Harmonization strategies for multicenter radiomics investigations

Long-axial field-of-view PET/CT improves radiomics feature reliability

PURPOSE

To assess the influence of long-axial field-of-view (LAFOV) PET/CT systems on radiomics feature reliability, to assess the suitability for short-duration or low-activity acquisitions for textural feature analysis and to investigate the influence of acceptance angle.

METHODS

34 patients were analysed: twelve patients underwent oncological 2-[18F]-FDG PET/CT, fourteen [18F]PSMA-1007 and eight [68Ga]Ga-DOTATOC. Data were obtained using a 106 cm LAFOV system for 10 min. Sinograms were generated from list-mode data corresponding to scan durations of 2, 5, 10, 20, 30, 60, 120, 240, 360 and 600s using both standard (minimum ring difference MRD 85 crystals) and maximum acceptance angles (MRD 322). Target lesions were segmented and radiomics features were calculated. To assess feature correlation, Pearson's product-moment correlation coefficient (PPMCC) was calculated with respect to the full duration acquisition for MRD 85 and 322 respectively. The number of features with excellent (r > 0.9), moderate (r > 0.7 and < 0.9) and poor (r ≤ 0.7) correlation was compared as a measure of feature stability. Intra-class heterogeneity was assessed by means of the quartile coefficient of dispersion.

RESULTS

As expected, PPMCC improved with acquisition time for all features. By 240s almost all features showed at least moderate agreement with the full count (C100%) data, and by 360s almost all showed excellent agreement. Compared to standard-axial field of view (SAFOV) equivalent scans, fewer features showed moderate or poor agreement, and this was most pronounced for [68Ga]Ga-DOTATOC. Data obtained at C100% at MRD 322 were better able to capture between-patient heterogeneities.

CONCLUSION

The improved feature reliability at longer acquisition times and higher MRD demonstrate the advantages of high sensitivity LAFOV systems for reproducible and low-noise data. High fidelity between MRD 85 and MRD 322 was seen at all scan durations > 2s. When contrasted with data comparable to a simulated SAFOV acquisition, full-count and full-MRD data were better able to capture underlying feature heterogeneities.

Myocardial perfusion SPECT radiomic features reproducibility assessment: Impact of image reconstruction and harmonization

BACKGROUND

Coronary artery disease (CAD) has one of the highest mortality rates in humans worldwide. Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) provides clinicians with myocardial metabolic information non-invasively. However, there are some limitations to interpreting SPECT images performed by physicians or automatic quantitative approaches. Radiomics analyzes images objectively by extracting quantitative features and can potentially reveal biological characteristics that the human eye cannot detect. However, the reproducibility and repeatability of some radiomic features can be highly susceptible to segmentation and imaging conditions.

PURPOSE

We aimed to assess the reproducibility of radiomic features extracted from uncorrected MPI-SPECT images reconstructed with 15 different settings before and after ComBat harmonization, along with evaluating the effectiveness of ComBat in realigning feature distributions.

MATERIALS AND METHODS

A total of 200 patients (50% normal and 50% abnormal) including rest and stress (without attenuation and scatter corrections) MPI-SPECT images were included. Images were reconstructed using 15 combinations of filter cut-off frequencies, filter orders, filter types, reconstruction algorithms, number of iterations and subsets resulting in 6000 images. Image segmentation was performed on the left ventricle in the first reconstruction for each patient and applied to 14 others. A total of 93 radiomic features were extracted from the segmented area, and ComBat was used to harmonize them. The intraclass correlation coefficient (ICC) and overall concordance correlation coefficient (OCCC) tests were performed before and after ComBat to examine the impact of each parameter on feature robustness and to assess harmonization efficiency. The ANOVA and the Kruskal-Wallis tests were performed to evaluate the effectiveness of ComBat in correcting feature distributions. In addition, the Student's t-test, Wilcoxon rank-sum, and signed-rank tests were implemented to assess the significance level of the impacts made by each parameter of different batches and patient groups (normal vs. abnormal) on radiomic features.

RESULTS

Before applying ComBat, the majority of features (ICC: 82, OCCC: 61) achieved high reproducibility (ICC/OCCC ≥ 0.900) under every batch except Reconstruction. The largest and smallest number of poor features (ICC/OCCC < 0.500) were obtained by IterationSubset and Order batches, respectively. The most reliable features were from the first-order (FO) and gray-level co-occurrence matrix (GLCM) families. Following harmonization, the minimum number of robust features increased (ICC: 84, OCCC: 78). Applying ComBat showed that Order and Reconstruction were the least and the most responsive batches, respectively. The most robust families, in a descending order, were found to be FO, neighborhood gray-tone difference matrix (NGTDM), GLCM, gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), and gray-level dependence matrix (GLDM) under Cut-off, Filter, and Order batches. The Wilcoxon rank-sum test showed that the number of robust features significantly differed under most batches in the Normal and Abnormal groups.

CONCLUSION

The majority of radiomic features show high levels of robustness across different OSEM reconstruction parameters in uncorrected MPI-SPECT. ComBat is effective in realigning feature distributions and enhancing radiomic features reproducibility.

Multimodal Imaging Approach for Tumor Treatment Response Evaluation in the Era of Immunotherapy

ABSTRACT

Immunotherapy is likely the most remarkable advancement in lung cancer treatment during the past decade. Although immunotherapy provides substantial benefits, their therapeutic responses differ from those of conventional chemotherapy and targeted therapy, and some patients present unique immunotherapy response patterns that cannot be judged under the current measurement standards. Therefore, the response monitoring of immunotherapy can be challenging, such as the differentiation between real response and pseudo-response. This review outlines the various tumor response patterns to immunotherapy and discusses methods for quantifying computed tomography (CT) and 18 F-fluorodeoxyglucose positron emission tomography (PET) in the field of lung cancer. Emerging technologies in magnetic resonance imaging (MRI) and non-FDG PET tracers are also explored. With immunotherapy responses, the role for imaging is essential in both anatomical radiological responses (CT/MRI) and molecular changes (PET imaging). Multiple aspects must be considered when assessing treatment responses using CT and PET. Finally, we introduce multimodal approaches that integrate imaging and nonimaging data, and we discuss future directions for the assessment and prediction of lung cancer responses to immunotherapy.

The Challenge of External Generalisability: Insights from the Bicentric Validation of a [68Ga]Ga-PSMA-11 PET Based Radiomics Signature for Primary Prostate Cancer Characterisation Using Histopathology as Reference

Background: PSMA PET radiomics is a promising tool for primary prostate cancer (PCa) characterisation. However, small single-centre studies and lack of external validation hinder definitive conclusions on the potential of PSMA PET radiomics in the initial workup of PCa. We aimed to validate a radiomics signature in a larger internal cohort and in an external cohort from a separate centre. Methods: One hundred and twenty-seven PCa patients were retrospectively enrolled across two independent hospitals. The first centre (IRCCS San Raffaele Scientific Institute, Centre 1) contributed 62 [68Ga]Ga-PSMA-11 PET scans, 20 patients classified as low-grade (ISUP grade < 4), and 42 as high-grade (ISUP grade ≥ 4). The second centre (Stanford University Hospital, Centre 2) provided 65 [68Ga]Ga-PSMA-11 PET scans, and 49 low-grade and 16 high-grade patients. A radiomics model previously generated in Centre 1 was tested on the two cohorts separately and afterward on the entire dataset. Then, we evaluated whether the radiomics features selected in the previous investigation could generalise to new data. Several machine learning (ML) models underwent training and testing using 100-fold Monte Carlo cross-validation, independently at both Centre 1 and Centre 2, with a 70-30% train-test split. Additionally, models were trained in one centre and tested in the other, and vice versa. Furthermore, data from both centres were combined for training and testing using Monte Carlo cross-validation. Finally, a new radiomics signature built on this bicentric dataset was proposed. Several performance metrics were computed. Results: The previously generated radiomics signature resulted in an area under the receiver operating characteristic curve (AUC) of 80.4% when tested on Centre 1, while it generalised poorly to Centre 2, where it reached an AUC of 62.7%. When the whole cohort was considered, AUC was 72.5%. Similarly, new ML models trained on the previously selected features yielded, at best, an AUC of 80.9% for Centre 1 and performed at chance for Centre 2 (AUC of 49.3%). A new signature built on this bicentric dataset reached, at best, an average AUC of 91.4% in the test set. Conclusions: The satisfying performance of radiomics models when used in the original development settings, paired with the poor performance otherwise observed, emphasises the need to consider centre-specific factors and dataset characteristics when developing radiomics models. Combining radiomics datasets is a viable strategy to reduce such centre-specific biases, but external validation is still needed.

Deep feature batch correction using ComBat for machine learning applications in computational pathology

Background

Developing artificial intelligence (AI) models for digital pathology requires large datasets from multiple sources. However, without careful implementation, AI models risk learning confounding site-specific features in datasets instead of clinically relevant information, leading to overestimated performance, poor generalizability to real-world data, and potential misdiagnosis.

Methods

Whole-slide images (WSIs) from The Cancer Genome Atlas (TCGA) colon (COAD), and stomach adenocarcinoma datasets were selected for inclusion in this study. Patch embeddings were obtained using three feature extraction models, followed by ComBat harmonization. Attention-based multiple instance learning models were trained to predict tissue-source site (TSS), as well as clinical and genetic attributes, using raw, Macenko normalized, and Combat-harmonized patch embeddings.

Results

TSS prediction achieved high accuracy (AUROC > 0.95) with all three feature extraction models. ComBat harmonization significantly reduced the AUROC for TSS prediction, with mean AUROCs dropping to approximately 0.5 for most models, indicating successful mitigation of batch effects (e.g., CCL-ResNet50 in TCGA-COAD: Pre-ComBat AUROC = 0.960, Post-ComBat AUROC = 0.506, p < 0.001). Clinical attributes associated with TSS, such as race and treatment response, showed decreased predictability post-harmonization. Notably, the prediction of genetic features like MSI status remained robust after harmonization (e.g., MSI in TCGA-COAD: Pre-ComBat AUROC = 0.667, Post-ComBat AUROC = 0.669, p=0.952), indicating the preservation of true histological signals.

Conclusion

ComBat harmonization of deep learning-derived histology features effectively reduces the risk of AI models learning confounding features in WSIs, ensuring more reliable performance estimates. This approach is promising for the integration of large-scale digital pathology datasets.

Impact of intensity standardisation and ComBat batch size on clinical-radiomic prognostic models performance in a multi-centre study of patients with glioblastoma

PURPOSE

To assess the effect of different intensity standardisation techniques (ISTs) and ComBat batch sizes on radiomics survival model performance and stability in a heterogenous, multi-centre cohort of patients with glioblastoma (GBM).

METHODS

Multi-centre pre-operative MRI acquired between 2014 and 2020 in patients with IDH-wildtype unifocal WHO grade 4 GBM were retrospectively evaluated. WhiteStripe (WS), Nyul histogram matching (HM), and Z-score (ZS) ISTs were applied before radiomic feature (RF) extraction. RFs were realigned using ComBat and minimum batch size (MBS) of 5, 10, or 15 patients. Cox proportional hazards models for overall survival (OS) prediction were produced using five different selection strategies and the impact of IST and MBS was evaluated using bootstrapping. Calibration, discrimination, relative explained variation, and model fit were assessed. Instability was evaluated using 95% confidence intervals (95% CIs), feature selection frequency and calibration curves across the bootstrap resamples.

RESULTS

One hundred ninety-five patients were included. Median OS = 13 (95% CI: 12-14) months. Twelve to fourteen unique MRI protocols were used per MRI sequence. HM and WS produced the highest relative increase in model discrimination, explained variation and model fit but IST choice did not greatly impact on stability, nor calibration. Larger ComBat batches improved discrimination, model fit, and explained variation but higher MBS (reduced sample size) reduced stability (across all performance metrics) and reduced calibration accuracy.

CONCLUSION

Heterogenous, real-world GBM data poses a challenge to the reproducibility of radiomics. ComBat generally improved model performance as MBS increased but reduced stability and calibration. HM and WS tended to improve model performance.

KEY POINTS

Question ComBat harmonisation of RFs and intensity standardisation of MRI have not been thoroughly evaluated in multicentre, heterogeneous GBM data. Findings The addition of ComBat and ISTs can improve discrimination, relative model fit, and explained variance but degrades the calibration and stability of survival models. Clinical relevance Radiomics risk prediction models in real-world, multicentre contexts could be improved by ComBat and ISTs, however, this degrades calibration and prediction stability and this must be thoroughly investigated before patients can be accurately separated into different risk groups.

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

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

Mitigating Interobserver Variability in Radiomics with ComBat: A Feasibility Study

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

PET radiomics in lung cancer: advances and translational challenges

Radiomics is an emerging field of medical imaging that aims at improving the accuracy of diagnosis, prognosis, treatment planning and monitoring non-invasively through the automated or semi-automated quantitative analysis of high-dimensional image features. Specifically in the field of nuclear medicine, radiomics utilizes imaging methods such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) to evaluate biomarkers related to metabolism, blood flow, cellular activity and some biological pathways. Lung cancer ranks among the leading causes of cancer-related deaths globally, and radiomics analysis has shown great potential in guiding individualized therapy, assessing treatment response, and predicting clinical outcomes. In this review, we summarize the current state-of-the-art radiomics progress in lung cancer, highlighting the potential benefits and existing limitations of this approach. The radiomics workflow was introduced first including image acquisition, segmentation, feature extraction, and model building. Then the published literatures were described about radiomics-based prediction models for lung cancer diagnosis, differentiation, prognosis and efficacy evaluation. Finally, we discuss current challenges and provide insights into future directions and potential opportunities for integrating radiomics into routine clinical practice.

Habitat Imaging With Tumoral and Peritumoral Radiomics for Prediction of Lung Adenocarcinoma Invasiveness on Preoperative Chest CT: A Multicenter Study

BACKGROUND. Tumor growth processes result in spatial heterogeneity, with the development of tumor subregions (i.e., habitats) having unique biologic characteristics. OBJECTIVE. The purpose of our study was to develop and validate a habitat model combining tumor and peritumoral radiomic features on chest CT for predicting invasiveness of lung adenocarcinoma. METHODS. This retrospective study included 1156 patients (mean age, 57.5 years; 464 men, 692 women), from three centers and a public dataset, who underwent chest CT before lung adenocarcinoma resection (variable date ranges across datasets). Patients from one center formed training (n = 500) and validation (n = 215) sets; patients from the other sources formed three external test sets (n = 249, 113, 79). For each patient, a single nodule was manually segmented on chest CT. The nodule segmentation was combined with an automatically generated 4-mm peritumoral region into a whole-volume volume of interest (VOI). A gaussian mixture model (GMM) identified voxel clusters with similar first-order energy across patients. GMM results were used to divide each patient's whole-volume VOI into multiple habitats, which were defined consistently across patients. Radiomic features were extracted from each habitat. After feature selection, a habitat model was developed for predicting invasiveness, with the use of pathologic assessment as a reference. An integrated model was constructed, combining features extracted from habitats and whole-volume VOIs. Model performance was evaluated, including in subgroups based on nodule density (pure ground-glass, part-solid, and solid). The code for habitat imaging and model construction is publicly available (https://github.com/Shangyoulan/Habitat/). RESULTS. Invasive cancer was diagnosed in 626 of 1156 patients. GMM identified four as the optimal number of voxel clusters and thus of per-patient tumor habitats. The habitat model had an AUC of 0.932 in the validation set and 0.881, 0.880, and 0.764 in the three external test sets. The integrated model had an AUC of 0.947 in the validation set and 0.936, 0.908, and 0.800 in the three external test sets. In the three external test sets combined, across nodule densities, AUCs for the habitat model were 0.836-0.869 and for the integrated model were 0.846-0.917. CONCLUSION. Habitat imaging combining tumoral and peritumoral radiomic features could help predict lung adenocarcinoma invasiveness. Prediction is improved when combining information on tumor subregions and the tumor overall. CLINICAL IMPACT. The findings may aid personalized preoperative assessments to guide clinical decision-making in lung adenocarcinoma.

Deep Learning for MRI Segmentation and Molecular Subtyping in Glioblastoma: Critical Aspects from an Emerging Field

Deep learning (DL) has been applied to glioblastoma (GBM) magnetic resonance imaging (MRI) assessment for tumor segmentation and inference of molecular, diagnostic, and prognostic information. We comprehensively overviewed the currently available DL applications, critically examining the limitations that hinder their broader adoption in clinical practice and molecular research. Technical limitations to the routine application of DL include the qualitative heterogeneity of MRI, related to different machinery and protocols, and the absence of informative sequences, possibly compensated by artificial image synthesis. Moreover, taking advantage from the available benchmarks of MRI, algorithms should be trained on large amounts of data. Additionally, the segmentation of postoperative imaging should be further addressed to limit the inaccuracies previously observed for this task. Indeed, molecular information has been promisingly integrated in the most recent DL tools, providing useful prognostic and therapeutic information. Finally, ethical concerns should be carefully addressed and standardized to allow for data protection. DL has provided reliable results for GBM assessment concerning MRI analysis and segmentation, but the routine clinical application is still limited. The current limitations could be prospectively addressed, giving particular attention to data collection, introducing new technical advancements, and carefully regulating ethical issues.

Impact of harmonization on the reproducibility of MRI radiomic features when using different scanners, acquisition parameters, and image pre-processing techniques: a phantom study

This study investigated the impact of ComBat harmonization on the reproducibility of radiomic features extracted from magnetic resonance images (MRI) acquired on different scanners, using various data acquisition parameters and multiple image pre-processing techniques using a dedicated MRI phantom. Four scanners were used to acquire an MRI of a nonanatomic phantom as part of the TCIA RIDER database. In fast spin-echo inversion recovery (IR) sequences, several inversion durations were employed, including 50, 100, 250, 500, 750, 1000, 1500, 2000, 2500, and 3000 ms. In addition, a 3D fast spoiled gradient recalled echo (FSPGR) sequence was used to investigate several flip angles (FA): 2, 5, 10, 15, 20, 25, and 30 degrees. Nineteen phantom compartments were manually segmented. Different approaches were used to pre-process each image: Bin discretization, Wavelet filter, Laplacian of Gaussian, logarithm, square, square root, and gradient. Overall, 92 first-, second-, and higher-order statistical radiomic features were extracted. ComBat harmonization was also applied to the extracted radiomic features. Finally, the Intraclass Correlation Coefficient (ICC) and Kruskal-Wallis's (KW) tests were implemented to assess the robustness of radiomic features. The number of non-significant features in the KW test ranged between 0-5 and 29-74 for various scanners, 31-91 and 37-92 for three times tests, 0-33 to 34-90 for FAs, and 3-68 to 65-89 for IRs before and after ComBat harmonization, with different image pre-processing techniques, respectively. The number of features with ICC over 90% ranged between 0-8 and 6-60 for various scanners, 11-75 and 17-80 for three times tests, 3-83 to 9-84 for FAs, and 3-49 to 3-63 for IRs before and after ComBat harmonization, with different image pre-processing techniques, respectively. The use of various scanners, IRs, and FAs has a great impact on radiomic features. However, the majority of scanner-robust features is also robust to IR and FA. Among the effective parameters in MR images, several tests in one scanner have a negligible impact on radiomic features. Different scanners and acquisition parameters using various image pre-processing might affect radiomic features to a large extent. ComBat harmonization might significantly impact the reproducibility of MRI radiomic features.

Review on radiomic analysis in 18F-fluorodeoxyglucose positron emission tomography for prediction of melanoma outcomes

Over the past decade, several strategies have revolutionized the clinical management of patients with cutaneous melanoma (CM), including immunotherapy and targeted tyrosine kinase inhibitor (TKI)-based therapies. Indeed, immune checkpoint inhibitors (ICIs), alone or in combination, represent the standard of care for patients with advanced disease without an actionable mutation. Notably BRAF combined with MEK inhibitors represent the therapeutic standard for disease disclosing BRAF mutation. At the same time, FDG PET/CT has become part of the routine staging and evaluation of patients with cutaneous melanoma. There is growing interest in using FDG PET/CT measurements to predict response to ICI therapy and/or target therapy. While semiquantitative values such as standardized uptake value (SUV) are limited for predicting outcome, new measures including tumor metabolic volume, total lesion glycolysis and radiomics seem promising as potential imaging biomarkers for nuclear medicine. The aim of this review, prepared by an interdisciplinary group of experts, is to take stock of the current literature on radiomics approaches that could improve outcomes in CM.

Enhancing predictability of IDH mutation status in glioma patients at initial diagnosis: a comparative analysis of radiomics from MRI, [18F]FET PET, and TSPO PET

PURPOSE

According to the World Health Organization classification for tumors of the central nervous system, mutation status of the isocitrate dehydrogenase (IDH) genes has become a major diagnostic discriminator for gliomas. Therefore, imaging-based prediction of IDH mutation status is of high interest for individual patient management. We compared and evaluated the diagnostic value of radiomics derived from dual positron emission tomography (PET) and magnetic resonance imaging (MRI) data to predict the IDH mutation status non-invasively.

METHODS

Eighty-seven glioma patients at initial diagnosis who underwent PET targeting the translocator protein (TSPO) using [18F]GE-180, dynamic amino acid PET using [18F]FET, and T1-/T2-weighted MRI scans were examined. In addition to calculating tumor-to-background ratio (TBR) images for all modalities, parametric images quantifying dynamic [18F]FET PET information were generated. Radiomic features were extracted from TBR and parametric images. The area under the receiver operating characteristic curve (AUC) was employed to assess the performance of logistic regression (LR) classifiers. To report robust estimates, nested cross-validation with five folds and 50 repeats was applied.

RESULTS

TBRGE-180 features extracted from TSPO-positive volumes had the highest predictive power among TBR images (AUC 0.88, with age as co-factor 0.94). Dynamic [18F]FET PET reached a similarly high performance (0.94, with age 0.96). The highest LR coefficients in multimodal analyses included TBRGE-180 features, parameters from kinetic and early static [18F]FET PET images, age, and the features from TBRT2 images such as the kurtosis (0.97).

CONCLUSION

The findings suggest that incorporating TBRGE-180 features along with kinetic information from dynamic [18F]FET PET, kurtosis from TBRT2, and age can yield very high predictability of IDH mutation status, thus potentially improving early patient management.

Contrast Enhanced CT Radiogenomics in a Retrospective NSCLC Cohort: Models, Attempted Validation of a Published Model and the Relevance of the Clinical Context

RATIONALE AND OBJECTIVE

To develop a radiogenomic predictive model for non-small cell lung cancer (NSCLC) patients studied through contrast enhanced chest computed tomography (CE-CT) targeting the most frequent gene alterations. M&M: A retrospective study of patients with NSCLC imaged with CE-CT before treatment and had their tumor genomics sequenced at our institution was performed. Data was gathered from their imaging studies, their electronic medical records and a web-based database search (cBioPortal.ca). All of the patient data was tabulated for analysis. Two predictive models (M1 & M2) were created using different approaches and a third model was extracted from the literature to also be tested in our population.

RESULTS

Out of 157 patients, eighty were male (51%) and 124 (79%) had a history of smoking. The three most prevalent genes were KRAS, TP53 and EGFR. The M1 radiomics-only model median AUC were 0.61 (TP53), 0.53 (KRAS) and 0.64 (EGFR) and for M1 radiomics + clinical were 0.61 (TP53), 0.61 (KRAS) and 0.80 (EGFR). The M2 radiomics-only model median AUC were 0.63 (TP53), 0.60 (KRAS) and 0.65 (EGFR) and for M2 radiomics + clinical were 0.64 (TP53), 0.62 (KRAS) and 0.81 (EGFR). The external EGFR radiomic model showed an AUC of 0.69 and 0.86 for the radiomics-only and combined radiomics + clinical respectively.

CONCLUSION

Our study was able to provide robust predictive radiomics model evaluation for the detection of TP53, KRAS and EGFR. We also compared our performance with an already published model and observed how impactful clinical variables can be on models' performance.

CLINICAL RELEVANCE STATEMENT

Identifying tumor mutations in patients that can't undergo biopsy is critical for their outcomes.

KEYPOINTS

• Tumor genomic profiling is critical for treatment selection • CE-CT radiomics produce robust predictive models comparable to those already published • Clinical variables should be considered/included in predictive models.

Multiparametric MRI-based radiomic model for predicting lymph node metastasis after neoadjuvant chemoradiotherapy in locally advanced rectal cancer

OBJECTIVES

To construct and validate multiparametric MR-based radiomic models based on primary tumors for predicting lymph node metastasis (LNM) following neoadjuvant chemoradiotherapy (nCRT) in locally advanced rectal cancer (LARC) patients.

METHODS

A total of 150 LARC patients from two independent centers were enrolled. The training cohort comprised 100 patients from center A. Fifty patients from center B were included in the external validation cohort. Radiomic features were extracted from the manually segmented volume of interests of the primary tumor before and after nCRT. Feature selection was performed using multivariate logistic regression analysis. The clinical risk factors were selected via the least absolute shrinkage and selection operator method. The radiologist's assessment of LNM was performed. Eight models were constructed using random forest classifiers, including four single-sequence models, three combined-sequence models, and a clinical model. The models' discriminative performance was assessed via receiver operating characteristic curve analysis quantified by the area under the curve (AUC).

RESULTS

The AUCs of the radiologist's assessment, the clinical model, and the single-sequence models ranged from 0.556 to 0.756 in the external validation cohort. Among the single-sequence models, modelpost_DWI exhibited superior predictive power, with an AUC of 0.756 in the external validation set. In combined-sequence models, modelpre_T2_DWI_post had the best diagnostic performance in predicting LNM after nCRT, with a significantly higher AUC (0.831) than those of the clinical model, modelpre_T2_DWI, and the single-sequence models (all p < 0.05).

CONCLUSIONS

A multiparametric model that incorporates MR radiomic features before and after nCRT is optimal for predicting LNM after nCRT in LARC.

CRITICAL RELEVANCE STATEMENT

This study enrolled 150 LARC patients from two independent centers and constructed multiparametric MR-based radiomic models based on primary tumors for predicting LNM following nCRT, which aims to guide therapeutic decisions and predict prognosis for LARC patients.

KEY POINTS

The biological characteristics of primary tumors and metastatic LNs are similar in rectal cancer. Radiomics features and clinical data before and after nCRT provide complementary tumor information. Preoperative prediction of LN status after nCRT contributes to clinical decision-making.

Multivariate testing and effect size measures for batch effect evaluation in radiomic features

While precision medicine applications of radiomics analysis are promising, differences in image acquisition can cause "batch effects" that reduce reproducibility and affect downstream predictive analyses. Harmonization methods such as ComBat have been developed to correct these effects, but evaluation methods for quantifying batch effects are inconsistent. In this study, we propose the use of the multivariate statistical test PERMANOVA and the Robust Effect Size Index (RESI) to better quantify and characterize batch effects in radiomics data. We evaluate these methods in both simulated and real radiomics features extracted from full-field digital mammography (FFDM) data. PERMANOVA demonstrated higher power than standard univariate statistical testing, and RESI was able to interpretably quantify the effect size of site at extremely large sample sizes. These methods show promise as more powerful and interpretable methods for the detection and quantification of batch effects in radiomics studies.

The Effect of Image Resampling on the Performance of Radiomics-Based Artificial Intelligence in Multicenter Prostate MRI

BACKGROUND

Single center MRI radiomics models are sensitive to data heterogeneity, limiting the diagnostic capabilities of current prostate cancer (PCa) radiomics models.

PURPOSE

To study the impact of image resampling on the diagnostic performance of radiomics in a multicenter prostate MRI setting.

STUDY TYPE

Retrospective.

POPULATION

Nine hundred thirty patients (nine centers, two vendors) with 737 eligible PCa lesions, randomly split into training (70%, N = 500), validation (10%, N = 89), and a held-out test set (20%, N = 148).

FIELD STRENGTH/SEQUENCE

1.5T and 3T scanners/T2-weighted imaging (T2W), diffusion-weighted imaging (DWI), and apparent diffusion coefficient maps.

ASSESSMENT

A total of 48 normalized radiomics datasets were created using various resampling methods, including different target resolutions (T2W: 0.35, 0.5, and 0.8 mm; DWI: 1.37, 2, and 2.5 mm), dimensionalities (2D/3D) and interpolation techniques (nearest neighbor, linear, Bspline and Blackman windowed-sinc). Each of the datasets was used to train a radiomics model to detect clinically relevant PCa (International Society of Urological Pathology grade ≥ 2). Baseline models were constructed using 2D and 3D datasets without image resampling. The resampling configurations with highest validation performance were evaluated in the test dataset and compared to the baseline models.

STATISTICAL TESTS

Area under the curve (AUC), DeLong test. The significance level used was 0.05.

RESULTS

The best 2D resampling model (T2W: Bspline and 0.5 mm resolution, DWI: nearest neighbor and 2 mm resolution) significantly outperformed the 2D baseline (AUC: 0.77 vs. 0.64). The best 3D resampling model (T2W: linear and 0.8 mm resolution, DWI: nearest neighbor and 2.5 mm resolution) significantly outperformed the 3D baseline (AUC: 0.79 vs. 0.67).

DATA CONCLUSION

Image resampling has a significant effect on the performance of multicenter radiomics artificial intelligence in prostate MRI. The recommended 2D resampling configuration is isotropic resampling with T2W at 0.5 mm (Bspline interpolation) and DWI at 2 mm (nearest neighbor interpolation). For the 3D radiomics, this work recommends isotropic resampling with T2W at 0.8 mm (linear interpolation) and DWI at 2.5 mm (nearest neighbor interpolation).

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Magnetic resonance imaging radiomic features stability in brain metastases: Impact of image preprocessing, image-, and feature-level harmonization

Background and purpose

Magnetic resonance imaging (MRI) scans are highly sensitive to acquisition and reconstruction parameters which affect feature stability and model generalizability in radiomic research. This work aims to investigate the effect of image pre-processing and harmonization methods on the stability of brain MRI radiomic features and the prediction performance of radiomic models in patients with brain metastases (BMs).

Materials and methods

Two T1 contrast enhanced brain MRI data-sets were used in this study. The first contained 25 BMs patients with scans at two different time points and was used for features stability analysis. The effect of gray level discretization (GLD), intensity normalization (Z-score, Nyul, WhiteStripe, and in house-developed method named N-Peaks), and ComBat harmonization on features stability was investigated and features with intraclass correlation coefficient >0.8 were considered as stable. The second data-set containing 64 BMs patients was used for a classification task to investigate the informativeness of stable features and the effects of harmonization methods on radiomic model performance.

Results

Applying fixed bin number (FBN) GLD, resulted in higher number of stable features compare to fixed bin size (FBS) discretization (10 ± 5.5 % higher). `Harmonization in feature domain improved the stability for non-normalized and normalized images with Z-score and WhiteStripe methods. For the classification task, keeping the stable features resulted in good performance only for normalized images with N-Peaks along with FBS discretization.

Conclusions

To develop a robust MRI based radiomic model we recommend using an intensity normalization method based on a reference tissue (e.g N-Peaks) and then using FBS discretization.

State of the art: radiomics and radiomics-related artificial intelligence on the road to clinical translation

Radiomics and artificial intelligence carry the promise of increased precision in oncologic imaging assessments due to the ability of harnessing thousands of occult digital imaging features embedded in conventional medical imaging data. While powerful, these technologies suffer from a number of sources of variability that currently impede clinical translation. In order to overcome this impediment, there is a need to control for these sources of variability through harmonization of imaging data acquisition across institutions, construction of standardized imaging protocols that maximize the acquisition of these features, harmonization of post-processing techniques, and big data resources to properly power studies for hypothesis testing. For this to be accomplished, it will be critical to have multidisciplinary and multi-institutional collaboration.

Radiomics Harmonization in Ultrasound Images for Cervical Cancer Lymph Node Metastasis Prediction Using Cycle-GAN

Background: Ultrasound (US) based radiomics is susceptible to variations in scanners, sonographers. Objective: To retrospectively investigate the feasibility of an adapted cycle generative adversarial networks (CycleGAN) in the style transfer to improve US based radiomics in the prediction of lymph node metastasis (LNM) with images from multiple scanners for patients with early cervical cancer (ECC). Methods: The CycleGAN was firstly trained to transfer paired US phantom images from one US device to another one; the model was then further trained and tested with clinical US images of ECC by transferring images from four US devices to one specific device; finally, the adapted model was tested with its effects on the radiomics feature harmonization and accuracy of LNM prediction in US based radiomics for ECC patients. Results: Phantom study demonstrated an increased radiomics harmonization using CycleGAN with an average Pearson correlation coefficient of 0.60 and 0.81 for radiomics features extracted from original and generated images in correlation with the target phantom images, respectively. Additionally, the image quality metric Peak Signal-to-Noise Ratio (PSNR) was increased from 11.18 for the original images to 15.45 for the generated image. Clinical US images of 169 ECC patients were enrolled for style transfer model training and validation. The area under curve (AUC) of LNM prediction radiomics models with features extracted from generated images of different style transfer models ranged from 0.73 to 0.85. The AUC was improved from 0.78 with features extracted from original images to 0.85 with style transferred images. Conclusions: The adapted CycleGAN network is able to increase the radiomics feature harmonization for images from different ultrasound equipment based on image domain and improve the LNM prediction accuracy for ECC.

Standardized brain tumor imaging protocols for clinical trials: current recommendations and tips for integration

Standardized MRI acquisition protocols are crucial for reducing the measurement and interpretation variability associated with response assessment in brain tumor clinical trials. The main challenge is that standardized protocols should ensure high image quality while maximizing the number of institutions meeting the acquisition requirements. In recent years, extensive effort has been made by consensus groups to propose different "ideal" and "minimum requirements" brain tumor imaging protocols (BTIPs) for gliomas, brain metastases (BM), and primary central nervous system lymphomas (PCSNL). In clinical practice, BTIPs for clinical trials can be easily integrated with additional MRI sequences that may be desired for clinical patient management at individual sites. In this review, we summarize the general concepts behind the choice and timing of sequences included in the current recommended BTIPs, we provide a comparative overview, and discuss tips and caveats to integrate additional clinical or research sequences while preserving the recommended BTIPs. Finally, we also reflect on potential future directions for brain tumor imaging in clinical trials.

Enhancing Interoperability and Harmonisation of Nuclear Medicine Image Data and Associated Clinical Data

Nuclear imaging techniques such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) in combination with computed tomography (CT) are established imaging modalities in clinical practice, particularly for oncological problems. Due to a multitude of manufacturers, different measurement protocols, local demographic or clinical workflow variations as well as various available reconstruction and analysis software, very heterogeneous datasets are generated. This review article examines the current state of interoperability and harmonisation of image data and related clinical data in the field of nuclear medicine. Various approaches and standards to improve data compatibility and integration are discussed. These include, for example, structured clinical history, standardisation of image acquisition and reconstruction as well as standardised preparation of image data for evaluation. Approaches to improve data acquisition, storage and analysis will be presented. Furthermore, approaches are presented to prepare the datasets in such a way that they become usable for projects applying artificial intelligence (AI) (machine learning, deep learning, etc.). This review article concludes with an outlook on future developments and trends related to AI in nuclear medicine, including a brief research of commercial solutions.

Computed Tomography-derived intratumoral and peritumoral radiomics in predicting EGFR mutation in lung adenocarcinoma

OBJECTIVE

To investigate the value of Computed Tomography (CT) radiomics derived from different peritumoral volumes of interest (VOIs) in predicting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients.

MATERIALS AND METHODS

A retrospective cohort of 779 patients who had pathologically confirmed lung adenocarcinoma were enrolled. 640 patients were randomly divided into a training set, a validation set, and an internal testing set (3:1:1), and the remaining 139 patients were defined as an external testing set. The intratumoral VOI (VOI_I) was manually delineated on the thin-slice CT images, and seven peritumoral VOIs (VOI_P) were automatically generated with 1, 2, 3, 4, 5, 10, and 15 mm expansion along the VOI_I. 1454 radiomic features were extracted from each VOI. The t-test, the least absolute shrinkage and selection operator (LASSO), and the minimum redundancy maximum relevance (mRMR) algorithm were used for feature selection, followed by the construction of radiomics models (VOI_I model, VOI_P model and combined model). The performance of the models were evaluated by the area under the curve (AUC).

RESULTS

399 patients were classified as EGFR mutant (EGFR+), while 380 were wild-type (EGFR-). In the training and validation sets, internal and external testing sets, VOI4 (intratumoral and peritumoral 4 mm) model achieved the best predictive performance, with AUCs of 0.877, 0.727, and 0.701, respectively, outperforming the VOI_I model (AUCs of 0.728, 0.698, and 0.653, respectively).

CONCLUSIONS

Radiomics extracted from peritumoral region can add extra value in predicting EGFR mutation status of lung adenocarcinoma patients, with the optimal peritumoral range of 4 mm.

Optimal batch determination for improved harmonization and prognostication of multi-center PET/CT radiomics feature in head and neck cancer

Objective. To determine the optimal approach for identifying and mitigating batch effects in PET/CT radiomics features, and further improve the prognosis of patients with head and neck cancer (HNC), this study investigated the performance of three batch harmonization methods.Approach. Unsupervised harmonization identified the batch labels by K-means clustering. Supervised harmonization regarding the image acquisition factors (center, manufacturer, scanner, filter kernel) as known/given batch labels, and Combat harmonization was then implemented separately and sequentially based on the batch labels, i.e. harmonizing features among batches determined by each factor individually or harmonizing features among batches determined by multiple factors successively. Extensive experiments were conducted to predict overall survival (OS) on public PET/CT datasets that contain 800 patients from 9 centers.Main results. In the external validation cohort, results show that compared to original models without harmonization, Combat harmonization would be beneficial in OS prediction with C-index of 0.687-0.740 versus 0.684-0.767. Supervised harmonization slightly outperformed unsupervised harmonization in all models (C-index: 0.692-0.767 versus 0.684-0.750). Separate harmonization outperformed sequential harmonization in CT_m+clinic and CT_cm+clinic models with C-index of 0.752 and 0.722, respectively, while sequential harmonization involved clinical features in PET_rs+clinic model further improving the performance and achieving the highest C-index of 0.767.Significance. Optimal batch determination especially sequential harmonization for Combat holds the potential to improve the prognostic power of radiomics model in multi-center HNC dataset with PET/CT imaging.

Development and validation of a contrast-enhanced CT-based radiomics nomogram for differentiating mass-like thymic hyperplasia and low-risk thymoma

PURPOSE

To explore the efficiency of a contrast-enhanced CT-based radiomics nomogram integrated with radiomics signature and clinically independent predictors to distinguish mass-like thymic hyperplasia (ml-TH) from low-risk thymoma (LRT) preoperatively.

METHODS

135 Patients with histopathology confirmed ml-TH (n = 65) and LRT (n = 70) were randomly divided into training set (n = 94) and validation set (n = 41) at a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) algorithm was used to obtain the optimal features. Based on the selected features, four machine learning models, support vector machine (SVM), logistic regression (LR), extreme gradient boosting (XGBOOST), and random forest (RF) were constructed. Multivariate logistic regression was used to establish a radiomics nomogram containing clinically independent predictors and radiomics signature. Receiver operating characteristic (ROC), DeLong test, and calibration curves were used to detect the performance of the radiomics nomogram in training set and validation set.

RESULTS

In the validation set, the area under the curve (AUC) value of LR (0.857; 95% CI: 0.741, 0.973) was the highest of the four machine learning models. Radiomics nomogram containing radiomics signature and clinically independent predictors (including age, shape, and net enhancement degree) had better calibration and identification in the training set (AUC: 0.959; 95% CI: 0.922, 0.996) and validation set (AUC: 0.895; 95% CI: 0.795, 0.996).

CONCLUSION

We constructed a contrast-enhanced CT-based radiomics nomogram containing clinically independent predictors and radiomics signature as a noninvasive preoperative prediction method to distinguish ml-TH from LRT. The radiomics nomogram we constructed has potential for preoperative clinical decision making.

Radiomics and machine learning analysis by computed tomography and magnetic resonance imaging in colorectal liver metastases prognostic assessment

OBJECTIVE

The aim of this study was the evaluation radiomics analysis efficacy performed using computed tomography (CT) and magnetic resonance imaging in the prediction of colorectal liver metastases patterns linked to patient prognosis: tumor growth front; grade; tumor budding; mucinous type. Moreover, the prediction of liver recurrence was also evaluated.

METHODS

The retrospective study included an internal and validation dataset; the first was composed by 119 liver metastases from 49 patients while the second consisted to 28 patients with single lesion. Radiomic features were extracted using PyRadiomics. Univariate and multivariate approaches including machine learning algorithms were employed.

RESULTS

The best predictor to identify tumor growth was the Wavelet_HLH_glcm_MaximumProbability with an accuracy of 84% and to detect recurrence the best predictor was wavelet_HLH_ngtdm_Complexity with an accuracy of 90%, both extracted by T1-weigthed arterial phase sequence. The best predictor to detect tumor budding was the wavelet_LLH_glcm_Imc1 with an accuracy of 88% and to identify mucinous type was wavelet_LLH_glcm_JointEntropy with an accuracy of 92%, both calculated on T2-weigthed sequence. An increase statistically significant of accuracy (90%) was obtained using a linear weighted combination of 15 predictors extracted by T2-weigthed images to detect tumor front growth. An increase statistically significant of accuracy at 93% was obtained using a linear weighted combination of 11 predictors by the T1-weigthed arterial phase sequence to classify tumor budding. An increase statistically significant of accuracy at 97% was obtained using a linear weighted combination of 16 predictors extracted on CT to detect recurrence. An increase statistically significant of accuracy was obtained in the tumor budding identification considering a K-nearest neighbors and the 11 significant features extracted T1-weigthed arterial phase sequence.

CONCLUSIONS

The results confirmed the Radiomics capacity to recognize clinical and histopathological prognostic features that should influence the choice of treatments in colorectal liver metastases patients to obtain a more personalized therapy.

Dual-Centre Harmonised Multimodal Positron Emission Tomography/Computed Tomography Image Radiomic Features and Machine Learning Algorithms for Non-small Cell Lung Cancer Histopathological Subtype Phenotype Decoding

AIMS

We aimed to build radiomic models for classifying non-small cell lung cancer (NSCLC) histopathological subtypes through a dual-centre dataset and comprehensively evaluate the effect of ComBat harmonisation on the performance of single- and multimodality radiomic models.

MATERIALS AND METHODS

A public dataset of NSCLC patients from two independent centres was used. Two image fusion methods, namely guided filtering-based fusion and image fusion based on visual saliency map and weighted least square optimisation, were used. Radiomic features were extracted from each scan, including first-order, texture and moment-invariant features. Subsequently, ComBat harmonisation was applied to the extracted features from computed tomography (CT), positron emission tomography (PET) and fused images to correct the centre effect. For feature selection, least absolute shrinkage and selection operator (Lasso) and recursive feature elimination (RFE) were investigated. For machine learning, logistic regression (LR), support vector machine (SVM) and AdaBoost were evaluated for classifying NSCLC subtypes. Training and evaluation of the models were carried out in a robust framework to offset plausible errors and performance was reported using area under the curve, balanced accuracy, sensitivity and specificity before and after harmonisation. N-way ANOVA was used to assess the effect of different factors on the performance of the models.

RESULTS

Support vector machine fed with selected features by recursive feature elimination from a harmonised PET feature set achieved the highest performance (area under the curve = 0.82) in classifying NSCLC histopathological subtypes. Although the performance of the models did not significantly improve for CT images after harmonisation, the performance of PET and guided filtering-based fusion feature signatures significantly improved for almost all models. Although the selection of the image modality and feature selection methods was effective on the performance of the model (ANOVA P-values <0.001), machine learning and harmonisation did not change the performance significantly (ANOVA P-values = 0.839 and 0.292, respectively).

CONCLUSION

This study confirmed the potential of radiomic analysis on PET, CT and hybrid images for histopathological classification of NSCLC subtypes.

Dual adversarial deconfounding autoencoder for joint batch-effects removal from multi-center and multi-scanner radiomics data

Medical imaging represents the primary tool for investigating and monitoring several diseases, including cancer. The advances in quantitative image analysis have developed towards the extraction of biomarkers able to support clinical decisions. To produce robust results, multi-center studies are often set up. However, the imaging information must be denoised from confounding factors-known as batch-effect-like scanner-specific and center-specific influences. Moreover, in non-solid cancers, like lymphomas, effective biomarkers require an imaging-based representation of the disease that accounts for its multi-site spreading over the patient's body. In this work, we address the dual-factor deconfusion problem and we propose a deconfusion algorithm to harmonize the imaging information of patients affected by Hodgkin Lymphoma in a multi-center setting. We show that the proposed model successfully denoises data from domain-specific variability (p-value < 0.001) while it coherently preserves the spatial relationship between imaging descriptions of peer lesions (p-value = 0), which is a strong prognostic biomarker for tumor heterogeneity assessment. This harmonization step allows to significantly improve the performance in prognostic models with respect to state-of-the-art methods, enabling building exhaustive patient representations and delivering more accurate analyses (p-values < 0.001 in training, p-values < 0.05 in testing). This work lays the groundwork for performing large-scale and reproducible analyses on multi-center data that are urgently needed to convey the translation of imaging-based biomarkers into the clinical practice as effective prognostic tools. The code is available on GitHub at this https://github.com/LaraCavinato/Dual-ADAE .

Comparative analysis of batch correction methods for FDG PET/CT using metabolic radiogenomic data of lung cancer patients

In radiomics research, the issue of different instruments being used is significant. In this study, we compared three correction methods to reduce the batch effects in radiogenomic data from fluorodeoxyglucose (FDG) PET/CT images of lung cancer patients. Texture features of the FDG PET/CT images and genomic data were retrospectively obtained. The features were corrected with different methods: phantom correction, ComBat method, and Limma method. Batch effects were estimated using three analytic tools: principal component analysis (PCA), the k-nearest neighbor batch effect test (kBET), and the silhouette score. Finally, the associations of features and gene mutations were compared between each correction method. Although the kBET rejection rate and silhouette score were lower in the phantom-corrected data than in the uncorrected data, a PCA plot showed a similar variance. ComBat and Limma methods provided correction with low batch effects, and there was no significant difference in the results of the two methods. In ComBat- and Limma-corrected data, more texture features exhibited a significant association with the TP53 mutation than in those in the phantom-corrected data. This study suggests that correction with ComBat or Limma methods can be more effective or equally as effective as the phantom method in reducing batch effects.

Prediction of synchronous distant metastasis of primary pancreatic ductal adenocarcinoma using the radiomics features derived from 18F-FDG PET and MRI

AIM

To explore the potential of the joint radiomics analysis of positron-emission tomography (PET) and magnetic resonance imaging (MRI) of primary tumours for predicting the risk of synchronous distant metastasis (SDM) in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS

18F-FDG PET and MRI images of PDAC patients from January 2011 to December 2020 were collected retrospectively. Patients (n=66) who received 18F-FDG PET/CT and MRI were included in a development group. Patients (n=25) scanned with hybrid PET/MRI were incorporated in an external test group. A radiomics signature was constructed using the least absolute shrinkage and selection operator algorithm to select PET-MRI radiomics features of primary PDAC tumours. A radiomics nomogram was developed by combining the radiomics signature and important clinical indicators using univariate and multivariate analysis to assess patients' metastasis risk. The nomogram was verified with the employment of an external test group.

RESULTS

Regarding the development cohort, the radiomics nomogram was found to be better for predicting the risk of distant metastasis (area under the curve [AUC]: 0.93, sensitivity: 87%, specificity: 85%) than the clinical model (AUC: 0.70, p<0.001; sensitivity:70%, specificity: 65%) and the radiomics signature (AUC: 0.89, p>0.05; sensitivity: 65%, specificity:100%). Concerning the external test cohort, the radiomics nomogram yielded an AUC of 0.85.

CONCLUSION

PET-MRI based radiomics analysis exhibited effective prediction of the risk of SDM for preoperative PDAC patients and may offer complementary information and provide hints for cancer staging.

Prognostic Assessment of Gastropancreatic Neuroendocrine Neoplasm: Prospects and Limits of Radiomics

Neuroendocrine neoplasms (NENs) are a group of lesions originating from cells of the diffuse neuroendocrine system. NENs may involve different sites, including the gastrointestinal tract (GEP-NENs). The incidence and prevalence of GEP-NENs has been constantly rising thanks to the increased diagnostic power of imaging and immuno-histochemistry. Despite the plethora of biochemical markers and imaging techniques, the prognosis and therapeutic choice in GEP-NENs still represents a challenge, mainly due to the great heterogeneity in terms of tumor lesions and clinical behavior. The concept that biomedical images contain information about tissue heterogeneity and pathological processes invisible to the human eye is now well established. From this substrate comes the idea of radiomics. Computational analysis has achieved promising results in several oncological settings, and the use of radiomics in different types of GEP-NENs is growing in the field of research, yet with conflicting results. The aim of this narrative review is to provide a comprehensive update on the role of radiomics on GEP-NEN management, focusing on the main clinical aspects analyzed by most existing reports: predicting tumor grade, distinguishing NET from other tumors, and prognosis assessment.

Radiomic analysis for early differentiation of lung cancer recurrence from fibrosis in patients treated with lung stereotactic ablative radiotherapy

Objective. The development of radiation-induced fibrosis after stereotactic ablative radiotherapy (SABR) can obscure follow-up images and delay detection of a local recurrence in early-stage lung cancer patients. The objective of this study was to develop a radiomics model for computer-assisted detection of local recurrence and fibrosis for an earlier timepoint (<1 year) after the SABR treatment.Approach. This retrospective clinical study included CT images (n= 107) of 66 patients treated with SABR. A z-score normalization technique was used for radiomic feature standardization across scanner protocols. The training set for the radiomics model consisted of CT images (66 patients; 22 recurrences and 44 fibrosis) obtained at 24 months (median) follow-up. The test set included CT-images of 41 patients acquired at 5-12 months follow-up. Combinations of four widely used machine learning techniques (support vector machines, gradient boosting, random forests (RF), and logistic regression) and feature selection methods (Relief feature scoring, maximum relevance minimum redundancy, mutual information maximization, forward feature selection, and LASSO) were investigated. Pyradiomics was used to extract 106 radiomic features from the CT-images for feature selection and classification.Main results. An RF + LASSO model scored the highest in terms of AUC (0.87) and obtained a sensitivity of 75% and a specificity of 88% in identifying a local recurrence in the test set. In the training set, 86% accuracy was achieved using five-fold cross-validation. Delong's test indicated that AUC achieved by the RF+LASSO is significantly better than 11 other machine learning models presented here. The top three radiomic features: interquartile range (first order), Cluster Prominence (GLCM), and Autocorrelation (GLCM), were revealed as differentiating a recurrence from fibrosis with this model.Significance. The radiomics model selected, out of multiple machine learning and feature selection algorithms, was able to differentiate a recurrence from fibrosis in earlier follow-up CT-images with a high specificity rate and satisfactory sensitivity performance.

Generalization optimizing machine learning to improve CT scan radiomics and assess immune checkpoint inhibitors' response in non-small cell lung cancer: a multicenter cohort study

Background

Recent developments in artificial intelligence suggest that radiomics may represent a promising non-invasive biomarker to predict response to immune checkpoint inhibitors (ICIs). Nevertheless, validation of radiomics algorithms in independent cohorts remains a challenge due to variations in image acquisition and reconstruction. Using radiomics, we investigated the importance of scan normalization as part of a broader machine learning framework to enable model external generalizability to predict ICI response in non-small cell lung cancer (NSCLC) patients across different centers.

Methods

Radiomics features were extracted and compared from 642 advanced NSCLC patients on pre-ICI scans using established open-source PyRadiomics and a proprietary DeepRadiomics deep learning technology. The population was separated into two groups: a discovery cohort of 512 NSCLC patients from three academic centers and a validation cohort that included 130 NSCLC patients from a fourth center. We harmonized images to account for variations in reconstruction kernel, slice thicknesses, and device manufacturers. Multivariable models, evaluated using cross-validation, were used to estimate the predictive value of clinical variables, PD-L1 expression, and PyRadiomics or DeepRadiomics for progression-free survival at 6 months (PFS-6).

Results

The best prognostic factor for PFS-6, excluding radiomics features, was obtained with the combination of Clinical + PD-L1 expression (AUC = 0.66 in the discovery and 0.62 in the validation cohort). Without image harmonization, combining Clinical + PyRadiomics or DeepRadiomics delivered an AUC = 0.69 and 0.69, respectively, in the discovery cohort, but dropped to 0.57 and 0.52, in the validation cohort. This lack of generalizability was consistent with observations in principal component analysis clustered by CT scan parameters. Subsequently, image harmonization eliminated these clusters. The combination of Clinical + DeepRadiomics reached an AUC = 0.67 and 0.63 in the discovery and validation cohort, respectively. Conversely, the combination of Clinical + PyRadiomics failed generalizability validations, with AUC = 0.66 and 0.59.

Conclusion

We demonstrated that a risk prediction model combining Clinical + DeepRadiomics was generalizable following CT scan harmonization and machine learning generalization methods. These results had similar performances to routine oncology practice using Clinical + PD-L1. This study supports the strong potential of radiomics as a future non-invasive strategy to predict ICI response in advanced NSCLC.

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

Normalization Strategies in Multi-Center Radiomics Abdominal MRI: Systematic Review and Meta-Analyses

Goal: Artificial intelligence applied to medical image analysis has been extensively used to develop non-invasive diagnostic and prognostic signatures. However, these imaging biomarkers should be largely validated on multi-center datasets to prove their robustness before they can be introduced into clinical practice. The main challenge is represented by the great and unavoidable image variability which is usually addressed using different pre-processing techniques including spatial, intensity and feature normalization. The purpose of this study is to systematically summarize normalization methods and to evaluate their correlation with the radiomics model performances through meta-analyses. This review is carried out according to the PRISMA statement: 4777 papers were collected, but only 74 were included. Two meta-analyses were carried out according to two clinical aims: characterization and prediction of response. Findings of this review demonstrated that there are some commonly used normalization approaches, but not a commonly agreed pipeline that can allow to improve performance and to bridge the gap between bench and bedside.

Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features

OBJECTIVES

To explore an optimal machine learning (ML) model trained on MRI-based radiomic features to differentiate benign from malignant indistinguishable vertebral compression fractures (VCFs).

METHODS

This retrospective study included patients within 6 weeks of back pain (non-traumatic) who underwent MRI and were diagnosed with benign and malignant indistinguishable VCFs. The two cohorts were retrospectively recruited from the Affiliated Hospital of Qingdao University (QUH) and Qinghai Red Cross Hospital (QRCH). Three hundred seventy-six participants from QUH were divided into the training (n = 263) and validation (n = 113) cohort based on the date of MRI examination. One hundred three participants from QRCH were used to evaluate the external generalizability of our prediction models. A total of 1045 radiomic features were extracted from each region of interest (ROI) and used to establish the models. The prediction models were established based on 7 different classifiers.

RESULTS

These models showed favorable efficacy in differentiating benign from malignant indistinguishable VCFs. However, our Gaussian naïve Bayes (GNB) model attained higher AUC and accuracy (0.86, 87.61%) than the other classifiers in validation cohort. It also remains the high accuracy and sensitivity for the external test cohort.

CONCLUSIONS

Our GNB model performed better than the other models in the present study, suggesting that it may be more useful for differentiating indistinguishable benign form malignant VCFs.

KEY POINTS

• The differential diagnosis of benign and malignant indistinguishable VCFs based on MRI is rather difficult for spine surgeons or radiologists. • Our ML models facilitate the differential diagnosis of benign and malignant indistinguishable VCFs with improved diagnostic efficacy. • Our GNB model had the high accuracy and sensitivity for clinical application.

Prognostic value of pre-therapeutic FDG-PET radiomic analysis in gastro-esophageal junction cancer

The main aim of this study was to evaluate the prognostic value of radiomic approach in pre-therapeutic ¹⁸F-fluorodeoxyglucose positron-emission tomography (FDG-PET/CT) in a large cohort of patients with gastro-esophageal junction cancer (GEJC). This was a retrospective monocenter study including 97 consecutive patients with GEJC who underwent a pre-therapeutic FDG-PET and were followed up for 3 years. Standard first-order radiomic PET indices including SUV_max, SUV_mean, SUV_peak, MTV and TLG and 32 textural features (TFs) were calculated using LIFEx software on PET imaging. Prognostic significance of these parameters was assessed in univariate and multivariate analysis. Relapse-free survival (RFS) and overall survival (OS) were respectively chosen as primary and secondary endpoints. An internal validation cohort was used by randomly drawing one-third of included patients. The main characteristics of this cohort were: median age of 65 years [41-88], sex ratio H/F = 83/14, 81.5% of patients with a histopathology of adenocarcinoma and 43.3% with a stage IV disease. The median follow-up was 28.5 months [4.2-108.5]. Seventy-seven (79.4%) patients had locoregional or distant progression or recurrence and 71 (73.2%) died. In univariate analysis, SUV_mean, Histogram-Entropy and 2 TFs (GLCM-Homogeneity and GLCM-Energy) were significantly correlated with RFS and OS, as well as 2 others TFs (GLRLM-LRE and GLRLM-GLNU) with OS only. In multivariate analysis, Histogram-Entropy remained an independent prognostic factor of both RFS and OS whereas SUV_mean was an independent prognostic factor of OS only. These results were partially confirmed in our internal validation cohort of 33 patients. Our results suggest that radiomic approach reveals independent prognostic factors for survival in patients with GEJC.

External validation of an MR-based radiomic model predictive of locoregional control in oropharyngeal cancer

OBJECTIVES

To externally validate a pre-treatment MR-based radiomics model predictive of locoregional control in oropharyngeal squamous cell carcinoma (OPSCC) and to assess the impact of differences between datasets on the predictive performance.

METHODS

Radiomic features, as defined in our previously published radiomics model, were extracted from the primary tumor volumes of 157 OPSCC patients in a different institute. The developed radiomics model was validated using this cohort. Additionally, parameters influencing performance, such as patient subgroups, MRI acquisition, and post-processing steps on prediction performance will be investigated. For this analysis, matched subgroups (based on human papillomavirus (HPV) status of the tumor, T-stage, and tumor subsite) and a subgroup with only patients with 4-mm slice thickness were studied. Also the influence of harmonization techniques (ComBat harmonization, quantile normalization) and the impact of feature stability across observers and centers were studied. Model performances were assessed by area under the curve (AUC), sensitivity, and specificity.

RESULTS

Performance of the published model (AUC/sensitivity/specificity: 0.74/0.75/0.60) drops when applied on the validation cohort (AUC/sensitivity/specificity: 0.64/0.68/0.60). The performance of the full validation cohort improves slightly when the model is validated using a patient group with comparable HPV status of the tumor (AUC/sensitivity/specificity: 0.68/0.74/0.60), using patients acquired with a slice thickness of 4 mm (AUC/sensitivity/specificity: 0.67/0.73/0.57), or when quantile harmonization was performed (AUC/sensitivity/specificity: 0.66/0.69/0.60).

CONCLUSION

The previously published model shows its generalizability and can be applied on data acquired from different vendors and protocols. Harmonization techniques and subgroup definition influence performance of predictive radiomics models.

KEY POINTS

• Radiomics, a noninvasive quantitative image analysis technique, can support the radiologist by enhancing diagnostic accuracy and/or treatment decision-making. • A previously published model shows its generalizability and could be applied on data acquired from different vendors and protocols.

Deep learning-based harmonization of CT reconstruction kernels towards improved clinical task performance

OBJECTIVES

To develop a deep learning-based harmonization framework, assessing whether it can improve performance of radiomics models given different kernels in different clinical tasks and additionally generalize to mitigate the effects of new/unobserved kernels on radiomics features.

METHODS

Patient data with 2 reconstruction kernels and phantom data with 22 reconstruction kernels were included. Eighty-five patients were studied for lymph node metastasis (LNM) prediction, and 164 patients for differential diagnosis between lung cancer (LC) and pulmonary tuberculosis (TB). Two convolutional neural network (CNN) models were developed to convert images (i) from B70f to B30f (CNNa) and (ii) from B30f to B70f (CNNb). Model performance between the two kernels was evaluated using AUC and compared with other well-known harmonization methods. Patient-normalized feature difference (PNFD) was used to identify the incompatible kernels (i.e., kernel with median PNFD > 1) with baseline (B30f/B70f), and measure the ability of the CNN models to convert the non-comparable kernels.

RESULTS

For LC versus pulmonary TB diagnosis, AUCs of CNNa vs. others were 0.85 vs. 0.54-0.74 (p = 0.0001-0.0003), and for CNNb vs. others: 0.87 vs. 0.54-0.86 (p = 0.0001-0.55). For LNM prediction, AUCs of CNNa vs. others were 0.68 vs. 0.56-0.61 (p = 0.10-0.39), and for CNNb vs. others: 0.78 vs. 0.70-0.73 (p = 0.07-0.40). After CNN harmonization, 17 of 20 (85%) of investigated unknown kernels produced comparable radiomics feature values relative to baseline (median PNFD from 1.10-2.31 to 0.23-1.13).

CONCLUSION

The CNN harmonization effectively improved performance of radiomics models between reconstruction kernels in different clinical tasks, and reduced feature differences between unknown kernels vs. baseline.

KEY POINTS

• The soft (B30f) and sharp (B70f) kernels strongly affect radiomics reproducibility and generalizability. • The convolutional neural network (CNN) harmonization methods performed better than location-scale (ComBat and centering-scaling) and matrix factorization harmonization methods (based on singular value decomposition (SVD) and independent component analysis (ICA)) in both clinical tasks. • The CNN harmonization methods improve feature reproducibility not only between specific kernels (B30f and B70f) from the same scanner, but also between unobserved kernels from different scanners of different vendors.

Long-axial field-of-view PET/CT: perspectives and review of a revolutionary development in nuclear medicine based on clinical experience in over 7000 patients

Recently introduced long-axial field-of-view (LAFOV) PET/CT systems represent one of the most significant advancements in nuclear medicine since the advent of multi-modality PET/CT imaging. The higher sensitivity exhibited by such systems allow for reductions in applied activity and short duration scans. However, we consider this to be just one small part of the story: Instead, the ability to image the body in its entirety in a single FOV affords insights which standard FOV systems cannot provide. For example, we now have the ability to capture a wider dynamic range of a tracer by imaging it over multiple half-lives without detrimental image noise, to leverage lower radiopharmaceutical doses by using dual-tracer techniques and with improved quantification. The potential for quantitative dynamic whole-body imaging using abbreviated protocols potentially makes these techniques viable for routine clinical use, transforming PET-reporting from a subjective analysis of semi-quantitative maps of radiopharmaceutical uptake at a single time-point to an accurate and quantitative, non-invasive tool to determine human function and physiology and to explore organ interactions and to perform whole-body systems analysis. This article will share the insights obtained from 2 years' of clinical operation of the first Biograph Vision Quadra (Siemens Healthineers) LAFOV system. It will also survey the current state-of-the-art in PET technology. Several technologies are poised to furnish systems with even greater sensitivity and resolution than current systems, potentially with orders of magnitude higher sensitivity. Current barriers which remain to be surmounted, such as data pipelines, patient throughput and the hindrances to implementing kinetic analysis for routine patient care will also be discussed.

