Biology subjects

Khadangi, A.

Publications and source records attributed to Khadangi, A..

3 recordsLinked to original sources

bioRxiv2021

CardioVinci: building blocks for virtual cardiac cells using deep learning

Recent advances in high-throughput microscopy imaging have made it easier to acquire large volumes of cell images. Thanks to electron microscopy (EM) imaging, they provide a high-resolution and sufficient field of view that suits imaging large cell types, including cardiomyocytes. A significant bottleneck with these large datasets is the time taken to collect, extract and statistically analyse 3D changes in cardiac ultrastructures. We address this bottleneck with CardioVinci.

bioinformatics↗

bioRxiv2020

EM-stellar: benchmarking deep learning for electron microscopy image segmentation

The inherent low contrast of electron microscopy (EM) datasets presents a significant challenge for rapid segmentation of cellular ultrastructures from EM data. This challenge is particularly prominent when working with high resolution big-datasets that are now acquired using electron tomography and serial block-face imaging techniques. Deep learning (DL) methods offer an exciting opportunity to automate the segmentation process by learning from manual annotations of a small sample of EM data. While many DL methods are being rapidly adopted to segment EM data no benchmark analysis has been conducted on these methods to date. We present EM-stellar, a Jupyter Notebook platform that is hosted on google Colab that can be used to benchmark the performance of a range of state-of-the-art DL methods on user-provided datasets. Using EM-Stellar we show that the performance of any DL method is dependent on the properties of the images being segmented. It also follows that no single DL method performs consistently across all performance evaluation metrics.

bioinformatics↗

bioRxiv2020

EM-net: Deep learning for electron microscopy image segmentation

Recent high-throughput electron microscopy techniques such as focused ion-beam scanning electron microscopy (FIB-SEM) provide thousands of serial sections which assist the biologists in studying sub-cellular structures at high resolution and large volume. Low contrast of such images hinder image segmentation and 3D visualisation of these datasets. With recent advances in computer vision and deep learning, such datasets can be segmented and reconstructed in 3D with greater ease and speed than with previous approaches. However, these methods still rely on thousands of ground-truth samples for training and electron microscopy datasets require significant amounts of time for carefully curated manual annotations. We address these bottlenecks with EM-net, a scalable deep convolutional neural network for EM image segmentation. We have evaluated EM-net using two datasets, one of which belongs to an ongoing competition on EM stack segmentation since 2012. We show that EM-net variants achieve better performances than current deep learning methods using small- and medium-sized ground-truth datasets. We also show that the ensemble of top EM-net base classifiers outperforms other methods across a wide variety of evaluation metrics.

bioinformatics↗