Zone-size nonuniformity of 18F-FDG PET regional textural features predicts survival in patients with oropharyngeal cancer

Early prediction of radiotherapy outcomes in pharyngeal cancer using deep learning on baseline [18F]Fluorodeoxyglucose positron emission Tomography/Computed tomography

OBJECTIVES

This study aimed to develop an integrated segmentation-free deep learning (DL) framework to predict multiple aspects of radiotherapy outcome in pharyngeal cancer patients by analyzing pretreatment 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography-computed tomography (PET/CT).

METHODS

We utilized baseline 18F-FDG-PET/CT scans from patients newly diagnosed with oropharyngeal or hypopharyngeal cancer. The study cohort comprised 162 patients for training and 32 for validation, all of whom completed definitive chemoradiotherapy or radiotherapy for organ-preservation. Following image augmentation, fused PET and CT images were used to train three distinct DL models. An ensemble voting classifier was then employed to predict local recurrence (LR), neck lymph node relapse (NR), and distant metastases (DM). Model performance was evaluated using receiver operating characteristic curve analysis.

RESULTS

With a median follow-up of 36 months, the training cohort experienced, LR in 45 (27.8 %), NR in 32 (19.8 %), and DM in 21 (13.0 %) patients. By optimizing single models and finalizing with an ensemble voting classifier, the area under the curve for the occurrence of LR, NR, and DM was 0.850, 0.878, and 0.893, whereas the accuracy for the three endpoints were 87.5 %, 68.8 %, and 78.1 %, respectively.

CONCLUSIONS

By utilizing baseline 18F-FDG-PET/CT, our proposed DL models can provide a supplemental prediction for various therapeutic outcome in patients with pharyngeal cancer undergoing radiotherapy-based treatment. The accuracy for NR and DM predictions requires further optimization through additional technological breakthrough or combing clinical parameters. External validation is an important future step to confirm the model's generalizability and clinical utility.

Risk Stratification for Oropharyngeal Squamous Cell Carcinoma Using Texture Analysis on CT - A Step Beyond HPV Status

Background and Purpose: Human papillomavirus-associated oropharyngeal squamous cell carcinoma (OPSCC) is increasingly prevalent. Despite the overall more favorable outcome, the observed heterogeneous treatment response within this patient group highlights the need for additional means to prognosticate and guide clinical decision-making. Promising prediction models using radiomics from primary OPSCC have been derived. However, no model/s using metastatic lymphadenopathy exist to allow prognostication in those instances when the primary tumor is not seen. The aim of our study was to evaluate whether radiomics using metastatic lymphadenopathy allows for the development of a useful risk assessment model comparable to the primary tumor and whether additional knowledge of the HPV status further improves its prognostic efficacy. Materials and Methods: 80 consecutive patients diagnosed with stage III-IV OPSCC between February 2009 and October 2015, known human papillomavirus status, and pre-treatment CT images were retrospectively identified. Manual segmentation of primary tumor and metastatic lymphadenopathy was performed and the extracted texture features were used to develop multivariate assessment models to prognosticate treatment response. Results: Texture analysis of either the primary or metastatic lymphadenopathy from pre-treatment enhanced CT images can be used to develop models for the stratification of treatment outcomes in OPSCC patients. AUCs range from .78 to .85 for the various OPSCC groups tested, indicating high predictive capability of the models. Conclusions: This preliminary study can form the basis multi-centre trial that may help optimize treatment and improve quality of life in patients with OPSCC in the era of personalized medicine.

Application of Machine Learning Analyses Using Clinical and [18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer

PURPOSE

To develop and identify machine learning (ML) models using pretreatment clinical and 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic characteristics to predict disease recurrences in patients with breast cancers who underwent surgery.

PROCEDURES

This retrospective study included 112 patients with 118 breast cancer lesions who underwent [18F]-FDG-PET/ X-ray computed tomography (CT) preoperatively, and these lesions were assigned to training (n=95) and testing (n=23) cohorts. A total of 12 clinical and 40 [18F]-FDG-PET-based radiomic characteristics were used to predict recurrences using 7 different ML algorithms, namely, decision tree, random forest (RF), neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine (SVM) with a 10-fold cross-validation and synthetic minority over-sampling technique. Three different ML models were created using clinical characteristics (clinical ML models), radiomic characteristics (radiomic ML models), and both clinical and radiomic characteristics (combined ML models). Each ML model was constructed using the top ten characteristics ranked by the decrease in Gini impurity. The areas under ROC curves (AUCs) and accuracies were used to compare predictive performances.

RESULTS

In training cohorts, all 7 ML algorithms except for logistic regression algorithm in the radiomics ML model (AUC = 0.760) achieved AUC values of >0.80 for predicting recurrences with clinical (range, 0.892-0.999), radiomic (range, 0.809-0.984), and combined (range, 0.897-0.999) ML models. In testing cohorts, the RF algorithm of combined ML model achieved the highest AUC and accuracy (95.7% (22/23)) with similar classification performance between training and testing cohorts (AUC: training cohort, 0.999; testing cohort, 0.992). The important characteristics for modeling process of this RF algorithm were radiomic GLZLM_ZLNU and AJCC stage.

CONCLUSIONS

ML analyses using both clinical and [18F]-FDG-PET-based radiomic characteristics may be useful for predicting recurrence in patients with breast cancers who underwent surgery.

The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer

OBJECTIVE

To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer.

METHODS

This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index).

RESULTS

Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808).

CONCLUSION

ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer.

ADVANCES IN KNOWLEDGE

ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.

A systematic review and meta-analysis of predictive and prognostic models for outcome prediction using positron emission tomography radiomics in head and neck squamous cell carcinoma patients

BACKGROUND

Positron emission tomography (PET) images of head and neck squamous cell carcinoma (HNSCC) patients can assess the functional and biochemical processes at cellular levels. Therefore, PET radiomics-based prediction and prognostic models have the potentials to understand tumour heterogeneity and assist clinicians with diagnosis, prognosis and management of the disease. We conducted a systematic review of published modelling information to evaluate the usefulness of PET radiomics in the prediction and prognosis of HNSCC patients.

METHODS

We searched bibliographic databases (MEDLINE, Embase, Web of Science) from 2010 to 2021 and considered 31 studies with pre-defined inclusion criteria. We followed the CHARMS checklist for data extraction and performed quality assessment using the PROBAST tool. We conducted a meta-analysis to estimate the accuracy of the prediction and prognostic models using the diagnostic odds ratio (DOR) and average C-statistic, respectively.

RESULTS

Manual segmentation method followed by 40% of the maximum standardised uptake value (SUVmax ) thresholding is a commonly used approach. The area under the receiver operating curves of externally validated prediction models ranged between 0.60-0.87, 0.65-0.86 and 0.62-0.75 for overall survival, distant metastasis and recurrence, respectively. Most studies highlighted an overall high risk of bias (outcome definition, statistical methodologies and external validation of models) and high unclear concern in terms of applicability. The meta-analysis showed the estimated pooled DOR of 6.75 (95% CI: 4.45, 10.23) for prediction models and the C-statistic of 0.71 (95% CI: 0.67, 0.74) for prognostic models.

CONCLUSIONS

Both prediction and prognostic models using clinical variables and PET radiomics demonstrated reliable accuracy for detecting adverse outcomes in HNSCC, suggesting the prospect of PET radiomics in clinical settings for diagnosis, prognosis and management of HNSCC patients. Future studies of prediction and prognostic models should emphasise the quality of reporting, external model validation, generalisability to real clinical scenarios and enhanced reproducibility of results.

A Radiomics-Based Classifier for the Progression of Oropharyngeal Cancer Treated with Definitive Radiotherapy

In this study, we investigated whether radiomics features from pre-treatment positron emission tomography (PET) images could be used to predict disease progression in patients with HPV-positive oropharyngeal cancer treated with definitive proton or x-ray radiotherapy. Machine learning models were built using a dataset from Mayo Clinic, Rochester, Minnesota (n = 72) and tested on a dataset from Mayo Clinic, Phoenix, Arizona (n = 22). A total of 71 clinical and radiomics features were considered. The Mann-Whitney U test was used to identify the top 2 clinical and top 20 radiomics features that were significantly different between progression and progression-free patients. Two dimensionality reduction methods were used to define two feature sets (manually filtered or machine-driven). A forward feature selection scheme was conducted on each feature set to build models of increased complexity (number of input features from 1 to 6) and evaluate model robustness and overfitting. The machine-driven features had superior performance and were less prone to overfitting compared to the manually filtered features. The four-variable Gaussian Naïve Bayes model using the 'Radiation Type' clinical feature and three machine-driven features achieved a training accuracy of 79% and testing accuracy of 77%. These results demonstrate that radiomics features can provide risk stratification beyond HPV-status to formulate individualized treatment and follow-up strategies.

