Dynamic monitoring of radiation-induced white matter microstructure injury in nasopharyngeal carcinoma via high-angular resolution diffusion imaging

PURPOSE

To investigate white matter microstructural abnormalities caused by radiotherapy in nasopharyngeal carcinoma (NPC) patients using MRI high-angular resolution diffusion imaging (HARDI).

METHODS

We included 127 patients with pathologically confirmed NPC: 36 in the pre-radiotherapy group, 29 in the acute response period (post-RT-AP), 23 in the early delayed period (post-RT-ED) group, and 39 in the late-delayed period (post-RT-LD) group. HARDI data were acquired for each patient, and dispersion parameters were calculated to compare the differences in specific fibre bundles among the groups. The Montreal Neurocognitive Assessment (MoCA) was used to evaluate neurocognitive function, and the correlations between dispersion parameters and MoCA were analysed.

RESULTS

In the right cingulum frontal parietal bundles, the fractional anisotropy value decreased to the lowest level post-RT-AP and then reversed and increased post-RT-ED and post-RT-LD. The mean, axial, and radial diffusivity were significantly increased in the post-RT-AP (p < 0.05) and decreased in the post-RT-ED and post-RT-LD groups to varying degrees. MoCA scores were decreased post-radiotherapy than those before radiotherapy (p = 0.005). MoCA and mean diffusivity exhibited a mild correlation in the left cingulum frontal parahippocampal bundle.

CONCLUSIONS

White matter tract changes detected by HARDI are potential biomarkers for monitoring radiotherapy-related brain damage in NPC patients.

Individualized radiology screening for newly diagnosed nasopharyngeal carcinoma

OBJECTIVES

Current guidelines recommend universal PET/CT screening for metastases staging in newly diagnosed nasopharyngeal carcinoma (NPC) despite the low rate of synchronous distant metastasis (SDM). The study aims to achieve individualized screening recommendations of NPC based on the risk of SDM.

METHODS AND MATERIALS

18 pre-treatment peripheral blood indicators was retrospectively collected from 2271 primary NPC patients. A peripheral blood risk score (PBRS) was constructed by indicators associated with SDM on least absolute shrinkage and selection operator (LASSO) regression. The PBRS-based distant metastases (PBDM) model was developed from features selected by logistic regression analyses in the training cohort and then validated in the validation cohort. Receiver operator characteristic curve analysis, calibration curves, and decision curve analysis were applied to evaluate PBDM model performance.

RESULTS

Pre-treatment Epstein-Barr viral DNA copy number, percentage of total lymphocytes, serum lactate dehydrogenase level, and monocyte-to-lymphocyte ratio were most strongly associated with SDM in NPC and used to construct the PBRS. Sex (male), T stage (T3-4), N stage (N2-3), and PBRS (≥1.076) were identified as independent risk factors for SDM and applied in the PBDM model, which showed good performance. Through the model, patients in the training cohort were stratified into low-, medium-, and high-risk groups. Individualized screening recommendations were then developed for patients with differing risk levels.

CONCLUSION

The PBDM model offers individualized recommendations for applying PET/CT for metastases staging in NPC, allowing more targeted screening of patients with greater risk of SDM compared with current recommendations.

Matted Lymph Nodes on MRI in Nasopharyngeal Carcinoma: Prognostic Factor and Potential Indication for Induction Chemotherapy Benefits

BACKGROUND

Lymph node characteristics markedly affect nasopharyngeal carcinoma (NPC) prognosis. Matted node (MN), an important characteristic for lymph node, lacks explored MRI-based prognostic implications.

PURPOSE

Investigate MRI-determined MNs' prognostic value in NPC, including 5-year overall survival (OS), distant metastasis-free survival (DMFS), local recurrence-free survival (LRFS), progression-free survival (PFS), and its role in induction chemotherapy (IC).

STUDY TYPE

Retrospective cohort survival study.

POPULATION

Seven hundred ninety-two patients with non-metastatic NPC (female: 27.3%, >45-year old: 50.1%) confirmed by biopsy.

FIELD STRENGTH/SEQUENCE

5-T/3.0-T, T1-, T2- and post-contrast T1-weighted fast spin echo sequences acquired.

ASSESSMENT

MNs were defined as ≥3 nodes abutting with intervening fat plane replaced by extracapsular nodal spread (ENS). Patients were observed every 3 months for 2 years and every 6 months for 5 years using MRI. Follow-up extended from treatment initiation to death or final follow-up. MNs were evaluated by three radiologists with inter-reader reliability calculated. A 1:1 matched-pair method compared survival differences between MN-positive patients with or without IC. Primary endpoints (OS, DMFS, LRFS, PFS) were calculated from therapy initiation to respective event.

STATISTICAL TESTS

Kappa values assessed inter-reader reliability. Correlation between MN, ENS, and LNN was studied through Spearman's correlation coefficient. Clinical characteristics were calculated via Fisher's exact, Chi-squared, and Student's t-test. Kaplan-Meier curves and log-rank tests analyzed all time-to-event data. Confounding factors were included in Multivariable Cox proportional hazard models to identify independent prognostic factors. P-values <0.05 were considered statistically significant.

RESULTS

MNs incidence was 24.6%. MNs independently associated with decreased 5-year OS, DMFS, and PFS; not LRFS (P = 0.252). MN-positive patients gained significant survival benefit from IC in 5-year OS (88.4% vs. 66.0%) and PFS (76.4% vs. 53.5%), but not DMFS (83.1% vs. 69.9%, P = 0.145) or LRFS (89.9% vs. 77.8%, P = 0.140).

DATA CONCLUSION

MNs may independently stratify NPC risk and offer survival benefit from IC.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Semi-supervised model based on implicit neural representation and mutual learning (SIMN) for multi-center nasopharyngeal carcinoma segmentation on MRI

BACKGROUND

The issue of using deep learning to obtain accurate gross tumor volume (GTV) and metastatic lymph nodes (MLN) segmentation for nasopharyngeal carcinoma (NPC) on heterogeneous magnetic resonance imaging (MRI) images with limited labeling remains unsolved.

METHOD

We collected 918 patients with MRI images from three hospitals to develop and validate models and proposed a semi-supervised framework for the fine delineation of multi-center NPC boundaries by integrating uncertainty-based implicit neural representations named SIMN. The framework utilizes the deep mutual learning approach with CNN and Transformer, incorporating dynamic thresholds. Additionally, domain adaptive algorithms are employed to enhance the performance.

RESULTS

SIMN predictions have a high overlap ratio with the ground truth. Under the 20 % labeled cases, for the internal test cohorts, the average DSC in GTV and MLN are 0.7981 and 0.7804, respectively; for external test cohort Wu Zhou Red Cross Hospital, the average DSC in GTV and MLN are 0.7217 and 0.7581, respectively; for external test cohorts First People Hospital of Foshan, the average DSC in GTV and MLN are 0.7004 and 0.7692, respectively. No significant differences are found in DSC, HD95, ASD, and Recall for patients with different clinical categories. Moreover, SIMN outperformed existing classical semi-supervised methods.

CONCLUSIONS

SIMN showed a highly accurate GTV and MLN segmentation for NPC on multi-center MRI images under Semi-Supervised Learning (SSL), which can easily transfer to other centers without fine-tuning. It suggests that it has the potential to act as a generalized delineation solution for heterogeneous MRI images with limited labels in clinical deployment.

Early detection of nasopharyngeal carcinoma: performance of a short contrast-free screening magnetic resonance imaging

BACKGROUND

Although contrast-enhanced magnetic resonance imaging (MRI) detects early-stage nasopharyngeal carcinoma (NPC) not detected by endoscopic-guided biopsy (EGB), a short contrast-free screening MRI would be desirable for NPC screening programs. This study evaluated a screening MRI in a plasma Epstein-Barr virus (EBV)-DNA NPC screening program.

METHODS

EBV-DNA-screen-positive patients underwent endoscopy, and endoscopy-positive patients underwent EGB. EGB was negative if the biopsy was negative or was not performed. Patients also underwent a screening MRI. Diagnostic performance was based on histologic confirmation of NPC in the initial study or during a follow-up period of at least 2 years.

RESULTS

The study prospectively recruited 354 patients for MRI and endoscopy; 40/354 (11.3%) endoscopy-positive patients underwent EGB. Eighteen had NPC (5.1%), and 336 without NPC (94.9%) were followed up for a median of 44.8 months. MRI detected additional NPCs in 3/18 (16.7%) endoscopy-negative and 2/18 (11.1%) EGB-negative patients (stage I/II, n = 4; stage III, n = 1). None of the 24 EGB-negative patients who were MRI-negative had NPC. MRI missed NPC in 2/18 (11.1%), one of which was also endoscopy-negative. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of MRI, endoscopy, and EGB were 88.9%, 91.1%, 34.8%, 99.4%, and 91.0%; 77.8%, 92.3%, 35.0%, 98.7%, and 91.5%; and 66.7%, 92.3%, 31.6%, 98.1%, and 91.0%, respectively.

CONCLUSION

A quick contrast-free screening MRI complements endoscopy in NPC screening programs. In EBV-screen-positive patients, MRI enables early detection of NPC that is endoscopically occult or negative on EGB and increases confidence that NPC has not been missed.

MFNet: Meta-learning based on frequency-space mix for MRI segmentation in nasopharyngeal carcinoma

Deep learning techniques have been applied to medical image segmentation and demonstrated expert-level performance. Due to the poor generalization abilities of the models in the deployment in different centres, common solutions, such as transfer learning and domain adaptation techniques, have been proposed to mitigate this issue. However, these solutions necessitate retraining the models with target domain data and annotations, which limits their deployment in clinical settings in unseen domains. We evaluated the performance of domain generalization methods on the task of MRI segmentation of nasopharyngeal carcinoma (NPC) by collecting a new dataset of 321 patients with manually annotated MRIs from two hospitals. We transformed the modalities of MRI, including T1WI, T2WI and CE-T1WI, from the spatial domain to the frequency domain using Fourier transform. To address the bottleneck of domain generalization in MRI segmentation of NPC, we propose a meta-learning approach based on frequency domain feature mixing. We evaluated the performance of MFNet against existing techniques for generalizing NPC segmentation in terms of Dice and MIoU. Our method evidently outperforms the baseline in handling the generalization of NPC segmentation. The MF-Net clearly demonstrates its effectiveness for generalizing NPC MRI segmentation to unseen domains (Dice = 67.59%, MIoU = 75.74% T1W1). MFNet enhances the model's generalization capabilities by incorporating mixed-feature meta-learning. Our approach offers a novel perspective to tackle the domain generalization problem in the field of medical imaging by effectively exploiting the unique characteristics of medical images.

Three-dimensional pseudo-continuous arterial spin-labelled perfusion imaging for diagnosing upper cervical lymph node metastasis in patients with nasopharyngeal carcinoma: a whole-node histogram analysis

AIM

To evaluate whole-node histogram parameters of blood flow (BF) maps derived from three-dimensional pseudo-continuous arterial spin-labelled (3D pCASL) imaging in discriminating metastatic from benign upper cervical lymph nodes (UCLNs) for nasopharyngeal carcinoma (NPC) patients.

