Radiomics in PET/CT: More Than Meets the Eye?

Integrative radiopathomics model for predicting progression-free survival in patients with nonmetastatic nasopharyngeal carcinoma

PURPOSE

To construct an integrative radiopathomics model for predicting progression-free survival (PFS) in nonmetastatic nasopharyngeal carcinoma (NPC) patients.

METHODS

357 NPC patients who underwent pretreatment MRI and pathological whole-slide imaging (WSI) were included in this study and randomly divided into two groups: a training set (n = 250) and validation set (n = 107). Radiomic features extracted from MRI were selected using the minimum redundancy maximum relevance and least absolute shrinkage and selection operator methods. The pathomics signature based on WSI was constructed using a deep learning architecture, the Swin Transformer. The radiopathomics model was constructed by incorporating three feature sets: the radiomics signature, pathomics signature, and independent clinical factors. The prognostic efficacy of the model was assessed using the concordance index (C-index). Kaplan-Meier curves for the stratified risk groups were tested by the log-rank test.

RESULTS

The radiopathomics model exhibited superior predictive performance with C-indexes of 0.791 (95% confidence interval [CI]: 0.724-0.871) in the training set and 0.785 (95% CI: 0.716-0.875) in the validation set compared to any single-modality model (radiomics: 0.619, 95% CI: 0.553-0.706; pathomics: 0.732, 95% CI: 0.662-0.802; clinical model: 0.655, 95% CI: 0.581-0.728) (all, P < 0.05). The radiopathomics model effectively stratified patients into high- and low-risk groups in both the training and validation sets (P < 0.001).

CONCLUSION

The developed radiopathomics model demonstrated its reliability in predicting PFS for NPC patients. It effectively stratified individual patients into distinct risk groups, providing valuable insights for prognostic assessment.

PET radiomics-based lymphovascular invasion prediction in lung cancer using multiple segmentation and multi-machine learning algorithms

The current study aimed to predict lymphovascular invasion (LVI) using multiple machine learning algorithms and multi-segmentation positron emission tomography (PET) radiomics in non-small cell lung cancer (NSCLC) patients, offering new avenues for personalized treatment strategies and improving patient outcomes. One hundred and twenty-six patients with NSCLC were enrolled in this study. Various automated and semi-automated PET image segmentation methods were applied, including Local Active Contour (LAC), Fuzzy-C-mean (FCM), K-means (KM), Watershed, Region Growing (RG), and Iterative thresholding (IT) with different percentages of the threshold. One hundred five radiomic features were extracted from each region of interest (ROI). Multiple feature selection methods, including Minimum Redundancy Maximum Relevance (MRMR), Recursive Feature Elimination (RFE), and Boruta, and multiple classifiers, including Multilayer Perceptron (MLP), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Random Forest (RF), were employed. Synthetic Minority Oversampling Technique (SMOTE) was also used to determine if it boosts the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Our results indicated that the combination of SMOTE, IT (with 45% threshold), RFE feature selection and LR classifier showed the best performance (AUC = 0.93, ACC = 0.84, SEN = 0.85, SPE = 0.84) followed by SMOTE, FCM segmentation, MRMR feature selection, and LR classifier (AUC = 0.92, ACC = 0.87, SEN = 1, SPE = 0.84). The highest ACC belonged to the IT segmentation (with 45 and 50% thresholds) alongside Boruta feature selection and the NB classifier without SMOTE (ACC = 0.9, AUC = 0.78 and 0.76, SEN = 0.7, and SPE = 0.94, respectively). Our results indicate that selection of appropriate segmentation method and machine learning algorithm may be helpful in successful prediction of LVI in patients with NSCLC with high accuracy using PET radiomics analysis.

Challenges and limitations in applying radiomics to PET imaging: Possible opportunities and avenues for research

Radiomics, the high-throughput extraction of quantitative imaging features from medical images, holds immense potential for advancing precision medicine in oncology and beyond. While radiomics applied to positron emission tomography (PET) imaging offers unique insights into tumor biology and treatment response, it is imperative to elucidate the challenges and constraints inherent in this domain to facilitate their translation into clinical practice. This review examines the challenges and limitations of applying radiomics to PET imaging, synthesizing findings from the last five years (2019-2023) and highlights the significance of addressing these challenges to realize the full clinical potential of radiomics in oncology and molecular imaging. A comprehensive search was conducted across multiple electronic databases, including PubMed, Scopus, and Web of Science, using keywords relevant to radiomics issues in PET imaging. Only studies published in peer-reviewed journals were eligible for inclusion in this review. Although many studies have highlighted the potential of radiomics in predicting treatment response, assessing tumor heterogeneity, enabling risk stratification, and personalized therapy selection, various challenges regarding the practical implementation of the proposed models still need to be addressed. This review illustrates the challenges and limitations of radiomics in PET imaging across various cancer types, encompassing both phantom and clinical investigations. The analyzed studies highlight the importance of reproducible segmentation methods, standardized pre-processing and post-processing methodologies, and the need to create large multicenter studies registered in a centralized database to promote the continuous validation and clinical integration of radiomics into PET imaging.

Radiomics for clinical decision support in radiation oncology

Radiomics is a promising tool for the development of quantitative biomarkers to support clinical decision-making. It has been shown to improve the prediction of response to treatment and outcome in different settings, particularly in the field of radiation oncology by optimising the dose delivery solutions and reducing the rate of radiation-induced side effects, leading to a fully personalised approach. Despite the promising results offered by radiomics at each of these stages, standardised methodologies, reproducibility and interpretability of results are still lacking, limiting the potential clinical impact of these tools. In this review, we briefly describe the principles of radiomics and the most relevant applications of radiomics at each stage of cancer management in the framework of radiation oncology. Furthermore, the integration of radiomics into clinical decision support systems is analysed, defining the challenges and offering possible solutions for translating radiomics into a clinically applicable tool.

MRI-based radiomics models predict cystic brain radionecrosis of nasopharyngeal carcinoma after intensity modulated radiotherapy

Objective

To construct radiomics models based on MRI at different time points for the early prediction of cystic brain radionecrosis (CBRN) for nasopharyngeal carcinoma (NPC).

Methods

A total of 202 injured temporal lobes from 155 NPC patients with radiotherapy-induced temporal lobe injury (RTLI) after intensity modulated radiotherapy (IMRT) were included in the study. All the injured lobes were randomly divided into the training (n = 143) and validation (n = 59) sets. Radiomics models were constructed by using features extracted from T2WI at two different time points: at the end of IMRT (post-IMRT) and the first-detected RTLI (first-RTLI). A delta-radiomics feature was defined as the percentage change in a radiomics feature from post-IMRT to first-RTLI. The radiomics nomogram was constructed by combining clinical risk factors and radiomics signatures using multivariate logistic regression analysis. Predictive performance was evaluated using area under the curve (AUC) from receiver operating characteristic analysis and decision curve analysis (DCA).

Results

The post-IMRT, first-RTLI, and delta-radiomics models yielded AUC values of 0.84 (95% CI: 0.76-0.92), 0.86 (95% CI: 0.78-0.94), and 0.77 (95% CI: 0.67-0.87), respectively. The nomogram exhibited the highest AUC of 0.91 (95% CI: 0.85-0.97) and sensitivity of 0.82 compared to any single radiomics model. From the DCA, the nomogram model provided more clinical benefit than the radiomics models or clinical model.

Conclusion

The radiomics nomogram model combining clinical factors and radiomics signatures based on MRI at different time points after radiotherapy showed excellent prediction potential for CBRN in patients with NPC.

Impact of Respiratory-gated 4D PET/CT Scan for Motion Correction in Characterizing Lesions Adjacent to the Diaphragm - A Cross-sectional Study at a Tertiary Care Institute

Purpose

The blur introduced by breathing motion degrades the diagnostic accuracy of whole-body F-18 fluorodeoxyglucose positron emission tomography-computed tomography (18F-FDG PET-CT) in lesions adjacent to the diaphragm by increasing the apparent size and by decreasing their metabolic activity. This study aims to evaluate the efficacy of motion correction by four-dimensional phase-based respiratory-gated (RG) 18F-FDG PET-CT in improving metabolic parameters of lesions adjacent to the diaphragm (especially in the lungs or liver).

Materials and Methods

Eighteen patients with known lung or liver lesions underwent conventional 18F-FDG PET-CT and respiratory-gated PET-CT acquisition of the desired region using a pressure-sensing, phase-based respiratory-gating system. Maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were obtained for these lesions from gated and nongated PET-CT images for analysis. Furthermore, a visual analysis of lesions was done.

Statistics

Statistical significance of the RG image parameters was assessed by the two-tailed paired Student's t test and confirmed with the robust nonparametric Wilcoxon's signed-rank test (two-tailed asymptotic).

Results

There was an overall significant increase in SUVmax (P 0.001) in all gating methods with a percentage increase maximum of about 18.13%. On gating methods, MTV decreased significantly (P = 0.001) than that of nongating method (maximum reduction of about 32.9%). There was a significant difference (P = 0.02) in TLG between gated and nongated methods.

Conclusion

Motion correction with phase-based respiratory gating improves the diagnostic value of 18F-FDG PET-CT imaging for lung and liver lesions by more accurate delineation of the lesion volume and quantitation of SUV and can thus impact staging, diagnosis as well as management in selected patients.

Radiotherapy modification based on artificial intelligence and radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography

Over the last decades, the refinement of radiation therapy techniques has been associated with an increasing interest for individualized radiation therapy with the aim of increasing or maintaining tumor control and reducing radiation toxicity. Developments in artificial intelligence (AI), particularly machine learning and deep learning, in imaging sciences, including nuclear medecine, have led to significant enthusiasm for the concept of "rapid learning health system". AI combined with radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography ([18F]-FDG PET/CT) offers a unique opportunity for the development of predictive models that can help stratify each patient's risk and guide treatment decisions for optimal outcomes and quality of life of patients treated with radiation therapy. Here we present an overview of the current contribution of AI and radiomics-based machine learning models applied to (18F)-FDG PET/CT in the management of cancer treated by radiation therapy.

Development of a Model Based on Delta-Radiomic Features for the Optimization of Head and Neck Squamous Cell Carcinoma Patient Treatment

Background and Objectives: To our knowledge, this is the first study that investigated the prognostic value of radiomics features extracted from not only staging 18F-fluorodeoxyglucose positron emission tomography (FDG PET/CT) images, but also post-induction chemotherapy (ICT) PET/CT images. This study aimed to construct a training model based on radiomics features obtained from PET/CT in a cohort of patients with locally advanced head and neck squamous cell carcinoma treated with ICT, to predict locoregional recurrence, development of distant metastases, and the overall survival, and to extract the most significant radiomics features, which were included in the final model. Materials and Methods: This retrospective study analyzed data of 55 patients. All patients underwent PET/CT at the initial staging and after ICT. Along the classical set of 13 parameters, the original 52 parameters were extracted from each PET/CT study and an additional 52 parameters were generated as a difference between radiomics parameters before and after the ICT. Five machine learning algorithms were tested. Results: The Random Forest algorithm demonstrated the best performance (R² 0.963-0.998) in the majority of datasets. The strongest correlation in the classical dataset was between the time to disease progression and time to death (r = 0.89). Another strong correlation (r ≥ 0.8) was between higher-order texture indices GLRLM_GLNU, GLRLM_SZLGE, and GLRLM_ZLNU and standard PET parameters MTV, TLG, and SUVmax. Patients with a higher numerical expression of GLCM_ContrastVariance, extracted from the delta dataset, had a longer survival and longer time until progression (p = 0.001). Good correlations were observed between Discretized_SUVstd or Discretized_SUVSkewness and time until progression (p = 0.007). Conclusions: Radiomics features extracted from the delta dataset produced the most robust data. Most of the parameters had a positive impact on the prediction of the overall survival and the time until progression. The strongest single parameter was GLCM_ContrastVariance. Discretized_SUVstd or Discretized_SUVSkewness demonstrated a strong correlation with the time until progression.

Integration of Radiomics and Tumor Biomarkers in Interpretable Machine Learning Models

Despite the unprecedented performance of deep neural networks (DNNs) in computer vision, their clinical application in the diagnosis and prognosis of cancer using medical imaging has been limited. One of the critical challenges for integrating diagnostic DNNs into radiological and oncological applications is their lack of interpretability, preventing clinicians from understanding the model predictions. Therefore, we studied and propose the integration of expert-derived radiomics and DNN-predicted biomarkers in interpretable classifiers, which we refer to as ConRad, for computerized tomography (CT) scans of lung cancer. Importantly, the tumor biomarkers can be predicted from a concept bottleneck model (CBM) such that once trained, our ConRad models do not require labor-intensive and time-consuming biomarkers. In our evaluation and practical application, the only input to ConRad is a segmented CT scan. The proposed model was compared to convolutional neural networks (CNNs) which act as a black box classifier. We further investigated and evaluated all combinations of radiomics, predicted biomarkers and CNN features in five different classifiers. We found the ConRad models using nonlinear SVM and the logistic regression with the Lasso outperformed the others in five-fold cross-validation, with the interpretability of ConRad being its primary advantage. The Lasso is used for feature selection, which substantially reduces the number of nonzero weights while increasing the accuracy. Overall, the proposed ConRad model combines CBM-derived biomarkers and radiomics features in an interpretable ML model which demonstrates excellent performance for lung nodule malignancy classification.

Combination of FDG PET/CT Radiomics and Clinical Parameters for Outcome Prediction in Patients with Hodgkin’s Lymphoma

Purpose: The aim of the study is to evaluate the prognostic value of a joint evaluation of PET and CT radiomics combined with standard clinical parameters in patients with HL. Methods: Overall, 88 patients (42 female and 46 male) with a median age of 43.3 (range 21–85 years) were included. Textural analysis of the PET/CT images was performed using freely available software (LIFE X). 65 radiomic features (RF) were evaluated. Univariate and multivariate models were used to determine the value of clinical characteristics and FDG PET/CT radiomics in outcome prediction. In addition, a binary logistic regression model was used to determine potential predictors for radiotherapy treatment and odds ratios (OR), with 95% confidence intervals (CI) reported. Features relevant to survival outcomes were assessed using Cox proportional hazards to calculate hazard ratios with 95% CI. Results: albumin (p = 0.034) + ALP (p = 0.028) + CT radiomic feature GLRLM GLNU mean (p = 0.012) (Area under the curve (AUC): 95% CI (86.9; 100.0)—Brier score: 3.9, 95% CI (0.1; 7.8) remained significant independent predictors for PFS outcome. PET-SHAPE Sphericity (p = 0.033); CT grey-level zone length matrix with high gray-level zone emphasis (GLZLM SZHGE mean (p = 0.028)); PARAMS XSpatial Resampling (p = 0.0091) as well as hemoglobin results (p = 0.016) remained as independent factors in the final model for a binary outcome as predictors of the need for radiotherapy (AUC = 0.79). Conclusion: We evaluated the value of baseline clinical parameters as well as combined PET and CT radiomics in HL patients for survival and the prediction of the need for radiotherapy treatment. We found that different combinations of all three factors/features were independently predictive of the here evaluated endpoints.

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.

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.

Quantitative Analysis of TP53-Related Lung Cancer Based on Radiomics

Background

The role of TP53 mutations in the diagnosis and treatment of lung cancer has attracted increasing attention from experts worldwide. This study aimed to explore the expression of TP53 gene in lung cancer and its correlation with radiomics quantitative features.

Methods

A total of 93 cases of lung cancer confirmed by pathology were selected, including 44 cases with TP53 mutations and 49 cases with TP53 wild-type. ITK-SNAP software was used to segment the pulmonary nodules, AK software was used to extract radiomic features, and a model was established to predict the type of TP53 gene mutation in lung cancer lesions.

Results

A total of 852 features were extracted, and 10 features remained after feature selection. The accuracy, areas under the curve, specificity, sensitivity, positive predictive value, and negative predictive value of the logistic regression model were 0.80, 0.86, 0.89, 0.74, 0.90, and 0.71, respectively.

Conclusion

TP53 gene mutations are correlated with radiomic features in lung cancer, which may have application value for TP53 therapy in the future.

18F-FDG PET/CT radiomic analysis for classifying and predicting microvascular invasion in hepatocellular carcinoma and intrahepatic cholangiocarcinoma

Background

Microvascular invasion (MVI) is a critical risk factor for early recurrence of hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). The aim of this study was to explore the contribution of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) radiomic features for the preoperative prediction of HCC and ICC classification and MVI.

Methods

In this retrospective study, 127 (HCC: ICC =76:51) patients with suspected MVI accompanied by either HCC or ICC were included (In HCC group, MVI positive: negative =46:30 in ICC group, MVI positive: negative =31:20). Results-driven feature engineering workflow was used to select the most predictive feature combinations. The prediction model was based on supervised machine learning classifier. Ten-fold cross validation on training cohort and independent test cohort were constructed to ensure stability and generalization ability of models.

Results

For HCC and ICC classification, radiomics predictors composed of two PET and one CT feature achieved area under the curve (AUC) of 0.86 (accuracy, sensitivity, specificity was 0.82, 0.78, 0.88, respectively) on test cohort. For MVI prediction, in HCC group, our MVI prediction model achieved AUC of 0.88 (accuracy, sensitivity, specificity was 0.78, 0.88, 0.60 respectively) with three PET features associated with tumor stage on test cohort. In ICC group, the phenotype composed of two PET features and carbohydrate antigen 19-9 (CA19-9) achieved AUC of 0.90 (accuracy, sensitivity, specificity was 0.77, 0.75, 0.80, respectively).

Conclusions

¹⁸F-FDG PET/CT radiomic features integrating clinical factors have potential in HCC and ICC classification and MVI prediction, while PET features have dominant predictive power in model performance. The prediction model has value in providing a non-invasive biomarker for an earlier indication and comprehensive quantification of primary liver cancers.

3D Convolutional Neural Network Framework with Deep Learning for Nuclear Medicine

Though artificial intelligence (AI) has been used in nuclear medicine for more than 50 years, more progress has been made in deep learning (DL) and machine learning (ML), which have driven the development of new AI abilities in the field. ANNs are used in both deep learning and machine learning in nuclear medicine. Alternatively, if 3D convolutional neural network (CNN) is used, the inputs may be the actual images that are being analyzed, rather than a set of inputs. In nuclear medicine, artificial intelligence reimagines and reengineers the field's therapeutic and scientific capabilities. Understanding the concepts of 3D CNN and U-Net in the context of nuclear medicine provides for a deeper engagement with clinical and research applications, as well as the ability to troubleshoot problems when they emerge. Business analytics, risk assessment, quality assurance, and basic classifications are all examples of simple ML applications. General nuclear medicine, SPECT, PET, MRI, and CT may benefit from more advanced DL applications for classification, detection, localization, segmentation, quantification, and radiomic feature extraction utilizing 3D CNNs. An ANN may be used to analyze a small dataset at the same time as traditional statistical methods, as well as bigger datasets. Nuclear medicine's clinical and research practices have been largely unaffected by the introduction of artificial intelligence (AI). Clinical and research landscapes have been fundamentally altered by the advent of 3D CNN and U-Net applications. Nuclear medicine professionals must now have at least an elementary understanding of AI principles such as neural networks (ANNs) and convolutional neural networks (CNNs).

A multi-modality physical phantom for mimicking tumour heterogeneity patterns in PET/CT and PET/MRI

Background

Hybrid imaging (e.g., positron emission tomography [PET]/computed tomography [CT], PET/magnetic resonance imaging [MRI]) helps one to visualize and quantify morphological and physiological tumor characteristics in a single study. The noninvasive characterization of tumor heterogeneity is essential for grading, treatment planning, and following‐up oncological patients. However, conventional (CONV) image‐based parameters, such as tumor diameter, tumor volume, and radiotracer activity uptake, are insufficient to describe tumor heterogeneities. Here, radiomics shows promise for a better characterization of tumors. Nevertheless, the validation of such methods demands imaging objects capable of reflecting heterogeneities in multi‐modality imaging. We propose a phantom to simulate tumor heterogeneity repeatably in PET, CT, and MRI.

Methods

The phantom consists of three 50‐ml plastic tubes filled partially with acrylic spheres of S1: 1.6 mm, S2: 50%(1.6 mm)/50%(6.3 mm), or S3: 6.3‐mm diameter. The spheres were fixed to the bottom of each tube by a plastic grid, yielding one sphere free homogeneous region and one heterogeneous (S1, S2, or S3) region per tube. A 3‐tube phantom and its replica were filled with a fluorodeoxyglucose (18F) solution for test–retest measurements in a PET/CT Siemens TPTV and a PET/MR Siemens Biograph mMR system. A number of 42 radiomic features (10 first order and 32 texture features) were calculated for each phantom region and imaging modality. Radiomic features stability was evaluated through coefficients of variation (COV) across phantoms and scans for PET, CT, and MRI. Further, the Wilcoxon test was used to assess the capability of stable features to discriminate the simulated phantom regions.

Results

The different patterns (S1–S3) did present visible heterogeneity in all imaging modalities. However, only for CT and MRI, a clear visual difference was present between the different patterns. Across all phantom regions in PET, CT, and MR images, 10, 16, and 21 features out of 42 evaluated features in total had a COV of 10% or less. In particular, CONV, histogram, and gray‐level run length matrix features showed high repeatability for all the phantom regions and imaging modalities. Several of repeatable texture features allowed the image‐based discrimination of the different phantom regions (p < 0.05). However, depending on the feature, different pattern discrimination capabilities were found for the different imaging modalities.