Prognostic value of initial [ 18 F]FDG PET/computed tomography volumetric and texture analysis-based parameters in patients with head and neck squamous cell carcinoma

AIM OF WORK

To determine the predictive value of initial [ 18 F]FDG PET/computed tomography (CT) volumetric and radiomics-derived analyses in patients with head and neck squamous cell carcinoma (HNSCC).

METHODS

Forty-six adult patients had pathologically proven HNSCC and underwent pretherapy [ 18 F]FDG PET/CT were enrolled. Semi-quantitative PET-derived volumetric [(maximum standardized uptake value (SUVmax) and mean SUV (SUVmean), total lesion glycolysis (TLG) and metabolic tumor volume (MTV)] and radiomics analyses using LIFEx 6.73.3 software were performed.

RESULTS

In the current study group, the receiver operating characteristic curve marked a cutoff point of 21.105 for primary MTV with area under the curve (AUC) of 0.727, sensitivity of 62.5%, and specificity of 86.8% ( P value 0.041) to distinguish responders from non-responders, while no statistically significant primary SUVmean or max or primary TLG cut off points could be determined. It also marked the cutoff point for survival prediction of 10.845 for primary MTV with AUC 0.728, sensitivity of 80%, and specificity of 77.8% ( P value 0.026). A test of the synergistic performance of PET-derived volumetric and textural features significant parameters was conducted in an attempt to develop the most accurate and stable prediction model. Therefore, multivariate logistic regression analysis was performed to detect independent predictors of mortality. With a high specificity of 97.1% and an overall accuracy of 89.1%, the combination of primary tumor MTV and the textural feature gray-level co-occurrence matrix correlation provided the most accurate prediction of mortality ( P value < 0.001).

CONCLUSION

Textural feature indices are a noninvasive method for capturing intra-tumoral heterogeneity. In our study, a PET-derived prediction model was successfully generated with high specificity and accuracy.

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

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

CT radiomics nomogram predicts pathological response after induced chemotherapy and overall survival in patients with advanced laryngeal cancer: A single-center retrospective study

Purpose

This study aimed to develop a radiomics nomogram to predict pathological response (PR) after induction chemotherapy (IC) and overall survival (OS) in patients with advanced laryngeal cancer (LC).

Methods

This retrospective study included patients with LC (n = 114) who had undergone contrast computerized tomography (CT); patients were randomly assigned to training (n = 81) and validation cohorts (n = 33). Potential radiomics scores were calculated to establish a model for predicting the PR status using least absolute shrinkage and selection operator (LASSO) regression. Multivariable logistic regression analyses were performed to select significant variables for predicting PR status. Kaplan–Meier analysis was performed to assess the risk stratification ability of PR and radiomics score (rad-score) for predicting OS. A prognostic nomogram was developed by integrating radiomics features and clinicopathological characteristics using multivariate Cox regression. All LC patients were stratified as low- and high-risk by the median CT radiomic score, C-index, calibration curve. Additionally, decision curve analysis (DCA) of the nomogram was performed to test model performance and clinical usefulness.

Results

Overall, PR rates were 45.6% (37/81) and 39.3% (13/33) in the training and validation cohorts, respectively. Eight features were optimally selected to build a rad-score model, which was significantly associated with PR and OS. The median OS in the PR group was significantly shorter than that in the non-PR group in both cohorts. Multivariate Cox analysis revealed that volume [hazard ratio, (HR) = 1.43], N stage (HR = 1.46), and rad-score (HR = 2.65) were independent risk factors associated with OS. The above four variables were applied to develop a nomogram for predicting OS, and the DCAs indicated that the predictive performance of the nomogram was better than that of the clinical model.

Conclusion

For patients with advanced LC, CT radiomics score was an independent biomarker for estimating PR after IC. Moreover, the nomogram that incorporated radiomics features and clinicopathological factors performed better for individualized OS estimation.

Quantitative and visual analyses of the effect of activity reduction on image metrics and quality in 18F-FDG PET/MRI in pediatric oncology

BACKGROUND

: The aim of our study was to evaluate the effect of reduced injected tracer activities on the quantitative image metrics and the visual image quality in whole-body 18F-FDG PET/MRI with TOF capability in pediatric oncology.

METHODS

Seventy-seven PET/MRI examinations of 54 patients were analyzed (standard injected activity: 1.9 MBq/kg, standard PET scan duration: 5 min per bed position). Lower activity PET images (1.2 MBq/kg and 0.9 MBq/kg) were retrospectively simulated from the originally acquired list-mode data sets. Quantitative parameters were assessed by measuring the SUV metrics, signal-to-noise ratio (SNR), contrast-to-noise ratios (CNR), and textural features in each PET data set. PET images were also evaluated visually for image quality by using a scoring system.

RESULTS

SNRs were found as significantly different among PET data sets (p < 0.001) and showed increasing image noise with decreasing activities. CNR values did not show significant differences among PET data sets. The mean relative percentage changes in SUV metrics were found to be lower in 1.2 MBq/kg data set compared to 0.9 MBq/kg data set. Lesion SUVmax, SUVmean, SULpeak, and textural features were significantly different in 0.9 MBq/kg data set compared to the original data set (p < 0.05 for all). However, SUV metrics and textural features did not show a significant difference between the original and 1.2 MBq/kg data sets. While, the mean visual scores in 0.9 MBq/kg data set were significantly different compared to the original data set (p < 0.001), there was no significant difference between the original and 1.2 MBq/kg data sets in terms of general image quality and image sharpness.

DISCUSSION

Our analyses showed that the reduction of injected activity to 1.2 MBq/kg may be feasible in pediatric oncological PET/ MRI, with a smaller relative percentage change in quantitative parameters and with similar image quality to the original data set.

Prognostic value of fluorodeoxyglucose positron emission tomography derived metabolic parameters and textural features in pediatric sarcoma

PURPOSE

The aim of this study was to evaluate the prognostic value of PET-derived metabolic features and textural parameters of primary tumors in pediatric sarcoma patients.

METHODS

The imaging findings of 43 patients (14 girls and 29 boys; age 11.4 ± 4.4 years) who underwent 18-fluorodeoxyglucose positron emission tomography (PET)/computed tomography for primary staging prior to therapy between 2005 and 2020 were retrospectively evaluated. The diagnoses were osteosarcoma in 10, rhabdomyosarcoma in 10, and Ewing sarcoma in 23 patients. PET metabolic data and textural features of primary tumors were obtained. Cox proportional hazards regression models were used to identify predictors for progression-free survival and overall survival. Survival curves were estimated by using the Kaplan-Meier method.

RESULTS

Distant metastases were detected in primary staging in 13 patients (30.2%). The median follow-up duration after diagnosis was 28 months (range: 10-171 months). In multivariate Cox regression analysis, the presence of distant metastasis and neighborhood grey-level difference matrix_Contrast (ngldm_Contrast) were found as independent predictors for both progression-free survival and overall survival. Grey-level zone length matrix_Zone-length nonuniformity (glzlm_ZLNU) was also found as an independent predictor for overall survival. The Kaplan-Meier survival analysis showed that higher ngldm_Contrast and glzlm_ZLNU values of primary tumors were significantly associated with shorter progression-free survival and overall survival.

CONCLUSION

In addition to the presence of distant metastasis at initial diagnosis, textural features of primary tumors may be used as prognostic biomarkers to identify patients with worse prognosis in pediatric sarcoma. Higher tumor heterogeneity is significantly associated with shorter progression-free survival and OS.

Radiomics in Oncological PET Imaging: A Systematic Review-Part 1, Supradiaphragmatic Cancers

Radiomics is an upcoming field in nuclear oncology, both promising and technically challenging. To summarize the already undertaken work on supradiaphragmatic neoplasia and assess its quality, we performed a literature search in the PubMed database up to 18 February 2022. Inclusion criteria were: studies based on human data; at least one specified tumor type; supradiaphragmatic malignancy; performing radiomics on PET imaging. Exclusion criteria were: studies only based on phantom or animal data; technical articles without a clinically oriented question; fewer than 30 patients in the training cohort. A review database containing PMID, year of publication, cancer type, and quality criteria (number of patients, retrospective or prospective nature, independent validation cohort) was constructed. A total of 220 studies met the inclusion criteria. Among them, 119 (54.1%) studies included more than 100 patients, 21 studies (9.5%) were based on prospectively acquired data, and 91 (41.4%) used an independent validation set. Most studies focused on prognostic and treatment response objectives. Because the textural parameters and methods employed are very different from one article to another, it is complicated to aggregate and compare articles. New contributions and radiomics guidelines tend to help improving quality of the reported studies over the years.

Role of Texture Analysis in Oropharyngeal Carcinoma: A Systematic Review of the Literature

Simple Summary

The incidence of squamous cell carcinomas of the oropharynx has rapidly increased in the last two decades due to human papilloma virus infection (HPV). HPV-positive and HPV-negative squamous cell tumours differ in radiological imaging, treatment, and prognosis; therefore, differential diagnosis is mandatory. Radiomics with texture analysis is an innovative technique that has been used increasingly in recent years to characterise the tissue heterogeneity of certain structures such as neoplasms or organs by measuring the spatial distribution of pixel values on radiological imaging. This review delineates the application of texture analysis in oropharyngeal tumours and explores how radiomics may potentially improve clinical decision-making.

Abstract

Human papilloma virus infection (HPV) is associated with the development of lingual and palatine tonsil carcinomas. Diagnosing, differentiating HPV-positive from HPV-negative cancers, and assessing the presence of lymph node metastases or recurrences by the visual interpretation of images is not easy. Texture analysis can provide structural information not perceptible to human eyes. A systematic literature search was performed on 16 February 2022 for studies with a focus on texture analysis in oropharyngeal cancers. We conducted the research on PubMed, Scopus, and Web of Science platforms. Studies were screened for inclusion according to the preferred reporting items for systematic reviews. Twenty-six studies were included in our review. Nineteen articles related specifically to the oropharynx and seven articles analysed the head and neck area with sections dedicated to the oropharynx. Six, thirteen, and seven articles used MRI, CT, and PET, respectively, as the imaging techniques by which texture analysis was performed. Regarding oropharyngeal tumours, this review delineates the applications of texture analysis in (1) the diagnosis, prognosis, and assessment of disease recurrence or persistence after therapy, (2) early differentiation of HPV-positive versus HPV-negative cancers, (3) the detection of cancers not visualised by imaging alone, and (4) the assessment of lymph node metastases from unknown primary carcinomas.

Radiomics in medical imaging: pitfalls and challenges in clinical management

BACKGROUND

Radiomics and radiogenomics are two words that recur often in language of radiologists, nuclear doctors and medical physicists especially in oncology field. Radiomics is the technique of medical images analysis to extract quantitative data that are not detected by human eye.

METHODS

This article is a narrative review on Radiomics in Medical Imaging. In particular, the review exposes the process, the limitations related to radiomics, and future prospects are discussed.

RESULTS

Several studies showed that radiomics is very promising. However, there were some critical issues: poor standardization and generalization of radiomics results, data-quality control, repeatability, reproducibility, database balancing and issues related to model overfitting.

CONCLUSIONS

Radiomics procedure should made considered all pitfalls and challenges to obtain robust and reproducible results that could be generalized in other patients cohort.

Computed tomography-based radiomics signature as a pretreatment predictor of progression-free survival in locally advanced hypopharyngeal carcinoma with a different response to induction chemotherapy

PURPOSE

To establish and validate a radiomics signature for stratifying the risk of progression-free survival (PFS) in patients with locally advanced hypopharyngeal carcinoma (LAHC) undergoing induction chemotherapy (IC).

METHODS

We extracted radiomics features from baseline contrast-enhanced computed tomography (CECT) images. We enrolled 112 LAHC patients (78 in the training cohort and 34 in the validation cohort). We used cox regression model and random survival forests variable hunting (RSFVH) algorithm for feature selection and radiomics signature building. The radiomics signature was established in the training cohort and tested in the validation cohort. We used the Kaplan-Meier analysis and log-rank test to evaluate the ability of radiomics signature in PFS risk stratification among patients with different IC responses and constructed a radiomics nomogram to predict individual PFS risk.

RESULTS

The radiomics signature performed well in stratifying patients into highrisk and low-risk groups of progression in both the training and validation cohorts. The radiomics nomogram showed good discriminative ability for predicting PFS. Survival outcome analysis of subsets indicated that the radiomics signature performed well in stratifying the risk of PFS in patients with LAHC with different IC responses.

CONCLUSIONS

The radiomics signature was a pretreatment predictor for PFS in patients with LAHC who exhibited different responses to IC.

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

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

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

Simple Summary

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

Abstract

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

Radiomic Features of 18F-FDG PET in Hodgkin Lymphoma Are Predictive of Outcomes

Purpose

In the present study, we aimed to investigate whether the radiomic features of baseline ¹⁸F-FDG PET can predict the prognosis of Hodgkin lymphoma (HL).

Methods

A total 65 HL patients (training cohort: n = 49; validation cohort: n = 16) were retrospectively enrolled in the present study. A total of 47 radiomic features were extracted from pretreatment PET images. The least absolute shrinkage and selection operator (LASSO) regression was used to select the most useful prognostic features in the training cohort. The distance between the two lesions that were the furthest apart (D_max) was recorded. The receiver operating characteristic (ROC) curve, Kaplan–Meier method, and Cox proportional hazards model were used to assess the prognostic factors.

Results

Long-zone high gray-level emphasis extracted from a gray-level zone-length matrix (LZHGE_GLZLM) (HR = 9.007; p=0.044) and Dmax (HR = 3.641; p=0.048) were independently correlated with 2-year progression-free survival (PFS). A prognostic stratification model was established based on both risk predictors, which could distinguish three risk categories for PFS (p=0.0002). The 2-year PFS was 100.0%, 64.7%, and 33.3%, respectively.

Conclusions

LZHGE_GLZLM and Dmax were independent prognostic factors for survival outcomes. Besides, we proposed a prognostic stratification model that could further improve the risk stratification of HL patients.

Prediction of Neoadjuvant Chemotherapy Response in Osteosarcoma Using Convolutional Neural Network of Tumor Center 18F-FDG PET Images

We compared the accuracy of prediction of the response to neoadjuvant chemotherapy (NAC) in osteosarcoma patients between machine learning approaches of whole tumor utilizing fluorine−¹⁸fluorodeoxyglucose (¹⁸F-FDG) uptake heterogeneity features and a convolutional neural network of the intratumor image region. In 105 patients with osteosarcoma, ¹⁸F-FDG positron emission tomography/computed tomography (PET/CT) images were acquired before (baseline PET0) and after NAC (PET1). Patients were divided into responders and non-responders about neoadjuvant chemotherapy. Quantitative ¹⁸F-FDG heterogeneity features were calculated using LIFEX version 4.0. Receiver operating characteristic (ROC) curve analysis of ¹⁸F-FDG uptake heterogeneity features was used to predict the response to NAC. Machine learning algorithms and 2-dimensional convolutional neural network (2D CNN) deep learning networks were estimated for predicting NAC response with the baseline PET0 images of the 105 patients. ML was performed using the entire tumor image. The accuracy of the 2D CNN prediction model was evaluated using total tumor slices, the center 20 slices, the center 10 slices, and center slice. A total number of 80 patients was used for k-fold validation by five groups with 16 patients. The CNN network test accuracy estimation was performed using 25 patients. The areas under the ROC curves (AUCs) for baseline PET maximum standardized uptake value (SUVmax), total lesion glycolysis (TLG), metabolic tumor volume (MTV), and gray level size zone matrix (GLSZM) were 0.532, 0.507, 0.510, and 0.626, respectively. The texture features test accuracy of machine learning by random forest and support vector machine were 0.55 and 0. 54, respectively. The k-fold validation accuracy and validation accuracy were 0.968 ± 0.01 and 0.610 ± 0.04, respectively. The test accuracy of total tumor slices, the center 20 slices, center 10 slices, and center slices were 0.625, 0.616, 0.628, and 0.760, respectively. The prediction model for NAC response with baseline PET0 texture features machine learning estimated a poor outcome, but the 2D CNN network using ¹⁸F-FDG baseline PET0 images could predict the treatment response before prior chemotherapy in osteosarcoma. Additionally, using the 2D CNN prediction model using a tumor center slice of ¹⁸F-FDG PET images before NAC can help decide whether to perform NAC to treat osteosarcoma patients.

