A Deep Look Into the Future of Quantitative Imaging in Oncology: A Statement of Working Principles and Proposal for Change

Radiomics-driven personalized radiotherapy for primary and recurrent tumors: A general review with a focus on reirradiation

PURPOSE

This review systematically investigates the role of radiomics in radiotherapy, with a particular emphasis on the use of quantitative imaging biomarkers for predicting clinical outcomes, assessing toxicity, and optimizing treatment planning. While the review encompasses various applications of radiomics in radiotherapy, it particularly highlights its potential for guiding reirradiation of recurrent cancers.

METHODS

A systematic review was conducted based on a Medline search with the search engine PubMed using the keywords "radiomics or radiomic" and "radiotherapy or reirradiation". Out of 189 abstracts reviewed, 147 original articles were included in the analysis. These studies were categorized by tumor localization, imaging modality, study objectives, and performance metrics, with a particular emphasis on the inclusion of external validation and adherence to a standardized radiomics pipeline.

RESULTS

The review identified 14 tumor localizations, with the majority of studies focusing on lung (33 studies), head and neck (27 studies), and brain (15 studies) cancers. CT was the most frequently employed imaging modality (77 studies) for radiomics, followed by MRI (46 studies) and PET (13 studies). The overall AUC across all studies, primarily focused on predicting the risk of recurrence (94 studies) or toxicity (41 studies), was 0.80 (SD=0.08). However, only 24 studies (16.3%) included external validation, with a slightly lower AUC compared to those without it. For studies using CT versus MRI or PET, both had a median AUC of 0.79, with IQRs of 0.73-0.86 for CT and 0.76-0.855 for MRI/PET, showing no significant differences in performance. Five studies involving reirradiation reported a median AUC of 0.81 (IQR: 0.73-0.825).

CONCLUSION

Radiomics demonstrates considerable potential in personalizing radiotherapy by improving treatment precision through better outcome prediction and treatment planning. However, its clinical adoption is hindered by the lack of external validation and variability in study designs. Future research should focus on implementing rigorous validation methods and standardizing imaging protocols to enhance the reliability and generalizability of radiomics in clinical radiotherapy, with particular attention to its application in reirradiation.

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.

Longitudinal Image Data for Outcome Modeling

In oncology, medical imaging is crucial for diagnosis, treatment planning and therapy execution. Treatment responses can be complex and varied and are known to involve factors of treatment, patient characteristics and tumor microenvironment. Longitudinal image analysis is able to track temporal changes, aiding in disease monitoring, treatment evaluation, and outcome prediction. This allows for the enhancement of personalized medicine. However, analyzing longitudinal 2D and 3D images presents unique challenges, including image registration, reliable segmentation, dealing with variable imaging intervals, and sparse data. This review presents an overview of techniques and methodologies in longitudinal image analysis, with a primary focus on outcome modeling in radiation oncology.

Utility of CT Radiomics and Delta Radiomics for Survival Evaluation in Locally Advanced Nasopharyngeal Carcinoma with Concurrent Chemoradiotherapy

BACKGROUND

A high incidence rate of nasopharyngeal carcinoma (NPC) has been observed in Southeast Asia compared to other parts of the world. Radiomics is a computational tool to predict outcomes and may be used as a prognostic biomarker for advanced NPC treated with concurrent chemoradiotherapy. Recently, radiomic analysis of the peripheral tumor microenvironment (TME), which is the region surrounding the gross tumor volume (GTV), has shown prognostic usefulness. In this study, not only was gross tumor volume (GTVt) analyzed but also tumor peripheral regions (GTVp) were explored in terms of the TME concept. Both radiomic features and delta radiomic features were analyzed using CT images acquired in a routine radiotherapy process.

METHODS

A total of 50 patients with NPC stages III, IVA, and IVB were enrolled between September 2004 and February 2014. Survival models were built using Cox regression with clinical factors (i.e., gender, age, overall stage, T stage, N stage, and treatment dose) and radiomic features. Radiomic features were extracted from GTVt and GTVp. GTVp was created surrounding GTVt for TME consideration. Furthermore, delta radiomics, which is the longitudinal change in quantitative radiomic features, was utilized for analysis. Finally, C-index values were computed using leave-one-out cross-validation (LOOCV) to evaluate the performances of all prognosis models.

RESULTS

Models were built for three different clinical outcomes, including overall survival (OS), local recurrence-free survival (LRFS), and progression-free survival (PFS). The range of the C-index in clinical factor models was (0.622, 0.729). All radiomics models, including delta radiomics models, were in the range of (0.718, 0.872). Among delta radiomics models, GTVt and GTVp were in the range of (0.833, 0.872) and (0.799, 0.834), respectively.

CONCLUSIONS

Radiomic analysis on the proximal region surrounding the gross tumor volume of advanced NPC patients for survival outcome evaluation was investigated, and preliminary positive results were obtained. Radiomic models and delta radiomic models demonstrated performance that was either superior to or comparable with that of conventional clinical models.

RADCURE: An open-source head and neck cancer CT dataset for clinical radiation therapy insights

PURPOSE

This manuscript presents RADCURE, one of the most extensive head and neck cancer (HNC) imaging datasets accessible to the public. Initially collected for clinical radiation therapy (RT) treatment planning, this dataset has been retrospectively reconstructed for use in imaging research.

ACQUISITION AND VALIDATION METHODS

RADCURE encompasses data from 3346 patients, featuring computed tomography (CT) RT simulation images with corresponding target and organ-at-risk contours. These CT scans were collected using systems from three different manufacturers. Standard clinical imaging protocols were followed, and contours were manually generated and reviewed at weekly RT quality assurance rounds. RADCURE imaging and structure set data was extracted from our institution's radiation treatment planning and oncology information systems using a custom-built data mining and processing system. Furthermore, images were linked to our clinical anthology of outcomes data for each patient and includes demographic, clinical and treatment information based on the 7th edition TNM staging system (Tumor-Node-Metastasis Classification System of Malignant Tumors). The median patient age is 63, with the final dataset including 80% males. Half of the cohort is diagnosed with oropharyngeal cancer, while laryngeal, nasopharyngeal, and hypopharyngeal cancers account for 25%, 12%, and 5% of cases, respectively. The median duration of follow-up is five years, with 60% of the cohort surviving until the last follow-up point.

DATA FORMAT AND USAGE NOTES

The dataset provides images and contours in DICOM CT and RT-STRUCT formats, respectively. We have standardized the nomenclature for individual contours-such as the gross primary tumor, gross nodal volumes, and 19 organs-at-risk-to enhance the RT-STRUCT files' utility. Accompanying demographic, clinical, and treatment data are supplied in a comma-separated values (CSV) file format. This comprehensive dataset is publicly accessible via The Cancer Imaging Archive.

POTENTIAL APPLICATIONS

RADCURE's amalgamation of imaging, clinical, demographic, and treatment data renders it an invaluable resource for a broad spectrum of radiomics image analysis research endeavors. Researchers can utilize this dataset to advance routine clinical procedures using machine learning or artificial intelligence, to identify new non-invasive biomarkers, or to forge prognostic models.

The Role of Radiomics in Rectal Cancer

PURPOSE

Radiomics is a promising method for advancing imaging assessment in rectal cancer. This review aims to describe the emerging role of radiomics in the imaging assessment of rectal cancer, including various applications of radiomics based on CT, MRI, or PET/CT.

METHODS

We conducted a literature review to highlight the progress of radiomic research to date and the challenges that need to be addressed before radiomics can be implemented clinically.

RESULTS

The results suggest that radiomics has the potential to provide valuable information for clinical decision-making in rectal cancer. However, there are still challenges in terms of standardization of imaging protocols, feature extraction, and validation of radiomic models. Despite these challenges, radiomics holds great promise for personalized medicine in rectal cancer, with the potential to improve diagnosis, prognosis, and treatment planning. Further research is needed to validate the clinical utility of radiomics and to establish its role in routine clinical practice.

CONCLUSION

Overall, radiomics has emerged as a powerful tool for improving the imaging assessment of rectal cancer, and its potential benefits should not be underestimated.

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.

Multiparametric Oncologic Hybrid Imaging: Machine Learning Challenges and Opportunities

BACKGROUND

Machine learning (ML) is considered an important technology for future data analysis in health care.

METHODS

The inherently technology-driven fields of diagnostic radiology and nuclear medicine will both benefit from ML in terms of image acquisition and reconstruction. Within the next few years, this will lead to accelerated image acquisition, improved image quality, a reduction of motion artifacts and - for PET imaging - reduced radiation exposure and new approaches for attenuation correction. Furthermore, ML has the potential to support decision making by a combined analysis of data derived from different modalities, especially in oncology. In this context, we see great potential for ML in multiparametric hybrid imaging and the development of imaging biomarkers.

RESULTS AND CONCLUSION

In this review, we will describe the basics of ML, present approaches in hybrid imaging of MRI, CT, and PET, and discuss the specific challenges associated with it and the steps ahead to make ML a diagnostic and clinical tool in the future.

KEY POINTS

· ML provides a viable clinical solution for the reconstruction, processing, and analysis of hybrid imaging obtained from MRI, CT, and PET..

Artificial intelligence and radiation effects on brain tissue in glioblastoma patient: preliminary data using a quantitative tool

PURPOSE

The quantification of radiotherapy (RT)-induced functional and morphological brain alterations is fundamental to guide therapeutic decisions in patients with brain tumors. The magnetic resonance imaging (MRI) allows to define structural RT-brain changes, but it is unable to evaluate early injuries and to objectively quantify the volume tissue loss. Artificial intelligence (AI) tools extract accurate measurements that permit an objective brain different region quantification. In this study, we assessed the consistency between an AI software (Quibim Precision^® 2.9) and qualitative neruroradiologist evaluation, and its ability to quantify the brain tissue changes during RT treatment in patients with glioblastoma multiforme (GBM).

METHODS

GBM patients treated with RT and subjected to MRI assessment were enrolled. Each patient, pre- and post-RT, undergoes to a qualitative evaluation with global cerebral atrophy (GCA) and medial temporal lobe atrophy (MTA) and a quantitative assessment with Quibim Brain screening and hippocampal atrophy and asymmetry modules on 19 extracted brain structures features.

RESULTS

A statistically significant strong negative association between the percentage value of the left temporal lobe and the GCA score and the left temporal lobe and the MTA score was found, while a moderate negative association between the percentage value of the right hippocampus and the GCA score and the right hippocampus and the MTA score was assessed. A statistically significant strong positive association between the CSF percentage value and the GCA score and a moderate positive association between the CSF percentage value and the MTA score was found. Finally, quantitative feature values showed that the percentage value of the cerebro-spinal fluid (CSF) statistically differences between pre- and post-RT.

CONCLUSIONS

AI tools can support a correct evaluation of RT-induced brain injuries, allowing an objective and earlier assessment of the brain tissue modifications.

Multi-institutional Prognostic Modeling in Head and Neck Cancer: Evaluating Impact and Generalizability of Deep Learning and Radiomics

Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance.

Significance

ML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation.

Biomarkers of aging

Aging biomarkers are a combination of biological parameters to (i) assess age-related changes, (ii) track the physiological aging process, and (iii) predict the transition into a pathological status. Although a broad spectrum of aging biomarkers has been developed, their potential uses and limitations remain poorly characterized. An immediate goal of biomarkers is to help us answer the following three fundamental questions in aging research: How old are we? Why do we get old? And how can we age slower? This review aims to address this need. Here, we summarize our current knowledge of biomarkers developed for cellular, organ, and organismal levels of aging, comprising six pillars: physiological characteristics, medical imaging, histological features, cellular alterations, molecular changes, and secretory factors. To fulfill all these requisites, we propose that aging biomarkers should qualify for being specific, systemic, and clinically relevant.

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.

Bayesian feature selection for radiomics using reliability metrics

Introduction: Imaging of tumors is a standard step in diagnosing cancer and making subsequent treatment decisions. The field of radiomics aims to develop imaging based biomarkers using methods rooted in artificial intelligence applied to medical imaging. However, a challenging aspect of developing predictive models for clinical use is that many quantitative features derived from image data exhibit instability or lack of reproducibility across different imaging systems or image-processing pipelines.

Methods: To address this challenge, we propose a Bayesian sparse modeling approach for image classification based on radiomic features, where the inclusion of more reliable features is favored via a probit prior formulation.

Results: We verify through simulation studies that this approach can improve feature selection and prediction given correct prior information. Finally, we illustrate the method with an application to the classification of head and neck cancer patients by human papillomavirus status, using as our prior information a reliability metric quantifying feature stability across different imaging systems.

Post-Surgical Imaging Assessment in Rectal Cancer: Normal Findings and Complications

Rectal cancer (RC) is one of the deadliest malignancies worldwide. Surgery is the most common treatment for RC, performed in 63.2% of patients. The type of surgical approach chosen aims to achieve maximum residual function with the lowest risk of recurrence. The selection is made by a multidisciplinary team that assesses the characteristics of the patient and the tumor. Total mesorectal excision (TME), including both low anterior resection (LAR) and abdominoperineal resection (APR), is still the standard of care for RC. Radical surgery is burdened by a 31% rate of major complications (Clavien-Dindo grade 3-4), such as anastomotic leaks and a risk of a permanent stoma. In recent years, less-invasive techniques, such as local excision, have been tested. These additional procedures could mitigate the morbidity of rectal resection, while providing acceptable oncologic results. The "watch and wait" approach is not a globally accepted model of care but encouraging results on selected groups of patients make it a promising strategy. In this plethora of treatments, the radiologist is called upon to distinguish a physiological from a pathological postoperative finding. The aim of this narrative review is to identify the main post-surgical complications and the most effective imaging techniques.

Risk Assessment and Cholangiocarcinoma: Diagnostic Management and Artificial Intelligence

Intrahepatic cholangiocarcinoma (iCCA) is the second most common primary liver tumor, with a median survival of only 13 months. Surgical resection remains the only curative therapy; however, at first detection, only one-third of patients are at an early enough stage for this approach to be effective, thus rendering early diagnosis as an efficient approach to improving survival. Therefore, the identification of higher-risk patients, whose risk is correlated with genetic and pre-cancerous conditions, and the employment of non-invasive-screening modalities would be appropriate. For several at-risk patients, such as those suffering from primary sclerosing cholangitis or fibropolycystic liver disease, the use of periodic (6-12 months) imaging of the liver by ultrasound (US), magnetic Resonance Imaging (MRI)/cholangiopancreatography (MRCP), or computed tomography (CT) in association with serum CA19-9 measurement has been proposed. For liver cirrhosis patients, it has been proposed that at-risk iCCA patients are monitored in a similar fashion to at-risk HCC patients. The possibility of using Artificial Intelligence models to evaluate higher-risk patients could favor the diagnosis of these entities, although more data are needed to support the practical utility of these applications in the field of screening. For these reasons, it would be appropriate to develop screening programs in the research protocols setting. In fact, the success of these programs reauires patient compliance and multidisciplinary cooperation.

Radiomics in Lung Metastases: A Systematic Review

Due to the rich vascularization and lymphatic drainage of the pulmonary tissue, lung metastases (LM) are not uncommon in patients with cancer. Radiomics is an active research field aimed at the extraction of quantitative data from diagnostic images, which can serve as useful imaging biomarkers for a more effective, personalized patient care. Our purpose is to illustrate the current applications, strengths and weaknesses of radiomics for lesion characterization, treatment planning and prognostic assessment in patients with LM, based on a systematic review of the literature.

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.

Dual-center validation of using magnetic resonance imaging radiomics to predict stereotactic radiosurgery outcomes

Background

MRI radiomic features and machine learning have been used to predict brain metastasis (BM) stereotactic radiosurgery (SRS) outcomes. Previous studies used only single-center datasets, representing a significant barrier to clinical translation and further research. This study, therefore, presents the first dual-center validation of these techniques.