Conclusion

The proposed phantom appears suitable for simulating heterogeneities in PET, CT, and MRI. We demonstrate that it is possible to select radiomic features for the readout of the phantom. Most of these features had been shown to be relevant in previous clinical studies.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

A review on advances in 18F-FDG PET/CT radiomics standardisation and application in lung disease management

Radiomics analysis quantifies the interpolation of multiple and invisible molecular features present in diagnostic and therapeutic images. Implementation of 18-fluorine-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) radiomics captures various disorders in non-invasive and high-throughput manner. ¹⁸F-FDG PET/CT accurately identifies the metabolic and anatomical changes during cancer progression. Therefore, the application of ¹⁸F-FDG PET/CT in the field of oncology is well established. Clinical application of ¹⁸F-FDG PET/CT radiomics in lung infection and inflammation is also an emerging field. Combination of bioinformatics approaches or textual analysis allows radiomics to extract additional information to predict cell biology at the micro-level. However, radiomics texture analysis is affected by several factors associated with image acquisition and processing. At present, researchers are working on mitigating these interrupters and developing standardised workflow for texture biomarker establishment. This review article focuses on the application of ¹⁸F-FDG PET/CT in detecting lung diseases specifically on cancer, infection and inflammation. An overview of different approaches and challenges encountered on standardisation of ¹⁸F-FDG PET/CT technique has also been highlighted. The review article provides insights about radiomics standardisation and application of ¹⁸F-FDG PET/CT in lung disease management.

Prognostic Value of Metabolic, Volumetric and Textural Parameters of Baseline [18F]FDG PET/CT in Early Triple-Negative Breast Cancer

Simple Summary

The aim of this study was to evaluate PET/CT parameters to determine different prognostic groups in TNBC, in order to select patients with a high risk of relapse, for whom therapeutic escalation can be considered. We have demonstrated that the MTV, TLG and entropy of the primary breast lesion could be of interest to predict the prognostic outcome of TNBC patients.

Abstract

(1) Background: triple-negative breast cancer (TNBC) remains a clinical and therapeutic challenge primarily affecting young women with poor prognosis. TNBC is currently treated as a single entity but presents a very diverse profile in terms of prognosis and response to treatment. Positron emission tomography/computed tomography (PET/CT) with ¹⁸F-fluorodeoxyglucose ([¹⁸F]FDG) is gaining importance for the staging of breast cancers. TNBCs often show high [¹⁸F]FDG uptake and some studies have suggested a prognostic value for metabolic and volumetric parameters, but no study to our knowledge has examined textural features in TNBC. The objective of this study was to evaluate the association between metabolic, volumetric and textural parameters measured at the initial [¹⁸F]FDG PET/CT and disease-free survival (DFS) and overall survival (OS) in patients with nonmetastatic TBNC. (2) Methods: all consecutive nonmetastatic TNBC patients who underwent a [¹⁸F]FDG PET/CT examination upon diagnosis between 2012 and 2018 were retrospectively included. The metabolic and volumetric parameters (SUV_max, SUV_mean, SUV_peak, MTV, and TLG) and the textural features (entropy, homogeneity, SRE, LRE, LGZE, and HGZE) of the primary tumor were collected. (3) Results: 111 patients were enrolled (median follow-up: 53.6 months). In the univariate analysis, high TLG, MTV and entropy values of the primary tumor were associated with lower DFS (p = 0.008, p = 0.006 and p = 0.025, respectively) and lower OS (p = 0.002, p = 0.001 and p = 0.046, respectively). The discriminating thresholds for two-year DFS were calculated as 7.5 for MTV, 55.8 for TLG and 2.6 for entropy. The discriminating thresholds for two-year OS were calculated as 9.3 for MTV, 57.4 for TLG and 2.67 for entropy. In the multivariate analysis, lymph node involvement in PET/CT was associated with lower DFS (p = 0.036), and the high MTV of the primary tumor was correlated with lower OS (p = 0.014). (4) Conclusions: textural features associated with metabolic and volumetric parameters of baseline [¹⁸F]FDG PET/CT have a prognostic value for identifying high-relapse-risk groups in early TNBC patients.

Evaluation of conventional and deep learning based image harmonization methods in radiomics studies

Objective.To evaluate the impact of image harmonization on outcome prediction models using radiomics.Approach.234 patients from the Brain Tumor Image Segmentation Benchmark (BRATS) dataset with T1 MRI were enrolled in this study. Images were harmonized to a reference image using histogram matching (H_HM) and a generative adversarial network (GAN)-based method (H_GAN). 88 radiomics features were extracted on H_HM, H_GANand original (H_NONE) images. Wilcoxon paired test was used to identify features significantly impacted by the harmonization protocol used. Radiomic prediction models were built using feature selection with the Least Absolute Shrinkage and Selection Operator (LASSO) and Kaplan-Meier analysis.Main results.More than 50% of the features (49/88) were statistically modified by the harmonization with H_HMand 55 with H_GAN(adjustedp-value < 0.05). The contribution of histogram and texture features selected by the LASSO, in comparison to shape features that were not impacted by harmonization, was higher in harmonized datasets (47% for H_none, 62% for H_HMand 71% for H_GAN). Both image-based harmonization methods allowed to split patients into two groups with significantly different survival (p<0.05). With the H_GANimages, we were also able to build and validate a model using only features impacted by the harmonization (median survivals of 189 versus 437 days,p= 0.006)Significance.Data harmonization in a multi-institutional cohort allows to recover the predictive value of some radiomics features that was lost due to differences in the image properties across centers. In terms of ability to build survival prediction models in the BRATS dataset, the loss of power from impacted histogram and heterogeneity features was compensated by the selection of additional shape features. The harmonization using a GAN-based approach outperformed the histogram matching technique, supporting the interest for the development of new advanced harmonization techniques for radiomic analysis purposes.

AI-Based Detection, Classification and Prediction/Prognosis in Medical Imaging:: Towards Radiophenomics

Artificial intelligence (AI) techniques have significant potential to enable effective, robust, and automated image phenotyping including the identification of subtle patterns. AI-based detection searches the image space to find the regions of interest based on patterns and features. There is a spectrum of tumor histologies from benign to malignant that can be identified by AI-based classification approaches using image features. The extraction of minable information from images gives way to the field of "radiomics" and can be explored via explicit (handcrafted/engineered) and deep radiomics frameworks. Radiomics analysis has the potential to be used as a noninvasive technique for the accurate characterization of tumors to improve diagnosis and treatment monitoring. This work reviews AI-based techniques, with a special focus on oncological PET and PET/CT imaging, for different detection, classification, and prediction/prognosis tasks. We also discuss needed efforts to enable the translation of AI techniques to routine clinical workflows, and potential improvements and complementary techniques such as the use of natural language processing on electronic health records and neuro-symbolic AI techniques.

