Textural features on 18F-FDG PET/CT and dynamic contrast-enhanced MR imaging for predicting treatment response and survival of patients with hypopharyngeal carcinoma

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.

Fully automated segmentation and radiomics feature extraction of hypopharyngeal cancer on MRI using deep learning

OBJECTIVES

To use convolutional neural network for fully automated segmentation and radiomics features extraction of hypopharyngeal cancer (HPC) tumor in MRI.

METHODS

MR images were collected from 222 HPC patients, among them 178 patients were used for training, and another 44 patients were recruited for testing. U-Net and DeepLab V3 + architectures were used for training the models. The model performance was evaluated using the dice similarity coefficient (DSC), Jaccard index, and average surface distance. The reliability of radiomics parameters of the tumor extracted by the models was assessed using intraclass correlation coefficient (ICC).

RESULTS

The predicted tumor volumes by DeepLab V3 + model and U-Net model were highly correlated with those delineated manually (p < 0.001). The DSC of DeepLab V3 + model was significantly higher than that of U-Net model (0.77 vs 0.75, p < 0.05), particularly in those small tumor volumes of < 10 cm3 (0.74 vs 0.70, p < 0.001). For radiomics extraction of the first-order features, both models exhibited high agreement (ICC: 0.71-0.91) with manual delineation. The radiomics extracted by DeepLab V3 + model had significantly higher ICCs than those extracted by U-Net model for 7 of 19 first-order features and for 8 of 17 shape-based features (p < 0.05).

CONCLUSION

Both DeepLab V3 + and U-Net models produced reasonable results in automated segmentation and radiomic features extraction of HPC on MR images, whereas DeepLab V3 + had a better performance than U-Net.

CLINICAL RELEVANCE STATEMENT

The deep learning model, DeepLab V3 + , exhibited promising performance in automated tumor segmentation and radiomics extraction for hypopharyngeal cancer on MRI. This approach holds great potential for enhancing the radiotherapy workflow and facilitating prediction of treatment outcomes.

KEY POINTS

• DeepLab V3 + and U-Net models produced reasonable results in automated segmentation and radiomic features extraction of HPC on MR images. • DeepLab V3 + model was more accurate than U-Net in automated segmentation, especially on small tumors. • DeepLab V3 + exhibited higher agreement for about half of the first-order and shape-based radiomics features than U-Net.

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.

The Usefulness of Machine Learning-Based Evaluation of Clinical and Pretreatment [18F]-FDG-PET/CT Radiomic Features for Predicting Prognosis in Hypopharyngeal Cancer

PURPOSE

To examine whether the machine learning (ML) analyses using clinical and pretreatment 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography ([¹⁸F]-FDG-PET)-based radiomic features were useful for predicting prognosis in patients with hypopharyngeal cancer.

PROCEDURES

This retrospective study included 100 patients with hypopharyngeal cancer who underwent [¹⁸F]-FDG-PET/X-ray computed tomography (CT) before treatment, and these patients were allocated to the training (n=80) and validation (n=20) cohorts. Eight clinical (age, sex, histology, T stage, N stage, M stage, UICC stage, and treatment) and 40 [¹⁸F]-FDG-PET-based radiomic features were used to predict disease progression. A feature reduction procedure based on the decrease of the Gini impurity was applied. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were compared using the area under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis.

RESULTS

The five most important features for predicting disease progression were UICC stage, N stage, gray level co-occurrence matrix entropy (GLCM_Entropy), gray level run length matrix run length non-uniformity (GLRLM_RLNU), and T stage. Patients who experienced disease progression displayed significantly higher UICC stage, N stage, GLCM_Entropy, GLRLM_RLNU, and T stage than those without progression (each, p<0.001). In both cohorts, the logistic regression model constructed by these 5 features was the best performing classifier (training: AUC=0.860, accuracy=0.800; validation: AUC=0.803, accuracy=0.700). In the logistic regression model, 5-year PFS was significantly higher in patients with predicted non-progression than those with predicted progression (75.8% vs. 8.3%, p<0.001), and this model was only the independent factor for PFS in multivariate analysis (hazard ratio = 3.22; 95% confidence interval = 1.03-10.11; p=0.045).

CONCLUSIONS

The logistic regression model constructed by UICC, T and N stages and pretreatment [¹⁸F]-FDG-PET-based radiomic features, GLCM_Entropy, and GLRLM_RLNU may be the most important predictor of prognosis in patients with hypopharyngeal cancer.

Carotid arterial blowout after organ preserving chemoradiation therapy in hypopharyngeal cancer

Laryngeal preserving concurrent chemoradiation has been advocated for hypopharyngeal cancers. The use of radiotherapy (RT) in the larynx could lead to increased rates of radionecrosis. In this study, we investigated a rare but disastrous complication, carotid blow-out syndrome (CBS), related with the persistent radionecrosis. Retrospective cohort study. This retrospective study enrolled hypopharyngeal cancer patients with biopsy-proven pharyngeal and laryngeal chondronecrosis (PLCRN), which was rated by the Chandler Grading System. From 2002 to 2018, a total of 346 hypopharygeal cancer patients received upfront radiation therapy, 13 PLCRN patients were identified in a rate of 3.8%. All PLRN patients received RT with a mean radiation dose of 70.81 ± 0.85 Gy. All patients had Chandler Grade IV at the time of presentation, which was a mean of 15.08 months (range: 5-109 months) from the time of cancer diagnosis to PLCRN diagnosis. In 5 of the 13 PLCRN patients developed CBS. Three of the CBS originated from superior thyroid artery, one from lingual artery and one from the carotid artery. Three (60%) of the 5 CBS patients expired due to loss of airway and hemodynamic instability. Two (40%) were rescued by emergent airway secure and emergent angiographic embolization. Persistent PLCRN could lead to disastrous vascular complications. CBSs were demonstrated to be more frequently originated from the branches of carotid artery rather than carotid artery per se. Clinical alert with early airway protection could strive for time to do interventions and prevent mortalities.

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.

Diagnostic Performance of Vascular Permeability and Texture Parameters for Evaluating the Response to Neoadjuvant Chemoradiotherapy in Patients With Esophageal Squamous Cell Carcinoma

Background

Esophageal squamous cell carcinoma (ESCC) is an aggressive type of cancer, associated with poor prognosis. The development of an accurate and non-invasive method to evaluate the pathologic response of patients with ESCC to chemoradiotherapy remains a critical issue. Therefore, the aim of this study was to assess the importance of vascular permeability and texture parameters in predicting the response to neoadjuvant chemoradiotherapy (NACRT) in patients with ESCC.

Methods

This prospective analysis included patients with T1–T2 stage of ESCC, without either lymphatic or metastasis, and distant metastasis. All patients underwent surgery having received two rounds of NACRT. All patients underwent dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) twice, i.e., before the first NACRT and after the second NACRT. Patients were assessed for treatment response at 30 days after the second NACRT. Patients were divided into the complete response (CR) and partial response (PR) groups based on their responses to NACRT. Vascular permeability and texture parameters were extracted from the DCE-MRI scans. After assessing the diagnostic performance of individual parameters, a combined model with vascular permeability and texture parameters was generated to predict the response to NACRT.

Results

In this study, the CR and PR groups included 16 patients each. The volume transfer constant (Ktrans), extracellular extravascular volume fraction (ve), and entropy values, as well as changes to each of these parameters, extracted from the second DCE-MRI scans, showed significant differences between the CR and PR groups. The area under the curve (AUC) of Ktrans, ve, and entropy values showed good diagnostic ability (0.813, 0.789, and 0.707, respectively). A logistic regression model combining Ktrans, ve, and entropy had significant diagnostic ability (AUC=0.977).

