A novel fully automatic segmentation and counting system for metastatic lymph nodes on multimodal magnetic resonance imaging: Evaluation and prognostic implications in nasopharyngeal carcinoma.

BACKGROUND: The number of metastatic lymph nodes (MLNs) is crucial for the survival of nasopharyngeal carcinoma (NPC), but manual counting is laborious. This study aims to explore the feasibility and prognostic value of automatic MLNs segmentation and counting. METHODS: We retrospectively enrolled 980 newly diagnosed patients in the primary cohort and 224 patients from two external cohorts. We utilized the nnUnet model for automatic MLNs segmentation on multimodal magnetic resonance imaging. MLNs counting methods, including manual delineation-assisted counting (MDAC) and fully automatic lymph node counting system (AMLNC), were compared with manual evaluation (Gold standard). RESULTS: In the internal validation group, the MLNs segmentation results showed acceptable agreement with manual delineation, with a mean Dice coefficient of 0.771. The consistency among three counting methods was as follows 0.778 (Gold vs. AMLNC), 0.638 (Gold vs. MDAC), and 0.739 (AMLNC vs. MDAC). MLNs numbers were categorized into three-category variable (1-4, 5-9, > 9) and two-category variable (<4, ≥ 4) based on the gold standard and AMLNC. These categorical variables demonstrated acceptable discriminating abilities for 5-year overall survival (OS), progression-free, and distant metastasis-free survival. Compared with base prediction model, the model incorporating two-category AMLNC-counting numbers showed improved C-indexes for 5-year OS prediction (0.658 vs. 0.675, P = 0.045). All results have been successfully validated in the external cohort. CONCLUSIONS: The AMLNC system offers a time- and labor-saving approach for fully automatic MLNs segmentation and counting in NPC. MLNs counting using AMLNC demonstrated non-inferior performance in survival discrimination compared to manual detection.

Artificial intelligence for diagnosis and prognosis prediction of natural killer/T cell lymphoma using magnetic resonance imaging.

Accurate diagnosis and prognosis prediction are conducive to early intervention and improvement of medical care for natural killer/T cell lymphoma (NKTCL). Artificial intelligence (AI)-based systems are developed based on nasopharynx magnetic resonance imaging. The diagnostic systems achieve areas under the curve of 0.905-0.960 in detecting malignant nasopharyngeal lesions and distinguishing NKTCL from nasopharyngeal carcinoma in independent validation datasets. In comparison to human radiologists, the diagnostic systems show higher accuracies than resident radiologists and comparable ones to senior radiologists. The prognostic system shows promising performance in predicting survival outcomes of NKTCL and outperforms several clinical models. For patients with early-stage NKTCL, only the high-risk group benefits from early radiotherapy (hazard ratio = 0.414 vs. late radiotherapy; 95% confidence interval, 0.190-0.900, p = 0.022), while progression-free survival does not differ in the low-risk group. In conclusion, AI-based systems show potential in assisting accurate diagnosis and prognosis prediction and may contribute to therapeutic optimization for NKTCL.

Optimal cut-off value for identifying objective response in patients with nasopharyngeal carcinoma after induction chemotherapy.

BACKGROUND: We aimed to establish the most suitable threshold for objective response (OR) in the Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1 in patients with nasopharyngeal carcinoma (NPC). METHODS: According to RECIST 1.1, we retrospectively evaluated MR images of NPC lesions in patients before and after induction chemotherapy (IC). Restricted cubic spline and maximally selected rank statistics were used to determine the cut-off value. Survival rates and differences between groups were compared with Kaplan-Meier curves and log-rank tests. RESULTS: Of 1126 patients, 365 cases who received IC treatment were suitable for RECIST 1.1 evaluation. The 20% cut-off value maximized between-group differences according to maximally selected rank statistics. No difference in distant metastasis-free survival between OR and non-response groups was shown using the primary threshold of OR (30%), while it differed when 20% was employed. CONCLUSIONS: With an optimal cut-off value of 20%, RECIST may assist clinicians to accurately evaluate disease response in NPC patients.

Dual-energy computed tomography in a multiparametric regression model for diagnosing lymph node metastases in pancreatic ductal adenocarcinoma.

