Information fusion for fully automated segmentation of head and neck tumors from PET and CT images

BACKGROUND

PET/CT images combining anatomic and metabolic data provide complementary information that can improve clinical task performance. PET image segmentation algorithms exploiting the multi-modal information available are still lacking.

PURPOSE

Our study aimed to assess the performance of PET and CT image fusion for gross tumor volume (GTV) segmentations of head and neck cancers (HNCs) utilizing conventional, deep learning (DL), and output-level voting-based fusions.

METHODS

The current study is based on a total of 328 histologically confirmed HNCs from six different centers. The images were automatically cropped to a 200 × 200 head and neck region box, and CT and PET images were normalized for further processing. Eighteen conventional image-level fusions were implemented. In addition, a modified U2-Net architecture as DL fusion model baseline was used. Three different input, layer, and decision-level information fusions were used. Simultaneous truth and performance level estimation (STAPLE) and majority voting to merge different segmentation outputs (from PET and image-level and network-level fusions), that is, output-level information fusion (voting-based fusions) were employed. Different networks were trained in a 2D manner with a batch size of 64. Twenty percent of the dataset with stratification concerning the centers (20% in each center) were used for final result reporting. Different standard segmentation metrics and conventional PET metrics, such as SUV, were calculated.

RESULTS

In single modalities, PET had a reasonable performance with a Dice score of 0.77 ± 0.09, while CT did not perform acceptably and reached a Dice score of only 0.38 ± 0.22. Conventional fusion algorithms obtained a Dice score range of [0.76-0.81] with guided-filter-based context enhancement (GFCE) at the low-end, and anisotropic diffusion and Karhunen-Loeve transform fusion (ADF), multi-resolution singular value decomposition (MSVD), and multi-level image decomposition based on latent low-rank representation (MDLatLRR) at the high-end. All DL fusion models achieved Dice scores of 0.80. Output-level voting-based models outperformed all other models, achieving superior results with a Dice score of 0.84 for Majority_ImgFus, Majority_All, and Majority_Fast. A mean error of almost zero was achieved for all fusions using SUVpeak , SUVmean and SUVmedian .

CONCLUSION

PET/CT information fusion adds significant value to segmentation tasks, considerably outperforming PET-only and CT-only methods. In addition, both conventional image-level and DL fusions achieve competitive results. Meanwhile, output-level voting-based fusion using majority voting of several algorithms results in statistically significant improvements in the segmentation of HNC.

A qualitative study of improving megavoltage computed tomography image quality and maintaining dose accuracy using cycleGAN-based image synthesis

BACKGROUND

Due to inconsistent positioning, tumor shrinking, and weight loss during fractionated treatment, the initial plan was no longer appropriate after a few fractional treatments, and the patient will require adaptive helical tomotherapy (HT) to overcome the issue. Patients are scanned with megavoltage computed tomography (MVCT) before each fractional treatment, which is utilized for patient setup and provides information for dose reconstruction. However, the low contrast and high noise of MVCT make it challenging to delineate treatment targets and organs at risk (OAR).

PURPOSE

This study developed a deep-learning-based approach to generate high-quality synthetic kilovoltage computed tomography (skVCT) from MVCT and meet clinical dose requirements.

METHODS

Data from 41 head and neck cancer patients were collected; 25 (2995 slices) were used for training, and 16 (1898 slices) for testing. A cycle generative adversarial network (cycleGAN) based on attention gate and residual blocks was used to generate MVCT-based skVCT. For the 16 patients, kVCT-based plans were transferred to skVCT images and electron density profile-corrected MVCT images to recalculate the dose. The quantitative indices and clinically relevant dosimetric metrics, including the mean absolute error (MAE), structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), gamma passing rates, and dose-volume-histogram (DVH) parameters (Dmax , Dmean , Dmin ), were used to assess the skVCT images.

RESULTS

The MAE, PSNR, and SSIM of MVCT were 109.6 ± 12.3 HU, 27.5 ± 1.1 dB, and 91.9% ± 1.7%, respectively, while those of skVCT were 60.6 ± 9.0 HU, 34.0 ± 1.9 dB, and 96.5% ± 1.1%. The image quality and contrast were enhanced, and the noise was reduced. The gamma passing rates improved from 98.31% ± 1.11% to 99.71% ± 0.20% (2 mm/2%) and 99.77% ± 0.18% to 99.98% ± 0.02% (3 mm/3%). No significant differences (p > 0.05) were observed in DVH parameters between kVCT and skVCT.

CONCLUSION

With training on a small data set (2995 slices), the model successfully generated skVCT with improved image quality, and the dose calculation accuracy was similar to that of MVCT. MVCT-based skVCT can increase treatment accuracy and offer the possibility of implementing adaptive radiotherapy.

Imaging Characteristics Predictive of Cervical Extranodal Tumor Extension in Patients With Head and Neck Squamous Cell Carcinoma

OBJECTIVES

The aims of the study were to determine the predictive imaging findings of extranodal extension (ENE) in metastatic cervical lymph nodes of head and neck squamous cell carcinoma and to investigate the interobserver agreement among radiologists with different experience levels.

MATERIALS AND METHODS

Patients with cervical lymph node dissection and who had metastatic lymph nodes and preoperative imaging were included. Three radiologists evaluated nodal necrosis, irregular contour, gross invasion, and perinodal fat stranding. They also noted their overall impression regarding the presence of the ENE. Sensitivity, specificity, odds ratios based on logistic regression, and interobserver agreement of ENE status were calculated.

