ArtSeg-Artifact segmentation and removal in brightfield cell microscopy images without manual pixel-level annotations.

Brightfield cell microscopy is a foundational tool in life sciences. The acquired images are prone to contain visual artifacts that hinder downstream analysis, and automatically removing them is therefore of great practical interest. Deep convolutional neural networks are state-of-the-art for image segmentation, but require pixel-level annotations, which are time-consuming to produce. Here, we propose ScoreCAM-U-Net, a pipeline to segment artifactual regions in brightfield images with limited user input. The model is trained using only image-level labels, so the process is faster by orders of magnitude compared to pixel-level annotation, but without substantially sacrificing the segmentation performance. We confirm that artifacts indeed exist with different shapes and sizes in three different brightfield microscopy image datasets, and distort downstream analyses such as nuclei segmentation, morphometry and fluorescence intensity quantification. We then demonstrate that our automated artifact removal ameliorates this problem. Such rapid cleaning of acquired images using the power of deep learning models is likely to become a standard step for all large scale microscopy experiments.

Live-cell microscopy or fluorescence anisotropy with budded baculoviruses-which way to go with measuring ligand binding to M4 muscarinic receptors?

M4 muscarinic acetylcholine receptor is a G protein-coupled receptor (GPCR) that has been associated with alcohol and cocaine abuse, Alzheimer's disease, and schizophrenia which makes it an interesting drug target. For many GPCRs, the high-affinity fluorescence ligands have expanded the options for high-throughput screening of drug candidates and serve as useful tools in fundamental receptor research. Here, we explored two TAMRA-labelled fluorescence ligands, UR-MK342 and UR-CG072, for development of assays for studying ligand-binding properties to M4 receptor. Using budded baculovirus particles as M4 receptor preparation and fluorescence anisotropy method, we measured the affinities and binding kinetics of both fluorescence ligands. Using the fluorescence ligands as reporter probes, the binding affinities of unlabelled ligands could be determined. Based on these results, we took a step towards a more natural system and developed a method using live CHO-K1-hM4R cells and automated fluorescence microscopy suitable for the routine determination of unlabelled ligand affinities. For quantitative image analysis, we developed random forest and deep learning-based pipelines for cell segmentation. The pipelines were integrated into the user-friendly open-source Aparecium software. Both image analysis methods were suitable for measuring fluorescence ligand saturation binding and kinetics as well as for screening binding affinities of unlabelled ligands.

Evaluating Very Deep Convolutional Neural Networks for Nucleus Segmentation from Brightfield Cell Microscopy Images.

Advances in microscopy have increased output data volumes, and powerful image analysis methods are required to match. In particular, finding and characterizing nuclei from microscopy images, a core cytometry task, remains difficult to automate. While deep learning models have given encouraging results on this problem, the most powerful approaches have not yet been tested for attacking it. Here, we review and evaluate state-of-the-art very deep convolutional neural network architectures and training strategies for segmenting nuclei from brightfield cell images. We tested U-Net as a baseline model; considered U-Net++, Tiramisu, and DeepLabv3+ as latest instances of advanced families of segmentation models; and propose PPU-Net, a novel light-weight alternative. The deeper architectures outperformed standard U-Net and results from previous studies on the challenging brightfield images, with balanced pixel-wise accuracies of up to 86%. PPU-Net achieved this performance with 20-fold fewer parameters than the comparably accurate methods. All models perform better on larger nuclei and in sparser images. We further confirmed that in the absence of plentiful training data, augmentation and pretraining on other data improve performance. In particular, using only 16 images with data augmentation is enough to achieve a pixel-wise F1 score that is within 5% of the one achieved with a full data set for all models. The remaining segmentation errors are mainly due to missed nuclei in dense regions, overlapping cells, and imaging artifacts, indicating the major outstanding challenges.