arXiv subjects

Jiaming Guo

Publications and source records attributed to Jiaming Guo.

58 records · Page 4Linked to original sources

arXiv2019

Multi-label Detection and Classification of Red Blood Cells in Microscopic Images

Cell detection and cell type classification from biomedical images play an important role for high-throughput imaging and various clinical application. While classification of single cell sample can be performed with standard computer vision and machine learning methods, analysis of multi-label samples (region containing congregating cells) is more challenging, as separation of individual cells can be difficult (e.g. touching cells) or even impossible (e.g. overlapping cells). As multi-instance images are common in analyzing Red Blood Cell (RBC) for Sickle Cell Disease (SCD) diagnosis, we develop and implement a multi-instance cell detection and classification framework to address this challenge. The framework firstly trains a region proposal model based on Region-based Convolutional Network (RCNN) to obtain bounding-boxes of regions potentially containing single or multiple cells from input microscopic images, which are extracted as image patches. High-level image features are then calculated from image patches through a pre-trained Convolutional Neural Network (CNN) with ResNet-50 structure. Using these image features inputs, six networks are then trained to make multi-label prediction of whether a given patch contains cells belonging to a specific cell type. As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples. Finally, for the purpose of SCD testing, we train another machine learning classifier to predict whether the given image patch contains abnormal cell type based on outputs from the six networks. Testing result of the proposed framework shows that it can achieve good performance in automatic cell detection and classification.

eess.IV↗

arXiv2019

Predicting Alzheimer's Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging

Imaging-based early diagnosis of Alzheimer Disease (AD) has become an effective approach, especially by using nuclear medicine imaging techniques such as Positron Emission Topography (PET). In various literature it has been found that PET images can be better modeled as signals (e.g. uptake of florbetapir) defined on a network (non-Euclidean) structure which is governed by its underlying graph patterns of pathological progression and metabolic connectivity. In order to effectively apply deep learning framework for PET image analysis to overcome its limitation on Euclidean grid, we develop a solution for 3D PET image representation and analysis under a generalized, graph-based CNN architecture (PETNet), which analyzes PET signals defined on a group-wise inferred graph structure. Computations in PETNet are defined in non-Euclidean, graph (network) domain, as it performs feature extraction by convolution operations on spectral-filtered signals on the graph and pooling operations based on hierarchical graph clustering. Effectiveness of the PETNet is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which shows improved performance over both deep learning and other machine learning-based methods.

cs.LG↗

arXiv2019

Three-Dimensional Microscopy by Milling with Ultraviolet Excitation

Analysis of three-dimensional biological samples is critical to understanding tissue function and the mechanisms of disease. Many chronic conditions, like neurodegenerative diseases and cancers, correlate with complex tissue changes that are difficult to explore using two-dimensional histology. While three-dimensional techniques such as confocal and light-sheet microscopy are well-established, they are time consuming, require expensive instrumentation, and are limited to small tissue volumes. Three-dimensional microscopy is therefore impractical in clinical settings and often limited to core facilities at major research institutions. There would be a tremendous benefit to providing clinicians and researchers with the ability to routinely image large three-dimensional tissue volumes at cellular resolution. In this paper, we propose an imaging methodology that enables fast and inexpensive three-dimensional imaging that can be readily integrated into current histology pipelines. This method relies on block-face imaging of paraffin-embedded samples using deep-ultraviolet excitation. The imaged surface is then ablated to reveal the next tissue section for imaging. The final image stack is then aligned and reconstructed to provide tissue models that exceed the depth and resolution achievable with modern three-dimensional imaging systems.

physics.bio-ph↗

arXiv2019

Unsupervised Bi-directional Flow-based Video Generation from one Snapshot

Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this work, we leverage an unsupervised variational model to learn rich motion patterns in the form of long-term bi-directional flow fields, and apply the predicted flows to generate high-quality video sequences. In contrast to the state-of-the-art approach, our method does not require external flow supervisions for learning. This is achieved through a novel module that performs bi-directional flows prediction from a single image. In addition, with the bi-directional flow consistency check, our method can handle occlusion and warping artifacts in a principled manner. Our method can be trained end-to-end based on arbitrarily sampled natural video clips, and it is able to capture multi-modal motion uncertainty and synthesizes photo-realistic novel sequences. Quantitative and qualitative evaluations over synthetic and real-world datasets demonstrate the effectiveness of the proposed approach over the state-of-the-art methods.

cs.CV↗