Quantitative magnetic resonance imaging (qMRI) measures have provided insights into the composition, quality, and structure‐function of musculoskeletal tissues. Low signal‐to‐noise ratio has limited application to tendon. Advances in scanning sequences and sample positioning have improved signal from tendon allowing for evaluation of structure and function. The purpose of this study was to elucidate relationships between tendon qMRI metrics (T1, T2, T1ρ and diffusion tensor imaging [DTI] metrics) with tendon tissue mechanics, collagen concentration and organization. Sixteen human Achilles tendon specimens were collected, imaged with qMRI, and subjected to mechanical testing with quantitative polarized light imaging. T2 values were related to tendon mechanics [peak stress (
- Award ID(s):
- 1821342
- NSF-PAR ID:
- 10099975
- Date Published:
- Journal Name:
- 11th Annual Undergraduate Research & Scholarship Symposium, Duquesne University
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract r sp = 0.51,p = 0.044), equilibrium stress (r sp = 0.54,p = 0.033), percent relaxation (r sp = −0.55,p = 0.027), hysteresis (r sp = −0.64,p = 0.007), linear modulus (r sp = 0.67,p = 0.009)]. T1ρ had a statistically significant relationship with percent relaxation (r = 0.50,p = 0.048). Collagen content was significantly related to DTI measures (range ofr = 0.56–0.62). T2 values from a single slice of the midportion of human Achilles tendons were strongest predictors of tendon tensile mechanical metrics. DTI diffusivity indices (mean diffusivity, axial diffusivity, radial diffusivity) were strongly correlated with collagen content. These findings build on a growing body of literature supporting the feasibility of qMRI to characterize tendon tissue and noninvasively measure tendon structure and function. Statement of Clinical Significance: Quantitative MRI can be applied to characterize tendon tissue and is a noninvasive measure that relates to tendon composition and mechanical behavior. -
more » « less
Abstract Background Magnetic resonance imaging (MRI) scans are known to suffer from a variety of acquisition artifacts as well as equipment‐based variations that impact image appearance and segmentation performance. It is still unclear whether a direct relationship exists between magnetic resonance (MR) image quality metrics (IQMs) (e.g., signal‐to‐noise, contrast‐to‐noise) and segmentation accuracy.
Purpose Deep learning (DL) approaches have shown significant promise for automated segmentation of brain tumors on MRI but depend on the quality of input training images. We sought to evaluate the relationship between IQMs of input training images and DL‐based brain tumor segmentation accuracy toward developing more generalizable models for multi‐institutional data.
Methods We trained a 3D DenseNet model on the BraTS 2020 cohorts for segmentation of tumor subregions enhancing tumor (ET), peritumoral edematous, and necrotic and non‐ET on MRI; with performance quantified via a 5‐fold cross‐validated Dice coefficient. MRI scans were evaluated through the open‐source quality control tool MRQy, to yield 13 IQMs per scan. The Pearson correlation coefficient was computed between whole tumor (WT) dice values and IQM measures in the training cohorts to identify quality measures most correlated with segmentation performance. Each selected IQM was used to group MRI scans as “better” quality (BQ) or “worse” quality (WQ), via relative thresholding. Segmentation performance was re‐evaluated for the DenseNet model when (i) training on BQ MRI images with validation on WQ images, as well as (ii) training on WQ images, and validation on BQ images. Trends were further validated on independent test sets derived from the BraTS 2021 training cohorts.
Results For this study, multimodal MRI scans from the BraTS 2020 training cohorts were used to train the segmentation model and validated on independent test sets derived from the BraTS 2021 cohort. Among the selected IQMs, models trained on BQ images based on inhomogeneity measurements (coefficient of variance, coefficient of joint variation, coefficient of variation of the foreground patch) and the models trained on WQ images based on noise measurement peak signal‐to‐noise ratio (SNR) yielded significantly improved tumor segmentation accuracy compared to their inverse models.
Conclusions Our results suggest that a significant correlation may exist between specific MR IQMs and DenseNet‐based brain tumor segmentation performance. The selection of MRI scans for model training based on IQMs may yield more accurate and generalizable models in unseen validation.
