Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures

Algorithmic approaches in hand imaging for rheumatic musculoskeletal diseases: A systematic literature review

OBJECTIVE

This systematic literature review provides a comprehensive overview of the use of machine learning (ML) in hand imaging of rheumatic musculoskeletal diseases (RMDs). The review evaluates ML algorithms, imaging modalities, patient populations, validation methods, and areas for improvement.

METHODS

The review was conducted following PRISMA guidelines and registered with PROSPERO. Articles were retrieved from PubMed, EMBASE, and Scopus using relevant MeSH terms and keywords. The search, executed in October 2024, was conducted manually and with BiBot, an AI-based tool for literature reviews. Studies focusing on ML applications in osteoarthritis (OA), rheumatoid arthritis (RA), and psoriatic arthritis (PsA) were included.

RESULTS

From 400 initially identified studies, 32 met the inclusion criteria. RA was the most studied disease (88 %), followed by OA (22 %) and PsA (9 %). Convolutional neural networks (CNNs) were the most frequently used algorithms (50 %). Standard radiographs (59 %) were the predominant imaging modality, followed by MRI (16 %). Despite recommendations for ML studies, external validation was conducted in only 15 % of studies, and just 6 % of datasets were publicly available. Interpretability tools were employed in 28 % of studies to enhance clinical relevance.

CONCLUSION

ML has significant potential to improve diagnostics and disease management in hand imaging of RMDs. However, key challenges remain, including the need for increased external validation, broader disease coverage (OA and PsA), and improved data-sharing practices to enhance reproducibility and clinical adoption.

Comparative analysis of machine learning models for predicting pathological complete response to neoadjuvant chemotherapy in breast cancer: An MRI radiomics approach

PURPOSE

The aim of this work is to compare different machine learning models for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer using radiomics features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHOD

The study included 55 patients with breast cancer, among whom 18 achieved pCR and 37 did not respond completely to NAC (non-pCR). After some pre-processing steps, 1446 features were extracted and corrected for batch effects using ComBat. Five machine learning algorithms, namely random forest (RF), decision tree (DT), logistic regression (LR), k-nearest neighbors (k-NN), and extreme gradient boosting (XGB), were evaluated using area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score as classification metrics. A Leave-Group-Out cross validation (LGOCV) was applied in the outer loop.

RESULTS

RF and DT models exhibited the highest performances compared to the other algorithms. DT achieved an accuracy of 0.96 ± 0.07, and RF achieved 0.95 ± 0.05. The AUC values for RF and DT were 0.98 ± 0.06 and 0.94 ± 0.07, respectively. LR and k-NN demonstrated lower performance across all metrics, while XGB showed competitive results but slightly lower than RF and DT.

CONCLUSIONS

This study demonstrates the potential of radiomics and machine learning for predicting pCR to NAC in breast cancer. RF and DT models proved to be the most effective in capturing underlying patterns in radiomics data. Further research is required to validate and strengthen the proposed approach and explore its applicability in diverse radiomics datasets and clinical scenarios.

Application of radiomics features in differential diagnosis of odontogenic cysts

OBJECTIVES

Cysts in jaws may have similar radiographic features. However, it is important to clarify the diagnosis prior to surgery. The aim of this study was to compare the radiomic features of radicular cysts (RCs), dentigerous cysts (DCs), and odontogenic keratocysts (OKCs) as a non-invasive diagnostic alternative to biopsy.

METHODS

In total, 161 odontogenic cysts diagnosed histopathologically (55 RCs, 53 DCs, and 53 OKCs) were included in the present study. Each cyst was semi-automatically segmented on CBCT images, and radiomic features were extracted by an observer. A second observer repeated 20% of the evaluations and the radiomic features. Those achieving an inter-observer agreement level above 0.850 were included in the study. Consequently, five shape-based and 22 textural features were investigated in the study. Statistical analysis was performed comparing both three cyst features and making pairwise comparisons.

RESULTS

All features included in the study showed statistical differences between cysts, with the exception of one textural feature (NGTDM coarseness) (P < .05). However, only one shape-based feature (shericity) and one textural feature (GLSZM large area emphasis) were statistically different in pairwise comparisons of all three cysts (P < .05).

CONCLUSION

Radiomics features of the RCs, DCs, and OKCs showed significant differences, and may have the potential to be used as a non-invasive method in the differential diagnosis of cysts.

Hybrid deep learning for computational precision in cardiac MRI segmentation: Integrating Autoencoders, CNNs, and RNNs for enhanced structural analysis

Recent advancements in cardiac imaging have been significantly enhanced by integrating deep learning models, offering transformative potential in early diagnosis and patient care. The research paper explores the application of hybrid deep learning methodologies, focusing on the roles of Autoencoders, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) in enhancing cardiac image analysis. The study implements a comprehensive approach, combining traditional algorithms such as Sobel, Watershed, and Otsu's Thresholding with advanced deep learning models to achieve precise and accurate imaging outcomes. The Autoencoder model, developed for image enhancement and feature extraction, achieved a notable accuracy of 99.66% on the test data. Optimized for image recognition tasks, the CNN model demonstrated a high precision rate of 98.9%. The RNN model, utilized for sequential data analysis, showed a prediction accuracy of 98%, further underscoring the robustness of the hybrid framework. The research drew upon a diverse range of academic databases and pertinent publications within cardiac imaging and deep learning, focusing on peer-reviewed articles and studies published in the past five years. Models were implemented using the TensorFlow and Keras frameworks. The proposed methodology was evaluated in the clinical validation phase using advanced imaging protocols, including the QuickScan technique and balanced steady-state free precession (bSSFP) imaging. The validation metrics were promising: the Signal-to-Noise Ratio (SNR) was improved by 15%, the Contrast-to-Noise Ratio (CNR) saw an enhancement of 12%, and the ejection fraction (EF) analysis provided a 95% correlation with manually segmented data. These metrics confirm the efficacy of the models, showing significant improvements in image quality and diagnostic accuracy. The integration of adversarial defense strategies, such as adversarial training and model ensembling, have been analyzed to enhance model robustness against malicious inputs. The reliability and comparison of the model's ability have been investigated to maintain clinical integrity, even in adversarial attacks that could otherwise compromise segmentation outcomes. These findings indicate that integrating Autoencoders, CNNs, and RNNs within a hybrid deep-learning framework is promising for enhancing cardiac MRI segmentation and early diagnosis. The study contributes to the field by demonstrating the applicability of these advanced techniques in clinical settings, paving the way for improved patient outcomes through more accurate and timely diagnoses.

Breast density prediction model in digital versus synthetic mammograms from a radiomic point of view: A retrospective study

PURPOSE

In this retrospective study, we develop radiomics prediction models from synthetic mammograms(SM) and digital mammograms(DM) images to identify which imaging modality has the most predictive power when employed for prediction of breast density.

METHODS

Patients aged between 45 and 74 years, were included in the study. For each, a SM in standard resolution (ST) and High Resolution (HR) were obtained, and a 150 x 150 pixels square area was defined on the images to be used for texture analysis of the breast parenchyma. A semi-automated placing strategy was used to reduce user reliance on the segmentation location. S-IBEX software was employed to extract radiomics features. Feature robustness analysis was also done to ensure model reproducibility. The Least Absolute Shrinkage and Selection Operator(LASSO) logistic regression model was trained to predict dichotomized breast density according to BIRADS classification model performance was assessed through receiver operating curves (ROC) for DM, HR, and ST.

RESULTS

We extracted 123 features from the 10 ROIs of 96 patient. After robustness analysis, the most predictive features were employed to build logistic regression-based models. The average performance of the models were 0.74, 0.67, and 0.64 on DM, HR, and ST, respectively, suggesting that DM maintains the highest informative content on breast density.

CONCLUSIONS

This study investigated how well radiomics models trained on various imaging modalities predicted breast density. Our results may be pertinent to the debate over screening mammography technique optimization using quantitative measures based on radiomics features.

Extracting full information from OCT scans-signs of early age-related macular degeneration within inner retinal layers by local neighbourhood statistics. Part I: Methodology

BACKGROUND AND OBJECTIVES

Associations between the occurrence of early age-related macular degeneration (AMD) and alterations in retinal layer thicknesses have been reported based on classical processing of optical coherence tomography (OCT) data by noise removal and subsequent image segmentation. However, speckle noise within OCT data itself bears a substantial part of the total information. For this reason, an omics-type approach was designed for full exploitation of OCT data, which was able to identify signs of early AMD throughout the retina as a whole.

METHODS

A nested case-control study was designed with 200 early AMD cases and 200 healthy controls. For every participant, within a randomly selected OCT scan and a randomly selected column therein, manual grading was performed for 26 retinal feature positions. At each position, a total of 3792 descriptors were computed, based on nonlinear transformations of OCT data, first-order neighbourhood statistics and Haralick features. Equivalence and differences between cases and controls were tested for every descriptor at each graded position. Results of multiple testing were expressed in terms of false and true discovery rates controlled by the Benjamini-Yekutieli procedure.

RESULTS

In terms of the amount and disparity of true discoveries, overall non-equivalence of early AMD and healthy groups was found. Strong difference signals were observed at the internal limiting membrane and two central retinal positions, particularly for descriptors emphasising speckle noise.

CONCLUSIONS

Between retinae of healthy controls and early AMD patients, significant differences were observed at the level of local neighbourhood statistics within the OCT data. Thus, independent evidence was obtained for AMD affecting not only the outer retinal layers but also the retina as a whole, even in the early stages of the disease. Within OCT data, both cartoons and speckle bear essential parts of total information. A constructive, completely documented, traceable and repeatable approach was pursued without invoking artificial intelligence methods.

Investigating the Effects of Reconstruction Conditions on Image Quality and Radiomic Analysis in Photon-counting Computed Tomography

Introduction

Photon-counting computed tomography (CT) is equipped with an adaptive iterative reconstruction method called quantum iterative reconstruction (QIR), which allows the intensity to be changed during image reconstruction. It is known that the reconstruction conditions of CT images affect the analysis results when performing radiomic analysis. The aim of this study is to investigate the effect of QIR intensity on image quality and radiomic analysis of renal cell carcinoma (RCC).

Materials and Methods

The QIR intensities were selected as off, 2 and 4. The image quality evaluation items considered were task-based transfer function (TTF), noise power spectrum (NPS), and low-contrast object specific contrast-to-noise ratio (CNRLO). The influence on radiomic analysis was assessed using the discrimination accuracy of clear cell RCC.

Results

For image quality evaluation, TTF and NPS values were lower and CNRLO values were higher with increasing QIR intensity; for radiomic analysis, sensitivity, specificity, and accuracy were higher with increasing QIR intensity. Principal component analysis and receiver operating characteristics analysis also showed higher values with increasing QIR intensity.

Conclusion

It was confirmed that the intensity of the QIR intensity affects both the image quality and the radiomic analysis.

Extracting full information from OCT scans-signs of early age-related macular degeneration within inner retinal layers by local neighbourhood statistics. Part II: Results

BACKGROUND AND OBJECTIVES

Associations between the occurrence of early age related macular degeneration (AMD) and alterations in retinal layer thicknesses have been reported, based on classical processing of optical coherence tomography (OCT) data by noise removal and subsequent image segmentation. However, speckle noise within OCT data itself bears a substantial part of the total information. For this reason, we designed an omics-type approach for full exploitation of OCT data, which was able to identify signs of early AMD throughout the retina as a whole.

METHODS

A nested case-control study was designed with 200 early AMD cases and 200 healthy controls. For each participant, within a randomly selected OCT scan and a randomly selected column therein, manual grading was performed for 26 retinal feature positions. At every position, a total of 3792 descriptors were computed, based on nonlinear transformations of OCT data, first-order neighbourhood statistics and Haralick features. Equivalence and differences between cases and controls were tested for each descriptor at every graded position. Results of multiple testing were expressed in terms of false and true discovery rates controlled by the Benjamini-Yekutieli procedure.

RESULTS

In terms of the amount and disparity of true discoveries, overall non-equivalence was found for early AMD and healthy groups. Strong difference signals were observed at the internal limiting membrane and two central retinal positions, particularly for descriptors emphasising speckle noise.

CONCLUSIONS

Between the retinae of healthy controls and early AMD patients, significant differences were observed at the level of local neighbourhood statistics within OCT data. Thus, independent evidence was obtained for AMD affecting not only the outer retinal layers but the retina as a whole, even in the early stages of the disease. Within OCT data, both cartoon and speckle bear essential parts of the total information. We pursued a constructive, completely documented, traceable and repeatable approach without invoking artificial intelligence methods.

Mitigating Interobserver Variability in Radiomics with ComBat: A Feasibility Study

This study investigates Intraobserver Features Variability (IFV) in radiomics studies and assesses the effectiveness of the ComBat harmonization method in mitigating these effects. Methods: This study utilizes data from the NSCLC-Radiomics-Interobserver1 dataset, comprising CT scans of 22 Non-Small Cell Lung Cancer (NSCLC) patients, with multiple Gross Tumor Volume (GTV) delineations performed by five radiation oncologists. Segmentation was completed manually ("vis") or by autosegmentation with manual editing ("auto"). A total of 1229 radiomic features were extracted from each GTV, segmentation method, and oncologist. Features extracted included first order, shape, GLCM, GLRLM, GLSZM, and GLDM from original, wavelet-filtered, and LoG-filtered images. Results: Before implementing ComBat harmonization, 83% of features exhibited p-values below 0.05 in the "vis" approach; this percentage decreased to 34% post-harmonization. Similarly, for the "auto" approach, 75% of features demonstrated statistical significance prior to ComBat, but this figure declined to 33% after its application. Among a subset of three expert radiation oncologists, percentages changed from 77% to 25% for "vis" contouring and from 64% to 23% for "auto" contouring. This study demonstrates that ComBat harmonization could effectively reduce IFV, enhancing the feasibility of multicenter radiomics studies. It also highlights the significant impact of physician experience on radiomics analysis outcomes.

Radiomics Analysis for Clinical Decision Support in 177Lu-DOTATATE Therapy of Metastatic Neuroendocrine Tumors using CT Images

Background

Radiomics is the computation of quantitative image features extracted from medical imaging modalities to help clinical decision support systems, which could ultimately meliorate personalized management based on individual characteristics.

Objective

This study aimed to create a predictive model of response to peptide receptor radionuclide therapy (PRRT) using radiomics computed tomography (CT) images to decrease the dose for patients if they are not a candidate for treatment.

Material and Methods

In the current retrospective study, 34 patients with neuroendocrine tumors whose disease is clinically confirmed participated. Effective factors in the treatment were selected by eXtreme gradient boosting (XGBoost) and minimum redundancy maximum relevance (mRMR). Classifiers of decision trees (DT), random forest (RF), and K-nearest neighbors (KNN) with selected quantitative and clinical features were used for modeling. A confusion matrix was used to evaluate the performance of the model.

Results

Out of 866 quantitative and clinical features, nine features with the XGBoost method and ten features with the mRMR pattern were selected that had the most relevance in predicting response to treatment. Selected features of the XGBoost method in integration with the RF classifier provided the highest accuracy (accuracy: 89%), and features selected by the mRMR method in combination with the RF classifier showed satisfactory performance (accuracy: 74%).

Conclusion

This exploratory analysis shows that radiomic features with high accuracy can effectively predict response to personalize treatment.

Radiomics Signatures Based on Computed Tomography for Noninvasive Prediction of CXCL10 Expression and Prognosis in Ovarian Cancer

BACKGROUND

Ovarian cancer (OC) is an aggressive gynecological tumor usually diagnosed with malignant ascites and even observed widespread metastasis or distant spread.

AIMS

We aimed to develop and identify radiomics models according to computed tomography (CT) for preoperative prediction of CXCL10 expression and prognosis in patients with OC.

METHODS

Genomic data with CT images and corresponding clinicopathological parameters were extracted from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). To analyze the prognosis, we carried out the univariate Cox regression analysis (UCRA), multivariate Cox regression analysis (MCRA), and Kaplan-Meier (KM) analysis. For the data reduction, logistic regression, operator regression, least absolute shrinkage selection, radiomic feature construction, and feature selection were utilized. The predictive performance of the radiomic signatures was assessed using the analyses of the receiver operating characteristic (ROC) curve, decision curve (DCA), and precision-recall (PR) curve. To evaluate the correlation between the radiomic score (Rad-score) and CXCL10 expression, the Wilcoxon rank-sum test was applied.

RESULTS

Three radiomics models effectively predicted CXCL10 expression levels (AUC = 0.791, 0.748, and 0.718 for the set of training; AUC = 0.761, 0.746, and 0.701 for the set of validation). A higher Rad-score significantly correlated with upregulated CXCL10 expression.

CONCLUSION

CXCL10 expression can be predicted noninvasively and preoperatively via radiomic signatures based on contrast-enhanced CT images.

Prediction of prognosis in glioblastoma with radiomics features extracted by synthetic MRI images using cycle-consistent GAN

To propose a style transfer model for multi-contrast magnetic resonance imaging (MRI) images with a cycle-consistent generative adversarial network (CycleGAN) and evaluate the image quality and prognosis prediction performance for glioblastoma (GBM) patients from the extracted radiomics features. Style transfer models of T1 weighted MRI image (T1w) to T2 weighted MRI image (T2w) and T2w to T1w with CycleGAN were constructed using the BraTS dataset. The style transfer model was validated with the Cancer Genome Atlas Glioblastoma Multiforme (TCGA-GBM) dataset. Moreover, imaging features were extracted from real and synthesized images. These features were transformed to rad-scores by the least absolute shrinkage and selection operator (LASSO)-Cox regression. The prognosis performance was estimated by the Kaplan-Meier method. For the accuracy of the image quality of the real and synthesized MRI images, the MI, RMSE, PSNR, and SSIM were 0.991 ± 2.10 × 10 - 4 , 2.79 ± 0.16, 40.16 ± 0.38, and 0.995 ± 2.11 × 10 - 4 , for T2w, and .992 ± 2.63 × 10 - 4 , 2.49 ± 6.89 × 10 - 2 , 40.51 ± 0.22, and 0.993 ± 3.40 × 10 - 4 for T1w, respectively. The survival time had a significant difference between good and poor prognosis groups for both real and synthesized T2w (p < 0.05). However, the survival time had no significant difference between good and poor prognosis groups for both real and synthesized T1w. On the other hand, there was no significant difference between the real and synthesized T2w in both good and poor prognoses. The results of T1w were similar in the point that there was no significant difference between the real and synthesized T1w. It was found that the synthesized image could be used for prognosis prediction. The proposed prognostic model using CycleGAN could reduce the cost and time of image scanning, leading to a promotion to build the patient's outcome prediction with multi-contrast images.