RESULTS

Of 106 lymph nodes (that met inclusion criteria), 31 had radiologically determined ENE. On pathologic examination, 22 of 31 nodes were positive for ENE. The increasing number of metastatic lymph nodes was associated with the presence of the ENE ( P = 0.010). Irregular contour had the highest sensitivity (78.6%) and gross invasion had the highest specificity (96%) for the determination of the ENE. The radiologists' impression regarding the presence of the pathlogical ENE had 39.3% sensitivity and 82% specificity. Metastatic lymph nodes with a perinodal fat stranding and with the longest diameter of greater than 2 cm were found to be strong predictors of the ENE. The gross invasion demonstrated the highest κ value (0.731) among the evaluated imaging criteria.

CONCLUSIONS

In the assessment of ENE, the gross invasion had the highest specificity among imaging features and showed the highest interobserver agreement. Perinodal fat stranding and the longest diameter of greater than 2 cm in a metastatic lymph node were the best predictors of the ENE.

Imaging of the Posttreatment Head and Neck: Expected Findings and Potential Complications

Interpretation of posttreatment imaging findings in patients with head and neck cancer can pose a substantial challenge. Malignancies in this region are often managed through surgery, radiation therapy, chemotherapy, and newer approaches like immunotherapy. After treatment, patients may experience various expected changes, including mucositis, soft-tissue inflammation, laryngeal edema, and salivary gland inflammation. Imaging techniques such as CT, MRI, and PET scans help differentiate these changes from tumor recurrence. Complications such as osteoradionecrosis, chondroradionecrosis, and radiation-induced vasculopathy can arise because of radiation effects. Radiation-induced malignancies may occur in the delayed setting. This review article emphasizes the importance of posttreatment surveillance imaging to ensure proper care of patients with head and neck cancer and highlights the complexities in distinguishing between expected treatment effects and potential complications. Keywords: CT, MR Imaging, Radiation Therapy, Ear/Nose/Throat, Head/Neck, Nervous-Peripheral, Bone Marrow, Calvarium, Carotid Arteries, Jaw, Face, Larynx © RSNA, 2024.

Impact of systematic dynamic maneuvers during computed tomography scan on the T classification of head and neck cancers

OBJECTIVES

To evaluate the impact of systematic dynamic maneuvers during CT scan on the T-staging of head and neck cancer (HNC).

MATERIALS AND METHODS

CT scans from the initial workup of 443 consecutive patients treated for HNC in our institution were retrospectively analyzed. CT scans were performed in both expert centers (comprehensive cancer center and university hospital) and non-expert centers. We noted whether dynamic maneuvers (DM) were performed, in 3 categories, namely: DM not done (DMND), done and inadequate (DMDI), done and adequate (DMDA). In the group with DMDA, T-stage was evaluated without and with DM. Interobserver agreement for T staging was assessed after independent double reading of CT scans with and without DM by two radiologists in a random sample.

RESULTS

Among the 443 CT scans, DMND was observed in 36.3%, DMDI in 9.3% and DMDA in 54.4%. DMDA were significantly more frequent in expert than in non-expert centers (93.4 vs 6.6%, p < 0.001). In CT scans with DMDA, analysis of the 141 scans rated as T1, T2, T3, or T4 without DM showed agreement of 88.7% with scans with DM, corresponding to a reclassification rate of 11.3% (kappa = 0.85, 95%CI [0.78;0.92]). Among lesions initially classed as Tx without DM (N = 100), the reclassification rate was 76% including DM.

CONCLUSION

The performance of systematic DM integrated into CT protocols is useful to reclassify the T stage in HNC and is essential in case of lesions initially classified as Tx without DM. DM should be performed routinely in expert and nonexpert centers.

A Novel Immobilization Method for the Treatment of Head and Neck Cancer Using 3D Printing

Proper immobilization is critical for the delivery of high-quality radiation therapy. In cases when traditional immobilization is not feasible, 3-dimensional (3D) printing may provide a better-tolerated custom immobilization that is comparably effective. We present the successful treatment of a patient with inoperable oropharyngeal squamous cell carcinoma who was unable to tolerate traditional immobilization. To avoid covering the face, we created a 3D-printed cradle for the back of his head and neck. This design enabled the patient to tolerate traditional simulation scans with and without intravenous contrast and was subsequently able to undergo volumetric modulated arc therapy treatment. He successfully underwent treatment without evidence of disease more than 2 years after completion. The effect of 3D printing within the context of radiation oncology, as well as in other specialties, will undoubtedly continue to increase the variety of treatment options available to patients.

Sentinel lymph node biopsy for head and neck malignancies utilizing simultaneous radioisotope gamma probe and indocyanine green fluorescence navigation

We depict an innovative surgical approach for sentinel lymph node biopsy (SLNB) in head and neck malignancies that utilizes both near-infrared (NIR) imaging with indocyanine green (ICG) dye and hand-held gamma probe intraoperatively to isolate and excise SLNs. Twenty-one patients presented to our institution with cutaneous melanoma, cutaneous squamous cell carcinoma (SCC), and oral cavity SCC tumors that met criteria for SLNB based on tumor depth and histology. The video offers a step-by-step approach for this technique along with descriptions of recommended equipment. Among 21 patients, two patients had positive SLNs on final pathology. One patient developed a local recurrence over an average of 16.2 months of follow-up (SD = 15.6). SLNB with ICG and radionucleotide co-localization may enhance the identification of sentinel nodes without compromising outcomes in the hands of surgeons well-versed in the technique.

Evaluating the Elasticity of Metastatic Cervical Lymph Nodes in Head and Neck Squamous Cell Carcinoma Patients Using DWI-based Virtual MR Elastography

PURPOSE

The assessment of metastatic cervical lymph nodes in head and neck squamous cell carcinoma patients is crucial; as such, many studies focusing on non-invasive imaging techniques to evaluate metastatic cervical lymph nodes have been performed. The aim of our study was to assess the usefulness of elasticity values on diffusion weighted imaging (DWI)-based virtual MR elastography in the evaluation of metastatic cervical lymph nodes from head and neck squamous cell carcinoma.

METHODS

Two head and neck radiologists measured the elasticity values of 16 metastatic cervical lymph nodes from head and neck squamous cell carcinoma and 13 benign cervical lymph nodes on DWI-based virtual MR elastography maps. Mean, minimum, maximum, and median elasticity values were evaluated for lymph nodes between the two groups and interobserver agreement in measuring the elasticity was also evaluated.

RESULTS

The mean, maximum, and median elasticity values of metastatic cervical lymph nodes were significantly higher than those of benign cervical lymph nodes (P = 0.001, 0.01, and 0.002, respectively). Diagnostic accuracy, sensitivity, and specificity of the mean elasticity were 82.8%, 93.8%, and 69.2%, respectively. Interobserver agreement was excellent for the mean and median elasticity (intraclass correlation coefficients were 0.98 for both).

CONCLUSION

Estimated elasticity values based on DWI-based virtual MR elastography show significant difference between benign and metastatic cervical lymph nodes from head and neck squamous cell carcinoma. While precise modulation of MR sequences and calibration parameters still needs to be established, elasticity values can be useful in differentiating between these lymph nodes.

Comparison of Doppler Imaging and Microvascular Imaging in Cervical Lymph Node Blood Flow Analysis

Cervical lymph node metastasis is an important determinant of cancer stage and the selection of an appropriate treatment plan for patients with head and neck cancer. Therefore, metastatic cervical lymph nodes should be effectively differentiated from lymphoma, tuberculous lymphadenitis, and other benign lymphadenopathies. The aim of this work is to describe the performance of Doppler ultrasound and superb microvascular imaging (SMI) in evaluating blood flow information of cervical lymph nodes. In addition, the features of flow imaging in metastatic lymph nodes, lymphoma, and tuberculous lymphadenitis were described. Compared with Doppler ultrasound, SMI, the latest blood flow imaging technology, could detect more blood flow signals because the sensitivity, specificity, and accuracy of SMI in the diagnosis of cervical lymph node disease were higher. This article summarizes the value of Doppler ultrasound and SMI in evaluating cervical lymph node diseases and focuses on the diagnostic performance of SMI.

Investigation of autosegmentation techniques on T2-weighted MRI for off-line dose reconstruction in MR-linac workflow for head and neck cancers

BACKGROUND

In order to accurately accumulate delivered dose for head and neck cancer patients treated with the Adapt to Position workflow on the 1.5T magnetic resonance imaging (MRI)-linear accelerator (MR-linac), the low-resolution T2-weighted MRIs used for daily setup must be segmented to enable reconstruction of the delivered dose at each fraction.

PURPOSE

In this pilot study, we evaluate various autosegmentation methods for head and neck organs at risk (OARs) on on-board setup MRIs from the MR-linac for off-line reconstruction of delivered dose.

METHODS

Seven OARs (parotid glands, submandibular glands, mandible, spinal cord, and brainstem) were contoured on 43 images by seven observers each. Ground truth contours were generated using a simultaneous truth and performance level estimation (STAPLE) algorithm. Twenty total autosegmentation methods were evaluated in ADMIRE: 1-9) atlas-based autosegmentation using a population atlas library (PAL) of 5/10/15 patients with STAPLE, patch fusion (PF), random forest (RF) for label fusion; 10-19) autosegmentation using images from a patient's 1-4 prior fractions (individualized patient prior [IPP]) using STAPLE/PF/RF; 20) deep learning (DL) (3D ResUNet trained on 43 ground truth structure sets plus 45 contoured by one observer). Execution time was measured for each method. Autosegmented structures were compared to ground truth structures using the Dice similarity coefficient, mean surface distance (MSD), Hausdorff distance (HD), and Jaccard index (JI). For each metric and OAR, performance was compared to the inter-observer variability using Dunn's test with control. Methods were compared pairwise using the Steel-Dwass test for each metric pooled across all OARs. Further dosimetric analysis was performed on three high-performing autosegmentation methods (DL, IPP with RF and 4 fractions [IPP_RF_4], IPP with 1 fraction [IPP_1]), and one low-performing (PAL with STAPLE and 5 atlases [PAL_ST_5]). For five patients, delivered doses from clinical plans were recalculated on setup images with ground truth and autosegmented structure sets. Differences in maximum and mean dose to each structure between the ground truth and autosegmented structures were calculated and correlated with geometric metrics.

RESULTS

DL and IPP methods performed best overall, all significantly outperforming inter-observer variability and with no significant difference between methods in pairwise comparison. PAL methods performed worst overall; most were not significantly different from the inter-observer variability or from each other. DL was the fastest method (33 s per case) and PAL methods the slowest (3.7-13.8 min per case). Execution time increased with a number of prior fractions/atlases for IPP and PAL. For DL, IPP_1, and IPP_RF_4, the majority (95%) of dose differences were within ± 250 cGy from ground truth, but outlier differences up to 785 cGy occurred. Dose differences were much higher for PAL_ST_5, with outlier differences up to 1920 cGy. Dose differences showed weak but significant correlations with all geometric metrics (R2 between 0.030 and 0.314).

CONCLUSIONS

The autosegmentation methods offering the best combination of performance and execution time are DL and IPP_1. Dose reconstruction on on-board T2-weighted MRIs is feasible with autosegmented structures with minimal dosimetric variation from ground truth, but contours should be visually inspected prior to dose reconstruction in an end-to-end dose accumulation workflow.

Deep learning for diagnosis of head and neck cancers through radiographic data: a systematic review and meta-analysis

PURPOSE

This study aims to review deep learning applications for detecting head and neck cancer (HNC) using magnetic resonance imaging (MRI) and radiographic data.

METHODS

Through January 2023, a PubMed, Scopus, Embase, Google Scholar, IEEE, and arXiv search were carried out. The inclusion criteria were implementing head and neck medical images (computed tomography (CT), positron emission tomography (PET), MRI, Planar scans, and panoramic X-ray) of human subjects with segmentation, object detection, and classification deep learning models for head and neck cancers. The risk of bias was rated with the quality assessment of diagnostic accuracy studies (QUADAS-2) tool. For the meta-analysis diagnostic odds ratio (DOR) was calculated. Deeks' funnel plot was used to assess publication bias. MIDAS and Metandi packages were used to analyze diagnostic test accuracy in STATA.

RESULTS

From 1967 studies, 32 were found eligible after the search and screening procedures. According to the QUADAS-2 tool, 7 included studies had a low risk of bias for all domains. According to the results of all included studies, the accuracy varied from 82.6 to 100%. Additionally, specificity ranged from 66.6 to 90.1%, sensitivity from 74 to 99.68%. Fourteen studies that provided sufficient data were included for meta-analysis. The pooled sensitivity was 90% (95% CI 0.820.94), and the pooled specificity was 92% (CI 95% 0.87-0.96). The DORs were 103 (27-251). Publication bias was not detected based on the p-value of 0.75 in the meta-analysis.

CONCLUSION

With a head and neck screening deep learning model, detectable screening processes can be enhanced with high specificity and sensitivity.

The Use of MR-Guided Radiation Therapy for Head and Neck Cancer and Recommended Reporting Guidance

Although magnetic resonance imaging (MRI) has become standard diagnostic workup for head and neck malignancies and is currently recommended by most radiological societies for pharyngeal and oral carcinomas, its utilization in radiotherapy has been heterogeneous during the last decades. However, few would argue that implementing MRI for annotation of target volumes and organs at risk provides several advantages, so that implementation of the modality for this purpose is widely accepted. Today, the term MR-guidance has received a much broader meaning, including MRI for adaptive treatments, MR-gating and tracking during radiotherapy application, MR-features as biomarkers and finally MR-only workflows. First studies on treatment of head and neck cancer on commercially available dedicated hybrid-platforms (MR-linacs), with distinct common features but also differences amongst them, have also been recently reported, as well as "biological adaptation" based on evaluation of early treatment response via functional MRI-sequences such as diffusion weighted ones. Yet, all of these approaches towards head and neck treatment remain at their infancy, especially when compared to other radiotherapy indications. Moreover, the lack of standardization for reporting MR-guided radiotherapy is a major obstacle both to further progress in the field and to conduct and compare clinical trials. Goals of this article is to present and explain all different aspects of MR-guidance for radiotherapy of head and neck cancer, summarize evidence, as well as possible advantages and challenges of the method and finally provide a comprehensive reporting guidance for use in clinical routine and trials.

Diagnostic Utility of Restriction Spectrum Imaging in Head and Neck Tumors: A Pilot Study

OBJECTIVE

Imaging is crucial in the assessment of head and neck cancers for site, extension, and enlarged lymph nodes. Restriction spectrum imaging (RSI) is a new diffusion-weighted magnetic resonance imaging (MRI) technique that enhances the ability to differentiate aggressive cancer from low-grade or benign tumors and helps guide treatment and biopsy. Its contribution to imaging of brain and prostate tumors has been previously published. However, there are no prior studies using RSI sequence in head and neck tumors. The purpose of this study was to evaluate the feasibility of performing RSI in head and neck cancer.

METHODS

An additional RSI sequence was added in the routine MRI neck protocol for 13 patients diagnosed with head and neck cancer between November 2018 and April 2019. Restriction spectrum imaging sequence was performed with b values of 0, 500, 1500, and 3000 s/mm 2 and 29 directions on 1.5T magnetic resonance scanners.Diffusion-weighted imaging (DWI) images and RSI images were compared according to their ability to detect the primary malignancy and possible metastatic lymph nodes.

RESULTS

In 71% of the patients, RSI outperformed DWI in detecting the primary malignancy and possible metastatic lymph nodes, whereas in the remaining cases, the 2 were comparable. In 66% of the patients, RSI detected malignant lymph nodes that DWI/apparent diffusion coefficient failed to detect.

