Abstract. Image segmentation is a fundamental problem in biomedical image analysis. Recent advances in deep learning have achieved promising results on many biomedical image segmentation benchmarks. However, due to large variations in biomedical images (different modalities, image settings, objects, noise, etc), to utilize deep learning on a new application, it usually needs a new set of training data. This can incur a great deal of annotation effort and cost, because only biomedical experts can annotate effectively, and often there are too many instances in images (e.g., cells) to annotate. In this paper, we aim to address the following question: With limited effort (e.g., time) for annotation, what instances should be annotated in order to attain the best performance? We present a deep active learning framework that combines fully convolutional network (FCN) and active learning to significantly reduce annotation effort by making judicious suggestions on the most effective annotation areas. We utilize uncertainty and similarity information provided by FCN and formulate a generalized version of the maximum set cover problem to determine the most representative and uncertain areas for annotation. Extensive experiments using the 2015 MICCAI Gland Challenge dataset and a lymph node ultrasound image segmentation dataset show that, using annotation suggestions by our method, state-of-the-art segmentation performance can be achieved by using only 50% of training data.

No abstract

A continuing challenge in quantitative cell biology is the accurate and robust 3D segmentation of structures of interest from fluorescence microscopy images in an automated, reproducible, and widely accessible manner for subsequent interpretable data analysis. We describe the Allen Cell Structure Segmenter, a new Python-based open source toolkit developed for 3D segmentation of intracellular structures in fluorescence microscope images. This toolkit brings together classic image segmentation and iterative deep learning workflows first to generate initial high-quality 3D intracellular structure segmentations and then to easily curate these results to generate the ground truths for building robust and accurate deep learning models. The toolkit takes advantage of the high-replicate 3D live cell image data collected at the Allen Institute for Cell Science of over 30 endogenous fluorescently tagged human induced pluripotent stem cell (hiPSC) lines. Each cell line represents a different intracellular structure with one or more distinct localization patterns within undifferentiated hiPS cells and hiPSC-derived cardiomyocytes. The Allen Cell Structure Segmenter consists of two complementary elements, a classic image segmentation workflow with a restricted set of algorithms and parameters and an iterative deep learning segmentation workflow. We created a collection of 20 classic image segmentation workflows based on 20 distinct and representative intracellular structure localization patterns as a "lookup table" reference and starting point for users. The iterative deep learning workflow can take over when the classic segmentation workflow is insufficient. Two straightforward "human-in-the-loop" curation strategies convert a set of classic image segmentation workflow results into a set of 3D ground truth images for iterative model training without the need for manual painting in 3D. The deep learning model architectures used in this toolkit were designed and tested specifically for 3D fluorescence microscope images and implemented as readable scripts. This toolkit was applied to the robust segmentation of fluorescent lamin B1, which exhibits significant variability in its localization pattern during the cell cycle. The Allen Cell Structure Segmenter thus leverages state of the art computer vision algorithms in an accessible way to facilitate their application by the experimental biology researcher.

The robust specification of organ development depends on coordinated cell-cell communication. This process requires signal integration among multiple pathways, relying on second messengers such as calcium ions. Calcium signaling encodes a significant portion of the cellular state by regulating transcription factors, enzymes, and cytoskeletal proteins. However, the relationships between the inputs specifying cell and organ development, calcium signaling dynamics, and final organ morphology are poorly understood. Here, we have designed a quantitative image-analysis pipeline for decoding organ-level calcium signaling. With this pipeline, we extracted spatiotemporal features of calcium signaling dynamics during the development of the Drosophila larval wing disc, a genetic model for organogenesis. We identified specific classes of wing phenotypes that resulted from calcium signaling pathway perturbations, including defects in gross morphology, vein differentiation, and overall size. We found four qualitative classes of calcium signaling activity. These classes can be ordered based on agonist stimulation strength Gaq-mediated signaling. In vivo calcium signaling dynamics depend on both receptor tyrosine kinase/phospholipase C g and G protein-coupled receptor/phospholipase C b activities. We found that spatially patterned calcium dynamics correlate with known differential growth rates between anterior and posterior compartments. Integrated calcium signaling activity decreases with increasing tissue size, and it responds to morphogenetic perturbations that impact organ growth. Together, these findings define how calcium signaling dynamics integrate upstream inputs to mediate multiple response outputs in developing epithelial organs.

This study aimed to investigate whether hypoxia can affect nonalcoholic fatty liver disease (NAFLD) progression and the associated mechanisms, specifically regarding the hypoxia-inducible factor (HIF)-2α/peroxisome proliferator-activated receptor (PPAR)α pathway in vitro and in vivo. Recent studies have reported that, compared with HIF-1α, HIF-2α has different effects on lipid metabolism. We propose hypoxia may exacerbate NAFLD by the HIF-2α upregulation-induced suppression of PPARα in the liver. To verify this hypothesis, a steatotic human hepatocyte (L02) cell line treated with free fatty acids and a mouse model of NAFLD fed a high-fat diet were used. Steatotic hepatocytes were treated with hypoxia, HIF-2α siRNA, PPARα agonists, and inhibitors, respectively. Meanwhile, the NAFLD mice were exposed to intermittent hypoxia or intermittent hypoxia with PPARα agonists. The relative gene expression levels of HIF-1α, HIF-2α, mitochondrial function, fatty acid β-oxidation and lipogenesis were examined. Evidence of lipid accumulation was observed, which demonstrated that, compared with normal hepatocytes, steatotic hepatocytes exhibited higher sensitivity to hypoxia. This phenomenon was closely associated with HIF-2α. Moreover, lipid accumulation in hepatocytes was ameliorated by HIF-2α silencing or a PPARα agonist, despite the hypoxia treatment. HIF-2α overexpression under hypoxic conditions suppressed PPARα, leading to PGC-1α, NRF-1, ESRRα downregulation, and mitochondrial impairment. Additionally, β-oxidation genes such as CPT1α, CPT2α, ACOX1, and ACOX2 were downregulated and lipogenesis genes including LXRα, FAS, and SCD1 were upregulated by hypoxia. Therefore, we concluded that HIF-2α overexpression induced by hypoxia aggravated NAFLD progression by suppressing fatty acid β-oxidation and inducing lipogenesis in the liver via PPARα.