Differential diagnostic value of radiomics models in benign versus malignant vertebral compression fractures: A systematic review and meta-analysis

PURPOSE

Early diagnosis of benign and malignant vertebral compression fractures by analyzing imaging data is crucial to guide treatment and assess prognosis, and the development of radiomics made it an alternative option to biopsy examination. This systematic review and meta-analysis was conducted with the purpose of quantifying the diagnostic efficacy of radiomics models in distinguishing between benign and malignant vertebral compression fractures.

METHODS

Searching on PubMed, Embase, Web of Science and Cochrane Library was conducted to identify eligible studies published before September 23, 2023. After evaluating for methodological quality and risk of bias using the Radiomics Quality Score (RQS) and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), we selected studies providing confusion matrix results to be included in random-effects meta-analysis.

RESULTS

A total of sixteen articles, involving 1,519 vertebrae with pathological-diagnosed tumor infiltration, were included in our meta-analysis. The combined sensitivity and specificity of the top-performing models were 0.92 (95 % CI: 0.87-0.96) and 0.93 (95 % CI: 0.88-0.96), respectively. Their AUC was 0.97 (95 % CI: 0.96-0.99). By contrast, radiologists' combined sensitivity was 0.90 (95 %CI: 0.75-0.97) and specificity was 0.92 (95 %CI: 0.67-0.98). The AUC was 0.96 (95 %CI: 0.94-0.97). Subsequent subgroup analysis and sensitivity test suggested that part of the heterogeneity might be explained by differences in imaging modality, segmentation, deep learning and cross-validation.

CONCLUSION

We found remarkable diagnosis potential in correctly distinguishing vertebral compression fractures in complex clinical contexts. However, the published radiomics models still have a great heterogeneity, and more large-scale clinical trials are essential to validate their generalizability.

Artificial Intelligence-Driven Radiomics in Head and Neck Cancer: Current Status and Future Prospects

BACKGROUND

Radiomics is a rapidly growing field used to leverage medical radiological images by extracting quantitative features. These are supposed to characterize a patient's phenotype, and when combined with artificial intelligence techniques, to improve the accuracy of diagnostic models and clinical outcome prediction.

OBJECTIVES

This review aims at examining the application areas of artificial intelligence-based radiomics (AI-based radiomics) for the management of head and neck cancer (HNC). It further explores the workflow of AI-based radiomics for personalized and precision oncology in HNC. Finally, it examines the current challenges of AI-based radiomics in daily clinical oncology and offers possible solutions to these challenges.

METHODS

Comprehensive electronic databases (PubMed, Medline via Ovid, Scopus, Web of Science, CINAHL, and Cochrane Library) were searched following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. The quality of included studies and their risk of biases were evaluated using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD)and Prediction Model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Out of the 659 search hits retrieved, 45 fulfilled the inclusion criteria. Our review revealed that the application of AI-based radiomics model as an ancillary tool for improved decision-making in HNC management includes radiomics-based cancer diagnosis and radiomics-based cancer prognosis. The radiomics-based cancer diagnosis includes tumor staging, tumor grading, and classification of malignant and benign tumors. Similarly, radiomics-based cancer prognosis includes prediction for treatment response, recurrence, metastasis, and survival. In addition, the challenges in the implementation of these models for clinical evaluations include data imbalance, feature engineering (extraction and selection), model generalizability, multi-modal fusion, and model interpretability.

CONCLUSION

Considering the highly subjective and interobserver variability that is peculiar to the interpretation of medical images by expert clinicians, AI-based radiomics seeks to offer potentially useful quantitative information, which is not visible to the human eye or unintentionally often remain ignored during clinical imaging practice. By enabling the extraction of this type of information, AI-based radiomics has the potential to revolutionize HNC oncology, providing a platform for more personalized, higher quality, and cost-effective care for HNC patients.

BTK Expression Level Prediction and the High-Grade Glioma Prognosis Using Radiomic Machine Learning Models

We aimed to study whether the Bruton's tyrosine kinase (BTK) expression is correlated with the prognosis of patients with high-grade gliomas (HGGs) and predict its expression level prior to surgery, by constructing radiomic models. Clinical and gene expression data of 310 patients from The Cancer Genome Atlas (TCGA) were included for gene-based prognostic analysis. Among them, contrast-enhanced T1-weighted imaging (T1WI + C) from The Cancer Imaging Archive (TCIA) with genomic data was selected from 82 patients for radiomic models, including support vector machine (SVM) and logistic regression (LR) models. Furthermore, the nomogram incorporating radiomic signatures was constructed to evaluate its clinical efficacy. BTK was identified as an independent risk factor for HGGs through univariate and multivariate Cox regression analyses. Three radiomic features were selected to construct the SVM and LR models, and the validation set showed area under curve (AUCs) values of 0.711 (95% CI, 0.598-0.824) and 0.736 (95% CI, 0.627-0.844), respectively. The median survival times of the high Rad_score and low-Rad_score groups based on LR model were 15.53 and 23.03 months, respectively. In addition, the total risk score of each patient was used to construct a predictive nomogram, and the AUCs calculated from the corresponding time-dependent ROC curves were 0.533, 0.659, and 0.767 for 1, 3, and 5 years, respectively. BTK is an independent risk factor associated with poor prognosis in patients, and the radiomic model constructed in this study can effectively and non-invasively predict preoperative BTK expression levels and patient prognosis based on T1WI + C.

Significance of MRI-based radiomics in predicting pathological complete response to neoadjuvant chemoradiotherapy of locally advanced rectal cancer: A narrative review

Neoadjuvant chemoradiotherapy is the standard treatment for patients with locally advanced rectal cancers owing to its ability to downstage primary tumours. Some patients can achieve pathological complete response after neoadjuvant therapy, and can adopt a "watch and wait" treatment strategy to avoid overtreatment. Therefore, it is essential to develop strategies for predicting responses to neoadjuvant therapy. Radiomics has shown great potential in extracting tumour features from high-throughput medical images for the construction of mathematics models for predicting the effects of anticancerous therapies. Herein, we explored MRI-based radiomics and found that it can predict responses of locally advanced rectal cancers to chemoradiation. Efficient radiomics model allow early-stage prediction of the effect of neoadjuvant chemoradiotherapy on locally advanced rectal cancers. It helps clinicians to make informed therapeutic decisions. In this review, we discuss the workflow of radiomics, and summarize the clinical application of MRI-based radiomics in predicting pathological complete response to neoadjuvant chemoradiotherapy of locally advanced rectal cancer.

Machine learning prediction model for gray-level co-occurrence matrix features of synchronous liver metastasis in colorectal cancer

BACKGROUND

Synchronous liver metastasis (SLM) is a significant contributor to morbidity in colorectal cancer (CRC). There are no effective predictive device integration algorithms to predict adverse SLM events during the diagnosis of CRC.

AIM

To explore the risk factors for SLM in CRC and construct a visual prediction model based on gray-level co-occurrence matrix (GLCM) features collected from magnetic resonance imaging (MRI).

METHODS

Our study retrospectively enrolled 392 patients with CRC from Yichang Central People's Hospital from January 2015 to May 2023. Patients were randomly divided into a training and validation group (3:7). The clinical parameters and GLCM features extracted from MRI were included as candidate variables. The prediction model was constructed using a generalized linear regression model, random forest model (RFM), and artificial neural network model. Receiver operating characteristic curves and decision curves were used to evaluate the prediction model.

RESULTS

Among the 392 patients, 48 had SLM (12.24%). We obtained fourteen GLCM imaging data for variable screening of SLM prediction models. Inverse difference, mean sum, sum entropy, sum variance, sum of squares, energy, and difference variance were listed as candidate variables, and the prediction efficiency (area under the curve) of the subsequent RFM in the training set and internal validation set was 0.917 [95% confidence interval (95%CI): 0.866-0.968] and 0.09 (95%CI: 0.858-0.960), respectively.

CONCLUSION

A predictive model combining GLCM image features with machine learning can predict SLM in CRC. This model can assist clinicians in making timely and personalized clinical decisions.

The relationship between contrast-enhanced computed tomography radiomics features and mitosis karyorrhexis index in neuroblastoma

OBJECTIVE

Mitosis karyorrhexis index (MKI) can reflect the proliferation status of neuroblastoma cells. This study aimed to investigate the contrast-enhanced computed tomography (CECT) radiomics features associated with the MKI status in neuroblastoma.

MATERIALS AND METHODS

246 neuroblastoma patients were retrospectively included and divided into three groups: low-MKI, intermediate-MKI, and high-MKI. They were randomly stratified into a training set and a testing set at a ratio of 8:2. Tumor regions of interest were delineated on arterial-phase CECT images, and radiomics features were extracted. After reducing the dimensionality of the radiomics features, a random forest algorithm was employed to establish a three-class classification model to predict MKI status.

RESULTS

The classification model consisted of 5 radiomics features. The mean area under the curve (AUC) of the classification model was 0.916 (95% confidence interval (CI) 0.913-0.921) in the training set and 0.858 (95% CI 0.841-0.864) in the testing set. Specifically, the classification model achieved AUCs of 0.928 (95% CI 0.927-0.934), 0.915 (95% CI 0.912-0.919), and 0.901 (95% CI 0.900-0.909) for predicting low-MKI, intermediate-MKI, and high-MKI, respectively, in the training set. In the testing set, the classification model achieved AUCs of 0.873 (95% CI 0.859-0.882), 0.860 (95% CI 0.852-0.872), and 0.820 (95% CI 0.813-0.839) for predicting low-MKI, intermediate-MKI, and high-MKI, respectively.

CONCLUSIONS

CECT radiomics features were found to be correlated with MKI status and are helpful for reflecting the proliferation status of neuroblastoma cells.

Imaging Genomics and Multiomics: A Guide for Beginners Starting Radiomics-Based Research

Radiomics uses advanced mathematical analysis of pixel-level information from radiologic images to extract existing information in traditional imaging algorithms. It is intended to find imaging biomarkers related to the genomics of tumors or disease patterns that improve medical care by advanced detection of tumor response patterns in tumors and to assess prognosis. Radiomics expands the paradigm of medical imaging to help with diagnosis, management of diseases and prognostication, leveraging image features by extracting information that can be used as imaging biomarkers to predict prognosis and response to treatment. Radiogenomics is an emerging area in radiomics that investigates the association between imaging characteristics and gene expression profiles. There are an increasing number of research publications using different radiomics approaches without a clear consensus on which method works best. We aim to describe the workflow of radiomics along with a guide of what to expect when starting a radiomics-based research project.

Machine learning-based radiomic analysis and growth visualization for ablation site recurrence diagnosis in follow-up CT

OBJECTIVES

Detecting ablation site recurrence (ASR) after thermal ablation remains a challenge for radiologists due to the similarity between tumor recurrence and post-ablative changes. Radiomic analysis and machine learning methods may show additional value in addressing this challenge. The present study primarily sought to determine the efficacy of radiomic analysis in detecting ASR on follow-up computed tomography (CT) scans. The second aim was to develop a visualization tool capable of emphasizing regions of ASR between follow-up scans in individual patients.

MATERIALS AND METHODS

Lasso regression and Extreme Gradient Boosting (XGBoost) classifiers were employed for modeling radiomic features extracted from regions of interest delineated by two radiologists. A leave-one-out test (LOOT) was utilized for performance evaluation. A visualization method, creating difference heatmaps (diff-maps) between two follow-up scans, was developed to emphasize regions of growth and thereby highlighting potential ASR.

RESULTS

A total of 55 patients, including 20 with and 35 without ASR, were included in the radiomic analysis. The best performing model was achieved by Lasso regression tested with the LOOT approach, reaching an area under the curve (AUC) of 0.97 and an accuracy of 92.73%. The XGBoost classifier demonstrated better performance when trained with all extracted radiomic features than without feature selection, achieving an AUC of 0.93 and an accuracy of 89.09%. The diff-maps correctly highlighted post-ablative liver tumor recurrence in all patients.

CONCLUSIONS

Machine learning-based radiomic analysis and growth visualization proved effective in detecting ablation site recurrence on follow-up CT scans.

Computed tomography radiomic feature analysis of thymic epithelial tumors: Differentiation of thymic epithelial tumors from thymic cysts and prediction of histological subtypes

PURPOSE

To investigate the value of computed tomography (CT) radiomic feature analysis for the differential diagnosis between thymic epithelial tumors (TETs) and thymic cysts, and prediction of histological subtypes of TETs.

MATERIALS AND METHODS

Twenty-four patients with TETs (13 low-risk and 9 high-risk thymomas, and 2 thymic carcinomas) and 12 with thymic cysts were included in this study. For each lesion, the radiomic features of a volume of interest covering the lesion were extracted from non-contrast enhanced CT images. The Least Absolute Shrinkage and Selection Operator (Lasso) method was used for the feature selection. Predictive models for differentiating TETs from thymic cysts (model A), and high risk thymomas + thymic carcinomas from low risk thymomas (model B) were created from the selected features. The receiver operating characteristic curve was used to evaluate the effectiveness of radiomic feature analysis for differentiating among these tumors.

RESULTS

In model A, the selected 5 radiomic features for the model A were NGLDM_Contrast, GLCM_Correlation, GLZLM_SZLGE, DISCRETIZED_HISTO_Entropy_log2, and DISCRETIZED_HUmin. In model B, sphericity was the only selected feature. The area under the curve, sensitivity, and specificity of radiomic feature analysis were 1 (95% confidence interval [CI]: 1-1), 100%, and 100%, respectively, for differentiating TETs from thymic cysts (model A), and 0.76 (95%CI: 0.53-0.99), 64%, and 100% respectively, for differentiating high-risk thymomas + thymic carcinomas from low-risk thymomas (model B).

CONCLUSION

CT radiomic analysis could be utilized as a non-invasive imaging technique for differentiating TETs from thymic cysts, and high-risk thymomas + thymic carcinomas from low-risk thymomas.

A comparison of machine learning methods for radiomics modeling in prediction of occult lymph node metastasis in clinical stage IA lung adenocarcinoma patients

Background

Accurate prediction of occult lymph node metastasis (ONM) is an important basis for determining whether lymph node (LN) dissection is necessary in clinical stage IA lung adenocarcinoma patients. The aim of this study is to determine the best machine learning algorithm for radiomics modeling and to compare the performances of the radiomics model, the clinical-radilogical model and the combined model incorporate both radiomics features and clinical-radilogical features in preoperatively predicting ONM in clinical stage IA lung adenocarcinoma patients.

Methods

Patients with clinical stage IA lung adenocarcinoma undergoing curative surgery from one institution were retrospectively recruited and assigned to training and test cohorts. Radiomics features were extracted from the preoperative computed tomography (CT) images of the primary tumor. Seven machine learning algorithms were used to construct radiomics models, and the model with the best performance, evaluated using the area under the curve (AUC), was selected. Univariate and multivariate logistic regression analyses were performed on the clinical-radiological features to identify statistically significant features and to develop a clinical model. The optimal radiomics and clinical models were integrated to build a combined model, and its predictive performance was assessed using receiver operating characteristic curves, Brier score, and decision curve analysis (DCA).

Results

This study included 258 patients who underwent resection (training cohort, n=182; test cohort, n=76). Six radiomics features were identified. Among the seven machine learning algorithms, extreme gradient boosting (XGB) demonstrated the highest performance for radiomics modeling, with an AUC of 0.917. The combined model improved the AUC to 0.933 and achieved a Brier score of 0.092. DCA revealed that the combined model had optimal clinical efficacy.

Conclusions

The superior performance of the combined model, based on XGB algorithm in predicting ONM in patients with clinical stage IA lung adenocarcinoma, might aid surgeons in deciding whether to conduct mediastinal LN dissection and contribute to improve patients' prognosis.

Machine learning-based radiomics to distinguish pulmonary nodules between lung adenocarcinoma and tuberculosis

BACKGROUND

Radiomics is increasingly utilized to distinguish pulmonary nodules between lung adenocarcinoma (LUAD) and tuberculosis (TB). However, it remains unclear whether different segmentation criteria, such as the inclusion or exclusion of the cavity region within nodules, affect the results.

METHODS

A total of 525 patients from two medical centers were retrospectively enrolled. The radiomics features were extracted according to two regions of interest (ROI) segmentation criteria. Multiple logistic regression models were trained to predict the pathology: (1) The clinical model relied on clinical-radiological semantic features; (2) The radiomics models (radiomics+ and radiomics-) utilized radiomics features from different ROIs (including or excluding cavities); (3) the composite models (composite+ and composite-) incorporated both above.

RESULTS

In the testing set, the radiomics+/- models and the composite+/- models still possessed efficient prediction performance (AUC ≥ 0.94), while the AUC of the clinical model was 0.881. In the validation set, the AUC of the clinical model was only 0.717, while that of the radiomics+/- models and the composite+/- models ranged from 0.801 to 0.825. The prediction performance of all the radiomics+/- and composite+/- models were significantly superior to that of the clinical model (p < 0.05). Whether the ROI segmentation included or excluded the cavity had no significant effect on these models (radiomics+ vs. radiomics-, composite+ model vs. composite-) (p > 0.05).

CONCLUSIONS

The present study established a machine learning-based radiomics strategy for differentiating LUAD from TB lesions. The ROI segmentation including or excluding the cavity region may exert no significant effect on the predictive ability.

Research on automatic recognition radiomics algorithm for early sacroiliac arthritis based on sacroiliac MRI imaging

OBJECTIVE

To create an automated machine learning model using sacroiliac joint MRI imaging for early sacroiliac arthritis detection, aiming to enhance diagnostic accuracy.

METHODS

We conducted a retrospective analysis involving 71 patients with early sacroiliac arthritis and 85 patients with normal sacroiliac joint MRI scans. Transverse T1WI and T2WI sequences were collected and subjected to radiomics analysis by two physicians. Patients were randomly divided into training and test groups at a 7:3 ratio. Initially, we extracted the region of interest on the sacroiliac joint surface using ITK-SNAP 3.6.0 software and extracted radiomic features. We retained features with an Intraclass Correlation Coefficient > 0.80, followed by filtering using max-relevance and min-redundancy (mRMR) and LASSO algorithms to establish an automatic identification model for sacroiliac joint surface injury. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC) was calculated. Model performance was assessed by accuracy, sensitivity, and specificity.

RESULTS

We evaluated model performance, achieving an AUC of 0.943 for the SVM-T1WI training group, with accuracy, sensitivity, and specificity values of 0.878, 0.836, and 0.943, respectively. The SVM-T1WI test group exhibited an AUC of 0.875, with corresponding accuracy, sensitivity, and specificity values of 0.909, 0.929, and 0.875, respectively. For the SVM-T2WI training group, the AUC was 0.975, with accuracy, sensitivity, and specificity values of 0.933, 0.889, and 0.750. The SVM-T2WI test group produced an AUC of 0.902, with accuracy, sensitivity, and specificity values of 0.864, 0.889, and 0.800. In the SVM-bimodal training group, we achieved an AUC of 0.974, with accuracy, sensitivity, and specificity values of 0.921, 0.889, and 0.971, respectively. The SVM-bimodal test group exhibited an AUC of 0.964, with accuracy, sensitivity, and specificity values of 0.955, 1.000, and 0.875, respectively.

CONCLUSION

The radiomics-based detection model demonstrates excellent automatic identification performance for early sacroiliitis.

Research status and progress of radiomics in bone and soft tissue tumors: A review

Bone and soft tissue tumors are diverse, accompanying by complex histological components and significantly divergent biological behaviors. It is a challenge to address the demand for qualitative imaging as traditional imaging is restricted to the detection of anatomical structures and aberrant signals. With the improvement of digitalization in hospitals and medical centers, the introduction of electronic medical records and easier access to large amounts of information coupled with the improved computational power, traditional medicine has evolved into the combination of human brain, minimal data, and artificial intelligence. Scholars are committed to mining deeper levels of imaging data, and radiomics is worthy of promotion. Radiomics extracts subvisual quantitative features, analyzes them based on medical images, and quantifies tumor heterogeneity by outlining the region of interest and modeling. Two observers separately examined PubMed, Web of Science and CNKI to find existing studies, case reports, and clinical guidelines about research status and progress of radiomics in bone and soft tissue tumors from January 2010 to February 2023. When evaluating the literature, factors such as patient age, medical history, and severity of the condition will be considered. This narrative review summarizes the application and progress of radiomics in bone and soft tissue tumors.

A Radiomics Approach to Identify Immunologically Active Tumor in Patients with Head and Neck Squamous Cell Carcinomas

BACKGROUND

We recently developed a gene-expression-based HOT score to identify the hot/cold phenotype of head and neck squamous cell carcinomas (HNSCCs), which is associated with the response to immunotherapy. Our goal was to determine whether radiomic profiling from computed tomography (CT) scans can distinguish hot and cold HNSCC.

METHOD

We included 113 patients from The Cancer Genome Atlas (TCGA) and 20 patients from the Groupe Hospitalier Pitié-Salpêtrière (GHPS) with HNSCC, all with available pre-treatment CT scans. The hot/cold phenotype was computed for all patients using the HOT score. The IBEX software (version 4.11.9, accessed on 30 march 2020) was used to extract radiomic features from the delineated tumor region in both datasets, and the intraclass correlation coefficient (ICC) was computed to select robust features. Machine learning classifier models were trained and tested in the TCGA dataset and validated using the area under the receiver operator characteristic curve (AUC) in the GHPS cohort.

RESULTS

A total of 144 radiomic features with an ICC >0.9 was selected. An XGBoost model including these selected features showed the best performance prediction of the hot/cold phenotype with AUC = 0.86 in the GHPS validation dataset.

CONCLUSIONS AND RELEVANCE

We identified a relevant radiomic model to capture the overall hot/cold phenotype of HNSCC. This non-invasive approach could help with the identification of patients with HNSCC who may benefit from immunotherapy.

The Crying Need for a Better Response Assessment in Rectal Cancer

OPINION STATEMENT

Since total neoadjuvant treatment achieves almost 30% pathologic complete response, organ preservation has been increasingly debated for good responders after neoadjuvant treatment for patients diagnosed with rectal cancer. Two organ preservation strategies are available: a watch and wait strategy and a local excision strategy including patients with a near clinical complete response. A major issue is the selection of patients according to the initial tumor staging or the response assessment. Despite modern imaging improvement, identifying complete response remains challenging. A better selection could be possible by radiomics analyses, exploiting numerous image features to feed data characterization algorithms. The subsequent step is to include baseline and/or pre-therapeutic MRI, PET-CT, and CT radiomics added to the patients' clinicopathological data, inside machine learning (ML) prediction models, with predictive or prognostic purposes. These models could be further improved by the addition of new biomarkers such as circulating tumor biomarkers, molecular profiling, or pathological immune biomarkers.

An artificial intelligence-assisted diagnosis modeling software (AIMS) platform based on medical images and machine learning: a development and validation study

Background

Supervised machine learning methods [both radiomics and convolutional neural network (CNN)-based deep learning] are usually employed to develop artificial intelligence models with medical images for computer-assisted diagnosis and prognosis of diseases. A classical machine learning-based modeling workflow involves a series of interconnected components and various algorithms, but this makes it challenging, tedious, and labor intensive for radiologists and researchers to build customized models for specific clinical applications if they lack expertise in machine learning methods.

Methods

We developed a user-friendly artificial intelligence-assisted diagnosis modeling software (AIMS) platform, which supplies standardized machine learning-based modeling workflows for computer-assisted diagnosis and prognosis systems with medical images. In contrast to other existing software platforms, AIMS contains both radiomics and CNN-based deep learning workflows, making it an all-in-one software platform for machine learning-based medical image analysis. The modular design of AIMS allows users to build machine learning models easily, test models comprehensively, and fairly compare the performance of different models in a specific application. The graphical user interface (GUI) enables users to process large numbers of medical images without programming or script addition. Furthermore, AIMS also provides a flexible image processing toolkit (e.g., semiautomatic segmentation, registration, morphological operations) to rapidly create lesion labels for multiphase analysis, multiregion analysis of an individual tumor (e.g., tumor mass and peritumor), and multimodality analysis.

Results

The functionality and efficiency of AIMS were demonstrated in 3 independent experiments in radiation oncology, where multiphase, multiregion, and multimodality analyses were performed, respectively. For clear cell renal cell carcinoma (ccRCC) Fuhrman grading with multiphase analysis (sample size =187), the area under the curve (AUC) value of the AIMS was 0.776; for ccRCC Fuhrman grading with multiregion analysis (sample size =177), the AUC value of the AIMS was 0.848; for prostate cancer Gleason grading with multimodality analysis (sample size =206), the AUC value of the AIMS was 0.980.

Conclusions

AIMS provides a user-friendly infrastructure for radiologists and researchers, lowering the barrier to building customized machine learning-based computer-assisted diagnosis models for medical image analysis.

Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer

BACKGROUND

Numerous features are commonly generated in radiomics applications as applied to medical imaging, and identification of robust radiomics features (RFs) can be an important step to derivation of reliable, reproducible solutions. In this work, we utilize a tensor radiomics (TR) framework, where numerous fusions are explored, to generate different flavours of RFs, and we aimed to identify RFs that are robust to fusion techniques in head and neck cancer. Overall, we aimed to predict progression-free survival (PFS) using Hybrid Machine Learning Systems (HMLS) and reproducible RFs.

METHODS

The study was performed on 408 patients with head and neck cancer from The Cancer Imaging Archive. After image preprocessing, 15 fusion techniques were employed to combine Positron Emission Tomography (PET) and Computed Tomography (CT) images. Subsequently, 215 RFs were extracted through a standardized radiomics software, with 17 'flavours' generated using PET-only, CT-only, and 15 fused PET&CT images. The variability of RFs across flavours was studied using the Intraclass Correlation Coefficient (ICC). Furthermore, the features were categorized into seven reliability groups, 106 reproducible RFs with ICC>0.75 were selected, highly correlated flavours were removed, Principal Component Analysis was used to convert 17 flavours to 1 attribute, the polynomial function was utilized to increase RFs, and Analysis of variance (ANOVA) was used to select the relevant attributes. Finally, 3 classifiers including Random Forest (RFC), Logistic regression (LR), and Multi-layer perceptron were applied to the preselected relevant attributes to predict binary PFS. In 5-fold cross-validation, 80% of 4 divisions were utilized to train the model, and the remaining 20% was utilized to evaluate the model. Further, the remaining fold was used for external nested testing.

RESULTS

Reliability analysis indicated that most morphological features belong to the high-reliability category. By contrast, local intensity and statistical features extracted from images belong to the low-reliability category. In the tensor framework, the highest 5-fold cross-validation accuracy of 76.7%±3.3% with an external nested testing of 70.6%±6.7% resulted from the reproducible TR+polynomial function+ANOVA+LR algorithm while the accuracy of 70.0%±4.2% with the external nested testing of 67.7%±4.9% was achieved through the PCA fusion+RFC (non-tensor paradigm).

CONCLUSIONS

This study demonstrated that using reproducible RFs as utilized within a tensor fusion radiomics framework, linked with ANOVA and LR, added value to prediction of progression-free survival outcome in head and neck cancer patients.

Machine learning-based radiomics for predicting BRAF-V600E mutations in ameloblastoma

Background

Ameloblastoma is a locally invasive and aggressive epithelial odontogenic neoplasm. The BRAF-V600E gene mutation is a prevalent genetic alteration found in this tumor and is considered to have a crucial role in its pathogenesis. The objective of this study is to develop and validate a radiomics-based machine learning method for the identification of BRAF-V600E gene mutations in ameloblastoma patients.

Methods

In this retrospective study, data from 103 patients diagnosed with ameloblastoma who underwent BRAF-V600E mutation testing were collected. Of these patients, 72 were included in the training cohort, while 31 were included in the validation cohort. To address class imbalance, synthetic minority over-sampling technique (SMOTE) is applied in our study. Radiomics features were extracted from preprocessed CT images, and the most relevant features, including both radiomics and clinical data, were selected for analysis. Machine learning methods were utilized to construct models. The performance of these models in distinguishing between patients with and without BRAF-V600E gene mutations was evaluated using the receiver operating characteristic (ROC) curve.

Results

When the analysis was based on radiomics signature, Random Forest performed better than the others, with the area under the ROC curve (AUC) of 0.87 (95%CI, 0.68-1.00). The performance of XGBoost model is slightly lower than that of Random Forest, and its AUC is 0.83 (95% CI, 0.60-1.00). The nomogram evident that among younger women, the affected region primarily lies within the mandible, and patients with larger tumor diameters exhibit a heightened risk. Additionally, patients with higher radiomics signature scores are more susceptible to the BRAF-V600E gene mutations.

Conclusions

Our study presents a comprehensive radiomics-based machine learning model using five different methods to accurately detect BRAF-V600E gene mutations in patients diagnosed with ameloblastoma. The Random Forest model's high predictive performance, with AUC of 0.87, demonstrates its potential for facilitating a convenient and cost-effective way of identifying patients with the mutation without the need for invasive tumor sampling for molecular testing. This non-invasive approach has the potential to guide preoperative or postoperative drug treatment for affected individuals, thereby improving outcomes.

Distinct characteristics and severity of brain magnetic resonance imaging lesions in women and men with multiple sclerosis assessed using verified texture analysis measures

Background and goal

In vivo characterization of brain lesion types in multiple sclerosis (MS) has been an ongoing challenge. Based on verified texture analysis measures from clinical magnetic resonance imaging (MRI), this study aimed to develop a method to identify two extremes of brain MS lesions that were approximately severely demyelinated (sDEM) and highly remyelinated (hREM), and compare them in terms of common clinical variables.

Method

Texture analysis used an optimized gray-level co-occurrence matrix (GLCM) method based on FLAIR MRI from 200 relapsing-remitting MS participants. Two top-performing metrics were calculated: texture contrast and dissimilarity. Lesion identification applied a percentile approach according to texture values calculated: ≤ 25 percentile for hREM and ≥75 percentile for sDEM.

Results

The sDEM had a greater total normalized volume yet smaller average size, and worse MRI texture than hREM. In lesion distribution mapping, the two lesion types appeared to overlap largely in location and were present the most in the corpus callosum and periventricular regions. Further, in sDEM, the normalized volume was greater and in hREM, the average size was smaller in men than women. There were no other significant results in clinical variable-associated analyses.

Conclusion

Percentile statistics of competitive MRI texture measures may be a promising method for probing select types of brain MS lesion pathology. Associated findings can provide another useful dimension for improved measurement and monitoring of disease activity in MS. The different characteristics of sDEM and hREM between men and women likely adds new information to the literature, deserving further confirmation.

Promoting the application of pediatric radiomics via an integrated medical engineering approach

Radiomics is widely used in adult tumors but has been rarely applied to the field of pediatrics. Promoting the application of radiomics in pediatric diseases, especially in the early diagnosis and stratified treatment of tumors, is of great value to the realization of the WHO 2030 "Global Initiative for Childhood Cancer." This paper discusses the general characteristics of radiomics, the particularity of its application to pediatric diseases, and the current status and prospects of pediatric radiomics. Radiomics is a data-driven science, and the combination of medicine and engineering plays a decisive role in improving data quality, data diversity, and sample size. Compared with adult radiomics, pediatric radiomics is significantly different in data type, disease spectrum, disease staging, and progression. Some progress has been made in the identification, classification, stratification, survival prediction, and prognosis of tumor diseases. In the future, big data applications from multiple centers and cross-talent training should be strengthened to improve the benefits for clinical workers and children.

Within-Modality Synthesis and Novel Radiomic Evaluation of Brain MRI Scans

One of the most common challenges in brain MRI scans is to perform different MRI sequences depending on the type and properties of tissues. In this paper, we propose a generative method to translate T2-Weighted (T2W) Magnetic Resonance Imaging (MRI) volume from T2-weight-Fluid-attenuated-Inversion-Recovery (FLAIR) and vice versa using Generative Adversarial Networks (GAN). To evaluate the proposed method, we propose a novel evaluation schema for generative and synthetic approaches based on radiomic features. For the evaluation purpose, we consider 510 pair-slices from 102 patients to train two different GAN-based architectures Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet). The results indicate that generative methods can produce similar results to the original sequence without significant change in the radiometric feature. Therefore, such a method can assist clinics to make decisions based on the generated image when different sequences are not available or there is not enough time to re-perform the MRI scans.

Contrast-enhanced CT radiomics improves the prediction of abdominal aortic aneurysm progression

OBJECTIVES

To determine if three-dimensional (3D) radiomic features of contrast-enhanced CT (CECT) images improve prediction of rapid abdominal aortic aneurysm (AAA) growth.

METHODS

This longitudinal cohort study retrospectively analyzed 195 consecutive patients (mean age, 72.4 years ± 9.1) with a baseline CECT and a subsequent CT or MR at least 6 months later. 3D radiomic features were measured for 3 regions of the AAA, viz. the vessel lumen only; the intraluminal thrombus (ILT) and aortic wall only; and the entire AAA sac (lumen, ILT, and wall). Multiple machine learning (ML) models to predict rapid growth, defined as the upper tercile of observed growth (> 0.25 cm/year), were developed using data from 60% of the patients. Diagnostic accuracy was evaluated using the area under the receiver operating characteristic curve (AUC) in the remaining 40% of patients.

RESULTS

The median AAA maximum diameter was 3.9 cm (interquartile range [IQR], 3.3-4.4 cm) at baseline and 4.4 cm (IQR, 3.7-5.4 cm) at the mean follow-up time of 3.2 ± 2.4 years (range, 0.5-9 years). A logistic regression model using 7 radiomic features of the ILT and wall had the highest AUC (0.83; 95% confidence interval [CI], 0.73-0.88) in the development cohort. In the independent test cohort, this model had a statistically significantly higher AUC than a model including maximum diameter, AAA volume, and relevant clinical factors (AUC = 0.78, 95% CI, 0.67-0.87 vs AUC = 0.69, 95% CI, 0.57-0.79; p = 0.04).

CONCLUSION

A radiomics-based method focused on the ILT and wall improved prediction of rapid AAA growth from CECT imaging.

KEY POINTS

• Radiomic analysis of 195 abdominal CECT revealed that an ML-based model that included textural features of intraluminal thrombus (if present) and aortic wall improved prediction of rapid AAA progression compared to maximum diameter. • Predictive accuracy was higher when radiomic features were obtained from the thrombus and wall as opposed to the entire AAA sac (including lumen), or the lumen alone. • Logistic regression of selected radiomic features yielded similar accuracy to predict rapid AAA progression as random forests or support vector machines.

Multi-algorithms analysis for pre-treatment prediction of response to transarterial chemoembolization in hepatocellular carcinoma on multiphase MRI

OBJECTIVES

This study compared the accuracy of predicting transarterial chemoembolization (TACE) outcomes for hepatocellular carcinoma (HCC) patients in the four different classifiers, and comprehensive models were constructed to improve predictive performance.

METHODS

The subjects recruited for this study were HCC patients who had received TACE treatment from April 2016 to June 2021. All participants underwent enhanced MRI scans before and after intervention, and pertinent clinical information was collected. Registry data for the 144 patients were randomly assigned to training and test datasets. The robustness of the trained models was verified by another independent external validation set of 28 HCC patients. The following classifiers were employed in the radiomics experiment: machine learning classifiers k-nearest neighbor (KNN), support vector machine (SVM), the least absolute shrinkage and selection operator (Lasso), and deep learning classifier deep neural network (DNN).

RESULTS

DNN and Lasso models were comparable in the training set, while DNN performed better in the test set and the external validation set. The CD model (Clinical & DNN merged model) achieved an AUC of 0.974 (95% CI: 0.951-0.998) in the training set, superior to other models whose AUCs varied from 0.637 to 0.943 (p < 0.05). The CD model generalized well on the test set (AUC = 0.831) and external validation set (AUC = 0.735).

CONCLUSIONS

DNN model performs better than other classifiers in predicting TACE response. Integrating with clinically significant factors, the CD model may be valuable in pre-treatment counseling of HCC patients who may benefit the most from TACE intervention.

An Automated Method for Artifical Intelligence Assisted Diagnosis of Active Aortitis Using Radiomic Analysis of FDG PET-CT Images

The aim of this study was to develop and validate an automated pipeline that could assist the diagnosis of active aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images. The aorta was automatically segmented by convolutional neural network (CNN) on FDG PET-CT of aortitis and control patients. The FDG PET-CT dataset was split into training (43 aortitis:21 control), test (12 aortitis:5 control) and validation (24 aortitis:14 control) cohorts. Radiomic features (RF), including SUV metrics, were extracted from the segmented data and harmonized. Three radiomic fingerprints were constructed: A-RFs with high diagnostic utility removing highly correlated RFs; B used principal component analysis (PCA); C-Random Forest intrinsic feature selection. The diagnostic utility was evaluated with accuracy and area under the receiver operating characteristic curve (AUC). Several RFs and Fingerprints had high AUC values (AUC > 0.8), confirmed by balanced accuracy, across training, test and external validation datasets. Good diagnostic performance achieved across several multi-centre datasets suggests that a radiomic pipeline can be generalizable. These findings could be used to build an automated clinical decision tool to facilitate objective and standardized assessment regardless of observer experience.

Dynamic radiomics for predicting the efficacy of antiangiogenic therapy in colorectal liver metastases

Background and objective

For patients with advanced colorectal liver metastases (CRLMs) receiving first-line anti-angiogenic therapy, an accurate, rapid and noninvasive indicator is urgently needed to predict its efficacy. In previous studies, dynamic radiomics predicted more accurately than conventional radiomics. Therefore, it is necessary to establish a dynamic radiomics efficacy prediction model for antiangiogenic therapy to provide more accurate guidance for clinical diagnosis and treatment decisions.

Methods

In this study, we use dynamic radiomics feature extraction method that extracts static features using tomographic images of different sequences of the same patient and then quantifies them into new dynamic features for the prediction of treatmentefficacy. In this retrospective study, we collected 76 patients who were diagnosed with unresectable CRLM between June 2016 and June 2021 in the First Hospital of China Medical University. All patients received standard treatment regimen of bevacizumab combined with chemotherapy in the first-line treatment, and contrast-enhanced abdominal CT (CECT) scans were performed before treatment. Patients with multiple primary lesions as well as missing clinical or imaging information were excluded. Area Under Curve (AUC) and accuracy were used to evaluate model performance. Regions of interest (ROIs) were independently delineated by two radiologists to extract radiomics features. Three machine learning algorithms were used to construct two scores based on the best response and progression-free survival (PFS).

Results

For the task that predict the best response patients will achieve after treatment, by using ROC curve analysis, it can be seen that the relative change rate (RCR) feature performed best among all features and best in linear discriminantanalysis (AUC: 0.945 and accuracy: 0.855). In terms of predicting PFS, the Kaplan-Meier plots suggested that the score constructed using the RCR features could significantly distinguish patients with good response from those with poor response (Two-sided P<0.0001 for survival analysis).

Conclusions

This study demonstrates that the application of dynamic radiomics features can better predict the efficacy of CRLM patients receiving antiangiogenic therapy compared with conventional radiomics features. It allows patients to have a more accurate assessment of the effect of medical treatment before receiving treatment, and this assessment method is noninvasive, rapid, and less expensive. Dynamic radiomics model provides stronger guidance for the selection of treatment options and precision medicine.

Current status and future perspectives of radiomics in hepatocellular carcinoma

Given the frequent co-existence of an aggressive tumor and underlying chronic liver disease, the management of hepatocellular carcinoma (HCC) patients requires experienced multidisciplinary team discussion. Moreover, imaging plays a key role in the diagnosis, staging, restaging, and surveillance of HCC. Currently, imaging assessment of HCC entails the assessment of qualitative characteristics which are prone to inter-reader variability. Radiomics is an emerging field that extracts high-dimensional mineable quantitative features that cannot be assessed visually with the naked eye from medical imaging. The main potential applications of radiomic models in HCC are to predict histology, response to treatment, genetic signature, recurrence, and survival. Despite the encouraging results to date, there are challenges and limitations that need to be overcome before radiomics implementation in clinical practice. The purpose of this article is to review the main concepts and challenges pertaining to radiomics, and to review recent studies and potential applications of radiomics in HCC.

Nomogram model based on radiomics signatures and age to assist in the diagnosis of knee osteoarthritis

BACKGROUND

Knee osteoarthritis (KOA) is a common disease in the elderly. An effective method for accurate diagnosis could affect the management and prognosis of patients.

OBJECTIVES

To develop a nomogram model based on X-ray imaging data and age, and to evaluate its effectiveness in the diagnosis of KOA.

METHODS

A total of 4403 knee X-rays from 1174 patients (July 2017 to November 2018) were retrospectively analyzed. Radiomics features were extracted and selected from the X-ray image data to quantify the phenotypic characteristics of the lesion region. Feature selection was performed in three steps to enable the derivation of robust and effective radiomics signatures. Then, logistic regression (LR), support vector machine (SVM) AdaBoost, gradient boosting decision tree (GBDT), and multi-layer perceptron (MLP) was adopted to verify the performance of radiomics signatures. In addition, a nomogram model combining age with radiomics signatures was constructed. At last, receiver operating characteristic (ROC) curve, calibration and decision curves were used to evaluate the discriminative performance.

RESULTS

The LR model has the best classification performance among the four radiomics models in testing cohort (LR AUC vs. SVM AUC: 0.843 vs. 0.818, DeLong test P = 0.0024; LR AUC vs. GBDT AUC: 0.843 vs. 0.821, P = 0.0028; LR AUC vs. MLP AUC: 0.843 vs. 0.822, P = 0.0019). The nomogram model achieved better predictive efficacy than the radiomics model in testing cohort compared to radiomics models although the statistical difference was not significant (Nomogram AUC vs. Radiomics AUC: 0.847 vs. 0.843, P = 0.06). The decision curve analysis revealed that the constructed nomogram had clinical usefulness.

CONCLUSION

The nomogram model combining radiomics signatures with age has good performance for the accurate diagnosis of KOA and may help to improve clinical decision-making.

Radiomics for Alzheimer's Disease: Fundamental Principles and Clinical Applications

Alzheimer's disease is a neurodegenerative disease with a huge impact on people's quality of life, life expectancy, and morbidity. The ongoing prevalence of the disease, in conjunction with an increased financial burden to healthcare services, necessitates the development of new technologies to be employed in this field. Hence, advanced computational methods have been developed to facilitate early and accurate diagnosis of the disease and improve all health outcomes. Artificial intelligence is now deeply involved in the fight against this disease, with many clinical applications in the field of medical imaging. Deep learning approaches have been tested for use in this domain, while radiomics, an emerging quantitative method, are already being evaluated to be used in various medical imaging modalities. This chapter aims to provide an insight into the fundamental principles behind radiomics, discuss the most common techniques alongside their strengths and weaknesses, and suggest ways forward for future research standardization and reproducibility.

Reproducibility assessment of radiomics features in various ultrasound scan settings and different scanner vendors

INTRODUCTION

Radiomics in Ultrasound (US) imaging has been investigated for the prediction and prognosis of cancers. However, inter-scanner and intra-scanner variations may affect the reproducibility of radiomics results. This study aims to evaluate the reproducibility of US textural radiomics features across various scan settings and scanner vendors.

MATERIALS AND METHODS

US images in quality control (QC) phantom were obtained by three scanners (Philips, Samsung, and Siemens) with different scan settings and parameters. Circular regions of interest (ROIs) inside isoechoic, hypoechoic, and hyperechoic objects were manually delineated. Forty textural radiomics features were extracted from each ROI, and then the robust features that could distinguish different echogenic objects were obtained by the Mann-Whitney U test. Reproducibility of the robust radiomics features was assessed by the intraclass correlation coefficient (ICC) and coefficient of variation (CV); ICC>0.90 and %CV<20 were considered reproducible.

RESULTS

According to the Mann-Whitney U test results, ten robust features could differentiate the hypoechoic, and 15 robust features could differentiate the hyperechoic objects from the isoechoic objects (P<0.001). The total ICC of the robust features for each echogenic object was >0.95 in different scanners and scan settings. Four and seven features were individually reproducible (%CV < 20, ICC>0.90) in hypoechoic and hyperechoic objects, respectively. Also, four features seem reproducible by changing the ROI location across the horizontal and vertical lines for both convex and linear array transducers.

CONCLUSIONS

Most of the US textural radiomics features in this study were not reproducible. However, several features showed high reproducibility at different scan settings and scanners. These features may also be reproducible when ROI size and location change slightly.

A methodological framework for AI-assisted diagnosis of active aortitis using radiomic analysis of FDG PET-CT images: Initial analysis

BACKGROUND

The aim of this study was to explore the feasibility of assisted diagnosis of active (peri-)aortitis using radiomic imaging biomarkers derived from [18F]-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography (FDG PET-CT) images.

METHODS

The aorta was manually segmented on FDG PET-CT in 50 patients with aortitis and 25 controls. Radiomic features (RF) (n = 107), including SUV (Standardized Uptake Value) metrics, were extracted from the segmented data and harmonized using the ComBat technique. Individual RFs and groups of RFs (i.e., signatures) were used as input in Machine Learning classifiers. The diagnostic utility of these classifiers was evaluated with area under the receiver operating characteristic curve (AUC) and accuracy using the clinical diagnosis as the ground truth.

RESULTS

Several RFs had high accuracy, 84% to 86%, and AUC scores 0.83 to 0.97 when used individually. Radiomic signatures performed similarly, AUC 0.80 to 1.00.

CONCLUSION

A methodological framework for a radiomic-based approach to support diagnosis of aortitis was outlined. Selected RFs, individually or in combination, showed similar performance to the current standard of qualitative assessment in terms of AUC for identifying active aortitis. This framework could support development of a clinical decision-making tool for a more objective and standardized assessment of aortitis.

Impact of image filtering and assessment of volume-confounding effects on CT radiomic features and derived survival models in non-small cell lung cancer

Background

No evidence supports the choice of specific imaging filtering methodologies in radiomics. As the volume of the primary tumor is a well-recognized prognosticator, our purpose is to assess how filtering may impact the feature/volume dependency in computed tomography (CT) images of non-small cell lung cancer (NSCLC), and if such impact translates into differences in the performance of survival modeling. The role of lesion volume in model performances was also considered and discussed.

