Related papers: CTransformer: Deep-transformer-based 3D cell membr…

Recent advancements in the ability to construct three-dimensional (3D) tissues and organoids from stem cells and biomaterials have not only opened abundant new research avenues in disease modeling and regenerative medicine but also have…

Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks, largely attributed to their long-range self-attention mechanism and scalability. However, most transformer architectures embed…

Properties of crystalline materials are closely linked to microstructure arising from the spatial arrangement, orientation, and phase of nanocrystals. Rapid characterization of crystalline microstructure can accelerate the identification of…

Understanding the morphological structure of medical images and precisely segmenting the region of interest or abnormality is an important task that can assist in diagnosis. However, the unique properties of medical imaging make clear…

Transformer-based neural networks have surpassed promising performance on many biomedical image segmentation tasks due to a better global information modeling from the self-attention mechanism. However, most methods are still designed for…

Recovering 3D phase features of complex, multiple-scattering biological samples traditionally sacrifices computational efficiency and processing time for physical model accuracy and reconstruction quality. This trade-off hinders the rapid…

Recent breakthroughs in self-supervised learning have enabled the use of large unlabeled datasets to train visual foundation models that can generalize to a variety of downstream tasks. While this training paradigm is well suited for the…

Abdominal multi-organ segmentation in computed tomography (CT) is crucial for many clinical applications including disease detection and treatment planning. Deep learning methods have shown unprecedented performance in this perspective.…

Diffusion MRI (dMRI) provides unique insights into fetal brain microstructure in utero. Longitudinal and cross-sectional fetal dMRI studies can reveal crucial neurodevelopmental changes but require precise spatial alignment across scans and…

The placenta is a complex organ, playing multiple roles during fetal development. Very little is known about the association between placental morphological abnormalities and fetal physiology. In this work, we present an open sourced,…

"Epigenetic Tracking" is a model of systems of biological cells, able to generate arbitrary 2 or 3-dimensional cellular shapes of any kind and complexity (in terms of number of cells, number of colours, etc.) starting from a single cell. If…

We present feature finding and tracking algorithms in 3D in living cells, and demonstrate their utility to measure metrics important in cell biological processes. We developed a computational imaging hybrid approach that combines automated…

During development, cell fates are determined through a combination of intracellular transcriptional regulations and extracellular signaling. As a result, spatial patterns of different cell types arise. We investigate the decision between…

Through mechanical forces, biological cells remodel the surrounding collagen network, generating striking deformation patterns. Tethers-tracts of high densification and fiber alignment-form between cells, thinner bands emanate from cell…

In this study, we build upon a previously proposed neuroevolution framework to evolve deep convolutional models. Specifically, the genome encoding and the crossover operator are extended to make them applicable to layered networks. We also…

The membrane curvature of cells and intracellular compartments continuously adapts to enable cells to perform vital functions, from cell division to signal trafficking. Understanding how membrane geometry affects these processes in vivo is…

Reconstructing neuron morphology from 3D light microscope imaging data is critical to aid neuroscientists in analyzing brain networks and neuroanatomy. With the boost from deep learning techniques, a variety of learning-based segmentation…

Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently,…

Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels. While there exist various 2D graph-based molecular pretraining approaches,…

We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab…