Computational Optics Enables Breast Cancer Profiling in Point-of-Care Settings

The global burden of cancer, severe diagnostic bottlenecks in underserved regions, and underfunded health care systems are fueling the need for inexpensive, rapid, and treatment-informative diagnostics. On the basis of advances in computational optics and deep learning, we have developed a low-cost...

Full description

Saved in:

Bibliographic Details
Published in:	ACS nano Vol. 12; no. 9; pp. 9081 - 9090
Main Authors:	Min, Jouha, Im, Hyungsoon, Allen, Matthew, McFarland, Phillip J, Degani, Ismail, Yu, Hojeong, Normandin, Erica, Pathania, Divya, Patel, Jaymin M, Castro, Cesar M, Weissleder, Ralph, Lee, Hakho
Format:	Journal Article
Language:	English
Published:	United States American Chemical Society 25-09-2018
Subjects:	Algorithms Biopsy, Fine-Needle Breast Neoplasms - diagnostic imaging Cell Line, Tumor Deep Learning Female Humans Image Processing, Computer-Assisted Point-of-Care Systems global health deep learning breast cancer diagnostics artificial intelligence
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The global burden of cancer, severe diagnostic bottlenecks in underserved regions, and underfunded health care systems are fueling the need for inexpensive, rapid, and treatment-informative diagnostics. On the basis of advances in computational optics and deep learning, we have developed a low-cost digital system, termed AIDA (artificial intelligence diffraction analysis), for breast cancer diagnosis of fine needle aspirates. Here, we show high accuracy (>90%) in (i) recognizing cells directly from diffraction patterns and (ii) classifying breast cancer types using deep-learning-based analysis of sample aspirates. The image algorithm is fast, enabling cellular analyses at high throughput (∼3 s per 1000 cells), and the unsupervised processing allows use by lower skill health care workers. AIDA can perform quantitative molecular profiling on individual cells, revealing intratumor molecular heterogeneity, and has the potential to improve cancer diagnosis and treatment. The system could be further developed for other cancers and thus find widespread use in global health.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 J.M., H.I., R.W., H.L. designed the study. J.M., H.I., I.D., H.Y. fabricated the AIDA device. J.M., H.I., P.M, D.P. designed and optimized assay conditions. J.M. processed samples, and J.M. H.I., E.N., J.P., C.M.C., R.W., H.L. analyzed the data. H.I., M.A., and H.L. established computational algorithms. R.W. oversaw clinical testing. J.M., H.I., C.M.C., R.W., and H.L. wrote the paper, which was edited by all authors. These authors contributed equally to the manuscript Author contributions
ISSN:	1936-0851 1936-086X
DOI:	10.1021/acsnano.8b03029