A Super-Resolution Diffusion Model for Recovering Bone Microstructure from CT Images.

Purpose: To use a diffusion-based deep learning model to recover bone microstructure from low-resolution images of the proximal femur, a common site of traumatic osteoporotic fractures. Materials and Methods: Training and testing data in this retrospective study consisted of high-resolution cadaveric micro-CT scans (n = 26), which served as ground truth. The images were downsampled prior to use for model training. The model was used to increase spatial resolution in these low-resolution images threefold, from 0.72 mm to 0.24 mm, sufficient to visualize bone microstructure. Model performance was validated using microstructural metrics and finite element simulation-derived stiffness of trabecular regions. Performance was also evaluated across a handful of image quality assessment metrics. Correlations between model performance and ground truth were assessed using intraclass correlation coefficients (ICCs) and Pearson correlation coefficients. Results: Compared with popular deep learning baselines, the proposed model exhibited greater accuracy (mean ICC of proposed model, 0.92 vs ICC of next best method, 0.83) and lower bias (mean difference in means, 3.80% vs 10.00%, respectively) across the physiologic metrics. Two gradient-based image quality metrics strongly correlated with accuracy across structural and mechanical criteria (r > 0.89). Conclusion: The proposed method may enable accurate measurements of bone structure and strength with a radiation dose on par with current clinical imaging protocols, improving the viability of clinical CT for assessing bone health.Keywords: CT, Image Postprocessing, Skeletal-Appendicular, Long Bones, Radiation Effects, Quantification, Prognosis, Semisupervised Learning Online supplemental material is available for this article. © RSNA, 2023.

Compression drives diverse transcriptomic and phenotypic adaptations in melanoma.

Physical forces are prominent during tumor progression. However, it is still unclear how they impact and drive the diverse phenotypes found in cancer. Here, we apply an integrative approach to investigate the impact of compression on melanoma cells. We apply bioinformatics to screen for the most significant compression-induced transcriptomic changes and investigate phenotypic responses. We show that compression-induced transcriptomic changes are associated with both improvement and worsening of patient prognoses. Phenotypically, volumetric compression inhibits cell proliferation and cell migration. It also induces organelle stress and intracellular oxidative stress and increases pigmentation in malignant melanoma cells and normal human melanocytes. Finally, cells that have undergone compression become more resistant to cisplatin treatment. Our findings indicate that volumetric compression is a double-edged sword for melanoma progression and drives tumor evolution.

Biophysical informatics reveals distinctive phenotypic signatures and functional diversity of single-cell lineages.

MOTIVATION: In this work, we present an analytical method for quantifying both single-cell morphologies and cell network topologies of tumor cell populations and use it to predict 3D cell behavior. RESULTS: We utilized a supervised deep learning approach to perform instance segmentation on label-free live cell images across a wide range of cell densities. We measured cell shape properties and characterized network topologies for 136 single-cell clones derived from the YUMM1.7 and YUMMER1.7 mouse melanoma cell lines. Using an unsupervised clustering algorithm, we identified six distinct morphological subclasses. We further observed differences in tumor growth and invasion dynamics across subclasses in an in vitro 3D spheroid model. Compared to existing methods for quantifying 2D or 3D phenotype, our analytical method requires less time, needs no specialized equipment and is capable of much higher throughput, making it ideal for applications such as high-throughput drug screening and clinical diagnosis. AVAILABILITY AND IMPLEMENTATION: https://github.com/trevor-chan/Melanoma_NetworkMorphology. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.