arXiv subjects

Peder E. Z. Larson

Publications and source records attributed to Peder E. Z. Larson.

At least 19 recordsLinked to original sources

arXiv2026

Fine-UNETR for PSMA PET/CT Lesion Segmentation: Automated Tumor Quantification and Overall Survival Stratification in Prostate Cancer

Introduction: To develop and evaluate Fine-UNETR, a Vision Transformer-based architecture for automated segmentation of PSMA-avid lesions on whole-body PET/CT, and to assess clinical utility of AI-derived tumor burden biomarkers for overall survival stratification in radioligand therapy. Methods: In this retrospective study, 373 PSMA PET/CT scans (mean age, 71+-8 years) from patients with prostate cancer were analyzed. Fine-UNETR, a modified UNETR with 8x8x8 voxel patch embedding and axial sliding window training, was trained on 299 scans and validated on 74 scans. Overall survival stratification was assessed in an independent cohort of 67 pre-radioligand therapy patients using Kaplan-Meier analysis and log-rank testing. External validation was performed on 192 cases from the AutoPET IV PSMA PET/CT dataset. Results: Fine-UNETR achieved a Dice similarity coefficient (DSC) of 66.63%, sensitivity of 70.27%, precision of 67.77%, and a lesion detection rate of 79.53% (96.05% for lesions with SUVmax >= 5). On the external validation dataset, the model achieved a DSC of 44.11% and a lesion detection rate of 87.18%, indicating that lesion detection performance was preserved despite reduced voxel-level overlap. AI-derived biomarkers showed excellent agreement with ground truth (total tumor volume: r=0.984; total lesion uptake: r=0.989; lesion count: r=0.960). In the clinical cohort, total tumor volume (p=0.0019), SUVmax (p=0.014), and SUVmean (p=0.016) significantly stratified overall survival. Conclusion: Fine-UNETR enables accurate automated whole-body PSMA lesion segmentation and tumor burden quantification. Performance on an external dataset demonstrates robustness despite evidence of domain shift. AI-derived biomarkers significantly stratified overall survival in a pre-radioligand therapy cohort, supporting the clinical utility of automated PSMA PET/CT quantification for prognostication.

eess.IV↗

arXiv2026

A Mixed Precision FFT with applications in MRI

A mixed precision Fast Fourier transform (FFT) implementation is presented. The procedure uses per-block microscaling (MX), a global power-of-two prescale, and prequantized low bit twiddles. We evaluate forward and round-trip FFT fidelity on two public MRI datasets and compare the effect of various low precision formats, image sizes, and MX block sizes on image quality. Results show that mantissa precision is the primary limiter under MX scaling while ablations suggest weak dependence on image size but a clear block-size trade-off with larger block sizes resulting in better numerical performance.

eess.SP↗

arXiv2025

Estimating Sensitivity Maps for X-Nuclei Magnetic Resonance Spectroscopic Imaging

The purpose of this research is to estimate sensitivity maps when imaging X-nuclei that may not have a significant presence throughout the field of view. We propose to estimate the coil's sensitivities by solving a least-squares problem where each row corresponds to an individual estimate of the sensitivity for a given voxel. Multiple estimates come from the multiple bins of the spectrum with spectroscopy, multiple times with dynamic imaging, or multiple frequencies when utilizing spectral excitation. The method presented in this manuscript, called the L2 optimal method, is compared to the commonly used RefPeak method which uses the spectral bin with the highest energy to estimate the sensitivity maps. The L2 optimal method yields more accurate sensitivity maps when imaging a numerical phantom and is shown to yield a higher signal-to-noise ratio when imaging the brain, pancreas, and heart with hyperpolarized pyruvate as the contrast agent with hyperpolarized MRI. The L2 optimal method is able to better estimate the sensitivity by extracting more information from the measurements.

eess.IV↗

arXiv2024

Initial Experience of Metabolic Imaging with Hyperpolarized [1-13C]pyruvate MRI in Kidney Transplant Patients

BACKGROUND: Kidney transplant is the treatment of choice for patients with end-stage renal disease. Early detection of allograft injury is important to delay or prevent irreversible damage. PURPOSE: To investigate the feasibility of hyperpolarized (HP) [1-13C]pyruvate MRI for assessing kidney allograft metabolism. SUBJECTS: 6 participants (mean age, 45.2 +- 12.4 years, 2 females) scheduled for kidney allograft biopsy and 5 patients (mean age, 59.6 +- 10.4 years, 2 females) with renal cell carcinoma (RCC). ASSESSMENT: Five of the six kidney allograft participants underwent biopsy after MRI. Estimated glomerular filtration rate (eGFR) and urine protein-to-creatine ratio (uPCR) were collected within 4 weeks of MRI. Kidney metabolism was quantified from HP [1-13C]pyruvate MRI using the lactate-to-pyruvate ratio in allograft kidneys and non-tumor bearing kidneys from RCC patients. RESULTS: Biopsy was performed a mean of 9 days (range 5-19 days) after HP [1-13C]pyruvate MRI. Three biopsies were normal, one showed low-grade fibrosis and one showed moderate microvascular inflammation. All had stable functioning allografts with eGFR > 60 mL/min/1.73 m2 and normal uPCR. One participant who did not undergo biopsy had reduced eGFR of 49 mL/min/1.73 m2 and elevated uPCR. The mean lactate-to-pyruvate ratio was 0.373 in participants with normal findings (n = 3) and 0.552 in participants with abnormal findings (n = 2). The lactate-to-pyruvate ratio was highest (0.847) in the participant with reduced eGFR and elevated uPRC. Native non-tumor bearing kidneys had a mean lactate-to-pyruvate ratio of 0.309. DATA CONCLUSION: Stable allografts with normal findings at biopsy showed lactate-to-pyruvate ratios similar to native non-tumor bearing kidneys, whereas allografts with abnormal findings showed higher lactate-to-pyruvate ratios.

physics.med-ph↗

arXiv2024

Data Format Standardization and DICOM Integration for Hyperpolarized 13C MRI

Hyperpolarized (HP) 13C MRI has shown promise as a valuable modality for in vivo measurements of metabolism and is currently in human trials at 15 research sites worldwide. With this growth it is important to adopt standardized data storage practices as it will allow sites to meaningfully compare data. In this paper we (1) describe data that we believe should be stored and (2) demonstrate pipelines and methods that utilize the Digital Imaging and Communications in Medicine (DICOM) standard. This includes proposing a set of minimum set of information that is specific to HP 13C MRI studies. We then show where the majority of these can be fit into existing DICOM Attributes, primarily via the "Contrast/Bolus" module. We also demonstrate pipelines for utilizing DICOM for HP 13C MRI. DICOM is the most common standard for clinical medical image storage and provides the flexibility to accommodate the unique aspects of HP 13C MRI, including the HP agent information but also spectroscopic and metabolite dimensions. The pipelines shown include creating DICOM objects for studies on human and animal imaging systems with various pulse sequences. We also show a python-based method to efficiently modify DICOM objects to incorporate the unique HP 13C MRI information that is not captured by existing pipelines. Moreover, we propose best practices for HP 13C MRI data storage that will support future multi-site trials, research studies and technical developments of this imaging technique.

physics.med-ph↗

arXiv2024

Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction

Magnetic resonance imaging is subject to slow acquisition times due to the inherent limitations in data sampling. Recently, supervised deep learning has emerged as a promising technique for reconstructing sub-sampled MRI. However, supervised deep learning requires a large dataset of fully-sampled data. Although unsupervised or self-supervised deep learning methods have emerged to address the limitations of supervised deep learning approaches, they still require a database of images. In contrast, scan-specific deep learning methods learn and reconstruct using only the sub-sampled data from a single scan. Here, we introduce Scan-Specific Self-Supervised Bayesian Deep Non-Linear Inversion (DNLINV) that does not require an auto calibration scan region. DNLINV utilizes a deep image prior-type generative modeling approach and relies on approximate Bayesian inference to regularize the deep convolutional neural network. We demonstrate our approach on several anatomies, contrasts, and sampling patterns and show improved performance over existing approaches in scan-specific calibrationless parallel imaging and compressed sensing.