Prediction of the local treatment outcome in patients with oropharyngeal squamous cell carcinoma using deep learning analysis of pretreatment FDG-PET images

Background

This study aimed to assess the utility of deep learning analysis using pretreatment FDG-PET images to predict local treatment outcome in oropharyngeal squamous cell carcinoma (OPSCC) patients.

Methods

One hundred fifty-four OPSCC patients who received pretreatment FDG-PET were included and divided into training (n = 102) and test (n = 52) sets. The diagnosis of local failure and local progression-free survival (PFS) rates were obtained from patient medical records. In deep learning analyses, axial and coronal images were assessed by three different architectures (AlexNet, GoogLeNET, and ResNet). In the training set, FDG-PET images were analyzed after the data augmentation process for the diagnostic model creation. A multivariate clinical model was also created using a binomial logistic regression model from a patient’s clinical characteristics. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. Assessment of local PFS rates was also performed.

Results

Training sessions were successfully performed with an accuracy of 74–89%. ROC curve analyses revealed an AUC of 0.61–0.85 by the deep learning model in the test set, whereas it was 0.62 by T-stage, 0.59 by clinical stage, and 0.74 by a multivariate clinical model. The highest AUC (0.85) was obtained with deep learning analysis of ResNet architecture. Cox proportional hazards regression analysis revealed deep learning-based classification by a multivariate clinical model (P < .05), and ResNet (P < .001) was a significant predictor of the treatment outcome. In the Kaplan-Meier analysis, the deep learning-based classification divided the patient’s local PFS rate better than the T-stage, clinical stage, and a multivariate clinical model.

Conclusions

Deep learning-based diagnostic model with FDG-PET images indicated its possibility to predict local treatment outcomes in OPSCCs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08599-6.

Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET/CT and machine learning

PURPOSE

To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on 18F-FDG PET/CT and radiomic features using machine-learning methods.

METHODS

A total of 199 colorectal cancer patients underwent pre-therapy diagnostic 18F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting 18F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis.

RESULTS

The CRC patients were divided into a training set (n = 144) and a test set (n = 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808-0.925) and XGBoost (AUC 0.903, 95% CI 0.855-0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by 18F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all p < 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC.

CONCLUSION

In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on 18F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than 18F-FDG PET/CT in both the training and test sets.

Prediction of the treatment outcome using machine learning with FDG-PET image-based multiparametric approach in patients with oral cavity squamous cell carcinoma

AIM

To investigate the value of machine learning-based multiparametric analysis using 2-[¹⁸F]-fluoro-2-deoxy-d-glucose positron-emission tomography (FDG-PET) images to predict treatment outcome in patients with oral cavity squamous cell carcinoma (OCSCC).

MATERIALS AND METHODS

Ninety-nine patients with OCSCC who received pretreatment integrated FDG-PET/computed tomography (CT) were included. They were divided into the training (66 patients) and validation (33 patients) cohorts. The diagnosis of local control or local failure was obtained from patient's medical records. Conventional FDG-PET parameters, including the maximum and mean standardised uptake values (SUVmax and SUVmean), metabolic tumour volume (MTV), and total lesion glycolysis (TLG), quantitative tumour morphological parameters, intratumoural histogram, and texture parameters, as well as T-stage and clinical stage, were evaluated by a machine learning analysis. The diagnostic ability of T-stage, clinical stage, and conventional FDG-PET parameters (SUVmax, SUVmean, MTV, and TLG) was also assessed separately.

RESULTS

In support-vector machine analysis of the training dataset, the final selected parameters were T-stage, SUVmax, TLG, morphological irregularity, entropy, and run-length non-uniformity. In the validation dataset, the diagnostic performance of the created algorithm was as follows: sensitivity 0.82, specificity 0.7, positive predictive value 0.86, negative predictive value 0.64, and accuracy 0.79. In a univariate analysis using conventional FDG-PET parameters, T-stage and clinical stage, diagnostic accuracy of each variable was revealed as follows: 0.61 in T-stage, 0.61 in clinical stage, 0.64 in SUVmax, 0.61 in SUVmean, 0.64 in MTV, and 0.7 in TLG.

CONCLUSION

A machine-learning-based approach to analysing FDG-PET images by multiparametric analysis might help predict local control or failure in patients with OCSCC.

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.

Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC

OBJECTIVE

Tumor metabolic phenotype can be assessed with integrated image pattern analysis of 18F-fluoro-deoxy-glucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT), called radiomics. This study was performed to assess the prognostic value of radiomics PET parameters in head and neck squamous cell carcinoma (HNSCC) patients.

METHODS

18F-fluoro-deoxy-glucose (FDG) PET/CT data of 215 patients from HNSCC collection free database in The Cancer Imaging Archive (TCIA), and 122 patients in Seoul St. Mary's Hospital with baseline FDG PET/CT for locally advanced HNSCC were reviewed. Data from TCIA database were used as a training cohort, and data from Seoul St. Mary's Hospital as a validation cohort. With the training cohort, primary tumors were segmented by Nestles' adaptive thresholding method. Segmental tumors in PET images were preprocessed using relative resampling of 64 bins. Forty-two PET parameters, including conventional parameters and texture parameters, were measured. Binary groups of homogeneous imaging phenotypes, clustered by K-means method, were compared for overall survival (OS) and disease-free survival (DFS) by log-rank test. Selected individual radiomics parameters were tested along with clinical factors, including age and sex, by Cox-regression test for OS and DFS, and the significant parameters were tested with multivariate analysis. Significant parameters on multivariate analysis were again tested with multivariate analysis in the validation cohort.

RESULTS

A total of 119 patients, 70 from training, and 49 from validation cohort, were included in the study. The median follow-up period was 62 and 52 months for the training and the validation cohort, respectively. In the training cohort. binary groups with different metabolic radiomics phenotypes showed significant difference in OS (p = 0.036), and borderline difference in DFS (p = 0.086). Gray-Level Non-Uniformity for zone (GLNUGLZLM) was the most significant prognostic factor for both OS (hazard ratio [HR] 3.1, 95% confidence interval [CI] 1.4-7.3, p = 0.008) and DFS (HR 4.5, CI 1.3-16, p = 0.020). Multivariate analysis revealed GLNUGLZLM as an independent prognostic factor for OS (HR 3.7, 95% CI 1.1-7.5, p = 0.032). GLNUGLZLM remained as an independent prognostic factor in the validation cohort (HR 14.8. 95% CI 3.3-66, p < 0.001).

CONCLUSIONS

Baseline FDG PET radiomics contain risk information for survival prognosis in HNSCC patients. The metabolic heterogeneity parameter, GLNUGLZLM, may assist clinicians in patient risk assessment as a feasible prognostic factor.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

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

Incorporating radiomic feature of pretreatment 18F-FDG PET improves survival stratification in patients with EGFR-mutated lung adenocarcinoma

BACKGROUND

To investigate the survival prognostic value of the radiomic features of 18F-FDG PET in patients who had EGFR (epidermal growth factor receptor) mutated lung adenocarcinoma and received targeted TKI (tyrosine kinase inhibitor) treatment.

METHODS

Fifty-one patients with stage III-IV lung adenocarcinoma and actionable EGFR mutation who received first-line TKI were retrospectively analyzed. All patients underwent pretreatment 18F-FDG PET/CT, and we calculated the PET-derived radiomic features. Cox proportional hazard model was used to examine the association between the radiomic features and the survival outcomes, including progression-free survival (PFS) and overall survival (OS). A score model was established according to the independent prognostic predictors and we compared this model to the TNM staging system using Harrell's concordance index (c-index).

RESULTS

Forty-eight patients (94.1%) experienced disease progression and 41 patients (80.4%) died. Primary tumor SUV entropy > 5.36, and presence of pleural effusion were independently associated with worse OS (both p < 0.001) and PFS (p = 0.001, and 0.003, respectively). We used these two survival predictors to devise a scoring system (score 0-2). Patients with a score of 1 or 2 had a worse survival than those with a score of 0 (HR for OS: 3.6, p = 0.006 for score 1, and HR: 21.8, p < 0.001 for score 2; HR for PFS: 2.2, p = 0.027 for score 1 and HR: 8.8, p < 0.001 for score 2). Our scoring system surpassed the TNM staging system (c-index = 0.691 versus 0.574, p = 0.013 for OS, and c-index = 0.649 versus 0.517, p = 0.004 for PFS).

CONCLUSIONS

In this preliminary study, combining PET radiomics with clinical risk factors may improve survival stratification in stage III-IV lung adenocarcinoma with actionable EFGR mutation. Our proposed scoring system may assist with optimization of individualized treatment strategies in these patients.

Texture indices of 4'-[methyl-11C]-thiothymidine uptake predict p16 status in patients with newly diagnosed oropharyngeal squamous cell carcinoma: comparison with 18F-FDG uptake

Background

In oropharyngeal squamous cell carcinoma (OPSCC), human papillomavirus (HPV)/p16 status is important as a prognostic biomarker.

Purpose

We evaluated the relationship between 4′-[methyl-¹¹C]-thiothymidine (¹¹C-4DST) and ¹⁸F-FDG PET texture indices and p16 status in patients with newly diagnosed OPSCC.

Methods

We retrospectively reviewed the collected data of 256 consecutive, previously untreated patients with primary head and neck tumors enrolled between November 2011 and October 2019. Complete data on both ¹¹C-4DST and ¹⁸F-FDG PET/CT studies before therapy, patients with OPSCC, and p16 status were available for 34 patients. Six of them were excluded because they did not exhibit sufficient ¹¹C-4DST and/or ¹⁸F-FDG tumor uptake to perform textural analysis. Finally, 28 patients with newly diagnosed OPSCC were investigated. The maximum standardized uptake value (SUVmax) and 6 texture indices (homogeneity, entropy, short-run emphasis, long-run emphasis, low gray-level zone emphasis, and high gray-level zone emphasis) were derived from PET images. The presence of p16 expression in tumor specimens was examined by immunohistochemistry and compared with the PET parameters.

Results

Using ¹¹C-4DST, the expression of p16 was associated with a higher homogeneity (P = 0.012), lower short-run emphasis (P = 0.005), higher long-run emphasis (P = 0.009), and lower high-gray-level-zone emphasis (P = 0.042) values. There was no significant difference between ¹⁸F-FDG PET parameters and p16 status.

Conclusion

Texture indices of the primary tumor on ¹¹C-4DST PET, but not ¹⁸F-FDG PET, may be of value in predicting the condition’s p16 status in patients with newly diagnosed OPSCC.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

TRIAL REGISTRATION

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

Dual tracer 68Ga-DOTATOC and 18F-FDG PET/computed tomography radiomics in pancreatic neuroendocrine neoplasms: an endearing tool for preoperative risk assessment

AIM

To explore the potentiality of radiomics analysis, performed on Ga-DOTATOC and fluorine-18-fluorodeoxyglucose (F-FDG) PET/computed tomography (CT) images, in predicting tumour aggressiveness and outcome in patients candidate to surgery for pancreatic neuroendocrine neoplasms (PanNENs).

PATIENTS AND METHODS

Retrospective study including 61 patients who underwent Ga-DOTATOC and F-FDG PET/CT before surgery for PanNEN. Semiquantitative variables [SUVmax and somatostatin receptor density (SRD) for Ga-DOTATOC PET; SUVmax and MTV for F-FDG PET] and texture features [intensity variability, size zone variability (SZV), zone percentage, entropy; homogeneity, dissimilarity and coefficient of variation (Co-V)] have been analysed to evaluate their possible role in predicting tumour characteristics. Principal component analysis (PCA) was firstly performed and then multiple regression analyses were performed by using the extracted principal components.

RESULTS

Regarding Ga-DOTATOC PET, SZV, entropy, intensity variability and SRD were predictive for tumour dimension. Regarding F-FDG PET, intensity variability, SZV, homogeneity, SUVmax and MTV were predictive for tumour dimension. Four principal components were extracted from PCA: PC1 correlated with all F-FDG variables, while PC2, PC3 and PC4 with Ga-DOTATOC variables. PC1 was the only significantly predicting angioinvasion (P = 0.0222); PC4 was the only one significantly predicting lymph nodal involvement (P = 0.0151). All principal components except PC4 significantly predicted tumour dimension (P  <0.0001 for PC1, P = 0.0016 for PC2 and P < 0.0001 for PC3). Co-V from Ga-DOTATOC PET/CT was predictive of the outcome.

CONCLUSION

Specific texture features derived from preoperative Ga-DOTATOC and F-FDG PET/CT could noninvasively predict specific tumour characteristics and patients' outcome, delineating the potential role of dual tracer technique and texture analysis in the risk assessment of patients with PanNENs.

Intratumor Heterogeneity Assessed by 18F-FDG PET/CT Predicts Treatment Response and Survival Outcomes in Patients with Hodgkin Lymphoma

RATIONALE AND OBJECTIVES

Radiomic analysis of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) images enables the extraction of quantitative information of intratumour heterogeneity. This study investigated whether the baseline ¹⁸F-FDG PET/CT radiomics can predict treatment response and survival outcomes in patients with Hodgkin lymphoma (HL).

MATERIALS AND METHODS

Thirty-five patients diagnosed with HL who underwent ¹⁸F-FDG PET/CT scans before and during chemotherapy were retrospectively enrolled in this investigation. For each patient, we extracted 709 radiomic features from pretreatment PET/CT images. Clinical variables (age, gender, B symptoms, bulky tumor, and disease stage) and radiomic signatures (intensity, texture, and wavelet) were analyzed according to response to therapy, progression-free survival (PFS), and overall survival (OS). Receiver operating characteristic curve, logistic regression, and Cox proportional hazards model were used to examine potential predictive and prognostic factors.

RESULTS

High-intensity run emphasis (HIR) of PET and run-length nonuniformity (RLNU) of CT extracted from gray-level run-length matrix (GLRM) in high-frequency wavelets were independent predictive factors for the treatment response (odds ratio [OR] = 36.4, p = 0.014; OR = 30.4, p = 0.020). Intensity nonuniformity (INU) of PET and wavelet short run emphasis (SRE) of CT from GLRM and Ann Arbor stage were independently related to PFS (hazard ratio [HR] = 9.29, p = 0.023; HR = 18.40, p = 0.012; HR = 7.46, p = 0.049). Zone-size nonuniformity (ZSNU) of PET from gray-level size zone matrix (GLSZM) was independently associated with OS (HR = 41.02, p = 0.001). Based on these factors, a prognostic stratification model was devised for the risk stratification of patients. The proposed model allowed the identification of four risk groups for PFS and OS (p < 0.001 and p < 0.001).

CONCLUSION

HIR_{_}GLRM_PET and RLNU_{_}GLRM_CT in high-frequency wavelets serve as independent predictive factors for treatment response. ZSNU_{_}GLSZM_PET, INU_{_}GLRM_PET, and wavelet SRE_{_}GLRM_CT serve as independent prognostic factors for survival outcomes. The present study proposes a prognostic stratification model that may be clinically beneficial in guiding risk-adapted treatment strategies for patients with HL.