Methods

SRS datasets were acquired from 2 centers (n = 123 BMs and n = 117 BMs). Each dataset contained 8 clinical features, 107 pretreatment T1w contrast-enhanced MRI radiomic features, and post-SRS BM progression endpoints determined from follow-up MRI. Random decision forest models were used with clinical and/or radiomic features to predict progression. 250 bootstrap repetitions were used for single-center experiments.

Results

Training a model with one center's dataset and testing it with the other center's dataset required using a set of features important for outcome prediction at both centers, and achieved area under the receiver operating characteristic curve (AUC) values up to 0.70. A model training methodology developed using the first center's dataset was locked and externally validated with the second center's dataset, achieving a bootstrap-corrected AUC of 0.80. Lastly, models trained on pooled data from both centers offered balanced accuracy across centers with an overall bootstrap-corrected AUC of 0.78.

Conclusions

Using the presented validated methodology, radiomic models trained at a single center can be used externally, though they must utilize features important across all centers. These models' accuracies are inferior to those of models trained using each individual center's data. Pooling data across centers shows accurate and balanced performance, though further validation is required.

[18F]-FDG PET and MRI radiomic signatures to predict the risk and the location of tumor recurrence after re-irradiation in head and neck cancer

PURPOSE

To evaluate whether radiomics from [18F]-FDG PET and/or MRI before re-irradiation (reRT) of recurrent head and neck cancer (HNC) could predict the occurrence and the location "in-field" or "outside" of a second locoregional recurrence (LR).

METHODS

Among the 55 patients re-irradiated at curative intend for HNC from 2012 to 2019, 48 had an MRI and/or PET before the start of the reRT. Thirty-nine radiomic features (RF) were extracted from the re-irradiated GTV (rGTV) using LIFEx software. Student t tests and Spearman correlation coefficient were used to select the RF that best separate patients who recurred from those who did not, and "in-field" from "outside" recurrences. Principal component analysis involving these features only was used to create a prediction model. Leave-one-out cross-validation was performed to evaluate the models.

RESULTS

After a median follow-up of 17 months, 40/55 patients had developed a second LR, including 18 "in-field" and 22 "outside" recurrences. From pre-reRT MRI, a model based on three RF (GLSZM_SZHGLE, GLSZM_LGLZE, and skewness) predicted whether patients would recur with a balanced accuracy (BA) of 83.5%. Another model from pre-reRT MRI based on three other RF (GLSZM_ LZHGE, NGLDM_Busyness, and GLZLM_SZE) predicted whether patients would recur "in-field" or "outside" with a BA of 78.5%. From pre-reRT PET, a model based on four RF (Kurtosis, SUVbwmin, GLCM_Correlation, and GLCM_Contrast) predicted the LR location with a BA of 84.5%.

CONCLUSION

RF characterizing tumor heterogeneity extracted from pre-reRT PET and MRI predicted whether patients would recur, and whether they would recur "in-field" or "outside".

Tumor Microenvironment, Radiology, and Artificial Intelligence: Should We Consider Tumor Periphery?

OBJECTIVES

The tumor microenvironment (TME) consists of cellular and noncellular components which enable the tumor to interact with its surroundings and plays an important role in the tumor progression and how the immune system reacts to the malignancy. In the present study, we investigate the diagnostic potential of the TME in differentiating benign and malignant lesions using image quantification and machine learning.

METHODS

A total of 229 breast lesions and 220 cervical lymph nodes were included in the study. A group of expert radiologists first performed medical imaging and segmented the lesions, after which a rectangular mask was drawn, encompassing all of the contouring. The mask was extended in each axis up to 50%, and 29 radiomics features were extracted from each mask. Radiomics features that showed a significant difference in each contour were used to develop a support vector machine (SVM) classifier for benign and malignant lesions in breast and lymph node images separately.

RESULTS

Single radiomics features extracted from extended contours outperformed radiologists' contours in both breast and lymph node lesions. Furthermore, when fed into the SVM model, the extended models also outperformed the radiologist's contour, achieving an area under the receiver operating characteristic curve of 0.887 and 0.970 in differentiating breast and lymph node lesions, respectively.

CONCLUSIONS

Our results provide convincing evidence regarding the importance of the tumor periphery and TME in medical imaging diagnosis. We propose that the immediate tumor periphery should be considered for differentiating benign and malignant lesions in image quantification studies.

The role of artificial intelligence in veterinary radiation oncology

Veterinary radiation oncology regularly deploys sophisticated contouring, image registration, and treatment planning optimization software for patient care. Over the past decade, advances in computing power and the rapid development of neural networks, open-source software packages, and data science have been realized and resulted in new research and clinical applications of artificial intelligent (AI) systems in radiation oncology. These technologies differ from conventional software in their level of complexity and ability to learn from representative and local data. We provide clinical and research application examples of AI in human radiation oncology and their potential applications in veterinary medicine throughout the patient's care-path: from treatment simulation, deformable registration, auto-segmentation, automated treatment planning and plan selection, quality assurance, adaptive radiotherapy, and outcomes modeling. These technologies have the potential to offer significant time and cost savings in the veterinary setting; however, since the range of usefulness of these technologies have not been well studied nor understood, care must be taken if adopting AI technologies in clinical practice. Over the next several years, some practical and realizable applications of AI in veterinary radiation oncology include automated segmentation of normal tissues and tumor volumes, deformable registration, multi-criteria plan optimization, and adaptive radiotherapy. Keys in achieving success in adopting AI in veterinary radiation oncology include: establishing "truth-data"; data harmonization; multi-institutional data and collaborations; standardized dose reporting and taxonomy; adopting an open access philosophy, data collection and curation; open-source algorithm development; and transparent and platform-independent code development.

Wasserstein-based texture analysis in radiomic studies

The emerging field of radiomics that transforms standard-of-care images to quantifiable scalar statistics endeavors to reveal the information hidden in these macroscopic images. The concept of texture is widely used and essential in many radiomic-based studies. Practice usually reduces spatial multidimensional texture matrices, e.g., gray-level co-occurrence matrices (GLCMs), to summary scalar features. These statistical features have been demonstrated to be strongly correlated and tend to contribute redundant information; and does not account for the spatial information hidden in the multivariate texture matrices. This study proposes a novel pipeline to deal with spatial texture features in radiomic studies. A new set of textural features that preserve the spatial information inherent in GLCMs is proposed and used for classification purposes. The set of the new features uses the Wasserstein metric from optimal mass transport theory (OMT) to quantify the spatial similarity between samples within a given label class. In particular, based on a selected subset of texture GLCMs from the training cohort, we propose new representative spatial texture features, which we incorporate into a supervised image classification pipeline. The pipeline relies on the support vector machine (SVM) algorithm along with Bayesian optimization and the Wasserstein metric. The selection of the best GLCM references is considered for each classification label and is performed during the training phase of the SVM classifier using a Bayesian optimizer. We assume that sample fitness is defined based on closeness (in the sense of the Wasserstein metric) and high correlation (Spearman's rank sense) with other samples in the same class. Moreover, the newly defined spatial texture features consist of the Wasserstein distance between the optimally selected references and the remaining samples. We assessed the performance of the proposed classification pipeline in diagnosing the coronavirus disease 2019 (COVID-19) from computed tomographic (CT) images. To evaluate the proposed spatial features' added value, we compared the performance of the proposed classification pipeline with other SVM-based classifiers that account for different texture features, namely: statistical features only, optimized spatial features using Euclidean metric, non-optimized spatial features with Wasserstein metric. The proposed technique, which accounts for the optimized spatial texture feature with Wasserstein metric, shows great potential in classifying new COVID CT images that the algorithm has not seen in the training step. The MATLAB code of the proposed classification pipeline is made available. It can be used to find the best reference samples in other data cohorts, which can then be employed to build different prediction models.

A global taxonomy of interpretable AI: unifying the terminology for the technical and social sciences

Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are "weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a-highly needed-standard for the communication among interdisciplinary areas of AI.

