Radiomic Features Research Articles

Impact of Harmonization on MRI Radiomics Feature Variability Across Preprocessing Methods for Parkinson's Disease Motor Subtype Classification.

This study aimed to assess the reproducibility of MRI-derived radiomic features across multiple preprocessing methods for classifying Parkinson's disease (PD) motor subtypes and to evaluate the impact of ComBat harmonization on feature stability and machine learning performance. T1-weighted MRI scans from 140 PD patients (70 tremor-dominant and 70 postural instability gait difficulty) and 70 healthy controls were obtained from the Parkinson's Progression Markers Initiative (PPMI) database, acquired using different scanner models. Radiomic features were extracted from 16 brain regions using various preprocessing pipelines. ComBat harmonization was applied using a combined batch variable incorporating both scanner models and preprocessing methods. Intraclass correlation coefficients (ICC) and Kruskal-Wallis tests assessed feature reproducibility before and after harmonization. Feature selection was performed using Linear Support Vector Classifier with L1 regularization. Support vector machine classifiers were used for PD subtype classification. ComBat harmonization significantly improved feature reproducibility across all feature groups. The percentage of features showing excellent robustness (ICC ≥ 0.90) increased from 40.2 to 56.3% after harmonization. First-order statistic features showed the highest robustness, with 71.11% demonstrating excellent ICC after harmonization. The proportion of features significantly affected by preprocessing methods was reduced following harmonization. Classification accuracy improved dramatically, from a range of 34-75% before harmonization to 89-96% after harmonization across all preprocessing methods. AUC values similarly increased from 0.28-0.87 to 0.95-0.99 after harmonization. ComBat harmonization significantly enhanced the reproducibility of radiomic features across preprocessing methods and improved PD motor subtype classification performance. This study highlights the importance of harmonization in radiomics research for PD and suggests potential clinical applications in personalized treatment planning.

NIMG-75. SIMILARITY DISTANCES-BASED DELTA RADIOMICS (SDDR) ENABLES LONGITUDINAL MRI COMPARISONS FOR SURVIVAL PREDICTION IN GLIOMAS: A MULTI-INSTITUTIONAL VALIDATION

Abstract Radiomics (computerized feature analysis) on treatment-naive MRI scans has demonstrated great value in outcome prediction for Glioblastoma (GBM). However, delta radiomics (analysis of radiomic feature variation between different events, e.g., before and after treatment) has not been explored on account of challenges with precise spatial correspondences between pre- and post-operative scans. This work presents a survival prediction model for GBM, Similarity Distances-based delta radiomics (SDDR), based on the hypothesis that similarity distance-measures between radiomic features on pre-, and post-treatment images can accurately capture temporal changes within-and-around the tumor, and provide improved prediction of overall survival, compared to models based on a single timepoint. 150 patients from 2 publicly-available Glioma repositories (University of California San Francisco “UCSF” (n=48), LUMIERE (n=67)) and 2 two proprietary datasets (from xCures (n=13), and Cleveland Clinic (CCF) (n=74)) were obtained. UCSF and LUMIERE cohorts were used as separate hold-out sets, in each of which the remaining collections were used as discovery set. Following pre-processing, tumor segmentation into Edema (ED) and Enhancing tumor (ET) were performed. SDDR was then computed, which is the distance between probability densities functions from 156 gray co-occurrence (GLCM) and 52 gradient-based co-occurrences statistics (COLLAGE) features extracted from pre and-post-treatment MRI. Six statistical distances (e.g., Earth mover distance) normalized by the scanning interval (in weeks) yielded n=2496 SDDR measurements per tumor region (1248/region, 936 delta-GLCM, and 312 delta-COLLAGE). The same set of features were computed from pretreatment MRI (Pre-R) for comparison. Features were fed to LASSO-Cox regression for survival analysis. SDDR for GLCM features extracted from ET outperformed Pre-R, and demonstrated significant differences between high and low risk groups for both hold out tests: UCSF (p=0.0069, HR =2.8, C-index=0.69) and LUMIERE (p=0.0061, HR = 1.9, C-index 0.65). SDDR-based multi-institutional survival analysis demonstrated promise in reliable longitudinal risk-stratification in GBM.

NIMG-71. T2 RELAXIVITY AND DIFFUSION TENSOR METRICS IN THE PREDICTION OF PROGRESSION-FREE SURVIVAL IN NON-RECURRENT HIGH GRADE GLIOMA

Abstract High grade glioma (HGG) is the most common primary brain tumour; we aimed to evaluate T2 relaxivity and diffusion tensor imaging (DTI) metrics in the prediction of progression-free survival. Seventy-two non-recurrent HGG subjects (IDH: MUT=10, Unknown=20) followed at our institution after surgery and combined chemo-radiotherapy were included. All data used were prior to progression as per RANO criteria; only the first 2 years of follow up was included in the analyses. T2 relaxation rates (1/T2) were calculated voxel-wise assuming mono-exponential decay. Diffusion data were corrected from two opposite phase encode acquisitions and DTI metrics evaluated included FA, MD, p, q, and L1. Whole- and half-brain (ipsilateral/contralateral) masks were generated by brain extraction and registration; data extracted from these masks were analyzed using python 3.8 with the exception of numerous histogram features extracted using fsl tools. Radiomics features were also extracted using the pyradiomics package. The lofo-importance package was used for feature selection. A multi-level approach was used to reduce the initial 32,000 MRI features to a final number of 443; from these, the 50 highest-ranked features were used further. Within-subject feature engineering was then performed including 1–4 step forward and backward lag, lag difference, as well as area, maximum, mean and cumulative sum. Non-MRI features included available demographic, histological and treatment-related data. A LightGBM classification model was used for the prediction of progression within 90 days; the data were grouped by subject, such that each subject was present only in training or testing datasets. Hyperparameters were tuned using randomized search cross validation, and the final model using 5-fold cross validation reached a mean ROC-AUC of 0.89. Our results show the potential of quantitative MRI features derived from qualitatively unremarkable images within the progress-free interval to identify subjects at risk of imminent progression.

NIMG-01. RADIOMIC DATA ANALYSIS WITH ENSEMBLE MACHINE LEARNING TECHNIQUES PREDICT GRADE, HISTOPATHOLOGIC SUBTYPE, AND 1P/19Q CO-DELETION STATUS IN PATIENTS WITH LOW-GRADE GLIOMAS

Abstract Low-grade gliomas (LGGs) are a diverse group of primary brain tumors characterized by their variable prognosis and treatment response. Traditionally, the management of LGGs has relied on histopathological analysis, which sometimes offers limited insight into tumor behavior and treatment outcomes. Recent advances in radiomics have enabled the extraction of detailed quantitative features from routine imaging, providing a non-invasive method to assess tumor characteristics. These radiomic features can capture underlying tumor heterogeneity more comprehensively than conventional methods. Integrating radiomic data with ensemble machine learning techniques offers a promising approach to enhance the prediction of tumor grade, histopathologic subtype, and genetic alterations such as 1p/19q co-deletion status in LGGs, potentially leading to more tailored therapeutic strategies. We combined radiomic-genomic data from 159 magnetic resonance imaging (MRI) scans from the updated LGG-1p19qDeletion dataset (Erickson 2020) and 114 MRI scans from the ReMIND dataset (Juvekar 2024). Expert radiologists performed segmentations. A total of 2446 extracted radiomic features were initially extracted. Feature selection was performed using wrapper- and filter-based techniques with cross-validation. Prediction models were built using machine learning techniques, including random forest and extreme gradient boosting. Using Random Forest, we achieved high accuracy in predicting histopathologic subtype (88.14%, AUC 96.68%) with precision of 87.86% and Dice score of 87.88%. For grade prediction (accuracy 76.19%, AUC 91.84%), precision was 73.91%, and the Dice score was 77.27%. For 1p/19q co-deletion status (accuracy 75.61%, AUC 82.74%), precision was 77.78%, and the Dice score was 73.68%. Our study establishes a robust radiomic workflow to predict tumor grade, histopathologic subtype, and 1p/19q co-deletion status in low-grade gliomas, enhancing diagnostic accuracy and treatment personalization. This methodology can be applied clinically to improve the stratification of treatment plans for low-grade gliomas, potentially leading to effective, personalized therapy options. Using multicentric data potentially improved external validity, something which past research lacked. Future research should focus on validating and deploying this model using observational multicentric study designs.

Computed tomography radiomics reveals prognostic value of immunophenotyping in laryngeal squamous cell carcinoma: a comparison of whole tumor- versus habitats-based approaches.

To compare the performance of whole tumor and habitats-based computed tomography (CT) radiomics for predicting immunophenotyping in laryngeal squamous cell carcinomas (LSCC) and further evaluate the stratified effect of the radiomics model on disease-free survival (DFS) and overall survival (OS) of LSCC patients. In all, 106 LSCC patients (40 with inflamed and 66 with non-inflamed immunophenotyping) were randomly assigned into a training (n = 53) and testing (n = 53) cohort. Briefly, 750 radiomics features from contrast-enhanced CT images were respectively extracted from the whole tumor and two Otsu method-derived subregions. Intraclass correlation coefficients (ICCs) were calculated to evaluate the reproducibility. The radiomics models for predicting immunophenotyping were respectively created using K-nearest neighbors (KNN), logistic regression (LR), and Naive bayes (NB) classifiers. The performance of models in the testing cohort were compared using area under the curve (AUC). The prognostic value of the optimal model was determined by survival analysis. The radiomics features derived from whole tumor showed better reproducibility than those derived from habitats. The best model for the whole tumor (LR classifier) showed superior performance than that for the habitats (KNN classifier) in the testing cohort, but there were no significant differences (AUC: 0.741 vs. 0.611, p = 0.112). Multivariable Cox regression analysis showed that the immunophenotyping predicted by the optimal model was an independent risk factor of unfavorable DFS (p = 0.009) and OS (p = 0.008) in LSCC patients. Whole tumor-based CT radiomics could serve as a potential predictive biomarker of immunophenotyping and outcome prediction in LSCC patients.

NIMG-27. RADIOMETHYLOMICS FOR NON-INVASIVE PREDICTION OF TUMOR PHENOTYPES AND SURVIVAL IN GLIOBLASTOMA

Abstract BACKGROUND DNA methylation profiling has become a pivotal tool in neuro-oncology. However, little is known about the impact of methylation profiling on radiological imaging in IDH-wildtype glioblastoma (GBM). This study explored the potential of radiomics to non-invasively predict molecular characteristics based on the methylation profiling of GBM. METHODS This study included a multi-sampling cohort of 32 patients with 113 samples and a single-sampling cohort of 87 patients with 87 samples, which underwent genome-wide methylation analysis and were classified as GBM by the DKFZ/Heidelberg CNS tumor classifier. We performed two different methylation-based deconvolution analyses. Deconvolution 1 estimated the fractions of tumor subtypes (RTK_I, RTK_II, MES_TYP, and MES_ATYP) and cell types in the microenvironment. Deconvolution 2 inferred the abundance of malignant cell states (stem-like and differentiated cell components) and cell types in the microenvironment. We derived 6084 radiomic features from preoperative multi-parametric MRI in each patient. RESULTS In the multi-sampling cohort, Deconvolution 1 and Deconvolution 2 demonstrated that tumor subclass components and immune components exhibited heterogeneous distribution across samples within patients; however, the stem-like to differentiated cell ratio was preserved across samples within patients. In the entire cohort, patients with tumors exhibiting a high proportion of the stem-like component, defined as stem-like tumors, had significantly shorter overall survival. Stem-like tumors exhibited significantly higher levels of the RTK_I component and lower proportions of the RTK_II component compared to non-stem-like tumors. A machine learning model that utilizes support vector machines to classify stem-like tumors using radiomic features achieved a mean AUC of 0.71 (95% confidence interval: 0.56–0.85) in nested cross-validation. CONCLUSIONS We showed that radiomethylomics can be used to predict tumor composition and patient survival from preoperative MRI in GBM. Based on these promising results we will increase our power with additional samples to facilitate a personalized approach to GBM management.

INNV-02. BRAINMETS: A CLINICIAN-FRIENDLY SOFTWARE TO MANUALLY SEGMENT BRAIN METASTASES AND DETECT PRIMARY TUMOR ORIGIN USING DEEP LEARNING

Abstract Estimates suggest that around 20%-40% of cancer patients are affected by brain metastases. A subset of these patients first present with central nervous system manifestations with an unknown primary. The issue then arises regarding which region of the body should be imaged, if not the entire body, exposing the patient to more radiation. To address this issue, streamline workflows, and save precious time, we developed a software clinicians can use to identify primary tumor locus. “BrainMets” is a user-friendly software that handles a DICOM input, allows the user to segment the region(s) of interest manually, and uses a deep learning model to predict the most likely tumor origin. The model is a mixed-effects neural network pre-trained on radiomic features from open-source data by Ocaña-Tienda et al. (2023) using 637 high-resolution imaging studies from 10 different medical centers with an accuracy of 90.5%, precision of 92.7%, recall of 87.8%, and F1 score of 90.2%. The software leverages the open-source software 3D-Slicer to help segment regions of interest, extract radiomic features, and make predictions. It is built using Flask, a Python package for backend development. The frontend user interface is created using HTML/CSS and Bootstrap. The “BrainMets” software thus strives to enhance diagnostic workflow significantly, reduce appointment times for scans, and improve patient experience. Future enhancements include integrating more AI models, improving healthcare IT system compatibility, and updating datasets to boost predictive accuracy and generalizability. This tool sets a new standard in personalized medicine, optimizing treatment strategies for cancer patients with brain metastases. As adoption increases, it could substantially improve patient outcomes and reduce healthcare costs associated with misdiagnosis and overtreatment. Further research and development will focus on expanding its applicability across various types of cancers.

CTIM-33. IMMUNE BIOMARKERS OF TREATMENT RELATED IMAGING CHANGES IN GLIOBLASTOMA PATIENTS TREATED WITH STANDARD OF CARE PLUS PEMBROLIZUMAB

Abstract Pseudoprogression is a post-treatment imaging phenomenon in glioblastoma (GBM) that mimics true progression. Immune checkpoint inhibition with pembrolizumab has shown clinical benefits in multiple cancers and is a burgeoning treatment in GBM. Discerning pseudoprogression, or treatment-related imaging changes, from true progression is essential for appropriate treatment recommendations. However, there are no reliable biomarkers that can differentiate between pseudoprogression and true progression. Our prospective single-arm study (NCT 03347617) evaluated immune cell sub-populations (B-cells, T-cells, NK cells, monocytes, and myeloid cells) in newly diagnosed GBM patients who received standard-of-care chemoradiation plus concurrent pembrolizumab after maximal safe resection. Flow cytometry was performed on blood collected at predetermined timepoints (pre-treatment, post-radiation, suspected progression, and confirmed progression) and immune cell sub-populations were evaluated as covariates in univariable and multivariable logistic regression analysis. Of the 56 patients enrolled in this trial, 51 completed blood collection. Median survival was 13.84 months. Fifteen (29%) patients had pseudoprogression by modified RANO criteria and 36 (70.5%) had suspected or confirmed progression. Univariable analysis identified the following serum derived immune populations as being significantly associated with pseudoprogression: cytotoxic T-cell percentage (CD3+CD8+; HR: 1.10; p=0.045); total NK Cells percentage (CD3+CD56+; HR:0.912; p=0.0.053); IGD+CD27-naïve B-cells of B-cell percentage (HR: 0.976; p=0.014); IGD+CD27+non-switched B of B-cell percentage (HR:1.07; p=0.036). Backward selection multivariable logistic regression analysis confirmed the significant association of cytotoxic T-cell percentage (CD3+CD8+; HR:1.02; p=0.049) with pseudoprogression while controlling for IGD+CD27+non-switched B of B-cell percentage (HR:1.01, p=0.116). Increasing levels of serum cytotoxic T-cells in GBM patients treated with standard-of-care plus pembrolizumab is associated with pseudoprogression and may be used to differentiate between true progression. Validation of results is needed in a control population treated with standard-of-care prior to clinical implementation. Future studies will utilize serum immune biomarkers coupled with radiomic features to better characterize the pseudoprogression signature in GBM.