CONCLUSIONS

This is the first study of RSI in head and neck imaging and showed its superiority over the conventional DWI sequence. Because of its ability to differentiate benign and malignant lymph nodes in some cases, the addition of RSI to routine head and neck MRI should be considered.

Ultrasound diagnosis and treatment of branchial cleft cyst and preoperative management

OBJECTIVE

The ultrasonic diagnosis of cervical and facial cystic masses, as well as cases of missed diagnosis and misdiagnosis, was examined, to improve the diagnosis of branchial cleft anomalies.

METHODS

A retrospective analysis was conducted on 17 patients with branchial cleft cyst anomalies, including 11 males and 6 females, aged 12-53 years, with an average age of 33 ± 2 years, were unilateral single. All patients who underwent an ultrasound examination and image storage for retrospective analysis, and both longitudinal and transverse sections were scanned to observe the shape, size, boundary, peripheral relationship, and blood flow signal of the masses. All cases were examined with an enhanced CT scan, and pathological reports were generated.

RESULTS

Among the 17 cases of branchial cleft anomalies, 15 cases were branchial cleft cysts, while one case involved fistula formation and one case involved sinus tract formation. Based on the type of branchial cleft, the first, second, and third cysts were classified in 4, 12, and 1 case, respectively. The sensitivity rate and specificity of ultrasonic diagnosis were 14/17 (82.4%) and 4/6 (66.7%), respectively. Ultrasonic characteristic analysis for the masses can be found in simple cystic masses or hypoechoic masses, most of them are of a regular shape and have a distinct boundary, and almost no blood flow signal. All patients who were misdiagnosed exhibited blood flow signals, including 1 patient with an abundant blood flow signal, 1 patient suspected of having ectopic thyroid with an abnormal function due to the rat-tail sign, 2 patients misdiagnosed as local inflammatory focus, and 1 patient misdiagnosed with tuberculous lymphadenitis.

CONCLUSION

Ultrasound has a detection rate of up to 100% for cervical and facial masses, providing a fundamental determination of lesion characteristics and specific guidance for preoperative diagnosis. If the blood flow signals can be identified and carefully considered their peripheral relationship, the diagnostic rate can be improved.

Stratifying risk of malignancy in cystic lateral neck lumps: a multivariant analysis of demographic, radiological and histological investigation factors and the development of a patient-centred risk-predictive tool for malignancy

BACKGROUND

Management of lateral cystic neck masses with no apparent upper aerodigestive tract primary tumour in adults is controversial. Imaging modalities and fine needle aspiration cytology often struggle to distinguish the presence of malignancy.

METHOD

This study entailed a multicentre retrospective review of all patients with isolated lateral cystic neck masses from 2012 to 2018 in three Welsh health boards, utilising demographic data and first-line investigations (ultrasound scanning and fine needle aspiration cytology) to develop an evidence-based predictive tool for risk of malignancy.

RESULTS

It was found that 29.1 per cent of cystic lesions were malignant on final histology. Age, male gender, non-benign ultrasound scan findings and fine needle aspiration cytology were significant risk factors on univariate analysis. The final multivariate analysis predicted a risk of malignancy ranging from 2.1 to 65.0 per cent depending on the covariate pattern. Smoking status was non-significant.

CONCLUSION

A rigorous, risk-stratified approach to the management of these patients should aid the clinician in minimising morbidity and optimising resources.

Polarized hyperspectral microscopic imaging system for enhancing the visualization of collagen fibers and head and neck squamous cell carcinoma

Significance

Polarized hyperspectral microscopes with the capability of full Stokes vector imaging have potential for many biological and medical applications.

Aim

The aim of this study is to investigate polarized hyperspectral imaging (PHSI) for improving the visualization of collagen fibers, which is an important biomarker related to tumor development, and improving the differentiation of normal and tumor cells on pathologic slides.

Approach

We customized a polarized hyperspectral microscopic imaging system comprising an upright microscope with a motorized stage, two linear polarizers, two liquid crystal variable retarders (LCVRs), and a compact SnapScan hyperspectral camera. The polarizers and LCVRs worked in tandem with the hyperspectral camera to acquire polarized hyperspectral images, which were further used to calculate four Stokes vectors: S 0 , S 1 , S 2 , and S 3 . Synthetic RGB images of the Stokes vectors were generated for the visualization of cellular components in PHSI images. Regions of interest of collagen, normal cells, and tumor cells in the synthetic RGB images were selected, and spectral signatures of the selected components were extracted for comparison. Specifically, we qualitatively and quantitatively investigated the enhanced visualization and spectral characteristics of dense fibers and sparse fibers in normal stroma tissue, fibers accumulated within tumors, and fibers accumulated around tumors.

Results

By employing our customized polarized hyperspectral microscope, we extract the spectral signatures of Stokes vector parameters of collagen as well as of tumor and normal cells. The measurement of Stokes vector parameters increased the image contrast of collagen fibers and cells in the slides.

Conclusions

With the spatial and spectral information from the Stokes vector data cubes (S 0 , S 1 , S 2 , and S 3 ), our PHSI microscope system enhances the visualization of tumor cells and tumor microenvironment components, thus being beneficial for pathology and oncology.

T1 and T2 mapping for identifying malignant lymph nodes in head and neck squamous cell carcinoma

BACKGROUND

This study seeks to assess the utility of T1 and T2 mapping in distinguishing metastatic lymph nodes from reactive lymphadenopathy in patients with head and neck squamous cell carcinoma (HNSCC), using diffusion-weighted imaging (DWI) as a comparison.

METHODS

Between July 2017 and November 2019, 46 HNSCC patients underwent neck MRI inclusive of T1 and T2 mapping and DWI. Quantitative measurements derived from preoperative T1 and T2 mapping and DWI of metastatic and non-metastatic lymph nodes were compared using independent samples t-test or Mann-Whitney U test. Receiver operating characteristic curves and the DeLong test were employed to determine the most effective diagnostic methodology.

RESULTS

We examined a total of 122 lymph nodes, 45 (36.9%) of which were metastatic proven by pathology. Mean T2 values for metastatic lymph nodes were significantly lower than those for benign lymph nodes (p < 0.001). Conversely, metastatic lymph nodes exhibited significantly higher apparent diffusion coefficient (ADC) and standard deviation of T1 values (T1SD) (p < 0.001). T2 generated a significantly higher area under the curve (AUC) of 0.890 (0.826-0.954) compared to T1SD (0.711 [0.613-0.809]) and ADC (0.660 [0.562-0.758]) (p = 0.007 and p < 0.001). Combining T2, T1SD, ADC, and lymph node size achieved an AUC of 0.929 (0.875-0.983), which did not significantly enhance diagnostic performance over using T2 alone (p = 0.089).

CONCLUSIONS

The application of T1 and T2 mapping is feasible in differentiating metastatic from non-metastatic lymph nodes in HNSCC and can improve diagnostic efficacy compared to DWI.

Fully-automated, CT-only GTV contouring for palliative head and neck radiotherapy

Planning for palliative radiotherapy is performed without the advantage of MR or PET imaging in many clinics. Here, we investigated CT-only GTV delineation for palliative treatment of head and neck cancer. Two multi-institutional datasets of palliative-intent treatment plans were retrospectively acquired: a set of 102 non-contrast-enhanced CTs and a set of 96 contrast-enhanced CTs. The nnU-Net auto-segmentation network was chosen for its strength in medical image segmentation, and five approaches separately trained: (1) heuristic-cropped, non-contrast images with a single GTV channel, (2) cropping around a manually-placed point in the tumor center for non-contrast images with a single GTV channel, (3) contrast-enhanced images with a single GTV channel, (4) contrast-enhanced images with separate primary and nodal GTV channels, and (5) contrast-enhanced images along with synthetic MR images with separate primary and nodal GTV channels. Median Dice similarity coefficient ranged from 0.6 to 0.7, surface Dice from 0.30 to 0.56, and 95th Hausdorff distance from 14.7 to 19.7 mm across the five approaches. Only surface Dice exhibited statistically-significant difference across these five approaches using a two-tailed Wilcoxon Rank-Sum test (p ≤ 0.05). Our CT-only results met or exceeded published values for head and neck GTV autocontouring using multi-modality images. However, significant edits would be necessary before clinical use in palliative radiotherapy.

The Effects of Human Papillomavirus Status and Treatment on the Positive Predictive Value of Post-radiotherapy 18F-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography in Advanced Head and Neck Squamous Cell Carcinoma

AIMS

The high negative predictive value of post-chemoradiation (CRT) positron emission tomography-computed tomography (PET-CT) is well established in head and neck squamous cell cancers (HNSCC). The positive predictive value (PPV) remains under scrutiny, with increasing evidence that it is affected by several factors. The aim of this study was to assess the PPV of post-treatment PET-CT for residual nodal disease when stratified by treatment modality and tumour human papillomavirus (HPV) status.

MATERIALS AND METHODS

This was a retrospective cohort study in a tertiary oncology centre carried out between January 2013 and December 2019. Patients were radically treated with radiotherapy only/CRT for node-positive HNSCC. PET-CT nodal responses were categorised as complete, equivocal (EQR) or incomplete (ICR), and outcomes extracted from electronic records.

RESULTS

In total, 480 patients were evaluated, all had a minimum potential follow-up of 2 years, with a median of 39.2 months. The PPV of 12-week PET-CT was significantly different between HPV-positive (22.5%) and HPV-unrelated (52.7%) disease, P < 0.001. It was also significantly different between the CRT (24.8%) and radiotherapy-only (51.1%) groups, P = 0.001. The PPV of an EQR was significantly less than an ICR, irrespective of HPV status and primary treatment modality. In HPV-positive disease, the PPV of an EQR was 9.0% for the CRT group compared with 21.4% for radiotherapy only, P = 0.278. The PPV in those who achieved an ICR was 34.2% in the CRT group, significantly lower than 70.0% in the radiotherapy-only group, P = 0.03.

CONCLUSION

The PPV of 12-week PET-CT is significantly lower for HPV-positive compared with HPV-unrelated HNSCC. It is poorer in patients with HPV-positive disease treated with CRT compared with radiotherapy alone.

Thoracic skeletal muscle index is effective for CT-defined sarcopenia evaluation in patients with head and neck cancer

PURPOSE

Computed tomography (CT)-defined sarcopenia, as a measurement of low skeletal muscle (SM), is a poor prognostic indicator in patients with head and neck cancer (HNC), independent of weight or nutritional status. We used SM measures at the second thoracic vertebra (T2) to determine T2-SM index (SMI) thresholds for sarcopenia, and investigate the impact of low T2-SMI on overall survival (OS), and weight loss during radiotherapy (RT).

METHODS

Adult patients with newly diagnosed HNC with a diagnostic PET-CT or RT planning CT scan were included. SM was analysed at T2 and a model applied to predict SM at L3. T2-SMI thresholds for sarcopenia were established with predicted measures, stratified by BMI and sex. Impact of sarcopenia and low T2-SMI on OS and weight loss during RT was investigated.

RESULTS

A total of 361 scans were analysed (84% males, 54% oropharynx tumours). Sarcopenia was found in 49%, demonstrating worse OS (p = 0.037). T2-SMI cutoff values were: females-74 cm2/m2 [area under the curve (AUC): 0.89 (95%CI 0.80-0.98)], males (BMI < 25)-63 cm2/m2 [AUC 0.93 (95%CI 0.89-0.96)], males (BMI ≥ 25)-88cm2/m2 [AUC 0.86 (95%CI 0.78-0.93)]. No difference in OS with T2-SMI categories. Lowest T2-SMI quartile of < 63 cm2/m2 demonstrated worse OS (p = 0.017). Weight loss during RT was higher in patients; who were not sarcopenic (6.2% vs 4.9%, p = 0.023); with higher T2-SMI (6.3% vs 4.9%, p = 0.014) and; in the highest quartiles (3.6% vs 5.7% vs 7.2%, p < 0.001).

CONCLUSIONS

These T2-SMI thresholds are effective in assessing CT-defined sarcopenia in HNC. Further assessment of clinical application is warranted.

Impact of consensus guidelines on delineation of primary tumor clinical target volume (CTVp) for head and neck cancer: Results of a national review project

BACKGROUND AND PURPOSE

A significant interobserver variability (IOV) for clinical target volume of the primary tumor (CTVp) delineation was shown in a previous national review project. Since then, international expert consensus guidelines (CG) for the delineation of CTVp were published. The aim of this follow-up study was to 1) objectify the extent of implementation of the CG, 2) assess its impact on delineation quality and consistency, 3) identify any remaining ambiguities.

MATERIALS AND METHODS

All Belgian RT departments were invited to complete an online survey and submit CTVp for 5 reference cases. Organs at risk and GTV of the primary tumor were predefined. Margins, volumes, IOV between all participating centers (IOVall) and IOV compared to a reference consensus delineation (IOVref) were calculated and compared to the previous analysis. A qualitative analysis was performed assessing the correct interpretation of the CG for each case.

RESULTS

17 RT centers completed both survey and delineations, of which 88% had implemented CG. Median DSCref for CTVp_total was 0.80-0.92. IOVall and IOVref improved significantly for the centers following CG (p = 0.005). IOVref for CTVp_high was small with a DSC higher than 0.90 for all cases. A significant volume decrease for the CTVp receiving 70 Gy was observed. Interpretation of CG was more accurate for (supra)glottic carcinoma. 60% of the radiation oncologists thinks clarification of CG is indicated.

CONCLUSION

Implementation of consensus guidelines for CTVp delineation is already fairly advanced on a national level, resulting in significantly increased delineation uniformity. The accompanying substantial decrease of CTV receiving high dose RT calls for caution and correct interpretation of CG. Clarification of the existing guidelines seems appropriate especially for oropharyngeal and hypopharyngeal carcinoma.

Comparative analysis of diagnostic ultrasound and histopathology for detecting cervical lymph node metastases in head and neck cancer

PURPOSE

We evaluated the current performance of diagnostic ultrasound (US) for detecting cervical lymph node (LN) metastases based on objective measures and subjective findings in comparison to the gold standard, histopathological evaluation.

PATIENTS AND METHODS

From 2007 to 2016, we prospectively included patients with head and neck cancer who were scheduled for surgical therapy including neck dissection. LNs were examined by multimodal US by a level III head and neck sonologist and individually assigned to a map containing six AAO-HNS neck LN levels preoperatively. During the operation, LNs were dissected and then assessed by routine histopathology, with 86% of them examined individually and the remaining LNs (14%) per AAO-HNS neck LN level. The optimal cutoff points (OCPs) of four defined LN diameters and 2D and 3D roundness indices per AAO-HNS neck LN level were determined.

RESULTS

In total, 235 patients were included, and 4539 LNs were analyzed by US, 7237 by histopathology and 2684 by both methods. Of these, 259 (9.65%) were classified as suspicious for metastasis by US, whereas 299 (11.14%) were found to be positive by histopathology. Subjective US sensitivity and specificity were 0.79 and 0.99, respectively. The OCPs of the individual LN diameters and the 2D and 3D roundness index were determined individually for all AAO-HNS neck LN levels. Across all levels, the OCP for the 2D index was 1.79 and the 3D index was 14.97. The predictive performance of all distances, indices, and subjective findings improved with increasing metastasis size. Anticipation of pN stage was best achieved with subjective US findings and the smallest diameter (Cohen's κ = 0.713 and 0.438, respectively).

CONCLUSION

Our LN mapping and meticulous 1:1 node-by-node comparison reveals the usefulness of US for detecting metastatic involvement of neck LNs in head and neck carcinomas as compared to histopathology. The predictive ability for small tumor deposits less than 8 mm in size remains weak and urgently needs improvement.

