Single-cell segmentation in bacterial biofilms with an optimized deep learning method enables tracking of cell lineages and measurements of growth rates

Article Biochemical Research Methods

DeLTA 2.0: A deep learning pipeline for quantifying single-cell spatial and temporal dynamics

Owen M. O’Connor et al.

PLoS Computational Biology (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Deep learning exoplanets detection by combining real and synthetic data

Sara Cuéllar et al.

PLoS One (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

Shared biophysical mechanisms determine early biofilm architecture development across different bacterial species

Hannah Jeckel et al.

Summary: This study reveals shared biophysical mechanisms that determine early biofilm architecture development at the single-cell level, regulated by cellular aspect ratio and cell density.

PLOS BIOLOGY (2022)

添加到收藏夹

Proceedings Paper Engineering, Biomedical

REALISTIC-SHAPE BACTERIAL BIOFILM SIMULATOR FOR DEEP LEARNING-BASED 3D SINGLE-CELL SEGMENTATION

Tanjin Taher Toma et al.

Summary: Bacterial biofilms are complex biological systems that are important in areas such as infectious diseases and fuel cells. However, our understanding of biofilm communities is limited due to barriers in live cell imaging and analysis. Developing effective automatic image analysis techniques can provide new insights into unknown characteristics of individual bacteria cells within biofilms such as structure and cell-to-cell interaction.

2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022) (2022)

添加到收藏夹

Article Biochemistry & Molecular Biology

EASI-FISH for thick tissue defines lateral hypothalamus spatio-molecular organization

Yuhan Wang et al.

Summary: The study introduces EASI-FISH technology and a computational pipeline for investigating gene expression and cell type distribution in brain tissue. Through research in the LHA region, nine spatially and molecularly defined cell subregions were identified.

CELL (2021)

添加到收藏夹

Review Microbiology

Advances and opportunities in image analysis of bacterial cells and communities

Hannah Jeckel et al.

Summary: This article discusses the importance of cellular morphology and sub-cellular spatial structure on microbial cell function, as well as the development of computational image analysis techniques. By utilizing automated image processing, quantification of properties of single cells and microbial communities can be achieved, opening up new opportunities for quantitative studies in microbiology.

FEMS MICROBIOLOGY REVIEWS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Weighted boxes fusion: Ensembling boxes from different object detection models

Roman Solovyev et al.

Summary: This study introduces a novel method, weighted boxes fusion, for combining predictions from different object detection models, significantly improving the quality of the ensemble predicted rectangles. The method achieved top results in various datasets and challenges, with the 3D version of boxes fusion being successfully applied in winning teams of specific competitions.

IMAGE AND VISION COMPUTING (2021)

添加到收藏夹

Article Biology

Spatial alanine metabolism determines local growth dynamics of Escherichia coli colonies

Francisco Diaz-Pascual et al.

Summary: Bacteria commonly live in spatially structured biofilm assemblages, where metabolic activity leads to physiologically differentiated subpopulations. Study on E. coli colony biofilms reveals spatial and temporal heterogeneity in alanine metabolism, impacting cellular viability and growth, and shaping colony morphology. Overall, there is a remarkable spatiotemporal complexity of metabolism in biofilms, which is crucial for understanding biofilm physiology, architecture, and function.

ELIFE (2021)

添加到收藏夹

Article Biochemical Research Methods

Single-objective high-resolution confocal light sheet fluorescence microscopy for standard biological sample geometries

Stoyan Yordanov et al.

Summary: A single-objective light sheet fluorescence system was developed for biological imaging, utilizing axial plane optical microscopy and digital confocal slit detection to reduce phototoxicity and photobleaching. This system offers similar optical resolution to spinning disk confocal microscopy but significantly reduces photobleaching at the same signal level.

BIOMEDICAL OPTICS EXPRESS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Boosting Instance Segmentation with Synthetic Data: A study to overcome the limits of real world data sets

Florentin Poucin et al.

Summary: A major challenge in computer vision for the automotive industry is the huge amount of well-annotated data required for real-world perception models, which can be addressed by using synthetically-generated images as an efficient alternative. This paper proposes a simple approach of combining synthetic and real images to enhance instance segmentation, with a training strategy based on dataset mixing that overcomes domain shift between real and synthetic datasets. Comparison studies highlight the benefits of this method in boosting network performance on both real and synthetic image inferences.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) (2021)

添加到收藏夹

Review Biochemistry & Molecular Biology