OBJECTIVE: To investigate the diagnostic value of dual-energy computed tomography (DECT) quantitative parameters in the identification of regional lymph node metastasis in pancreatic ductal adenocarcinoma (PDAC). METHODS: This retrospective diagnostic study assessed 145 patients with pathologically confirmed pancreatic ductal adenocarcinoma from August 2016-October 2020. Quantitative parameters for targeted lymph nodes were measured using DECT, and all parameters were compared between benign and metastatic lymph nodes to determine their diagnostic value. A logistic regression model was constructed; the receiver operator characteristics curve was plotted; the area under the curve (AUC) was calculated to evaluate the diagnostic efficacy of each energy DECT parameter; and the DeLong test was used to compare AUC differences. Model evaluation was used for correlation analysis of each DECT parameter. RESULTS: Statistical differences in benign and metastatic lymph nodes were found for several parameters. Venous phase iodine density had the highest diagnostic efficacy as a single parameter, with AUC 0.949 [95% confidence interval (CI):0.915-0.972, threshold: 3.95], sensitivity 79.80%, specificity 96.00%, and accuracy 87.44%. Regression models with multiple parameters had the highest diagnostic efficacy, with AUC 0.992 (95% CI: 0.967-0.999), sensitivity 95.96%, specificity 96%, and accuracy 94.97%, which was higher than that for a single DECT parameter, and the difference was statistically significant. CONCLUSION: Among all DECT parameters for regional lymph node metastasis in PDAC, venous phase iodine density has the highest diagnostic efficacy as a single parameter, which is convenient for use in clinical settings, whereas a multiparametric regression model has higher diagnostic value compared with the single-parameter model.

Value of radiological depth of invasion in non-pT4 Oral tongue squamous cell carcinoma: implication for preoperative MR T-staging.

OBJECTIVE: The prognostic stratification for oral tongue squamous cell carcinoma (OTSCC) is heavily based on postoperative pathological depth of invasion (pDOI). This study aims to propose a preoperative MR T-staging system based on tumor size for non-pT4 OTSCC. METHODS: Retrospectively, 280 patients with biopsy-confirmed, non-metastatic, pT1-3 OTSCC, treated between January 2010 and December 2017, were evaluated. Multiple MR sequences, including axial T2-weighted imaging (WI), unenhanced T1WI, and axial, fat-suppressed coronal, and sagittal contrast-enhanced (CE) T1WI, were utilized to measure radiological depth of invasion (rDOI), tumor thickness, and largest diameter. Intra-class correlation (ICC) and univariate and multivariate analyses were used to evaluate measurement reproducibility, and factors' significance, respectively. Cutoff values were established using an exhaustive method. RESULTS: Intra-observer (ICC = 0.81-0.94) and inter-observer (ICC = 0.79-0.90) reliability were excellent for rDOI measurements, and all measurements were significantly associated with overall survival (OS) (all p < .001). Measuring the rDOI on axial CE-T1WI with cutoffs of 8 mm and 12 mm yielded an optimal MR T-staging system for rT1-3 disease (5-year OS of rT1 vs rT2 vs rT3: 94.0% vs 72.8% vs 57.5%). Using multivariate analyses, the proposed T-staging exhibited increasingly worse OS (hazard ratio of rT2 and rT3 versus rT1, 3.56 [1.35-9.6], p = .011; 4.33 [1.59-11.74], p = .004; respectively), which outperformed pathological T-staging based on nonoverlapping Kaplan-Meier curves and improved C-index (0.682 vs. 0.639, p < .001). CONCLUSIONS: rDOI is a critical predictor of OTSCC mortality and facilitates preoperative prognostic stratification, which should be considered in future oral subsite MR T-staging. CLINICAL RELEVANCE STATEMENT: Utilizing axial CE-T1WI, an MR T-staging system for non-pT4 OTSCC was developed by employing rDOI measurement with optimal thresholds of 8 mm and 12 mm, which is comparable with pathological staging and merits consideration in future preoperative oral subsite planning. KEY POINTS: • Tumor morphology, measuring sequences, and observers could impact MR-derived measurements and compromise the consistency with histology. • MR-derived measurements, including radiological depth of invasion (rDOI), tumor thickness, and largest diameter, have a prognostic impact on OS (all p < .001). • rDOI with cutoffs of 8 mm and 12 mm on axial CE-T1WI is an optimal predictor of OS and could facilitate risk stratification in non-pT4 OTSCC disease.

TdDS-UNet: top-down deeply supervised U-Net for the delineation of 3D colorectal cancer.

Automatically delineating colorectal cancers with fuzzy boundaries from 3D images is a challenging task, but the problem of fuzzy boundary delineation in existing deep learning-based methods have not been investigated in depth. Here, an encoder-decoder-based U-shaped network (U-Net) based on top-down deep supervision (TdDS) was designed to accurately and automatically delineate the fuzzy boundaries of colorectal cancer. TdDS refines the semantic targets of the upper and lower stages by mapping ground truths that are more consistent with the stage properties than upsampling deep supervision. This stage-specific approach can guide the model to learn a coarse-to-fine delineation process and improve the delineation accuracy of fuzzy boundaries by gradually shrinking the boundaries. Experimental results showed that TdDS is more customizable and plays a role similar to the attentional mechanism, and it can further improve the capability of the model to delineate colorectal cancer contours. A total of 103, 12, and 29 3D pelvic magnetic resonance imaging volumes were used for training, validation, and testing, respectively. The comparative results indicate that the proposed method exhibits the best comprehensive performance, with a dice similarity coefficient (DSC) of 0.805 ± 0.053 and a hausdorff distance (HD) of 9.28 ± 5.14 voxels. In the delineation performance analysis section also showed that 44.49% of the delineation results are satisfactory and do not require revisions. This study can provide new technical support for the delineation of 3D colorectal cancer. Our method is open source, and the code is available athttps://github.com/odindis/TdDS/tree/main.

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.

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.

Multiscale feature fusion network for 3D head MRI image registration.

BACKGROUND: Image registration technology has become an important medical image preprocessing step with the wide application of computer-aided diagnosis technology in various medical image analysis tasks. PURPOSE: We propose a multiscale feature fusion registration based on deep learning to achieve the accurate registration and fusion of head magnetic resonance imaging (MRI) and solve the problem that general registration methods cannot handle the complex spatial information and position information of head MRI. METHODS: Our proposed multiscale feature fusion registration network consists of three sequentially trained modules. The first is an affine registration module that implements affine transformation; the second is to realize non-rigid transformation, a deformable registration module composed of top-down and bottom-up feature fusion subnetworks in parallel; and the third is a deformable registration module that also realizes non-rigid transformation and is composed of two feature fusion subnetworks in series. The network decomposes the deformation field of large displacement into multiple deformation fields of small displacement by multiscale registration and registration, which reduces the difficulty of registration. Moreover, multiscale information in head MRI is learned in a targeted manner, which improves the registration accuracy, by connecting the two feature fusion subnetworks. RESULTS: We used 29 3D head MRIs for training and seven volumes for testing and calculated the values of the registration evaluation metrics for the new algorithm to register anterior and posterior lateral pterygoid muscles. The Dice similarity coefficient was 0.745 ± 0.021, the Hausdorff distance was 3.441 ± 0.935 mm, the Average surface distance was 0.738 ± 0.098 mm, and the Standard deviation of the Jacobian matrix was 0.425 ± 0.043. Our new algorithm achieved a higher registration accuracy compared with state-of-the-art registration methods. CONCLUSIONS: Our proposed multiscale feature fusion registration network can realize end-to-end deformable registration of 3D head MRI, which can effectively cope with the characteristics of large deformation displacement and the rich details of head images and provide reliable technical support for the diagnosis and analysis of head diseases.

Synergistic Association of Hepatitis B Surface Antigen and Plasma Epstein-Barr Virus DNA Load on Distant Metastasis in Patients With Nasopharyngeal Carcinoma.

Importance: Hepatitis B surface antigen (HBsAg) reportedly increases the risk of distant metastasis among patients with nasopharyngeal carcinoma (NPC). However, the associated potential interaction and changes in hazard ratios (HRs) between HBsAg and different plasma Epstein-Barr (EBV) DNA levels are unknown. Moreover, the potential HBsAg-positive-associated NPC metastatic mechanism remains unclear. Objective: To investigate the prognostic value and biological associations of HBsAg and plasma EBV DNA levels on distant metastasis in patients with NPC. Design, Setting, and Participants: Retrospective cohort study performed at Sun Yat-sen University Cancer Center between January 2010 and January 2013. A total of 792 patients with nonmetastatic NPC were enrolled. The median (range) follow-up time was 62.1 (1.4-83.4) months. Of these patients, 17.8% presented with HBsAg positivity. Cytological experiments were performed to evaluate the role of HBsAg in the invasion and migration of EBV-positive NPC cells. Data analysis was performed from July 2020 to April 2021. Main Outcomes and Measures: The primary end point was distant metastasis-free survival. Association rules were used to identify new rules related to distant metastasis. Interaction plots, univariate and multivariate Cox regression analyses, stratification analysis, and quantification using HRs were conducted. Additionally, cell migration and invasion assays, as well as Western blotting, were performed in the cytological validation. Results: Among the 792 patients, 576 (72.7%) were male, with a median (IQR) age of 45 (38-53) years. The HBsAg-positive group exhibited a significant interaction and increased risk of distant metastasis when plasma EBV DNA cutoff levels were 1.5 × 1000 copies/mL or greater. The HR was 9.16 (95% CI, 2.46-34.14) when the plasma EBV DNA load reached 6 × 1000 copies/mL, which was higher than that in patients with stage IV disease (HR, 2.01; 95% CI, 1.13-3.56; P = .02). In cytological experiments, HBsAg promoted epithelial-mesenchymal transition by upregulating vimentin and fibronectin in EBV-positive NPC cells in vitro, thereby promoting invasion and migration of EBV-positive NPC cells. Conclusions and Relevance: In this cohort study, the observed synergistic association between HBsAg and plasma EBV DNA load represented a novel potential mechanism underlying the increased risk of distant metastasis in patients with NPC. Hence, attention should be paid to patients with NPC with HBsAg positivity, especially when the plasma EBV DNA level is 6 × 1000 copies/mL or greater. Consideration of this synergistic association will contribute to more accurate individualized management.

Prognostic potential of a voxelwise invasion risk map of nasopharyngeal carcinoma based on a coordinate system of the nasopharynx.

Background: Tumor invasion risk (TIR) is an important prognostic factor in nasopharyngeal carcinoma (NPC). We propose a novel prognostic analytic method for NPC based on a voxelwise analysis of TIR in a coordinate system of the nasopharynx. Methods: A stable nasopharynx coordinate system was constructed based on anatomical landmarks to obtain an accurate TIR profile for NPC. The coordinate system was validated by image registration of the lateral pterygoid muscle (LPM). The tumors were registered to the coordinate system through shift, scale, and rotation transformations. The voxelwise TIR map for NPC was obtained by superposition of all registered and mirrored tumor regions of interest. The minimum risk (MinR) point of the tumor region was used as an independent prognostic factor for NPC. The cutoff value was calculated with density plot and validated with restricted cubic splines (RCSs), and then the patients were divided into 2 groups for overall survival (OS) analysis. Results: The first voxelwise TIR map of NPC was obtained based on 778 patients. The OS of patients with a low TIR was 76.8% and was 92.6% for patients with a high TIR [P<0.001; hazard ratio (HR) =1/0.45; 95% CI: 0.27-0.77; adjusted P=0.004]. Thus, patients with a low TIR had a poor prognosis, whereas patients with a high TIR had a good prognosis. The MinR may be better at grading the prognosis of patients compared to the American Joint Committee on Cancer (AJCC) staging or tumor/node (T/N) classification systems. Conclusions: The voxelwise TIR map provides a new method for the prognostic analysis of NPC. Potential clinical applications of voxelwise TIR mapping are clinical target volume (CTV) delineation and dose-painting for NPC.

Prognostic value of MR-detected mandibular nerve involvement: potential indication for future individual induction chemotherapy in T4 nasopharyngeal carcinoma.

PURPOSE: To investigate the prognostic significance of MR-detected mandibular nerve involvement (MNI) and its value for induction chemotherapy (IC) administration in patients with nasopharyngeal carcinoma (NPC) and T4 disease. METHODS: This retrospective study enrolled 792 non-metastatic, biopsy-proven NPC patients. Univariate and multivariate analysis were used to evaluate potential prognosticators. The inter-observer agreement was assessed by the kappa values. RESULTS: MR-detected MNI was observed in 141 (72.3%) patients among 195 patients with T4 disease, with excellent agreement between the readers (kappa = 0.926). Patients with MR-detected MNI presented better 5-year overall survival (OS) (hazard ratio [HR], 0.40; P = 0.006) than those with MR-negative MNI. Of these patients, IC treatment was verified as an independent factor (HR: 0.35; P = 0.014) with preferable effect on OS. CONCLUSION: MR-detected MNI could serve as an independent favorable prognostic predictor for OS in NPC patients with stage T4, which should be considered for stratifying these patients for IC administration.

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.

Carotid space involvement is a prognostic factor and marker for induction chemotherapy in patients with nasopharyngeal carcinoma.

