Cheng Kang

Cheng Kang


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 December 2017 in Scientific Reports
Verified
Journal Article
Open access
PDF file
YLYuezhi Li
Yuezhi Li
CKCheng Kang
Cheng Kang
ZWZhaoguo Wei
Zhaoguo Wei
XQXingda Qu
Xingda Qu
TLTiebang Liu
Tiebang Liu
YHYong Hu
Yong Hu
This study aimed to examine alterations in electroencephalography (EEG) phase synchronization in working memory processing in depressed patients. Sixty-four-channel EEG signals were recorded from 33 depressed patients and 32 healthy controls during a visual n-back task. Alterations in functional connections in the patients were investigated using event-related phase coherence in terms of the phase synchronization index (PSI). Compared with the control subjects, the depressed patients showed a lower task-dependent increase in the PSI of delta, theta, and alpha oscillations in a frontoparietal network, but a higher task-dependent increase in the PSI of beta oscillations in the frontoparietal network. Additionally, depressed patients showed a lower task-dependent decrease in the PSI of delta, theta, alpha, and beta oscillations in centro-parieto-occipital sites. Insufficient phase synchronization and desynchronization during working memory processing reflects impairments in cortical inhibition, memory, and attention efficiency in major depression, while the abnormal increase in phase synchronization in beta oscillations in the frontoparietal network may indicate a new cortical circuit concerned with the repair of impaired ability in attention, memory retention, and working memory central executive processing. These findings present a compensatory mechanism for impaired cognitive function in major depression, and advance our understanding of functional aspect of beta oscillations.

13 April 2020 in IEEE/ACM Transactions on Computational Biology and Bioinformatics
Verified
Journal Article
Closed access
XYXiang Yu
Xiang Yu
CKCheng Kang
Cheng Kang
DGDavid Guttery
David Guttery
Seifedine KadrySeifedine Kadry
Seifedine Kadry
YCYang Chen
Yang Chen
Yudong ZhangYudong Zhang
Yudong Zhang
Breast cancer is the most common cancer in women and the second most common cancer worldwide. Based on mammographic imaging, a mainstream clinical breast screening technique, we present a diagnostic system for accurate classification of breast abnormalities based on ResNet-50. To improve the proposed model, we created a new data augmentation framework called SCDA (Scaling and Contrast limited adaptive histogram equalization Data Augmentation). In its procedure, we first conduct the scaling operation to the original training set, followed by applying contrast limited adaptive histogram equalisation (CLAHE) to the scaled training set. By stacking the training set after SCDA with the original training set, we formed a new training set. The network trained by the augmented training set, was coined as ResNet-SCDA-50. Our system, which aims at a binary classification on mammographic images acquired from INbreast and MINI-MIAS, classifies masses, microcalcification as "abnormal", while normal regions are classified as "normal". We present the first attempt to use the image contrast enhancement method as the data augmentation method, resulting in an averaged 98.55% specificity and 92.83% sensitivity, which gives our best model an overall accuracy of 95.74%. Our proposed method is effective in classifying breast abnormality.

13 January 2020 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Open access
CKCheng Kang
Cheng Kang
XYXiang Yu
Xiang Yu
Shuihua WangShuihua Wang
Shuihua Wang
DGDavid Guttery
David Guttery
HPHari Mohan Pandey
Hari Mohan Pandey
Yudong ZhangYudong Zhang
Yudong Zhang
Traditional deep learning methods are suboptimal in classifying ambiguity features, which often arise in noisy and hard to predict categories, especially, to distinguish semantic scoring. Semantic scoring, depending on semantic logic to implement evaluation, inevitably contains fuzzy description and misses some concepts, for example, the ambiguous relationship between normal and probably normal always presents unclear boundaries (normal—more likely normal—probably normal). Thus, human error is common when annotating images. Differing from existing methods that focus on modifying kernel structure of neural networks, this article proposes a dominant fuzzy fully connected layer (FFCL) for breast imaging reporting and data system (BI-RADS) scoring and validates the universality of this proposed structure. This proposed model aims to develop complementary properties of scoring for semantic paradigms, while constructing fuzzy rules based on analyzing human thought patterns, and to particularly reduce the influence of semantic conglutination. Specifically, this semantic-sensitive defuzzifier layer projects features occupied by relative categories into semantic space, and a fuzzy decoder modifies probabilities of the last output layer referring to the global trend. Moreover, the ambiguous semantic space between two relative categories shrinks during the learning phases, as the positive and negative growth trends of one category appearing among its relatives were considered. We first used the Euclidean distance to zoom in the distance between the real scores and the predicted scores, and then employed two sample t test method to evidence the advantage of the FFCL architecture. Extensive experimental results performed on the curated breast imaging subset of digital database of screening mammography dataset show that our FFCL structure can achieve superior performances for both triple and multiclass classification in BI-RADS scoring, outperforming the state-of-the-art methods.