Potential Added Value of PET/CT Radiomics for Survival Prognostication beyond AJCC 8th Edition Staging in Oropharyngeal Squamous Cell Carcinoma

Accurate risk-stratification can facilitate precision therapy in oropharyngeal squamous cell carcinoma (OPSCC). We explored the potential added value of baseline positron emission tomography (PET)/computed tomography (CT) radiomic features for prognostication and risk stratification of OPSCC beyond the American Joint Committee on Cancer (AJCC) 8th edition staging scheme. Using institutional and publicly available datasets, we included OPSCC patients with known human papillomavirus (HPV) status, without baseline distant metastasis and treated with curative intent. We extracted 1037 PET and 1037 CT radiomic features quantifying lesion shape, imaging intensity, and texture patterns from primary tumors and metastatic cervical lymph nodes. Utilizing random forest algorithms, we devised novel machine-learning models for OPSCC progression-free survival (PFS) and overall survival (OS) using “radiomics” features, “AJCC” variables, and the “combined” set as input. We designed both single- (PET or CT) and combined-modality (PET/CT) models. Harrell’s C-index quantified survival model performance; risk stratification was evaluated in Kaplan–Meier analysis. A total of 311 patients were included. In HPV-associated OPSCC, the best “radiomics” model achieved an average C-index ± standard deviation of 0.62 ± 0.05 (p = 0.02) for PFS prediction, compared to 0.54 ± 0.06 (p = 0.32) utilizing “AJCC” variables. Radiomics-based risk-stratification of HPV-associated OPSCC was significant for PFS and OS. Similar trends were observed in HPV-negative OPSCC. In conclusion, radiomics imaging features extracted from pre-treatment PET/CT may provide complimentary information to the current AJCC staging scheme for survival prognostication and risk-stratification of HPV-associated OPSCC.

Improving PET Imaging Acquisition and Analysis With Machine Learning: A Narrative Review With Focus on Alzheimer's Disease and Oncology

Machine learning (ML) algorithms have found increasing utility in the medical imaging field and numerous applications in the analysis of digital biomarkers within positron emission tomography (PET) imaging have emerged. Interest in the use of artificial intelligence in PET imaging for the study of neurodegenerative diseases and oncology stems from the potential for such techniques to streamline decision support for physicians providing early and accurate diagnosis and allowing personalized treatment regimens. In this review, the use of ML to improve PET image acquisition and reconstruction is presented, along with an overview of its applications in the analysis of PET images for the study of Alzheimer's disease and oncology.

Deep learning analysis using FDG-PET to predict treatment outcome in patients with oral cavity squamous cell carcinoma

OBJECTIVE

To assess the utility of deep learning analysis using ¹⁸F-fluorodeoxyglucose (FDG) uptake by positron emission tomography (PET/CT) to predict disease-free survival (DFS) in patients with oral cavity squamous cell carcinoma (OCSCC).

METHODS

One hundred thirteen patients with OCSCC who received pretreatment FDG-PET/CT were included. They were divided into training (83 patients) and test (30 patients) sets. The diagnosis of treatment control/failure and the DFS rate were obtained from patients' medical records. In deep learning analyses, three planes of axial, coronal, and sagittal FDG-PET images were assessed by ResNet-101 architecture. In the training set, image analysis was performed for the diagnostic model creation. The test data set was subsequently analyzed for confirmation of diagnostic accuracy. T-stage, clinical stage, and conventional FDG-PET parameters (the maximum and mean standardized uptake value (SUVmax and SUVmean), heterogeneity index, metabolic tumor volume (MTV), and total lesion glycolysis (TLG) were also assessed with determining the optimal cutoff from training dataset and then validated their diagnostic ability from test dataset.

RESULTS

In dividing into patients with treatment control and failure, the highest diagnostic accuracy of 0.8 was obtained using deep learning classification, with a sensitivity of 0.8, specificity of 0.8, positive predictive value of 0.89, and negative predictive value of 0.67. In the Kaplan-Meier analysis, the DFS rate was significantly different only with the analysis of deep learning-based classification (p < .01).

CONCLUSIONS

Deep learning-based diagnosis with FDG-PET images may predict treatment outcome in patients with OCSCC.

KEY POINTS

• Deep learning-based diagnosis of FDG-PET images showed the highest diagnostic accuracy to predict the treatment outcome in patients with oral cavity squamous cell carcinoma. • Deep learning-based diagnosis was shown to differentiate patients between good and poor disease-free survival more clearly than conventional T-stage, clinical stage, and conventional FDG-PET-based parameters.

Applications of radiomics in precision diagnosis, prognostication and treatment planning of head and neck squamous cell carcinomas

Recent advancements in computational power, machine learning, and artificial intelligence technology have enabled automated evaluation of medical images to generate quantitative diagnostic and prognostic biomarkers. Such objective biomarkers are readily available and have the potential to improve personalized treatment, precision medicine, and patient selection for clinical trials. In this article, we explore the merits of the most recent addition to the “-omics” concept for the broader field of head and neck cancer – “Radiomics”. This review discusses radiomics studies focused on (molecular) characterization, classification, prognostication and treatment guidance for head and neck squamous cell carcinomas (HNSCC). We review the underlying hypothesis, general concept and typical workflow of radiomic analysis, and elaborate on current and future challenges to be addressed before routine clinical application.

Role of imaging biomarkers for prognostic prediction in patients with pancreatic ductal adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive tumours. PDAC has a poor prognosis; therefore, it is necessary to perform further risk stratification. Identifying prognostic factors before treatment might help to implement suitable and personalised treatment for individuals and avoid side effects. Conventional staging systems and tumour biomarkers are fundamental to establish prognosis; however, they have obvious limitations. Novel imaging biomarkers extracted from advanced imaging techniques offer opportunities to evaluate underlying tumour physiological characteristics, such as mutational status, cellular composition, local microenvironment, tumour metabolism, and biological behaviour. Thus, imaging biomarkers might help the decision making of oncologists and surgeons. The present review discusses the functions of imaging biomarkers for prognostic prediction in patients with PDAC and their potential value for further translation in clinical practice.

Radiomic analysis for response assessment in advanced head and neck cancers, a distant dream or an inevitable reality? A systematic review of the current level of evidence

OBJECTIVE

The recent increase in publications on radiomic analysis as means to produce diagnostic and predictive biomarkers in head and neck cancers (HNCC) reveal complicated and often conflicting results. The objective of this paper is to systematically review the published data, and evaluate the current level of evidence accumulated that would determine clinical application.

METHODS

Data sources: Articles in the English language available on the Ovid-MEDLINE and Embase databases were used for the literature search. Study selection:Studies which evaluated the role of radiomics as a predictive or prognostic tool for response assessment in HNCC were included in this review.Study appraisal and synthesis methods: The authors set-out to perform a meta-analysis, however given the small number of studies retrieved that presented adequate data, combined with excessive methodological heterogeneity, we could only perform a structured descriptive systematic review summarizing the key findings. Independent extraction of articles was performed by two authors using predefined data fields and any disagreement was resolved by consensus.

RESULTS

Though most papers concluded that radiomics is an effective predictive and prognostic biomarker in the management of HNCC, significant heterogeneity exists in the study methodology and statistical modelling; thus precluding accurate mathematical comparison or the ability to make clear recommendations going forwards. Moreover, most studies have not been validated and the reproducibility of their results will be a challenge.

CONCLUSION

Until robust external validation studies on the reproducibility and accuracy of radiomic analysis methods on HNCC are carried out, the current level of evidence remains low, with the authors advising caution against hasty implementation of these tools in the multidisciplinary clinic.

ADVANCES IN KNOWLEDGE

This review is the first attempt to critically analyze the merits and demerits of currently published literature on tumour heterogeneity studies in HNCC, and identifies specific loop holes that need to be addressed by research groups, for a meaningful clinical translation of this potential biomarker.

Prognostic value of the radiomics-based model in progression-free survival of hypopharyngeal cancer treated with chemoradiation

PURPOSE

To develop a radiomics-based model to stratify the risk of early progression (local/regional recurrence or metastasis) among patients with hypopharyngeal cancer undergoing chemoradiotherapy and modify their pretreatment plans.

MATERIALS AND METHODS

We randomly assigned 113 patients into two cohorts: training (n = 80) and validation (n = 33). The radiomic significant features were selected in the training cohort using least absolute shrinkage and selection operator and Akaike information criterion methods, and they were used to build the radiomic model. The concordance index (C-index) was applied to evaluate the model's prognostic performance. A Kaplan-Meier analysis and the log-rank test were used to assess risk stratification ability of models in predicting progression. A nomogram was plotted to predict individual risk of progression.

