Volume Of Interest Research Articles

Multi-Modal Ensemble Deep Learning in Head and Neck Cancer HPV Sub-Typing.

Oropharyngeal Squamous Cell Carcinoma (OPSCC) is one of the common forms of heterogeneity in head and neck cancer. Infection with human papillomavirus (HPV) has been identified as a major risk factor for OPSCC. Therefore, differentiating the HPV-positive and negative cases in OPSCC patients is an essential diagnostic factor influencing future treatment decisions. In this study, we investigated the accuracy of a deep learning-based method for image interpretation and automatically detected the HPV status of OPSCC in routinely acquired Computed Tomography (CT) and Positron Emission Tomography (PET) images. We introduce a 3D CNN-based multi-modal feature fusion architecture for HPV status prediction in primary tumor lesions. The architecture is composed of an ensemble of CNN networks and merges image features in a softmax classification layer. The pipeline separately learns the intensity, contrast variation, shape, texture heterogeneity, and metabolic assessment from CT and PET tumor volume regions and fuses those multi-modal features for final HPV status classification. The precision, recall, and AUC scores of the proposed method are computed, and the results are compared with other existing models. The experimental results demonstrate that the multi-modal ensemble model with soft voting outperformed single-modality PET/CT, with an AUC of 0.76 and F1 score of 0.746 on publicly available TCGA and MAASTRO datasets. In the MAASTRO dataset, our model achieved an AUC score of 0.74 over primary tumor volumes of interest (VOIs). In the future, more extensive cohort validation may suffice for better diagnostic accuracy and provide preliminary assessment before the biopsy.

Detectability of cold tumors by xSPECT bone technology compared with hot tumors: a supine phantom study.

Detecting cold as well as hot tumors is vital for interpreting bone tumors on single-photon emission computed tomography (SPECT) images. This study aimed to visually and quantitatively demonstrate the detectability of cold tumors using xSPECT technology compared with that of hot tumors in the phantom study. Five tumors of different sizes and normal bone contained a mixture of 99mTc and K2HPO4 in a spine phantom. We acquired SPECT data using an xSPECT protocol and transverse images were reconstructed using xSPECT Bone (xB) and xSPECT Quant (xQ). Mean standardized uptake values (SUVmean) in volumes of interest (VOI) were calculated. Recovery coefficients (RCs) for each tumor site were calculated with reference to radioactive concentrations. The SUVmeans of the whole vertebral body for hot tumor bone image in cortical bone phantom reconstructed by with xB and xQ were 5.77 and 4.86 respectively. The SUVmean of xB was similar to the true value. The SUVmeans for xB and xQ reconstructed images of cold tumors were both approximately 0.16. The RC of the cold tumor on xQ images increased as the tumor diameter decreased, whereas that of xB remained almost constant regardless of the tumor diameter. In conclusion, the quantitative accuracy of detecting hot and cold tumors was higher in the xB image than in the xQ image. Moreover, the visual detectability of cold tumors was also excellent in xB images.

Robustness of [18F]FDG PET/CT radiomic analysis in the setting of drug-induced cardiotoxicity

Background and objectivesStandardization of radiomic data acquisition protocols is still at a very early stage, revealing a strong need to work towards the definition of uniform image processing methodologies The aim of this study is to identify sources of variability in radiomic data derived from image discretization and resampling methodologies prior to image feature extraction. Furthermore, to identify robust potential image-based biomarkers for the early detection of cardiotoxicity. MethodsImage post-acquisition processing, interpolation, and volume of interest (VOI) segmentation were performed. Four experiments were conducted to assess the reliability in terms of the intraclass correlation coefficient (ICC) of the radiomic features and the effects of the variation of voxel size and gray level discretization. Statistical analysis was performed separating the patients according to cardiotoxicity diagnosis. Differences of texture features were studied with Mann-Whitney U test. P-values <0.05 after multiple testing correction were considered statistically significant. Additionally, a non-supervised k-Means clustering algorithm was evaluated. ResultsThe effect of the variation in the voxel size demonstrated a non-dependency relationship with the values of the radiomic features, regardless of the chosen discretization method. The median ICC values were 0.306 and 0.872 for absolute agreement and consistency, respectively, when varying the discretization bin number. The median ICC values were 0.678 and 0.878 for absolute agreement and consistency, respectively, when varying the discretization bin size. A total of 16 first order, 6 Gray Level Co-occurrence Matrix (GLCM), 4 Gray Level Dependence Matrix (GLDM) and 4 Gray Level Run Length Matrix (GLRLM) features demonstrated statistically significant differences between the diagnosis groups for interim scans (P<0.05) for the fixed bin size (FBS) discretization methodology. However, no statistically significant differences between diagnostic groups were found for the fixed bin number (FBN) discretization methodology. Two clusters based on the radiomic features were identified. ConclusionsGray level discretization has a major impact on the repeatability of the radiomic features. The selection of the optimal processing methodology has led to the identification of texture-based patterns for the differentiation of early cardiac damage profiles.

Breath-Hold-Triggered BOLD fMRI in Drug-Resistant Nonlesional Focal Epilepsy-APilot Study.

Individuals with drug-resistant epilepsy may benefit from epilepsy surgery. In nonlesional cases, where no epileptogenic lesion can be detected on structural magnetic resonance imaging, multimodal neuroimaging studies are required. Breath-hold-triggered BOLD fMRI (bh-fMRI) was developed to measure cerebrovascular reactivity in stroke or angiopathy and highlights regional network dysfunction by visualizing focal impaired flow increase after vasodilatory stimulus. This regional dysfunction may correlate with the epileptogenic zone. In this prospective single-center single-blind pilot study, we aimed to establish the feasibility and safety of bh-fMRI in individuals with drug-resistant non-lesional focal epilepsy undergoing presurgical evaluation. In this prospective study, 10consecutive individuals undergoing presurgical evaluation for drug-resistant focal epilepsy were recruited after case review at amultidisciplinary patient management conference. Electroclinical findings and results of other neuroimaging were used to establish the epileptogenic zone hypothesis. To calculate significant differences in cerebrovascular reactivity in comparison to the normal population, bh-fMRIs of 16healthy volunteers were analyzed. The relative flow change of each volume of interest (VOI) of the atlas was then calculated compared to the flow change of the whole brain resulting in an atlas of normal cerebral reactivity. Consequently, the mean flow change of every VOI of each patient was tested against the healthy volunteers group. Areas with significant impairment of cerebrovascular reactivity had decreased flow change and were compared to the epileptogenic zone localization hypothesis in asingle-blind design. Acquisition of bh-fMRI was feasible in 9/10cases, with one patient excluded due to noncompliance with breathing maneuvers. No adverse events were observed, and breath-hold for intermittent hypercapnia was well tolerated. On blinded review, we observed full or partial concordance of the local network dysfunction seen on bh-fMRI with the electroclinical hypothesis in 6/9cases, including cases with extratemporal lobe epilepsy and those with nonlocalizing 18F-fluorodeoxyglucose positron emission tomography (FDG-PET). This represents the first report of bh-fMRI in individuals with epilepsy undergoing presurgical evaluation. We found bh-fMRI to be feasible and safe, with apromising agreement to electroclinical findings. Thus, bh-fMRI may represent apotential modality in the presurgical evaluation of epilepsy. Further studies are needed to establish clinical utility.

Optimisation of the air fraction correction for lung PET/CT: addressing resolution mismatch

BackgroundIncreased pulmonary 18\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{18}{}$$\\end{document}F-FDG metabolism in patients with idiopathic pulmonary fibrosis, and other forms of diffuse parenchymal lung disease, can predict measurements of health and lung physiology. To improve PET quantification, voxel-wise air fractions (AF) determined from CT can be used to correct for variable air content in lung PET/CT. However, resolution mismatches between PET and CT can cause artefacts in the AF-corrected image.MethodsThree methodologies for determining the optimal kernel to smooth the CT are compared with noiseless simulations and non-TOF MLEM reconstructions of a patient-realistic digital phantom: (i) the point source insertion-and-subtraction method, hpts\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{pts}$$\\end{document}; (ii) AF-correcting with varyingly smoothed CT to achieve the lowest RMSE with respect to the ground truth (GT) AF-corrected volume of interest (VOI), hAFC\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{AFC}$$\\end{document}; iii) smoothing the GT image to match the reconstruction within the VOI, hPVC\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{PVC}$$\\end{document}. The methods were evaluated both using VOI-specific kernels, and a single global kernel optimised for the six VOIs combined. Furthermore, hPVC\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{PVC}$$\\end{document} was implemented on thorax phantom data measured on two clinical PET/CT scanners with various reconstruction protocols.ResultsThe simulations demonstrated that at <200\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$<200$$\\end{document} iterations (200 i), the kernel width was dependent on iteration number and VOI position in the lung. The hpts\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{pts}$$\\end{document} method estimated a lower, more uniform, kernel width in all parts of the lung investigated. However, all three methods resulted in approximately equivalent AF-corrected VOI RMSEs (<10%) at ≥\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ge$$\\end{document}200i. The insensitivity of AF-corrected quantification to kernel width suggests that a single global kernel could be used. For all three methodologies, the computed global kernel resulted in an AF-corrected lung RMSE <10% at ≥\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ge$$\\end{document}200i, while larger lung RMSEs were observed for the VOI–specific kernels. The global kernel approach was then employed with the hPVC\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{PVC}$$\\end{document} method on measured data. The optimally smoothed GT emission matched the reconstructed image well, both within the VOI and the lung background. VOI RMSE was <10%, pre-AFC, for all reconstructions investigated.ConclusionsSimulations for non-TOF PET indicated that around 200i were needed to approach image resolution stability in the lung. In addition, at this iteration number, a single global kernel, determined from several VOIs, for AFC, performed well over the whole lung. The hPVC\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$h_{PVC}$$\\end{document} method has the potential to be used to determine the kernel for AFC from scans of phantoms on clinical scanners.

Ultra-low dose CT scanning for PET/CT.

The use of computed tomography (CT) for attenuation correction (AC) in whole-body PET/CT can result in a significant contribution to radiation exposure. This can become a limiting factor for reducing considerably the overall radiation exposure of the patient when using the new long axial field of view (LAFOV) PET scanners. However, recent CT technology have introduced features such as the tin (Sn) filter, which can substantially reduce the CT radiation dose. The purpose of this study was to investigate the ultra-low dose CT for attenuation correction using the Sn filter together with other dose reduction options such as tube current (mAs) reduction. We explore the impact of dose reduction in the context of AC-CT and how it affects PET image quality. The study evaluated a range of ultra-low dose CT protocols using five physical phantoms that represented a broad collection of tissue electron densities. A long axial field of view (LAFOV) PET/CT scanner was used to scan all phantoms, applying various CT dose reduction parameters such as reducing tube current (mAs), increasing the pitch value, and applying the Sn filter. The effective dose resulting from the CT scans was determined using the CTDIVol reported by the scanner. Several voxel-based and volumes of interest (VOI)-based comparisons were performed to compare the ultra-low dose CT images, the generated attenuation maps, and corresponding PET images against those images acquired with the standard low dose CT protocol. Finally, two patient datasets were acquired using one of the suggested ultra-low dose CT settings. By incorporating the Sn filter and adjusting mAs to the lowest available value, the radiation dose in CT images of PBU-60 phantom was significantly reduced; resulting in an effective dose of nearly 2% compared to the routine low dose CT protocols currently in clinical use. The assessment of PET images using VOI and voxel-based comparisons indicated relative differences (RD%) of under 6% for mean activity concentration (AC) in the torso phantom and patient dataset and under 8% for a source point in the CIRS phantom. The maximum RD% value of AC was 14% for the point source in the CIRS phantom. Increasing the tube current from 6 mAs to 30 mAs in patients with high BMI, or with arms down, can suppress the photon starvation artifact, whilst still preserving a dose reduction of 90%. Introducing a Sn filter in CT imaging lowers radiation dose by more than 90%. This reduction has minimal effect on PET image quantification at least for patients without Body Mass Index (BMI) higher than 30. Notably, this study results need validation using a larger clinical PET/CT dataset in the future, including patients with higher BMI.

Micro finite element analysis of continuously loaded mini-implants - A micro-CT study in the rat tail model.

Implant migration has been described as a minor displacement of orthodontic mini-implants (OMIs) when subjected to constant forces. Aim of this study was to evaluate the impact of local stresses on implant migration and bone remodelling around constantly loaded OMIs. Two mini-implants were placed in one caudal vertebra of 61 rats, connected by a nickel‑titanium contraction spring, and loaded with different forces (0.0, 0.5, 1.0, 1.5N). In vivo micro-CT scans were taken immediately and 1, 2 (n=61), 4, 6 and 8 (n=31) weeks post-op. Nine volumes of interest (VOIs) around each implant were defined. To analyse stress values, micro-finite element models were created. Bone remodelling was analysed by calculating the bone volume change between scans performed at consecutive time points. Statistical analysis was performed using a linear mixed model and likelihood-ratio-tests, followed by Tuckey post hoc tests when indicated. The highest stresses were observed in the proximal top VOI. In all VOIs, stress values tended to reach their maximum after two weeks and decreased thereafter. Bone remodelling analysis revealed initial bone loss within the first two weeks and bone gain up to week eight, which was noted especially in the highest loading group. The magnitude of local stresses influenced bone remodelling and it can be speculated that the stress related bone resorption favoured implant migration. After a first healing phase with a high degree of bone resorption, net bone gain representing consolidation was observed.

Striatal Amyloid deposition in sporadic Alzheimer’s Disease

AbstractBackgroundIt has been shown that disorders associated with early‐life alterations in amyloid production or processing such as in autosomal dominant Alzheimer’s disease (AD) and down syndrome‐associated dementia have a different pattern of Aβ deposition, with early striatal accumulation, as compared to sporadic late‐onset cases, in which striatal deposition has been suggested to be a marker of late and advanced amyloidosis. It is not clear, however, if the pattern of amyloid accumulation is related to any other factors or if it has any impact on brain metabolism. We aimed to determine if there are any clinical or demographic predictors of striatal tau accumulation in sporadic AD and whether its presence affects the subjects´ brain metabolism.MethodSubjects that underwent positron emission tomography (PET) scans with 18F‐FDG and 11C‐PIB were analyzed retrospectively. Only those with clinical diagnosis of AD and mild cognitive impairment (MCI) due to AD were considered for the analysis. Visual analyses were performed to exclude subjects without cortical amyloid accumulation. Mean values from cortical volumes of interest (VOIs) and striatum were obtained. Amyloid deposition was correlated with age and disease duration via Pearson’s correlations. Amyloid deposition was also correlated to brain metabolism as assessed by FDG PET.Result150 subjects were included in this study. Neither age nor disease duration was correlated with striatal amyloid accumulation. Subjects with striatal Pib accumulation showed higher cortical amyloid burden. Moreover, higher striatal amyloid burden was positively correlated with higher frontal amyloid burden specifically. Amyloid burden in the striatum did not seem to have an impact on the glucose metabolism in the striatum itself. However, variations in cortical glucose metabolism could be observed. A higher striatal amyloid burden was correlated with cortical glucose hypometabolism, specifically in the precuneus and temporal areas (Figure 1).ConclusionThere seems to be a stage of sporadic Alzheimer’s disease in which amyloid accumulates in the striatum. This, in turn, appears to have an impact on brain functioning. Whether this has a real impact on cognitive performance remains to be elucidated.

Predictive value of metabolic parameters derived from preoperative 18F-FDG positron emission tomography/computed tomography for brain metastases in patients with surgically resected non-small cell lung cancer.

Brain metastases (BMs) are common complications in patients with non-small cell lung cancer (NSCLC). The purpose of this study was to investigate whether the metabolic parameters derived from preoperative 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) can predict BM development in patients with surgically resected NSCLC. We retrospectively reviewed 128 consecutive patients with stage I-IIIA NSCLC who underwent 18F-FDG PET/CT before curative surgery at The First Affiliated Hospital of Jinan University between November 2012 and October 2021. By drawing a volume of interest (VOI), the maximum standardized uptake values (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) of the primary tumor as well as the mean SUV (SUVmean) of the liver and arterial blood were measured. The tumor-to-liver SUV ratio (TLR) and tumor-to-blood SUV ratio (TBR) were also calculated. Receiver operating characteristic curve analysis was used to determine the best cut-off values for positron emission tomography (PET) parameters to predict BM-free survival, and Cox proportional hazards regression analysis was used to assess the predictive value of clinical variables and PET parameters. The median follow-up duration for survival patients was 23.4 months, and 15 patients (11.7%) experienced BM as the initial relapse site. The cumulative rates of BM over the course of 1, 2, and 5 years were 4.5%, 10.5%, and 17.5%, respectively. The optimal cut-off values for the prediction of BM-free survival were 7.7, 4.9, and 4.5 for SUVmax, TLR, and TBR, and 5.5 mL and 16.1 for MTV and TLG, respectively. In the Cox proportional hazards model, the risk of BM was significantly associated with TLR [hazard ratio (HR) =10.712; 95% confidence interval (CI): 2.958-38.801; P<0.001] and MTV (HR =3.150; 95% CI: 0.964-10.293; P=0.020) after adjusting for tumor stage, clinicopathological factors, and other PET parameters. Preoperative TLR and MTV of the primary tumor may be helpful in predicting BM development in patients with surgically resected NSCLC. Tumor metabolic parameters may potentially be used to stratify the risk of BM and determine individualized surveillance strategies.

Hippocampus substructure segmentation using morphological vision transformer learning

The hippocampus plays a crucial role in memory and cognition. Because of the associated toxicity from whole brain radiotherapy, more advanced treatment planning techniques prioritize hippocampal avoidance, which depends on an accurate segmentation of the small and complexly shaped hippocampus. To achieve accurate segmentation of the anterior and posterior regions of the hippocampus from T1 weighted (T1w) MR images, we developed a novel model, Hippo-Net, which uses a cascaded model strategy. The proposed model consists of two major parts: (1) a localization model is used to detect the volume-of-interest (VOI) of hippocampus. (2) An end-to-end morphological vision transformer network (Franchi et al 2020 Pattern Recognit. 102 107246, Ranem et al 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW) pp 3710–3719) is used to perform substructures segmentation within the hippocampus VOI. The substructures include the anterior and posterior regions of the hippocampus, which are defined as the hippocampus proper and parts of the subiculum. The vision transformer incorporates the dominant features extracted from MR images, which are further improved by learning-based morphological operators. The integration of these morphological operators into the vision transformer increases the accuracy and ability to separate hippocampus structure into its two distinct substructures. A total of 260 T1w MRI datasets from medical segmentation decathlon dataset were used in this study. We conducted a five-fold cross-validation on the first 200 T1w MR images and then performed a hold-out test on the remaining 60 T1w MR images with the model trained on the first 200 images. In five-fold cross-validation, the Dice similarity coefficients were 0.900 ± 0.029 and 0.886 ± 0.031 for the hippocampus proper and parts of the subiculum, respectively. The mean surface distances (MSDs) were 0.426 ± 0.115 mm and 0.401 ± 0.100 mm for the hippocampus proper and parts of the subiculum, respectively. The proposed method showed great promise in automatically delineating hippocampus substructures on T1w MR images. It may facilitate the current clinical workflow and reduce the physicians’ effort.

CART-AI-Radiomics: Survival and Neurotoxicity Prediction in B-Cell Lymphoma Patients Treated with CAR-T Cells through an Imaging Features-Based Model

Background: Despite clinical outcome improvements observed in relapsed/refractory (R/R) B-cell lymphoma patients (pts) treated with antigen receptor modified T-cells (CAR-T cells), a sizeable proportion still progress or relapse after infusion. Besides, this procedure is associated with significant morbidity primarily due to the immune effector cell-associated neurotoxicity syndrome (ICANS). The main goal of the CART-AI-Radiomics study is to apply artificial intelligence to develop new imaging-based prognostic and predictive models that integrate molecular and imaging biomarkers towards improved stratification of pts at high risk of R/R. In this sub-study, we retrospectively assessed the ability of imaging features and clinical data to predict survival and neurotoxicity. Methods: Consecutive pts diagnosed of diffuse large B-cell lymphoma (DLBCL) and primary mediastinal B-cell lymphoma (PMBCL) treated with anti-CD19 CAR-T cells from 2019-2022 in Valencia Clinic Hospital and La Fe Hospital were included (cut-off date: July 2023). All the pre-infusion flourine18 fluorodeoxyglucose positron emission tomography/computed tomography ( 18F-FDG PET/CT) scans and clinical data were collected. The volume of interest (VOI) was manually contoured for all visible lesions in the PET/CT imaging exams. A subsequent imaging features extraction was performed. Features included PET conventional parameters-maximum standardized uptake value (SUV max), metabolic tumor volume (MTV; defined as the volume of voxels with SUVs higher than the threshold of 41% × SUV max) and total lesion glycolysis (TLG)-and radiomic features. Imaging parameters were calculated for all lesions (total) and for the dominant lesion (DL), whereas clinical variables were measured before lymphodepletion (LD). Univariate and multivariate analyses were carried out using Cox proportional-hazards models for survival prediction and logistic regression for neurotoxicity assessment. Survival analyses were conducted according to MTV total values. Results: A total of 29 pts (median age 63.2 [range 21.8-79.3] years; 18 [62.1%] females) who received CAR-T cell therapy were included. Twenty-six (89.7%) pts had DLBCL and 3 (10.3%) had PMBCL. At the time of pre-LD, 22 (75.9%) pts had increased lactate dehydrogenase (LDH) levels 18 (62.1%), presented with stage IV disease, 16 (55.17%) with an International Prognostic Index (IPI) score of 3-5, 8 (27.6%) had bulky disease. Median number of prior treatment lines was 2 (range 2-6). Twenty-three (79.3%) pts were treated with axicabtagene ciloleucel and 6 (20.7%) with tisagenlecleucel. Bridging therapy before LD was required by 26 (89.6%) pts. For survival analyses, a cut-off MTV total value of 236.03 mL that maximized the Log-Rank statistic was selected to divide pts into high MTV total and low MTV total categories. Median overall survival (OS) was 5.7 [3.2-NA, 95% CI] months and 36.2 [13.9-NA, 95% CI] months for the high and low MTV total, respectively (Fig. 1). In multivariate analyses, a model including MTV total, SUV max and TLG total as imaging feature, and ICANS, C-reactive protein LD (CRP LD), LDH LD, lymphocytes count LD (Li LD) as clinical variables was able to successfully predict OS ( p = 0.019). Median progression-free survival (PFS) was 3 [1.31-NA, 95% CI] months and 11.06 [5.81-NA, 95% CI] months for the high and low MTV total, respectively. In multivariate analysis, a successful prediction of PFS ( p = 0.007) was achieved with a model including the same predictors that were used for OS. For the neurotoxicity assessment, a logistic regression model including six conventional PET parameters-MTV total, MTV DL,TLG total, TLG DL, median SUV DL, SUV max-two radiomic features,-entropy and entropy DL-and four clinical variables-CRP LD, LDH LD, Li LD and type of CAR-T cell treatment-was able to successfully predict the development of ICANS with an area under the curve of 0.971, a sensitivity of 0.813, a specificity of 0.846 and an accuracy of 0.828 (Fig. 2). Conclusions: Imaging features extracted from pre-infusion 18F-FDG PET/CT images in combination with several clinical features could predict survival and neurotoxicity in pts with DLBCL or PMBCL treated with CAR-T cell therapy. Quantitative features extracted from the PET/CT imaging exams may be useful for patient risk stratification and neurotoxicity prediction. Validation of these classifiers in independent datasets is warranted.