eess.IV↗

arXiv2023

T2 Relaxation during Radiofrequency (RF) pulses

Radiofrequency (RF) pulses are a critical part of every MRI pulse sequence, and must be specifically designed for ultrashort echo time (UTE) and zero echo time (ZTE) acquisitions. When considering the behavior of RF pulses, most often longitudinal T1 or transverse T2 relaxation is assumed to be negligible during the RF pulses themselves. This is usually valid with conventional sequences since most tissue T1s and T2s are much longer than typical RF pulse durations. However, when imaging tissues that have transverse relaxation times that are of the order of, or shorter than, the RF pulse duration, as is often the case with UTE and ZTE MRI, then relaxation during the pulse must be considered. This article covers the theory of T2/T2* relaxation during an RF pulse, and the implications and applications of this for imaging of ultrashort-T2* species.

physics.med-ph↗

arXiv2023

Lung Imaging with UTE MRI

Cross-sectional imaging of the lungs, or pulmonary imaging, has proven to be an incredibly valuable tool in a wide range of pulmonary diseases. The vast majority of lung imaging is done with CT, as it is fast enough to freeze respiratory motion and provides high spatial resolution to visualize fine structure of the lungs. MRI of the lungs is inherently challenging due to the presence of large local magnetic field gradients, relatively low proton density, and motion. The benefits of performing MRI for lung imaging include no ionizing radiation, opportunities for multiple contrasts, and integration with other MRI also offers the opportunity to obtain multiple tissue contrasts. The most common lung MRI techniques are structural T1-weighted scans, but also emerging are functional contrasts such as ventilation and perfusion, as well as other MRI contrast mechanisms including T2-weighting and diffusion-weighting. Finally, lung MRI can be combined with other MRI scanning techniques, including cardiac MRI, abdominal MRI, whole-body MRI, and PET/MRI, for increasing examination efficiency by only requiring a single scan session and providing more comprehensive assessment that includes evaluation of the pulmonary system. This article covers pulse sequences, motion management methods, image reconstruction, and contrast mechanisms of UTE MRI (e.g. T1-weighting, ventilation mapping) for imaging of the lung.

physics.med-ph↗

arXiv2023

Multi-coil Magnetic Resonance Imaging with Compressed Sensing Using Physically Motivated Regularization

With the advent of multi-coil imaging and compressed sensing, a number of model based reconstruction algorithms have been created. They incorporate a multitude of different regularization functions based on physics, observed phenomenology, and heuristics. Moreover, several iterative methods exist that attempt to simultaneously estimate the sensitivity maps and the image. In this manuscript, we present a generalization of several existing iterative model based algorithms. We devise a calibrationless instance of this generalization that only incorporates regularization terms based on physics and the accepted compressed sensing phenomenology of sparsity in the wavelet domain. We compare the results of the new amalgamated optimization problem with existing methods on both simulated and real datasets. We show that the images reconstructed using the new method, entitled Multi-coil Compressed Sensing (MCCS), are of higher quality than existing methods in all cases studied.

eess.IV↗

arXiv2022

Mixed Supervision of Histopathology Improves Prostate Cancer Classification from MRI

Non-invasive prostate cancer detection from MRI has the potential to revolutionize patient care by providing early detection of clinically-significant disease (ISUP grade group >= 2), but has thus far shown limited positive predictive value. To address this, we present an MRI-based deep learning method for predicting clinically significant prostate cancer applicable to a patient population with subsequent ground truth biopsy results ranging from benign pathology to ISUP grade group~5. Specifically, we demonstrate that mixed supervision via diverse histopathological ground truth improves classification performance despite the cost of reduced concordance with image-based segmentation. That is, where prior approaches have utilized pathology results as ground truth derived from targeted biopsies and whole-mount prostatectomy to strongly supervise the localization of clinically significant cancer, our approach also utilizes weak supervision signals extracted from nontargeted systematic biopsies with regional localization to improve overall performance. Our key innovation is performing regression by distribution rather than simply by value, enabling use of additional pathology findings traditionally ignored by deep learning strategies. We evaluated our model on a dataset of 973 (testing n=160) multi-parametric prostate MRI exams collected at UCSF from 2015-2018 followed by MRI/ultrasound fusion (targeted) biopsy and systematic (nontargeted) biopsy of the prostate gland, demonstrating that deep networks trained with mixed supervision of histopathology can significantly exceed the performance of the Prostate Imaging-Reporting and Data System (PI-RADS) clinical standard for prostate MRI interpretation.