Conclusions

The use of a combined model with vascular permeability and texture parameters can improve post-NACRT prognostication in patients with ESCC.

Diagnostic Accuracy of Combined PET/CT with MRI, 18F-FDG PET/MRI, and 18F-FDG PET/CT in Patients with Oropharyngeal and Hypopharyngeal Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis

Introduction

The aim of this paper is to compare the diagnostic accuracy of PET/CT, PET/MRI, and the combination of PET/CT and MRI for detecting synchronous cancer and distant metastasis in patients with oropharyngeal and hypopharyngeal squamous cell carcinomas (OHSCC).

Method

A large and growing body of literature has been conducted using the Preferred Reporting Items for Systematic Reviews (PRISMA). The researchers collected all accessible literature existing through Cochrane Library (John Wiley & Sons) electronic databases, Embase (Elsevier), PubMed (U.S. National Library of Medicine), Scopus, and Google Scholar up to June 2020. Analyses were conducted using Stata version 12.0 (StataCorp LP).

Results

A total of nine studies consisting of 1166 patients were included. The pooled sensitivity of combined PET/CT with MRI, 18F-FDG PET/MRI, and 18F-FDG PET/CT was 0.92, 0.80, and 0.79, respectively, and the corresponding specificities were 0.93, 0.91, and 0.88. The overall prevalence of distant metastases and synchronous cancer in patients with oropharyngeal and hypopharyngeal squamous cell carcinomas was 9.2% and 11.8%, respectively, with the esophagus (4.6%) being the most common site of synchronous cancer. The most common sites of distant metastases were lung (3%), bone (1.2%), and distant lymph nodes (1.2%), respectively.

Conclusion

Our study showed an approximately similar diagnostic performance for PET/CT, PET/MRI, and the combination of PET/CT and MRI for metastasis assessment in advanced oropharyngeal and hypopharyngeal squamous cell carcinomas.

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.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for pretreatment prediction of neoadjuvant chemotherapy response in locally advanced hypopharyngeal cancer

Objective:The aim of this study was to predict response to neoadjuvant chemotherapy (NAC) in patients with locally advanced hypopharyngeal cancer by dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).Methods:A retrospective study enrolled 46 diagnosed locally advanced hypopharyngeal cancer. DCE-MRI were performed prior to and after two cycles of NAC. The volume transfer constant (K^trans), extracellular extravascular volume fraction (V_e), and plasma volume fraction (K_ep) were computed from primary tumors. DCE-MRI parameters were used to measure tumor response according to the Response Evaluation Criteria in Solid Tumors criteria (RECIST).Results：After 2 NAC cycles, 30 out of 46 patients were categorized into the responder group, whereas the other 16 were categorized into non-responder group. Compared with the pretreatment value, the post-treatment K^trans and K_ep was significantly lower (P < 0.05), but no significant change in V_e (P > 0.05). Compared with non-responders, a notably higher pretreatment K^trans, K_ep, lower post-treatment K^trans, higher ΔK^trans and ΔK_ep were observed in responders (all P < 0.05). While the pretreatment V_e, post-treatment V_e, and ΔV_e did not differ significantly (P>0.05) between the two groups. The receiver operating characteristic curve analysis revealed that pretreatment K^trans of 0.202/min is the most optimal cut-off in predicting response to chemotherapy, resulting in an AUC of 0.837 and corresponding sensitivity and specificity of 76.7%, and 81.1%, respectively.Conclusion:DCE-MRI especially pretreatment K^trans can potentially predict the treatment response to neoadjuvant chemotherapy for hypopharyngeal cancer.Advances in knowledge:Few studies of DCE-MRI on hypopharyngeal cancer treated with chemoradiation reported. The results demonstrate that DCE-MRI especially pretreatment K^trans may be more potential value in predicting the treatment response to neoadjuvant chemotherapy for hypopharyngeal cancer.