OBJECTIVES: The carotid space is an integral part of the parapharyngeal space, with ambiguous prognostic value for patients with nasopharyngeal carcinoma (NPC). This study aimed to investigate the prognostic significance of carotid space involvement (CSI) and propose a treatment strategy. MATERIALS AND METHODS: This retrospective study enrolled 792 patients with biopsy-confirmed, non-distant metastatic NPC staged by magnetic resonance imaging before treatment. We used multivariable Cox regression models and Kaplan-Meier methods to assess the association between the variables and survival outcomes. A matched-pair method (1:1) was used to compare the survival differences between the patients with CSI treated with induction chemotherapy (ICT)and that of those who were not. RESULTS: The incidence rate of CSI was 21.7 % (172/792). Multivariate analysis revealed that CSI was not an independent prognostic factor for survival outcomes in the 792 patients with NPC; however, the Chi-square test showed a different distribution of treatment strategies with ICT for patients with and without CSI. After stratification by ICT, CSI was an independent prognostic factor for overall survival (OS) (p = 0.049) in patients without ICT, but not for distant metastasis-free, local recurrence-free, or progression-free survival (p˃0.05). Additionally, ICT improved OS in patients with CSI (hazard ratio, 0.42; p = 0.019). Matched pair analysis showed that patients with CSI gained prolonged OS from ICT compared with the non-ICT group (88.4 % vs 69.4 %, p = 0.028). CONCLUSION: CSI was an independent negative prognostic factor for OS in patients with NPC without ICT and might be an imaging marker for identifying eligible candidates for ICT.

Survival impact of additional induction chemotherapy in nasopharyngeal carcinoma with chronic hepatitis B infection: a retrospective, bi-center study.

Background: Patients with nasopharyngeal carcinoma (NPC) who have hepatitis B virus (HBV) infection tend to be treated with induction chemotherapy (IC) due to a higher metastasis rate. However, additional IC may lead to immunosuppression and can negatively affect the prognosis. We evaluated whether receiving IC improved the prognosis of patients with NPC co-infected with HBV, on the basis of concurrent chemoradiotherapy (CCRT). Methods: This large-scale retrospective cohort study included data of patients with pathologically confirmed NPC that were collected from two hospitals between January 2010 and March 2014. Patients were followed-up every 3 months during the first 2 years and once every 6 months thereafter. Univariate analysis identified confounding factors associated with prognosis. Stage-based subgroup analyses and 1:1 random-matched pair analyses were performed to compare the survival differences between patients treated with IC + CCRT and those treated with CCRT alone. Results: Among the 1,076 enrolled patients, 16.6% were hepatitis B surface antigen (HBsAg)-positive. Among HBsAg-positive patients with stage II/III/IV NPC, distant metastasis-free survival (DMFS) (79.3% vs. 89.9%; P=0.045) and progression-free survival (PFS) (70.6% vs. 83.7%; P=0.025) were lower in patients who received IC + CCRT than in those who received CCRT alone. After adjusting for confounding factors, IC + CCRT was validated as a negative prognosticator for DMFS and PFS, while matched-pair analysis with HBsAg-negative patients showed a better overall survival (OS) for IC + CCRT (88.4% vs. 82.6%; P=0.04). Conclusions: Compared with CCRT alone, IC + CCRT negatively affects DMFS and PFS in patients with NPC with chronic HBV infection. We advocate withholding IC but administering stronger initial treatment in NPC patients complicated with HBV infection.

RuleFit-Based Nomogram Using Inflammatory Indicators for Predicting Survival in Nasopharyngeal Carcinoma, a Bi-Center Study.