NIMG-60. SUBTYPING GLIOBLASTOMA FROM JOINT CLUSTERING OF IMAGING AND GENOMIC DATA

Abstract PURPOSE To comprehensively unravel the heterogeneity of glioblastoma, we developed a subtyping method using integrated imaging and genomic data. METHODS We assembled a retrospective cohort of 571 IDH-wildtype glioblastoma patients, obtaining pre-operative multi-parametric MRI (T1, T1-GD, T2, T2-FLAIR, DSC, DTI) scans (available for 462 patients) and targeted next-generation sequencing (NGS) data (available for 355 patients). We extracted 971 radiomic features from these MRI scans, selecting 12 significant dimensions through L21-norm minimization guided by 13 key driver genes from the five most frequently altered pathways in glioblastoma compared to healthy controls (RB1, P53, MAPK, PI3K, and RTK). Subtypes were identified using a joint clustering approach that integrated radiomics and genomics. RESULTS Our method identified three glioblastoma subtypes with distinct risk levels: high-risk (subtype 1), medium-risk (subtype 2), and low-risk (subtype 3), each characterized by their differential overall survival outcomes (Kaplan-Meier analysis, p < 0.05). The intensities of axial diffusivity in enhancing tumor regions and radial diffusivity in non-enhancing cores increased across three subtypes. All subtypes shared a common tendency for more frequent mutation co-occurrence pattern in [TP53,RB1] but exhibited unique molecular characteristics. For example, subtype 1 displayed a relatively high frequency of co-occurring mutations in [TP53,KDR] and [NOTCH2,MDM4]; subtype 2 had six co-occurring pairs [TP53,KDR], [PTPN11,NF1], [RB1,FUBP1], [PTEN,CIC], [PTEN,KRAS], and [NOTCH2,CDKN2A]; subtype 3 showed six co-occurring pairs [PTPN11,NF1], [PDGFRA,NF1], [NTRK1,NOTCH2], [MET,ATRX], [KRAS,KDR], and [FGFR2,DNMT3A] plus four significant patterns of mutual exclusivity in [TP53,PTPN11], [TP53,EGFR], [EGFR,RB1], and [EGFR,NF1]. CONCLUSION Our study discovered distinct glioblastoma subtypes, revealing complex patterns and structures across multiple data modalities without relying on prior clinical assumptions. This is promising to help enhance the precision of diagnosis and treatment of glioblastoma.

Advancing ischemic stroke diagnosis and clinical outcome prediction using improved ensemble techniques in DSC-PWI radiomics.

Ischemic stroke is a leading global cause of death and disability and is expected to rise in the future. The present diagnostic techniques, like CT and MRI, have some limitations in distinguishing acute from chronic ischemia and in early ischemia detection. This study investigates the function of ensemble models based on the dynamic radiomics features (DRF) from the dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) ischemic stroke diagnosis, neurological impairment assessment, and modified Rankin Scale (mRS) outcome prediction). DRF is extracted from the 3D images, features are selected, and dimensionality is reduced. After that, ensemble models are applied. Two model structures were developed: a voting classifier with 6 bagging classifiers and a stacking classifier based on 4 bagging classifiers. The ensemble models were evaluated on three core tasks. The Stacking_ens_LR model performed best for ischemic stroke detection, the LR Bagging model for NIH Stroke Scale (NIHSS) prediction, and the NB Bagging model for outcome prediction. These outcomes illustrate the strength of ensemble models. The work showcases the role of ensemble models and DRF in the stroke management process.

Glioma subtype prediction based on radiomics of tumor and peritumoral edema under automatic segmentation

Comprehensive and non-invasive preoperative molecular diagnosis is important for prognostic and therapy decision-making in adult-type diffuse gliomas. We employed a deep learning method for automatic segmentation of brain gliomas directly from conventional magnetic resonance imaging (MRI) scans of the tumor core and peritumoral edema regions based on available glioma MRI data provided in the BraTS2021. Three-dimensional volumes of interest were segmented from 424 cases of glioma imaging data retrospectively obtained from two medical centers using the segmentation method and radiomic features were extracted. We developed a subtype prediction model based on extracted radiomic features and analyzed significance and correlations between glioma morphological characteristics and pathological features using data from patients with adult-type diffuse glioma. The automated segmentation achieved mean Dice scores of 0.884 and 0.889 for the tumor core and whole tumor, respectively. The area under the receiver operating characteristic curve for the prediction of adult-type diffuse gliomas subtypes was 0.945. “Glioblastoma, IDH-wildtype”, “Astrocytoma, IDH-mutant”, and “Oligodendroglioma, IDH-mutant, 1p/19q-coded” showed AUCs of 0.96, 0.914, and 0.961, respectively, for subtype prediction. Glioma morphological characteristics, molecular and pathological levels, and clinical data showed significant differences and correlations. An automatic segmentation model for gliomas based on 3D U-Nets was developed, and the prediction model for gliomas built using the parameters obtained from the automatic segmentation model showed high overall performance.

Unveiling Tim-3 immune checkpoint expression in hepatocellular carcinoma through abdominal contrast-enhanced CT habitat radiomics

IntroductionImmune checkpoint inhibitors (ICIs) are important systemic therapeutic agents for hepatocellular carcinoma (HCC), among which T-cell immunoglobulin and mucin-domain containing protein 3 (Tim-3) is considered an emerging target for ICI therapy. This study aims to evaluate the prognostic value of Tim-3 expression and develop a predictive model for Tim-3 infiltration in HCC.MethodsWe collected data from 424 HCC patients in The Cancer Genome Atlas (TCGA) and data from 102 pathologically confirmed HCC patients from our center for prognostic analysis. Multivariate Cox regression analyses were performed on both datasets to determine the prognostic significance of Tim-3 expression. In radiomics analysis, we used the K-means algorithm to cluster regions of interest in arterial phase enhancement and venous phase enhancement images from patients at our center. Radiomic features were extracted from three subregions as well as the entire tumor using pyradiomics. Five machine learning methods were employed to construct Habitat models based on habitat features and Rad models based on traditional radiomic features. The predictive performance of the models was compared using ROC curves, DCA curves, and calibration curves.ResultsMultivariate Cox analyses from both our center and the TCGA database indicated that high Tim-3 expression is an independent risk factor for poor prognosis in HCC patients. Higher levels of Tim-3 expression were significantly associated with worse prognosis. Among the ten models evaluated, the Habitat model constructed using the LightGBM algorithm showed the best performance in predicting Tim-3 expression status (training set vs. test set AUC 0.866 vs. 0.824).DiscussionThis study confirmed the importance of Tim-3 as a prognostic marker in HCC. The habitat radiomics model we developed effectively predicted intratumoral Tim-3 infiltration, providing valuable insights for the evaluation of ICI therapy in HCC patients.

A Machine Learning Model Based on Thyroid US Radiomics to Discriminate Between Benign and Malignant Nodules

Background/Objectives: Thyroid nodules are a very common finding, mostly benign but sometimes malignant, and thus require accurate diagnosis. Ultrasound and fine needle biopsy are the most widely used and reliable diagnostic methods to date, but they are sometimes limited in addressing benign from malignant nodules, mainly with regard to ultrasound, by the operator’s experience. Radiomics, quantitative feature extraction from medical images and machine learning offer promising avenues to improve diagnosis. The aim of this work was to develop a machine learning model based on thyroid ultrasound images to classify nodules into benign and malignant classes. Methods: For this purpose, images of ultrasonography from 142 subjects were collected. Among these subjects, 40 patients (28.2%) belonged to the class “malignant” and 102 patients (71.8%) belonged to the class “benign”, according to histological diagnosis from fine-needle aspiration. This image set was used for the training, cross-validation and internal testing of three different machine learning models. A robust radiomic approach was applied, under the hypothesis that the radiomic feature could capture the disease heterogeneity among the two groups. Three models consisting of four ensembles of machine learning classifiers (random forests, support vector machines and k-nearest neighbor classifiers) were developed for the binary classification task of interest. The best performing model was then externally tested on a cohort of 21 new patients. Results: The best model (ensemble of random forest) showed Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) (%) of 85 (majority vote), 83.7 ** (mean) [80.2–87.2], accuracy (%) of 83, 81.2 ** [77.1–85.2], sensitivity (%) of 70, 67.5 ** [64.3–70.7], specificity (%) of 88, 86.5 ** [82–91], positive predictive value (PPV) (%) of 70, 66.5 ** [57.9–75.1] and negative predictive value (NPV) (%) of 88, 87.1 ** [85.5–88.8] (* p < 0.05, ** p < 0.005) in the internal test cohort. It achieved an accuracy of 90.5%, a sensitivity of 100%, a specificity of 86.7%, a PPV of 75% and an NPV of 100% in the external testing cohort. Conclusions: The model constituted of four ensembles of random forest classifiers could identify all the malignant nodes and the consistent majority of benign in the external testing cohort.

