With the global burden of cancer on the rise, it is critical to developing new modalities that could detect cancer and guide targeted treatments in fast and inexpensive ways. The need for such technologies is vital, especially in underserved regions where severe diagnostic bottlenecks exist. Recently, we developed a low-cost digital diagnostic system for breast cancer using fine-needle aspirates (FNAs). Named, AIDA (artificial intelligence diffraction analysis), the system combines lens-free digital diffraction imaging with deep-learning algorithms to achieve automated, rapid, and high-throughput cellular analyses for breast cancer diagnosis of FNA and subtype classification for better-guided treatments (Min et al. ACS Nano 12:9081-9090, 2018). Although primarily validated for breast cancer and lymphoma (Min et al. ACS Nano 12:9081-9090, 2018; Im et al. Nat Biomed Eng 2:666-674, 2018), the system could be easily adapted to diagnosing other prevalent cancers and thus find widespread use for global health.
Keywords: Artificial intelligence; Breast cancer; Cellular analysis; Deep-learning algorithms; Global health; Point-of-care diagnostics.
© 2022. Springer Science+Business Media, LLC, part of Springer Nature.