Development of a Hybrid-Imaging-Based Prognostic Index for Metastasized-Melanoma Patients in Whole-Body 18F-FDG PET/CT and PET/MRI Data

Besides tremendous treatment success in advanced melanoma patients, the rapid development of oncologic treatment options comes with increasingly high costs and can cause severe life-threatening side effects. For this purpose, predictive baseline biomarkers are becoming increasingly important for risk stratification and personalized treatment planning. Thus, the aim of this pilot study was the development of a prognostic tool for the risk stratification of the treatment response and mortality based on PET/MRI and PET/CT, including a convolutional neural network (CNN) for metastasized-melanoma patients before systemic-treatment initiation. The evaluation was based on 37 patients (19 f, 62 ± 13 y/o) with unresectable metastasized melanomas who underwent whole-body 18F-FDG PET/MRI and PET/CT scans on the same day before the initiation of therapy with checkpoint inhibitors and/or BRAF/MEK inhibitors. The overall survival (OS), therapy response, metastatically involved organs, number of lesions, total lesion glycolysis, total metabolic tumor volume (TMTV), peak standardized uptake value (SULpeak), diameter (Dmlesion) and mean apparent diffusion coefficient (ADCmean) were assessed. For each marker, a Kaplan−Meier analysis and the statistical significance (Wilcoxon test, paired t-test and Bonferroni correction) were assessed. Patients were divided into high- and low-risk groups depending on the OS and treatment response. The CNN segmentation and prediction utilized multimodality imaging data for a complementary in-depth risk analysis per patient. The following parameters correlated with longer OS: a TMTV < 50 mL; no metastases in the brain, bone, liver, spleen or pleura; ≤4 affected organ regions; no metastases; a Dmlesion > 37 mm or SULpeak < 1.3; a range of the ADCmean < 600 mm2/s. However, none of the parameters correlated significantly with the stratification of the patients into the high- or low-risk groups. For the CNN, the sensitivity, specificity, PPV and accuracy were 92%, 96%, 92% and 95%, respectively. Imaging biomarkers such as the metastatic involvement of specific organs, a high tumor burden, the presence of at least one large lesion or a high range of intermetastatic diffusivity were negative predictors for the OS, but the identification of high-risk patients was not feasible with the handcrafted parameters. In contrast, the proposed CNN supplied risk stratification with high specificity and sensitivity.

Radiomic Analysis: Study Design, Statistical Analysis, and Other Bias Mitigation Strategies

Rapid advances in automated methods for extracting large numbers of quantitative features from medical images have led to tremendous growth of publications reporting on radiomic analyses. Translation of these research studies into clinical practice can be hindered by biases introduced during the design, analysis, or reporting of the studies. Herein, the authors review biases, sources of variability, and pitfalls that frequently arise in radiomic research, with an emphasis on study design and statistical analysis considerations. Drawing on existing work in the statistical, radiologic, and machine learning literature, approaches for avoiding these pitfalls are described.

Role of Artificial Intelligence in Radiogenomics for Cancers in the Era of Precision Medicine

Simple Summary

Recently, radiogenomics has played a significant role and offered a new understanding of cancer’s biology and behavior in response to standard therapy. It also provides a more precise prognosis, investigation, and analysis of the patient’s cancer. Over the years, Artificial Intelligence (AI) has provided a significant strength in radiogenomics. In this paper, we offer computational and oncological prospects of the role of AI in radiogenomics, as well as its offers, achievements, opportunities, and limitations in the current clinical practices.

Abstract

Radiogenomics, a combination of “Radiomics” and “Genomics,” using Artificial Intelligence (AI) has recently emerged as the state-of-the-art science in precision medicine, especially in oncology care. Radiogenomics syndicates large-scale quantifiable data extracted from radiological medical images enveloped with personalized genomic phenotypes. It fabricates a prediction model through various AI methods to stratify the risk of patients, monitor therapeutic approaches, and assess clinical outcomes. It has recently shown tremendous achievements in prognosis, treatment planning, survival prediction, heterogeneity analysis, reoccurrence, and progression-free survival for human cancer study. Although AI has shown immense performance in oncology care in various clinical aspects, it has several challenges and limitations. The proposed review provides an overview of radiogenomics with the viewpoints on the role of AI in terms of its promises for computational as well as oncological aspects and offers achievements and opportunities in the era of precision medicine. The review also presents various recommendations to diminish these obstacles.

Feature Robustness and Diagnostic Capabilities of Convolutional Neural Networks Against Radiomics Features in Computed Tomography Imaging

MATERIALS AND METHODS

Imaging phantoms were scanned twice on 3 computed tomography scanners from 2 different manufactures with varying tube voltages and currents. Phantoms were segmented, and features were extracted using PyRadiomics and a pretrained CNN. After standardization the concordance correlation coefficient (CCC), mean feature variance, feature range, and the coefficient of variant were calculated to assess feature robustness. In addition, the cosine similarity was calculated for the vectorized activation maps for an exemplary phantom. For the in vivo comparison, the radiomics and CNN features of 30 patients with hepatocellular carcinoma (HCC) and 30 patients with hepatic colon carcinoma metastasis were compared.

RESULTS

In total, 851 radiomics features and 256 CNN features were extracted for each phantom. For all phantoms, the global CCC of the CNN features was above 98%, whereas the highest CCC for the radiomics features was 36%. The mean feature variance and feature range was significantly lower for the CNN features. Using a coefficient of variant ≤0.2 as a threshold to define robust features and averaging across all phantoms 346 of 851 (41%) radiomics features and 196 of 256 (77%) CNN features were found to be robust. The cosine similarity was greater than 0.98 for all scanner and parameter variations. In the retrospective analysis, 122 of the 256 CNN (49%) features showed significant differences between HCC and hepatic colon metastasis.

DISCUSSION

Convolutional neural network features were more stable compared with radiomics features against technical variations. Moreover, the possibility of tumor entity differentiation based on CNN features was shown. Combined with visualization methods, CNN features are expected to increase reproducibility of quantitative image representations. Further studies are warranted to investigate the impact of feature stability on radiological image-based prediction of clinical outcomes.

Multiparametric Oncologic Hybrid Imaging: Machine Learning Challenges and Opportunities

BACKGROUND

 Machine learning (ML) is considered an important technology for future data analysis in health care.

METHODS

 The inherently technology-driven fields of diagnostic radiology and nuclear medicine will both benefit from ML in terms of image acquisition and reconstruction. Within the next few years, this will lead to accelerated image acquisition, improved image quality, a reduction of motion artifacts and - for PET imaging - reduced radiation exposure and new approaches for attenuation correction. Furthermore, ML has the potential to support decision making by a combined analysis of data derived from different modalities, especially in oncology. In this context, we see great potential for ML in multiparametric hybrid imaging and the development of imaging biomarkers.

RESULTS AND CONCLUSION

 In this review, we will describe the basics of ML, present approaches in hybrid imaging of MRI, CT, and PET, and discuss the specific challenges associated with it and the steps ahead to make ML a diagnostic and clinical tool in the future.

KEY POINTS

  · ML provides a viable clinical solution for the reconstruction, processing, and analysis of hybrid imaging obtained from MRI, CT, and PET..

CITATION FORMAT

· Küstner T, Hepp T, Seith F. Multiparametric Oncologic Hybrid Imaging: Machine Learning Challenges and Opportunities. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1718-4128.

An artificial intelligence framework integrating longitudinal electronic health records with real-world data enables continuous pan-cancer prognostication

Despite widespread adoption of electronic health records (EHRs), most hospitals are not ready to implement data science research in the clinical pipelines. Here, we develop MEDomics, a continuously learning infrastructure through which multimodal health data are systematically organized and data quality is assessed with the goal of applying artificial intelligence for individual prognosis. Using this framework, currently composed of thousands of individuals with cancer and millions of data points over a decade of data recording, we demonstrate prognostic utility of this framework in oncology. As proof of concept, we report an analysis using this infrastructure, which identified the Framingham risk score to be robustly associated with mortality among individuals with early-stage and advanced-stage cancer, a potentially actionable finding from a real-world cohort of individuals with cancer. Finally, we show how natural language processing (NLP) of medical notes could be used to continuously update estimates of prognosis as a given individual's disease course unfolds.