Advances in and applications of imaging and radiomics in head and neck cancer survivorship

PURPOSE OF REVIEW

Radiological imaging is an essential component of head/neck cancer (HNC) care. Advances in imaging modalities (including CT, PET, MRI and ultrasound) and analysis have enhanced our understanding of tumour characteristics and prognosis. However, the application of these methods to evaluate treatment-related toxicities and functional burden is still emerging. This review showcases recent literature applying advanced imaging and radiomics to the assessment and management of sequelae following chemoradiotherapy for HNC.

RECENT FINDINGS

Whilst primarily early-stage/exploratory studies, recent investigations have showcased the feasibility of using radiological imaging, particularly advanced/functional MRI (including diffusion-weighted and dynamic contrast-enhanced MRI), to quantify treatment-induced tissue change in the head/neck musculature, and the clinical manifestation of lymphoedema/fibrosis and dysphagia. Advanced feature analysis and radiomic studies have also begun to give specific focus to the prediction of functional endpoints, including dysphagia, trismus and fibrosis.

SUMMARY

There is demonstrated potential in the use of novel imaging techniques, to help better understand pathophysiology, and improve assessment and treatment of functional deficits following HNC treatment. As larger studies emerge, technologies continue to progress, and pathways to clinical translation are honed, the application of these methods offers an exciting opportunity to transform clinical practices and improve outcomes for HNC survivors.

Changes in serial multiparametric MRI and FDG-PET/CT functional imaging during radiation therapy can predict treatment response in patients with head and neck cancer

OBJECTIVES

To test if tumour changes measured using combination of diffusion-weighted imaging (DWI) MRI and FDG-PET/CT performed serially during radiotherapy (RT) in mucosal head and neck carcinoma can predict treatment response.

METHODS

Fifty-five patients from two prospective imaging biomarker studies were analysed. FDG-PET/CT was performed at baseline, during RT (week 3), and post RT (3 months). DWI was performed at baseline, during RT (weeks 2, 3, 5, 6), and post RT (1 and 3 months). The ADCmean from DWI and FDG-PET parameters SUVmax, SUVmean, metabolic tumour volume (MTV), and total lesion glycolysis (TLG) were measured. Absolute and relative change (%∆) in DWI and PET parameters were correlated to 1-year local recurrence. Patients were categorised into favourable, mixed, and unfavourable imaging response using optimal cut-off (OC) values of DWI and FDG-PET parameters and correlated to local control.

RESULTS

The 1-year local, regional, and distant recurrence rates were 18.2% (10/55), 7.3% (4/55), and 12.7% (7/55), respectively. ∆Week 3 ADCmean (AUC 0.825, p = 0.003; OC ∆ > 24.4%) and ∆MTV (AUC 0.833, p = 0.001; OC ∆ > 50.4%) were the best predictors of local recurrence. Week 3 was the optimal time point for assessing DWI imaging response. Using a combination of ∆ADCmean and ∆MTV improved the strength of correlation to local recurrence (p ≤ 0.001). In patients who underwent both week 3 MRI and FDG-PET/CT, significant differences in local recurrence rates were seen between patients with favourable (0%), mixed (17%), and unfavourable (78%) combined imaging response.

CONCLUSIONS

Changes in mid-treatment DWI and FDG-PET/CT imaging can predict treatment response and could be utilised in the design of future adaptive clinical trials.

CLINICAL RELEVANCE STATEMENT

Our study shows the complementary information provided by two functional imaging modalities for mid-treatment response prediction in patients with head and neck cancer.

KEY POINTS

•FDG-PET/CT and DWI MRI changes in tumour during radiotherapy in head and neck cancer can predict treatment response. •Combination of FDG-PET/CT and DWI parameters improved correlation to clinical outcome. •Week 3 was the optimal time point for DWI MRI imaging response assessment.

Dual-energy computed tomography for improved visualization of internal jugular chain neck lymph node metastasis and nodal necrosis in head and neck squamous cell carcinoma

PURPOSE

To evaluate and compare the utility of 40-keV virtual monochromatic imaging (VMI) reconstructed from dual-energy computed tomography (DECT) in the assessment of neck lymph node metastasis with 70-keV VMI, which is reportedly equivalent to conventional 120-kVp single-energy computed tomography.

MATERIALS AND METHODS

Patients with head and neck squamous cell carcinoma who had neck lymph node metastasis in contact with the sternocleidomastoid muscle (SCM) and underwent contrast-enhanced DECT were included. In 40- and 70-keV VMI, contrast differences and contrast noise ratio (CNR) between the solid component of neck lymph node metastasis (SC) and the SCM and between SC and nodal necrosis (NN) were calculated. Two board-certified radiologists independently and qualitatively evaluated the boundary discrimination between SC and SCM and the diagnostic certainty of NN.

RESULTS

We evaluated 45 neck lymph node metastases. The contrast difference between SC and SCM and SC and NN were significantly higher at 40-keV VMI than at 70-keV VMI (p < 0.001). The CNR between SC and SCM was significantly higher at 40-keV VMI than at 70-keV VMI (p < 0.001). Scoring of the boundary discrimination between SC and SCM as well as the diagnostic certainty of NN at 40-keV VMI was significantly higher than that at 70-keV VMI (p < 0.001). The inter-rater agreements for these scores were higher at 40-keV VMI than at 70-keV VMI.

CONCLUSION

Additional employing 40-keV VMI in routine clinical practice may be useful in the diagnosis of head and neck lymph node metastases and nodal necrosis.