Deep learning radiomics based on contrast enhanced MRI for preoperatively predicting early recurrence in hepatocellular carcinoma after curative resection

PurposeTo explore the role of deep learning (DL) and radiomics-based integrated approach based on contrast enhanced magnetic resonance imaging (CEMRI) for predicting early recurrence (ER) in hepatocellular carcinoma (HCC) patients after curative resection.MethodsTotal 165 HCC patients (ER, n = 96 vs. non-early recurrence (NER), n = 69) were retrospectively collected and divided into a training cohort (n = 132) and a validation cohort (n = 33). From pretreatment CEMR images, a total of 3111 radiomics features were extracted, and radiomics models were constructed using five machine learning classifiers (logistic regression, support vector machine, k-nearest neighbor, extreme gradient Boosting, and multilayer perceptron). DL models were established via three variations of ResNet architecture. The clinical-radiological (CR), radiomics combined with clinical-radiological (RCR), and deep learning combined with RCR (DLRCR) models were constructed. Model discrimination, calibration, and clinical utilities were evaluated by receiver operating characteristic curve, calibration curve, and decision curve analysis, respectively. The best-performing model was compared with the widely used staging systems and preoperative prognostic indexes.ResultsThe RCR model (area under the curve (AUC): 0.841 and 0.811) and the optimal radiomics model (AUC: 0.839 and 0.804) achieved better performance than the CR model (AUC: 0.662 and 0.752) in the training and validation cohorts, respectively. The optimal DL model (AUC: 0.870 and 0.826) outperformed the radiomics model in the both cohorts. The DL, radiomics, and CR predictors (aspartate aminotransferase (AST) and tumor diameter) were combined to construct the DLRCR model. The DLRCR model presented the best performance over any model, yielding an AUC, an accuracy, a sensitivity, a specificity of 0.917, 0.886, 0.889, and 0.882 in the training cohort and of 0.844, 0.818, 0.800, and 0.846 in the validation cohort, respectively. The DLRCR model achieved better clinical utility compared to the clinical staging systems and prognostic indexes.ConclusionBoth radiomics and DL models derived from CEMRI can predict HCC recurrence, and DL and radiomics-based integrated approach can provide a more effective tool for the precise prediction of ER for HCC patients undergoing resection.

PET/CT radiomics and deep learning in the diagnosis of benign and malignant pulmonary nodules: progress and challenges

Lung cancer is currently the leading cause of cancer-related deaths, and early diagnosis and screening can significantly reduce its mortality rate. Since some early-stage lung cancers lack obvious clinical symptoms and only present as pulmonary nodules (PNs) in imaging examinations, accurately determining the benign or malignant nature of PNs is crucial for improving patient survival rates. 18F-FDG PET/CT is important in diagnosing PNs, but its specificity needs improvement. Radiomics can provide information beyond traditional visual assessment, overcoming its limitations by extracting high-throughput quantitative features from medical images. Radiomics features based on 18F-FDG PET/CT and deep learning methods have shown great potential in the noninvasive diagnosis of PNs. This paper reviews the latest advancements in these methods and discusses their contributions to improving diagnostic accuracy and the challenges they face.

Perirenal Fat CT Radiomics-Based Survival Model for Upper Tract Urothelial Carcinoma: Integrating Texture Features with Clinical Predictors

Background: Upper tract urothelial carcinoma (UTUC) presents significant challenges in prognostication due to its rarity and complex anatomy. This study introduces a novel approach integrating perirenal fat (PRF) radiomics with clinical factors to enhance prognostic accuracy in UTUC. Methods: The study retrospectively analyzed 103 UTUC patients who underwent radical nephroureterectomy. PRF radiomics features were extracted from preoperative CT scans using a semi-automated segmentation method. Three prognostic models were developed: clinical, radiomics, and combined. Model performance was assessed using concordance index (C-index), time-dependent Area Under the Curve (AUC), and integrated Brier score. Results: The combined model demonstrated superior performance (C-index: 0.784, 95% CI: 0.707–0.861) compared to the radiomics (0.759, 95% CI: 0.678–0.840) and clinical (0.653, 95% CI: 0.547–0.759) models. Time-dependent AUC analysis revealed the radiomics model’s particular strength in short-term prognosis (12-month AUC: 0.9281), while the combined model excelled in long-term predictions (60-month AUC: 0.8403). Key PRF radiomics features showed stronger prognostic value than traditional clinical factors. Conclusions: Integration of PRF radiomics with clinical data significantly improves prognostic accuracy in UTUC. This approach offers a more nuanced analysis of the tumor microenvironment, potentially capturing early signs of tumor invasion not visible through conventional imaging. The semi-automated PRF segmentation method presents advantages in reproducibility and ease of use, facilitating potential clinical implementation.

Machine Learning Models Based on [18F]FDG PET Radiomics for Bone Marrow Assessment in Non-Hodgkin Lymphoma

Non-Hodgkin lymphoma is a heterogeneous group of cancers that triggers bone marrow infiltration in 20–40% of cases. Bone marrow biopsy in combination with a visual assessment of [18F]FDG PET/CT images is used to assess the marrow status. Despite the potential of both techniques, they still have limitations due to the subjectivity of visual assessment. The present study aims to develop models based on bone marrow uptake in [18F]FDG PET/CT images at the time of diagnosis to differentiate bone marrow status. For this purpose, a model trained for skeleton segmentation and based on the U-Net architecture is retrained for bone marrow segmentation from CT images. The mask obtained from this segmentation together with the [18F]FDG PET image is used to extract radiomics features with which 11 machine learning models for marrow status differentiation are trained. The segmentation model yields very satisfactory results with Jaccard and Dice index values of 0.933 and 0.964, respectively. As for the classification models, a maximum F1_score_weighted and F1_score_macro of 0.962 and 0.747, respectively, are achieved. This highlights the potential of these features for bone marrow assessment, laying the foundation for a new clinical decision support system.

International Metabolic Prognostic Index Is Superior to Other Metabolic Tumor Volume-Based Prognostication Methods in a Real-Life Cohort of Diffuse Large B-Cell Lymphoma.

Baseline metabolic tumor volume (MTV) is a promising prognostic marker in diffuse large B-cell lymphoma (DLBCL). We assessed the prognostic value of 4 novel metabolic risk scores in a real-life DLBCL cohort and compared them with the revised international prognostic index (IPI). Methods: We included a consecutive series of untreated DLBCL, not otherwise specified cases that were diagnosed in our hospital from 2008 to 2021 with available baseline [18F]FDG PET/CT. Clinical data were collected retrospectively, including the individual components of the revised IPI. MTV and other radiomic features, including lesion dissemination and tumor volume surface ratio, were calculated. Four novel metabolic risk scores including the international metabolic prognostic index (IMPI), the MTV/World Health Organization performance status, the MTV/standardized maximum distance, and clinical PET models were used to calculate the risk of progression using predefined cutoffs. Survival outcomes considered were 3-y progression free survival (PFS), 3-y time to progression (TTP), and 3-y overall survival (OS). The Harrell C-index was used to assess the discriminative performance of the risk scores. A multivariable model was built. Results: We included 355 DLBCL, not otherwise specified cases with a median MTV of 219 cm3 (range, 0-5,656 cm3). The IMPI had the highest C-index for 3-y PFS, 3-y TTP, and 3-y OS among the 4 metabolic risk scores (0.674, 0.696, and 0.677, respectively). For the 3-y TTP, the IMPI outperformed the strongest clinical risk score, the IPI, although the difference in the Harrell C-indices was small (0.696 vs. 0.693). Regarding the 3-y PFS and 3-y OS, the IPI has the highest C-index of all risk scores (0.696 and 0.693). The IMPI, the MTV/World Health Organization performance status, and the IPI score can recognize a poor risk group with a 3-y OS below 50% (43%, 32%, and 39%, respectively). In multivariable analysis, the IMPI remains an independent prognostic factor (P = 0.0089; hazard ratio, 1.207; 95% CI, 1.048-1.389). MTV and standardized maximum distance have the strongest prognostic values when used as a continuous variable. The tumor volume surface ratio has no significant prognostic value in our analysis. Conclusion: The IMPI has the strongest prognostic performance compared with the other 3 novel metabolic risk scores. However, in our real-world dataset, the IMPI could not replace the IPI, and further prospective trials are needed to compare their performance.

Radiomics Features from Positron Emission Tomography with [18F] Fluorodeoxyglucose Can Help Predict Cervical Nodal Status in Patients with Head and Neck Cancer

Radiomics Features from Positron Emission Tomography with [18F] Fluorodeoxyglucose Can Help Predict Cervical Nodal Status in Patients with Head and Neck Cancer

Radiomics Feature Stability in True and Virtual Non-Contrast Reconstructions from Cardiac Photon-Counting Detector CT Datasets

Radiomics Feature Stability in True and Virtual Non-Contrast Reconstructions from Cardiac Photon-Counting Detector CT Datasets