generalization against a time-shuffled negative control. Results: The DF–λ morphodynamic phase map revealed three characteristic regimes: (1) stable morphodynamics (λ < 0), associated with compact, smoother boundaries; (2) metastable dynamics (λ ≈ 0), reflecting weakly stable or transitional behavior; and (3) unstable or chaotic dynamics (λ > 0), associated with divergent latent trajectories. Latent-space flow fields exhibited contraction-induced attractor-like basins and smoothly diverging directions. Kernel-density estimation of DF–λ distributions revealed a prominent population cluster within the metastable regime, characterized by moderate-to-high geometric irregularity (DF ≈ 1.85–2.00) and near-neutral dynamical stability (λ ≈ −0.02 to +0.01). Exploratory clinical overlays showed that fractal dimension exhibited a modest negative association with survival, whereas λ did not correlate with clinical outcome, suggesting that the two descriptors capture complementary and clinically distinct aspects of tumor morphology. Conclusions: Glioblastoma morphology can be represented as a continuous dynamical process within a learned latent manifold. Combining Neural ODE–based dynamics, fractal morphometry, and Lyapunov stability provides a principled framework for dynamic radiomics, offering interpretable morphodynamic descriptors that bridge fractal geometry, nonlinear dynamics, and deep learning. Because BraTS is cross-sectional and the synthetic step index does not represent biological time, any clinical interpretation is hypothesis-generating; validation in longitudinal and covariate-rich cohorts is required before prognostic or treatment-monitoring use. The resulting DF–λ morphodynamic map provides a hypothesis-generating morphodynamic representation that should be evaluated in covariate-rich and longitudinal cohorts before any prognostic or treatment-monitoring use. Full article

Leveraging the complementary strengths of handcrafted radiomics and data-driven deep learning, this work develops and rigorously benchmarks three modeling streams (Models A, B and C) for pancreatic ductal adenocarcinoma (PDAC) detection on multiphase abdominal Computed Tomography (CT) scans. Model A distills hundreds of PyRadiomics descriptors to sixteen interpretable features that feed a gradient-boosted machine learning model, achieving discrimination (external AUC ≈ 0.99) with excellent calibration. Model B adopts a 3-D CBAM-ResNet-18 trained under weighted cross-entropy and mixed precision; although less accurate in isolation, it yields volumetric Grad-CAM maps that localize the tumor and provide explainability. Model C explores two fusion strategies that merge radiomics and deep embeddings: (i) a two-stage “frozen-stream” variant that locks both feature extractors and learns only a lightweight gating block plus classifier, and (ii) a full end-to-end version that allows the CNN’s adaptor layer to co-train with the fusion head. The frozen approach surpasses the single stream, whereas the end-to-end model reports external AUC of 0.987, balanced sensitivity/specificity above 0.93, and a Brier score below 0.05, while preserving clear Grad-CAM alignment with radiologist-drawn masks. Results demonstrate that a carefully engineered deep-radiomic fusion pipeline can deliver accurate, well-calibrated and interpretable PDAC triage directly from routine CT. Our contributions include a stability-verified 16-feature radiomic signature, a novel deep-radiomic fusion design that improves robustness and interpretability across vendors and a fully guideline-aligned, openly released pipeline for reproducible PDAC detection on routine CT. Full article

Background: Radiomic feature robustness is a key prerequisite for the reproducibility and clinical translation of imaging biomarkers. Variability across software platforms can significantly affect feature consistency, compromising predictive modeling reliability. This study aimed to develop and validate a hierarchical clustering-based workflow for evaluating radiomic feature robustness within and across software platforms, identifying stable and reproducible features suitable for clinical applications. Methods: A multi-cancer CT dataset including 97 lesions from 71 patients, comprising primary colorectal cancer (CRC), colorectal liver metastases, and hepatocellular carcinoma (HCC), was analyzed. Radiomic features were extracted using two IBSI-compliant platforms (MM Radiomics of syngo.via Frontier and 3D Slicer with PyRadiomics). Intra-software reliability was assessed through the intraclass correlation coefficient ICC(A,1), while cross-software stability was evaluated using hierarchical clustering validated by the Adjusted Rand Index (ARI). A Composite Index (CI) integrating correlation, distributional similarity, and mean fractional ratio quantified inter-platform feature robustness. Results: Over 95% of radiomic features demonstrated good-to-excellent intra-software reliability. Several clustering configurations achieved ARI = 1.0, confirming strong cross-platform concordance. The most robust and recurrent features were predominantly wavelet-derived descriptors and first-order statistics, particularly cluster shade (GLCM-based) and mean intensity-related features. Conclusions: The proposed multi-stage framework effectively identifies stable, non-redundant, and transferable radiomic features across IBSI-compliant software platforms. These findings provide a methodological foundation for cross-platform harmonization and enhance the reproducibility of radiomic biomarkers in oncologic imaging. Full article

