Cell type classification and unsupervised morphological phenotype identification from low-res images with deep learning

Convolutional neural networks (ConvNets) have been used for both classification and semantic segmentation of cellular images. Here we establish a method for cell type classification utilizing images taken on a benchtop microscope directly from cell culture flasks eliminating the need for a dedicated imaging platform. Significant flask-to-flask heterogeneity was discovered and overcome to support network generalization to novel data. Cell density was found to be a prominent source of heterogeneity even within the single-cell regime indicating the presence of morphological effects due to diffusion-mediated cell-cell interaction. Expert classification was poor for single-cell images and excellent for multi-cell images suggesting experts rely on the identification of characteristic phenotypes within subsets of each population and not ubiquitous identifiers. Finally we introduce Self-Label Clustering, an unsupervised clustering method relying on ConvNet feature extraction able to identify distinct morphological phenotypes within a cell type, some of which are observed to be cell density dependent.Author summaryK.Y., N.D.R., and S.X.S. designed experiments and computational analysis. K.Y. performed experiments and ConvNets design/training, K.Y., N.D.R and S.X.S wrote the paper.

Efficient ConvNet Feature Extraction with Multiple RoI Pooling for Landmark-Based Visual Localization of Autonomous Vehicles

Efficient and robust visual localization is important for autonomous vehicles. By achieving impressive localization accuracy under conditions of significant changes, ConvNet landmark-based approach has attracted the attention of people in several research communities including autonomous vehicles. Such an approach relies heavily on the outstanding discrimination power of ConvNet features to match detected landmarks between images. However, a major challenge of this approach is how to extract discriminative ConvNet features efficiently. To address this challenging, inspired by the high efficiency of the region of interest (RoI) pooling layer, we propose a Multiple RoI (MRoI) pooling technique, an enhancement of RoI, and a simple yet efficient ConvNet feature extraction method. Our idea is to leverage MRoI pooling to exploit multilevel and multiresolution information from multiple convolutional layers and then fuse them to improve the discrimination capacity of the final ConvNet features. The main advantages of our method are (a) high computational efficiency for real-time applications; (b) GPU memory efficiency for mobile applications; and (c) use of pretrained model without fine-tuning or retraining for easy implementation. Experimental results on four datasets have demonstrated not only the above advantages but also the high discriminating power of the extracted ConvNet features with state-of-the-art localization accuracy.