eess.IV↗

arXiv2022

Utilizing the Structure of the Curvelet Transform with Compressed Sensing

The discrete curvelet transform decomposes an image into a set of fundamental components that are distinguished by direction and size as well as a low-frequency representation. The curvelet representation is approximately sparse; thus, it is a useful sparsifying transformation to be used with compressed sensing. However, the low-frequency portion is seldom sparse. This manuscript presents a method to modify the redundant sparsifying transformation comprised of the wavelet and curvelet transforms to take advantage of this fact with compressed sensing image reconstruction. Instead of relying on sparsity for this low-frequency estimate, the Nyquist-Shannon theorem specifies a square region centered on the $0$ frequency to be collected, which is used to generate a blurry estimate. A Basis Pursuit Denoising problem is solved to determine the missing details after modifying the sparsifying transformation to take advantage of the known fully sampled region. Improvements in quality are shown on magnetic resonance and optical images.

eess.IV↗

arXiv2022

Federated Learning with Research Prototypes for Multi-Center MRI-based Detection of Prostate Cancer with Diverse Histopathology

Early prostate cancer detection and staging from MRI are extremely challenging tasks for both radiologists and deep learning algorithms, but the potential to learn from large and diverse datasets remains a promising avenue to increase their generalization capability both within- and across clinics. To enable this for prototype-stage algorithms, where the majority of existing research remains, in this paper we introduce a flexible federated learning framework for cross-site training, validation, and evaluation of deep prostate cancer detection algorithms. Our approach utilizes an abstracted representation of the model architecture and data, which allows unpolished prototype deep learning models to be trained without modification using the NVFlare federated learning framework. Our results show increases in prostate cancer detection and classification accuracy using a specialized neural network model and diverse prostate biopsy data collected at two University of California research hospitals, demonstrating the efficacy of our approach in adapting to different datasets and improving MR-biomarker discovery. We open-source our FLtools system, which can be easily adapted to other deep learning projects for medical imaging.

cs.CV↗

arXiv2022

Synthetic PET via Domain Translation of 3D MRI

Historically, patient datasets have been used to develop and validate various reconstruction algorithms for PET/MRI and PET/CT. To enable such algorithm development, without the need for acquiring hundreds of patient exams, in this paper we demonstrate a deep learning technique to generate synthetic but realistic whole-body PET sinograms from abundantly-available whole-body MRI. Specifically, we use a dataset of 56 $^{18}$F-FDG-PET/MRI exams to train a 3D residual UNet to predict physiologic PET uptake from whole-body T1-weighted MRI. In training we implemented a balanced loss function to generate realistic uptake across a large dynamic range and computed losses along tomographic lines of response to mimic the PET acquisition. The predicted PET images are forward projected to produce synthetic PET time-of-flight (ToF) sinograms that can be used with vendor-provided PET reconstruction algorithms, including using CT-based attenuation correction (CTAC) and MR-based attenuation correction (MRAC). The resulting synthetic data recapitulates physiologic $^{18}$F-FDG uptake, e.g. high uptake localized to the brain and bladder, as well as uptake in liver, kidneys, heart and muscle. To simulate abnormalities with high uptake, we also insert synthetic lesions. We demonstrate that this synthetic PET data can be used interchangeably with real PET data for the PET quantification task of comparing CT and MR-based attenuation correction methods, achieving $\leq 7.6\%$ error in mean-SUV compared to using real data. These results together show that the proposed synthetic PET data pipeline can be reasonably used for development, evaluation, and validation of PET/MRI reconstruction methods.

