Repeatability and Reproducibility of Radiomic Features: A Systematic Review

Mitigating the impact of image processing variations on tumour [18F]-FDG-PET radiomic feature robustness

Radiomics analysis of [18F]-fluorodeoxyglucose ([18F]-FDG) PET images could be leveraged for personalised cancer medicine. However, the inherent sensitivity of radiomic features to intensity discretisation and voxel interpolation complicates its clinical translation. In this work, we evaluated the robustness of tumour [18F]-FDG-PET radiomic features to 174 different variations in intensity resolution or voxel size, and determined whether implementing parameter range conditions or dependency corrections could improve their robustness. Using 485 patient images spanning three cancer types: non-small cell lung cancer (NSCLC), melanoma, and lymphoma, we observed features were more sensitive to intensity discretisation than voxel interpolation, especially texture features. In most of our investigations, the majority of non-robust features could be made robust by applying parameter range conditions. Correctable features, which were generally fewer than conditionally robust, showed systematic dependence on bin configuration or voxel size that could be minimised by applying corrections based on simple mathematical equations. Melanoma images exhibited limited robustness and correctability relative to NSCLC and lymphoma. Our study provides an in-depth characterisation of the sensitivity of [18F]-FDG-PET features to image processing variations and reinforces the need for careful selection of imaging biomarkers prior to any clinical application.

Computed tomography (CT) derived radiomics to predict post-operative disease recurrence in gastric cancer; a systematic review and meta-analysis

INTRODUCTION

Radiomics offers the potential to predict oncological outcomes from pre-operative imaging in order to identify 'high risk' patients at increased risk of recurrence. The application of radiomics in predicting disease recurrence provides tailoring of therapeutic strategies. We aim to comprehensively assess the existing literature regarding the current role of radiomics as a predictor of disease recurrence in gastric cancer.

METHODS

A systematic search was conducted in Medline, EMBASE, and Web of Science databases. Inclusion criteria encompassed retrospective and prospective studies investigating the use of radiomics to predict post-operative recurrence in ovarian cancer. Study quality was assessed using the QUADAS-2 and Radiomics Quality Score tools.

RESULTS

Nine studies met the inclusion criteria, involving a total of 6,662 participants. Radiomic-based nomograms demonstrated consistent performance in predicting disease recurrence, as evidenced by satisfactory area under the receiver operating characteristic curve values (AUC range 0.72 - 1). The pooled AUCs calculated using the inverse-variance method for both the training and validation datasets were 0.819 and 0.789 respectively CONCLUSION: Our review provides good evidence supporting the role of radiomics as a predictor of post-operative disease recurrence in gastric cancer. Included studies noted good performance in predicting their primary outcome. Radiomics may enhance personalised medicine by tailoring treatment decision based on predicted prognosis.

Developing a Novel Image Marker to Predict the Clinical Outcome of Neoadjuvant Chemotherapy (NACT) for Ovarian Cancer Patients

Objective

Neoadjuvant chemotherapy (NACT) is one kind of treatment for advanced stage ovarian cancer patients. However, due to the nature of tumor heterogeneity, the clinical outcome to NACT vary significantly among different subgroups. The patients with partial responses to NACT may lead to suboptimal debulking surgery, which will result in adverse prognosis. To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy prognosis prediction of the NACT at an early stage.

Methods

For this purpose, we first computed a total of 1373 radiomics features to quantify the tumor characteristics, which can be grouped into three categories: geometric, intensity, and texture features. Second, all these features were optimized by principal component analysis algorithm to generate a compact and informative feature cluster. This cluster was used as input for developing and optimizing support vector machine (SVM) based classifiers, which indicated the likelihood of the patient receiving suboptimal cytoreduction after the NACT treatment. Two different kernels for SVM algorithm were explored and compared. To validate this scheme, a total of 42 ovarian cancer patients were retrospectively collected. A nested leave-one-out cross-validation framework was adopted for model performance assessment.

Results

The results demonstrated that the model with a Gaussian radial basis function kernel SVM yielded an AUC (area under the ROC [receiver characteristic operation] curve) of 0.806 ± 0.078. Meanwhile, this model achieved overall accuracy (ACC) of 83.3%, positive predictive value (PPV) of 81.8%, and negative predictive value (NPV) of 83.9%.

Conclusion

This study provides meaningful information for the development of radiomics based image markers in NACT treatment outcome prediction.

Three-dimensional texture analyses of multi-quantitative relaxation time maps for evaluating cartilage repair with the treatment of allogeneic human adipose-derived mesenchymal progenitor cells

BACKGROUND

To explore the ability of three-dimensional texture analyses based on gray-level run-length matrix (GLRLM) for examining the spatial distribution of pixel values on magnetic resonance imaging (MRI) relaxation time maps and detecting the compositional variation of cartilage repair following treatment with allogeneic human adipose-derived mesenchymal progenitor cells (haMPCs).

METHODS

Participants with knee osteoarthritis were randomly divided into three groups with intra-articular haMPCs injections: low-, medium-, and high-dose groups. We analyzed five GLRLM parameters in the T1rho, T2 and T2star maps, including run length non-uniformity (RLNonUni), gray-level non-uniformity (GLevNonU), long run emphasis (LngREmph), short run emphasis (ShrtREmp), and fraction of images in runs. We used the relative D values (the ratio of difference values to baseline) as the objective to avoid errors caused by individual differences. We calculated the two-tailed Pearson's linear correlation coefficient (r) to investigate the correlations of the texture parameters with the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) scores.

RESULTS

Compared with the base time, significant reduction of WOMAC score was observed in both high and medium doses groups at terminal time, indicating relief of pain symptoms in high and medium groups with the treatment of allogeneic haMPCs. Significant differences were observed in the GLRLM parameters of cartilage MR relaxation time maps in different doses groups. In both T1rho and T2 relaxation time maps, the high-dose group showed significant increases in relative D values of RLNonUni, GLevNonU, LngREmph and ShrtREmp, which indicated significant changes in the uniformity of relaxation time maps. For T2star map, GLRLM parameters such as GLevNonU and ShrtREmp, especially LngREmph, showed significant increases in relative D values in high-dose group. Among all GLRLM features, LngREmph of three relaxation time maps had performed excellent linear correlations with WOMAC scores.

CONCLUSIONS

Texture analysis of the cartilage may allow the detection of compositional variation in cartilage repair with the treatment of allogeneic haMPCs. This technique displays potential applications in understanding the mechanism of stem cell repair of the cartilage and assessing the treatment response.

Visual Knowledge Domain of Artificial Intelligence in Computed Tomography: A Review Based on Bibliometric Analysis

ABSTRACT

Artificial intelligence (AI)-assisted medical imaging technology is a new research area of great interest that has developed rapidly over the last decade. However, there has been no bibliometric analysis of published studies in this field. The present review focuses on AI-related studies on computed tomography imaging in the Web of Science database and uses CiteSpace and VOSviewer to generate a knowledge map and conduct the basic information analysis, co-word analysis, and co-citation analysis. A total of 7265 documents were included and the number of documents published had an overall upward trend. Scholars from the United States and China have made outstanding achievements, and there is a general lack of extensive cooperation in this field. In recent years, the research areas of great interest and difficulty have been the optimization and upgrading of algorithms, and the application of theoretical models to practical clinical applications. This review will help researchers understand the developments, research areas of great interest, and research frontiers in this field and provide reference and guidance for future studies.

Radiomics and artificial intelligence: General notions and applications in the carotid vulnerable plaque

Carotid atherosclerosis plays a substantial role in cardiovascular morbidity and mortality. Given the multifaceted impact of this disease, there has been increasing interest in harnessing artificial intelligence (AI) and radiomics as complementary tools for the quantitative analysis of medical imaging data. This integrated approach holds promise not only in refining medical imaging data analysis but also in optimizing the utilization of radiologists' expertise. By automating time consuming tasks, AI allows radiologists to focus on more pertinent responsibilities. Simultaneously, the capacity of AI in radiomics to extract nuanced patterns from raw data enhances the exploration of carotid atherosclerosis, advancing efforts in terms of (1) early detection and diagnosis, (2) risk stratification and predictive modeling, (3) improving workflow efficiency, and (4) contributing to advancements in research. This review provides an overview of general concepts related to radiomics and AI, along with their application in the field of carotid vulnerable plaque. It also offers insights into various research studies conducted on this topic across different imaging techniques.

Does consensus contour improve robustness and accuracy in 18F-FDG PET radiomic features?

PURPOSE

The purpose of our study is to validate the robustness and accuracy of consensus contour in 2-deoxy-2-[18 F]fluoro-D-glucose (18 F-FDG) PET radiomic features.

METHODS

225 nasopharyngeal carcinoma (NPC) and 13 extended cardio-torso (XCAT) simulated data were enrolled. All segmentation were performed with four segmentation methods under two different initial masks, respectively. Consensus contour (ConSeg) was then developed using the majority vote rule. 107 radiomic features were extracted by Pyradiomics based on segmentation and the intraclass correlation coefficient (ICC) was calculated for each feature between masks or among segmentation, respectively. In XCAT ICC between segmentation and simulated ground truth were also calculated to access the accuracy.

RESULTS

ICC varied with the dataset, segmentation method, initial mask and feature type. ConSeg presented higher ICC for radiomic features in robustness tests and similar ICC in accuracy tests, compared with the average of four segmentation results. Higher ICC were also generally observed in irregular initial masks compared with rectangular masks in both robustness and accuracy tests. Furthermore, 19 features (17.76%) had ICC ≥ 0.75 in both robustness and accuracy tests for any of the segmentation methods or initial masks. The dataset was observed to have a large impact on the correlation relationships between radiomic features, but not the segmentation method or initial mask.

CONCLUSIONS

The consensus contour combined with irregular initial mask could improve the robustness and accuracy in radiomic analysis to some extent. The correlation relationships between radiomic features and feature clusters largely depended on the dataset, but not segmentation method or initial mask.

Comparing quantitative image parameters between animal and clinical CT-scanners: a translational phantom study analysis

Purpose

This study compares phantom-based variability of extracted radiomics features from scans on a photon counting CT (PCCT) and an experimental animal PET/CT-scanner (Albira II) to investigate the potential of radiomics for translation from animal models to human scans. While oncological basic research in animal PET/CT has allowed an intrinsic comparison between PET and CT, but no 1:1 translation to a human CT scanner due to resolution and noise limitations, Radiomics as a statistical and thus scale-independent method can potentially close the critical gap.

Methods

Two phantoms were scanned on a PCCT and animal PET/CT-scanner with different scan parameters and then the radiomics parameters were extracted. A Principal Component Analysis (PCA) was conducted. To overcome the limitation of a small dataset, a data augmentation technique was applied. A Ridge Classifier was trained and a Feature Importance- and Cluster analysis was performed.

Results

PCA and Cluster Analysis shows a clear differentiation between phantom types while emphasizing the comparability of both scanners. The Ridge Classifier exhibited a strong training performance with 93% accuracy, but faced challenges in generalization with a test accuracy of 62%.

Conclusion

These results show that radiomics has great potential as a translational tool between animal models and human routine diagnostics, especially using the novel photon counting technique. This is another crucial step towards integration of radiomics analysis into clinical practice.

Tumor Stiffness Measurement at Multifrequency MR Elastography to Predict Lymphovascular Space Invasion in Endometrial Cancer

Background Pathologic lymphovascular space invasion (LVSI) is associated with poor outcome in endometrial cancer. Its relationship with tumor stiffness, which can be measured with use of MR elastography, has not been extensively explored. Purpose To assess whether MR elastography-based mechanical characteristics can aid in the noninvasive prediction of LVSI in patients with endometrial cancer. Materials and Methods This prospective study included consecutive adult patients with a suspected uterine tumor who underwent MRI and MR elastography between October 2022 and July 2023. A region of interest delineated on T2-weighted magnitude images was duplicated on MR elastography images and used to calculate c (stiffness in meters per second) and φ (viscosity in radians) values. Pathologic assessment of hysterectomy specimens for LVSI served as the reference standard. Data were compared between LVSI-positive and -negative groups with use of the Mann-Whitney U test. Multivariable logistic regression was used to determine variables associated with LVSI positivity and develop diagnostic models for predicting LVSI. Model performance was assessed with use of area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. Results A total of 101 participants were included, 72 who were LVSI-negative (median age, 53 years [IQR, 48-62 years]) and 29 who were LVSI-positive (median age, 54 years [IQR, 49-60 years]). The tumor stiffness in the LVSI-positive group was higher than in the LVSI-negative group (median, 4.1 m/sec [IQR, 3.2-4.6 m/sec] vs 2.2 m/sec [IQR, 2.0-2.8 m/sec]; P < .001). Tumor volume, cancer antigen 125 level, and tumor stiffness were associated with LVSI positivity (adjusted odds ratio range, 1.01-9.06; P range, <.001-.04). The combined model (AUC, 0.93) showed better performance for predicting LVSI compared with clinical-radiologic model (AUC, 0.77; P = .003) and similar performance to the MR elastography-based model (AUC, 0.89; P = .06). Conclusion The addition of tumor stiffness as measured at MR elastography into a clinical-radiologic model improved prediction of LVSI in patients with endometrial cancer. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Ehman in this issue.

Development and Validation of an Ultrasonography-Based Machine Learning Model for Predicting Outcomes of Bruxism Treatments

BACKGROUND AND OBJECTIVES

We aimed to develop a predictive model for the outcome of bruxism treatments using ultrasonography (USG)-based machine learning (ML) techniques. This study is a quantitative research study (predictive modeling study) in which different treatment methods applied to bruxism patients are evaluated through artificial intelligence.

MATERIALS AND METHODS

The study population comprised 102 participants with bruxism in three treatment groups: Manual therapy, Manual therapy and Kinesio Tape or Botulinum Toxin-A injection. USG imaging was performed on the masseter muscle to calculate muscle thickness, and pain thresholds were evaluated using an algometer. A radiomics platform was utilized to handle imaging and clinical data, as well as to perform a subsequent radiomics statistical analysis.

RESULTS

The area under the curve (AUC) values of all machine learning methods ranged from 0.772 to 0.986 for the training data and from 0.394 to 0.848 for the test data. The Support Vector Machine (SVM) led to excellent discrimination between bruxism and normal patients from USG images. Radiomics characteristics in pre-treatment ultrasound scans of patients, showing coarse and nonuniform muscles, were associated with a greater chance of less effective pain reduction outcomes.

CONCLUSIONS

This study has introduced a machine learning model using SVM analysis on ultrasound (USG) images for bruxism patients, which can detect masseter muscle changes on USG. Support Vector Machine regression analysis showed the combined ML models can also predict the outcome of the pain reduction.

Radiomic profiles improve prognostication and reveal targets for therapy in cervical cancer

Cervical cancer (CC) is a major global health problem with 570,000 new cases and 266,000 deaths annually. Prognosis is poor for advanced stage disease, and few effective treatments exist. Preoperative diagnostic imaging is common in high-income countries and MRI measured tumor size routinely guides treatment allocation of cervical cancer patients. Recently, the role of MRI radiomics has been recognized. However, its potential to independently predict survival and treatment response requires further clarification. This retrospective cohort study demonstrates how non-invasive, preoperative, MRI radiomic profiling may improve prognostication and tailoring of treatments and follow-ups for cervical cancer patients. By unsupervised clustering based on 293 radiomic features from 132 patients, we identify three distinct clusters comprising patients with significantly different risk profiles, also when adjusting for FIGO stage and age. By linking their radiomic profiles to genomic alterations, we identify putative treatment targets for the different patient clusters (e.g., immunotherapy, CDK4/6 and YAP-TEAD inhibitors and p53 pathway targeting treatments).

Predicting histopathological features of aggressiveness in lung cancer using CT radiomics: a systematic review

PURPOSE

To examine the accuracy of CT radiomics to predict histopathological features of aggressiveness in lung cancer using a systematic review of test accuracy studies.

METHODS

Data sources searched included Medline, Embase, Web of Science, and Cochrane Library from up to 3 November 2023. Included studies reported test accuracy of CT radiomics models to detect the presence of: spread through air spaces (STAS), predominant adenocarcinoma pattern, adenocarcinoma grade, lymphovascular invasion (LVI), tumour infiltrating lymphocytes (TIL) and tumour necrosis, in patients with lung cancer. The primary outcome was test accuracy. Two reviewers independently assessed articles for inclusion and assessed methodological quality using the QUality Assessment of Diagnostic Accuracy Studies-2 tool. A single reviewer extracted data, which was checked by a second reviewer. Narrative data synthesis was performed.

RESULTS

Eleven studies were included in the final analysis. 10/11 studies were in East Asian populations. 4/11 studies investigated STAS, 6/11 investigated adenocarcinoma invasiveness or growth pattern, and 1/11 investigated LVI. No studies investigating TIL or tumour necrosis met inclusion criteria. Studies were of generally mixed to poor methodological quality. Reported accuracies for radiomic models ranged from 0.67 to 0.94.

CONCLUSION

Due to the high risk of bias and concerns regarding applicability, the evidence is inconclusive as to whether radiomic features can accurately predict prognostically important histopathological features of cancer aggressiveness. Many studies were excluded due to lack of external validation. Rigorously conducted prospective studies with sufficient external validity will be required for radiomic models to play a role in improving lung cancer outcomes.

Influence of image preprocessing on the segmentation-based reproducibility of radiomic features: in vivo experiments on discretization and resampling parameters

PURPOSE

To systematically investigate the impact of image preprocessing parameters on the segmentation-based reproducibility of magnetic resonance imaging (MRI) radiomic features.