26 September 2016 in Frontiers in Human Neuroscience
Verified
Journal Article
Open access
YLYuezhi Li
Yuezhi Li
CKCheng Kang
Cheng Kang
XQXingda Qu
Xingda Qu
YZYunfei Zhou
Yunfei Zhou
WWWuyi Wang
Wuyi Wang
YHYong Hu
Yong Hu
This study is to examine changes of functional connectivity in patients with depressive disorder using synchronous brain activity. Event-related potentials were acquired during a visual oddball task in 14 patients with depressive disorder and 19 healthy controls. Electroencephalogram recordings were analyzed using event-related phase coherence to obtain the functional network. Alteration of the phase synchronization index (PSI) of the functional network was investigated. Patients with depression showed a decreased number of significant electrode pairs in delta phase synchronization, and an increased number of significant electrode pairs in theta, alpha, and beta phase synchronization, compared with controls. Patients with depression showed lower target-dependent PSI increment in the frontal-parietal/temporal/occipital electrode pairs in delta-phase synchronization than healthy participants. However, patients with depression showed higher target-dependent PSI increments in theta band in the prefrontal/frontal and frontal-temporal electrode pairs, higher PSI increments in alpha band in the prefrontal pairs, and higher increments of beta PSI in the central and right frontal-parietal pairs than controls. It implied that the decrease in delta PSI activity in major depression may indicate impairment of the connection between the frontal and parietal/temporal/occipital regions. The increase in theta, alpha, and beta PSI in the frontal/prefrontal sites may reflect the compensatory mechanism to maintain normal cognitive performance. These findings may provide a foundation for a new approach to assess the effectiveness of therapeutic strategies for depression.


26 May 2020 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Closed access
CKCheng Kang
Cheng Kang
YLYuezhi Li
Yuezhi Li
DNDaniel Novak
Daniel Novak
Yudong ZhangYudong Zhang
Yudong Zhang
QZQinghua Zhou
Qinghua Zhou
YHYong Hu
Yong Hu
Working memory (WM) – one of the brain ability that maintains information – can evaluate the function of brain. Activities related to memory sustention, inhibition and disinhibition have gathered significant attention for the basic neurocognitive architecture. Although researchers have proposed some brain models that attempt to explain the entire procedure of WM, little evidence can proof and describe it, and more particularly, regions and structures of maintenance, inhibition and disinhibition require more investigation. We used phase lock coherence and general partial directed coherence to construct connections among four adaptively fitted EEG sources, and we also applied previous published models to describe the brain circuits of maintenance, inhibition and disinhibition. Referring to a classical visual n-back paradigm, we recruited forty five mental health undergraduates in this experiment. We found that the bilateral prefrontal cortex (PFC) mainly focused on some cognitive components, for example, rehearsal before recognition to classify objects, inhibition to maintain positive memory and activities, and disinhibition to arouse or activate subsequent interactions in brain. Meanwhile, the right PFC sometimes could assist left PFC to implement high capacity WM tasks. By contrast, the posterior regions, PPC, tends to be engaged in attention arousing and maintaining. These two findings suggest that a) the recurrent maintenance circuit may keep the brain executing positive cognitive components, b) then the instantly monitoring inhibition would pause the deadlocked sustention function to save energy, and c) the arriving of disinhibition arouses the next step in brain to select new subject or focus on novel subjects.