1954. Dynamic PET facilitated Modeling and Novel Antibiotic Regimens for Tuberculous Meningitis due to Multidrug-Resistant Strains

1954. Dynamic PET facilitated Modeling and Novel Antibiotic Regimens for Tuberculous Meningitis due to Multidrug-Resistant Strains

A single centre intercomparison between commercial treatment planning systems for 90Y radioembolization using virtual and experimental phantoms

IntroductionDedicated Treatment Planning Systems (TPSs) were developed to personalize 90Y-transarterial radioembolization. This study evaluated the agreement among four commercial TPSs assessing volumes of interest (VOIs) volumes and dose metrics. MethodsA homogeneous (EH) and an anthropomorphic phantom with hot and cold inserts (EA) filled with 99mTc-pertechnetate were acquired with a SPECT/CT scanner. Their virtual versions (VH and VA, respectively) and a phantom with activity inside a single voxel (VK) were generated by an in-house MATLAB script. Images and delineated VOIs were imported into the TPSs to compute voxel-based absorbed dose distributions with various dose deposition approaches: local deposition method (LDM) and dose kernel convolution (DKC) with/without local density correction (LDC). VOI volumes and mean absorbed doses were assessed against their median value across TPSs. Dose-volume histograms (DVHs) and VK-derived dose profiles were evaluated. ResultsSmall (<2.1 %) and large (up to 42.4 %) relative volume differences were observed on large (>500 ml) and small VOIs, respectively. Mean absorbed doses relative differences were < 3 % except for small VOIs with steep dose gradients (up to 89.1 % in the VA Cold Sphere VOI). Within the same TPS, LDC negligibly affected the mean absorbed dose, while DKC and LDM showed differences up to 63 %. DHVs were mostly overlapped in experimental phantoms, with some differences in the virtual versions. Dose profiles agreed within 1 %. ConclusionTPSs showed an overall good agreement except for small VOI volumes and mean absorbed doses of VOIs with steep dose gradients. These discrepancies should be considered in the dosimetry uncertainty assessment, thus requiring an appropriate harmonization.

Evaluation of molecular receptors status in breast cancer using an mpMRI-based feature fusion radiomics model: mimicking radiologists’ diagnosis

ObjectiveTo investigate the performance of a novel feature fusion radiomics (RFF) model that incorporates features from multiparametric MRIs (mpMRI) in distinguishing different statuses of molecular receptors in breast cancer (BC) preoperatively.Methods460 patients with 466 pathology-confirmed BCs who underwent breast mpMRI at 1.5T in our center were retrospectively included hormone receptor (HR) positive (HR+) (n=336) and HR negative (HR-) (n=130). The HR- patients were further categorized into human epidermal growth factor receptor 2 (HER-2) enriched BC (HEBC) (n=76) and triple negative BC (TNBC) (n=54). All lesions were divided into a training/validation cohort (n=337) and a test cohort (n=129). Volumes of interest (VOIs) delineation, followed by radiomics feature extraction, was performed on T2WI, DWI600 (b=600 s/mm2), DWI800 (b=800 s/mm2), ADC map, and DCE1-6 (six continuous DCE-MRI) images of each lesion. Simulating a radiologist’s work pattern, 150 classification base models were constructed and analyzed to determine the top four optimum sequences for classifying HR+ vs. HR-, TNBC vs. HEBC, TNBC vs. non-TNBC in a random selected training cohort (n=337). Building upon these findings, the optimal single sequence models (Rss) and combined sequences models (RFF) were developed. The AUC, sensitivity, accuracy and specificity of each model for subtype differentiation were evaluated. The paired samples Wilcoxon signed rank test was used for performance comparison.ResultsDuring the three classification tasks, the optimal single sequence for classifying HR+ vs. HR- was DWI600, while the ADC map, derived from DWI800 performed the best in distinguishing TNBC vs. HEBC, as well as identifying TNBC vs. non-TNBC, with corresponding training AUC values of 0.787, 0.788, and 0.809, respectively. Furthermore, the integration of the top four sequences in RFF models yielded improved performance, achieving AUC values of 0.809, 0.805 and 0.847, respectively. Consistent results was observed in both the training/validation and testing cohorts, with AUC values of 0.778, 0.787, 0.818 and 0.726, 0.773, 0.773, respectively (all p &amp;lt; 0.05 except HR+ vs. HR-).ConclusionThe RFF model, integrating mpMRI radiomics features, demonstrated promising ability to mimic radiologists’ diagnosis for preoperative identification of molecular receptors of BC.