MATERIALS AND METHODS

Eighty NPC patients with a total of 170 histologically confirmed UCLNs (67 benign and 103 metastatic) were included retrospectively. Pre-treatment 3D pCASL imaging was performed and whole-node histogram analysis was then applied. Histogram parameters and morphological features, such as minimum axis diameter (MinAD), maximum axis diameter (MaxAD), and location of UCLNs, were assessed and compared between benign and metastatic lesions. Predictors were identified and further applied to establish a combined model by multivariate logistic regression in predicting the probability of metastatic UCLNs. Receiver operating characteristic (ROC) curves were used to analyse the diagnostic performance.

RESULTS

Metastatic UCLNs had larger MinAD and MinAD/MaxAD ratio, greater energy and entropy values, and higher incidence of level II (upper jugular group), but lower BF10th value than benign nodes (all p<0.05). MinAD, BF10th, energy, and entropy were validated as independent predictors in diagnosing metastatic UCLNs. The combined model yielded an area under the curve (AUC) of 0.932, accuracy of 84.42 %, sensitivity of 80.6 %, and specificity of 90.29 %.

CONCLUSIONS

Whole-node histogram analysis on BF maps is a feasible tool to differentiate metastatic from benign UCLNs in NPC patients, and the combined model can further improve the diagnostic efficacy.

Prognostic value of pre-treatment [18F] FDG PET/CT in recurrent nasopharyngeal carcinoma without distant metastasis

BACKGROUND

[18 F]-Fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) has the ability to detect local and/or regional recurrence as well as distant metastasis. We aimed to evaluate the prognosis value of PET/CT in locoregional recurrent nasopharyngeal (lrNPC).

METHODS

A total of 451 eligible patients diagnosed with recurrent I-IVA (rI-IVA) NPC between April 2009 and December 2015 were retrospectively included in this study. The differences in overall survival (OS) of lrNPC patients with and without PET/CT were compared in the I-II, III-IVA, r0-II, and rIII-IVA cohorts, which were grouped by initial staging and recurrent staging (according to MRI).

RESULTS

In the III-IVA and rIII-IVA NPC patients, with PET/CT exhibited significantly higher OS rates in the univariate analysis (P = 0.045; P = 0.009; respectively). Multivariate analysis revealed that with PET/CT was an independent predictor of OS in the rIII-IVA cohort (hazard ratio [HR] = 0.476; 95% confidence interval [CI]: 0.267 to 0.847; P = 0.012). In the rIII-IVA NPC, patients receiving PET/CT sacns before salvage surgery had a better prognosis compared with MRI alone (P = 0.036). The recurrent stage (based on PET/CT) was an independent predictor of OS. (r0-II versus [vs]. rIII-IVA; HR = 0.376; 95% CI: 0.150 to 0.938; P = 0.036).

CONCLUSION

The present study showed that with PET/CT could improve overall survival for rIII-IVA NPC patients. PET/CT appears to be an effective method for assessing rTNM staging.

Pretreatment multiparametric MRI radiomics-integrated clinical hematological biomarkers can predict early rapid metastasis in patients with nasopharyngeal carcinoma

BACKGROUND

To establish and validate a predictive model combining pretreatment multiparametric MRI-based radiomic signatures and clinical characteristics for the risk evaluation of early rapid metastasis in nasopharyngeal carcinoma (NPC) patients.

METHODS

The cutoff time was used to randomly assign 219 consecutive patients who underwent chemoradiation treatment to the training group (n = 154) or the validation group (n = 65). Pretreatment multiparametric magnetic resonance (MR) images of individuals with NPC were employed to extract 428 radiomic features. LASSO regression analysis was used to select radiomic features related to early rapid metastasis and develop the Rad-score. Blood indicators were collected within 1 week of pretreatment. To identify independent risk variables for early rapid metastasis, univariate and multivariate logistic regression analyses were employed. Finally, multivariate logistic regression analysis was applied to construct a radiomics and clinical prediction nomogram that integrated radiomic features and clinical and blood inflammatory predictors.

RESULTS

The NLR, T classification and N classification were found to be independent risk indicators for early rapid metastasis by multivariate logistic regression analysis. Twelve features associated with early rapid metastasis were selected by LASSO regression analysis, and the Rad-score was calculated. The AUC of the Rad-score was 0.773. Finally, we constructed and validated a prediction model in combination with the NLR, T classification, N classification and Rad-score. The area under the curve (AUC) was 0.936 (95% confidence interval (95% CI): 0.901-0.971), and in the validation cohort, the AUC was 0.796 (95% CI: 0.686-0.905).

CONCLUSIONS

A predictive model that integrates the NLR, T classification, N classification and MR-based radiomics for distinguishing early rapid metastasis may serve as a clinical risk stratification tool for effectively guiding individual management.

WET-UNet: Wavelet integrated efficient transformer networks for nasopharyngeal carcinoma tumor segmentation

Nasopharyngeal carcinoma is a malignant tumor that occurs in the epithelium and mucosal glands of the nasopharynx, and its pathological type is mostly poorly differentiated squamous cell carcinoma. Since the nasopharynx is located deep in the head and neck, early diagnosis and timely treatment are critical to patient survival. However, nasopharyngeal carcinoma tumors are small in size and vary widely in shape, and it is also a challenge for experienced doctors to delineate tumor contours. In addition, due to the special location of nasopharyngeal carcinoma, complex treatments such as radiotherapy or surgical resection are often required, so accurate pathological diagnosis is also very important for the selection of treatment options. However, the current deep learning segmentation model faces the problems of inaccurate segmentation and unstable segmentation process, which are mainly limited by the accuracy of data sets, fuzzy boundaries, and complex lines. In order to solve these two challenges, this article proposes a hybrid model WET-UNet based on the UNet network as a powerful alternative for nasopharyngeal cancer image segmentation. On the one hand, wavelet transform is integrated into UNet to enhance the lesion boundary information by using low-frequency components to adjust the encoder at low frequencies and optimize the subsequent computational process of the Transformer to improve the accuracy and robustness of image segmentation. On the other hand, the attention mechanism retains the most valuable pixels in the image for us, captures the remote dependencies, and enables the network to learn more representative features to improve the recognition ability of the model. Comparative experiments show that our network structure outperforms other models for nasopharyngeal cancer image segmentation, and we demonstrate the effectiveness of adding two modules to help tumor segmentation. The total data set of this article is 5000, and the ratio of training and verification is 8:2. In the experiment, accuracy = 85.2% and precision = 84.9% can show that our proposed model has good performance in nasopharyngeal cancer image segmentation.

Cross-site prognosis prediction for nasopharyngeal carcinoma from incomplete multi-modal data

Accurate prognosis prediction for nasopharyngeal carcinoma based on magnetic resonance (MR) images assists in the guidance of treatment intensity, thus reducing the risk of recurrence and death. To reduce repeated labor and sufficiently explore domain knowledge, aggregating labeled/annotated data from external sites enables us to train an intelligent model for a clinical site with unlabeled data. However, this task suffers from the challenges of incomplete multi-modal examination data fusion and image data heterogeneity among sites. This paper proposes a cross-site survival analysis method for prognosis prediction of nasopharyngeal carcinoma from domain adaptation viewpoint. Utilizing a Cox model as the basic framework, our method equips it with a cross-attention based multi-modal fusion regularization. This regularization model effectively fuses the multi-modal information from multi-parametric MR images and clinical features onto a domain-adaptive space, despite the absence of some modalities. To enhance the feature discrimination, we also extend the contrastive learning technique to censored data cases. Compared with the conventional approaches which directly deploy a trained survival model in a new site, our method achieves superior prognosis prediction performance in cross-site validation experiments. These results highlight the key role of cross-site adaptability of our method and support its value in clinical practice.

Design, Preclinical Evaluation, and Clinical Translation of 68Ga-FAPI-LM3, a Heterobivalent Molecule for PET Imaging of Nasopharyngeal Carcinoma

Extensive research has been conducted on radiolabeled fibroblast activation protein (FAP) inhibitors (FAPIs) and p-Cl-Phe-cyclo(d-Cys-Tyr-d-4-amino-Phe(carbamoyl)-Lys-Thr-Cys)d-Tyr-NH2 (LM3) peptides for imaging of FAP and somatostatin receptor 2 (SSTR2)-positive tumors. In this study, we designed and synthesized a FAPI-LM3 heterobivalent molecule radiolabeled with 68Ga and evaluated its effectiveness in both tumor xenografts and patients with nasopharyngeal carcinoma (NPC). Methods: The synthesis of FAPI-LM3 was based on the structures of FAPI-46 and LM3. After radiolabeling with 68Ga, its dual-receptor-binding affinity was evaluated in vitro and in vivo. Preclinical studies, including small-animal PET and biodistribution evaluation, were conducted on HT-1080-FAP and HT-1080-SSTR2 tumor xenografts. The feasibility of 68Ga-FAPI-LM3 PET/CT in a clinical setting was evaluated in patients with NPC, and the results were compared with those of 18F-FDG. Results: 68Ga-FAPI-LM3 showed high affinity for both FAP and SSTR2. The tumor uptake of 68Ga-FAPI-LM3 was significantly higher than that of 68Ga-FAPI-46 and 68Ga-DOTA-LM3 in HT-1080-FAP-plus-HT-1080-SSTR2 tumor xenografts. In a clinical study involving 6 NPC patients, 68Ga-FAPI-LM3 PET/CT showed significantly higher uptake than did 18F-FDG in primary and metastatic lesions, leading to enhanced lesion detectability and tumor delineation. Conclusion: 68Ga-FAPI-LM3 exhibited FAPI and SSTR2 dual-receptor-targeting properties both in vitro and in vivo, resulting in improved tumor uptake and retention compared with that observed with monomeric 68Ga-FAPI and 68Ga-DOTA-LM3. This study highlights the clinical feasibility of 68Ga-FAPI-LM3 PET/CT for NPC imaging.

Radiologic extranodal extension for nodal staging in nasopharyngeal carcinoma

PURPOSE

Extranodal extension (ENE) has the potential to add value to the current nodal staging system (N8th) for predicting outcome in nasopharyngeal carcinoma (NPC). This study aimed to incorporate ENE, as well as cervical nodal necrosis (CNN) to the current stage N3 and evaluated their impact on outcome prediction. The findings were validated on an external cohort.

METHODS & MATERIALS

Pre-treatment MRI of 750 patients from the internal cohort were retrospectively reviewed. Predictive values of six modified nodal staging systems that incorporated four patterns of ENE and two patterns of CNN to the current stage N3 for disease-free survival (DFS) were compared with that of N8th using multivariate cox-regression and concordance statistics in the internal cohort. Performance of stage N3 for predicting disease recurrence was calculated. An external cohort of 179 patients was used to validate the findings.

