Proceedings of SPIE--the International Society for Optical Engineering最新文献

In this study, we investigate the performance of advanced 2D acquisition geometries - Pentagon and T-shaped - in digital breast tomosynthesis (DBT) and compare them against the conventional 1D geometry. Unlike the conventional approach, our proposed 2D geometries also incorporate anterior projections away from the chest wall. Implemented on the Next-Generation Tomosynthesis (NGT) prototype developed by X-ray Physics Lab (XPL), UPenn, we utilized various phantoms to compare three geometries: a Defrise slab phantom with alternating plastic slabs to study low-frequency modulation; a Checkerboard breast phantom (a 2D adaptation of the Defrise phantom design) to study the ability to reconstruct the fine features of the checkerboard squares; and the 360° Star-pattern phantom to assess aliasing and compute the Fourier-spectral distortion (FSD) metric that assesses spectral leakage and the contrast transfer function. We find that both Pentagon and T-shaped scans provide greater modulation amplitude of the Defrise phantom slabs and better resolve the squares of the Checkerboard phantom against the conventional scan. Notably, the Pentagon geometry exhibited a significant reduction in aliasing of spatial frequencies oriented in the right-left (RL) medio-lateral direction, which was corroborated by a near complete elimination of spectral leakage in the FSD plot. Conversely T-shaped scan redistributes the aliasing between both posteroanterior (PA) and RL directions thus maintaining non-inferiority against the conventional scan which is predominantly affected by PA aliasing. The results of this study underscore the potential of incorporating advanced 2D geometries in DBT systems, offering marked improvements in imaging performance over the conventional 1D approach.

Precise deformable image registration of multi-parametric MRI sequences is necessary for radiologists in order to identify abnormalities and diagnose diseases, such as prostate cancer and lymphoma. Despite recent advances in unsupervised learning-based registration, volumetric medical image registration that requires considering the variety of data distributions is still challenging. To address the problem of multi-parametric MRI sequence data registration, we propose an unsupervised domain-transported registration method, called OTMorph by employing neural optimal transport that learns an optimal transport plan to map different data distributions. We have designed a novel framework composed of a transport module and a registration module: the former transports data distribution from the moving source domain to the fixed target domain, and the latter takes the transported data and provides the deformed moving volume that is aligned with the fixed volume. Through end-to-end learning, our proposed method can effectively learn deformable registration for the volumes in different distributions. Experimental results with abdominal multi-parametric MRI sequence data show that our method has superior performance over around 67-85% in deforming the MRI volumes compared to the existing learning-based methods. Our method is generic in nature and can be used to register inter-/intra-modality images by mapping the different data distributions in network training.

White matter signals in resting state blood oxygen level dependent functional magnetic resonance (BOLD-fMRI) have been largely discounted, yet there is growing evidence that these signals are indicative of brain activity. Understanding how these white matter signals capture function can provide insight into brain physiology. Moreover, functional signals could potentially be used as early markers for neurological changes, such as in Alzheimer's Disease. To investigate white matter brain networks, we leveraged the OASIS-3 dataset to extract white matter signals from resting state BOLD-FMRI data on 711 subjects. The imaging was longitudinal with a total of 2,026 images. Hierarchical clustering was performed to investigate clusters of voxel-level correlations on the timeseries data. The stability of clusters was measured with the average Dice coefficients on two different cross fold validations. The first validated the stability between scans, and the second validated the stability between populations. Functional clusters at hierarchical levels 4, 9, 13, 18, and 24 had local maximum stability, suggesting better clustered white matter. In comparison with JHU-DTI-SS Type-I Atlas defined regions, clusters at lower hierarchical levels identified well-defined anatomical lobes. At higher hierarchical levels, functional clusters mapped motor and memory functional regions, identifying 50.00%, 20.00%, 27.27%, and 35.14% of the frontal, occipital, parietal, and temporal lobe regions respectively.

The reconstruction kernel in computed tomography (CT) generation determines the texture of the image. Consistency in reconstruction kernels is important as the underlying CT texture can impact measurements during quantitative image analysis. Harmonization (i.e., kernel conversion) minimizes differences in measurements due to inconsistent reconstruction kernels. Existing methods investigate harmonization of CT scans in single or multiple manufacturers. However, these methods require paired scans of hard and soft reconstruction kernels that are spatially and anatomically aligned. Additionally, a large number of models need to be trained across different kernel pairs within manufacturers. In this study, we adopt an unpaired image translation approach to investigate harmonization between and across reconstruction kernels from different manufacturers by constructing a multipath cycle generative adversarial network (GAN). We use hard and soft reconstruction kernels from the Siemens and GE vendors from the National Lung Screening Trial dataset. We use 50 scans from each reconstruction kernel and train a multipath cycle GAN. To evaluate the effect of harmonization on the reconstruction kernels, we harmonize 50 scans each from Siemens hard kernel, GE soft kernel and GE hard kernel to a reference Siemens soft kernel (B30f) and evaluate percent emphysema. We fit a linear model by considering the age, smoking status, sex and vendor and perform an analysis of variance (ANOVA) on the emphysema scores. Our approach minimizes differences in emphysema measurement and highlights the impact of age, sex, smoking status and vendor on emphysema quantification.

It is known that deep neural networks (DNNs) are vulnerable to adversarial noises. Improving adversarial robustness of DNNs is essential. This is not only because unperceivable adversarial noise is a threat to the performance of DNNs models, but also adversarially robust DNNs have a strong resistance to the white noises that may present everywhere in the actual world. To improve adversarial robustness of DNNs, a variety of adversarial training methods have been proposed. Most of the previous methods are designed under one single application scenario: image classification. However, image segmentation, landmark detection, and object detection are more commonly observed than classifying the entire images in the medical imaging field. Although classification tasks and other tasks (e.g., regression) share some similarities, they also differ in certain ways, e.g., some adversarial training methods use misclassification criteria, which is well-defined in classification but not in regression. These restrictions/limitations hinder application of adversarial training for many medical imaging analysis tasks. In our work, the contributions are as follows: (1) We investigated the existing adversarial training methods and discovered the challenges that make those methods unsuitable for adaptation in segmentation and detection tasks. (2) We modified and adapted some existing adversarial training methods for medical image segmentation and detection tasks. (3) We proposed a general adversarial training method for medical image segmentation and detection. (4) We implemented our method in diverse medical imaging tasks using publicly available datasets, including MRI segmentation, Cephalometric landmark detection, and blood cell detection. The experiments substantiated the effectiveness of our method.

Gradient nonlinearities not only induce spatial distortion in magnetic resonance imaging (MRI), but also introduce discrepancies between intended and acquired diffusion sensitization in diffusion weighted (DW) MRI. Advances in scanner performance have increased the importance of correcting gradient nonlinearities. The most common approaches for gradient nonlinear field estimations rely on phantom calibration field maps which are not always feasible, especially on retrospective data. Here, we derive a quadratic minimization problem for the complete gradient nonlinear field (L(r)). This approach starts with corrupt diffusion signal and estimates the L(r) in two scenarios: (1) the true diffusion tensor known and (2) the true diffusion tensor unknown (i.e., diffusion tensor is estimated). We show the validity of this mathematical approach, both theoretically and through tensor simulation. The estimated field is assessed through diffusion tensor metrics: mean diffusivity (MD), fractional anisotropy (FA), and principal eigenvector (V1). In simulation with 300 diffusion tensors, the study shows the mathematical model is not ill-posed and remains stable. We find when the true diffusion tensor is known (1) the change in determinant of the estimated L(r) field and the true field is near zero and (2) the median difference in estimated L(r) corrected diffusion metrics to true values is near zero. We find the results of L(r) estimation are dependent on the level of L(r) corruption. This work provides an approach to estimate gradient field without the need for additional calibration scans. To the best of our knowledge, the mathematical derivation presented here is novel.