Machine learning based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features to predict prognosis of cervical cancer patients

PURPOSE

To examine the usefulness of machine learning to predict prognosis in cervical cancer using clinical and radiomic features of 2-deoxy-2-[¹⁸F]fluoro-D-glucose (¹⁸F-FDG) positron emission tomography/computed tomography (CT) (¹⁸F-FDG-PET/CT).

METHODS

This retrospective study included 50 cervical cancer patients who underwent ¹⁸F-FDG-PET/CT before treatment. Four clinical (age, histology, stage, and treatment) and 41 ¹⁸F-FDG-PET-based radiomic features were ranked and a subset of useful features for association with disease progression was selected based on decrease of the Gini impurity. Six machine learning algorithms (random forest, neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis.

RESULTS

The five top predictors of disease progression were: stage, surface area, metabolic tumor volume, gray-level run length non-uniformity (GLRLM_RLNU), and gray-level non-uniformity for run (GLRLM_GLNU). The naive Bayes model was the best-performing classifier for predicting disease progression (AUC = 0.872, accuracy = 0.780, F1 score = 0.781, precision = 0.788, and recall = 0.780). In the naive Bayes model, 5-year PFS was significantly higher in predicted non-progression than predicted progression (80.1% vs. 9.1%, p < 0.001) and was only the independent factor for PFS in multivariate analysis (HR, 6.89; 95% CI, 1.92-24.69; p = 0.003).

CONCLUSION

A machine learning approach based on clinical and pretreatment ¹⁸F-FDG PET-based radiomic features may be useful for predicting tumor progression in cervical cancer patients.

A non-invasive, automated diagnosis of Menière's disease using radiomics and machine learning on conventional magnetic resonance imaging: A multicentric, case-controlled feasibility study

Purpose

This study investigated the feasibility of a new image analysis technique (radiomics) on conventional MRI for the computer-aided diagnosis of Menière’s disease.

Materials and methods

A retrospective, multicentric diagnostic case–control study was performed. This study included 120 patients with unilateral or bilateral Menière’s disease and 140 controls from four centers in the Netherlands and Belgium. Multiple radiomic features were extracted from conventional MRI scans and used to train a machine learning-based, multi-layer perceptron classification model to distinguish patients with Menière’s disease from controls. The primary outcomes were accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the classification model.

Results

The classification accuracy of the machine learning model on the test set was 82%, with a sensitivity of 83%, and a specificity of 82%. The positive and negative predictive values were 71%, and 90%, respectively.

Conclusion

The multi-layer perceptron classification model yielded a precise, high-diagnostic performance in identifying patients with Menière’s disease based on radiomic features extracted from conventional T2-weighted MRI scans. In the future, radiomics might serve as a fast and noninvasive decision support system, next to clinical evaluation in the diagnosis of Menière’s disease.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11547-021-01425-w.

An Automatic Detection and Localization of Mammographic Microcalcifications ROI with Multi-Scale Features Using the Radiomics Analysis Approach

Microcalcifications in breast tissue can be an early sign of breast cancer, and play a crucial role in breast cancer screening. This study proposes a radiomics approach based on advanced machine learning algorithms for diagnosing pathological microcalcifications in mammogram images and provides radiologists with a valuable decision support system (in regard to diagnosing patients). An adaptive enhancement method based on the contourlet transform is proposed to enhance microcalcifications and effectively suppress background and noise. Textural and statistical features are extracted from each wavelet layer's high-frequency coefficients to detect microcalcification regions. The top-hat morphological operator and wavelet transform segment microcalcifications, implying their exact locations. Finally, the proposed radiomic fusion algorithm is employed to classify the selected features into benign and malignant. The proposed model's diagnostic performance was evaluated on the MIAS dataset and compared with traditional machine learning models, such as the support vector machine, K-nearest neighbor, and random forest, using different evaluation parameters. Our proposed approach outperformed existing models in diagnosing microcalcification by achieving an 0.90 area under the curve, 0.98 sensitivity, and 0.98 accuracy. The experimental findings concur with expert observations, indicating that the proposed approach is most effective and practical for early diagnosing breast microcalcifications, substantially improving the work efficiency of physicians.

Classifying Ruptured Middle Cerebral Artery Aneurysms With a Machine Learning Based, Radiomics-Morphological Model: A Multicentral Study

Objective

Radiomics and morphological features were associated with aneurysms rupture. However, the multicentral study of their predictive power for specific-located aneurysms rupture is rare. We aimed to determine robust radiomics features related to middle cerebral artery (MCA) aneurysms rupture and evaluate the additional value of combining morphological and radiomics features in the classification of ruptured MCA aneurysms.

Methods

A total of 632 patients with 668 MCA aneurysms (423 ruptured aneurysms) from five hospitals were included. Radiomics and morphological features of aneurysms were extracted on computed tomography angiography images. The model was developed using a training dataset (407 patients) and validated with the internal (152 patients) and external validation (73 patients) datasets. The support vector machine method was applied for model construction. Optimal radiomics, morphological, and clinical features were used to develop the radiomics model (R-model), morphological model (M-model), radiomics-morphological model (RM-model), clinical-morphological model (CM-model), and clinical-radiomics-morphological model (CRM-model), respectively. A comprehensive nomogram integrating clinical, morphological, and radiomics predictors was generated.

Results

We found seven radiomics features and four morphological predictors of MCA aneurysms rupture. The R-model obtained an area under the receiver operating curve (AUC) of 0.822 (95% CI, 0.776, 0.867), 0.817 (95% CI, 0.744, 0.890), and 0.691 (95% CI, 0.567, 0.816) in the training, temporal validation, and external validation datasets, respectively. The RM-model showed an AUC of 0.848 (95% CI, 0.810, 0.885), 0.865 (95% CI, 0.807, 0.924), and 0.721 (95% CI, 0.601, 0.841) in the three datasets. The CRM-model obtained an AUC of 0.856 (95% CI, 0.820, 0.892), 0.882 (95% CI, 0.828, 0.936), and 0.738 (95% CI, 0.618, 0.857) in the three datasets. The CRM-model and RM-model outperformed the CM-model and M-model in the internal datasets (p < 0.05), respectively. But these differences were not statistically significant in the external dataset. Decision curve analysis indicated that the CRM-model obtained the highest net benefit for most of the threshold probabilities.

Conclusion

Robust radiomics features were determined related to MCA aneurysm rupture. The RM-model exhibited good ability in classifying ruptured MCA aneurysms. Integrating radiomics features into conventional models might provide additional value in ruptured MCA aneurysms classification.

Risk Stratification Using 18F-FDG PET/CT and Artificial Neural Networks in Head and Neck Cancer Patients Undergoing Radiotherapy

This study retrospectively analyzed the performance of artificial neural networks (ANN) to predict overall survival (OS) or locoregional failure (LRF) in HNSCC patients undergoing radiotherapy, based on 2-[¹⁸F]FDG PET/CT and clinical covariates. We compared predictions relying on three different sets of features, extracted from 230 patients. Specifically, (i) an automated feature selection method independent of expert rating was compared with (ii) clinical variables with proven influence on OS or LRF and (iii) clinical data plus expert-selected SUV metrics. The three sets were given as input to an artificial neural network for outcome prediction, evaluated by Harrell’s concordance index (HCI) and by testing stratification capability. For OS and LRF, the best performance was achieved with expert-based PET-features (0.71 HCI) and clinical variables (0.70 HCI), respectively. For OS stratification, all three feature sets were significant, whereas for LRF only expert-based PET-features successfully classified low vs. high-risk patients. Based on 2-[¹⁸F]FDG PET/CT features, stratification into risk groups using ANN for OS and LRF is possible. Differences in the results for different feature sets confirm the relevance of feature selection, and the key importance of expert knowledge vs. automated selection.