RESULTS

Incorporation of advanced ENE, which infiltrates into adjacent muscle/skin/salivary glands outperformed the other five modifications for predicting outcomes (p < 0.01) and achieved a significantly higher c-index for 5-year DFS (0.69 vs 0.72) (p < 0.01) when compared with that of N8th staging system. By adding advanced ENE to the current N3 increased the sensitivity for predicting disease recurrence from 22.4 % to 47.1 %. The finding was validated in the external cohort (5-year DFS 0.65 vs. 0.72, p < 0.01; sensitivity of stage N3 increased from 14.0 % to 41.9 % for disease recurrence).

CONCLUSION

Results from two centre cohorts confirmed that the radiological advanced ENE should be considered as a criterion for stage N3 disease in NPC.

CT-based peritumoral radiomics nomogram on prediction of response and survival to induction chemotherapy in locoregionally advanced nasopharyngeal carcinoma

PURPOSE

The study aims to harness the value of radiomics models combining intratumoral and peritumoral features obtained from pretreatment CT to predict treatment response as well as the survival of LA-NPC(locoregionally advanced nasopharyngeal carcinoma) patients receiving multiple types of induction chemotherapies, including immunotherapy and targeted therapy.

METHODS

276 LA-NPC patients (221 in the training and 55 in the testing cohort) were retrospectively enrolled. Various statistical analyses and feature selection techniques were applied to identify the most relevant radiomics features. Multiple machine learning models were trained and compared to build signatures for the intratumoral and each peritumoral region, along with a clinical signature. The performance of each model was evaluated using different metrics. Subsequently, a nomogram model was constructed by combining the best-performing radiomics and clinical models.

RESULTS

In the testing cohort, the nomogram model exhibited an AUC of 0.816, outperforming the other models. The nomogram model's calibration curve showed good agreement between predicted and observed outcomes in both the training and testing sets. When predicting survival, the model's concordance index (C-index) was 0.888 in the training cohort and 0.899 in the testing cohort, indicating its robust predictive ability.

CONCLUSION

In conclusion, the combined nomogram model, incorporating radiomics and clinical features, outperformed other models in predicting treatment response and survival outcomes for LA-NPC patients receiving induction chemotherapies. These findings highlight the potential clinical utility of the model, suggesting its value in individualized treatment planning and decision-making.

Radiomics and Deep Learning in Nasopharyngeal Carcinoma: A Review

Nasopharyngeal carcinoma is a common head and neck malignancy with distinct clinical management compared to other types of cancer. Precision risk stratification and tailored therapeutic interventions are crucial to improving the survival outcomes. Artificial intelligence, including radiomics and deep learning, has exhibited considerable efficacy in various clinical tasks for nasopharyngeal carcinoma. These techniques leverage medical images and other clinical data to optimize clinical workflow and ultimately benefit patients. In this review, we provide an overview of the technical aspects and basic workflow of radiomics and deep learning in medical image analysis. We then conduct a detailed review of their applications to seven typical tasks in the clinical diagnosis and treatment of nasopharyngeal carcinoma, covering various aspects of image synthesis, lesion segmentation, diagnosis, and prognosis. The innovation and application effects of cutting-edge research are summarized. Recognizing the heterogeneity of the research field and the existing gap between research and clinical translation, potential avenues for improvement are discussed. We propose that these issues can be gradually addressed by establishing standardized large datasets, exploring the biological characteristics of features, and technological upgrades.

FDG PET/CT Demonstrated Unilateral Striatum Hypometabolism in a Case of Advanced Nasopharyngeal Cancer

ABSTRACT

A 79-year-old man with nasopharyngeal cancer (NPC) presented with diplopia symptom and a history of diabetes mellitus was referred for an FDG PET/CT scan to determine the pretreatment staging. The FDG PET/CT scan revealed NPC with skull base invasion and decreased FDG uptake at the left striatum. A review of his clinical history and a brain MRI conducted 5 months ago confirmed a previous diagnosis of left hyperglycemic hemichorea. In this NPC patient with inadequate blood sugar control, unilateral striatum hypometabolism may persist for up to 5 months after the initial clinical symptoms.

Synthetic MRI quantitative parameters in discriminating stage T1 nasopharyngeal carcinoma and benign hyperplasia: Combination with morphological features

PURPOSE

To investigate the feasibility of synthetic MRI (syMRI) quantitative parameters and its combination with morphological features in discriminating stage T1 nasopharyngeal carcinoma (T1-NPC) and benign hyperplasia (BH).

MATERIAL AND METHODS

Eighty-eight patients with nasopharyngeal lesions (T1-NPC, n = 54; BH, n = 34) were retrospectively enrolled between October 2020 and May 2022. The syMRI quantitative parameters of nasopharyngeal lesions (T1, T2, PD, T1SD, T2SD, PDSD) and longus capitis (T1, T2, PD) were measured, and T1ratio, T2ratio and PDratio were calculated (lesion/longus capitis). The morphological features (lesion pattern, retention cyst, serrated protrusion, middle ear effusion, tumor volume, and retropharyngeal lymph node) were compared. Statistical analyses were performed using the independent sample t test, Chi-square test, logistic regression analysis, receiver operating characteristic curve (ROC), and DeLong test.

RESULTS

The T1, T2, PD, T1SD, T1ratio, and T2ratio values of T1-NPC were significantly lower than those of BH. The morphological features (lesion pattern, retention cyst, retropharyngeal lymph node) were significant difference between these two entities. T2 value has the highest AUC in all syMRI quantitative parameters, followed by T1, T1ratio, PD, T2ratio and T1SD. Combined syMRI quantitative parameters (T2, PD, T1ratio) can further improve the diagnosis efficiency. Combined syMRI parameters and morphological feature (T2, PD, lesion pattern, retropharyngeal lymph node) has the excellent diagnostic efficiency, with AUC, sensitivity, specificity, and accuracy of 0.979, 96.30%, 97.06%, 96.77%.

CONCLUSIONS

Synthetic MRI was helpful in distinguishing T1-NPC from BH, and combined syMRI quantitative parameters and morphological features has the optimal diagnostic performance.

Enhanced MRI Radiomics Based Model for Predicting Recurrence or Metastasis of Nasopharyngeal Cancer (NC) Undergoing Concurrent Chemoradiotherapy: A Retrospective Study

Nasopharyngeal Carcinoma (NC) refers to the malignant tumor that occurs at the top and side walls of the nasopharyngeal cavity. The NC incidence rate always dominates the first among the malignant tumors of the ear, nose and throat, and mainly occurs in Asia. NC cases are mainly concentrated in southern provinces in China, with about 4 million existing NC. With the pollution of environment and pickled diet, and the increase of life pressure, the domestic NC incidence rate has reached 4.5-6.5/100000 and is increasing year by year. It was reported that the known main causes of NC include hereditary factor, genetic mutations, and EB virus infection, common clinical symptoms of NC include nasal congestion, bloody mucus, etc. About 90% of NC is highly sensitive to radiotherapy which is regard as the preferred treatment method; However, for NC with lower differentiation, larger volume, and recurrence after treatment, surgical resection and local protons and heavy ions therapy are also indispensable means. According to reports, the subtle heterogeneity and diversity exists in some NC, with about 80% of NC undergone radiotherapy and about 25% experienced recurrence and death within five years after radiotherapy in China. Therefore, screening the NC population with suspected recurrence after concurrent chemoradiotherapy may improve survival rates in current clinical decision-making.

Pretreatment dual-energy CT for predicting early response to induction chemotherapy and survival in nasopharyngeal carcinoma

OBJECTIVES

To evaluate the predictive performance of pretreatment dual-energy CT (DECT) for early response to induction chemotherapy and survival in nasopharyngeal carcinoma (NPC).

METHODS

In this retrospective study, 56 NPC patients who underwent pretreatment DECT scans with posttreatment follow-up were enrolled. The DECT-derived normalised iodine concentration (nIC), effective atomic number (Zeff), 40-180 keV (20 keV interval), and Mix-0.3 value of the tumour lesions were measured to predict the early response to induction chemotherapy and survival in nasopharyngeal carcinoma. The Mann‒Whitney U test, ROC analysis, Kaplan‒Meier method with log-rank test, and Cox proportional hazards model were performed to evaluate the predictive performance of DECT parameters, respectively.

RESULTS

Among all DECT-derived parameters, ROC analysis showed the predictive performances of nIC and Zeff values for early objective response to induction chemotherapy (AUCs of 0.803 and 0.826), locoregional failure-free survival (AUCs of 0.786 and 0.767), progression-free survival (AUCs of 0.856 and 0.731) and overall survival (AUCs of 0.765 and 0.799) in NPC patients, respectively (all p < 0.05). Moreover, multivariate analysis showed that a high nIC value was an independent predictor of poor survival in NPC. In addition, survival analysis indicated that NPC patients with higher nIC values in primary tumours tend to have lower 5-year locoregional failure-free survival, progression-free survival and overall survival rates than those with lower nIC values.

CONCLUSIONS

DECT-derived nIC and Zeff values can predict early response to induction chemotherapy and survival in NPC; in particular, a high nIC value is an independent predictive factor of poor survival in NPC.

CLINICAL RELEVANCE STATEMENT

Preoperative dual-energy computed tomography may provide predictive value for early response and survival outcomes in patients with nasopharyngeal carcinoma, and facilitate their clinical management.

KEY POINTS

• Pretreatment dual-energy computed tomography helps to predict early response to therapy and survival in NPC. • NIC and Zeff values derived from dual-energy computed tomography can predict early objective response to induction chemotherapy and survival in NPC. • A high nIC value is an independent predictive factor of poor survival in NPC.

Prognosis Forecast of Re-Irradiation for Recurrent Nasopharyngeal Carcinoma Based on Deep Learning Multi-Modal Information Fusion

Radiation therapy is the primary treatment for recurrent nasopharyngeal carcinoma. However, it may induce necrosis of the nasopharynx, leading to severe complications such as bleeding and headache. Therefore, forecasting necrosis of the nasopharynx and initiating timely clinical intervention has important implications for reducing complications caused by re-irradiation. This research informs clinical decision-making by making predictions on re-irradiation of recurrent nasopharyngeal carcinoma using deep learning multi-modal information fusion between multi-sequence nuclear magnetic resonance imaging and plan dose. Specifically, we assume that the hidden variables of model data can be divided into two categories: task-consistency and task-inconsistency. The task-consistency variables are characteristic variables contributing to target tasks, while the task-inconsistency variables are not apparently helpful. These modal characteristics are adaptively fused when the relevant tasks are expressed through the construction of supervised classification loss and self-supervised reconstruction loss. The cooperation of supervised classification loss and self-supervised reconstruction loss simultaneously reserves the information of characteristic space and controls potential interference simultaneously. Finally, multi-modal fusion effectively fuses information through an adaptive linking module. We evaluated this method on a multi-center dataset. and found the prediction based on multi-modal features fusion outperformed predictions based on single-modal, partial modal fusion or traditional machine learning methods.

A Rulefit-based prognostic analysis using structured MRI report to select potential beneficiaries from induction chemotherapy in advanced nasopharyngeal carcinoma: A dual-centre study

BACKGROUND AND PURPOSE

Structured MRI report facilitate prognostic prediction for nasopharyngeal carcinoma (NPC). However, the intrinsic association among structured variables is not fully utilised. This study aimed to investigate the performance of a Rulefit-based model in feature integration behind structured MRI report and prognostic prediction in advanced NPC.

MATERIALS AND METHODS

We retrospectively enrolled 1207 patients diagnosed with non-metastatic advanced NPC from two centres, and divided into training (N = 544), internal testing (N = 367), and external testing (N = 296) cohorts. Machine learning algorithms including multivariate analysis, deep learning, Lasso, and Rulefit were used to establish corresponding prognostic models. The concordance indices (C- indices) of three clinical and six combined models with different algorithms for overall survival (OS) prediction were compared. Survival benefits of induction chemotherapy (IC) were calculated among risk groups stratified by different models. A website was established for individualised survival visualisation.

RESULTS

Incorporating structured variables into Stage model significantly improved the prognostic prediction performance. Six prognostic rules with structured variables were identified by Rulefit. OS prediction of Rules model was comparable to Lasso model in internal testing cohort (C-index: 0.720 vs. 0.713, P = 0.100) and achieved the highest C-index of 0.711 in external testing cohort, indicating better generalisability. The Rules model stratified patients into risk groups with significant 5-year OS differences in each cohort, and revealed significant survival benefits from additional IC in high-risk group.

CONCLUSION

The Rulefit-based Rules model, with the revelation of intrinsic associations behind structured variables, is promising in risk stratification and guiding individualised IC treatment for advanced NPC.

Application of narrow band imaging and Lugol's iodine staining in screening for nasopharyngeal carcinoma

BACKGROUND

To investigate the diagnostic value of conventional white light endoscopy (WLE), narrow band imaging (NBI) endoscopy, and Lugol's iodine staining under WLE (endoscopic iodine staining) in the screening and early diagnosis of nasopharyngeal carcinoma.

METHODS

Patients with nasopharyngeal lesions requiring biopsy attending the Department of Otolaryngology Head and Neck Surgery in our hospital between January 2021 and April 2023 were included in this study. Before biopsy, all subjects underwent conventional WLE, NBI endoscopy, and endoscopic iodine staining. On WLE, according to nasopharyngeal lesion morphology and color, patients were diagnosed with nasopharyngeal carcinoma ( +) or chronic hyperplastic nasopharyngitis (-). On NBI endoscopy, according to nasopharyngeal lesion vascular morphology, patients with type V manifestations (nasopharyngeal carcinoma) were categorized as NBI ( +) and patients with type I-IV manifestations (chronic hyperplastic nasopharyngitis) were categorized as NBI (-). Endoscopic iodine staining (1.6% Lugol's iodine solution) was positive ( +) if the mucosal surface was brown with no white patches, or negative (-) if there was no or light brown staining of the mucosal surface. Patients were divided into 2 groups based on histopathological diagnosis: nasopharyngeal carcinoma or chronic hyperplastic nasopharyngitis. Endoscopic diagnoses were compared with histopathological findings. The diagnostic performance of WLE, NBI endoscopy and endoscopic iodine staining for nasopharyngeal carcinoma were determined.

RESULTS

This study included 159 patients. On histopathology, 29 patients were diagnosed with nasopharyngeal carcinoma, and 130 patients were diagnosed with chronic hyperplastic nasopharyngitis. There were no significant differences in the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the receiver operating characteristic (ROC) curve (AUC) of conventional WLE, NBI endoscopy or endoscopic iodine staining for differentiating nasopharyngeal carcinoma and chronic hyperplastic nasopharyngitis. The diagnostic performance of the combination of conventional WLE, NBI endoscopy and endoscopic iodine staining was significantly improved compared to any procedure alone.

CONCLUSIONS

Conventional WLE, NBI endoscopy or endoscopic iodine staining had good diagnostic performance for differentiating nasopharyngeal carcinoma and chronic hyperplastic nasopharyngitis. In particular, NBI endoscopy and endoscopic iodine staining alone or combined had clinical utility for identifying patients with nasopharyngeal lesions that are eligible for a watch-and-wait strategy.

Comprehensive evaluation of similarity between synthetic and real CT images for nasopharyngeal carcinoma

BACKGROUND

Although magnetic resonance imaging (MRI)-to-computed tomography (CT) synthesis studies based on deep learning have significantly progressed, the similarity between synthetic CT (sCT) and real CT (rCT) has only been evaluated in image quality metrics (IQMs). To evaluate the similarity between synthetic CT (sCT) and real CT (rCT) comprehensively, we comprehensively evaluated IQMs and radiomic features for the first time.

METHODS

This study enrolled 127 patients with nasopharyngeal carcinoma who underwent CT and MRI scans. Supervised-learning (Unet) and unsupervised-learning (CycleGAN) methods were applied to build MRI-to-CT synthesis models. The regions of interest (ROIs) included nasopharynx gross tumor volume (GTVnx), brainstem, parotid glands, and temporal lobes. The peak signal-to-noise ratio (PSNR), mean absolute error (MAE), root mean square error (RMSE), and structural similarity (SSIM) were used to evaluate image quality. Additionally, 837 radiomic features were extracted for each ROI, and the correlation was evaluated using the concordance correlation coefficient (CCC).

RESULTS

The MAE, RMSE, SSIM, and PSNR of the body were 91.99, 187.12, 0.97, and 51.15 for Unet and 108.30, 211.63, 0.96, and 49.84 for CycleGAN. For the metrics, Unet was superior to CycleGAN (P < 0.05). For the radiomic features, the percentage of four levels (i.e., excellent, good, moderate, and poor, respectively) were as follows: GTVnx, 8.5%, 14.6%, 26.5%, and 50.4% for Unet and 12.3%, 25%, 38.4%, and 24.4% for CycleGAN; other ROIs, 5.44% ± 3.27%, 5.56% ± 2.92%, 21.38% ± 6.91%, and 67.58% ± 8.96% for Unet and 5.16% ± 1.69%, 3.5% ± 1.52%, 12.68% ± 7.51%, and 78.62% ± 8.57% for CycleGAN.

CONCLUSIONS

Unet-sCT was superior to CycleGAN-sCT for the IQMs. However, neither exhibited absolute superiority in radiomic features, and both were far less similar to rCT. Therefore, further work is required to improve the radiomic similarity for MRI-to-CT synthesis.

TRIAL REGISTRATION

This study was a retrospective study, so it was free from registration.

Multi-task deep learning-based radiomic nomogram for prognostic prediction in locoregionally advanced nasopharyngeal carcinoma

PURPOSE

Prognostic prediction is crucial to guide individual treatment for locoregionally advanced nasopharyngeal carcinoma (LA-NPC) patients. Recently, multi-task deep learning was explored for joint prognostic prediction and tumor segmentation in various cancers, resulting in promising performance. This study aims to evaluate the clinical value of multi-task deep learning for prognostic prediction in LA-NPC patients.

METHODS

A total of 886 LA-NPC patients acquired from two medical centers were enrolled including clinical data, [18F]FDG PET/CT images, and follow-up of progression-free survival (PFS). We adopted a deep multi-task survival model (DeepMTS) to jointly perform prognostic prediction (DeepMTS-Score) and tumor segmentation from FDG-PET/CT images. The DeepMTS-derived segmentation masks were leveraged to extract handcrafted radiomics features, which were also used for prognostic prediction (AutoRadio-Score). Finally, we developed a multi-task deep learning-based radiomic (MTDLR) nomogram by integrating DeepMTS-Score, AutoRadio-Score, and clinical data. Harrell's concordance indices (C-index) and time-independent receiver operating characteristic (ROC) analysis were used to evaluate the discriminative ability of the proposed MTDLR nomogram. For patient stratification, the PFS rates of high- and low-risk patients were calculated using Kaplan-Meier method and compared with the observed PFS probability.

RESULTS

Our MTDLR nomogram achieved C-index of 0.818 (95% confidence interval (CI): 0.785-0.851), 0.752 (95% CI: 0.638-0.865), and 0.717 (95% CI: 0.641-0.793) and area under curve (AUC) of 0.859 (95% CI: 0.822-0.895), 0.769 (95% CI: 0.642-0.896), and 0.730 (95% CI: 0.634-0.826) in the training, internal validation, and external validation cohorts, which showed a statistically significant improvement over conventional radiomic nomograms. Our nomogram also divided patients into significantly different high- and low-risk groups.

CONCLUSION

Our study demonstrated that MTDLR nomogram can perform reliable and accurate prognostic prediction in LA-NPC patients, and also enabled better patient stratification, which could facilitate personalized treatment planning.

AI-assisted compressed sensing and parallel imaging sequences for MRI of patients with nasopharyngeal carcinoma: comparison of their capabilities in terms of examination time and image quality

OBJECTIVE

To compare examination time and image quality between artificial intelligence (AI)-assisted compressed sensing (ACS) technique and parallel imaging (PI) technique in MRI of patients with nasopharyngeal carcinoma (NPC).

METHODS

Sixty-six patients with pathologically confirmed NPC underwent nasopharynx and neck examination using a 3.0-T MRI system. Transverse T2-weighted fast spin-echo (FSE) sequence, transverse T1-weighted FSE sequence, post-contrast transverse T1-weighted FSE sequence, and post-contrast coronal T1-weighted FSE were obtained by both ACS and PI techniques, respectively. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and duration of scanning of both sets of images analyzed by ACS and PI techniques were compared. The images from the ACS and PI techniques were scored for lesion detection, margin sharpness of lesions, artifacts, and overall image quality using the 5-point Likert scale.

RESULTS

The examination time with ACS technique was significantly shorter than that with PI technique (p < 0.0001). The comparison of SNR and CNR showed that ACS technique was significantly superior with PI technique (p < 0.005). Qualitative image analysis showed that the scores of lesion detection, margin sharpness of lesions, artifacts, and overall image quality were higher in the ACS sequences than those in the PI sequences (p < 0.0001). Inter-observer agreement was evaluated for all qualitative indicators for each method, in which the results showed satisfactory-to-excellent agreement (p < 0.0001).

CONCLUSION

Compared with the PI technique, the ACS technique for MR examination of NPC can not only shorten scanning time but also improve image quality.

CLINICAL RELEVANCE STATEMENT

The artificial intelligence (AI)-assisted compressed sensing (ACS) technique shortens examination time for patients with nasopharyngeal carcinoma, while improving the image quality and examination success rate, which will benefit more patients.

KEY POINTS

• Compared with the parallel imaging (PI) technique, the artificial intelligence (AI)-assisted compressed sensing (ACS) technique not only reduced examination time, but also improved image quality. • Artificial intelligence (AI)-assisted compressed sensing (ACS) pulls the state-of-the-art deep learning technique into the reconstruction procedure and helps find an optimal balance of imaging speed and image quality.

