Tumor volume definitions in head and neck squamous cell carcinoma - Comparing PET/MRI and histopathology.

BACKGROUND AND PURPOSE: In cancer treatment precise definition of the tumor volume is essential, but despite development in imaging modalities, this remains a challenge. Here, pathological tumor volumes from the surgical specimens were obtained and compared to tumor volumes defined from modern PET/MRI hybrid imaging. The purpose is to evaluate mismatch between the volumes defined from imaging and pathology was estimated and potential clinical impact. METHODS AND MATERIALS: Twenty-five patients with head and neck squamous cell carcinoma were scanned on an integrated PET/MRI system prior to surgery. Three gross tumor volumes (GTVs) from the primary tumor site were delineated defined from MRI (GTVMRI), PET (GTVPET) and one by utilizing both anatomical images and clinical information (GTVONCO). Twenty-five primary tumor specimens were extracted en bloc, scanned with PET/MRI and co-registered to the patient images. Each specimen was sectioned in blocks, sliced and stained with haematoxylin and eosin. All slices were digitalized and tumor delineated by a head and neck pathologist. The pathological tumor areas in all slices were interpolated yielding a pathological 3D tumor volume (GTVPATO). GTVPATOwas compared with the imaging GTV's and potential mismatch was estimated. RESULTS: Thirteen patients were included. The mean volume of GTVONCOwas larger than the GTV's defined from PET or MRI. The mean mismatch of the GTVPATOcompared to the GTVPET, GTVMRIand GTVONCOwas 31.9 %, 54.5 % and 27.9 % respectively, and the entire GTVPATO was only fully encompassed in GTVONCO in 1 of 13 patients. However, after the addition of a clinical 5 mm margin the GTVPATO was fully encompassed in GTVONCO in 11 out of 13 patients. CONCLUSIONS: Despite modern hybrid imaging modalities, a mismatch between imaging and pathological defined tumor volumes was observed in all patients.A 5 mm clinical margin was sufficient to ensure inclusion of the entire pathological volume in 11 out of 13 patients.

Deep learning for Dixon MRI-based attenuation correction in PET/MRI of head and neck cancer patients.

BACKGROUND: Quantitative whole-body PET/MRI relies on accurate patient-specific MRI-based attenuation correction (AC) of PET, which is a non-trivial challenge, especially for the anatomically complex head and neck region. We used a deep learning model developed for dose planning in radiation oncology to derive MRI-based attenuation maps of head and neck cancer patients and evaluated its performance on PET AC. METHODS: Eleven head and neck cancer patients, referred for radiotherapy, underwent CT followed by PET/MRI with acquisition of Dixon MRI. Both scans were performed in radiotherapy position. PET AC was performed with three different patient-specific attenuation maps derived from: (1) Dixon MRI using a deep learning network (PETDeep). (2) Dixon MRI using the vendor-provided atlas-based method (PETAtlas). (3) CT, serving as reference (PETCT). We analyzed the effect of the MRI-based AC methods on PET quantification by assessing the average voxelwise error within the entire body, and the error as a function of distance to bone/air. The error in mean uptake within anatomical regions of interest and the tumor was also assessed. RESULTS: The average (± standard deviation) PET voxel error was 0.0 ± 11.4% for PETDeep and -1.3 ± 21.8% for PETAtlas. The error in mean PET uptake in bone/air was much lower for PETDeep (-4%/12%) than for PETAtlas (-15%/84%) and PETDeep also demonstrated a more rapidly decreasing error with distance to bone/air affecting only the immediate surroundings (less than 1 cm). The regions with the largest error in mean uptake were those containing bone (mandible) and air (larynx) for both methods, and the error in tumor mean uptake was -0.6 ± 2.0% for PETDeep and -3.5 ± 4.6% for PETAtlas. CONCLUSION: The deep learning network for deriving MRI-based attenuation maps of head and neck cancer patients demonstrated accurate AC and exceeded the performance of the vendor-provided atlas-based method both overall, on a lesion-level, and in vicinity of challenging regions such as bone and air.

Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging-Based Radiation Therapy Planning of Patients With Head and Neck Cancer.

PURPOSE: Radiotherapy planning based only on positron emission tomography/magnetic resonance imaging (PET/MRI) lacks computed tomography (CT) information required for dose calculations. In this study, a previously developed deep learning model for creating synthetic CT (sCT) from MRI in patients with head and neck cancer was evaluated in 2 scenarios: (1) using an independent external dataset, and (2) using a local dataset after an update of the model related to scanner software-induced changes to the input MRI. METHODS AND MATERIALS: Six patients from an external site and 17 patients from a local cohort were analyzed separately. Each patient underwent a CT and a PET/MRI with a Dixon MRI sequence over either one (external) or 2 (local) bed positions. For the external cohort, a previously developed deep learning model for deriving sCT from Dixon MRI was directly applied. For the local cohort, we adapted the model for an upgraded MRI acquisition using transfer learning and evaluated it in a leave-one-out process. The sCT mean absolute error for each patient was assessed. Radiotherapy dose plans based on sCT and CT were compared by assessing relevant absorbed dose differences in target volumes and organs at risk. RESULTS: The MAEs were 78 ± 13 HU and 76 ± 12 HU for the external and local cohort, respectively. For the external cohort, absorbed dose differences in target volumes were within ± 2.3% and within ± 1% in 95% of the cases. Differences in organs at risk were <2%. Similar results were obtained for the local cohort. CONCLUSIONS: We have demonstrated a robust performance of a deep learning model for deriving sCT from MRI when applied to an independent external dataset. We updated the model to accommodate a larger axial field of view and software-induced changes to the input MRI. In both scenarios dose calculations based on sCT were similar to those of CT suggesting a robust and reliable method.

Intratumor heterogeneity is biomarker specific and challenges the association with heterogeneity in multimodal functional imaging in head and neck squamous cell carcinoma.

RATIONALE: Tumor biopsy cannot detect heterogeneity and an association between heterogeneity in functional imaging and molecular biology will have an impact on both diagnostics and treatment possibilities. PURPOSE: Multiparametric imaging can provide 3D information on functional aspects of a tumor and may be suitable for predicting intratumor heterogeneity. Here, we investigate the correlation between intratumor heterogeneity assessed with multiparametric imaging and multiple-biopsy immunohistochemistry. METHODS: In this prospective study, patients with primary or recurrent head and neck squamous cell carcinoma (HNSCC) underwent PET/MRI scanning prior to surgery. Tumors were removed en bloc and six core biopsies were used for immunohistochemical (IHC) staining with a predefined list of biomarkers: p40, p53, EGFR, Ki-67, GLUT1, VEGF, Bcl-2, CAIX, PD-L1. Intratumor heterogeneity of each IHC biomarker was quantified by calculating the coefficient of variation (CV) in tumor proportion score among the six core biopsies within each tumor lesion. The heterogeneity in the imaging biomarkers was assessed by calculating CV in 18F-fluorodeoxyglucose (FDG)-uptake, diffusion and perfusion. Concordance of the two variance measures was quantified using Spearman's rank correlation RESULTS: Twenty-eight patients with a total of 33 lesions were included. There was considerable heterogeneity in most of the IHC biomarkers especially in GLUT1, PD-L1, Ki-67, CAIX and p53, however we only observed a correlation between the heterogeneity in GLUT1 and p53 and between Ki-67 and EGFR. Heterogeneity in FDG uptake and diffusion correlated with heterogeneity in cell density. CONCLUSION: Considerable heterogeneity of IHC biomarkers was found, however, only few and weak correlations between the studied IHC markers were observed. The studied functional imaging biomarkers showed weak associations with heterogeneity in some of the IHC biomarkers. Thus, biological heterogeneity is not a general tumor characteristic but depends on the specific biomarker or imaging modality.

Feasibility of Multiparametric Positron Emission Tomography/Magnetic Resonance Imaging as a One-Stop Shop for Radiation Therapy Planning for Patients with Head and Neck Cancer.

PURPOSE: Multiparametric positron emission tomography (PET)/magnetic resonance imaging (MRI) as a one-stop shop for radiation therapy (RT) planning has great potential but is technically challenging. We studied the feasibility of performing multiparametric PET/MRI of patients with head and neck cancer (HNC) in RT treatment position. As a step toward planning RT based solely on PET/MRI, a deep learning approach was employed to generate synthetic computed tomography (sCT) from MRI. This was subsequently evaluated for dose calculation and PET attenuation correction (AC). METHODS AND MATERIALS: Eleven patients, including 3 pilot patients referred for RT of HNC, underwent PET/MRI in treatment position after a routine fluorodeoxyglucose-PET/CT planning scan. The PET/MRI scan protocol included multiparametric imaging. A convolutional neural network was trained in a leave-one-out process to predict sCT from the Dixon MRI. The clinical CT-based dose plans were recalculated on sCT, and the plans were compared in terms of relative differences in mean, maximum, near-maximum, and near-minimum absorbed doses for different volumes of interest. Comparisons between PET with sCT-based AC and PET with CT-based AC were assessed based on the relative differences in mean and maximum standardized uptake values (SUVmean and SUVmax) from the PET-positive volumes. RESULTS: All 11 patients underwent PET/MRI in RT treatment position. Apart from the 3 pilots, full multiparametric imaging was completed in 45 minutes for 7 out of 8 patients. One patient terminated the examination after 30 minutes. With the exception of 1 patient with an inserted tracheostomy tube, all dosimetric parameters of the sCT-based dose plans were within ±1% of the CT-based dose plans. For PET, the mean difference was 0.4 ± 1.2% for SUVmean and -0.5 ± 1.0% for SUVmax. CONCLUSIONS: Performing multiparametric PET/MRI of patients with HNC in RT treatment position was clinically feasible. The sCT generation resulted in AC of PET and dose calculations sufficiently accurate for clinical use. These results are an important step toward using multiparametric PET/MRI as a one-stop shop for personalized RT planning.