New Imaging Methods for Identifying Structural Differences in Cancer Cells

ASPIRE Award (2019-2021)

Robert F. Murphy, PhD (Principal) and Min Xu, PhD, Carnegie Mellon University; Yi-Wei Chang, PhD, University of Pennsylvania

The diversity of cancer types is reflected in the physical heterogeneity of tumor cells. This includes the shape, number, and spatial distribution of the cellular components that carry out various cellular functions. Current imaging technologies do not have high enough resolution to capture the differences in these cellular substructures, which limits doctors’ ability to diagnose cancers based on physical differences in tumor cells. Electron cryotomography (ECT) imaging is a relatively new technology that can produce 3D images of cells with resolutions under five nanometers. It allows for detailed imaging of the cellular interior, which makes it ideally suited for imaging and classification of tumor cells. However, to classify different cell types, ECT must be adapted for human cells and accompanied by advanced computer-based analysis methods that have yet to be developed. Researchers in the Murphy, Xu, and Chang labs are designing and testing classification and statistical analysis software that can be used to evaluate subcellular structural differences in different cancer cell lines. They will use four cultured breast tissue cell lines that range from non-cancerous to invasive carcinoma to train the software to recognize these differences. If successful, they should be able to analyze ECT images to differentiate both the diverse structures inside cells and differentiate cell lines based on the physical variability of these structures. In the future, these imaging methods may be translatable to tumor cells excised from patients, allowing doctors to use them to diagnose patients and predict their prognosis.

published research

Liu S, Ban X, Zeng X, Zhao F, Gao Y, Wu W, Zhang H, Chen F, Hall T, Gao X, Xu M. A unified framework for packing deformable and non-deformable subcellular structures in crowded cryo-electron tomogram simulation. BMC Bioinformatics. 2020.

Li R, Yu L, Zhou B, Zeng X, Wang Z, Yang X, Zhang J, Gao X, Jiang R, Xu M. Few-shot learning for classification of novel macromolecular structures in cryo-electron tomograms. PLoS Comput Biol. 2020.

Yu L, Li R, Zeng X, Wang H, Jin J, Ge Y, Jiang R, Xu M. Few shot domain adaptation for in situ macromolecule structural classification in cryoelectron tomograms. Bioinformatics. 2021.

Zhou B, Yu H, Zeng X, Yang X, Zhang J, Xu M. One-Shot Learning With Attention-Guided Segmentation in Cryo-Electron Tomography. Front Mol Biosci. 2021.

Chandra S, Gourisaria MK, Gm H, Konar D, Gao X, Wang T, Xu M. Prolificacy Assessment of Spermatozoan via State-of-the-Art Deep Learning Frameworks. IEEE Access. 2022.

Chharia A, Upadhyay R, Kumar V, Cheng C, Zhang J, Wang T, Xu M. Deep-Precognitive Diagnosis: Preventing Future Pandemics by Novel Disease Detection with Biologically-Inspired Conv-Fuzzy Network. IEEE Access. 2022.

Wu X, Li C, Zeng X, Wei H, Deng HW, Zhang J, Xu M. CryoETGAN: Cryo-Electron Tomography Image Synthesis via Unpaired Image Translation. Frontiers in Physiology. 2022.

Zeng X, Lin Z, Uddin MR, Zhou B, Cheng C, Zhang J, Freyberg Z, Xu M. Structure Detection in Three-Dimensional Cellular Cryoelectron Tomograms by Reconstructing Two-Dimensional Annotated Tilt Series. J Comput Biol. 2022.