arXiv subjects

Jonn Wu

Publications and source records attributed to Jonn Wu.

5 recordsLinked to original sources

arXiv2024

Neural blind deconvolution for deblurring and supersampling PSMA PET

Objective: To simultaneously deblur and supersample prostate specific membrane antigen (PSMA) positron emission tomography (PET) images using neural blind deconvolution. Approach: Blind deconvolution is a method of estimating the hypothetical "deblurred" image along with the blur kernel (related to the point spread function) simultaneously. Traditional \textit{maximum a posteriori} blind deconvolution methods require stringent assumptions and suffer from convergence to a trivial solution. A method of modelling the deblurred image and kernel with independent neural networks, called "neural blind deconvolution" had demonstrated success for deblurring 2D natural images in 2020. In this work, we adapt neural blind deconvolution for PVE correction of PSMA PET images with simultaneous supersampling. We compare this methodology with several interpolation methods, using blind image quality metrics, and test the model's ability to predict kernels by re-running the model after applying artificial "pseudokernels" to deblurred images. The methodology was tested on a retrospective set of 30 prostate patients as well as phantom images containing spherical lesions of various volumes. Results: Neural blind deconvolution led to improvements in image quality over other interpolation methods in terms of blind image quality metrics, recovery coefficients, and visual assessment. Predicted kernels were similar between patients, and the model accurately predicted several artificially-applied pseudokernels. Localization of activity in phantom spheres was improved after deblurring, allowing small lesions to be more accurately defined. Significance: The intrinsically low spatial resolution of PSMA PET leads to PVEs which negatively impact uptake quantification in small regions. The proposed method can be used to mitigate this issue, and can be straightforwardly adapted for other imaging modalities.

physics.med-ph↗

arXiv2024

Image denoising and model-independent parameterization for improving IVIM MRI

Variability of IVIM parameters throughout the literature is a long-standing issue, and perfusion-related parameters are difficult to interpret. We demonstrate for improving the analysis of intravoxel incoherent motion imaging (IVIM) magnetic resonance (MR) images, using image denoising and a quantitative approach that does not require imposing specific exponential models. IVIM images were acquired for 13 head-and-neck patients prior to radiotherapy. Of these, 5 patients also had post-radiotherapy scans acquired. Image quality was improved prior to parameter fitting via denoising. For this, we employed neural blind deconvolution, a method of undertaking the ill-posed mathematical problem of blind deconvolution using neural networks. The signal decay curve was then quantified in terms of area under the curve ($AUC$) parameters. Denoised images were assessed in terms of blind image quality metrics, and correlations between their derived parameters in parotid glands with radiotherapy dose levels. We assessed the method's ability to recover artificial pseudokernels which had been applied to denoised images. $AUC$ parameters were compared with the apparent diffusion coefficient ($ADC$), biexponential, and triexponential model parameters, in terms of their correlations with dose, and their relative contributions to the total variance of the dataset, obtained through singular value decomposition. Image denoising resulted in improved blind image quality metrics, and higher correlations between IVIM parameters and dose. $AUC$ parameters were more correlated with dose than traditional IVIM parameters, and captured the highest proportion of the dataset's variance. V This method of describing the signal decay curve with model-independent parameters like the $AUC$, and preprocessing images with denoising techniques, shows potential for improving reproducibility and utility of IVIM imaging.