METHODS

The MRI scans of 50 patients were included from the multi-institutional Brain Tumor Segmentation 2021 public glioma dataset. Whole tumor volumes were manually segmented by two independent readers, with the participation of eight readers. Radiomic features were extracted from two sequences: T2-weighted (T2) and contrast-enhanced T1-weighted (T1ce). Two methods were considered for discretization: bin count (i.e., relative discretization) and bin width (i.e., absolute discretization). Ten discretization (five for each method) and five resampling parameters were varied while other parameters were fixed. The intraclass correlation coefficient (ICC) was used for reliability analysis based on two commonly used cut-off values (0.75 and 0.90).

RESULTS

Image preprocessing parameters had a significant impact on the segmentation-based reproducibility of radiomic features. The bin width method yielded more reproducible features than the bin count method. In discretization experiments using the bin width on both sequences, according to the ICC cut-off values of 0.75 and 0.90, the rate of reproducible features ranged from 70% to 84% and from 35% to 57%, respectively, with an increasing percentage trend as parameter values decreased (from 84 to 5 for T2; 100 to 6 for T1ce). In the resampling experiments, these ranged from 53% to 74% and from 10% to 20%, respectively, with an increasing percentage trend from lower to higher parameter values (physical voxel size; from 1 x 1 x 1 to 2 x 2 x 2 mm3).

CONCLUSION

The segmentation-based reproducibility of radiomic features appears to be substantially influenced by discretization and resampling parameters. Our findings indicate that the bin width method should be used for discretization and lower bin width and higher resampling values should be used to allow more reproducible features.

Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study

Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.

Impact of 18F-FDG PET Intensity Normalization on Radiomic Features of Oropharyngeal Squamous Cell Carcinomas and Machine Learning-Generated Biomarkers

We aimed to investigate the effects of 18F-FDG PET voxel intensity normalization on radiomic features of oropharyngeal squamous cell carcinoma (OPSCC) and machine learning-generated radiomic biomarkers. Methods: We extracted 1,037 18F-FDG PET radiomic features quantifying the shape, intensity, and texture of 430 OPSCC primary tumors. The reproducibility of individual features across 3 intensity-normalized images (body-weight SUV, reference tissue activity ratio to lentiform nucleus of brain and cerebellum) and the raw PET data was assessed using an intraclass correlation coefficient (ICC). We investigated the effects of intensity normalization on the features' utility in predicting the human papillomavirus (HPV) status of OPSCCs in univariate logistic regression, receiver-operating-characteristic analysis, and extreme-gradient-boosting (XGBoost) machine-learning classifiers. Results: Of 1,037 features, a high (ICC ≥ 0.90), medium (0.90 > ICC ≥ 0.75), and low (ICC < 0.75) degree of reproducibility across normalization methods was attained in 356 (34.3%), 608 (58.6%), and 73 (7%) features, respectively. In univariate analysis, features from the PET normalized to the lentiform nucleus had the strongest association with HPV status, with 865 of 1,037 (83.4%) significant features after multiple testing corrections and a median area under the receiver-operating-characteristic curve (AUC) of 0.65 (interquartile range, 0.62-0.68). Similar tendencies were observed in XGBoost models, with the lentiform nucleus-normalized model achieving the numerically highest average AUC of 0.72 (SD, 0.07) in the cross validation within the training cohort. The model generalized well to the validation cohorts, attaining an AUC of 0.73 (95% CI, 0.60-0.85) in independent validation and 0.76 (95% CI, 0.58-0.95) in external validation. The AUCs of the XGBoost models were not significantly different. Conclusion: Only one third of the features demonstrated a high degree of reproducibility across intensity-normalization techniques, making uniform normalization a prerequisite for interindividual comparability of radiomic markers. The choice of normalization technique may affect the radiomic features' predictive value with respect to HPV. Our results show trends that normalization to the lentiform nucleus may improve model performance, although more evidence is needed to draw a firm conclusion.

Evaluation of bone marrow invasion on the machine learning of 18 F-FDG PET texture analysis in lower gingival squamous cell carcinoma

OBJECTIVES

Lower gingival squamous cell carcinoma (LGSCC) has the potential to invade the alveolar bone. Traditionally, the diagnosis of LGSCC relied on morphological imaging, but inconsistencies between these assessments and surgical findings have been observed. This study aimed to assess the correlation between LGSCC bone marrow invasion and PET texture features and to enhance diagnostic accuracy by using machine learning.

METHODS

A retrospective analysis of 159 LGSCC patients with pretreatment 18 F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) examination from 2009 to 2017 was performed. We extracted radiomic features from the PET images, focusing on pathologic bone marrow invasion detection. Extracted features underwent the least absolute shrinkage and selection operator algorithm-based selection and were then used for machine learning via the XGBoost package to distinguish bone marrow invasion presence. Receiver operating characteristic curve analysis was performed.

RESULTS

From the 159 patients, 88 qualified for further analysis (59 men; average age, 69.2 years), and pathologic bone marrow invasion was identified in 69 (78%) of these patients. Three significant radiological features were identified: Gray level co-occurrence matrix_Correlation, INTENSITY-BASED_IntensityInterquartileRange, and MORPHOLOGICAL_SurfaceToVolumeRatio. An XGBoost machine-learning model, using PET radiomic features to detect bone marrow invasion, yielded an area under the curve value of 0.83.

CONCLUSION

Our findings highlighted the potential of 18 F-FDG PET radiomic features, combined with machine learning, as a promising avenue for improving LGSCC diagnosis and treatment. Using 18 F-FDG PET texture features may provide a robust and accurate method for determining the presence or absence of bone marrow invasion in LGSCC patients.

Physics-Informed Discretization for Reproducible and Robust Radiomic Feature Extraction Using Quantitative MRI

OBJECTIVE

Given the limited repeatability and reproducibility of radiomic features derived from weighted magnetic resonance imaging (MRI), there may be significant advantages to using radiomics in conjunction with quantitative MRI. This study introduces a novel physics-informed discretization (PID) method for reproducible radiomic feature extraction and evaluates its performance using quantitative MRI sequences including magnetic resonance fingerprinting (MRF) and apparent diffusion coefficient (ADC) mapping.

MATERIALS AND METHODS

A multiscanner, scan-rescan dataset comprising whole-brain 3D quantitative (MRF T1, MRF T2, and ADC) and weighted MRI (T1w MPRAGE, T2w SPACE, and T2w FLAIR) from 5 healthy subjects was prospectively acquired. Subjects underwent 2 repeated acquisitions on 3 distinct 3 T scanners each, for a total of 6 scans per subject (30 total scans). First-order statistical (n = 23) and second-order texture (n = 74) radiomic features were extracted from 56 brain tissue regions of interest using the proposed PID method (for quantitative MRI) and conventional fixed bin number (FBN) discretization (for quantitative MRI and weighted MRI). Interscanner radiomic feature reproducibility was measured using the intraclass correlation coefficient (ICC), and the effect of image sequence (eg, MRF T1 vs T1w MPRAGE), as well as image discretization method (ie, PID vs FBN), on radiomic feature reproducibility was assessed using repeated measures analysis of variance. The robustness of PID and FBN discretization to segmentation error was evaluated by simulating segmentation differences in brainstem regions of interest. Radiomic features with ICCs greater than 0.75 following simulated segmentation were determined to be robust to segmentation.

RESULTS

First-order features demonstrated higher reproducibility in quantitative MRI than weighted MRI sequences, with 30% (n = 7/23) features being more reproducible in MRF T1 and MRF T2 than weighted MRI. Gray level co-occurrence matrix (GLCM) texture features extracted from MRF T1 and MRF T2 were significantly more reproducible using PID compared with FBN discretization; for all quantitative MRI sequences, PID yielded the highest number of texture features with excellent reproducibility (ICC > 0.9). Comparing texture reproducibility of quantitative and weighted MRI, a greater proportion of MRF T1 (n = 225/370, 61%) and MRF T2 (n = 150/370, 41%) texture features had excellent reproducibility (ICC > 0.9) compared with T1w MPRAGE (n = 148/370, 40%), ADC (n = 115/370, 32%), T2w SPACE (n = 98/370, 27%), and FLAIR (n = 102/370, 28%). Physics-informed discretization was also more robust than FBN discretization to segmentation error, as 46% (n = 103/222, 46%) of texture features extracted from quantitative MRI using PID were robust to simulated 6 mm segmentation shift compared with 19% (n = 42/222, 19%) of weighted MRI texture features extracted using FBN discretization.

CONCLUSIONS

The proposed PID method yields radiomic features extracted from quantitative MRI sequences that are more reproducible and robust than radiomic features extracted from weighted MRI using conventional (FBN) discretization approaches. Quantitative MRI sequences also demonstrated greater scan-rescan robustness and first-order feature reproducibility than weighted MRI.