physics.med-ph↗

arXiv2022

Physics-driven Deep Learning for PET/MRI

In this paper, we review physics- and data-driven reconstruction techniques for simultaneous positron emission tomography (PET) / magnetic resonance imaging (MRI) systems, which have significant advantages for clinical imaging of cancer, neurological disorders, and heart disease. These reconstruction approaches utilize priors, either structural or statistical, together with a physics-based description of the PET system response. However, due to the nested representation of the forward problem, direct PET/MRI reconstruction is a nonlinear problem. We elucidate how a multi-faceted approach accommodates hybrid data- and physics-driven machine learning for reconstruction of 3D PET/MRI, summarizing important deep learning developments made in the last 5 years to address attenuation correction, scattering, low photon counts, and data consistency. We also describe how applications of these multi-modality approaches extend beyond PET/MRI to improving accuracy in radiation therapy planning. We conclude by discussing opportunities for extending the current state-of-the-art following the latest trends in physics- and deep learning-based computational imaging and next-generation detector hardware.

eess.IV↗

arXiv2021

Attenuation Coefficient Estimation for PET/MRI With Bayesian Deep Learning pseudo-CT and Maximum Likelihood Estimation of Activity and Attenuation

A major remaining challenge for magnetic resonance-based attenuation correction methods (MRAC) is their susceptibility to sources of MRI artifacts (e.g. implants, motion) and uncertainties due to the limitations of MRI contrast (e.g. accurate bone delineation and density, and separation of air/bone). We propose using a Bayesian deep convolutional neural network that, in addition to generating an initial pseudo-CT from MR data, also produces uncertainty estimates of the pseudo-CT to quantify the limitations of the MR data. These outputs are combined with MLAA reconstruction that uses the PET emission data to improve the attenuation maps. With the proposed approach (UpCT-MLAA), we demonstrate accurate estimation of PET uptake in pelvic lesions and show recovery of metal implants. In patients without implants, UpCT-MLAA had acceptable but slightly higher RMSE than Zero-echo-time and Dixon Deep pseudo-CT when compared to CTAC. In patients with metal implants, MLAA recovered the metal implant; however, anatomy outside the implant region was obscured by noise and crosstalk artifacts. Attenuation coefficients from the pseudo-CT from Dixon MRI were accurate in normal anatomy; however, the metal implant region was estimated to have attenuation coefficients of air. UpCT-MLAA estimated attenuation coefficients of metal implants alongside accurate anatomic depiction outside of implant regions.

physics.med-ph↗

arXiv2021

Least Squares Optimal Density Compensation for the Gridding Non-uniform Discrete Fourier Transform

The Gridding algorithm has shown great utility for reconstructing images from non-uniformly spaced samples in the Fourier domain in several imaging modalities. Due to the non-uniform spacing, some correction for the variable density of the samples must be made. Existing methods for generating density compensation values are either sub-optimal or only consider a finite set of points (a set of measure 0) in the optimization. This manuscript presents the first density compensation algorithm for a general trajectory that takes into account the point spread function over a set of non-zero measure. We show that the images reconstructed with Gridding using the density compensation values of this method are of superior quality when compared to density compensation weights determined in other ways. Results are shown with a numerical phantom and with magnetic resonance images of the abdomen and the knee.

eess.IV↗

arXiv2021

Utilizing the Wavelet Transform's Structure in Compressed Sensing

Compressed sensing has empowered quality image reconstruction with fewer data samples than previously though possible. These techniques rely on a sparsifying linear transformation. The Daubechies wavelet transform is a common sparsifying transformation used for this purpose. In this work, we take advantage of the structure of this wavelet transform and identify an affine transformation that increases the sparsity of the result. After inclusion of this affine transformation, we modify the resulting optimization problem to comply with the form of the Basis Pursuit Denoising problem. Finally, we show theoretically that this yields a lower bound on the error of the reconstruction and present results where solving this modified problem yields images of higher quality for the same sampling patterns.

eess.IV↗

arXiv2021

Fast Variable Density Poisson-Disc Sample Generation with Directional Variation

We present a fast method for generating random samples according to a variable density Poisson-disc distribution. A minimum threshold distance is used to create a background grid array for keeping track of those points that might affect any new candidate point; this reduces the number of conflicts that must be checked before acceptance of a new point, thus reducing the number of computations required. We demonstrate the algorithm's ability to generate variable density Poisson-disc sampling patterns according to a parameterized function, including patterns where the variations in density are a function of direction. We further show that these sampling patterns are appropriate for compressed sensing applications. Finally, we present a method to generate patterns with a specific acceleration rate.

eess.IV↗