Association between body mass index (BMI) and [123I]Ioflupane (DaTSCAN) availabilities in patients with parkinsonism using single-photon emission computed tomography–computed tomography (SPECT-CT)

Aim[123I]Ioflupane (DaTSCAN) has a high binding affinity to the dopamine (DA) transporter (DaT) and tenfold less affinity to serotonin (5-HT) transporter (SERT). Both neurotransmitters are considered to contribute to body weight regulation. This study assesses the association between body mass index (BMI) and DaTSCAN availability in brain.MethodScans from 74 consecutive patients who had undergone DaTSCAN single-photon emission computed tomography–computed tomography (SPECT-CT) were used to obtain semi- and absolute quantitative data in several volumes of interest (VOIs). Relative semi-quantitative specific binding ratios (SBRs) from Chang attenuated SPECT were obtained from GE DaTQUANT. Absolute normalised concentration (NC) was calculated from attenuation/scatter corrected SPECT-CT images, using an adapted version of the EARL Ltd (European Association of Nuclear Medicine (EANM) Research 4 Life) template. Scans were subdivided into either degenerative parkinsonism (abnormal = 49), borderline (n = 14) or scan without evidence of dopaminergic deficit (SWEDD = 11) using visual assessment and SBR values by two nuclear medicine consultants.ResultsSBRs did not correlate with BMI. However, NC values correlated negatively in the entire cohort, with the strongest correlation in the frontal (r = − 0.649. p = 0.000), occipital (r = − 0.555, p = 0.000) regions and pons (r = − 0.555, p = 0.000). In the abnormal (n = 49) and SWEDD group (n = 11), NC of the frontal region was the most correlated with BMI (r = − 0.570, p = 0.000; r = − 0.813, p = 0.002, respectively). In the borderline group (n = 14), the left posterior putamen displayed the strongest correlation (r = − 0.765, p = 0.001).ConclusionAbsolute NC values demonstrate a strong inverse correlation with BMI, strongest in the extrastriatal regions. Due to the predominately non-overlapping distribution of DaT and SERT, this study suggests greater involvement of SERT in obesity with possible interplay with DA transmission.

Breast MRI radiomics and machine learning radiomics-based predictions of response to neoadjuvant chemotherapy - how are they affected by variations in tumour delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumour VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affects different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

Radiomic analysis will add differential diagnostic value of benign and malignant pulmonary nodules: a hybrid imaging study based on [18F]FDG and [18F]FLT PET/CT

PurposeTo investigate the clinical value of radiomic analysis on [18F]FDG and [18F]FLT PET on the differentiation of [18F]FDG-avid benign and malignant pulmonary nodules (PNs).MethodsData of 113 patients with inconclusive PNs based on preoperative [18F]FDG PET/CT who underwent additional [18F]FLT PET/CT scans within a week were retrospectively analyzed in the present study. Three methods of analysis including visual analysis, radiomic analysis based on [18F]FDG PET/CT images alone, and radiomic analysis based on dual-tracer PET/CT images were evaluated for differential diagnostic value of benign and malignant PNs.ResultsA total of 678 radiomic features were extracted from volumes of interest (VOIs) of 123 PNs. Fourteen valuable features were thereafter selected. Based on a visual analysis of [18F]FDG PET/CT images, the diagnostic accuracy, sensitivity, and specificity were 61.6%, 90%, and 28.8%, respectively. For the test set, the area under the curve (AUC), sensitivity, and specificity of the radiomic models based on [18F]FDG PET/CT plus [18F]FLT signature were equal or better than radiomics based on [18F]FDG PET/CT only (0.838 vs 0.810, 0.778 vs 0.778, 0.750 vs 0.688, respectively).ConclusionRadiomic analysis based on dual-tracer PET/CT images is clinically promising and feasible for the differentiation between benign and malignant PNs.Clinical relevance statementRadiomic analysis will add differential diagnostic value of benign and malignant pulmonary nodules: a hybrid imaging study based on [18F]FDG and [18F]FLT PET/CT.Key points• Radiomics brings new insights into the differentiation of benign and malignant pulmonary nodules beyond the naked eyes.• Dual-tracer imaging shows the biological behaviors of cancerous cells from different aspects.• Radiomics helps us get to the histological view in a non-invasive approach.Graphical

Influence of different time framings, reconstruction algorithms and post-processing methods on the quantification of myocardial blood flow from 13 N-NH3 PET images.

The aim was to investigate to what extent the quantification of myocardial blood flow (MBF) from dynamic 13 N-NH3 positron emission tomography(PET) images is affected by time frame schemes, time-of-flight (ToF), reconstruction algorithms, blood pool volume of interest (VOI) locations and compartment models in patients with suspected chronic coronary syndrome. A standard MBF value was determined from 25 patients' rest/stress 13 N-NH3 PET/CT images reconstructed with ordered subset expectation maximization (OSEM), 5 s time frame for the first frames without ToF, subsequently analyzed using a basal VOI and the deGrado compartment model. MBFs calculated using 2or 10 s for the first frames, ToF, block-sequential regularized expectation maximization (BSREM), apical or large VOI, Hutchins or Krivokapich compartment models were compared to MBFstandard in Bland-Altman plots (bias ± SD). Good agreement in global rest/stress MBF (mL/min/g) was found when changing the time frame scheme or reconstruction algorithm (MBFstandard vs. MBF2s : -0.02 ± 0.06; MBF10s : 0.01 ± 0.07; MBFBSREM : 0.01 ± 0.07), while a lower level of agreement was found when altering the other factors (MBFstandard vs.MBFToF : -0.07 ± 0.10; MBFapical VOI : -0.27 ± 0.25; MBFlarge VOI : -0.11 ± 0.10; MBFHutchins : -0.08 ± 0.10; MBFKrivokapich : -0.47 ± 0.50). Quantification of MBF from 13 N-NH3 PET images is more affected by choice of compartment models, ToF and blood pool VOIs than by different time frame schemes and reconstruction algorithms.