Preselection of robust radiomic features does not improve outcome modelling in non-small cell lung cancer based on clinical routine FDG-PET imaging

Background

Radiomics is a promising tool for identifying imaging-based biomarkers. Radiomics-based models are often trained on single-institution datasets; however, multi-centre imaging datasets are preferred for external generalizability owing to the influence of inter-institutional scanning differences and acquisition settings. The study aim was to determine the value of preselection of robust radiomic features in routine clinical positron emission tomography (PET) images to predict clinical outcomes in locally advanced non-small cell lung cancer (NSCLC).

Methods

A total of 1404 primary tumour radiomic features were extracted from pre-treatment [¹⁸F]fluorodeoxyglucose (FDG)-PET scans of stage IIIA/N2 or IIIB NSCLC patients using a training cohort (n = 79; prospective Swiss multi-centre randomized phase III trial SAKK 16/00; 16 centres) and an internal validation cohort (n = 31; single centre). Robustness studies investigating delineation variation, attenuation correction and motion were performed (intraclass correlation coefficient threshold > 0.9). Two 12-/24-month event-free survival (EFS) and overall survival (OS) logistic regression models were trained using standardized imaging: (1) with robust features alone and (2) with all available features. Models were then validated using fivefold cross-validation, and validation on a separate single-centre dataset. Model performance was assessed using area under the receiver operating characteristic curve (AUC).

Results

Robustness studies identified 179 stable features (13%), with 25% stable features for 3D versus 4D acquisition, 31% for attenuation correction and 78% for delineation. Univariable analysis found no significant robust features predicting 12-/24-month EFS and 12-month OS (p value > 0.076). Prognostic models without robust preselection performed well for 12-month EFS in training (AUC = 0.73) and validation (AUC = 0.74). Patient stratification into two risk groups based on 12-month EFS was significant for training (p value = 0.02) and validation cohorts (p value = 0.03).

Conclusions

A PET-based radiomics model using a standardized, multi-centre dataset to predict EFS in locally advanced NSCLC was successfully established and validated with good performance. Prediction models with robust feature preselection were unsuccessful, indicating the need for a standardized imaging protocol.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13550-021-00809-3.

Assessment of sorafenib induced changes in tumor perfusion of uveal melanoma metastases with dynamic contrast-enhanced ultrasound (DCE-US)

Purpose

Dynamic contrast-enhanced ultrasound (DCE-US) was used to monitor early response to sorafenib therapy in patients with liver metastases from uveal melanoma.

Methods

In total, 21 patients with liver metastases were recruited within a prospective trial and underwent daily sorafenib therapy. DCE-US of a target lesion was performed before initiation of treatment, on day 15 and 56. Two independent blinded investigators performed software analysis for DCE-US parameters and inter-observer-correlation was calculated. Response to treatment was evaluated on day 56. DCE-US parameters were correlated with clinical response and RECIST1.1 criteria.

Results

Inter-observer-correlation (r) of DCE-US parameters [time-to-peak (TTP), mean-transit-time (MTT), peak intensity (PI), regional blood volume (RBV), regional blood flow (RBF)] at baseline, day 15, and day 56 was highly significant (r-range 0.73–0.97, all p < 0.001). Out of 17 evaluable patients, 12 patients survived day 56 (clinical responders, cRE), whereas, five patients died before day 56 and were classified as non-responders (cNR). TTP values significantly increased in the cRE group 15 days after initiation of treatment for investigator 1 (p = 0.034) and at day 56 for both investigators (p = 0.028/0.028). MTT had increased significantly in the cRE group on day 56 (p = 0.037/0.022). In the cNR group changes for TTP and MTT remained insignificant. Thus, increase of the DCE-US parameters TTP and MTT are associated with response to treatment and prognosis.

Conclusion

An increase of TTP and MTT at frequent intervals could serve as a surrogate marker for early response evaluation to anti-angiogenic treatment of metastatic uveal melanoma.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00432-021-03666-8.

Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients

Background

Radiomics is a new technology to noninvasively predict survival prognosis with quantitative features extracted from medical images. Most radiomics-based prognostic studies of non-small-cell lung cancer (NSCLC) patients have used mixed datasets of different subgroups. Therefore, we investigated the radiomics-based survival prediction of NSCLC patients by focusing on subgroups with identical characteristics.

Methods

A total of 304 NSCLC (Stages I–IV) patients treated with radiotherapy in our hospital were used. We extracted 107 radiomic features (i.e., 14 shape features, 18 first-order statistical features, and 75 texture features) from the gross tumor volume drawn on the free breathing planning computed tomography image. Three feature selection methods [i.e., test–retest and multiple segmentation (FS1), Pearson's correlation analysis (FS2), and a method that combined FS1 and FS2 (FS3)] were used to clarify how they affect survival prediction performance. Subgroup analysis for each histological subtype and each T stage applied the best selection method for the analysis of All data. We used a least absolute shrinkage and selection operator Cox regression model for all analyses and evaluated prognostic performance using the concordance-index (C-index) and the Kaplan–Meier method. For subgroup analysis, fivefold cross-validation was applied to ensure model reliability.

Results

In the analysis of All data, the C-index for the test dataset is 0.62 (FS1), 0.63 (FS2), and 0.62 (FS3). The subgroup analysis indicated that the prediction model based on specific histological subtypes and T stages had a higher C-index for the test dataset than that based on All data (All data, 0.64 vs. SCC_all, 060; ADC_all, 0.69; T1, 0.68; T2, 0.65; T3, 0.66; T4, 0.70). In addition, the prediction models unified for each T stage in histological subtype showed a different trend in the C-index for the test dataset between ADC-related and SCC-related models (ADC_T1–ADC_T4, 0.72–0.83; SCC_T1–SCC_T4, 0.58–0.71).

Conclusions

Our results showed that feature selection methods moderately affected the survival prediction performance. In addition, prediction models based on specific subgroups may improve the prediction performance. These results may prove useful for determining the optimal radiomics-based predication model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01810-9.

MRI-Based Radiomics to Differentiate between Benign and Malignant Parotid Tumors With External Validation

Background

The differentiation between benign and malignant parotid lesions is crucial to defining the treatment plan, which highly depends on the tumor histology. We aimed to evaluate the role of MRI-based radiomics using both T2-weighted (T2-w) images and Apparent Diffusion Coefficient (ADC) maps in the differentiation of parotid lesions, in order to develop predictive models with an external validation cohort.

Materials and Methods

A sample of 69 untreated parotid lesions was evaluated retrospectively, including 37 benign (of which 13 were Warthin’s tumors) and 32 malignant tumors. The patient population was divided into three groups: benign lesions (24 cases), Warthin’s lesions (13 cases), and malignant lesions (32 cases), which were compared in pairs. First- and second-order features were derived for each lesion. Margins and contrast enhancement patterns (CE) were qualitatively assessed. The model with the final feature set was achieved using the support vector machine binary classification algorithm.

Results

Models for discriminating between Warthin’s and malignant tumors, benign and Warthin’s tumors and benign and malignant tumors had an accuracy of 86.7%, 91.9% and 80.4%, respectively. After the feature selection process, four parameters for each model were used, including histogram-based features from ADC and T2-w images, shape-based features and types of margins and/or CE. Comparable accuracies were obtained after validation with the external cohort.

Conclusions

Radiomic analysis of ADC, T2-w images, and qualitative scores evaluating margins and CE allowed us to obtain good to excellent diagnostic accuracies in differentiating parotid lesions, which were confirmed with an external validation cohort.

Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET/CT to Predict Prognosis of Patients with Endometrial Cancer

PURPOSE

To examine the prognostic significance of pretreatment 2-deoxy-2-[¹⁸F]fluoro-D-glucose ([¹⁸F]-FDG) positron emission tomography (PET)-based radiomic features using a machine learning approach in patients with endometrial cancers.

PROCEDURES

Included in this retrospective study were 53 patients with endometrial cancers who underwent [¹⁸F]-FDG PET/X-ray computed tomography (CT) before treatment. Since two different PET scanners were used, post-reconstruction harmonization was performed for all PET parameters using the ComBat harmonization method. Four clinical (age, histological type, stage, and treatment method) and 40 [¹⁸F]-FDG PET-based radiomic features were ranked, and a subset of useful features was selected based on the decrease in the Gini impurity in terms of associations with disease progression. The machine learning algorithms (random forest, neural network, k-nearest neighbors (kNN), naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method. Progression-free survival (PFS) and overall survival (OS) were assessed by the Cox regression analysis.

