Guoying Liu

Dr. Guoying Liu


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
25 September 2018 in Cancer Communications
Verified
Journal Article
Open access
PDF file
CLChaofeng Li
Chaofeng Li
BJBingzhong Jing
Bingzhong Jing
LKLiangru Ke
Liangru Ke
BLBin Li
Bin Li
WXWeixiong Xia
Weixiong Xia
XLXing Lv
Xing Lv
Background: Due to the occult anatomic location of the nasopharynx and frequent presence of adenoid hyperplasia, the positive rate for malignancy identification during biopsy is low, thus leading to delayed or missed diagnosis for nasopharyngeal malignancies upon initial attempt. Here, we aimed to develop an artificial intelligence tool to detect nasopharyngeal malignancies under endoscopic examination based on deep learning. Methods: An endoscopic images‐based nasopharyngeal malignancy detection model (eNPM‐DM) consisting of a fully convolutional network based on the inception architecture was developed and fine‐tuned using separate training and validation sets for both classification and segmentation. Briefly, a total of 28,966 qualified images were collected. Among these images, 27,536 biopsy‐proven images from 7951 individuals obtained from January 1st, 2008, to December 31st, 2016, were split into the training, validation and test sets at a ratio of 7:1:2 using simple randomization. Additionally, 1430 images obtained from January 1st, 2017, to March 31st, 2017, were used as a prospective test set to compare the performance of the established model against oncologist evaluation. The dice similarity coefficient (DSC) was used to evaluate the efficiency of eNPM‐DM in automatic segmentation of malignant area from the background of nasopharyngeal endoscopic images, by comparing automatic segmentation with manual segmentation performed by the experts. Results: All images were histopathologically confirmed, and included 5713 (19.7%) normal control, 19,107 (66.0%) nasopharyngeal carcinoma (NPC), 335 (1.2%) NPC and 3811 (13.2%) benign diseases. The eNPM‐DM attained an overall accuracy of 88.7% (95% confidence interval (CI) 87.8%–89.5%) in detecting malignancies in the test set. In the prospective comparison phase, eNPM‐DM outperformed the experts: the overall accuracy was 88.0% (95% CI 86.1%–89.6%) vs. 80.5% (95% CI 77.0%–84.0%). The eNPM‐DM required less time (40 s vs. 110.0 ± 5.8 min) and exhibited encouraging performance in automatic segmentation of nasopharyngeal malignant area from the background, with an average DSC of 0.78 ± 0.24 and 0.75 ± 0.26 in the test and prospective test sets, respectively. Conclusions: The eNPM‐DM outperformed oncologist evaluation in diagnostic classification of nasopharyngeal mass into benign versus malignant, and realized automatic segmentation of malignant area from the background of nasopharyngeal endoscopic images.

15 February 2017 in BMC Cancer
Verified
Journal Article
Open access
PDF file
LKLiang-Ru Ke
Liang-Ru Ke
WXWeixiong Xia
Weixiong Xia
WQWen-Ze Qiu
Wen-Ze Qiu
XHXin-Jun Huang
Xin-Jun Huang
JYJing Yang
Jing Yang
XLXing Lv
Xing Lv
Due to improvements in imaging and radiological techniques as well as the use of chemotherapy, distant metastasis has become the predominant mode of treatment failure in patients with locally advanced nasopharyngeal carcinoma (LA-NPC). Platinum-based systemic chemotherapy has shown survival benefits and is now the standard strategy for systemic therapy in patients with LA-NPC. Notably, the third-generation platinum reagent lobaplatin has shown anti-tumor effects in several solid tumors with lower incidences of gastrointestinal, hepatic and renal toxicity relative to other platinum drugs. However, the safety and efficacy of lobaplatin as a first-line regimen in patients with LA-NPC are undetermined. Patients with stage III–IVa-b NPC received lobaplatin at a dose of 30 mg/m2 on days 1 and 22 combined with a continuous 120-h intravenous injection of 5-fluorouracil at a dose of 4 g/m2 followed by lobaplatin at a dose of 50 mg/m2 on days 43 and 64 concomitant with intensity-modulated radiation therapy. Objective response rates and acute toxicity were assessed based on RECIST (1.1) and CTCAE v.3.0, respectively. Kaplan-Meier analysis was used to calculate survival rates. Fifty-nine patients were enrolled, and 44 patients (74.6%) received allocated cycles of chemotherapy. The objective response rates were 88.1% (95% confidence interval [CI], 0.77 to 0.95) and 100% after induction chemotherapy (ICT) and concurrent chemoradiotherapy (CRT), respectively. With a median follow-up period of 44 months, the 3-year estimated progression-free survival and overall survival were 86.4% (95% CI, 69.8 to 98.8) and 94.9% (95% CI, 89.5 to 100), respectively. The most common grade 3–4 toxicities were neutropenia (8.5%) and thrombocytopenia (40.7%) after ICT and CRT, respectively. Lobaplatin combined with 5-fluorouracil followed by lobaplatin-RT treatment showed encouraging anti-tumor effects with tolerable toxicities in patients with LA-NPC. Randomized controlled trials of lobaplatin in patients with LA-NPC are warranted. This trial was registered with the Chinese Clinical Trials Registry and approved on March 31st, 2012, number ChiCTR-ONC-12002060 .

10 May 2018 in Cancer Communications
Verified
Journal Article
Open access
PDF file
GLGuoying Liu
Guoying Liu
XLXing Lv
Xing Lv
YWYi‐Shan Wu
Yi‐Shan Wu
MMMin‐Jie Mao
Min‐Jie Mao
YYYan‐Fang Ye
Yan‐Fang Ye
WXWeixiong Xia
Weixiong Xia
Background: Available data in the literature comparing different induction chemotherapy (IC) regimens on locoregionally advanced nasopharyngeal carcinoma (NPC) are scarce. The purpose of the present study was to evaluate the outcomes of locoregionally advanced NPC patients who were treated with taxane, cisplatin and 5‐fluorouracil (TPF) or cisplatin and 5‐fluorouracil (PF) as IC followed by concurrent chemoradiotherapy (CCRT). Methods: In total, 1879 patients with locoregionally advanced NPC treated with IC and CCRT from a prospectively maintained database were included in the present observational study. We compared overall survival (OS), disease‐specific survival (DSS), distant metastasis‐free survival (DMFS), and locoregional relapse‐free survival, using the propensity score method. Results: In total, 1256 patients received TPF or PF as IC backbone. The TPF group showed significantly better OS (hazard ratio [HR], 0.660; 95% confidence interval [CI] 0.442–0.986; P = 0.042), DSS (HR, 0.624; 95% CI 0.411–0.947; P = 0.027) and DMFS (HR, 0.589; 95% CI 0.406–0.855; P = 0.005) compared with the PF group in multivariable analyses. Propensity score matching identified 294 patients in each cohort and confirmed that TPF was associated with significantly improved 5‐year OS (88.1% vs. 80.7%; P = 0.042), DSS (88.5% vs. 80.7%; P = 0.021) and DMFS (87.9% vs. 78.6%; P = 0.012) rates compared with the PF group. There were no significant differences in locoregional relapse‐free survival before or after matching. Conclusions: In our study, IC with the TPF regimen combined with CCRT showed improved long‐term survival for the patients with locoregionally advanced NPC compared with the PF regimen. However, a prospective randomized clinical trial to validate these findings is necessary.