Jiang Li

Bio: Jiang Li is an academic researcher from Old Dominion University. The author has contributed to research in topics: Deep learning & Support vector machine. The author has an hindex of 27, co-authored 194 publications receiving 2956 citations. Previous affiliations of Jiang Li include National Institutes of Health & University of Texas at Arlington.

Deep learning based imaging data completion for improved brain disease diagnosis.

Abstract: Combining multi-modality brain data for disease diagnosis commonly leads to improved performance. A challenge in using multi-modality data is that the data are commonly incomplete; namely, some modality might be missing for some subjects. In this work, we proposed a deep learning based framework for estimating multi-modality imaging data. Our method takes the form of convolutional neural networks, where the input and output are two volumetric modalities. The network contains a large number of trainable parameters that capture the relationship between input and output modalities. When trained on subjects with all modalities, the network can estimate the output modality given the input modality. We evaluated our method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, where the input and output modalities are MRI and PET images, respectively. Results showed that our method significantly outperformed prior methods.

A Robust Deep Model for Improved Classification of AD/MCI Patients

Abstract: Accurate classification of Alzheimer's disease (AD) and its prodromal stage, mild cognitive impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of a particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight coadaptation, which is a typical cause of overfitting in deep learning. In addition, we incorporated stability selection, an adaptive learning factor, and a multitask learning strategy into the deep learning framework. We applied the proposed method to the ADNI dataset, and conducted experiments for AD and MCI conversion diagnosis. Experimental results showed that the dropout technique is very effective in AD diagnosis, improving the classification accuracies by 5.9% on average as compared to the classical deep learning methods.

Testbeam studies of production modules of the ATLAS tile calorimeter

Abstract: We report test beam studies of 11% of the production ATLAS Tile Calorimeter modules. The modules were equipped with production front-end electronics and all the calibration systems planned for the final detector. The studies used muon, electron and hadron beams ranging in energy from 3 to 350 GeV. Two independent studies showed that the light yield of the calorimeter was View the MathML source, exceeding the design goal by 40%. Electron beams provided a calibration of the modules at the electromagnetic energy scale. Over 200 calorimeter cells the variation of the response was 2.4%. The linearity with energy was also measured. Muon beams provided an intercalibration of the response of all calorimeter cells. The response to muons entering in the ATLAS projective geometry showed an RMS variation of 2.5% for 91 measurements over a range of rapidities and modules. The mean response to hadrons of fixed energy had an RMS variation of 1.4% for the modules and projective angles studied. The response to hadrons normalized to incident beam energy showed an 8% increase between 10 and 350 GeV, fully consistent with expectations for a noncompensating calorimeter. The measured energy resolution for hadrons of View the MathML source was also consistent with expectations. Other auxiliary studies were made of saturation recovery of the readout system, the time resolution of the calorimeter and the performance of the trigger signals from the calorimeter.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

Abstract: Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.