Multi-omics staging of locally advanced rectal cancer predicts treatment response: a pilot study

Treatment response assessment of rectal cancer patients is a critical component of personalized cancer care and it allows to identify suitable candidates for organ-preserving strategies. This pilot study employed a novel multi-omics approach combining MRI-based radiomic features and untargeted metabolomics to infer treatment response at staging. The metabolic signature highlighted how tumor cell viability is predictively down-regulated, while the response to oxidative stress was up-regulated in responder patients, showing significantly reduced oxoproline values at baseline compared to non-responder patients (p-value < 10-4). Tumors with a high degree of texture homogeneity, as assessed by radiomics, were more likely to achieve a major pathological response (p-value < 10-3). A machine learning classifier was implemented to summarize the multi-omics information and discriminate responders and non-responders. Combining all available radiomic and metabolomic features, the classifier delivered an AUC of 0.864 (± 0.083, p-value < 10-3) with a best-point sensitivity of 90.9% and a specificity of 81.8%. Our results suggest that a multi-omics approach, integrating radiomics and metabolomic data, can enhance the predictive value of standard MRI and could help to avoid unnecessary surgical treatments and their associated long-term complications.

Increasing the efficiency of cone-beam CT based delta-radiomics using automated contours to predict radiotherapy-related toxicities in prostate cancer

Extracting longitudinal image quantitative data, known as delta-radiomics, has the potential to capture changes in a patient's anatomy throughout the course of radiation treatment for prostate cancer. Some of the major challenges of delta-radiomics studies are contouring the structures for individual fractions and accruing patients' data in an efficient manner. The manual contouring process is often time consuming and would limit the efficiency of accruing larger sample sizes for future studies. The problem is amplified because the contours are often made by highly trained radiation oncologists with limited time to dedicate to research studies of this nature. This work compares the use of automated prostate contours generated using a deformable image-based algorithm to make predictive models of genitourinary and changes in total international prostate symptom score in comparison to manually contours for a cohort of fifty patients. Area under the curve of manual and automated models were compared using the Delong test. This study demonstrated that the delta-radiomics models were similar for both automated and manual delta-radiomics models.

Inter- and Intra-Patient Repeatability of Radiomic Features from Multiparametric Whole-Body MRI in Patients with Metastatic Prostate Cancer

(1) Background: We assessed the test-re-test repeatability of radiomics in metastatic castration-resistant prostate cancer (mCPRC) bone disease on whole-body diffusion-weighted (DWI) and T1-weighted Dixon MRI. (2) Methods: In 10 mCRPC patients, 1.5 T MRI, including DWI and T1-weighted gradient-echo Dixon sequences, was performed twice on the same day. Apparent diffusion coefficient (ADC) and relative fat-fraction-percentage (rFF%) maps were calculated. Per study, up to 10 target bone metastases were manually delineated on DWI and Dixon images. All 106 radiomic features included in the Pyradiomics toolbox were derived for each target volume from the ADC and rFF% maps. To account for inter- and intra-patient measurement repeatability, the log-transformed individual target measurements were fitted to a hierarchical model, represented as a Bayesian network. Repeatability measurements, including the intraclass correlation coefficient (ICC), were derived. Feature ICCs were compared with mean ADC and rFF ICCs. (3) Results: A total of 65 DWI and 47 rFF% targets were analysed. There was no significant bias for any features. Pairwise correlation revealed fifteen ADC and fourteen rFF% feature sub-groups, without specific patterns between feature classes. The median intra-patient ICC was generally higher than the inter-patient ICC. Features that describe extremes in voxel values (minimum, maximum, range, skewness, and kurtosis) showed generally lower ICCs. Several mostly shape-based texture features were identified, which showed high inter- and intra-patient ICCs when compared with the mean ADC or mean rFF%, respectively. (4) Conclusions: Pyradiomics texture features of mCRPC bone metastases varied greatly in inter- and intra-patient repeatability. Several features demonstrated good repeatability, allowing for further exploration as diagnostic parameters in mCRPC bone disease.

MRI radiomics in head and neck cancer from reproducibility to combined approaches

The clinical applicability of radiomics in oncology depends on its transferability to real-world settings. However, the absence of standardized radiomics pipelines combined with methodological variability and insufficient reporting may hamper the reproducibility of radiomic analyses, impeding its translation to clinics. This study aimed to identify and replicate published, reproducible radiomic signatures based on magnetic resonance imaging (MRI), for prognosis of overall survival in head and neck squamous cell carcinoma (HNSCC) patients. Seven signatures were identified and reproduced on 58 HNSCC patients from the DB2Decide Project. The analysis focused on: assessing the signatures' reproducibility and replicating them by addressing the insufficient reporting; evaluating their relationship and performances; and proposing a cluster-based approach to combine radiomic signatures, enhancing the prognostic performance. The analysis revealed key insights: (1) despite the signatures were based on different features, high correlations among signatures and features suggested consistency in the description of lesion properties; (2) although the uncertainties in reproducing the signatures, they exhibited a moderate prognostic capability on an external dataset; (3) clustering approaches improved prognostic performance compared to individual signatures. Thus, transparent methodology not only facilitates replication on external datasets but also advances the field, refining prognostic models for potential personalized medicine applications.

Radiomics-based prediction of nonalcoholic fatty liver disease following pancreatoduodenectomy

PURPOSE

Predicting nonalcoholic fatty liver disease (NAFLD) following pancreaticoduodenectomy (PD) is challenging, which delays therapeutic intervention and makes its prevention difficult. We conducted this study to assess the potential application of preoperative computed tomography (CT) radiomics for predicting NAFLD.

METHODS

The subjects of this retrospective study were 186 patients with PD from a single institution. We extracted the predictors of NAFLD after PD statistically from conventional clinical and radiomic features of the estimated remnant pancreas and whole liver region on preoperative nonenhanced CT images. Based on these predictors, we developed a machine-learning predictive model, which integrated clinical and radiomic features. A comparative model used only clinical features as predictors.

RESULTS

The incidence of NAFLD after PD was 43.5%. The variables of the clinicoradiomic model included one shape feature of the pancreas, two texture features of the liver, and sex; the variables of the clinical model were age, sex, and chemoradiotherapy. The accuracy%, precision%, recall%, F1 score, and area under the curve of the two models were 75.0, 72.7, 66.7, 69.6, and 0.80; and 69.6, 68.4, 54.2, 60.5, and 0.69, respectively.

CONCLUSIONS

Preoperative CT-derived radiomic features from the pancreatic and liver regions are promising for the prediction of NAFLD post-PD. Using these features enhances the predictive model, enabling earlier intervention for high-risk patients.

Image-based artificial intelligence for the prediction of pathological complete response to neoadjuvant chemoradiotherapy in patients with rectal cancer: a systematic review and meta-analysis

OBJECTIVE

Artificial intelligence (AI) holds enormous potential for noninvasively identifying patients with rectal cancer who could achieve pathological complete response (pCR) following neoadjuvant chemoradiotherapy (nCRT). We aimed to conduct a meta-analysis to summarize the diagnostic performance of image-based AI models for predicting pCR to nCRT in patients with rectal cancer.

METHODS

This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. A literature search of PubMed, Embase, Cochrane Library, and Web of Science was performed from inception to July 29, 2023. Studies that developed or utilized AI models for predicting pCR to nCRT in rectal cancer from medical images were included. The Quality Assessment of Diagnostic Accuracy Studies-AI was used to appraise the methodological quality of the studies. The bivariate random-effects model was used to summarize the individual sensitivities, specificities, and areas-under-the-curve (AUCs). Subgroup and meta-regression analyses were conducted to identify potential sources of heterogeneity. Protocol for this study was registered with PROSPERO (CRD42022382374).

RESULTS

Thirty-four studies (9933 patients) were identified. Pooled estimates of sensitivity, specificity, and AUC of AI models for pCR prediction were 82% (95% CI: 76-87%), 84% (95% CI: 79-88%), and 90% (95% CI: 87-92%), respectively. Higher specificity was seen for the Asian population, low risk of bias, and deep-learning, compared with the non-Asian population, high risk of bias, and radiomics (all P < 0.05). Single-center had a higher sensitivity than multi-center (P = 0.001). The retrospective design had lower sensitivity (P = 0.012) but higher specificity (P < 0.001) than the prospective design. MRI showed higher sensitivity (P = 0.001) but lower specificity (P = 0.044) than non-MRI. The sensitivity and specificity of internal validation were higher than those of external validation (both P = 0.005).

CONCLUSIONS

Image-based AI models exhibited favorable performance for predicting pCR to nCRT in rectal cancer. However, further clinical trials are warranted to verify the findings.

Study on the differential diagnosis of benign and malignant breast lesions using a deep learning model based on multimodal images

OBJECTIVE

To establish a multimodal model for distinguishing benign and malignant breast lesions.

MATERIALS AND METHODS

Clinical data, mammography, and MRI images (including T2WI, diffusion-weighted images (DWI), apparent diffusion coefficient (ADC), and DCE-MRI images) of 132 benign and breast cancer patients were analyzed retrospectively. The region of interest (ROI) in each image was marked and segmented using MATLAB software. The mammography, T2WI, DWI, ADC, and DCE-MRI models based on the ResNet34 network were trained. Using an integrated learning method, the five models were used as a basic model, and voting methods were used to construct a multimodal model. The dataset was divided into a training set and a prediction set. The accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the model were calculated. The diagnostic efficacy of each model was analyzed using a receiver operating characteristic curve (ROC) and an area under the curve (AUC). The diagnostic value was determined by the DeLong test with statistically significant differences set at P < 0.05.

RESULTS

We evaluated the ability of the model to classify benign and malignant tumors using the test set. The AUC values of the multimodal model, mammography model, T2WI model, DWI model, ADC model and DCE-MRI model were 0.943, 0.645, 0.595, 0.905, 0.900, and 0.865, respectively. The diagnostic ability of the multimodal model was significantly higher compared with that of the mammography and T2WI models. However, compared with the DWI, ADC, and DCE-MRI models, there was no significant difference in the diagnostic ability of these models.

CONCLUSION

Our deep learning model based on multimodal image training has practical value for the diagnosis of benign and malignant breast lesions.

Application of deep learning in radiation therapy for cancer

In recent years, with the development of artificial intelligence, deep learning has been gradually applied to clinical treatment and research. It has also found its way into the applications in radiotherapy, a crucial method for cancer treatment. This study summarizes the commonly used and latest deep learning algorithms (including transformer, and diffusion models), introduces the workflow of different radiotherapy, and illustrates the application of different algorithms in different radiotherapy modules, as well as the defects and challenges of deep learning in the field of radiotherapy, so as to provide some help for the development of automatic radiotherapy for cancer.

Developing a novel image marker to predict the clinical outcome of neoadjuvant chemotherapy (NACT) for ovarian cancer patients

OBJECTIVE

Neoadjuvant chemotherapy (NACT) is one kind of treatment for advanced stage ovarian cancer patients. However, due to the nature of tumor heterogeneity, the clinical outcomes to NACT vary significantly among different subgroups. Partial responses to NACT may lead to suboptimal debulking surgery, which will result in adverse prognosis. To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy prognosis prediction of NACT at an early stage.

METHODS

For this purpose, we first computed a total of 1373 radiomics features to quantify the tumor characteristics, which can be grouped into three categories: geometric, intensity, and texture features. Second, all these features were optimized by principal component analysis algorithm to generate a compact and informative feature cluster. This cluster was used as input for developing and optimizing support vector machine (SVM) based classifiers, which indicated the likelihood of receiving suboptimal cytoreduction after the NACT treatment. Two different kernels for SVM algorithm were explored and compared. A total of 42 ovarian cancer cases were retrospectively collected to validate the scheme. A nested leave-one-out cross-validation framework was adopted for model performance assessment.

RESULTS

The results demonstrated that the model with a Gaussian radial basis function kernel SVM yielded an AUC (area under the ROC [receiver characteristic operation] curve) of 0.806 ± 0.078. Meanwhile, this model achieved overall accuracy (ACC) of 83.3%, positive predictive value (PPV) of 81.8%, and negative predictive value (NPV) of 83.9%.

CONCLUSION

This study provides meaningful information for the development of radiomics based image markers in NACT treatment outcome prediction.

Technical and clinical considerations of a physical liver phantom for CT radiomics analysis

OBJECTIVE

This study identifies key characteristics to help build a physical liver computed tomography (CT) phantom for radiomics harmonization; particularly, the higher-order texture metrics.

MATERIALS AND METHODS

CT scans of a radiomics phantom comprising of 18 novel 3D printed inserts with varying size, shape, and material combinations were acquired on a 64-slice CT scanner (Brilliance 64, Philips Healthcare). The images were acquired at 120 kV, 250 mAs, CTDIvol of 16.36 mGy, 2 mm slice thickness, and iterative noise-reduction reconstruction (iDose, Philips Healthcare, Andover, MA). Radiomics analysis was performed using the Cancer Imaging Phenomics Toolkit (CaPTk), following automated segmentation of 3D regions of interest (ROI) of the 18 inserts. The findings were compared to three additional ROI obtained of an anthropomorphic liver phantom, a patient liver CT scan, and a water phantom, at comparable imaging settings. Percentage difference in radiomic metrics values between phantom and tissue was used to assess the biological equivalency and <10% was used to claim equivalent.

RESULTS

The HU for all 18 ROI from the phantom ranged from -30 to 120 which is within clinically observed HU range of the liver, showing that our phantom material (T3-6B) is representative of biological CT tissue densities (liver) with >50% radiomic features having <10% difference from liver tissue. Based on the assessment of the Neighborhood Gray Tone Difference Matrix (NGTDM) metrics it is evident that the water phantom ROI show extreme values compared to the ROIs from the phantom. This result may further reinforce the difference between a structureless quantity such as water HU values and tissue HU values found in liver.

CONCLUSION

The 3-D printed patterns of the constructed radiomics phantom cover a wide span of liver tissue textures seen in CT images. Using our results, texture metrics can be selectively harmonized to establish clinically relevant and reliable radiomics panels.

Robustness of radiomic features in healthy abdominal parenchyma of patients with repeated examinations on dual-layer dual-energy CT

OBJECTIVES

Robustness of radiomic features in physiological tissue is an important prerequisite for quantitative analysis of tumor biology and response assessment. In contrast to previous studies which focused on different tumors with mostly short scan-re-scan intervals, this study aimed to evaluate the robustness of radiomic features in cancer-free patients and over a clinically encountered inter-scan interval.

MATERIALS AND METHODS

Patients without visible tumor burden who underwent at least two portal-venous phase dual energy CT examinations of the abdomen between May 2016 and January 2020 were included, while macroscopic tumor burden was excluded based upon follow-up imaging for all patients (≥3 months). Further, patients were excluded if no follow-up imaging was available, or if the CT protocol showed deviations between repeated examinations. Circular regions of interest were placed and proofread by two board-certified radiologists (4 years and 5 years experience) within the liver (segments 3 and 6), the psoas muscle (left and right), the pancreatic head, and the spleen to obtain radiomic features from normal-appearing organ parenchyma using PyRadiomics. Radiomic feature robustness was tested using the concordance correlation coefficient with a threshold of 0.75 considered indicative for deeming a feature robust.

RESULTS

In total, 160 patients with 480 repeated abdominal CT examinations (range: 2-4 per patient) were retrospectively included in this single-center, IRB-approved study. Considering all organs and feature categories, only 4.58 % (25/546) of all features were robust with the highest rate being found in the first order feature category (20.37 %, 22/108). Other feature categories (grey level co-occurrence matrix, grey level dependence matrix, grey level run length matrix, grey level size zone matrix, and neighborhood gray-tone difference matrix) yielded an overall low percentage of robust features (range: 0.00 %-1.19 %). A subgroup analysis revealed the reconstructed field of view and the X-ray tube current as determinants of feature robustness (significant differences in subgroups for all organs, p < 0.001) as well as the size of the region of interest (no significant difference for the pancreatic head with p = 0.135, significant difference with p < 0.001 for all other organs).

CONCLUSION

Radiomic feature robustness obtained from cancer-free subjects with repeated examinations using a consistent protocol and CT scanner was limited, with first order features yielding the highest proportion of robust features.

CT-based radiomics for predicting lymph node metastasis in esophageal cancer: a systematic review and meta-analysis

Objective

We aimed to evaluate the diagnostic effectiveness of computed tomography (CT)-based radiomics for predicting lymph node metastasis (LNM) in patients diagnosed with esophageal cancer (EC).

Methods

The present study conducted a comprehensive search by accessing the following databases: PubMed, Embase, Cochrane Library, and Web of Science, with the aim of identifying relevant studies published until July 10th, 2023. The diagnostic accuracy was summarized using the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC). The researchers utilized Spearman's correlation coefficient for assessing the threshold effect, besides performing meta-regression and subgroup analysis for the exploration of possible heterogeneity sources. The quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies-2 and the Radiomics Quality Score (RQS).

Results

The meta-analysis included six studies conducted from 2018 to 2022, with 483 patients enrolled and LNM rates ranging from 27.2% to 59.4%. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC, along with their corresponding 95% CI, were 0.73 (0.67, 0.79), 0.76 (0.69, 0.83), 3.1 (2.3, 4.2), 0.35 (0.28, 0.44), 9 (6, 14), and 0.78 (0.74, 0.81), respectively. The results demonstrated the absence of significant heterogeneity in sensitivity, while significant heterogeneity was observed in specificity; no threshold effect was detected. The observed heterogeneity in the specificity was attributed to the sample size and CT-scan phases (P < 0.05). The included studies exhibited suboptimal quality, with RQS ranging from 14 to 16 out of 36. However, most of the enrolled studies exhibited a low-risk bias and minimal concerns relating to applicability.

Conclusion

The present meta-analysis indicated that CT-based radiomics demonstrated a favorable diagnostic performance in predicting LNM in EC. Nevertheless, additional high-quality, large-scale, and multicenter trials are warranted to corroborate these findings.

Systematic Review Registration

Open Science Framework platform at https://osf.io/5zcnd.