-
In the medical sector, three-dimensional (3D) images are commonly used like computed tomography (CT) and magnetic resonance imaging (MRI). The 3D MRI is a non-invasive method of studying the soft-tissue structures in a knee joint for osteoarthritis studies. It can greatly improve the accuracy of segmenting structures such as cartilage, bone marrow lesion, and meniscus by identifying the bone structure first. U-net is a convolutional neural network that was originally designed to segment the biological images with limited training data. The input of the original U-net is a single 2D image and the output is a binary 2D image. In this study, we modified the U-net model to identify the knee bone structures using 3D MRI, which is a sequence of 2D slices. A fully automatic model has been proposed to detect and segment knee bones. The proposed model was trained, tested, and validated using 99 knee MRI cases where each case consists of 160 2D slices for a single knee scan. To evaluate the model’s performance, the similarity, dice coefficient (DICE), and area error metrics were calculated. Separate models were trained using different knee bone components including tibia, femur, patella, as well as a combined model for segmenting all the knee bones. Using the whole MRI sequence (160 slices), the method was able to detect the beginning and ending bone slices first, and then segment the bone structures for all the slices in between. On the testing set, the detection model accomplished 98.79% accuracy and the segmentation model achieved DICE 96.94% and similarity 93.98%. The proposed method outperforms several state-of-the-art methods, i.e., it outperforms U-net by 3.68%, SegNet by 14.45%, and FCN-8 by 2.34%, in terms of DICE score using the same dataset.more » « less
-
Deep learning has been applied to magnetic resonance imaging (MRI) for a variety of purposes, ranging from the acceleration of image acquisition and image denoising to tissue segmentation and disease diagnosis. Convolutional neural networks have been particularly useful for analyzing MRI data due to the regularly sampled spatial and temporal nature of the data. However, advances in the field of brain imaging have led to network- and surface-based analyses that are often better represented in the graph domain. In this analysis, we propose a general purpose cortical segmentation method that, given resting-state connectivity features readily computed during conventional MRI pre-processing and a set of corresponding training labels, can generate cortical parcellations for new MRI data. We applied recent advances in the field of graph neural networks to the problem of cortical surface segmentation, using resting-state connectivity to learn discrete maps of the human neocortex. We found that graph neural networks accurately learn low-dimensional representations of functional brain connectivity that can be naturally extended to map the cortices of new datasets. After optimizing over algorithm type, network architecture, and training features, our approach yielded mean classification accuracies of 79.91% relative to a previously published parcellation. We describe how some hyperparameter choices including training and testing data duration, network architecture, and algorithm choice affect model performance.more » « less
-
more » « less
Abstract Magnetic resonance imaging (MRI) is a routine diagnostic modality in oncology that produces excellent imaging resolution and tumor contrast without the use of ionizing radiation. However, improved contrast agents are still needed to further increase detection sensitivity and avoid toxicity/allergic reactions associated with paramagnetic metal contrast agents, which may be seen in a small percentage of the human population. Fluorine‐19 (19F)‐MRI is at the forefront of the developing MRI methodologies due to near‐zero background signal, high natural abundance of 100%, and unambiguous signal specificity. In this study, we have developed a colloidal nanoemulsion (NE) formulation that can encapsulate high volumes of the fluorous MRI tracer, perfluoro‐[15‐crown‐5]‐ether (PFCE) (35% v/v). These nanoparticles exhibit long‐term (at least 100 days) stability and high PFCE loading capacity in formulation with our semifluorinated triblock copolymer, M2F8H18. With sizes of approximately 200 nm, these NEs enable
in vivo delivery and passive targeting to tumors. Our diagnostic formulation, M2F8H18/PFCE NE, yieldedin vivo 19F‐MR images with a high signal‐to‐noise ratio up to 100 in a tumor‐bearing mouse model at clinically relevant scan times. M2F8H18/PFCE NE circulated stably in the vasculature, accumulated in high concentration of an estimated 4–9 × 1017 19F spins/voxel at the tumor site, and cleared from most organs over the span of 2 weeks. Uptake by the mononuclear phagocyte system to the liver and spleen was also observed, most likely due to particle size. These promising results suggest that M2F8H18/PFCE NE is a favorable19F‐MR diagnostic tracer for further development in oncological studies and potential clinical translation.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