Purpose: Traditional prognostic studies utilized different cut-off values, without evaluating potential information contained in inflammation-related hematological indicators. Using the interpretable machine-learning algorithm RuleFit, this study aimed to explore valuable inflammatory rules reflecting prognosis in nasopharyngeal carcinoma (NPC) patients. Patients and Methods: In total, 1706 biopsy-proven NPC patients treated in two independent hospitals (1320 and 386) between January 2010 and March 2014 were included. RuleFit was used to develop risk-predictive rules using hematological indicators with no distributive difference between the two centers. Time-event-dependent hematological rules were further selected by stepwise multivariate Cox analysis. Combining high-efficiency hematological rules and clinical predictors, a final model was established. Models based on other algorithms (AutoML, Lasso) and clinical predictors were built for comparison, as well as a reported nomogram. Area under the receiver operating characteristic curve (AUROC) and concordance index (C-index) were used to verify the predictive precision of different models. A site-based app was established for convenience. Results: RuleFit identified 22 combined baseline hematological rules, achieving AUROCs of 0.69 and 0.64 in the training and validation cohorts, respectively. By contrast, the AUROCs of the optimal contrast model based on AutoML were 1.00 and 0.58. For overall survival, the final model had a much higher C-index than the base model using TN staging in two cohorts (0.769 vs 0.717, P<0.001; 0.752 vs 0.688, P<0.001), and showing great generalizability in training and validation cohorts. The two models based on RuleFit rules performed best, compared with other models. As for other endpoints, the final model showed a similar trend. Kaplan-Meier curve exhibited 22.9% (390/1706) patients were "misclassified" by AJCC staging, but the final model could assess risk classification accurately. Conclusion: The proposed final models based on inflammation-related rules based on RuleFit showed significantly elevated predictive performance.

Value of skull base invasion subclassification in nasopharyngeal carcinoma: implication for prognostic stratification and use of induction chemotherapy.

OBJECTIVES: Prognoses for nasopharyngeal carcinoma (NPC) between categories T2 and T3 in the Eighth American Joint Committee on Cancer (AJCC) staging system were overlapped. We explored the value of skull base invasion (SBI) subclassification in prognostic stratification and use of induction chemotherapy (IC) to optimize T2/T3 categorization for NPC patients. METHODS: We retrospectively reviewed 1752 NPC patients from two hospitals. Eight skull base bone structures were evaluated. Survival differences were compared between slight SBI (T3 patients with pterygoid process and/or base of the sphenoid bone invasion only) and severe SBI (T3 patients with other SBIs) with or without IC using random matched-pair analysis. We calculated the prognosis and Harrel concordance index (C-index) for the revised T category and compared IC outcomes for the revised tumor stages. RESULTS: Compared to severe SBI, slight SBI showed better 5-year overall survival (OS) (81.5% vs. 92.3%, p = 0.001) and progression-free survival (PFS) (71.5% vs. 83.0%, p = 0.002). Additional IC therapy did not significantly improve OS and PFS in slight SBI. The proposed T category separated OS, PFS, and locoregional recurrence-free survival in T2 and T3 categories with statistical significance. An improved C-index for OS prediction was observed in the proposed T category with combined confounding factors, compared to the AJCC T staging system (0.725 vs. 0.713, p = 0.046). The survival benefits of IC were more obvious in the advanced stage. CONCLUSIONS: NPC patients with slight SBI were recommended to downstage to T2 category. The adjustment for T category enabled better prognostic stratification and guidance for IC use. KEY POINTS: • For nasopharyngeal carcinoma (NPC) patients in T3 category, slight skull base invasion was a significant positive predictor for OS and PFS. • NPC patients with slight SBI might not gain significant survival benefits from induction chemotherapy. • Downstaging slight SBI NPC patients to T2 category would make a more accurate risk stratification, improve the predicting performance in OS, and have a better guidance in the use of IC for patients in advanced stage.

Prognostic value of quantitative cervical nodal necrosis burden on MRI in nasopharyngeal carcinoma and its role as a stratification marker for induction chemotherapy.

OBJECTIVES: This study aimed to assess the prognostic value of quantitative cervical nodal necrosis (CNN) burden in N staging risk stratification in patients with nasopharyngeal carcinoma. METHODS: Univariate and multivariate Cox regression models evaluated the association between lymph node variables based on MRI images and survival. Revisions for the N classification system were proposed and compared to the 8th edition AJCC staging system using Harrell's concordance index (C-index). The survival outcomes of induction chemotherapy plus concurrent chemoradiotherapy (CCRT) and CCRT alone in patients with multiple CNNs were compared. RESULTS: In 1319 patients enrolled, CNN was not an independent prognostic factor for the main survival outcomes, but multiple CNNs (three or more necrotic nodes) were independent prognostic factors for distant metastasis-free survival (DMFS) (adjusted hazard ratio [HR], 2.05; p = 0.020) and progression-free survival (PFS) (HR, 1.78; p = 0.004), surpassing other nodal variables. On upgrading patients with multiple CNNs to revised N3 disease, the proposed N staging widened the differences in DMFS and PFS between N2 and N3 disease. The overall survival of patients with multiple CNNs who received CCRT plus induction chemotherapy was improved compared to that of those who received CCRT alone (76.1% vs. 55.7%; adjusted p = 0.030). CONCLUSIONS: Upgrading patients with multiple CNNs to stage N3 may improve prognostication of the current AJCC staging system. Multiple CNNs might be a potential marker for stratifying patients who would benefit from induction chemotherapy. KEY POINTS: • Quantitatively assessed the prognostic value of CNN burden in patients with NPC. • Upgrading patients with multiple CNNs to stage N3 may improve prognostication. • Multiple CNNs may be used as a stratification marker for induction chemotherapy.