Segmentation of Variants of Nuclei on Whole Slide Images by Using Radiomic Features

The histopathological segmentation of nuclear types is a challenging task because nuclei exhibit distinct morphologies, textures, and staining characteristics. Accurate segmentation is critical because it affects the diagnostic workflow for patient assessment. In this study, a framework was proposed for segmenting various types of nuclei from different organs of the body. The proposed framework improved the segmentation performance for each nuclear type using radiomics. First, we used distinct radiomic features to extract and analyze quantitative information about each type of nucleus and subsequently trained various classifiers based on the best input sub-features of each radiomic feature selected by a LASSO operator. Second, we inputted the outputs of the best classifier to various segmentation models to learn the variants of nuclei. Using the MoNuSAC2020 dataset, we achieved state-of-the-art segmentation performance for each category of nuclei type despite the complexity, overlapping, and obscure regions. The generalized adaptability of the proposed framework was verified by the consistent performance obtained in whole slide images of different organs of the body and radiomic features.

Multi-sequence MRI radiomics of colorectal liver metastases: Which features are reproducible across readers?

PURPOSE

To assess the inter-reader reproducibility of radiomics features on multiple MRI sequences after segmentations of colorectal liver metastases (CRLM).

METHOD

30 CRLM (in 23 patients) were manually delineated by three readers on MRI before the start of chemotherapy on the contrast enhanced T1-weighted images (CE-T1W) in the portal venous phase, T2-weighted images (T2W) and b800 diffusion weighted images (DWI). DWI delineations were copied to the ADC-maps. 107 radiomics features were extracted per sequence. The intraclass correlation coefficient (ICC) was calculated per feature. Features were considered reproducible if ICC > 0.9.

RESULTS

90% of CE-T1W features were reproducible with a median ICC of 0.98 (range 0.76-1.00). 81% of DWI features were robust with median ICC = 0.97 (range 0.38-1.00). The T2W features had a median ICC of 0.96 (range 0.55-0.99) and were reproducible in 80%. ADC showed the lowest number of reproducible features with 58% and median ICC = 0.91 (range 0.38-0.99) When considering the lower bound of the ICC 95% confidence intervals, 58%, 66%, 54% and 29% reached 0.9 for the CE-T1W, DWI, T2W and ADC features, respectively. The feature class with the best reproducibility differed per sequence.

CONCLUSIONS

The majority of MRI radiomics features from CE-T1W, T2W, DWI and ADC in colorectal liver metastases were robust for segmentation variability between readers. The CE-T1W yielded slightly better reproducibility results compared to DWI and T2W. The ADC features seem more susceptible to reader differences compared to the other three sequences.

Phantom study investigating the repeatability of radiomic features with alteration of image acquisition parameters in magnetic resonance imaging

BACKGROUND

Magnetic resonance imaging (MRI) has many different alterable parameters that affect how an image appears. This is relevant in radiomics which produces quantitative features through analysis of medical images. One significant acknowledged limitation of radiomics is repeatability. This phantom study aims to further investigate the repeatability of radiomic features (RaF), within MRI, across a range of different echo (TE) and repetition times (TR).

METHODS

A phantom was scanned 10 times under identical conditions on a 3T scanner using head coil over 4 months. The TE ranged from 80 to 110 ms while the TR from 3000 to 5000 ms. Radiomics analysis was performed on the same segmented section of the phantom across all TE and TR combinations. Intraclass Correlation Coefficient (ICC) was calculated across the different TE and TR ranges to investigate the repeatability of RaF.

RESULTS

Of 1596 features calculated, 187 features had ICC >0.9 across the range of TE, while 82 features had an ICC >0.9 across a range of TR. 664 had ICC >0.75 across the range of TEs, with 541 across the range of TR values. There was an overlap of 51 features with ICC >0.9.

CONCLUSION

Repeatability of RaF in MRI is dependent on imaging parameters and careful consideration of these, in combination with variable selection, is required when applying radiomics to MRI.

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer

Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Improving radiomics reproducibility using deep learning-based image conversion of CT reconstruction algorithms in hepatocellular carcinoma patients

OBJECTIVES

CT reconstruction algorithms affect radiomics reproducibility. In this study, we evaluate the effect of deep learning-based image conversion on CT reconstruction algorithms.

METHODS

This study included 78 hepatocellular carcinoma (HCC) patients who underwent four-phase liver CTs comprising non-contrast, late arterial (LAP), portal venous (PVP), and delayed phase (DP), reconstructed using both filtered back projection (FBP) and advanced modeled iterative reconstruction (ADMIRE). PVP images were used to train a convolutional neural network (CNN) model to convert images from FBP to ADMIRE and vice versa. LAP, PVP, and DP images were used for validation and testing. Radiomic features were extracted for each patient with a semi-automatic segmentation tool. We used concordance correlation coefficients (CCCs) to evaluate the radiomics reproducibility for original FBP (oFBP) vs. original ADMIRE (oADMIRE), oFBP vs. converted FBP (cFBP), and oADMIRE vs. converted ADMIRE (cADMIRE).

RESULTS

In the test group including 30 patients, the CCC and proportion of reproducible features (CCC ≥ 0.85) for oFBP vs. oADMIRE were 0.65 and 32.9% (524/1595) for LAP, 0.65 and 35.9% (573/1595) for PVP, and 0.69 and 43.8% (699/1595) for DP. For oFBP vs. cFBP, the values increased to 0.92 and 83.9% (1339/1595) for LAP, 0.89 and 71.0% (1133/1595) for PVP, and 0.90 and 79.7% (1271/1595) for DP. Similarly, for oADMIRE vs. cADMIRE, the values increased to 0.87 and 68.1% (1086/1595) for LAP, 0.91 and 82.1% (1309/1595) for PVP, and 0.89 and 76.2% (1216/1595) for DP.

CONCLUSIONS

CNN-based image conversion between CT reconstruction algorithms improved the radiomics reproducibility of HCCs.

CLINICAL RELEVANCE STATEMENT

This study demonstrates that using a CNN-based image conversion technique significantly improves the reproducibility of radiomic features in HCCs, highlighting its potential for enhancing radiomics research in HCC patients.

KEY POINTS

Radiomics reproducibility of HCC was improved via CNN-based image conversion between two different CT reconstruction algorithms. This is the first clinical study to demonstrate improvements across a range of radiomic features in HCC patients. This study promotes the reproducibility and generalizability of different CT reconstruction algorithms in radiomics research.

Role of sureness in evaluating AI/CADx: Lesion-based repeatability of machine learning classification performance on breast MRI

BACKGROUND

Artificial intelligence/computer-aided diagnosis (AI/CADx) and its use of radiomics have shown potential in diagnosis and prognosis of breast cancer. Performance metrics such as the area under the receiver operating characteristic (ROC) curve (AUC) are frequently used as figures of merit for the evaluation of CADx. Methods for evaluating lesion-based measures of performance may enhance the assessment of AI/CADx pipelines, particularly in the situation of comparing performances by classifier.

PURPOSE

The purpose of this study was to investigate the use case of two standard classifiers to (1) compare overall classification performance of the classifiers in the task of distinguishing between benign and malignant breast lesions using radiomic features extracted from dynamic contrast-enhanced magnetic resonance (DCE-MR) images, (2) define a new repeatability metric (termed sureness), and (3) use sureness to examine if one classifier provides an advantage in AI diagnostic performance by lesion when using radiomic features.

METHODS

Images of 1052 breast lesions (201 benign, 851 cancers) had been retrospectively collected under HIPAA/IRB compliance. The lesions had been segmented automatically using a fuzzy c-means method and thirty-two radiomic features had been extracted. Classification was investigated for the task of malignant lesions (81% of the dataset) versus benign lesions (19%). Two classifiers (linear discriminant analysis, LDA and support vector machines, SVM) were trained and tested within 0.632 bootstrap analyses (2000 iterations). Whole-set classification performance was evaluated at two levels: (1) the 0.632+ bias-corrected area under the ROC curve (AUC) and (2) performance metric curves which give variability in operating sensitivity and specificity at a target operating point (95% target sensitivity). Sureness was defined as 1-95% confidence interval of the classifier output for each lesion for each classifier. Lesion-based repeatability was evaluated at two levels: (1) repeatability profiles, which represent the distribution of sureness across the decision threshold and (2) sureness of each lesion. The latter was used to identify lesions with better sureness with one classifier over another while maintaining lesion-based performance across the bootstrap iterations.

RESULTS

In classification performance assessment, the median and 95% CI of difference in AUC between the two classifiers did not show evidence of difference (ΔAUC = -0.003 [-0.031, 0.018]). Both classifiers achieved the target sensitivity. Sureness was more consistent across the classifier output range for the SVM classifier than the LDA classifier. The SVM resulted in a net gain of 33 benign lesions and 307 cancers with higher sureness and maintained lesion-based performance. However, with the LDA there was a notable percentage of benign lesions (42%) with better sureness but lower lesion-based performance.

CONCLUSIONS

When there is no evidence for difference in performance between classifiers using AUC or other performance summary measures, a lesion-based sureness metric may provide additional insight into AI pipeline design. These findings present and emphasize the utility of lesion-based repeatability via sureness in AI/CADx as a complementary enhancement to other evaluation measures.