Lung cancer (LC) remains a leading cause of cancer mortality worldwide, where accurate and early identification of gene mutations such as epidermal growth factor receptor (EGFR) is critical for precision treatment. However, machine learning-based radiomics approaches often face challenges due to the small and imbalanced nature of the datasets. This study proposes a comprehensive framework based on Generic Sparse Regularized Autoencoders with Kullback–Leibler divergence (GSRA-KL) to generate high-quality synthetic radiomics data and overcome these limitations. A systematic approach generated 63 synthetic radiomics datasets by tuning a novel kl_weight regularization hyperparameter across three hidden-layer sizes, optimized using Optuna for computational efficiency. A rigorous assessment was conducted to evaluate the impact of hyperparameter tuning across 63 synthetic datasets, with a focus on the EGFR gene mutation. This evaluation utilized resemblance-dimension scores (RDS), novel utility-dimension scores (UDS), and t-SNE visualizations to ensure the validation of data quality, revealing that GSRA-KL achieves excellent performance (RDS > 0.45, UDS > 0.7), especially when class distribution is balanced, while remaining competitive with the Tabular Variational Autoencoder (TVAE). Additionally, a comprehensive statistical correlation analysis demonstrated strong and significant monotonic relationships among resemblance-based performance metrics up to moderate scaling (≤1.0*), confirming the robustness and stability of inter-metric associations under varying configurations. Complementary computational cost evaluation further indicated that moderate kl_weight values yield an optimal balance between reconstruction accuracy and resource utilization, with Spearman correlations revealing improved reconstruction quality (MSE $\rho =-0.78$, $p<0.001$) at reduced computational overhead. The ablation-style analysis confirmed that including the KL divergence term meaningfully enhances the generative capacity of GSRA-KL over its baseline counterpart. Furthermore, the GSRA-KL framework achieved substantial improvements in computational efficiency compared to prior PSO-based optimization methods, resulting in reduced memory usage and training time. Overall, GSRA-KL represents an incremental yet practical advancement for augmenting small and imbalanced high-dimensional radiomics datasets, showing promise for improved mutation prediction and downstream precision oncology studies. Full article

Objective: Axillary lymph node (ALN) status in breast cancer is pivotal for guiding treatment and determining prognosis. The study aimed to explore the feasibility and efficacy of a radiomics model using voxel-wise dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) time-intensity-curve (TIC) profile maps to predict ALN metastasis in breast cancer. Methods: A total of 615 breast cancer patients who underwent preoperative DCE-MRI from October 2018 to February 2024 were retrospectively enrolled and randomly allocated into training (n = 430) and testing (n = 185) sets (7:3 ratio). Based on wash-in rate, wash-out enhancement, and wash-out stability, each voxel within manually segmented 3D lesions that were categorized into 1 of 19 TIC subtypes from the DCE-MRI images. Three feature sets were derived: composition ratio (type-19), radiomics features of TIC subtypes (type-19-radiomics), and radiomics features of third-phase DCE-MRI (phase-3-radiomics). Student’s t-test and the least absolute shrinkage and selection operator (LASSO) was used to select features. Four models (type-19, type-19-radiomics, type-19-combined, and phase-3-radiomics) were constructed by a support vector machine (SVM) to predict ALN status. Model performance was assessed using sensitivity, specificity, accuracy, F1 score, and area under the curve (AUC). Results: The type-19-combined model significantly outperformed the phase-3-radiomics model (AUC = 0.779 vs. 0.698, p < 0.001; 0.674 vs. 0.559) and the type-19 model (AUC = 0.779 vs. 0.541, p < 0.001; 0.674 vs. 0.435, p < 0.001) in cross-validation and independent testing sets. The type-19-radiomics showed significantly better performance than the phase-3-radiomics model (AUC = 0.764 vs. 0.698, p = 0.002; 0.657 vs. 0.559, p = 0.037) and type-19 model (AUC = 0. 764 vs. 0.541, p < 0.001; 0.657 vs. 0.435, p < 0.001) in cross-validation and independent testing sets. Among four models, the type-19-combined model achieved the highest AUC (0.779, 0.674) in cross-validation and testing sets. Conclusions: Radiomics analysis of voxel-wise DCE-MRI TIC profile maps, simultaneously quantifying temporal and spatial hemodynamic heterogeneity, provides an effective, noninvasive method for predicting ALN metastasis in breast cancer. Full article