Colorectal liver metastases patients prognostic assessment: prospects and limits of radiomics and radiogenomics

In this narrative review, we reported un up-to-date on the role of radiomics to assess prognostic features, which can impact on the liver metastases patient treatment choice. In the liver metastases patients, the possibility to assess mutational status (RAS or MSI), the tumor growth pattern and the histological subtype (NOS or mucinous) allows a better treatment selection to avoid unnecessary therapies. However, today, the detection of these features require an invasive approach. Recently, radiomics analysis application has improved rapidly, with a consequent growing interest in the oncological field. Radiomics analysis allows the textural characteristics assessment, which are correlated to biological data. This approach is captivating since it should allow to extract biological data from the radiological images, without invasive approach, so that to reduce costs and time, avoiding any risk for the patients. Several studies showed the ability of Radiomics to identify mutational status, tumor growth pattern and histological type in colorectal liver metastases. Although, radiomics analysis in a non-invasive and repeatable way, however features as the poor standardization and generalization of clinical studies results limit the translation of this analysis into clinical practice. Clear limits are data-quality control, reproducibility, repeatability, generalizability of results, and issues related to model overfitting.

Explainable domain transfer of distant supervised cancer subtyping model via imaging-based rules extraction

Image texture analysis has for decades represented a promising opportunity for cancer assessment and disease progression evaluation, evolving in a discipline, i.e., radiomics. However, the road to a complete translation into clinical practice is still hampered by intrinsic limitations. As purely supervised classification models fail in devising robust imaging-based biomarkers for prognosis, cancer subtyping approaches would benefit from the employment of distant supervision, for instance exploiting survival/recurrence information. In this work, we assessed, tested, and validated the domain-generality of our previously proposed Distant Supervised Cancer Subtyping model on Hodgkin Lymphoma. We evaluate the model performance on two independent datasets coming from two hospitals, comparing and analyzing the results. Although successful and consistent, the comparison confirmed the instability of radiomics due to an across-center lack of reproducibility, leading to explainable results in one center and poor interpretability in the other. We thus propose a Random Forest-based Explainable Transfer Model for testing the domain-invariance of imaging biomarkers extracted from retrospective cancer subtyping. In doing so, we tested the predictive ability of cancer subtyping in a validation and perspective setting, which led to successful results and supported the domain-generality of the proposed approach. On the other hand, the extraction of decision rules enables to draw of risk factors and robust biomarkers to inform clinical decisions. This work shows the potentialities of the Distant Supervised Cancer Subtyping model to be further evaluated in larger multi-center datasets, to reliably translate radiomics into medical practice. The code is available at this GitHub repository.

External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study

OBJECTIVES

The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers' discriminative performance for pCR prediction.

METHODS

This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve.

RESULTS

Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models.

CONCLUSIONS

The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients.

KEY POINTS

• A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC. • The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer. • The RF classifier performed best in the current study.

Feasibility of radiomic feature harmonization for pooling of [18F]FET or [18F]GE-180 PET images of gliomas

INTRODUCTION

Large datasets are required to ensure reliable non-invasive glioma assessment with radiomics-based machine learning methods. This can often only be achieved by pooling images from different centers. Moreover, trained models should perform with high accuracy when applied to data from different centers. In this study, the impact of reconstruction settings and segmentation methods on radiomic features derived from amino acid and TSPO PET images of glioma patients was examined. Additionally, the ability to model and thus reduce feature differences was investigated.

METHODS

[¹⁸F]FET and [¹⁸F]GE-180 PET data were acquired from 19 glioma patients. For each acquisition, 10 reconstruction settings and 9 segmentation methods were included to emulate multicentric data. Statistical robustness measures were calculated before and after ComBat harmonization. Differences between features due to setting variations were assessed using Friedman test, coefficient of variation (CV) and inter-rater reliability measures, including intraclass and Spearman's rank correlation coefficients and Fleiss' Kappa.

RESULTS

According to Friedman analyses, most features (>60%) showed significant differences. Yet, CV and inter-rater reliability measures indicated higher robustness. ComBat resulted in almost complete harmonization (>87%) according to Friedman test and little to no improvement according to CV and inter-rater reliability measures. [¹⁸F]GE-180 features were more sensitive to reconstruction settings than [¹⁸F]FET features.

CONCLUSIONS

According to Friedman test, feature distributions could be successfully aligned using ComBat. However, depending on settings, changes in patient ranks were observed for some features and could not be eliminated by harmonization. Thus, for clinical utilization it is recommended to exclude affected features.

Risk Assessment and Pancreatic Cancer: Diagnostic Management and Artificial Intelligence

Pancreatic cancer (PC) is one of the deadliest cancers, and it is responsible for a number of deaths almost equal to its incidence. The high mortality rate is correlated with several explanations; the main one is the late disease stage at which the majority of patients are diagnosed. Since surgical resection has been recognised as the only curative treatment, a PC diagnosis at the initial stage is believed the main tool to improve survival. Therefore, patient stratification according to familial and genetic risk and the creation of screening protocol by using minimally invasive diagnostic tools would be appropriate. Pancreatic cystic neoplasms (PCNs) are subsets of lesions which deserve special management to avoid overtreatment. The current PC screening programs are based on the annual employment of magnetic resonance imaging with cholangiopancreatography sequences (MR/MRCP) and/or endoscopic ultrasonography (EUS). For patients unfit for MRI, computed tomography (CT) could be proposed, although CT results in lower detection rates, compared to MRI, for small lesions. The actual major limit is the incapacity to detect and characterize the pancreatic intraepithelial neoplasia (PanIN) by EUS and MR/MRCP. The possibility of utilizing artificial intelligence models to evaluate higher-risk patients could favour the diagnosis of these entities, although more data are needed to support the real utility of these applications in the field of screening. For these motives, it would be appropriate to realize screening programs in research settings.

A review of harmonization strategies for quantitative PET

PET can reveal in vivo biological processes at the molecular level. PET-derived quantitative values have been used as a surrogate marker for clinical decision-making in numerous clinical studies and trials. However, quantitative values in PET are variable depending on technical, biological, and physical factors. The variability may have a significant impact on a study outcome. Appropriate scanner calibration and quality control, standardization of imaging protocols, and any necessary harmonization strategies are essential to make use of PET as a biomarker with low bias and variability. This review summarizes benefits, limitations, and remaining challenges for harmonization of quantitative PET, including whole-body PET in oncology, brain PET in neurology, PET/MR, and non-¹⁸F PET imaging. This review is expected to facilitate harmonization of quantitative PET and to promote the contribution of PET-derived biomarkers to research and development in medicine.

Joint EANM/SNMMI guideline on radiomics in nuclear medicine : Jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council

PURPOSE

The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses for both hand-crafted and deep learning-based approaches.

METHODS

In a cooperative effort between the EANM and SNMMI, we agreed upon current best practices and recommendations for relevant aspects of radiomics analyses, including study design, quality assurance, data collection, impact of acquisition and reconstruction, detection and segmentation, feature standardization and implementation, as well as appropriate modelling schemes, model evaluation, and interpretation. We also offer an outlook for future perspectives.

CONCLUSION

Radiomics is a very quickly evolving field of research. The present guideline focused on established findings as well as recommendations based on the state of the art. Though this guideline recognizes both hand-crafted and deep learning-based radiomics approaches, it primarily focuses on the former as this field is more mature. This guideline will be updated once more studies and results have contributed to improved consensus regarding the application of deep learning methods for radiomics. Although methodological recommendations in the present document are valid for most medical image modalities, we focus here on nuclear medicine, and specific recommendations when necessary are made for PET/CT, PET/MR, and quantitative SPECT.

A Framework of Analysis to Facilitate the Harmonization of Multicenter Radiomic Features in Prostate Cancer

Pooling radiomic features coming from different centers in a statistical framework is challenging due to the variability in scanner models, acquisition protocols, and reconstruction settings. To remove technical variability, commonly called batch effects, different statistical harmonization strategies have been widely used in genomics but less considered in radiomics. The aim of this work was to develop a framework of analysis to facilitate the harmonization of multicenter radiomic features extracted from prostate T2-weighted magnetic resonance imaging (MRI) and to improve the power of radiomics for prostate cancer (PCa) management in order to develop robust non-invasive biomarkers translating into clinical practice. To remove technical variability and correct for batch effects, we investigated four different statistical methods (ComBat, SVA, Arsynseq, and mixed effect). The proposed approaches were evaluated using a dataset of 210 prostate cancer (PCa) patients from two centers. The impacts of the different statistical approaches were evaluated by principal component analysis and classification methods (LogitBoost, random forest, K-nearest neighbors, and decision tree). The ComBat method outperformed all other methods by achieving 70% accuracy and 78% AUC with the random forest method to automatically classify patients affected by PCa. The proposed statistical framework enabled us to define and develop a standardized pipeline of analysis to harmonize multicenter T2W radiomic features, yielding great promise to support PCa clinical practice.

Radiomics in clinical trials: perspectives on standardization

The term biomarker is used to describe a biological measure of the disease behavior. The existing imaging biomarkers are associated with the known tissue biological characteristics and follow a well-established roadmap to be implemented in routine clinical practice. Recently, a new quantitative imaging analysis approach named radiomics has emerged. It refers to the extraction of a large number of advanced imaging features with high-throughput computing. Extensive research has demonstrated its value in predicting disease behavior, progression, and response to therapeutic options. However, there are numerous challenges to establishing it as a clinically viable solution, including lack of reproducibility and transparency. The data-driven nature also does not offer insights into the underpinning biology of the observed relationships. As such, additional effort is needed to establish it as a qualified biomarker to inform clinical decisions. Here we review the technical difficulties encountered in the clinical applications of radiomics and current effort in addressing some of these challenges in clinical trial designs. By addressing these challenges, the true potential of radiomics can be unleashed.