Deep-Learning-Based Label-Free Segmentation of Cell Nuclei in Time-Lapse Refractive Index Tomograms
Jimin Lee,
Hyejin Kim,
Hyungjoo Cho,
YoungJu Jo,
Yujin Song,
Daewoong Ahn,
Kangwon Lee,
Yongkeun Park,
Sung-Joon Ye
Affiliations
Jimin Lee
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
Hyejin Kim
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
Hyungjoo Cho
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
YoungJu Jo
Department of Applied Physics, Stanford University, Stanford, CA, USA
Yujin Song
Department of Transdisciplinary Studies, Program in Nano Science and Technology, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
Daewoong Ahn
Tomocube Inc., Daejeon, South Korea
Kangwon Lee
Department of Transdisciplinary Studies, Program in Nano Science and Technology, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
Department of Transdisciplinary Studies, Program in Biomedical Radiation Sciences, Graduate School of Convergence Science and Technology, Seoul National University, Seoul, South Korea
We proposed a method of label-free segmentation of cell nuclei by exploiting a deep learning (DL) framework. Over the years, fluorescent proteins and staining agents have been widely used to identify cell nuclei. However, the use of exogenous agents inevitably prevents from long-term imaging of live cells and rapid analysis and even interferes with intrinsic physiological conditions. Without any agents, the proposed method was applied to label-free optical diffraction tomography (ODT) of human breast cancer cells. A novel architecture with optimized training strategies was validated through cross-modality and cross-laboratory experiments. The nucleus volumes from the DL-based label-free ODT segmentation accurately agreed with those from fluorescent-based. Furthermore, the 4D cell nucleus segmentation was successfully performed for the time-lapse ODT images. The proposed method would bring out broad and immediate biomedical applications with our framework publicly available.