Head and neck MRI-based T stage and [18F]FDG PET/CT-based N/M stage improved prognostic stratification in primary nasopharyngeal carcinoma

OBJECTIVES

To evaluate whether MRI-based T stage (TMRI), [18F]FDG PET/CT-based N (NPET/CT), and M stage (MPET/CT) are superior in NPC patients' prognostic stratification based on long-term survival evidences, and whether TNM staging method involving TMRI + NPET/CT + MPET/CT could improve NPC patients' prognostic stratification.

METHODS

From April 2007 to December 2013, 1013 consecutive untreated NPC patients with complete imaging data were enrolled. All patients' initial stages were repeated based on (1) the NCCN guideline recommended "TMRI + NMRI + MPET/CT" ("MMP") staging method; (2) the traditional "TMRI + NMRI + Mconventional work-up (CWU)" ("MMC") staging method; (3) the single-step "TPET/CT + NPET/CT + MPET/CT" ("PPP") staging method; or (4) the "TMRI + NPET/CT + MPET/CT" ("MPP") staging method recommended in present research. Survival curve, ROC curve, and net reclassification improvement (NRI) analysis were used to evaluate the prognosis predicting ability of different staging methods.

RESULTS

[18F]FDG PET/CT performed worse on T stage (NRI =  - 0.174, p < 0.001) but better on N (NRI = 0.135, p = 0.004) and M stage (NRI = 0.126, p = 0.001). The patients whose N stage upgraded by [18F]FDG PET/CT had worse survival (p = 0.011). The "TMRI + NPET/CT + MPET/CT" ("MPP") method performed better on survival prediction when compared with "MMP" (NRI = 0.079, p = 0.007), "MMC" (NRI = 0.190, p < 0.001), or "PPP" method (NRI = 0.107, p < 0.001). The "TMRI + NPET/CT + MPET/CT" ("MPP") method could reclassify patients' TNM stage to a more appropriate stage. The improvement is significant in patients with more than 2.5-years follow-up according to the time-dependent NRI values.

CONCLUSIONS

The MRI is superior to [18F]FDG PET/CT in T stage, and [18F]FDG PET/CT is superior to CWU in N/M stage. The "TMRI + NPET/CT + MPET/CT" ("MPP") staging method could significantly improve NPC patients' long-term prognostic stratification.

CLINICAL RELEVANCE STATEMENT

The present research provided long-term follow-up evidence for benefits of MRI and [18F]FDG PET/CT in TNM staging for nasopharyngeal carcinoma, and proposes a new imaging procedure for TNM staging incorporating MRI-based T stage and [18F]FDG PET/CT-based N and M stage, which significantly improves long-term prognostic stratification for patients with NPC.

KEY POINTS

• The long-term follow-up evidence of a large-scale cohort was provided to evaluate the advantages of MRI, [18F]FDG PET/CT, and CWU in the TNM staging of nasopharyngeal carcinoma. • A new imaging procedure for TNM stage of nasopharyngeal carcinoma was proposed.

Deep learning-based recurrence detector on magnetic resonance scans in nasopharyngeal carcinoma: A multicenter study

OBJECTIVES

Accuracy in the detection of recurrent nasopharyngeal carcinoma (NPC) on follow-up magnetic resonance (MR) scans needs to be improved.

MATERIAL AND METHODS

A total of 5 035 follow-up MR scans from 5 035 survivors with treated NPC between April 2007 and July 2020 were retrospectively collected from three cancer centers for developing and evaluating the deep learning (DL) model MODERN (MR-based Deep learning model for dEtecting Recurrent Nasopharyngeal carcinoma). In a reader study with 220 scans, the accuracy of two radiologists in detecting recurrence on scans with vs without MODERN was evaluated. The performance was measured using the area under the receiver operating characteristic curve (ROC-AUC) and accuracy with a 95% confidence interval (CI).

RESULTS

MODERN exhibited sound performance in the validation cohort (internal: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 1: ROC-AUC, 0.88, 95% CI, 0.86-0.90; external 2: ROC-AUC, 0.85, 95% CI, 0.82-0.88). In a reader study, MODERN alone achieved reliable accuracy compared to that of radiologists (MODERN: 84.1%, 95% CI, 79.3%-88.9%; competent: 80.9%, 95% CI, 75.7%-86.1%, P < 0.001; expert: 85.9%, 95% CI, 81.3%-90.5%, P < 0.001). The accuracy of radiologists was boosted by the MODERN score (competent with MODERN score: 84.6%, 95% CI, 79.8%-89.3%, P < 0.001; expert with MODERN score: 87.7%, 95% CI, 83.4%-92.1%, P < 0.001).

CONCLUSION

We developed a DL model for recurrence detection with reliable performance. Computer-human collaboration has the potential to refine the workflow in interpreting surveillant MR scans among patients with treated NPC.

Prognostic value of primary tumor and lymph node volumetric metabolic parameters at pre-treatment F-18 FDG PET/CT in nasopharyngeal carcinoma

BACKGROUND

The aim of this study was to evaluate the prognostic significance of volumetric metabolic parameters of pre-treatment PET/CT along with clinical characteristics in patients with non-metastatic nasopharyngeal carcinoma.

MATERIAL AND METHODS

Seventy-nine patients with nasopharyngeal carcinoma underwent F18- FDG PET/CT for pretreatment evaluation and included in this study. The patient features (patient age, tumor histopathology, T and N stage, size of primary tumor and the largest cervical lymph node) and PET parameters were analyzed: maximum, mean and peak standardized uptake values (SUVmax, SUVmean, SUVpeak), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) for primary tumor and largest cervical lymph node. After treatment, patients were evaluated for disease progression and mortality. Survival analysis for progression-free survival (PFS) and over-all survival (OS) was performed with Kaplan-Meier method using PET findings and clinical characteristics.

RESULTS

The median follow-up duration was 29.7 months (range 3-125 months). Among clinical characteristics, no parameters had significance association for PFS. Primary tumor-MTV and cervical lymph node-MTV were independent prognostic factors for PFS (p = 0.025 and p = 0.004, respectively).Patients with primary tumor-MTV >19.4 and patients with lymph node-MTV>3.4 had shorter PFS. For OS, age and the size of the lymph node were independent prognostic factor (p = 0.031 and p = 0.029).Patients with age over 54 years and patients with lymph node size >1 cm were associated with decreased OS.

CONCLUSION

Primary tumor-MTV and lymph node-MTV on pre-treatment PET/CT are significant prognostic factors for long-term PFS in non-metastatic nasopharyngeal carcinoma. We consider that measuring MTV as volume-based metabolic parameter on pretreatment PET/CT may contribute decision of treatment intensity and individualized risk stratification and may improve long-term PFS. Additionally, age and the size of lymph node are independent prognostic factors for mortality.

Radiomics-clinical nomogram based on pretreatment 18F-FDG PET-CT radiomics features for individualized prediction of local failure in nasopharyngeal carcinoma

To explore the prognostic significance of PET/CT-based radiomics signatures and clinical features for local recurrence-free survival (LRFS) in nasopharyngeal carcinoma (NPC). We retrospectively reviewed 726 patients who underwent pretreatment PET/CT at our center. Least absolute shrinkage and selection operator (LASSO) regression and the Cox proportional hazards model were applied to construct Rad-score, which represented the radiomics features of PET-CT images. Univariate and multivariate analyses were used to establish a nomogram model. The concordance index (C-index) and calibration curve were used to evaluate the predictive accuracy and discriminative ability. Receiver operating characteristic analysis was performed to stratify the local recurrence risk of patients. The nomogram was validated by evaluating its discrimination ability and calibration in the validation cohort. A total of eight features were selected to construct Rad-score. A radiomics-clinical nomogram was built after the selection of univariate and multivariable Cox regression analyses, including the Rad-score and maximum standardized uptake value (SUVmax). The C-index was 0.71 (0.67-0.74) in the training cohort and 0.70 (0.64-0.76) in the validation cohort. The nomogram also performed far better than the 8th T-staging system with an area under the receiver operating characteristic curve (AUC) of 0.75 vs. 0.60 for 2 years and 0.71 vs. 0.60 for 3 years. The calibration curves show that the nomogram indicated accurate predictions. Decision curve analysis (DCA) revealed significantly better net benefits with this nomogram model. The log-rank test results revealed a distinct difference in prognosis between the two risk groups. The PET/CT-based radiomics nomogram showed good performance in predicting LRFS and showed potential to identify patients at high-risk of developing NPC.

Adjuvant chemotherapy or no adjuvant chemotherapy? A prediction model for the risk stratification of recurrence or metastasis of nasopharyngeal carcinoma combining MRI radiomics with clinical factors

BACKGROUND

Dose adjuvant chemotherapy (AC) should be offered in nasopharyngeal carcinoma (NPC) patients? Different guidelines provided the different recommendations.

METHODS

In this retrospective study, a total of 140 patients were enrolled and followed for 3 years, with 24 clinical features being collected. The imaging features on the enhanced-MRI sequence were extracted by using PyRadiomics platform. The pearson correlation coefficient and the random forest was used to filter the features associated with recurrence or metastasis. A clinical-radiomics model (CRM) was constructed by the Cox multivariable analysis in training cohort, and was validated in validation cohort. All patients were divided into high- and low-risk groups through the median Rad-score of the model. The Kaplan-Meier survival curves were used to compare the 3-year recurrence or metastasis free rate (RMFR) of patients with or without AC in high- and low-groups.

RESULTS

In total, 960 imaging features were extracted. A CRM was constructed from nine features (seven imaging features and two clinical factors). In the training cohort, the area under curve (AUC) of CRM for 3-year RMFR was 0.872 (P <0.001), and the sensitivity and specificity were 0.935 and 0.672, respectively; In the validation cohort, the AUC was 0.864 (P <0.001), and the sensitivity and specificity were 1.00 and 0.75, respectively. Kaplan-Meier curve showed that the 3-year RMFR and 3-year cancer specific survival (CSS) rate in the high-risk group were significantly lower than those in the low-risk group (P <0.001). In the high-risk group, patients who received AC had greater 3-year RMFR than those who did not receive AC (78.6% vs. 48.1%) (p = 0.03).

CONCLUSION

Considering increasing RMFR, a prediction model for NPC based on two clinical factors and seven imaging features suggested the AC needs to be added to patients in the high-risk group and not in the low-risk group.