Methods

Four-hundred seventeen CT images NSCLC patients were retrieved from the NSCLC-Radiomics public repository. Pre-processing and features extraction were implemented using Pyradiomics v3.0.1. Features showing high correlation with volume across original and filtered images were excluded. Cox proportional hazards (PH) with least absolute shrinkage and selection operator (LASSO) regularization and CatBoost models were built with and without volume, and their concordance (C-) indices were compared using Wilcoxon signed-ranked test. The Mann Whitney U test was used to assess model performances after stratification into two groups based on low- and high-volume lesions.

Results

Radiomic models significantly outperformed models built on only clinical variables and volume. However, the exclusion/inclusion of volume did not generally alter the performances of radiomic models. Overall, performances were not substantially affected by the choice of either imaging filter (overall C-index 0.539-0.590 for Cox PH and 0.589-0.612 for CatBoost). The separation of patients with high-volume lesions resulted in significantly better performances in 2/10 and 7/10 cases for Cox PH and CatBoost models, respectively. Both low- and high-volume models performed significantly better with the inclusion of radiomic features (P<0.0001), but the improvement was largest in the high-volume group (+10.2% against +8.7% improvement for CatBoost models and +10.0% against +5.4% in Cox PH models).

Conclusions

Radiomic features complement well-known prognostic factors such as volume, but their volume-dependency is high and should be managed with vigilance. The informative content of radiomic features may be diminished in small lesion volumes, which could limit the applicability of radiomics in early-stage NSCLC, where tumors tend to be small. Our results also suggest an advantage of CatBoost models over the Cox PH models.

Application of Radiomics in Predicting Treatment Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: Strategies and Challenges

Neoadjuvant chemoradiotherapy (nCRT) followed by total mesorectal excision is the standard treatment for locally advanced rectal cancer (LARC). A noninvasive preoperative prediction method should greatly assist in the evaluation of response to nCRT and for the development of a personalized strategy for patients with LARC. Assessment of nCRT relies on imaging and radiomics can extract valuable quantitative data from medical images. In this review, we examined the status of radiomic application for assessing response to nCRT in patients with LARC and indicated a potential direction for future research.

Radiomics-based approaches outperform visual analysis for differentiating lipoma from atypical lipomatous tumors: a review

BACKGROUND

Differentiating atypical lipomatous tumors (ALTs) and well-differentiated liposarcomas (WDLs) from benign lipomatous lesions is important for guiding clinical management, though conventional visual analysis of these lesions is challenging due to overlap of imaging features. Radiomics-based approaches may serve as a promising alternative and/or supplementary diagnostic approach to conventional imaging.

PURPOSE

The purpose of this study is to review the practice of radiomics-based imaging and systematically evaluate the literature available for studies evaluating radiomics applied to differentiating ALTs/WDLs from benign lipomas.

REVIEW

A background review of the radiomic workflow is provided, outlining the steps of image acquisition, segmentation, feature extraction, and model development. Subsequently, a systematic review of MEDLINE, EMBASE, Scopus, the Cochrane Library, and the grey literature was performed from inception to June 2022 to identify size studies using radiomics for differentiating ALTs/WDLs from benign lipomas. Radiomic models were shown to outperform conventional analysis in all but one model with a sensitivity ranging from 68 to 100% and a specificity ranging from 84 to 100%. However, current approaches rely on user input and no studies used a fully automated method for segmentation, contributing to interobserver variability and decreasing time efficiency.

CONCLUSION

Radiomic models may show improved performance for differentiating ALTs/WDLs from benign lipomas compared to conventional analysis. However, considerable variability between radiomic approaches exists and future studies evaluating a standardized radiomic model with a multi-institutional study design and preferably fully automated segmentation software are needed before clinical application can be more broadly considered.

Synthetic Post-Contrast Imaging through Artificial Intelligence: Clinical Applications of Virtual and Augmented Contrast Media

Contrast media are widely diffused in biomedical imaging, due to their relevance in the diagnosis of numerous disorders. However, the risk of adverse reactions, the concern of potential damage to sensitive organs, and the recently described brain deposition of gadolinium salts, limit the use of contrast media in clinical practice. In recent years, the application of artificial intelligence (AI) techniques to biomedical imaging has led to the development of 'virtual' and 'augmented' contrasts. The idea behind these applications is to generate synthetic post-contrast images through AI computational modeling starting from the information available on other images acquired during the same scan. In these AI models, non-contrast images (virtual contrast) or low-dose post-contrast images (augmented contrast) are used as input data to generate synthetic post-contrast images, which are often undistinguishable from the native ones. In this review, we discuss the most recent advances of AI applications to biomedical imaging relative to synthetic contrast media.

Application of machine learning model to predict osteoporosis based on abdominal computed tomography images of the psoas muscle: a retrospective study

BACKGROUND

With rapid economic development, the world's average life expectancy is increasing, leading to the increasing prevalence of osteoporosis worldwide. However, due to the complexity and high cost of dual-energy x-ray absorptiometry (DXA) examination, DXA has not been widely used to diagnose osteoporosis. In addition, studies have shown that the psoas index measured at the third lumbar spine (L3) level is closely related to bone mineral density (BMD) and has an excellent predictive effect on osteoporosis. Therefore, this study developed a variety of machine learning (ML) models based on psoas muscle tissue at the L3 level of unenhanced abdominal computed tomography (CT) to predict osteoporosis.

METHODS

Medical professionals collected the CT images and the clinical characteristics data of patients over 40 years old who underwent DXA and abdominal CT examination in the Second Affiliated Hospital of Wenzhou Medical University database from January 2017 to January 2021. Using 3D Slicer software based on horizontal CT images of the L3, the specialist delineated three layers of the region of interest (ROI) along the bilateral psoas muscle edges. The PyRadiomics package in Python was used to extract the features of ROI. Then Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) algorithm were used to reduce the dimension of the extracted features. Finally, six machine learning models, Gaussian naïve Bayes (GNB), random forest (RF), logistic regression (LR), support vector machines (SVM), Gradient boosting machine (GBM), and Extreme gradient boosting (XGBoost), were applied to train and validate these features to predict osteoporosis.

RESULTS

A total of 172 participants met the inclusion and exclusion criteria for the study. 82 participants were enrolled in the osteoporosis group, and 90 were in the non-osteoporosis group. Moreover, the two groups had no significant differences in age, BMI, sex, smoking, drinking, hypertension, and diabetes. Besides, 826 radiomic features were obtained from unenhanced abdominal CT images of osteoporotic and non-osteoporotic patients. Five hundred fifty radiomic features were screened out of 826 by the Mann-Whitney U test. Finally, 16 significant radiomic features were obtained by the LASSO algorithm. These 16 radiomic features were incorporated into six traditional machine learning models (GBM, GNB, LR, RF, SVM, and XGB). All six machine learning models could predict osteoporosis well in the validation set, with the area under the receiver operating characteristic (AUROC) values greater than or equal to 0.8. GBM is more effective in predicting osteoporosis, whose AUROC was 0.86, sensitivity 0.70, specificity 0.92, and accuracy 0.81 in validation sets.

CONCLUSION

We developed six machine learning models to predict osteoporosis based on psoas muscle images of abdominal CT, and the GBM model had the best predictive performance. GBM model can better help clinicians to diagnose osteoporosis and provide timely anti-osteoporosis treatment for patients. In the future, the research team will strive to include participants from multiple institutions to conduct external validation of the ML model of this study.

A primer on texture analysis in abdominal radiology

The number of publications on texture analysis (TA), radiomics, and radiogenomics has been growing exponentially, with abdominal radiologists aiming to build new prognostic or predictive biomarkers for a wide range of clinical applications including the use of oncological imaging to advance the field of precision medicine. TA is specifically concerned with the study of the variation of pixel intensity values in radiological images. Radiologists aim to capture pixel variation in radiological images to deliver new insights into tumor biology that cannot be derived from visual inspection alone. TA remains an active area of investigation and requires further standardization prior to its clinical acceptance and applicability. This review is for radiologists interested in this rapidly evolving field, who are thinking of performing research or want to better interpret results in this arena. We will review the main concepts in TA, workflow processes, and existing challenges and steps to overcome them, as well as look at publications in body imaging with external validation.

Pancreatic cancer, radiomics and artificial intelligence

Patients with pancreatic ductal adenocarcinoma (PDAC) are generally classified into four categories based on contrast-enhanced CT at diagnosis: resectable, borderline resectable, unresectable, and metastatic disease. In the initial grading and staging of PDAC, structured radiological templates are useful but limited, as there is a need to define the aggressiveness and microscopic disease stage of these tumours to ensure adequate treatment allocation. Quantitative imaging analysis allows radiomics and dynamic imaging features to provide information of clinical outcomes, and to construct clinical models based on radiomics signatures or imaging phenotypes. These quantitative features may be used as prognostic and predictive biomarkers in clinical decision-making, enabling personalised management of advanced PDAC. Deep learning and convolutional neural networks also provide high level bioinformatics tools that can help define features associated with a given aspect of PDAC biology and aggressiveness, paving the way to define outcomes based on these features. Thus, the prediction of tumour phenotype, treatment response and patient prognosis may be feasible by using such comprehensive and integrated radiomics models. Despite these promising results, quantitative imaging is not ready for clinical implementation in PDAC. Limitations include the instability of metrics and lack of external validation. Large properly annotated datasets, including relevant semantic features (demographics, blood markers, genomics), image harmonisation, robust radiomics analysis, clinically significant tasks as outputs, comparisons with gold-standards (such as TNM or pretreatment classifications) and fully independent validation cohorts, will be required for the development of trustworthy radiomics and artificial intelligence solutions to predict PDAC aggressiveness in a clinical setting.