Featured Investigators

This study aims to use deep learning to perform automatic scapula bone segmentation and to simultaneously synthetize CT-like images. With funding from the CCMBM Pilot and Feasibility Grant Program, the proposed study builds a novel translational platform to revolutionize shoulder MR images in research studies, but also is paradigm-shifting in that it may provide a first step towards a more quantitative approach to surgical planning and patient management.
 

Methodology Needed to Obtain Bony and Soft Tissue Information
Scapular bone shape is an important determinant in surgical planning and predictor of post-operative outcomes for patients with shoulder instability and shoulder osteoarthritis. Currently, clinical evaluation of scapular bone shape is performed on a three-dimensional (3D) computed tomography (CT) scan, while a magnetic resonance imaging (MRI) scan is obtained to evaluate the soft tissue surrounding the shoulder. There is a clear clinical and research need for a methodology to obtain bony and soft tissue information from a single imaging study in an accurate, repeatable and fully automated fashion. 

Deep Learning Allows Automated Segmentation of Cartilage and Bone

Deep Learning (DL), especially convolutional neural networks (CNNs), has made strides in several domains as speech recognition, visual object detection, classification, drug discovery and genomics. DL shines when afforded large datasets, as its automated feature extraction allows one to solve problems too complex for conventional approaches. CNNs are representation learning methods characterized by the usage of multiple, simple, but non-linear units to build several interconnected layers. Each layer aggregates the information at increasing levels of abstraction starting with simple image elements, as edges or contrast, to more complex and semantic aggregations, uncovering latent patterns able to accomplish pattern recognition tasks. DL has allowed for the automatic segmentation of knee cartilage, knee and hip bone; however, the scapula is a unique thin structure with a complex shape that poses different challenges.  
 

Novel Directions for Shoulder Instability and Should Osteoarthritis in Clinical Treatment and Research

We have performed a pilot study utilizing a two-dimensional (2D) V-net convolutional neural network architecture with good results (mean Dice score coefficient: 82%), however further improvement is necessary for clinical or research implementation. We propose applying mixed precision training to allow for 3D processing in an efficient fashion. We also plan to augment our dataset with Statistical Shape Modeling to generate multiple synthetic training examples to be used for model pre-training and transfer learning. Finally, we plan to apply multi-task learning to simultaneously synthesize CT images and segment scapular bone from a standard clinical MRI scan. We will compare model performance on the MRI scan relative to a matched 3D-CT scan from previously acquired patient scans. The results of this study have the potential to greatly impact clinical treatment and create novel directions of research on shoulder instability and shoulder osteoarthritis.
 

Janet Lee, MD, MPH, MAS
 

Skeletal Effects of Puberty Suppression of Transgender Youth 
 

Skeletal Effects of Pubertal Suppression in Transgender Youth (SEPSITY) is a 1-year collaborative pilot study investigating bone measures of early pubertal transgender and gender diverse (TGD) youth prior to and during gender-affirming medical therapy with gonadotropin-releasing hormone agonists (GnRHa). Data from Europe have shown that late pubertal and adult transfeminine individuals, in particular, have low BMD prior to and following several years of gender-affirming sex hormones. We have shown that early pubertal TGD youth of both designated sexes at birth also have higher than expected rates of low BMD by DXA and QCT prior to initiation of gender-affirming medical therapy, and that those with low BMD have lower physical activity than those with normal BMD.

From the UCSF Child and Adolescent Gender Center, we are building a cohort of TGD youth initiating gender-affirming medical therapy in early puberty, with plans to continue following these youth into adulthood. Study participants complete standardized assessments of bone mineral density (BMD) and body composition with dual-energy X-ray absorptiometry (DXA), bone microarchitecture with high-resolution peripheral quantitative computed tomography (HR-pQCT), strength measures, anthropometrics, bone turnover markers, vitamin D status, dietary calcium intake, and physical activity. Our pilot data are expected to lead to longer-term intervention studies aiming to mitigate the expected lag in skeletal development during pubertal suppression, and to identify potential areas for intervention. Ultimately, our research will positively contribute to the clinical care of TGD youth. Funding from the CCMBM pilot and feasibility award has allowed us to study and build this important cohort.

Jeannie Bailey, PhD
 

The mechanistic pathophysiology associated with paraspinal muscular degeneration and chronic low back pain

In this pilot study, we will assess the spatial distribution of multifidus fat infiltration and cellular-makeup of muscle biopsies from distinct groups of chronic low back patients to decipher the underlying mechanisms negatively affecting multifidus and its regenerative potential. 
 

Chronic low back pain (CLBP) is the world's leading debilitating condition. The multifaceted and uncertain etiology underlying CLBP makes it notoriously difficult to determine specific diagnoses and effective treatments. The paraspinal muscles, particularly the multifidus (MF), have a uniquely important biomechanical role in stabilizing the lumbar spine and could be an effective target for conservative therapy. However, based on standard MRIs, MF muscle health is not shown to consistently associate with CLBP. MF is likely a critical component modulating the relationship between existing spinal pathology and patient symptoms, but the mechanisms underlying how MF is affected by spinal pathology remains unclear. We propose utilizing advanced MRI to precisely quantify fat infiltration spatial distribution, paired with knowledge of the underlying cellular composition and gene expression from corresponding MF tissue samples to clarify the cellular mechanisms compromising MF muscle quality. We will assess MF muscle quality and regenerative potential from two patient groups: a radicular CLBP group with disc herniation (n=8) and a localized CLBP group with disc pathology (n=8). First, using advanced MRI sequences for fat infiltration, we will distinguish patterns of relative quantity and spatial distribution of fat infiltration within MF between radicular and localized CLBP patient groups. Next, we will collect MF muscle tissue samples and analyze tissue-level MF composition based on presence and distribution of fiber type, fibrosis, fat cells, innervation, and inflammatory biomarkers. This will help decipher mechanisms affecting MF based on the diverse underlying cellular composition. Lastly, we will quantify the number of underlying fibro-adipogenic progenitor stem cells (FAPs) and use gene expression to determine cellular stemness, myogenesis, fibrosis, different adipose tissue types, inflammation, and innervation. This study will provide pilot data for us to pursue funding for a larger study. The goal of this overall work is have a clearer understanding of the pathophysiology of MF muscle degeneration and recovery potential associated with CLBP, which can lead to the development of therapies for muscle regeneration and targeted rehabilitation supporting focused conservative care approaches for managing and alleviating CLBP.
 

 

Jeannie Bailey, PhD

Assistant Professor, Orthopaedic Surgery

Research interests: Biomechanics and age-related conditions of the lumbar spine and participate in events and leverage collaboration between the departments of Orthopaedic Surgery and Physical Therapy, as well as utilizing Imaging and Epi biostats research cores.