Deep learning-based automatic segmentation of meningioma from multiparametric MRI for preoperative meningioma differentiation using radiomic features: a multicentre study.

OBJECTIVES: Develop and evaluate a deep learning-based automatic meningioma segmentation method for preoperative meningioma differentiation using radiomic features. METHODS: A retrospective multicentre inclusion of MR examinations (T1/T2-weighted and contrast-enhanced T1-weighted imaging) was conducted. Data from centre 1 were allocated to training (n = 307, age = 50.94 ± 11.51) and internal testing (n = 238, age = 50.70 ± 12.72) cohorts, and data from centre 2 external testing cohort (n = 64, age = 48.45 ± 13.59). A modified attention U-Net was trained for meningioma segmentation. Segmentation accuracy was evaluated by five quantitative metrics. The agreement between radiomic features from manual and automatic segmentations was assessed using intra class correlation coefficient (ICC). After univariate and minimum-redundancy-maximum-relevance feature selection, L1-regularized logistic regression models for differentiating between low-grade (I) and high-grade (II and III) meningiomas were separately constructed using manual and automatic segmentations; their performances were evaluated using ROC analysis. RESULTS: Dice of meningioma segmentation for the internal testing cohort were 0.94 ± 0.04 and 0.91 ± 0.05 for tumour volumes in contrast-enhanced T1-weighted and T2-weighted images, respectively; those for the external testing cohort were 0.90 ± 0.07 and 0.88 ± 0.07. Features extracted using manual and automatic segmentations agreed well, for both the internal (ICC = 0.94, interquartile range: 0.88-0.97) and external (ICC = 0.90, interquartile range: 0.78-70.96) testing cohorts. AUC of radiomic model with automatic segmentation was comparable with that of the model with manual segmentation for both the internal (0.95 vs. 0.93, p = 0.176) and external (0.88 vs. 0.91, p = 0.419) testing cohorts. CONCLUSIONS: The developed deep learning-based segmentation method enables automatic and accurate extraction of meningioma from multiparametric MR images and can help deploy radiomics for preoperative meningioma differentiation in clinical practice. KEY POINTS: • A deep learning-based method was developed for automatic segmentation of meningioma from multiparametric MR images. • The automatic segmentation method enabled accurate extraction of meningiomas and yielded radiomic features that were highly consistent with those that were obtained using manual segmentation. • High-grade meningiomas were preoperatively differentiated from low-grade meningiomas using a radiomic model constructed on features from automatic segmentation.

SeqSeg: A sequential method to achieve nasopharyngeal carcinoma segmentation free from background dominance.

Reliable nasopharyngeal carcinoma (NPC) segmentation plays an important role in radiotherapy planning. However, recent deep learning methods fail to achieve satisfactory NPC segmentation in magnetic resonance (MR) images, since NPC is infiltrative and typically has a small or even tiny volume with indistinguishable border, making it indiscernible from tightly connected surrounding tissues from immense and complex backgrounds. To address such background dominance problems, this paper proposes a sequential method (SeqSeg) to achieve accurate NPC segmentation. Specifically, the proposed SeqSeg is devoted to solving the problem at two scales: the instance level and feature level. At the instance level, SeqSeg is forced to focus attention on the tumor and its surrounding tissue through the deep Q-learning (DQL)-based NPC detection model by prelocating the tumor and reducing the scale of the segmentation background. Next, at the feature level, SeqSeg uses high-level semantic features in deeper layers to guide feature learning in shallower layers, thus directing the channel-wise and region-wise attention to mine tumor-related features to perform accurate segmentation. The performance of our proposed method is evaluated by extensive experiments on the large NPC dataset containing 1101 patients. The experimental results demonstrated that the proposed SeqSeg not only outperforms several state-of-the-art methods but also achieves better performance in multi-device and multi-center datasets.