RESULTS

Composed of four significant features, the radiomic model showed good performance in stratifying patients into high- and low-risk groups of progression in both the training and validation cohorts (log-rank test, p = 0.00016, p = 0.0063, respectively). Peripheral invasion and metastasis were selected as significant clinical variables. The combined radiomic-clinical model showed good discriminative performance, with C-indices 0.804 (95% confidence interval (CI), 0.688-0.920) and 0.756 (95% CI, 0.605-0.907) in the training and validation cohorts, respectively. The median progression-free survival (PFS) in the high-risk group was significantly shorter than that in the low-risk group in the training (median PFS, 9.5 m and 19.0 m, respectively; p [log-rank] < 0.0001) and validation (median PFS, 11.3 m and 22.5 m, respectively; p [log-rank] = 0.0063) cohorts.

CONCLUSIONS

A radiomics-based model was established to predict the risk of progression in hypopharyngeal cancer with chemoradiotherapy.

KEY POINTS

• Clinical information showed limited performance in stratifying the risk of progression among patients with hypopharyngeal cancer. • Imaging features extracted from CECT and NCCT images were independent predictors of PFS. • We combined significant features and valuable clinical variables to establish a nomogram to predict individual risk of progression.

Textural features of hypoxia PET predict survival in head and neck cancer during chemoradiotherapy

PURPOSE

The aim of this study was to investigate whether textural features of tumour hypoxia, assessed with serial [¹⁸F]fluoromisonidazole (FMISO)-PET, were able to predict clinical outcome in patients with head and neck squamous cell carcinoma (HNSCC, T1-4, N+, M0) during chemoradiotherapy (CRT).

METHODS

In a preliminary evaluation of a prospective trial, tumour hypoxia was evaluated in 29 patients via serial FMISO-PET before and during CRT. All patients received an initial [¹⁸F]fluorodeoxyglucose (FDG)-PET before CRT, and tumour regions were defined on this FDG-PET. The first-order metrics tumour-to-background ratio (TBR_mean, TBR_max, TBR_peak), coefficient of variation, total lesion uptake and integral non-uniformity were calculated for all scans. Further, 3 second-order (textural) features from two grey-level matrices were calculated, as well as differential non-uniformity (u_diff). Prognostic value was examined by median split for group separation (GS) in Kaplan-Meier estimates and correlated with overall survival (OS), quantified via log-rank tests (p ≤ 0.05) and group-relative hazard ratios (HR).

RESULTS

Within a median follow-up of 29.6 months (95% CI: 16.8-48.0 months), no first-order metrics predicted OS with a significant GS (all p > 0.05) on any FMISO-PET scan. Only u_diff before and in week 2 during CRT (p = 0.03, HR = 10.8 and p = 0.05, HR = 5.2) and non-uniformity from grey-level run length matrix in week 2 separated prognostic groups (p = 0.05, HR = 5.3); lower values were correlated with better OS. Further, the decrease in u_diff from before CRT to week 2 was correlated with better OS (p = 0.04, HR = 9.4). FDG-PET before CRT did not predict outcome in any measure.

CONCLUSIONS

Textural features on FMISO-PET scans before CRT, in week 2 and, to a limited degree, the change of features during CRT, were able to identify head and neck squamous cell carcinoma patients with better OS, suggesting that a higher homogeneity of the degree of hypoxia in tumours could correlate with a better outcome after CRT.

Prognostic Value of Pretreatment Radiomic Features of 18F-FDG PET in Patients With Hodgkin Lymphoma

PURPOSE

This study investigated whether a radiomic analysis of pretreatment F-FDG PET can predict prognosis in patients with Hodgkin lymphoma (HL).

METHODS

Forty-two patients who were diagnosed as having HL and underwent pretreatment F-FDG PET scans were retrospectively enrolled. For each patient, we extracted 450 radiomic features from PET images. The prognostic significance of the clinical and radiomic features was assessed in relation to progression-free survival (PFS) and overall survival (OS). Receiver operating characteristic curve, Cox proportional hazards regression, and Kaplan-Meier analyses were performed to examine the potential independent predictors and to evaluate the predictive value.

RESULTS

Intensity nonuniformity extracted from a gray-level run-length matrix and the Ann Arbor stage were independently associated with PFS (hazard ratio [HR] = 22.8, P < 0.001; HR = 7.6, P = 0.024) and OS (HR = 14.5, P = 0.012; HR = 8.5, P = 0.048), respectively. In addition, SUV kurtosis was an independent prognosticator for PFS (HR = 6.6, P = 0.026). We devised a prognostic scoring system based on these 3 risk predictors. The proposed scoring system further improved the risk stratification of the current staging classification (P < 0.001).

CONCLUSIONS

The radiomic feature intensity nonuniformity is an independent prognostic predictor of PFS and OS in patients with HL. We devised a prognostic scoring system, which may be more beneficial for patient risk stratification in guiding therapy compared with the current Ann Arbor staging system.

Prediction of Overall Survival and Progression-Free Survival by the 18F-FDG PET/CT Radiomic Features in Patients with Primary Gastric Diffuse Large B-Cell Lymphoma

Purpose. To determine whether the radiomic features of ¹⁸F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) contribute to prognosis prediction in primary gastric diffuse large B-cell lymphoma (PG-DLBCL) patients. Methods. This retrospective study included 35 PG-DLBCL patients who underwent PET/CT scans at West China Hospital before curative treatment. The volume of interest (VOI) was drawn around the tumor, and radiomic analysis of the PET and CT images, within the same VOI, was conducted. The metabolic and textural features of PET and CT images were evaluated. Correlations of the extracted features with the overall survival (OS) and progression-free survival (PFS) were evaluated. Univariate and multivariate analyses were conducted to assess the prognostic value of the radiomic parameters. Results. In the univariate model, many of the textural features, including kurtosis and volume, extracted from the PET and CT datasets were significantly associated with survival (5 for OS and 7 for PFS (PET); 7 for OS and 14 for PFS (CT)). Multivariate analysis identified kurtosis (hazard ratio (HR): 28.685, 95% confidence interval (CI): 2.067–398.152, p=0.012), metabolic tumor volume (MTV) (HR: 26.152, 95% CI: 2.089–327.392, p=0.011), and gray-level nonuniformity (GLNU) (HR: 14.642, 95% CI: 2.661–80.549, p=0.002) in PET and sphericity (HR: 11.390, 95% CI: 1.360–95.371, p=0.025) and kurtosis (HR: 11.791, 95% CI: 1.583–87.808, p=0.016), gray-level nonuniformity (GLNU) (HR: 6.934, 95% CI: 1.069–44.981, p=0.042), and high gray-level zone emphasis (HGZE) (HR: 9.805, 95% CI: 1.359–70.747, p=0.024) in CT as independent prognostic factors. Conclusion. ¹⁸F-FDG PET/CT radiomic features are potentially useful for survival prediction in PG-DLBCL patients. However, studies with larger cohorts are needed to confirm the clinical prognostication of these parameters.

Texture analysis of pretreatment [18F]FDG PET/CT for the prognostic prediction of locally advanced salivary gland carcinoma treated with interstitial brachytherapy

Background

The aim of this study was to evaluate the prognostic value of positron emission tomography (PET) parameters and the PET texture features of fluorine 18-fluorodeoxyglucose ([¹⁸F]FDG) uptake on pretreatment PET/computed tomography (CT) in patients with locally advanced salivary gland carcinoma treated with interstitial brachytherapy.

Methods

Forty-three patients with locally advanced salivary gland carcinoma of the head and neck were treated with ¹²⁵I interstitial brachytherapy as the sole modality and underwent [¹⁸F]FDG PET/CT scanning before treatment. Tumor segmentation and texture analysis were performed using the 3D slicer software. In total, 54 features were extracted and categorized as first-order statistics, morphology and shape, gray-level co-occurrence matrix, and gray-level run length matrix. Up to November 2018, the follow-up time ranged from 6 to 120 months (median 18 months). Cumulative survival was calculated by the Kaplan-Meier method. Factors between groups were compared by the log-rank test. Multivariate Cox regression analysis with a backward conditional method was used to predict progression-free survival (PFS).

