Search for: All records

We present a solution to image-based cell counting with dot annotations for both 2D and 3D cases. Current approaches have two major limitations: 1) inability to provide precise locations when cells overlap; and 2) reliance on costly labeled data. To address these two issues, we first adopt the inverse distance kernel, which yields separable density maps for better localization. Second, we take advantage of unlabeled data by self-supervised learning with focal consistency loss, which we propose for our pixel-wise task. These two contributions complement each other. Together, our framework compares favorably against stateof- the-art methods, including methods using full annotations on 2D and 3D benchmarks, while significantly reducing the amount of labeled data needed for training. In addition, we provide a tool to expedite the labeling process for dot annotations. Finally, we make the source code and labeling tool publicly available. 

Abstract. The widely used open-source community Noah with multi-parameterization options (Noah-MP) land surface model (LSM) isdesigned for applications ranging from uncoupled land surfacehydrometeorological and ecohydrological process studies to coupled numericalweather prediction and decadal global or regional climate simulations. It hasbeen used in many coupled community weather, climate, and hydrology models. Inthis study, we modernize and refactor the Noah-MP LSM by adopting modern Fortrancode standards and data structures, which substantially enhance the modelmodularity, interoperability, and applicability. The modernized Noah-MP isreleased as the version 5.0 (v5.0), which has five key features: (1) enhanced modularization as a result of re-organizing model physics into individualprocess-level Fortran module files, (2) an enhanced data structure with newhierarchical data types and optimized variable declaration andinitialization structures, (3) an enhanced code structure and calling workflowas a result of leveraging the new data structure and modularization, (4) enhanced(descriptive and self-explanatory) model variable naming standards, and (5) enhanced driver and interface structures to be coupled with the hostweather, climate, and hydrology models. In addition, we create a comprehensivetechnical documentation of the Noah-MP v5.0 and a set of model benchmark andreference datasets. The Noah-MP v5.0 will be coupled to variousweather, climate, and hydrology models in the future. Overall, the modernizedNoah-MP allows a more efficient and convenient process for future modeldevelopments and applications. 

Image-based cell counting is a fundamental yet challenging task with wide applications in biological research. In this paper, we propose a novel unified deep network framework designed to solve this problem for various cell types in both 2D and 3D images. Specifically, we first propose SAU-Net for cell counting by extending the segmentation network U-Net with a Self-Attention module. Second, we design an extension of Batch Normalization (BN) to facilitate the training process for small datasets. In addition, a new 3D benchmark dataset based on the existing mouse blastocyst (MBC) dataset is developed and released to the community. Our SAU-Net achieves state-of-the-art results on four benchmark 2D datasets - synthetic fluorescence microscopy (VGG) dataset, Modified Bone Marrow (MBM) dataset, human subcutaneous adipose tissue (ADI) dataset, and Dublin Cell Counting (DCC) dataset, and the new 3D dataset, MBC. The BN extension is validated using extensive experiments on the 2D datasets, since GPU memory constraints preclude use of 3D datasets. The source code is available at https://github.com/mzlr/sau-net.