Author name cluster

Zhenghai Huang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

YNIMG Journal 2026 Journal Article

Standardized quantification of [18F]Florbetazine amyloid PET with the Centiloid scale

Meiqi Wu
Menglin Liang
Chenhui Mao
Liling Dong
Qi Ge
Yuying Li
Jingnan Wang
Chao Ren

C]PiB across different image-processing pipelines and effective image resolutions (EIRs). METHODS: C]PiB SUVR were evaluated under different EIRs. RESULTS: F]FBZ SUVR were observed across EIRs with the SPM pipeline, whereas regression parameters varied across EIRs with the FreeSurfer pipeline. CONCLUSION: F]FBZ demonstrated equal or improved quantification precision, supporting its broader use in clinical and research Aβ imaging.

Details DOI

YNIMG Journal 2024 Journal Article

Evaluation of a novel PET tracer [18F]-Florbetazine for Alzheimer's disease diagnosis and β-amyloid deposition quantification

Meiqi Wu
Chao Ren
Chenhui Mao
Liling Dong
Bo Li
Xueqian Yang
Zhenghai Huang
Haiqiong Zhang

F]-92) is a selective PET tracer for β-amyloid (Aβ) depositions with a novel diaryl-azine scaffold to reduce lipophilicity and to achieve higher gray-to-white matter contrast. We aimed to assess its diagnostic value in Alzheimer's disease (AD) and pharmacokinetics characteristics in human subjects. METHODS: F]-Florbetazine and a structural MRI scan. The time-activity-curves (TACs) for volumes of interest (VOIs) in cerebral cortex, cerebellar cortex and cerebral white matter was depicted and their standardized uptake value ratios (SUVRs) with cerebellar cortex as reference were compared between HCs and AD patients. The cerebral gray-to-white matter SUV ratio (GWR) was also calculated. RESULTS: In HCs, radioactivities in the cerebral cortex VOIs were homogeneously low and at the same level as in cerebellar cortex, while in AD patients, cortical VOIs expected to contain Aβ exhibited high radioactivity. Cerebral cortex SUVRs remain relatively low in HCs while keep increasing along with time in AD patients. After 15 min, the cerebral cortex SUVRs became significant higher in AD patients compared to HCs with 100 % discrimination accuracy. In AD patients, GWR remained over 1.3 for all time intervals and visual inspection showed lower uptake in cerebral white matter compared to cerebral cortex. CONCLUSION: F]-Florbetazine can be potentially used for detection and quantification of Aβ depositions in the living human brain.

Details DOI

AAAI Conference 2021 Conference Paper

A Trace-restricted Kronecker-Factored Approximation to Natural Gradient

Kaixin Gao
Xiaolei Liu
Zhenghai Huang
Min Wang
Zidong Wang
Dachuan Xu
Fan Yu

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use secondorder optimization methods for training deep neural networks. In this work, inspired by diagonal approximations and factored approximations such as Kronecker-factored Approximate Curvature (KFAC), we propose a new approximation to the Fisher information matrix (FIM) called Trace-restricted Kronecker-factored Approximate Curvature (TKFAC), which can hold the certain trace relationship between the exact and the approximate FIM. In TKFAC, we decompose each block of the approximate FIM as a Kronecker product of two smaller matrices and scaled by a coefficient related to trace. We theoretically analyze TKFAC’s approximation error and give an upper bound of it. We also propose a new damping technique for TKFAC on convolutional neural networks to maintain the superiority of second-order optimization methods during training. Experiments show that our method has better performance compared with several state-of-the-art algorithms on some deep network architectures.

PDF Details

AAAI Conference 2021 Conference Paper

THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation

Mengyun Chen
Kaixin Gao
Xiaolei Liu
Zidong Wang
Ningxi Ni
Qian Zhang
Lei Chen
Chao Ding

It is well-known that second-order optimizer can accelerate the training of deep neural networks, however, the huge computation cost of second-order optimization makes it impractical to apply in real practice. In order to reduce the cost, many methods have been proposed to approximate a second-order matrix. Inspired by KFAC, we propose a novel Trace-based Hardware-driven layer-ORiented Natural Gradient Descent Computation method, called THOR, to make the second-order optimization applicable in the real application models. Specifically, we gradually increase the update interval and use the matrix trace to determine which blocks of Fisher Information Matrix (FIM) need to be updated. Moreover, by resorting the power of hardware, we have designed a hardware-driven approximation method for computing FIM to achieve better performance. To demonstrate the effectiveness of THOR, we have conducted extensive experiments. The results show that training ResNet-50 on ImageNet with THOR only takes 66. 7 minutes to achieve a top-1 accuracy of 75. 9 % under an 8 Ascend 910 environment with MindSpore, a new deep learning computing framework. Moreover, with more computational resources, THOR can only takes 2. 7 minutes to 75. 9 % with 256 Ascend 910.

PDF Details