Lichao Wang

Lichao Wang

Auto-generated profile, based on publicly available information

Lichao Wang

Imperial College London, London, UK

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
9 April 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
XXXiaodan Xing
Xiaodan Xing
HWHuanjun Wu
Huanjun Wu
LWLichao Wang
Lichao Wang
ISIain Stenson
Iain Stenson
MYMay Yong
May Yong
Guang YangGuang Yang
Guang Yang
Data quality is a key factor in the development of trustworthy AI in healthcare. A large volume of curated datasets with controlled confounding factors can improve the accuracy, robustness, and privacy of downstream AI algorithms. However, access to high-quality datasets is limited by the technical difficulties of data acquisition, and large-scale sharing of healthcare data is hindered by strict ethical restrictions. Data synthesis algorithms, which generate data with distributions similar to real clinical data, can serve as a potential solution to address the scarcity of good quality data during the development of trustworthy AI. However, state-of-the-art data synthesis algorithms, especially deep learning algorithms, focus more on imaging data while neglecting the synthesis of non-imaging healthcare data, including clinical measurements, medical signals and waveforms, and electronic healthcare records (EHRs). Therefore, in this article, we will review synthesis algorithms, particularly for non-imaging medical data, with the aim of providing trustworthy AI in this domain. This tutorial-style review article will provide comprehensive descriptions of non-imaging medical data synthesis, covering aspects such as algorithms, evaluations, limitations, and future research directions.

6 July 2016 in Oncotarget
Verified
Journal Article
Open access
PDF file
LCLinbo Cai
Linbo Cai
XQXiaoguang Qiu
Xiaoguang Qiu
HYHaihong Yang
Haihong Yang
MLMingyao Lai
Mingyao Lai
CSChangguo Shan
Changguo Shan
LWLichao Wang
Lichao Wang
// <![CDATA[ $('.header-date').hide();$('#titleAuthors').hide();$('#abstractHeader').hide(); // ]]> Linbo Cai1, Xiaoguang Qiu2, Haihong Yang3, Mingyao Lai1, Changguo Shan1, Weiping Hong1, Juan Li1, Longhui Luo1, Ping Zhang1, Lichao Wang1 1Department of Oncology, Guangdong 999 Brain Hospital, Guangzhou, China 2Department of Neurosurgery of Beijing Tiantan Hospital, Capital Medical University, Beijing, China 3Department of Oncology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China Correspondence to: Linbo Cai, email: cai_linbo@sina.com Xiaoguang Qiu, email: qxgtiantan@sina.com Keywords: stereotactic radiosurgery, X-knife, EGFR, NSCLC, brain metastases Received: February 23, 2016 Accepted: June 09, 2016 Published: July 06, 2016 ABSTRACT Background: Stereotactic radiosurgery (SRS) is a widely used therapy for brain metastases(BMs) in Non-small cell lung cancer(NSCLC). However, its role in symptomatic patients with EGFR mutation remains unclear. We have retrospectively reviewed the clinical data of patients with symptomatic BMs whom received SRS as a salvage approach and concurrent gifitinib therapy. Methods: Seven patients with primary NSCLC, symptomatic BMs, and EGFR mutation were identified in a retrospective review of patients treated with SRS using X-knife at Guangdong 999 Brain Hospital between 1 January 2012 and 31 August 2014. The median follow-up of these patients was 16 months. Image fusion technique was used to determine cumulative doses to targeted lesions, whole brain, and critical brain structures. Toxicities and complications were identified by clinical records. Results: SRS(X-knife) was selected to be performed on seven patients (two males and five females) diagnosed with NSCLC and EGFR mutation due to the presence of encephaledema, compression of ventricles, or other complications. Neurological symptoms (such as paresis, aphasia, sensory and visual disturbances) were not present in any patients before or after SRS treatment, and the postoperative Karnofsky performance status(KPS) was improved in all patients. Median overall survival(OS) was 16 months and median progression free survival(PFS) was 10 months. Conclusions: The improvement of KPS and survival were reliable by SRS(X-knife) with concurrent gifitinib therapy in NSCLC patients with symptomatic BMs, and EGFR mutation. Given the small sample size, further prospective studies with a greater number of patients are warranted to confirm our results.

1 April 2013
Verified
Journal Article
Closed access
LCLinbo Cai
Linbo Cai
JLJuan Li
Juan Li
MLMing-Yao Lai
Ming-Yao Lai
CSChang-Guo Shan
Chang-Guo Shan
ZLZong-De Lian
Zong-De Lian
LWLi-Chao Wang
Li-Chao Wang

27 June 2017 in F1000Research
Verified
Journal Article
Open access
PDF file
SPSebastian Pölsterl
Sebastian Pölsterl
PGPankaj Gupta
Pankaj Gupta
LWLichao Wang
Lichao Wang
SCSailesh Conjeti
Sailesh Conjeti
AKAmin Katouzian
Amin Katouzian
NNNassir Navab
Nassir Navab
Ensemble methods have been successfully applied in a wide range of scenarios, including survival analysis. However, most ensemble models for survival analysis consist of models that all optimize the same loss function and do not fully utilize the diversity in available models. We propose heterogeneous survival ensembles that combine several survival models, each optimizing a different loss during training. We evaluated our proposed technique in the context of the Prostate Cancer DREAM Challenge, where the objective was to predict survival of patients with metastatic, castrate-resistant prostate cancer from patient records of four phase III clinical trials. Results demonstrate that a diverse set of survival models were preferred over a single model and that our heterogeneous ensemble of survival models outperformed all competing methods with respect to predicting the exact time of death in the Prostate Cancer DREAM Challenge.