Radiomics has been widely recognized for its effectiveness in decoding tumor phenotypes through the extraction of quantitative imaging features. However, the robustness of radiomic methods to estimate clinically relevant biomarkers non-invasively remains largely untested. In this study, we propose Cascaded Data Processing Network (CDPNet), a radiomic feature learning method to predict tumor molecular status from medical images. We apply CDPNet to an epigenetic case, specifically targeting the estimation of O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation from Magnetic Resonance Imaging (MRI) scans of glioblastoma patients. CDPNet has three components: 1) Principal Component Analysis (PCA), 2) Fisher Linear Discriminant (FLD), and 3) a combination of hashing and blockwise histograms. The outlined architectural framework capitalizes on PCA to reconstruct input image patches, followed by FLD to extract discriminative filter banks, and finally using binary hashing and blockwise histogram module for indexing, pooling, and feature generation. To validate the effectiveness of CDPNet, we conducted an exhaustive evaluation on a comprehensive retrospective cohort comprising 484 IDH-wildtype glioblastoma patients with pre-operative multi-parametric MRI scans (T1, T1-Gd, T2, and T2-FLAIR). The prediction of MGMT promoter methylation status was cast as a binary classification problem. The developed model underwent rigorous training via 10-fold cross-validation on a discovery cohort of 446 patients. Subsequently, the model's performance was evaluated on a distinct and previously unseen replication cohort of 38 patients. Our method achieved an accuracy of 70.11% and an area under the curve of 0.71 (95% CI: 0.65 - 0.74).

Current deep learning methods in histopathology are limited by the small amount of available data and time consumption in labeling the data. Colorectal cancer (CRC) tumor budding quantification performed using H&E-stained slides is crucial for cancer staging and prognosis but is subject to labor-intensive annotation and human bias. Thus, acquiring a large-scale, fully annotated dataset for training a tumor budding (TB) segmentation/detection system is difficult. Here, we present a DatasetGAN-based approach that can generate essentially an unlimited number of images with TB masks from a moderate number of unlabeled images and a few annotated images. The images generated by our model closely resemble the real colon tissue on H&E-stained slides. We test the performance of this model by training a downstream segmentation model, UNet++, on the generated images and masks. Our results show that the trained UNet++ model can achieve reasonable TB segmentation performance, especially at the instance level. This study demonstrates the potential of developing an annotation-efficient segmentation model for automatic TB detection and quantification.

Animal models are pivotal in disease research and the advancement of therapeutic methods. The translation of results from these models to clinical applications is enhanced by employing technologies which are consistent for both humans and animals, like Magnetic Resonance Imaging (MRI), offering the advantage of longitudinal disease evaluation without compromising animal welfare. However, current animal MRI techniques predominantly employ 2D acquisitions due to constraints related to organ size, scan duration, image quality, and hardware limitations. While 3D acquisitions are feasible, they are constrained by longer scan times and ethical considerations related to extended sedation periods. This study evaluates the efficacy of SMORE, a self-supervised deep learning super-resolution approach, to enhance the through-plane resolution of anisotropic 2D MRI scans into isotropic resolutions. SMORE accomplishes this by self-training with high-resolution in-plane data, thereby eliminating domain discrepancies between the input data and external training sets. The approach is tested on mouse MRI scans acquired across a range of through-plane resolutions. Experimental results show SMORE substantially outperforms traditional interpolation methods. Additionally, we find that pre-training offers a promising approach to reduce processing time without compromising performance.

Accurate and reliable registration of longitudinal spine images is essential for assessment of disease progression and surgical outcome. Implementing a fully automatic and robust registration is crucial for clinical use, however, it is challenging due to substantial change in shape and appearance due to lesions. In this paper we present a novel method to automatically align longitudinal spine CTs and accurately assess lesion progression. Our method follows a two-step pipeline where vertebrae are first automatically localized, labeled and 3D surfaces are generated using a deep learning model, then longitudinally aligned using a Gaussian mixture model surface registration. We tested our approach on 37 vertebrae, from 5 patients, with baseline CTs and 3, 6, and 12 months follow-ups leading to 111 registrations. Our experiment showed accurate registration with an average Hausdorff distance of 0.65 mm and average Dice score of 0.92.