NIMG-62. QUANTITATIVE ASSESSMENT OF T2-FLAIR MISMATCH IN HUMAN NON-ENHANCING GLIOMAS USING SUBTRACTION MAPS OF T2-W AND FLAIR MRI

Abstract INTRODUCTION The T2-FLAIR mismatch (T2FM) sign on anatomical MRI is highly specific for isocitrate dehydrogenase (IDH)-mutant 1p/19q-intact gliomas (astrocytomas) and is characterized by relative hypointense FLAIR signal within the T2 hyperintense lesion. However, studies on T2FM sign have mostly utilized qualitative visual assessment. This study explored quantitative subtraction maps of T2-w and FLAIR MRI in human non-enhancing gliomas to quantify the extent of T2FM and assess T2FM subregion volumetric and diffusion MRI differences. METHODS Seventy-two newly-diagnosed, non-enhancing gliomas with known IDH- and 1p/19q-status from The Cancer Imaging Archive (TCIA) were studied. An institutional cohort (n= 36) was analyzed for validation. T2-FLAIR subtraction maps were generated from voxel-wise subtraction of co-registered, normalized T2-w and FLAIR MRI scans. Tumor volumes of interest (VOIs) were segmented on the T2 hyperintensity excluding macroscopic cysts. Tumor VOIs were split into mismatched and non-mismatched subregions using consistent T2-FLAIR subtraction map thresholds. Tumor subregion volumes and normalized apparent diffusion coefficient (nADC) values were obtained, and tumor T2FM percentage was calculated. RESULTS In the TCIA cohort, a threshold of &amp;gt; 16% T2FM had 92.3% specificity and 34.8% sensitivity and a threshold of &amp;gt; 42% T2FM had 100% specificity and 21.7% sensitivity for classifying IDH-mutant astrocytomas (AUC= 0.704, P= 0.004). IDH-mutant astrocytomas with &amp;gt; 16% T2FM had higher nADC in mismatched compared to non-mismatched subregions (mean difference= 0.51; P&amp;lt; 0.0001). Using the same T2FM thresholds, these findings were validated in the institutional cohort for glioma classification (AUC= 0.918, P&amp;lt; 0.0001; &amp;gt; 16% T2FM: 100% specificity, 66.7% sensitivity, PPV= 100%, NPV= 65.2%; &amp;gt; 42% T2FM: 100% specificity, 23.8% sensitivity, PPV= 100%, NPV= 48.3%) and subregion nADC differences (mean difference= 0.56, P&amp;lt; 0.0001). CONCLUSIONS T2-FLAIR subtraction maps may be a useful, automated tool for classifying non-enhancing gliomas and exploring T2FM subregion differences. Elevated nADC in mismatched subregions may reflect microcystic changes.

Peritumoural MRI radiomics signature of brain metastases can predict epidermal growth factor receptor mutation status in lung adenocarcinoma

To investigate whether magnetic resonance imaging (MRI) radiomics features of brain metastases (BMs) can predict epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma. Between June 2014 and December 2022, 58 histopathologically confirmed lung adenocarcinoma patients (27 with EGFR wild-type, 31 with EGFR mutation) who underwent gadobenate dimeglumine-enhanced brain MRI were recruited retrospectively. A total of 123 metastatic brain lesions were allocated randomly into the training cohort (n=86) and test cohort (n=37) at a ratio of 7:3. Radiomics models based on multi-sequence MRI images in different regions such as volume of interest (VOI)enhancing tumour, VOIwholetumour, VOIperitumour 1mm, VOIperitumour 3mm, and VOIperitumour 5mm were built. The optimal radiomics model was integrated into the clinical or radiological indicators to construct a fusion model through multivariable logistic regression analysis. The optimal radiomics model based on the VOIperitumour 1mm, a combination of nine features selected from the fluid-attenuated inversion recovery (FLAIR) sequence, yielded areas under the curves (AUCs) of >0.75 in the training and test cohorts. The prediction of the fusion model with integration of clinical factors (age) and radiomics score (the optimal radiomics model) was not better than that of the optimal radiomics model alone in the test cohort (AUC: 0.808 and 0.785, respectively, p=0.525). The FLAIR radiomics model based on VOIperitumour 1mm as an effective biomarker helps predict EGFR mutation status in lung adenocarcinoma patients with BMs and then assists clinicians in selecting optimal treatment strategies.