Results

The 3- and 5-year locoregional control (LC) rates were 55.4% and 37.0%, respectively. The 3- and 5-year PFS rates were 51.2% and 34.1%, respectively. The 3- and 5-year overall survival (OS) rates were 77.0% and 77.0%, respectively. Univariate analysis revealed that minimum intensity, mean intensity, median intensity, root mean square, and long run emphasis (LRE) were significant predictors of PFS, whereas clinicopathological factors, conventional PET parameters, and PET texture features failed to show significance. Multivariate Cox regression analysis showed that minimum intensity and LRE were significant predictors of PFS.

Conclusions

The texture analysis of pretreatment [¹⁸F]FDG PET/CT provided more information than conventional PET parameters for predicting patient prognosis of locally advanced salivary gland carcinoma treated with interstitial brachytherapy. The minimum intensity was a risk factor for PFS, and LRE was a favorable factor in prognostic prediction according to the primary results.

MRI Radiomic Features Are Independently Associated With Overall Survival in Soft Tissue Sarcoma

PURPOSE

Soft tissue sarcomas (STS) represent a heterogeneous group of diseases, and selection of individualized treatments remains a challenge. The goal of this study was to determine whether radiomic features extracted from magnetic resonance (MR) images are independently associated with overall survival (OS) in STS.

METHODS AND MATERIALS

This study analyzed 2 independent cohorts of adult patients with stage II-III STS treated at center 1 (N = 165) and center 2 (N = 61). Thirty radiomic features were extracted from pretreatment T1-weighted contrast-enhanced MR images. Prognostic models for OS were derived on the center 1 cohort and validated on the center 2 cohort. Clinical-only (C), radiomics-only (R), and clinical and radiomics (C+R) penalized Cox models were constructed. Model performance was assessed using Harrell's concordance index.

RESULTS

In the R model, tumor volume (hazard ratio [HR], 1.5) and 4 texture features (HR, 1.1-1.5) were selected. In the C+R model, both age (HR, 1.4) and grade (HR, 1.7) were selected along with 5 radiomic features. The adjusted c-indices of the 3 models ranged from 0.68 (C) to 0.74 (C+R) in the derivation cohort and 0.68 (R) to 0.78 (C+R) in the validation cohort. The radiomic features were independently associated with OS in the validation cohort after accounting for age and grade (HR, 2.4; P = .009).

CONCLUSIONS

This study found that radiomic features extracted from MR images are independently associated with OS when accounting for age and tumor grade. The overall predictive performance of 3-year OS using a model based on clinical and radiomic features was replicated in an independent cohort. Optimal models using clinical and radiomic features could improve personalized selection of therapy in patients with STS.

Inter-observer and segmentation method variability of textural analysis in pre-therapeutic FDG PET/CT in head and neck cancer

Aim

Characterizing tumor heterogeneity with textural indices extracted from 18F-fluorodeoxyglucose positron emission tomography (FDG PET/CT) is of growing interest in oncology. Several series showed promising results to predict survival in patients with head and neck squamous cell carcinoma (HNSCC), analyzing various tumor segmentation methods and textural indices. This preliminary study aimed at assessing the inter-observer and inter-segmentation method variability of textural indices in HNSCC pre-therapeutic FDG PET/CT.

Materials and methods

Consecutive patients with HNSCC referred in our department for a pre-therapeutic FDG PET/CT from January to March 2016 were retrospectively included. Two nuclear medicine physicians separately segmented all tumors using 3 different segmentation methods: a relative standardized uptake value (SUV) threshold (40%SUVmax), a signal-to-noise adaptive SUV threshold (DAISNE) and an image gradient-based method (PET-EDGE). SUV and metabolic tumor volume were recorded. Thirty-one textural indices were calculated using LIFEx software (www.lifexsoft.org). After correlation analysis, selected indices’ inter-segmentation method and inter-observer variability were calculated.

Results

Forty-three patients (mean age 63.8±9.3y) were analyzed. Due to a too small segmented tumor volume of interest, textural analysis could not be performed in 6, 11 and 15 cases with respectively DAISNE, 40%SUVmax and PET-EDGE segmentation methods. Five independent textural indices were selected (Homogeneity, Correlation, Entropy, Busyness and LZLGE). There was a high inter-contouring method variability for Homogeneity, Correlation, Entropy and LZLGE (p<0.0001 for each index). The inter-observer reproducibility analysis revealed an excellent agreement for 3 indices (Homogeneity, Correlation and Entropy) with an intraclass correlation coefficient higher than 0.90 for the 3 methods.

Conclusions

This preliminary study showed a high variability of 4 out of 5 textural indices (Homogeneity, Correlation, Entropy and LZLGE) extracted from pre-therapeutic FDG PET/CT in HNSCC using 3 different contouring methods. However, for each method, there was an excellent agreement between observers for 3 of these textural indices (Homogeneity, Correlation and Entropy).

Pre-treatment 18F-FDG PET-based radiomics predict survival in resected non-small cell lung cancer

AIM

To assess the prognostic value of 2-[¹⁸F]-fluoro-2-deoxy-d-glucose (FDG) positron-emission tomography (PET)-based radiomics using a machine learning approach in patients with non-small cell lung cancer (NSCLC).

MATERIALS AND METHODS

Ninety-three patients with stage I-III NSCLC who underwent combined PET/computed tomography (CT) followed by curative resection. A total of 35 unique quantitative radiomic features was extracted from the PET images, which included imaging phenotypes such as pixel intensity, shape, and texture. Radiomic features were ranked based on score according to their correlation with disease recurrence status within a 3-year follow-up. The recurrence risk classification performances of machine learning algorithms (random forest, neural network, naive Bayes, logistic regression, and support vector machine) using the 20 best-ranked features were compared using the areas under the receiver operating characteristic curve (AUC) and validated by the random sampling method.

RESULTS

Contrast and busyness texture features from neighbourhood grey-level difference matrix were found to be the two best predictors of disease recurrence. The random forest model obtained the best performance (AUC: 0.956, accuracy: 0.901, F1 score: 0.872, precision: 0.905, recall: 0.842), followed by the neural network model (AUC: 0.871, accuracy: 0.780, F1 score: 0.708, precision: 0.755, recall: 0.666).

CONCLUSION

A PET-based radiomic model was developed and validated for risk classification in NSCLC. The machine learning approach with random forest classifier exhibited good performance in predicting the recurrence risk. Radiomic features may help clinicians to improve the risk stratification for clinical practice.

A mathematical-descriptor of tumor-mesoscopic-structure from computed-tomography images annotates prognostic- and molecular-phenotypes of epithelial ovarian cancer

The five-year survival rate of epithelial ovarian cancer (EOC) is approximately 35-40% despite maximal treatment efforts, highlighting a need for stratification biomarkers for personalized treatment. Here we extract 657 quantitative mathematical descriptors from the preoperative CT images of 364 EOC patients at their initial presentation. Using machine learning, we derive a non-invasive summary-statistic of the primary ovarian tumor based on 4 descriptors, which we name "Radiomic Prognostic Vector" (RPV). RPV reliably identifies the 5% of patients with median overall survival less than 2 years, significantly improves established prognostic methods, and is validated in two independent, multi-center cohorts. Furthermore, genetic, transcriptomic and proteomic analysis from two independent datasets elucidate that stromal phenotype and DNA damage response pathways are activated in RPV-stratified tumors. RPV and its associated analysis platform could be exploited to guide personalized therapy of EOC and is potentially transferrable to other cancer types.

Radiomics in Oncological PET/CT: a Methodological Overview

Radiomics is a medical imaging analysis approach based on computer-vision. Metabolic radiomics in particular analyses the spatial distribution patterns of molecular metabolism on PET images. Measuring intratumoral heterogeneity via image is one of the main targets of radiomics research, and it aims to build a image-based model for better patient management. The workflow of radiomics using texture analysis follows these steps: 1) imaging (image acquisition and reconstruction); 2) preprocessing (segmentation & quantization); 3) quantification (texture matrix design & texture feature extraction); and 4) analysis (statistics and/or machine learning). The parameters or conditions at each of these steps are effect on the results. In statistical testing or modeling, problems such as multiple comparisons, dependence on other variables, and high dimensionality of small sample size data should be considered. Standardization of methodology and harmonization of image quality are one of the most important challenges with radiomics methodology. Even though there are current issues in radiomics methodology, it is expected that radiomics will be clinically useful in personalized medicine for oncology.