physics.med-ph↗

arXiv2024

Investigating heterogeneous PSMA ligand uptake inside parotid glands

The purpose was to investigate the spatial heterogeneity of prostate-specific membrane antigen (PSMA) positron emission tomography (PET) uptake within parotid glands. We aim to quantify patterns in well-defined regions to facilitate further investigations. Furthermore, we investigate whether uptake is correlated with computed tomography (CT) texture features. Parotid glands from [18F]DCFPyL PSMA PET/CT images of 30 prostate cancer patients were analyzed. Thresholding was used to define high-uptake regions, and uptake statistics were computed within various divisions. Spearman's rank correlation coefficient was calculated between PSMA PET uptake and the Grey Level Run Length Matrix (GLRLM) using a long and short run length emphasis (GLRLML and GLRLMS) in subregions of parotid glands. PSMA PET uptake was significantly higher (p < 0.001) in lateral/posterior regions of the glands than anterior/medial regions. Maximum uptake was found in the lateral half of parotid glands in 50 out of 60 glands. The difference in SUV between parotid halves is greatest when parotids are divided by a plane separating the anterior/medial and posterior/lateral halves symmetrically. PSMA PET uptake was significantly correlated with CT GLRLML (p < 0.001), and anti-correlated with CT GLRLMS (p < 0.001). Uptake of PSMA PET is heterogeneous within parotid glands, with uptake biased towards lateral and posterior regions. Uptake patterns within parotid glands were found to be strongly correlated with CT texture features, suggesting the possible future use of CT texture features as a proxy for inferring PSMA PET uptake in salivary glands.

physics.med-ph↗

arXiv2024

PSMA PET/CT as a predictive tool for sub-regional importance estimates in the parotid gland

Xerostomia and radiation-induced salivary gland dysfunction remain a common side effect for head-and-neck radiotherapy patients, and attempts have been made to quantify the heterogeneous dose response within parotid glands. Here several models of parotid gland subregional importance are compared with prostate specific membrane antigen (PSMA) positron emission tomography (PET) uptake. PSMA ligands show high concentrations in salivary glands, whose uptake has been previously found to relate to gland functionality. We develop a predictive model for relative importance estimates using PSMA PET and CT radiomic features, and demonstrate a methodology for predicting patient-specific importance deviations from the population. Intra-parotid gland uptake was compared with four regional importance models using 30 [18F]DCFPyL PSMA PET images. A radiomics-based predictive model of population importance was developed using a double cross-validation methodology. Population importance estimates were supplemented using patient-specific radiomic features. Anticorrelative relationships were found to exist between PSMA PET uptake and four independent models of subregional parotid gland importance from the literature. Kernel Ridge Regression with principal component analysis feature selection performed best over test sets (MAE = 0.08), with GLCM features being particularly important. Deblurring PSMA PET images strengthened correlations and improved model performance. This study suggests that regions of relatively low PSMA PET concentration in parotid glands may exhibit relatively high dose-sensitivity. We've demonstrated the utility of PSMA PET radiomic features for predicting relative importance within the parotid glands. PSMA PET appears promising for analyzing salivary gland functionality.

physics.med-ph↗

arXiv2017

Prefer Nested Segmentation to Compound Segmentation

Introduction: Intra-organ radiation dose sensitivity is becoming increasingly relevant in clinical radiotherapy. One method for assessment involves partitioning delineated regions of interest and comparing the relative contributions or importance to clinical outcomes. We show that an intuitive method for dividing organ contours, compound (sub-)segmentation, can unintentionally lead to sub-segments with inconsistent volumes, which will bias relative importance assessment. An improved technique, nested segmentation, is introduced and compared. Methods: Clinical radiotherapy planning parotid contours from 510 patients were segmented. Counts of radiotherapy dose matrix voxels interior to sub-segments were used to determine the equivalency of sub-segment volumes. The distribution of voxel counts within sub-segments were compared using Kolmogorov-Smirnov tests and characterized by their dispersion. Analytical solutions for 2D/3D analogues were derived and sub-segment area/volume were compared directly. Results: Both parotid and 2D/3D region of interest analogue segmentation confirmed compound segmentation intrinsically produces sub-segments with volumes that depend on the region of interest shape and selection location. Significant volume differences were observed when sub-segmenting parotid contours into 18ths, and vanishingly small sub-segments were observed when sub-segmenting into 96ths. Central sub-segments were considerably smaller than sub-segments on the periphery. Nested segmentation did not exhibit these shortcomings and produced sub-segments with equivalent volumes when dose grid and contour collinearity was addressed, even when dividing the parotid into 96ths. Nested segmentation was always faster or equivalent in runtime to compound segmentation. Conclusions: Nested segmentation is more suited than compound segmentation for analyses requiring equal weighting of sub-segments.

q-bio.QM↗