Unenhanced computed tomography radiomics help detect endoleaks after endovascular repair of abdominal aortic aneurysm

OBJECTIVES

To explore the feasibility of unenhanced CT images for endoleak detection of abdominal aortic aneurysm (AAA) after endovascular repair (EVAR).

METHODS

Patients who visited our hospital after EVAR from July 2014 to September 2021 were retrospectively collected. Two radiologists evaluated the presence or absence of endoleaks using the combination of contrast-enhanced and unenhanced CT as the referenced standard. After segmenting the aneurysm sac of the unenhanced CT, the radiomic features were automatically extracted from the region of interest. Histogram features of patients with and without endoleak were statistically analyzed to explore the differences between the two groups. Twelve common machine learning (ML) models based on radiomic features were constructed to evaluate the performance of endoleak detection with unenhanced CT images.

RESULTS

The study included 216 patients (69 ± 8 years; 191 men) with AAA, including 64 patients with endoleaks. A total of 1955 radiomic features of unenhanced CT were extracted. Compared with patients without endoleak, the aneurysm sac outside the stent of patients with endoleak had higher CT attenuation (41.7 vs. 33.6, p < 0.001) with smaller dispersion (51.5 vs. 58.8, p < 0.001). The average area under the curve (AUC) of the ML models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the accuracy was 81% ± 4, the sensitivity was 88% ± 10, and the specificity was 78% ± 5. When fixing the sensitivity to > 90% (92% ± 2), the models retained specificity at 72% ± 10.

CONCLUSIONS

Unenhanced CT features exhibit significant differences between patients with and without endoleak and can help detect endoleaks in AAA after EVAR with high sensitivity.

CLINICAL RELEVANCE STATEMENT

Unenhanced CT radiomics can help provide an alternative method of endoleak detection in patients who have adverse reactions to contrast media. This study further exploits the value of unenhanced CT examinations in the clinical management and surveillance of postoperative abdominal aortic aneurysm.

KEY POINTS

• Unenhanced CT features of the aneurysm sac outside the stent exhibit significant differences between patients with and without endoleak. The endoleak group showed higher unenhanced CT attenuation (41.7 vs 33.6, p < .001) with smaller dispersion (51.5 vs 58.8, p < .001) than the nonendoleak group. • Unenhanced CT radiomics can help detect endoleaks after intervention. The average area under the curve (AUC) of twelve common machine learning models constructed with unenhanced CT radiomics was 0.86 ± 0.05, the average accuracy was 81% ± 4. • When fixing the sensitivity to > 90% (92% ± 2), the machine learning models retained average specificity at 72% ± 10.

CT and MRI radiomics of bone and soft-tissue sarcomas: an updated systematic review of reproducibility and validation strategies

OBJECTIVE

To systematically review radiomic feature reproducibility and model validation strategies in recent studies dealing with CT and MRI radiomics of bone and soft-tissue sarcomas, thus updating a previous version of this review which included studies published up to 2020.

METHODS

A literature search was conducted on EMBASE and PubMed databases for papers published between January 2021 and March 2023. Data regarding radiomic feature reproducibility and model validation strategies were extracted and analyzed.

RESULTS

Out of 201 identified papers, 55 were included. They dealt with radiomics of bone (n = 23) or soft-tissue (n = 32) tumors. Thirty-two (out of 54 employing manual or semiautomatic segmentation, 59%) studies included a feature reproducibility analysis. Reproducibility was assessed based on intra/interobserver segmentation variability in 30 (55%) and geometrical transformations of the region of interest in 2 (4%) studies. At least one machine learning validation technique was used for model development in 34 (62%) papers, and K-fold cross-validation was employed most frequently. A clinical validation of the model was reported in 38 (69%) papers. It was performed using a separate dataset from the primary institution (internal test) in 22 (40%), an independent dataset from another institution (external test) in 14 (25%) and both in 2 (4%) studies.

CONCLUSIONS

Compared to papers published up to 2020, a clear improvement was noted with almost double publications reporting methodological aspects related to reproducibility and validation. Larger multicenter investigations including external clinical validation and the publication of databases in open-access repositories could further improve methodology and bring radiomics from a research area to the clinical stage.

CRITICAL RELEVANCE STATEMENT

An improvement in feature reproducibility and model validation strategies has been shown in this updated systematic review on radiomics of bone and soft-tissue sarcomas, highlighting efforts to enhance methodology and bring radiomics from a research area to the clinical stage.

KEY POINTS

• 2021-2023 radiomic studies on CT and MRI of musculoskeletal sarcomas were reviewed. • Feature reproducibility was assessed in more than half (59%) of the studies. • Model clinical validation was performed in 69% of the studies. • Internal (44%) and/or external (29%) test datasets were employed for clinical validation.

Reproducibility in Radiomics: A Comparison of Feature Extraction Methods and Two Independent Datasets

Radiomics involves the extraction of information from medical images that are not visible to the human eye. There is evidence that these features can be used for treatment stratification and outcome prediction. However, there is much discussion about the reproducibility of results between different studies. This paper studies the reproducibility of CT texture features used in radiomics, comparing two feature extraction implementations, namely the MATLAB toolkit and Pyradiomics, when applied to independent datasets of CT scans of patients: (i) the open access RIDER dataset containing a set of repeat CT scans taken 15 min apart for 31 patients (RIDER Scan 1 and Scan 2, respectively) treated for lung cancer; and (ii) the open access HN1 dataset containing 137 patients treated for head and neck cancer. Gross tumor volume (GTV), manually outlined by an experienced observer available on both datasets, was used. The 43 common radiomics features available in MATLAB and Pyradiomics were calculated using two intensity-level quantization methods with and without an intensity threshold. Cases were ranked for each feature for all combinations of quantization parameters, and the Spearman's rank coefficient, rs, calculated. Reproducibility was defined when a highly correlated feature in the RIDER dataset also correlated highly in the HN1 dataset, and vice versa. A total of 29 out of the 43 reported stable features were found to be highly reproducible between MATLAB and Pyradiomics implementations, having a consistently high correlation in rank ordering for RIDER Scan 1 and RIDER Scan 2 (rs > 0.8). 18/43 reported features were common in the RIDER and HN1 datasets, suggesting they may be agnostic to disease site. Useful radiomics features should be selected based on reproducibility. This study identified a set of features that meet this requirement and validated the methodology for evaluating reproducibility between datasets.

Rank acquisition impact on radiomics estimation (AсquIRE) in chest CT imaging: A retrospective multi-site, multi-use-case study

BACKGROUND

Radiomics is a method within medical image analysis that involves the extraction of quantitative data from radiologic scans, often in conjunction with machine learning algorithms to phenotype disease appearance, prognosticate disease outcome, and predict treatment response. However, variance in CT scanner acquisition parameters, such as convolution kernels or pixel spacing, can impact radiomics texture feature values.

PURPOSE

The extent to which the parameters influence radiomics features continues to be an active area of investigation. In this study, we describe a novel approach, Acquisition Impact on Radiomics Estimation (AcquIRE), to rank the impact of CT acquisition parameters on radiomic texture features.

METHODS

In this work, we used three chest CT imaging datasets (n = 749 patients) from nine sites comprising: i) lung granulomas and adenocarcinomas (D1) (10 and 52 patients, respectively); ii) minimal and frank invasive adenocarcinoma (D2) (74 and 145 patients); and iii) early-stage NSCLC patients (D3) (315 patients). Datasets D2 and D3 were collected from four sites each, and D1 from a single site. For each patient, 744 texture features and nine acquisition parameters were extracted and utilized to evaluate which parameters impact radiomic features the most. The AcquIRE method establishes a relative assessment between acquisition parameters and radiomic texture featuresa through the creation of a classification model, which is then utilized to assess the rank of the acquisition parameters.

RESULTS

Across the use cases, CT software version and convolution kernel parameters were found to have the most variance. In D1, it was observed that the Haralick texture feature family was the least affected by variations in acquisition parameters, while the Gabor feature family was the most impacted. However, in datasets D2 and D3, the Gabor features were found to be the least affected. Our findings suggest that the impact on radiomic parameters is as much a function of the problem in question as it is acquisition parameters.

CONCLUSIONS

The software version and convolution kernel parameters impacted the radiomics feature the most.

Advancing equitable and personalized cancer care: Novel applications and priorities of artificial intelligence for fairness and inclusivity in the patient care workflow

Patient care workflows are highly multimodal and intertwined: the intersection of data outputs provided from different disciplines and in different formats remains one of the main challenges of modern oncology. Artificial Intelligence (AI) has the potential to revolutionize the current clinical practice of oncology owing to advancements in digitalization, database expansion, computational technologies, and algorithmic innovations that facilitate discernment of complex relationships in multimodal data. Within oncology, radiation therapy (RT) represents an increasingly complex working procedure, involving many labor-intensive and operator-dependent tasks. In this context, AI has gained momentum as a powerful tool to standardize treatment performance and reduce inter-observer variability in a time-efficient manner. This review explores the hurdles associated with the development, implementation, and maintenance of AI platforms and highlights current measures in place to address them. In examining AI's role in oncology workflows, we underscore that a thorough and critical consideration of these challenges is the only way to ensure equitable and unbiased care delivery, ultimately serving patients' survival and quality of life.