Multifunctional Nanotheranostics for Dual-Modal Imaging-Guided Precision Therapy of Nasopharyngeal Carcinoma

Currently, the low survival rate and poor prognosis of patients with nasopharyngeal carcinoma are ascribed to the lack of early and accurate diagnosis and resistance to radiotherapy. In parallel, the integration of imaging-guided diagnosis and precise treatment has gained much attention in the field of theranostic nanotechnology. However, constructing dual-modal imaging-guided nanotheranostics with desired imaging performance as well as great biocompatibility remains challenging. Therefore, we developed a simple but multifunctional nanotheranostic GdCPP for the early and accurate diagnosis and efficient treatment of nasopharyngeal carcinoma (NPC), which combined fluorescence imaging and magnetic resonance imaging (MRI) onto a single nanoplatform for imaging-guided subsequent photodynamic therapy (PDT). GdCPP had an appropriate particle size (81.93 ± 0.69 nm) and was highly stable, resulting in sufficient tumor accumulation, which along with massive reactive oxygen species (ROS) generation upon irradiation further significantly killed tumor cells. Moreover, GdCPP owned much stronger r1 relaxivity (9.396 mM-1 s-1) compared to clinically used Gd-DTPA (5.034 mM-1 s-1) and exhibited better T1WI MRI performance. Under dual-modal imaging-guided PDT, GdCPP achieved efficient therapeutic outcomes without causing any noticeable tissue damage. The results of in vitro and in vivo studies indicated that GdCPP may be a suitable candidate for dual-modal imaging-guided precision tumor therapy.

Amide proton transfer (APT) and magnetization transfer (MT) in predicting short-term therapeutic outcome in nasopharyngeal carcinoma after chemoradiotherapy: a feasibility study of three-dimensional chemical exchange saturation transfer (CEST) MRI

BACKGROUND

The three-dimensional chemical exchange saturation transfer (3D CEST) technique is a novel and promising magnetic resonance sequence; however, its application in nasopharyngeal carcinoma (NPC) lacks sufficient evaluation. This study aimed to assess the feasibility of the 3D CEST technique in predicting the short-term treatment outcomes for chemoradiotherapy (CRT) in NPC patients.

METHODS

Forty NPC patients and fourteen healthy volunteers were enrolled and underwent the pre-treatment 3D CEST magnetic resonance imaging and diffusion-weighted imaging (DWI). The reliability of 3D CEST was assessed in healthy volunteers by calculating the intra- and inter-observer correlation coefficient (ICC) for amide proton transfer weighted-signal intensity (APTw-SI) and magnetization transfer ratio (MTR) values. NPC patients were divided into residual and non-residual groups based on short-term treatment outcomes after CRT. Whole-tumor regions of interest (ROIs) were manually drawn to measure APTw-SI, MTR and apparent diffusion coefficient (ADC) values. Multivariate analysis and the receiver operating characteristic curve (ROC) were used to evaluate the prediction performance of clinical characteristics, APTw-SI, MTR, ADC values, and combined models in predicting short-term treatment outcomes in NPC patients.

RESULTS

For the healthy volunteer group, all APTw-SI and MTR values exhibited good to excellent intra- and inter-observer agreements (0.736-0.910, 0.895-0.981, all P > 0.05). For NPC patients, MTR values showed a significant difference between the non-residual and residual groups (31.24 ± 5.21% vs. 34.74 ± 1.54%, P = 0.003) while no significant differences were observed for APTw-SI and ADC values (P > 0.05). Moreover, the diagnostic power of MTR value was superior to APTw-SI (AUC: 0.818 vs. 0.521, P = 0.017) and comparable to ADC values (AUC: 0.818 vs. 0.649, P > 0.05) in predicting short-term treatment outcomes for NPC patients. The prediction performance did not improve even when combining MTR values with APTw-SI and/or ADC values (P > 0.05).

CONCLUSIONS

The pre-treatment MTR value acquired through 3D CEST demonstrated superior predictive performance for short-term treatment outcomes compared to APTw-SI and ADC values in NPC patients after CRT.

Application value of 3D pCASL in early assessment of potential radiation encephalopathy in nasopharyngeal carcinoma patients undergoing radiotherapy

OBJECTIVE

The study explores the application value of three-dimensional arterial spin labeling magnetic resonance imaging (3D pCASL) in early assessment of radiation encephalopathy (REP) in patients with nasopharyngeal carcinoma (NPC).

METHODS

A retrospective analysis of 39 cases of NPC was performed. Routine enhanced MRI scan and 3D pCASL imaging were used to examine the apparent diffusion coefficient (ADC) and brain blood flow (CBF) before and after treatment with intensity-modulated radiotherapy (IMRT). Dosimetric analysis of irradiation was performed. Receiver operating characteristic curve (ROC) was used to analyze diagnostic performance of two imaging methods.

RESULTS

There was no statistically significant difference between the two methods for the measurement of temporal white matter ADC, but statistically significant difference was found in CBF. 3D pCASL imaging showed more sensitivity, specificity and higher accuracy than conventional MRI enhanced scan in showing REP. The maximum dose of the temporal lobe was at the enhanced area.

CONCLUSION

The present study demonstrates that 3D pCASL scan at month 3 can reflect blood flow perfusion differences in NPC patients after IMRT and can accurately assess the possibility of REP at early stage. Enhanced areas have a higher probability of REP than the surrounding areas.

ADVANCES IN KNOWLEDGE

There is few magnetic resonance angiography studies used to evaluate arterial circulation on its application on potential REP after radiotherapy for NPC. In our study, we evaluate the application value of 3D pCASL in the early assessment of potential REP in patients with NPC after radiotherapy. The study was to provide an improved understanding of the early specific characteristics on MRI imaging and evolution of potential radiation encephalopathy using 3D pCASL technique, which can quantitatively evaluate the changes of blood flow in tissues at early stage and help to diagnose and treat potential radiation encephalopathy as early as possible.

The impact of the COVID-19 pandemic on nasopharyngeal carcinoma extent at FDG PET/MR staging: The NPCOVIPET study

BACKGROUND

To evaluate the impact of coronavirus disease 2019 (COVID-19) pandemic on disease extent in patients with nasopharyngeal carcinoma (NPC) using 18 fuorodeoxyglucose (FDG) positron emission tomography (PET)/magnetic resonance imaging (MRI).

METHODS

This retrospective cohort study included biopsy-proven, newly diagnosed NPC patients using whole-body FDG PET/MR staging in two selected intervals: 1 May 2017 to 31 January 2020 (Group A, the pre-COVID-19 period), and 1 February 2020 to 30 June 2021 (Group B, the COVID-19 period).

RESULTS

Three-hundred and ninety patients were included. No significant difference was observed in terms of T classification, N classification, overall stage, N stations, and M stations between the two groups (p > 0.05). For the involved neck node levels, more patients had developed level Vc metastasis in the group B (p = 0.044).

CONCLUSION

Although the overall stage was not affected, more patients with NPC had developed level Vc metastasis in the era of COVID-19.

Evaluation of 11 C-Choline PET/CT for T Staging and Tumor Volume Delineation in Nasopharyngeal Cancer Patients in Comparison to 18 F-FDG PET/CT

PURPOSE

Accurate determination of the primary tumor extension of nasopharyngeal carcinoma (NPC) by 18 F-FDG PET/CT is limited by the high physiological 18 F-FDG uptake in the surrounding area, especially in the brain tissue. We aimed to assess whether 11 C-choline PET/CT could improve the accuracy of T staging and tumor volume delineation for NPC patients.

METHODS

Patients with pathologically confirmed diagnosis of NPC were enrolled. The primary tumor extension of each patient was evaluated by 11 C-choline PET/CT, 18 F-FDG PET/CT, and contrast-enhanced MRI. The PET/CT-based tumor volume ( VPET ) was measured by 3 threshold methods, including the threshold of SUV 2.5 (Th 2.5 ), 40% of maximal SUV (Th 40% ), and the relative background-dependent threshold (Th bgd ). Tumor volume and Dice similarity coefficient were compared among VPET with different segmentation methods and VMR .

RESULTS

Thirty-three patients with treatment-naive NPC and 6 patients with suspicious recurrent disease were enrolled. The NPC lesions were avid for both 11 C-choline and 18 F-FDG. Visual analysis showed that 11 C-choline PET/CT had better contrast and higher discernability than 18 F-FDG PET/CT for intracranial, skull base, and orbital involvement. 11 C-choline PET/CT also exhibited advantage over MRI for differentiation between local recurrence and radiation-induced alterations. For the tumor delineated, the VMR was larger than VPET in general, except for 18 F-FDG PET/CT with Th 2.5 threshold. For all 3 threshold methods applied, 11 C-choline PET/CT produced more consistent and comparable tumor volume to MRI than 18 F-FDG PET/CT. 11 C-choline PET/CT with Th bgd threshold showed the closest tumor volume and highest similarity to MRI.

CONCLUSIONS

11 C-choline PET/CT provides a higher accuracy than 18 F-FDG PET/CT in mapping tumor extension in locally advanced NPC and may be a promising complement to MRI in delineating the primary tumor.

Assessment of bone lesions with 18 F-FDG PET/MRI in patients with nasopharyngeal carcinoma

PURPOSE

The purpose of this study is to evaluate the role of 18 fluorodeoxyglucose ( 18 F) PET/MRI ( 18 F-FDG PET/MRI) for detecting bone metastasis in nasopharyngeal carcinoma (NPC).

PATIENTS AND METHODS

Between May 2017 and May 2021, 58 histologically proven NPC patients who underwent both 18 F-FDG PET/MRI and 99m Tc-MDP planar bone scintigraphy (PBS) for tumor staging were included. With the exception of the head, the skeletal system was classified into four groups: the spine, the pelvis, the thorax and the appendix.

RESULTS

Nine (15.5 %) of 58 patients were confirmed to have bone metastasis. There was no statistical difference between PET/MRI and PBS in patient-based analysis ( P  = 0.125). One patient with a super scan was confirmed to have extensive and diffuse bone metastases and excluded for lesion-based analysis. Of the 57 patients, all 48 true metastatic lesions were positive in PET/MRI whereas only 24 true metastatic lesions were positive in PBS (spine: 8, thorax: 0, pelvis: 11 and appendix: 5). PET/MRI was observed to be more sensitive than PBS in lesion-based analysis (sensitivity 100.0% versus 50.0 %; P  < 0.001).

CONCLUSIONS

Compared with PBS for tumor staging of NPC, PET/MRI was observed to be more sensitive in the lesion-based analysis of bone metastasis.

MRI-Based Metastatic Nodal Number and Associated Nomogram Improve Stratification of Nasopharyngeal Carcinoma Patients: Potential Indications for Individual Induction Chemotherapy

BACKGROUND

Metastatic lymph nodal number (LNN) is associated with the survival of nasopharyngeal carcinoma (NPC); however, counting multiple nodes is cumbersome.

PURPOSE

To explore LNN threshold and evaluate its use in risk stratification and induction chemotherapy (IC) indication.

STUDY TYPE

Retrospective.

POPULATION

A total of 792 radiotherapy-treated NPC patients (N classification: N0 182, N1 438, N2 113, N3 59; training group: 396, validation group: 396; receiving IC: 390).

FIELD STRENGTH/SEQUENCE

T1-, T2- and postcontrast T1-weighted fast spin echo MRI at 1.5 or 3.0 T.

ASSESSMENT

Nomogram with (model B) or without (model A) LNN was constructed to evaluate the 5-year overall (OS), distant metastasis-free (DMFS), and progression-free survival (PFS) for the group as a whole and N1 stage subgroup. High- and low-risk groups were divided (above vs below LNN- or model B-threshold); their response to IC was evaluated among advanced patients in stage III/IV.

STATISTICAL TESTS

Maximally selected rank, univariate and multivariable Cox analysis identified the optimal LNN threshold and other variables. Harrell's concordance index (C-index) and 2-fold cross-validation evaluated discriminative ability of models. Matched-pair analysis compared survival outcomes of adding IC or not. A P value < 0.05 was considered statistically significant.

RESULTS

Median follow-up duration was 62.1 months. LNN ≥ 4 was independently associated with decreased 5-year DMFS, OS, and PFS in entire patients or N1 subgroup. Compared to model A, model B (adding LNN, LNN ≥ 4 vs <4) presented superior C-indexes in the training (0.755 vs 0.727) and validation groups (0.676 vs 0.642) for discriminating DMFS. High-risk patients benefited from IC with improved post-IC response and OS, but low-risk patients did not (P = 0.785 and 0.690, respectively).

CONCLUSIONS

LNN ≥ 4 is an independent risk stratification factor of worse survival in entire or N1 staging NPC patients. LNN ≥ 4 or the associated nomogram has potential to identify high-risk patients requiring IC.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: 4.

Prognostic generalization of multi-level CT-dose fusion dosiomics from primary tumor and lymph node in nasopharyngeal carcinoma

PURPOSE

To investigate the prognostic performance of multi-level computed tomography (CT)-dose fusion dosiomics at the image-, matrix-, and feature-levels from the gross tumor volume (GTV) at nasopharynx and the involved lymph node for nasopharyngeal carcinoma (NPC) patients.

METHODS

Two hundred and nineteen NPC patients (175 vs. 44 for training vs. internal validation) were used to train prediction model, and 32 NPC patients were used for external validation. We first extracted CT and dose information from intratumoral nasopharynx (GTV_nx) and lymph node (GTV_nd) regions. Then, the corresponding peritumoral regions (RING_3 mm and RING_5 mm) were also considered. Thus, the individual and combination of intratumoral and peritumoral regions were as follows: GTV_nx, GTV_nd, RING_3 mm_nx, RING_3 mm_nd, RING_5 mm_nx, RING_5 mm_nd, GTV_nxnd, RING_3 mm_nxnd, RING_5 mm_nxnd, GTV + RING_3 mm_nxnd, and GTV + RING_5 mm_nxnd. For each region, 11 models were built by combining five clinical parameters and 127 features from: (1) dose images alone; (2-7) fused dose and CT images via wavelet-based fusion using CT weights of 0.2, 0.4, 0.6, and 0.8, gradient transfer fusion, and guided-filtering-based fusion (GFF); (8) fused matrices (sumMat); (9-10) fused features derived via feature averaging (avgFea) and feature concatenation (conFea); and finally, (11) CT images alone. The concordance index (C-index) and Kaplan-Meier curves with log-rank test were used to assess model performance.

RESULTS

The fusion models' performance was better than single CT/dose model on both internal and external validation. Models that combined the information from both GTV_nx and GTV_nd regions outperformed the single region model. For internal validation, GTV + RING_3 mm_nxnd GFF model achieved the highest C-index both in recurrence-free survival (RFS) and metastasis-free survival (MFS) predictions (RFS: 0.822; MFS: 0.786). The highest C-index in external validation set was achieved by RING_3 mm_nxnd model (RFS: 0.762; MFS: 0.719). The GTV + RING_3 mm_nxnd GFF model is able to significantly separate patients into high-risk and low-risk groups compared to dose-only or CT-only models.

CONCLUSION

Fusion dosiomics model combining the primary tumor, the involved lymph node, and 3 mm peritumoral information outperformed single-modality models for different outcome predictions, which is helpful for clinical decision-making and the development of personalized treatment.

18 F-FDG PET/CT Findings of Leptomeningeal Metastasis in Nasopharyngeal Carcinoma

ABSTRACT

Nasopharyngeal carcinoma (NC) is an epithelial tumor with distinctive prevalence in East and Southeast Asia. Most patients with NC only experience regional metastasis. In cases of distant metastasis, prognosis is grim. Leptomeningeal spread of the disease is a rare occurrence, which is sparsely described in the literature. We present a case of a 33-year-old man with a history of high-grade NC with leptomeningeal metastasis. Initial MRI lumbar spine demonstrated subtle findings consistent with leptomeningeal disease. These findings are easily discernible on 18 F-FDG PET/CT.

The application of 3-dimensional magnetic resonance imaging in nasopharyngeal carcinoma with pterygopalatine fossa invasion

OBJECT

The pterygopalatine fossa (PPF) is a covert neurovascular pathway in the skull base and connects with numerous intracranial and extracranial spaces. The aim of this study was to explore the magnetic resonance imaging (MRI) features of PPF invasion in patients with nasopharyngeal carcinoma (NPC).

MATERIAL AND METHODS

The medical records of 88 patients with stage T3 or T4 NPC were retrospectively analyzed. The 3-Dimensional (3D) volumetric images of MRI were reconstructed for the tiny connecting conduits of the invaded PPFs in the NPC patients. The infiltration incidence of conduits and connected further structures were calculated.

RESULTS

Forty-six PPFs from 37 patients were invaded by NPC. The proportions of stage T4 NPC and intracranial extension were higher in patients with PPF invasion than that without PPF invasion (P < 0.05). Each connecting conduit of the PPF had corresponding optimal reconstructed orientation based on 3D volumetric MRI images. The first three most common infiltrated conduits were palatovaginal canal, vidian canal and sphenopalatine foramen, which were adjacent to the nasopharynx. Among the conduits connecting with further structures, the most common infiltrated conduit was pterygomaxillary fissure, followed by foramen rotundum and inferior orbital fissure. Furthermore, The NPC lesions involved stage T4 structures via the conduits from 19.6% of the invaded PPFs.

CONCLUSIONS

The application of high-quality reconstruction images based on 3D sequence of MRI in NPC patients proved to be feasible and beneficial for the manifestation of the invaded PPFs and connecting conduits.

Set-up errors of the neck are underestimated using the overall registration frame of head and neck in IMRT for NPC

BACKGROUND

There is no standardized registration frame of cone beam CT (CBCT) in intensity modulated radiotherapy (IMRT) for nasopharyngeal carcinoma (NPC). The overall registration frame that covers the whole head and neck is the most commonly used CBCT registration frame for NPC patients in IMRT.

OBJECTIVE

To compare the set-up errors using different registration frames of CBCT for NPC to assess the set-up errors for different region of the commonly used clinical overall registration frame.

METHODS

294 CBCT images of 59 NPC patients were collected. Four registration frames were used for matching. The set-up errors were obtained using an automatic matching algorithm and then compared. The expansion margin from the clinical target volume (CTV) to the planned target volume (PTV) in the four groups was also calculated.

RESULTS

The average range of the isocenter translation and rotation errors of four registration frames are 0.89∼2.41 mm and 0.49∼1.53°, respectively, which results in a significant difference in the set-up errors (p < 0.05). The set-up errors obtained from the overall frame are smaller than those obtained from the head, upper neck, and lower neck frames. The margin ranges of the overall, head, upper neck, and lower neck frames in three translation directions are 1.49∼2.39 mm, 1.92∼2.45 mm, 1.86∼3.54 mm and 3.02∼4.78 mm, respectively. The expansion margins calculated from the overall frame are not enough, especially for the lower neck.

CONCLUSION

Set-up errors of the neck are underestimated by the overall registration frame. Thus, it is important to improve the position immobilization of the neck, especially the lower neck. The margin of the target volume of the head and neck region should be expanded separately if circumstances permit.

Dynamic Contrast-Enhanced MRI Parameters and Normalized ADC Values Could Aid Differentiation of Skull Base Osteomyelitis from Nasopharyngeal Cancer

BACKGROUND AND PURPOSE

The skull base osteomyelitis sometimes can be difficult to distinguish from nasopharyngeal cancer. This study aimed to investigate the differences between skull base osteomyelitis and nasopharyngeal cancer using dynamic contrast-enhanced MR imaging and normalized ADC values.

MATERIALS AND METHODS

This study included 8 and 12 patients with skull base osteomyelitis and nasopharyngeal cancer, respectively, who underwent dynamic contrast-enhanced MR imaging and DWI before primary treatment. Quantitative dynamic contrast-enhanced MR imaging parameters and ADC values of the ROIs were analyzed. Normalized ADC parameters were calculated by dividing the ROIs of the lesion by that of the spinal cord.

RESULTS

The rate transfer constant between extravascular extracellular space and blood plasma per minute (Kep) was significantly lower in patients with skull base osteomyelitis than in those with nasopharyngeal cancer (median, 0.43 versus 0.57; P = .04). The optimal cutoff value of Kep was 0.48 (area under the curve, 0.78; 95% CI, 0.55-1). The normalized mean ADC was significantly higher in patients with skull base osteomyelitis than in those with nasopharyngeal cancer (median, 1.90 versus 0.87; P < .001). The cutoff value of normalized mean ADC was 1.55 (area under the curve, 0.96; 95% CI, 0.87-1). The area under the curve of the combination of dynamic contrast-enhanced MR imaging parameters (Kep and extravascular extracellular space volume per unit tissue volume) was 0.89 (95% CI, 0.73-1), and the area under the curve of the combination of dynamic contrast-enhanced MR imaging parameters and normalized mean ADC value was 0.98 (95% CI, 0.93-1).

CONCLUSIONS

Quantitative dynamic contrast-enhanced MR imaging parameters and normalized ADC values may be useful in differentiating skull base osteomyelitis and nasopharyngeal cancer. The combination of dynamic contrast-enhanced MR imaging parameters and normalized ADC values outperformed each measure in isolation.

Lightweight Compound Scaling Network for Nasopharyngeal Carcinoma Segmentation from MR Images

Nasopharyngeal carcinoma (NPC) is a category of tumours with a high incidence in head-and-neck. To treat nasopharyngeal cancer, doctors invariably need to perform focal segmentation. However, manual segmentation is time consuming and laborious for doctors and the existing automatic segmentation methods require large computing resources, which makes some small and medium-sized hospitals unaffordable. To enable small and medium-sized hospitals with limited computational resources to run the model smoothly and improve the accuracy of structure, we propose a new LW-UNet network. The network utilises lightweight modules to form the Compound Scaling Encoder and combines the benefits of UNet to make the model both lightweight and accurate. Our model achieves a high accuracy with a Dice coefficient value of 0.813 with 3.55 M parameters and 7.51 G of FLOPs within 0.1 s (testing time in GPU), which is the best result compared with four other state-of-the-art models.

MRI-Based Back Propagation Neural Network Model as a Powerful Tool for Predicting the Response to Induction Chemotherapy in Locoregionally Advanced Nasopharyngeal Carcinoma

BACKGROUND

Pretreatment individualized assessment of tumor response to induction chemotherapy (ICT) is a need in locoregionally advanced nasopharyngeal carcinoma (LANPC). Imaging method plays vital role in tumor response assessment. However, powerful imaging method for ICT response prediction in LANPC is insufficient.