Photon-counting computed tomography (PCCT) represents a major technological innovation compared to conventional CT, offering improved spatial resolution, reduced electronic noise, and intrinsic spectral capabilities. These advances open new perspectives for synergy with radiomics, a field that extracts quantitative features from medical images. The ability of PCCT to generate multiple types of datasets, including high-resolution conventional images, iodine maps, and virtual monoenergetic reconstructions, increases the richness of extractable features and potentially enhances radiomics performance. This narrative review investigates the current evidence on the interplay between PCCT and radiomics in cardiothoracic imaging. Phantom studies demonstrate reduced reproducibility between PCCT and conventional CT systems, while intra-scanner repeatability remains high. Nonetheless, PCCT introduces additional complexity, as reconstruction parameters and acquisition settings significantly may affect feature stability. In chest imaging, early studies suggest that PCCT-derived features may improve nodule characterization, but existing machine learning models, such as those applied to interstitial lung disease, may require recalibration to accommodate the new imaging paradigm. In cardiac imaging, PCCT has shown particular promise: radiomic features extracted from myocardial and epicardial tissues can provide additional diagnostic insights, while spectral reconstructions improve plaque characterization. Proof-of-concept studies already suggest that PCCT radiomics can capture myocardial aging patterns and discriminate high-risk coronary plaques. In conclusion, evidence supports a growing synergy between PCCT and radiomics, with applications already emerging in both lung and cardiac imaging. By enhancing the reproducibility and richness of quantitative features, PCCT may significantly broaden the clinical potential of radiomics in computed tomography. Full article

Occupational health monitoring in demolition environments requires precise detection of blast-dust-induced pulmonary pathologies. However, it is often hindered by challenges such as contaminated imaging biomarkers, limited access to medical resources in mining areas, and opaque AI-based diagnostic models. This study presents a novel computational framework that combines industrial-grade robustness with clinical interpretability for the diagnosis of pulmonary nodules. We propose a hybrid framework that integrates morphological purification techniques (multi-step filling and convex hull operations) with multi-dimensional features fusion (radiomics + lightweight deep features). To enhance computational efficiency and interpretability, we design a soft voting ensemble classifier, eliminating the need for complex deep learning architectures. On the LIDC-IDRI dataset, our model achieved an AUC of 0.99 and an accuracy of 0.97 using standard clinical-grade hardware, outperforming state-of-the-art (SOTA) methods while requiring fewer computational resources. Ablation studies, feature weight maps, and normalized mutual information heatmaps confirm the robustness and interpretability of the model, while uncertainty quantification metrics such as the Brier score and Expected Calibration Error (ECE) better validate the model’s clinical applicability and prediction stability. This approach effectively achieves resource-accuracy co-optimization, maintaining low computational costs, and is highly suitable for resource-constrained clinical environments. The modular design of our framework also facilitates extensions to other medical imaging domains without the need for high-end infrastructure. Full article

Desmoid tumors are rare, locally invasive soft-tissue tumors with unpredictable clinical behavior. Imaging plays a crucial role in their diagnosis, measurement of disease burden, and assessment of treatment response. However, desmoid tumors’ unique imaging features present challenges to conventional imaging metrics. The heterogeneous nature of these tumors, with a variable composition (fibrous, myxoid, or cellular), complicates accurate delineation of tumor boundaries and volumetric assessment. Furthermore, desmoid tumors can demonstrate prolonged stability or spontaneous regression, and biologic quiescence is often manifested by collagenization rather than bulk size reduction, making traditional size-based response criteria, such as Response Evaluation Criteria in Solid Tumors (RECIST), suboptimal. To overcome these limitations, advanced imaging techniques offer promising opportunities. Functional and parametric imaging methods, such as diffusion-weighted MRI, dynamic contrast-enhanced MRI, and T2 relaxometry, can provide insights into tumor cellularity and maturation. Radiomics and artificial intelligence approaches may enhance quantitative analysis by extracting and correlating complex imaging features with biological behavior. Moreover, imaging biomarkers could facilitate earlier detection of treatment efficacy or resistance, enabling tailored therapy. By integrating advanced imaging into clinical practice, it may be possible to refine the evaluation of disease burden and treatment response, ultimately improving the management and outcomes of patients with desmoid tumors. Full article

