DeadNet: Identifying Phototoxicity from Label-free Microscopy Images of Cells using Deep ConvNets

Exposure to intense illumination light is an unavoidable consequence of fluorescence microscopy, and poses a risk to the health of the sample in every live-cell fluorescence microscopy experiment. Furthermore, the possible side-effects of phototoxicity on the scientific conclusions that are drawn from an imaging experiment are often unaccounted for. Previously, controlling for phototoxicity in imaging experiments required additional labels and experiments, limiting its widespread application. Here we provide a proof-of-principle demonstration that the phototoxic effects of an imaging experiment can be identified directly from a single phase-contrast image using deep convolutional neural networks (ConvNets). This lays the groundwork for an automated tool for assessing cell health in a wide range of imaging experiments. Interpretability of such a method is crucial for its adoption. We take steps towards interpreting the classification mechanism of the trained ConvNet by visualizing salient features of images that contribute to accurate classification.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[3]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[6]  Alexander Mordvintsev,et al.  Inceptionism: Going Deeper into Neural Networks , 2015 .

[7]  K J Halbhuber,et al.  Pulse-length dependence of cellular response to intense near-infrared laser pulses in multiphoton microscopes. , 1999, Optics letters.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Charles Kervrann,et al.  Fast live simultaneous multiwavelength four-dimensional optical microscopy , 2010, Proceedings of the National Academy of Sciences.

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  Herbert Schneckenburger,et al.  Light Dose is a Limiting Factor to Maintain Cell Viability in Fluorescence Microscopy and Single Molecule Detection , 2010, International journal of molecular sciences.

[12]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[13]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Ramprasaath R. Selvaraju,et al.  Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization , 2016 .

[18]  T. Saif,et al.  Contractile dynamics change before morphological cues during florescence illumination , 2015, Scientific Reports.

[19]  Ram Dixit,et al.  Cell damage and reactive oxygen species production induced by fluorescence microscopy: effect on mitosis and guidelines for non-invasive fluorescence microscopy. , 2003, The Plant journal : for cell and molecular biology.

[20]  J. Sparrow,et al.  Blue light-induced apoptosis of A2E-containing RPE: involvement of caspase-3 and protection by Bcl-2. , 2001, Investigative ophthalmology & visual science.

[21]  I. Vorobjev,et al.  Blue Light Inhibits Mitosis in Tissue Culture Cells , 1998, Bioscience reports.

[22]  S. van de Linde,et al.  Light-induced cell damage in live-cell super-resolution microscopy , 2015, Scientific Reports.

[23]  Pascal Roux,et al.  A quantitative method for measuring phototoxicity of a live cell imaging microscope. , 2012, Methods in enzymology.

[24]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .