RESUMO
Our sense of hearing is mediated by cochlear hair cells, of which there are two types organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains 5-15 thousand terminally differentiated hair cells, and their survival is essential for hearing as they do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. Machine learning can be used to automate the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, rat, guinea pig, pig, primate, and human cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 107,000 hair cells which have been identified and annotated as either inner or outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair-cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to give other hearing research groups the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.
Assuntos
Cóclea , Animais , Camundongos , Cobaias , Humanos , Ratos , Suínos , Células Ciliadas Auditivas , Microscopia de Fluorescência , Aprendizado de MáquinaRESUMO
Our sense of hearing is mediated by cochlear hair cells, localized within the sensory epithelium called the organ of Corti. There are two types of hair cells in the cochlea, which are organized in one row of inner hair cells and three rows of outer hair cells. Each cochlea contains a few thousands of hair cells, and their survival is essential for our perception of sound because they are terminally differentiated and do not regenerate after insult. It is often desirable in hearing research to quantify the number of hair cells within cochlear samples, in both pathological conditions, and in response to treatment. However, the sheer number of cells along the cochlea makes manual quantification impractical. Machine learning can be used to overcome this challenge by automating the quantification process but requires a vast and diverse dataset for effective training. In this study, we present a large collection of annotated cochlear hair-cell datasets, labeled with commonly used hair-cell markers and imaged using various fluorescence microscopy techniques. The collection includes samples from mouse, human, pig and guinea pig cochlear tissue, from normal conditions and following in-vivo and in-vitro ototoxic drug application. The dataset includes over 90'000 hair cells, all of which have been manually identified and annotated as one of two cell types: inner hair cells and outer hair cells. This dataset is the result of a collaborative effort from multiple laboratories and has been carefully curated to represent a variety of imaging techniques. With suggested usage parameters and a well-described annotation procedure, this collection can facilitate the development of generalizable cochlear hair cell detection models or serve as a starting point for fine-tuning models for other analysis tasks. By providing this dataset, we aim to supply other groups within the hearing research community with the opportunity to develop their own tools with which to analyze cochlear imaging data more fully, accurately, and with greater ease.
RESUMO
The segmentation of individual instances of mitochondria from imaging datasets is informative, yet time-consuming to do by hand, sparking interest in developing automated algorithms using deep neural networks. Existing solutions for various segmentation tasks are largely optimized for one of two types of biomedical imaging: high resolution three-dimensional (whole neuron segmentation in volumetric electron microscopy datasets) or two-dimensional low resolution (whole cell segmentation of light microscopy images). The former requires consistently predictable boundaries to segment large structures, while the latter is boundary invariant but struggles with segmentation of large 3D objects without downscaling. Mitochondria in whole cell 3D EM datasets often occupy the challenging middle ground: large with ambiguous borders, limiting accuracy with existing tools. To rectify this, we have developed skeleton oriented object segmentation (SKOOTS); a new segmentation approach which efficiently handles large, densely packed mitochondria. We show that SKOOTS can accurately, and efficiently, segment 3D mitochondria in previously difficult situations. Furthermore, we will release a new, manually annotated, 3D mitochondria segmentation dataset. Finally, we show this approach can be extended to segment objects in 3D light microscopy datasets. These results bridge the gap between existing segmentation approaches and increases the accessibility for three-dimensional biomedical image analysis.