RESULTS

The five best predictors of disease progression were coarseness, gray-level run length nonuniformity, stage, treatment method, and gray-level zone length nonuniformity. The kNN model obtained the best performance classifier for predicting the disease progression (AUC =0.890, accuracy =0.849, F1 score =0.848, precision =0.857, and recall =0.849). Coarseness which was the first ranked radiomic feature was selected for survival analyses, and only coarseness remained as a significant and independent factor for both PFS (hazard ratios (HR), 0.65; 95 % confidence interval [CI], 0.49-0.86; p=0.003) and OS (HR, 0.52; 95 % CI, 0.36-0.76; p<0.001) at multivariate Cox regression analysis.

CONCLUSIONS

[¹⁸F]-FDG PET-based radiomic analysis using a machine learning approach may be useful for predicting tumor progression and prognosis in patients with endometrial cancers.

Distant metastasis time to event analysis with CNNs in independent head and neck cancer cohorts

Deep learning models based on medical images play an increasingly important role for cancer outcome prediction. The standard approach involves usage of convolutional neural networks (CNNs) to automatically extract relevant features from the patient’s image and perform a binary classification of the occurrence of a given clinical endpoint. In this work, a 2D-CNN and a 3D-CNN for the binary classification of distant metastasis (DM) occurrence in head and neck cancer patients were extended to perform time-to-event analysis. The newly built CNNs incorporate censoring information and output DM-free probability curves as a function of time for every patient. In total, 1037 patients were used to build and assess the performance of the time-to-event model. Training and validation was based on 294 patients also used in a previous benchmark classification study while for testing 743 patients from three independent cohorts were used. The best network could reproduce the good results from 3-fold cross validation [Harrell’s concordance indices (HCIs) of 0.78, 0.74 and 0.80] in two out of three testing cohorts (HCIs of 0.88, 0.67 and 0.77). Additionally, the capability of the models for patient stratification into high and low-risk groups was investigated, the CNNs being able to significantly stratify all three testing cohorts. Results suggest that image-based deep learning models show good reliability for DM time-to-event analysis and could be used for treatment personalisation.

Spectral CT quantification stability and accuracy for pediatric patients: A phantom study

BACKGROUND

Spectral computed tomography (spectral CT) provides access to clinically relevant measures of endogenous and exogenous materials in patients. For pediatric patients, current spectral CT applications include lesion characterization, quantitative vascular imaging, assessments of tumor response to treatment, and more.

OBJECTIVE

The aim of this study is a comprehensive investigation of the accuracy and stability of spectral quantifications from a spectral detector-based CT system with respect to different patient sizes and radiation dose levels relevant for the pediatric population.

MATERIALS AND METHODS

A spectral CT phantom with tissue-mimicking materials and iodine concentrations relevant for pediatric imaging was scanned on a spectral detector CT system using a standard pediatric abdominal protocol at 100%, 67%, 33% and 10% of the nominal radiation dose level. Different pediatric patient sizes were simulated using supplemental 3D-printed extension rings. Virtual mono-energetic, iodine density, effective atomic number, and electron density results were analyzed for stability with respect to radiation dose and patient size.

RESULTS

Compared to conventional CT imaging, a pronounced improvement in the stability of attenuation measurements across patient size was observed when using virtual mono-energetic images. Iodine densities were within 0.1 mg/ml, effective atomic numbers were within 0.26 atomic numbers and electron density quantifications were within ±1.0% of their respective nominal values. Relative to the nominal dose clinical protocol, differences in attenuation of all tissue-mimicking materials were maintained below 1.6 HU for a 33% dose reduction, below 2.7 HU for a 67% dose reduction and below 3.7 HU for a 90% dose reduction, for all virtual mono-energetic energies equal to or greater than 50 keV. Iodine, and effective atomic number quantifications were stable to within 0.1 mg/ml and 0.06 atomic numbers, respectively, across all measured dose levels.

CONCLUSION

Spectral CT provides accurate and stable material quantification with respect to radiation dose reduction (up to 90%) and differing pediatric patient size. The observed consistency is an important step towards quantitative pediatric imaging at low radiation exposure levels.

The Era of Radiogenomics in Precision Medicine: An Emerging Approach to Support Diagnosis, Treatment Decisions, and Prognostication in Oncology

With the rapid development of new technologies, including artificial intelligence and genome sequencing, radiogenomics has emerged as a state-of-the-art science in the field of individualized medicine. Radiogenomics combines a large volume of quantitative data extracted from medical images with individual genomic phenotypes and constructs a prediction model through deep learning to stratify patients, guide therapeutic strategies, and evaluate clinical outcomes. Recent studies of various types of tumors demonstrate the predictive value of radiogenomics. And some of the issues in the radiogenomic analysis and the solutions from prior works are presented. Although the workflow criteria and international agreed guidelines for statistical methods need to be confirmed, radiogenomics represents a repeatable and cost-effective approach for the detection of continuous changes and is a promising surrogate for invasive interventions. Therefore, radiogenomics could facilitate computer-aided diagnosis, treatment, and prediction of the prognosis in patients with tumors in the routine clinical setting. Here, we summarize the integrated process of radiogenomics and introduce the crucial strategies and statistical algorithms involved in current studies.

Quantitative positron emission tomography imaging in the presence of iodinated contrast media using electron density quantifications from dual-energy computed tomography

PURPOSE

As preparation for future positron emission tomography (PET)/dual-energy computed tomography (DECT)T imaging modality and new possible clinical applications, the study aimed to evaluate the utility of clinically available spectral results from a DECT system for improving attenuation corrections of PET acquisitions in the presence of iodinated contrast media. The dependence of the accuracy of PET quantification values, reconstructed with conventional and spectral-based attenuation corrections, was examined as a function of the amount of iodine content and x-ray radiation exposure.

METHODS

Measurements were performed on commercial PET/CT and DECT systems, using a semi-anthropomorphic phantom with seven centrifuge tubes in its bore. Five different configurations of tube contents were scanned by both PET/CT and DECT. With the aim of mimicking clinically observed concentrations, in all phantom configurations the center tube contained a high concentration of radionuclide while the peripheral tubes contained a lower concentration of radionuclide. Iodine content was incrementally increased between phantom configurations by replacing iodine-free tubes with tubes that contained the original radionuclide concentration within a 10 mg/ml iodine dilution. DECT-based attenuation correction maps were generated by scaling electron density spectral results into corresponding 511 keV photon linear attenuation coefficients.

RESULTS

Mean SUV values obtained from the nominal PET reconstruction, using conventional CT images as input for the attenuation correction, demonstrate a monotonic increase of 8.6% when the water and radionuclide mixtures were replaced by iodine, water, and radionuclide (same level of activity) mixture. Mean SUV values obtained from the DECT-based reconstruction, in which the attenuation correction utilizes electron density values as input, demonstrate different, more stable behavior across all iodine insert configurations, with a standard deviation to mean ratio of less than 1%. This observed behavior was independent of the area size used for measurement. A minor radiation dose dependency of the electron density values (below 0.5%) was observed. This resulted in consistent (iodine independent) PET quantification behavior, which persisted even at the lowest radiation dose levels tested in our experiment, that is, 25% of the radiation dose utilized for CT acquisition in the clinical PET/CT protocol.

CONCLUSIONS

Utilization of DECT-generated electron density estimations for attenuation correction benefit PET quantification consistency in the presence of iodine and at nominal and low DECT radiation exposure levels. The ability to correctly account for iodinated contrast media in PET acquisitions will allow the development of new clinical applications that rely on the quantitative capabilities of spectral CT technologies and modern PET systems.

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Purpose

To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy ⁹⁰Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies

Methods

Given the noisy nature of ⁹⁰Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, ⁹⁰Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome.

Results

The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority.

Conclusion

We have developed new lesion-level response and progression models using textural radiomics features, derived from ⁹⁰Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.

Supervised Image Classification Algorithm Using Representative Spatial Texture Features: Application to COVID-19 Diagnosis Using CT Images

Although there is no universal definition for texture, the concept in various forms is nevertheless widely used and a key element of visual perception to analyze images in different fields. The present work's main idea relies on the assumption that there exist representative samples, which we refer to as references as well, i.e., "good or bad" samples that represent a given dataset investigated in a particular data analysis problem. These representative samples need to be accounted for when designing predictive models with the aim of improving their performance. In particular, based on a selected subset of texture gray-level co-occurrence matrices (GLCMs) from the training cohort, we propose new representative spatial texture features, which we incorporate into a supervised image classification pipeline. The pipeline relies on the support vector machine (SVM) algorithm along with Bayesian optimization and the Wasserstein metric from optimal mass transport (OMT) theory. The selection of the best, "good and bad," GLCM references is considered for each classification label and performed during the training phase of the SVM classifier using a Bayesian optimizer. We assume that sample fitness is defined based on closeness (in the sense of the Wasserstein metric) and high correlation (Spearman's rank sense) with other samples in the same class. Moreover, the newly defined spatial texture features consist of the Wasserstein distance between the optimally selected references and the remaining samples. We assessed the performance of the proposed classification pipeline in diagnosing the corona virus disease 2019 (COVID-19) from computed tomographic (CT) images.

Impact of inter-reader contouring variability on textural radiomics of colorectal liver metastases

BACKGROUND

Radiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating the impact of liver lesion contouring as a source of variability on radiomic features (RFs).

METHODS

After Ethics Committee approval, 70 liver metastases in 17 CRC patients were segmented on contrast-enhanced computed tomography scans by two residents and checked by experienced radiologists. RFs from grey level co-occurrence and run length matrices were extracted from three-dimensional (3D) regions of interest (ROIs) and the largest two-dimensional (2D) ROIs. Inter-reader variability was evaluated with Dice coefficient and Hausdorff distance, whilst its impact on RFs was assessed using mean relative change (MRC) and intraclass correlation coefficient (ICC). For the main lesion of each patient, one reader also segmented a circular ROI on the same image used for the 2D ROI.

RESULTS

The best inter-reader contouring agreement was observed for 2D ROIs according to both Dice coefficient (median 0.85, interquartile range 0.78-0.89) and Hausdorff distance (0.21 mm, 0.14-0.31 mm). Comparing RF values, MRC ranged 0-752% for 2D and 0-1567% for 3D. For 24/32 RFs (75%), MRC was lower for 2D than for 3D. An ICC > 0.90 was observed for more RFs for 2D (53%) than for 3D (34%). Only 2/32 RFs (6%) showed a variability between 2D and circular ROIs higher than inter-reader variability.

CONCLUSIONS

A 2D contouring approach may help mitigate overall inter-reader variability, albeit stable RFs can be extracted from both 3D and 2D segmentations of CRC liver metastases.

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

This short review aims at providing the readers with an update on the current status, as well as future perspectives in the quickly evolving field of radiomics applied to the field of PET/CT imaging. Numerous pitfalls have been identified in study design, data acquisition, segmentation, features calculation and modeling by the radiomics community, and these are often the same issues across all image modalities and clinical applications, however some of these are specific to PET/CT (and SPECT/CT) imaging and therefore the present paper focuses on those. In most cases, recommendations and potential methodological solutions do exist and should therefore be followed to improve the overall quality and reproducibility of published studies. In terms of future evolutions, the techniques from the larger field of artificial intelligence (AI), including those relying on deep neural networks (also known as deep learning) have already shown impressive potential to provide solutions, especially in terms of automation, but also to maybe fully replace the tools the radiomics community has been using until now in order to build the usual radiomics workflow. Some important challenges remain to be addressed before the full impact of AI may be realized but overall the field has made striking advances over the last few years and it is expected advances will continue at a rapid pace.

From multisource data to clinical decision aids in radiation oncology: The need for a clinical data science community

Big data are no longer an obstacle; now, by using artificial intelligence (AI), previously undiscovered knowledge can be found in massive data collections. The radiation oncology clinic daily produces a large amount of multisource data and metadata during its routine clinical and research activities. These data involve multiple stakeholders and users. Because of a lack of interoperability, most of these data remain unused, and powerful insights that could improve patient care are lost. Changing the paradigm by introducing powerful AI analytics and a common vision for empowering big data in radiation oncology is imperative. However, this can only be achieved by creating a clinical data science community in radiation oncology. In this work, we present why such a community is needed to translate multisource data into clinical decision aids.

Standardization of CT radiomics features for multi-center analysis: impact of software settings and parameters

The aim of this multicentric study is an inter-center benchmarking, to assess how different set tools applied to the same radiomics workflow affected the radiomics features (RFs) values. This topic is of key importance to start collaboration between different centers and to bring radiomic studies from benchmark to bedside. A per-lesion analysis was performed on 56 metastases (mts) selected from 14 patients. A single radiologist performed the segmentation of all mts, and RFs were extracted from the same segmentation of each mts, using two different software and file formats. Potential sources of discrepancies were evaluated. The intraclass correlation coefficient was used to describe how strongly the same radiomic measurements calculated in the two different centers resemble each other. Moreover, means of the relative changes of each RF were calculated, compared and gradually reduced. We showed that, after matching all formulas, discrepancies in RFs calculation between two centers ranged from 1% to 277%. Therefore, we evaluated other sources of variability using a stepwise approach, which led us to reduce the inter-center discrepancies to 0% for 22/25 RFs and below 2% for 3 RFs out of 25. In this study we demonstrated that different radiomic applications and masks formats might strongly impact the computation of some RFs. Therefore, when dealing with multi-center studies it is mandatory to adopt all strategies that can help in limiting the differences, thus keeping in mind the feasibility of these strategies in large cohort studies.

Dose-Distribution-Driven PET Image-Based Outcome Prediction (DDD-PIOP): A Deep Learning Study for Oropharyngeal Cancer IMRT Application

Purpose

To develop a deep learning-based AI agent, DDD-PIOP (Dose-Distribution-Driven PET Image Outcome Prediction), for predicting ¹⁸FDG-PET image outcomes of oropharyngeal cancer (OPC) in response to intensity-modulated radiation therapy (IMRT).

Methods

DDD-PIOP uses pre-radiotherapy ¹⁸FDG-PET/CT images and the planned spatial dose distribution as the inputs, and it predicts the ¹⁸FDG-PET image outcomes in response to the planned IMRT delivery. This AI agent centralizes a customized convolutional neural network (CNN) as a deep learning approach, and it incorporates a few designs to enhance prediction accuracy. 66 OPC patients who received IMRT treatment on a sequential boost regime (2 Gy/daily fraction) were studied for DDD-PIOP development. 61 patients were used for AI agent training/validation, and the remaining five were used as independent tests. To evaluate the developed AI agent’s performance, the predicted mean standardized uptake values (SUVs) of gross tumor volume (GTV) and clinical target volume (CTV) were compared with the ground truth values. Overall SUV distribution accuracy was evaluated by gamma test passing rates under different criteria.

Results

The developed DDD-PIOP successfully generated ¹⁸FDG-PET image outcome predictions for five test patients. The predicted mean SUV values of GTV/CTV were 3.50/1.41, which were close to the ground-truth values of 3.57/1.51. In 2D-based gamma tests, the average passing rate was 92.1% using 5%/10 mm criteria, which was improved to 95.9%/93.2% when focusing on GTV/CTV regions. 3D gamma test passing rates were 98.7% using 5%/10 mm criteria, and the corresponding GTV/CTV results were 99.8%/99.4%.

Conclusion

The reported results suggest that the developed AI agent DDD-PIOP successfully predicted ¹⁸FDG-PET image outcomes with high quantitative accuracy. The generated voxel-based image outcome predictions could be used for treatment planning optimization prior to radiation delivery for the best individual-based outcome.