Comparing deep learning and handcrafted radiomics to predict chemoradiotherapy response for locally advanced cervical cancer using pretreatment MRI

Concurrent chemoradiotherapy (CRT) is the standard treatment for locally advanced cervical cancer (LACC), but its responsiveness varies among patients. A reliable tool for predicting CRT responses is necessary for personalized cancer treatment. In this study, we constructed prediction models using handcrafted radiomics (HCR) and deep learning radiomics (DLR) based on pretreatment MRI data to predict CRT response in LACC. Furthermore, we investigated the potential improvement in prediction performance by incorporating clinical factors. A total of 252 LACC patients undergoing curative chemoradiotherapy are included. The patients are randomly divided into two independent groups for the training (167 patients) and test datasets (85 patients). Contrast-enhanced T1- and T2-weighted MR scans are obtained. For HCR analysis, 1890 imaging features are extracted and a support vector machine classifier with a five-fold cross-validation is trained on training dataset to predict CRT response and subsequently validated on test dataset. For DLR analysis, a 3-dimensional convolutional neural network was trained on training dataset and validated on test dataset. In conclusion, both HCR and DLR models could predict CRT responses in patients with LACC. The integration of clinical factors into radiomics prediction models tended to improve performance in HCR analysis. Our findings may contribute to the development of personalized treatment strategies for LACC patients.

Peri-lesion regions in differentiating suspicious breast calcification-only lesions specifically on contrast enhanced mammography

PURPOSE

The explore the added value of peri-calcification regions on contrast-enhanced mammography (CEM) in the differential diagnosis of breast lesions presenting as only calcification on routine mammogram.

METHODS

Patients who underwent CEM because of suspicious calcification-only lesions were included. The test set included patients between March 2017 and March 2019, while the validation set was collected between April 2019 and October 2019. The calcifications were automatically detected and grouped by a machine learning-based computer-aided system. In addition to extracting radiomic features on both low-energy (LE) and recombined (RC) images from the calcification areas, the peri-calcification regions, which is generated by extending the annotation margin radially with gradients from 1 mm to 9 mm, were attempted. Machine learning (ML) models were built to classify calcifications into malignant and benign groups. The diagnostic matrices were also evaluated by combing ML models with subjective reading.

RESULTS

Models for LE (significant features: wavelet-LLL_glcm_Imc2_MLO; wavelet-HLL_firstorder_Entropy_MLO; wavelet-LHH_glcm_DifferenceVariance_CC; wavelet-HLL_glcm_SumEntropy_MLO;wavelet-HLH_glrlm_ShortRunLowGray LevelEmphasis_MLO; original_firstorder_Entropy_MLO; original_shape_Elongation_MLO) and RC (significant features: wavelet-HLH_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_10Percentile_CC; original_firstorder_Maximum_MLO; wavelet-HHH_glcm_Autocorrelation_MLO; original_shape_Elongation_MLO; wavelet-LHL_glszm_GrayLevelNonUniformityNormalized_MLO; wavelet-LLH_firstorder_RootMeanSquared_MLO) images were set up with 7 features. Areas under the curve (AUCs) of RC models are significantly better than those of LE models with compact and expanded boundary (RC v.s. LE, compact: 0.81 v.s. 0.73, p < 0.05; expanded: 0.89 v.s. 0.81, p < 0.05) and RC models with 3 mm boundary extension yielded the best performance compared to those with other sizes (AUC = 0.89). Combining with radiologists' reading, the 3mm-boundary RC model achieved a sensitivity of 0.871 and negative predictive value of 0.937 with similar accuracy of 0.843 in predicting malignancy.

CONCLUSIONS

The machine learning model integrating intra- and peri-calcification regions on CEM has the potential to aid radiologists' performance in predicting malignancy of suspicious breast calcifications.

Quantitation of Oncologic Image Features for Radiomic Analyses in PET

Radiomics is an emerging and exciting field of study involving the extraction of many quantitative features from radiographic images. Positron emission tomography (PET) images are used in cancer diagnosis and staging. Utilizing radiomics on PET images can better quantify the spatial relationships between image voxels and generate more consistent and accurate results for diagnosis, prognosis, treatment, etc. This chapter gives the general steps a researcher would take to extract PET radiomic features from medical images and properly develop models to implement.

Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI

OBJECTIVE

The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis.

MATERIALS AND METHODS

We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model's performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model.

RESULTS

Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91-0.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8-0.84, F1-score = 0.9, PPV = 90%.

CONCLUSIONS

Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods.

Diagnostic and Therapeutic Issues in Glioma Using Imaging Data: The Challenge of Numerical Twinning

Glial tumors represent the leading etiology of primary brain tumors. Their particularities lie in (i) their location in a highly functional organ that is difficult to access surgically, including for biopsy, and (ii) their rapid, anisotropic mode of extension, notably via the fiber bundles of the white matter, which further limits the possibilities of resection. The use of mathematical tools enables the development of numerical models representative of the oncotype, genotype, evolution, and therapeutic response of lesions. The significant development of digital technologies linked to high-resolution NMR exploration, coupled with the possibilities offered by AI, means that we can envisage the creation of digital twins of tumors and their host organs, thus reducing the use of physical sampling.

Radiogenomics: Contemporary Applications in the Management of Rectal Cancer

Radiogenomics, a sub-domain of radiomics, refers to the prediction of underlying tumour biology using non-invasive imaging markers. This novel technology intends to reduce the high costs, workload and invasiveness associated with traditional genetic testing via the development of 'imaging biomarkers' that have the potential to serve as an alternative 'liquid-biopsy' in the determination of tumour biological characteristics. Radiogenomics also harnesses the potential to unlock aspects of tumour biology which are not possible to assess by conventional biopsy-based methods, such as full tumour burden, intra-/inter-lesion heterogeneity and the possibility of providing the information of tumour biology longitudinally. Several studies have shown the feasibility of developing a radiogenomic-based signature to predict treatment outcomes and tumour characteristics; however, many lack prospective, external validation. We performed a systematic review of the current literature surrounding the use of radiogenomics in rectal cancer to predict underlying tumour biology.

Prospective inter- and intra-tracer repeatability analysis of radiomics features in [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET scans in metastatic prostate cancer

OBJECTIVE

This study aimed to quantify both the intra- and intertracer repeatability of lesion-level radiomics features in [68Ga]Ga-prostate-specific membrane antigen (PSMA)-11 and [18F]F-PSMA-1007 positron emission tomography (PET) scans.

METHODS

Eighteen patients with metastatic prostate cancer (mPCa) were prospectively recruited for the study and randomised to one of three test-retest groups: (i) intratracer [68Ga]Ga-PSMA-11 PET, (ii) intratracer [18F]F-PSMA-1007 PET or (iii) intertracer between [68Ga]Ga-PSMA-11 and [18F]F-PSMA-1007 PET. Four conventional PET metrics (standardised uptake value (SUV)max, SUVmean, SUVtotal and volume) and 107 radiomics features were extracted from 75 lesions and assessed using the repeatability coefficient (RC) and the ICC. Radiomic feature repeatability was also quantified after the application of 16 filters to the PET image.

RESULTS

Test-retest scans were taken a median of 5 days apart (range: 2-7 days). SUVmean demonstrated the lowest RC limits of the conventional features, with RCs of 7.9%, 14.2% and 24.7% for the [68Ga]Ga-PSMA-11 PET, [18F]F-PSMA-1007 PET, and intertracer groups, respectively. 69%, 66% and 9% of all radiomics features had good or excellent ICC values (ICC ≥ 0.75) for the same groups. Feature repeatability therefore diminished considerably for the intertracer group relative to intratracer groups.

CONCLUSION

In this study, robust biomarkers for each tracer group that can be used in subsequent clinical studies were identified. Overall, the repeatability of conventional and radiomic features were found to be substantially lower for the intertracer group relative to both intratracer groups, suggesting that assessing patient response quantitatively should be done using the same radiotracer where possible.

ADVANCES IN KNOWLEDGE

Intertracer biomarker repeatability limits are significantly larger than intratracer limits.

Clinical Applications of Radiomics in Nuclear Medicine

Radiomics is an emerging field of artificial intelligence that focuses on the extraction and analysis of quantitative features such as intensity, shape, texture and spatial relationships from medical images. These features, often imperceptible to the human eye, can reveal complex patterns and biological insights. They can also be combined with clinical data to create predictive models using machine learning to improve disease characterization in nuclear medicine. This review article examines the current state of radiomics in nuclear medicine and shows its potential to improve patient care. Selected clinical applications for diseases such as cancer, neurodegenerative diseases, cardiovascular problems and thyroid diseases are examined. The article concludes with a brief classification in terms of future perspectives and strategies for linking research findings to clinical practice.