PURPOSE

To establish a robust model for predicting response to ICT in LANPC by comparing the performance of back propagation neural network (BPNN) model with logistic regression model.

STUDY TYPE

Retrospective.

POPULATION

A total of 286 LANPC patients were assigned to training (N = 200, 43.8 ± 10.9 years, 152 male) and testing (N = 86, 43.5 ± 11.3 years, 57 male) cohorts.

FIELD STRENGTH/SEQUENCE

T₂ -weighted imaging, contrast enhanced-T₁ -weighted imaging using fast spin echo sequences at 1.5 T scanner.

ASSESSMENT

Predictive clinical factors were selected by univariate and multivariate logistic models. Radiomic features were screened by interclass correlation coefficient, single-factor analysis, and the least absolute shrinkage selection operator (LASSO). Four models based on clinical factors (Model^clinic ), radiomics features (Model^radiomics ), and clinical factors + radiomics signatures using logistic (Model^combined ), and BPNN (Model^BPNN ) methods were established, and model performances were compared.

STATISTICAL TESTS

Student's t-test, Mann-Whitney U-test, and Chi-square test or Fisher's exact test were used for comparison analysis. The performance of models was assessed by area under the receiver operating characteristic (ROC) curve (AUC) and Delong test. P < 0.05 was considered statistical significance.

RESULTS

Three significant clinical factors: Epstein-Barr virus-DNA (odds ratio [OR] = 1.748; 95% confidence interval [CI], 0.969-3.171), sex (OR = 2.883; 95% CI, 1.364-6.745), and T stage (OR = 1.853; 95% CI, 1.201-3.052) were identified via univariate and multivariate logistic models. Twenty-four radiomics features were associated with treatment response. Model^BPNN demonstrated the highest performance among Model^combined , Model^radiomics , and Model^clinic (AUC of training cohort: 0.917 vs. 0.808 vs. 0.795 vs. 0.707; testing cohort: 0.897 vs. 0.755 vs. 0.698 vs. 0.695).

CONCLUSION

A machine-learning approach using BPNN showed better ability than logistic regression model to predict tumor response to ICT in LANPC.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Optimization of scan parameters to reduce acquisition time for RESOLVE-based diffusion kurtosis imaging (DKI) in nasopharyngeal carcinoma (NPC)

OBJECTIVE

To shorten acquisition time of readout segmentation of long variable echo trains (RESOLVE)-based diffusion kurtosis imaging (DKI) via Readout Partial Fourier (RPF) and b-value combinations.

METHODS

The RESOLVE-based DKI images of 38 patients with nasopharyngeal carcinoma (NPC) were prospectively enrolled. For RESOLVE-based DKI images with 5/8 RPF and without RPF, objective and subjective evaluations of image quality were performed. A total of nine groups with different b-value combinations were simulated, and the influence of different b-value combinations for RESOLVE-RPF-based DKI sequences was assessed using the intraclass correlation coefficient (ICC).

RESULTS

The mean values of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in DKI images without RPF were higher than those with 5/8 RPF (252.9 ± 77.7 vs 247.3 ± 85.5 and 5.8 ± 2.8 vs 5.4 ± 2.3, respectively), but not significantly (p = 0.460 and p = 0.180, respectively). In comparing the ICCs between nine groups of different b-value combinations in RESOLVE-RPF-based DKI, group (200, 800, 2000 s/mm2), group (200, 400, 800, 2000 s/mm2) and group (200, 800, 1500, 2000 s/mm2) were not significantly different (p > 0.001) and showed excellent agreement (0.81-1.00) with that of group (200, 400, 800, 1500, 2000 s/mm2). Using b-value optimization and RPF technology, the group with RPF (200, 400, 800, 2000 s/mm2) showed a 56% reduced scanning compared with the group without RPF (200, 400, 800, 1500, 2000 s/mm2; 3 min 46 s vs 8 min 31 s, respectively).

CONCLUSION

DKI with RPF did not significantly affect image quality, but both RPF and different b-value combinations can affect the scanning time. The combination of RPF and b-value optimization can ensure the stability of DKI parameters and reduce the scanning time by 56%.

ADVANCES IN KNOWLEDGE

This work is to optimize scan parameters, e.g. RPF and b-value combinations, to reduce acquisition time for RESOLVE-based DKI in NPC. To our knowledge, the effect of RESOLVE-RPF and b-value combinations on DKI has not been reported.

Automatic Delineation of Gross Tumor Volume Based on Magnetic Resonance Imaging by Performing a Novel Semisupervised Learning Framework in Nasopharyngeal Carcinoma

PURPOSE

We aimed to validate the accuracy and clinical value of a novel semisupervised learning framework for gross tumor volume (GTV) delineation in nasopharyngeal carcinoma.

METHODS AND MATERIALS

Two hundred fifty-eight patients with magnetic resonance imaging data sets were divided into training (n = 180), validation (n = 20), and testing (n = 58) cohorts. Ground truth contours of nasopharynx GTV (GTVnx) and node GTV (GTVnd) were manually delineated by 2 experienced radiation oncologists. Twenty percent (n = 36) labeled and 80% (n = 144) unlabeled images were used to train the model, producing model-generated contours for patients from the testing cohort. Nine experienced experts were invited to revise model-generated GTV in 20 randomly selected patients from the testing cohort. Six junior oncologists were asked to delineate GTV in 12 randomly selected patients from the testing cohort without and with the assistance of the model, and revision degrees were compared under these 2 modes. The Dice similarity coefficient (DSC) was used to quantify the accuracy of the model.

RESULTS

The model-generated contours showed a high accuracy compared with ground truth contours, with an average DSC score of 0.83 and 0.80 for GTVnx and GTVnd, respectively. There was no significant difference in DSC score between T1-2 and T3-4 patients (0.81 vs 0.83; P = .223), or between N1-2 and N3 patients (0.80 vs 0.79; P = .807). The mean revision degree was lower than 10% in 19 (95%) patients for GTVnx and in 16 (80%) patients for GTVnd. With assistance of the model, the mean revision degree for GTVnx and GTVnd by junior oncologists was reduced from 25.63% to 7.75% and from 21.38% to 14.44%, respectively. Meanwhile, the delineating efficiency was improved by over 60%.

CONCLUSIONS

The proposed semisupervised learning-based model showed a high accuracy for delineating GTV of nasopharyngeal carcinoma. It was clinically applicable and could assist junior oncologists to improve GTV contouring accuracy and save contouring time.

NPCNet: Jointly Segment Primary Nasopharyngeal Carcinoma Tumors and Metastatic Lymph Nodes in MR Images

Nasopharyngeal carcinoma (NPC) is a malignant tumor whose survivability is greatly improved if early diagnosis and timely treatment are provided. Accurate segmentation of both the primary NPC tumors and metastatic lymph nodes (MLNs) is crucial for patient staging and radiotherapy scheduling. However, existing studies mainly focus on the segmentation of primary tumors, eliding the recognition of MLNs, and thus fail to comprehensively provide a landscape for tumor identification. There are three main challenges in segmenting primary NPC tumors and MLNs: variable location, variable size, and irregular boundary. To address these challenges, we propose an automatic segmentation network, named by NPCNet, to achieve segmentation of primary NPC tumors and MLNs simultaneously. Specifically, we design three modules, including position enhancement module (PEM), scale enhancement module (SEM), and boundary enhancement module (BEM), to address the above challenges. First, the PEM enhances the feature representations of the most suspicious regions. Subsequently, the SEM captures multiscale context information and target context information. Finally, the BEM rectifies the unreliable predictions in the segmentation mask. To that end, extensive experiments are conducted on our dataset of 9124 samples collected from 754 patients. Empirical results demonstrate that each module realizes its designed functionalities and is complementary to the others. By incorporating the three proposed modules together, our model achieves state-of-the-art performance compared with nine popular models.

DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients With Advanced Nasopharyngeal Carcinoma Using Pretreatment PET/CT

Nasopharyngeal Carcinoma (NPC) is a malignant epithelial cancer arising from the nasopharynx. Survival prediction is a major concern for NPC patients, as it provides early prognostic information to plan treatments. Recently, deep survival models based on deep learning have demonstrated the potential to outperform traditional radiomics-based survival prediction models. Deep survival models usually use image patches covering the whole target regions (e.g., nasopharynx for NPC) or containing only segmented tumor regions as the input. However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e.g., local lymph node metastasis and adjacent tissue invasion). In this study, we propose a 3D end-to-end Deep Multi-Task Survival model (DeepMTS) for joint survival prediction and tumor segmentation in advanced NPC from pretreatment PET/CT. Our novelty is the introduction of a hard-sharing segmentation backbone to guide the extraction of local features related to the primary tumors, which reduces the interference from non-relevant background information. In addition, we also introduce a cascaded survival network to capture the prognostic information existing out of primary tumors and further leverage the global tumor information (e.g., tumor size, shape, and locations) derived from the segmentation backbone. Our experiments with two clinical datasets demonstrate that our DeepMTS can consistently outperform traditional radiomics-based survival prediction models and existing deep survival models.

Deep learning for locally advanced nasopharyngeal carcinoma prognostication based on pre- and post-treatment MRI

PURPOSE

We aimed to predict the prognosis of advanced nasopharyngeal carcinoma (stage Ⅲ-Ⅳa) using Pre- and Post-treatment MR images based on deep learning (DL).

METHODS

A total of 206 patients with primary nasopharyngeal carcinoma who were diagnosed and treated at the Renmin Hospital of Wuhan University between June 2012 and January 2018 were retrospectively selected. A rectangular region of interest (ROI), which included the tumor area, surrounding tissues and organs, was delineated on each Pre- and Post-treatment MR image. Two Inception-Resnet-V2 based transfer learning models, named Pre-model and Post-model, were trained with the Pre-treatment images and the Post-treatment images, respectively. In addition, an ensemble learning model based on the Pre-model and Post-models was established. The three established models were evaluated by receiver operating characteristic curve (ROC), confusion matrix, and Harrell's concordance indices (C-index). High-risk-related gradient-weighted class activation mapping (Grad-CAM) images were developed according to the DL models.

RESULTS

The Pre-model, Post-model, and ensemble model displayed a C-index of 0.717 (95% CI: 0.639 to 0.795), 0.811 (95% CI: 0.745-0.877), 0.830 (95% CI: 0.767-0.893), and AUC of 0.741 (95% CI: 0.584-0.900), 0.806 (95% CI: 0.670-0.942), and 0.842 (95% CI: 0.718-0.967) for the test cohort, respectively. In comparison with the models, the performance of Post-model was better than the performance of Pre-model, which indicated the importance of Post-treatment images for prognosis prediction. All three DL models performed better than the TNM staging system (0.723, 95% CI: 0.567-0.879). The captured features presented on Grad-CAM images suggested that the areas around the tumor and lymph nodes were related to the prognosis of the tumor.

CONCLUSIONS

The three established DL models based on Pre- and Post-treatment MR images have a better performance than TNM staging. Post-treatment MR images are of great significance for prognosis prediction and could contribute to clinical decision-making.