Radiomic feature (RF) analysis of computed tomography (CT) images may aid the diagnosis and staging of ovine pulmonary adenocarcinoma (OPA). We assessed the RF characteristics of OPA tumours in JSRV-infected sheep compared to non-tumour lung tissues, examined their stability over time, and analysed RF variations in the nascent tumour field (NTF) and nascent tumour margin field (NTmF). In monthly CT scans, lung tissues were automatically segmented by density, and lung tumours were manually segmented. RFs were calculated for each imaging session, selected according to stability and reproducibility, and adjusted for volume dependence where appropriate. Comparisons between scans within sheep were facilitated through fiducial registration and spatial transformations. Initially, 9/36 RFs differed significantly from non-tumour lung tissue of similar density. Predominant RF changes included ngtdm_Complexity, glrlm_RunLNUnif_VN, and gldm_SmDHGLE. RFs in lung tumour segments showed time-dependent changes, whereas non-tumour lung tissue of similar density remained consistent. OPA lung tumour RF characteristics are distinct from those of other lung tissues of similar density and evolve as the tumour develops. Such characteristics suggest that radiomic analysis offers potential for the early detection and management of JSRV-related lung tumours. This research enhances the understanding of OPA imaging, potentially informing better diagnosis and control measures for naturally occurring infections. Full article

Background: This study aims to investigate stability and reproducibility of radiomics biomarkers for adrenal lesion characterization across different software packages. Methods: Unenhanced CT images from patients with adrenal tumors were analyzed. Radiomic features were extracted using SOPHIA Radiomics and SIBEX software. The datasets underwent Z-score normalization. Statistical comparisons were made using two-sample t-tests and Spearman correlation coefficients. Three classification models—Logistic Regression, Linear Discriminant Analysis, and Linear Support Vector Machine—were trained on the datasets. Model performance was evaluated using accuracy, precision, recall, F1 score, and ROC curves. Feature importance and the statistical significance of model performance differences were also analyzed. Results: The t-test results showed no significant differences in the radiomic features extracted by SOPHIA and SIBEX (p-values all equal to 1.0). Spearman correlation coefficients were high for most features, suggesting a strong similarity between the two software tools. Classification models generally performed better on the SOPHIA dataset, with higher accuracy and precision. Feature importance analysis identified “Quadratic mean” and “Strength” as consistently influential features. Paired t-tests indicated significant differences in accuracy and precision, while Wilcoxon signed-rank tests did not find significant differences across all performance metrics. Conclusions: Radiomic features extracted by SOPHIA and SIBEX are comparable, but slight variations in model performance highlight the need for standardized extraction protocols and fine-tuning of predictive features. The study underscores the importance of ensuring the stability and reproducibility of radiomics features for reliable clinical application in adrenal lesion characterization. Full article

Background/Objectives: Glioblastoma (GBM) is an aggressive and lethal primary brain tumor with a poor prognosis, with a 5-year survival rate of approximately 5%. Despite advances in oncologic treatments, including surgery, radiotherapy, and chemotherapy, survival outcomes have remained stagnant, largely due to the failure of conventional therapies to address the tumor’s inherent heterogeneity. Radiomics, a rapidly emerging field, provides an opportunity to extract features from MRI scans, offering new insights into tumor biology and treatment response. This study evaluates the potential of delta radiomics, the study of changes in radiomic features over time in response to treatment or disease progression, exploring the potential of delta radiomics to track temporal radiation changes in tumor morphology and microstructure. Methods: A cohort of 50 female CD1 nude mice was injected intracranially with G7 glioblastoma cells and divided into irradiated (IR) and non-irradiated (non-IR) groups. MRI scans were performed at baseline (week 11) and post-radiation (weeks 12 and 14), and radiomic features, including shape, histogram, and texture parameters, were extracted and analyzed to capture radiation-induced changes. The most robust features were those identified through intra-observer reproducibility assessment, ensuring reliability in feature selection. A machine learning model was developed to classify irradiated tumors based on delta radiomic features, and statistical analyses were conducted to evaluate feature feasibility, stability, and predictive performance. Results: Our findings demonstrate that delta radiomics effectively captured significant temporal variations in tumor characteristics. Delta radiomics features exhibited distinct patterns across different time points in the IR group, enabling machine learning models to achieve a high accuracy. Conclusions: Delta radiomics offers a robust, non-invasive method for monitoring the treatment of glioblastoma (GBM) following radiation therapy. Future research should prioritize the application of MRI delta radiomics to effectively capture short-term changes resulting from intratumoral radiation effects. This advancement has the potential to significantly enhance treatment monitoring and facilitate the development of personalized therapeutic strategies. Full article