Robustness of PET Radiomics Features: Impact of Co-Registration with MRI

Radiomics holds great promise in the field of cancer management. However, the clinical application of radiomics has been hampered by uncertainty about the robustness of the features extracted from the images. Previous studies have reported that radiomics features are sensitive to changes in voxel size resampling and interpolation, image perturbation, or slice thickness. This study aims to observe the variability of positron emission tomography (PET) radiomics features under the impact of co-registration with magnetic resonance imaging (MRI) using the difference percentage coefficient, and the Spearman’s correlation coefficient for three groups of images: (i) original PET, (ii) PET after co-registration with T1-weighted MRI and (iii) PET after co-registration with FLAIR MRI. Specifically, seventeen patients with brain cancers undergoing [11C]-Methionine PET were considered. Successively, PET images were co-registered with MRI sequences and 107 features were extracted for each mentioned group of images. The variability analysis revealed that shape features, first-order features and two subgroups of higher-order features possessed a good robustness, unlike the remaining groups of features, which showed large differences in the difference percentage coefficient. Furthermore, using the Spearman’s correlation coefficient, approximately 40% of the selected features differed from the three mentioned groups of images. This is an important consideration for users conducting radiomics studies with image co-registration constraints to avoid errors in cancer diagnosis, prognosis, and clinical outcome prediction.

Respiratory Gating and the Performance of PET/CT in Pulmonary Lesions

Background

Motion artifacts related to the patient’s breathing can be the cause of underestimation of the lesion uptake and can lead to missing of small lung lesions. The respiratory gating (RG) technology has demonstrated a significant increase in image quality.

Objective

The aim of this paper was to evaluate the advantages of RG technique on PET/CT performance in lung lesions. The impact of 4D-PET/CT on diagnosis (metabolic characterization), staging and re-staging lung cancer was also assessed, including its application for radiotherapy planning. Finally, new technologies for respiratory motion management were also discussed.

Methods

A comprehensive electronic search of the literature was performed by using Medline database (PubMed) searching “PET/CT”, “gated” and “lung”. Original articles, review articles, and editorials published in the last 10 years were selected, included and critically reviewed in order to select relevant articles.

Results

Many papers compared Standardized Uptake Value (SUV) in gated and ungated PET studies showing an increase in SUV of gated images, particularly for the small lesions located in medium and lower lung. In addition, other features as Metabolic Tumor Volume (MTV), Total Lesion Glycolysis (TLG) and textural-features presented differences when obtained from gated and ungated PET acquisitions. Besides the increase in quantification, gating techniques can determine an increase in the diagnostic accuracy of PET/CT. Gated PET/CT was evaluated for lung cancer staging, therapy response assessment and for radiation therapy planning.

Conclusion

New technologies able to track the motion of organs lesion directly from raw PET data, can reduce or definitively solve problems (i.e.: extended acquisition time, radiation exposure) currently limiting the use of gated PET/CT in clinical routine.

MRI-based radiomics nomogram for predicting temporal lobe injury after radiotherapy in nasopharyngeal carcinoma

OBJECTIVES

To develop and validate a magnetic resonance imaging (MRI)-based radiomics nomogram model combining radiomic features and clinical factors for the prediction of radiotherapy-induced temporal lobe injury (RTLI) in patients with nasopharyngeal carcinoma (NPC).

METHODS

From 203 NPC cases receiving radiotherapy, 128 RTLI-positive and 278 RTLI-negative lobes were retrospectively analyzed. They were randomly divided into training (n = 285) and validation (n = 121) sets. Three hundred ninety-six texture features based on T2WI images were extracted from each temporal lobe. The minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) were used to reduce the dimension of the features and establish a radiomics signature model. Clinical risk factors and the radiomics signature were combined by multivariable logistic regression analysis to construct a radiomics nomogram model. We assessed the performance of the radiomics nomogram on discrimination, calibration, and clinical utility.

RESULTS

The radiomics signature consisted of 14 selected features that were significantly associated with RTLI. In the training set, the radiomics nomogram model demonstrated a better predictive performance (AUC, 0.87; 95% CI, 0.82-0.91) than the radiomics model (AUC, 0.71; 95% CI, 0.65-0.78) and clinical model (AUC, 0.73; 95% CI, 0.67-0.79). These results were confirmed in the validation set. The radiomics nomogram model demonstrated good calibration and was clinically useful by decision curve analysis.

CONCLUSION

The radiomics nomogram model combining radiomics signatures and clinical factors is an effective method for the noninvasive prediction of RTLI in NPC patients after radiotherapy.

KEY POINTS

• The radiomics model based on T2WI images at the end of intensity-modulated radiotherapy can predict radiotherapy-induced temporal lobe injury in patients with NPC. • Dosimetric factors can improve the prediction performance of the radiomics model in predicting radiotherapy-induced temporal lobe injury. • An MRI-based radiomics nomogram combining radiomics signatures and clinical factors had better prediction performance than both radiomics and clinical model for the prediction of radiotherapy-induced temporal lobe injury in patients with NPC.

Noninvasive assessment of coronary microvascular dysfunction using SPECT myocardial perfusion imaging and myocardial perfusion entropy quantification in a rodent model of type 2 diabetes

PURPOSE

Coronary microvascular dysfunction (CMVD) plays a major role in the occurrence of cardiovascular events (CVE). We recently suggested the clinical potential of myocardial perfusion entropy (MPE) quantification from SPECT myocardial perfusion images (MPI) for the prognosis of CVE occurrence. We hypothesized that the quantification of MPE from SPECT MPI would allow the assessment of CMVD-related MPE variations in a preclinical model of type 2 diabetes (T2D) including treatment with the anti-diabetic incretin liraglutide (LIR).

METHODS

Optimal conditions for the preclinical quantification of MPE using ²⁰¹Tl SPECT MPI were determined in rats with a T2D-like condition induced by a high-fat diet and streptozotocin injection (feasibility study, n = 43). Using such conditions, echocardiography and post-mortem LV capillary density evaluation were then used in order to assess the effect of LIR and the ability of MPE to assess CMVD (therapeutic study, n = 39).

RESULTS

The feasibility study identified dobutamine stress and acute NO synthase and cyclooxygenase inhibition as optimal conditions for the quantification of MPE, with significant increases in MPE being observed in T2D animals (P < 0.01 vs controls). In the therapeutic study, T2D rats were hyperglycemic (5.5 ± 0.5 vs 1.1 ± 0.3 g/L for controls, P < 0.001) and had a significantly lower left ventricular ejection fraction (LVEF) (65 ± 4% vs 74 ± 9%, P < 0.01) and LV capillary density (2400 ± 300 vs 2800 ± 600 mm^-3, P < 0.05). LIR partially restored glycemia (3.9 ± 0.6 g/L, P < 0.05 vs controls and T2D), totally prevented LVEF impairment (72 ± 7%, P = NS vs CTL), with no significant effect on capillary density. MPE was significantly increased in T2D rats (7.6 ± 0.5 vs 7.1 ± 0.5, P < 0.05), with no significant improvement in T2D-LIR rats (7.4 ± 0.4, P = NS vs controls and T2D).

CONCLUSION

MPE quantification allowed the preclinical noninvasive assessment of CMVD. Both MPE and capillary density quantification suggested that LIR did not improve T2D-induced CMVD. The relevance of MPE for CMVD assessment warrants further clinical investigation.

Value of PET imaging for radiation therapy

This comprehensive review written by experts in their field gives an overview on the current status of incorporating positron emission tomography (PET) into radiation treatment planning. Moreover, it highlights ongoing studies for treatment individualisation and per-treatment tumour response monitoring for various primary tumours. Novel tracers and image analysis methods are discussed. The authors believe this contribution to be of crucial value for experts in the field as well as for policy makers deciding on the reimbursement of this powerful imaging modality.

Value of PET imaging for radiation therapy

This comprehensive review written by experts in their field gives an overview on the current status of incorporating positron emission tomography (PET) into radiation treatment planning. Moreover, it highlights ongoing studies for treatment individualisation and per-treatment tumour response monitoring for various primary tumours. Novel tracers and image analysis methods are discussed. The authors believe this contribution to be of crucial value for experts in the field as well as for policy makers deciding on the reimbursement of this powerful imaging modality.

Prognostic value of 18F-FDG PET/CT with texture analysis in patients with rectal cancer treated by surgery

PURPOSE

The aim of this study was to evaluate the ability of texture analysis using pretreatment 18F-FDG PET/CT to predict prognosis in patients with surgically treated rectal cancer.

METHODS

We analyzed 94 patients with pathologically proven rectal cancer who underwent pretreatment 18F-FDG PET/CT and were subsequently treated with surgery. The volume of interest of the primary tumor was defined using a threshold of 40% of the maximum standardized uptake value (SUVmax), and conventional (SUVmax, metabolic tumor volume [MTV], total lesion glycolysis [TLG]) and textural PET features were extracted. Harmonization of PET features was performed with the ComBat method. The study endpoints were overall survival (OS) and progression-free survival (PFS), and the prognostic value of PET features was evaluated by Cox regression analysis.

RESULTS

In the follow-up period (median 41.7 [interquartile range, 30.5-60.4] months), 21 (22.3%) and 30 (31.9%) patients had cancer-related death or disease progression, respectively. Univariate analysis revealed a significant association of (1) MTV, TLG, and gray-level co-occurrence matrix (GLCM) entropy with OS; and (2) SUVmax, MTV, TLG, and GLCM entropy with PFS. In multivariate analysis including clinical characteristics, GLCM entropy (≥ 2.13) was the only relevant prognostic PET feature for poor OS (hazard ratio [HR]: 4.16, p = 0.035) and PFS (HR: 2.70, p = 0.046).

CONCLUSION

GLCM entropy, which indicates metabolic intratumoral heterogeneity, was an independent prognostic factor in patients with surgically treated rectal cancer. Compared with conventional PET features, GLCM entropy has better predictive value and shows potential to facilitate precision medicine.

Artificial Intelligence and Radiomics in Head and Neck Cancer Care: Opportunities, Mechanics, and Challenges

The advent of large-scale high-performance computing has allowed the development of machine-learning techniques in oncologic applications. Among these, there has been substantial growth in radiomics (machine-learning texture analysis of images) and artificial intelligence (which uses deep-learning techniques for "learning algorithms"); however, clinical implementation has yet to be realized at scale. To improve implementation, opportunities, mechanics, and challenges, models of imaging-enabled artificial intelligence approaches need to be understood by clinicians who make the treatment decisions. This article aims to convey the basic conceptual premises of radiomics and artificial intelligence using head and neck cancer as a use case. This educational overview focuses on approaches for head and neck oncology imaging, detailing current research efforts and challenges to implementation.

Radiomics Analysis of 3D Dose Distributions to Predict Toxicity of Radiotherapy for Cervical Cancer

Standard treatment for locally advanced cervical cancer (LACC) is chemoradiotherapy followed by brachytherapy. Despite radiation therapy advances, the toxicity rate remains significant. In this study, we compared the prediction of toxicity events after radiotherapy for locally advanced cervical cancer (LACC), based on either dose-volume histogram (DVH) parameters or the use of a radiomics approach applied to dose maps at the voxel level. Toxicity scores using the Common Terminology Criteria for Adverse Events (CTCAE v4), spatial dose distributions, and usual clinical predictors for the toxicity of 102 patients treated with chemoradiotherapy followed by brachytherapy for LACC were used in this study. In addition to usual DVH parameters, 91 radiomic features were extracted from rectum, bladder and vaginal 3D dose distributions, after discretization into a fixed bin width of 1 Gy. They were evaluated for predictive modelling of rectal, genitourinary (GU) and vaginal toxicities (grade ≥ 2). Logistic Normal Tissue Complication Probability (NTCP) models were derived using clinical parameters only or combinations of clinical, DVH and radiomics. For rectal acute/late toxicities, the area under the curve (AUC) using clinical parameters was 0.53/0.65, which increased to 0.66/0.63, and 0.76/0.87, with the addition of DVH or radiomics parameters, respectively. For GU acute/late toxicities, the AUC increased from 0.55/0.56 (clinical only) to 0.84/0.90 (+DVH) and 0.83/0.96 (clinical + DVH + radiomics). For vaginal acute/late toxicities, the AUC increased from 0.51/0.57 (clinical only) to 0.58/0.72 (+DVH) and 0.82/0.89 (clinical + DVH + radiomics). The predictive performance of NTCP models based on radiomics features was higher than the commonly used clinical and DVH parameters. Dosimetric radiomics analysis is a promising tool for NTCP modelling in radiotherapy.

Multiparameter Analysis Using 18F-FDG PET/CT in the Differential Diagnosis of Pancreatic Cystic Neoplasms

Purpose

To evaluate multiparametric analysis in differential diagnosis between pancreatic serous cystic neoplasms (SCNs) and mucinous cystic neoplasms (MCNs) as well as the differentiation of the benign and malignant MCNs with ¹⁸F-FDG (18-fluorodeoxyglucose) PET/CT (positron emission tomography).

Methods

Forty patients with total of 41 lesions (SCNs: 27/41; MCNs: 14/41), who were preoperatively examined with ¹⁸F-FDG PET/CT, were retrospectively analyzed. Multiple quantitative parameters using conventional and texture features were included. The combined model was established with complementary PET/MR parameters. The differential diagnostic efficacy of each independent parameter and the combined model were evaluated with receiver operating characteristic (ROC) analysis. Integrated discriminatory improvement (IDI) and net reclassification improvement (NRI) were used to evaluate improvement of diagnostic efficacy by using combination of multiple parameters.

Results

Among all independent parameters, the percentile 5th (0.88 ± 0.38 vs 0.47 ± 0.23, P < 0.001) showed the highest discriminative diagnostic value. The combination of multiple parameters can improve the differential diagnostic efficacy of SCNs and MCNs (sensitivity = 71.4%, specificity = 77.8%, and AUC = 0.788), and the addition of texture parameters to the conventional parameters allowed a significant reclassification with IDI = 0.236 (95% CI: 0.095-0.377) and categorical NRI = 0.434 (95% CI: 0.030-0.838). SURmax (tumor to normal pancreas ratio, T/P) and SURmax (tumor to aorta ratio, T/A) both showed the highest discriminative diagnostic value (sensitivity = 100.0%, specificity = 70.0%, AUC = 0.900, and Youden index = 0.700) in the differential diagnosis of benign and malignant MCNs, with the cutoff values of 0.84 and 0.90, respectively.

Conclusion

Combination of multiple parameters using ¹⁸F-FDG PET/CT could further improve differentiation between pancreatic SCNs and MCNs. SURmax (T/P) and SURmax (T/A) could improve differential diagnosis of benign and malignant MCNs.

Deep Neural Networks and Transfer Learning on a Multivariate Physiological Signal Dataset

While Deep Neural Networks (DNNs) and Transfer Learning (TL) have greatly contributed to several medical and clinical disciplines, the application to multivariate physiological datasets is still limited. Current examples mainly focus on one physiological signal and can only utilise applications that are customised for that specific measure, thus it limits the possibility of transferring the trained DNN to other domains. In this study, we composed a dataset (n=813) of six different types of physiological signals (Electrocardiogram, Electrodermal activity, Electromyogram, Photoplethysmogram, Respiration and Acceleration). Signals were collected from 232 subjects using four different acquisition devices. We used a DNN to classify the type of physiological signal and to demonstrate how the TL approach allows the exploitation of the efficiency of DNNs in other domains. After the DNN was trained to optimally classify the type of signal, the features that were automatically extracted by the DNN were used to classify the type of device used for the acquisition using a Support Vector Machine. The dataset, the code and the trained parameters of the DNN are made publicly available to encourage the adoption of DNN and TL in applications with multivariate physiological signals.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Artificial Intelligence and the Medical Physicist: Welcome to the Machine

Artificial intelligence (AI) is a branch of computer science dedicated to giving machines or computers the ability to perform human-like cognitive functions, such as learning, problem-solving, and decision making. Since it is showing superior performance than well-trained human beings in many areas, such as image classification, object detection, speech recognition, and decision-making, AI is expected to change profoundly every area of science, including healthcare and the clinical application of physics to healthcare, referred to as medical physics. As a result, the Italian Association of Medical Physics (AIFM) has created the “AI for Medical Physics” (AI4MP) group with the aims of coordinating the efforts, facilitating the communication, and sharing of the knowledge on AI of the medical physicists (MPs) in Italy. The purpose of this review is to summarize the main applications of AI in medical physics, describe the skills of the MPs in research and clinical applications of AI, and define the major challenges of AI in healthcare.

Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients

OBJECTIVE

The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging.

MATERIAL AND METHODS

Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M).

RESULTS

In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%.

CONCLUSION

This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes.

KEY POINTS

• Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.

Association of visual and quantitative heterogeneity of 18F-FDG PET images with treatment response in locally advanced rectal cancer: A feasibility study

BACKGROUND AND PURPOSE

Few tools are available to predict tumor response to treatment. This retrospective study assesses visual and automatic heterogeneity from 18F-FDG PET images as predictors of response in locally advanced rectal cancer.

METHODS

This study included 37 LARC patients who underwent an 18F-FDG PET before their neoadjuvant therapy. One expert segmented the tumor from the PET images. Blinded to the patient´s outcome, two experts established by consensus a visual score for tumor heterogeneity. Metabolic and texture parameters were extracted from the tumor area. Multivariate binary logistic regression with cross-validation was used to estimate the clinical relevance of these features. Area under the ROC Curve (AUC) of each model was evaluated. Histopathological tumor regression grade was the ground-truth.

RESULTS

Standard metabolic parameters could discriminate 50.1% of responders (AUC = 0.685). Visual heterogeneity classification showed correct assessment of the response in 75.4% of the sample (AUC = 0.759). Automatic quantitative evaluation of heterogeneity achieved a similar predictive capacity (73.1%, AUC = 0.815).

CONCLUSION

A response prediction model in LARC based on tumor heterogeneity (assessed either visually or with automatic texture measurement) shows that texture features may complement the information provided by the metabolic parameters and increase prediction accuracy.

Is FDG-PET texture analysis related to intratumor biological heterogeneity in lung cancer?

OBJECTIVES

We aimed at investigating the origin of the correlations between tumor volume and ¹⁸F-FDG-PET texture indices in lung cancer.

METHODS

Eighty-five consecutive patients with newly diagnosed non-small cell lung cancer (NSCLC) underwent a ¹⁸F-FDG-PET/CT scan before treatment. Seven phantom spheres uniformly filled with ¹⁸F-FDG, and covering a range of activities and volumes similar to that found in lung tumors, were also scanned. Established texture indices were computed for lung tumors and homogeneous spheres. The dependence between textural indices and volume in homogeneous spheres was modeled and then used to predict texture indices in lung tumors. Correlation analyses were carried out between predicted and texture features measured in lung tumors. Cox proportional hazards regression was used to investigate the associations between overall survival and volume-adjusted textural features.

RESULTS

All textural features showed strong, non-linear correlations with volume, both in tumors and homogeneous spheres. Correlations between predicted versus measured texture features were very high for contrast (r² = 0.91), dissimilarity (r² = 0.90), ZP (r² = 0.90), GLNN (r² = 0.86), and homogeneity (r² = 0.82); high for entropy (r² = 0.50) and HILAE (r² = 0.53); and low for energy (r² = 0.30). Cox regressions showed that among volume-adjusted features, only HILAE was associated with overall survival (b = - 0.35, p = 0.008).

CONCLUSION

We have shown that texture indices previously found to be correlated with a number of clinically relevant outcomes might not provide independent information apart from that driven by their correlation with tumor volume, suggesting that these metrics might not be suitable as intratumor heterogeneity markers.

KEY POINTS

• Associations between texture FDG-PET indices and overall survival have been widely reported in lung cancer, with tumor volume also being associated with overall survival, and therefore, it is still unclear whether the predictive power of textural indices is simply driven by this correlation. • Our results demonstrated strong non-linear correlations between textural indices and volume, showing an analogous behavior for lung tumors from patients and homogeneous spheres inserted in phantoms. • Our findings showed that texture FDG-PET indices might not provide independent information apart from that driven by their correlation with tumor volume.

Positron Emission Tomography for Response Evaluation in Microenvironment-Targeted Anti-Cancer Therapy

Therapeutic response is evaluated using the diameter of tumors and quantitative parameters of 2-[¹⁸F] fluoro-2-deoxy-d-glucose positron emission tomography (FDG-PET). Tumor response to molecular-targeted drugs and immune checkpoint inhibitors is different from conventional chemotherapy in terms of temporal metabolic alteration and morphological change after the therapy. Cancer stem cells, immunologically competent cells, and metabolism of cancer are considered targets of novel therapy. Accumulation of FDG reflects the glucose metabolism of cancer cells as well as immune cells in the tumor microenvironment, which differs among patients according to the individual immune function; however, FDG-PET could evaluate the viability of the tumor as a whole. On the other hand, specific imaging and cell tracking of cancer cell or immunological cell subsets does not elucidate tumor response in a complexed interaction in the tumor microenvironment. Considering tumor heterogeneity and individual variation in therapeutic response, a radiomics approach with quantitative features of multimodal images and deep learning algorithm with reference to pathologic and genetic data has the potential to improve response assessment for emerging cancer therapy.

A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method

Background

Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure.

This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[¹¹C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification.

Results

For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUV_mean, SUL_peak, SUV_min, SUL_peak prod-surface-area, SUV_mean prod-sphericity, surface mean SUV 3, SUL_peak prod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features.

Conclusions

The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.

Predictive value of quantitative 18F-FDG-PET radiomics analysis in patients with head and neck squamous cell carcinoma

BACKGROUND

Radiomics is aimed at image-based tumor phenotyping, enabling application within clinical-decision-support-systems to improve diagnostic accuracy and allow for personalized treatment. The purpose was to identify predictive 18-fluor-fluoro-2-deoxyglucose (¹⁸F-FDG) positron-emission tomography (PET) radiomic features to predict recurrence, distant metastasis, and overall survival in patients with head and neck squamous cell carcinoma treated with chemoradiotherapy.

METHODS

Between 2012 and 2018, 103 retrospectively (training cohort) and 71 consecutively included patients (validation cohort) underwent ¹⁸F-FDG-PET/CT imaging. The 434 extracted radiomic features were subjected, after redundancy filtering, to a projection resulting in outcome-independent meta-features (factors). Correlations between clinical, first-order ¹⁸F-FDG-PET parameters (e.g., SUVmean), and factors were assessed. Factors were combined with ¹⁸F-FDG-PET and clinical parameters in a multivariable survival regression and validated. A clinically applicable risk-stratification was constructed for patients' outcome.

RESULTS

Based on 124 retained radiomic features from 103 patients, 8 factors were constructed. Recurrence prediction was significantly most accurate by combining HPV-status, SUVmean, SUVpeak, factor 3 (histogram gradient and long-run-low-grey-level-emphasis), factor 4 (volume-difference, coarseness, and grey-level-non-uniformity), and factor 6 (histogram variation coefficient) (CI = 0.645). Distant metastasis prediction was most accurate assessing metabolic-active tumor volume (MATV)(CI = 0.627). Overall survival prediction was most accurate using HPV-status, SUVmean, SUVmax, factor 1 (least-axis-length, non-uniformity, high-dependence-of-high grey-levels), and factor 5 (aspherity, major-axis-length, inversed-compactness and, inversed-flatness) (CI = 0.764).

CONCLUSIONS

Combining HPV-status, first-order ¹⁸F-FDG-PET parameters, and complementary radiomic factors was most accurate for time-to-event prediction. Predictive phenotype-specific tumor characteristics and interactions might be captured and retained using radiomic factors, which allows for personalized risk stratification and optimizing personalized cancer care.

TRIAL REGISTRATION

Trial NL3946 (NTR4111), local ethics commission reference: Prediction 2013.191 and 2016.498. Registered 7 August 2013, https://www.trialregister.nl/trial/3946.

18F-FDG PET/CT radiomic predictors of pathologic complete response (pCR) to neoadjuvant chemotherapy in breast cancer patients

PURPOSE

Pathologic complete response (pCR) to neoadjuvant chemotherapy (NAC) is commonly accepted as the gold standard to assess outcome after NAC in breast cancer patients. ¹⁸F-Fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) has unique value in tumor staging, predicting prognosis, and evaluating treatment response. Our aim was to determine if we could identify radiomic predictors from PET/CT in breast cancer patient therapeutic efficacy prior to NAC.

METHODS

This retrospective study included 100 breast cancer patients who received NAC; there were 2210 PET/CT radiomic features extracted. Unsupervised and supervised machine learning models were used to identify the prognostic radiomic predictors through the following: (1) selection of the significant (p < 0.05) imaging features from consensus clustering and the Wilcoxon signed-rank test; (2) selection of the most discriminative features via univariate random forest (Uni-RF) and the Pearson correlation matrix (PCM); and (3) determination of the most predictive features from a traversal feature selection (TFS) based on a multivariate random forest (RF). The prediction model was constructed with RF and then validated with 10-fold cross-validation for 30 times and then independently validated. The performance of the radiomic predictors was measured in terms of area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

The PET/CT radiomic predictors achieved a prediction accuracy of 0.857 (AUC = 0.844) on the training split set and 0.767 (AUC = 0.722) on the independent validation set. When age was incorporated, the accuracy for the split set increased to 0.857 (AUC = 0.958) and 0.8 (AUC = 0.73) for the independent validation set and both outperformed the clinical prediction model. We also found a close association between the radiomic features, receptor expression, and tumor T stage.

CONCLUSION

Radiomic predictors from pre-treatment PET/CT scans when combined with patient age were able to predict pCR after NAC. We suggest that these data will be valuable for patient management.

Predictive Power of a Radiomic Signature Based on 18F-FDG PET/CT Images for EGFR Mutational Status in NSCLC

Radiomics has become an area of interest for tumor characterization in ¹⁸F-Fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) imaging. The aim of the present study was to demonstrate how imaging phenotypes was connected to somatic mutations through an integrated analysis of 115 non-small cell lung cancer (NSCLC) patients with somatic mutation testings and engineered computed PET/CT image analytics. A total of 38 radiomic features quantifying tumor morphological, grayscale statistic, and texture features were extracted from the segmented entire-tumor region of interest (ROI) of the primary PET/CT images. The ensembles for boosting machine learning scheme were employed for classification, and the least absolute shrink age and selection operator (LASSO) method was used to select the most predictive radiomic features for the classifiers. A radiomic signature based on both PET and CT radiomic features outperformed individual radiomic features, the PET or CT radiomic signature, and the conventional PET parameters including the maximum standardized uptake value (SUVmax), SUVmean, SUVpeak, metabolic tumor volume (MTV), and total lesion glycolysis (TLG), in discriminating between mutant-type of epidermal growth factor receptor (EGFR) and wild-type of EGFR- cases with an AUC of 0.805, an accuracy of 80.798%, a sensitivity of 0.826 and a specificity of 0.783. Consistently, a combined radiomic signature with clinical factors exhibited a further improved performance in EGFR mutation differentiation in NSCLC. In conclusion, tumor imaging phenotypes that are driven by somatic mutations may be predicted by radiomics based on PET/CT images.

Machine learning for radiomics-based multimodality and multiparametric modeling

Due to the recent developments of both hardware and software technologies, multimodality medical imaging techniques have been increasingly applied in clinical practice and research studies. Previously, the application of multimodality imaging in oncology has been mainly related to combining anatomical and functional imaging to improve diagnostic specificity and/or target definition, such as positron emission tomography/computed tomography (PET/CT) and single-photon emission CT (SPECT)/CT. More recently, the fusion of various images, such as multiparametric magnetic resonance imaging (MRI) sequences, different PET tracer images, PET/MRI, has become more prevalent, which has enabled more comprehensive characterization of the tumor phenotype. In order to take advantage of these valuable multimodal data for clinical decision making using radiomics, we present two ways to implement the multimodal image analysis, namely radiomic (handcrafted feature) based and deep learning (machine learned feature) based methods. Applying advanced machine (deep) learning algorithms across multimodality images have shown better results compared with single modality modeling for prognostic and/or prediction of clinical outcomes. This holds great potentials for providing more personalized treatment for patients and achieve better outcomes.

Exploring Tumor Heterogeneity Using PET Imaging: The Big Picture

Personalized medicine represents a major goal in oncology. It has its underpinning in the identification of biomarkers with diagnostic, prognostic, or predictive values. Nowadays, the concept of biomarker no longer necessarily corresponds to biological characteristics measured ex vivo but includes complex physiological characteristics acquired by different technologies. Positron-emission-tomography (PET) imaging is an integral part of this approach by enabling the fine characterization of tumor heterogeneity in vivo in a non-invasive way. It can effectively be assessed by exploring the heterogeneous distribution and uptake of a tracer such as 18F-fluoro-deoxyglucose (FDG) or by using multiple radiopharmaceuticals, each providing different information. These two approaches represent two avenues of development for the research of new biomarkers in oncology. In this article, we review the existing evidence that the measurement of tumor heterogeneity with PET imaging provide essential information in clinical practice for treatment decision-making strategy, to better select patients with poor prognosis for more intensive therapy or those eligible for targeted therapy.