Gong Zhang

Dr. Gong Zhang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
14 June 2023 in International Journal of Surgery
Verified
Journal Article
Open access
YLYanzhe Liu
Yanzhe Liu
SZShang Zhao
Shang Zhao
GZGong Zhang
Gong Zhang
XZXiu-Ping Zhang
Xiu-Ping Zhang
MHMing-Gen Hu
Ming-Gen Hu
RLRong Liu
Rong Liu
Background: Automated surgical workflow recognition is the foundation for computational models of medical knowledge to interpret surgical procedures. The fine-grained segmentation of the surgical process and the improvement of the accuracy of surgical workflow recognition facilitate the realization of autonomous robotic surgery. This study aimed to construct a multigranularity temporal annotation dataset of the standardized robotic left lateral sectionectomy (RLLS) and develop a deep learning-based automated model for multilevel overall and effective surgical workflow recognition. Methods: From December 2016 to May 2019, 45 cases of RLLS videos were enrolled in our dataset. All frames of RLLS videos in this study are labeled with temporal annotations. The authors defined those activities that truly contribute to the surgery as effective frames, while other activities are labeled as under-effective frames. Effective frames of all RLLS videos are annotated with three hierarchical levels of 4 steps, 12 tasks, and 26 activities. A hybrid deep learning model were used for surgical workflow recognition of steps, tasks, activities, and under-effective frames. Moreover, the authors also carried out multilevel effective surgical workflow recognition after removing under-effective frames. Results: The dataset comprises 4 383 516 annotated RLLS video frames with multilevel annotation, of which 2 418 468 frames are effective. The overall accuracies of automated recognition for Steps, Tasks, Activities, and under-effective frames are 0.82, 0.80, 0.79, and 0.85, respectively, with corresponding precision values of 0.81, 0.76, 0.60, and 0.85. In multilevel effective surgical workflow recognition, the overall accuracies were increased to 0.96, 0.88, and 0.82 for Steps, Tasks, and Activities, respectively, while the precision values were increased to 0.95, 0.80, and 0.68. Conclusion: In this study, the authors created a dataset of 45 RLLS cases with multilevel annotations and developed a hybrid deep learning model for surgical workflow recognition. The authors demonstrated a fairly higher accuracy in multilevel effective surgical workflow recognition when under-effective frames were removed. Our research could be helpful in the development of autonomous robotic surgery.

3 April 2020 in Trials
Verified
Journal Article
Open access
PDF file
GZGong Zhang
Gong Zhang
YKYuhao Kang
Yuhao Kang
HZHaifeng Zhang
Haifeng Zhang
FWFei Wang
Fei Wang
RLRong Liu
Rong Liu
Background: Data from meta-analysis suggest that robotic radical antegrade modular pancreatosplenectomy (RAMPS) is a safe and effective procedure for treating adenocarcinoma in the body or tail of the pancreas, and is oncologically superior to standard retrograde pancreatosplenectomy (SRPS). RAMPS is an operation that actively expands the scope of resection, and achieves a higher R0 resection rate and lymph nodes acquisition through expanded resection. However, previous studies on RAMPS were conducted under open and laparoscopic surgery. Robotic surgery, on the other hand, plays a role in ergonomics and offers several advantages, including less fatigue, tremor filtering, 7° of wrist-like motion, motion scaling, and three-dimensional vision. At present, there is still a world-wide lack of clinical studies to observe the safety and clinical efficacy of robotic RAMPS. Hence, prospective randomized controlled trials (RCTs) comparing robotic RAMPS and SRPS are required. We begin an RCT to compare short-term surgical and oncological outcomes of robotic RAMPS and SRPS in patients undergoing distal pancreatectomy. Methods: This is a randomized, single-center clinical trial. All participants are adult patients with primary pancreatic cancer, who are undergoing RAMPS or SRPS. The primary endpoints are R0 rate (resection margins are classified by a margin to tumor distance ≥ 1 mm). The secondary endpoints are the number of harvested lymph nodes, perioperative complications and perioperative indicators (duration of surgery, blood loss, blood transfusion volume, costs). Discussion: We are undertaking a prospective RCT to evaluate the surgical and oncological outcomes of robotic RAMPS. This procedure may become a standard approach to robotic pancreatosplenectomy. Trial registration: Chinese Clinical Trial Registry: ChiCTR1900020833, Registered on 20 January 2019.

1 January 2025 in Intelligent Surgery
Verified
Journal Article
Open access
GZGong Zhang
Gong Zhang
LPLichao Pan
Lichao Pan
XZXuan Zhang
Xuan Zhang
ZWZhaohai Wang
Zhaohai Wang
ZMZhiqiang Ma
Zhiqiang Ma
RLRong Liu
Rong Liu

21 November 2023 in World Journal of Surgical Oncology
Verified
Journal Article
Open access
PDF file
GZGong Zhang
Gong Zhang
FNFangfang Nie
Fangfang Nie
WZWeinan Zhao
Weinan Zhao
PHPin Han
Pin Han
JFJianhua Fu
Jianhua Fu
FRFang Ren
Fang Ren
Background: Endometrial carcinoma (EC) is the second most common gynecological malignancy, and the differences between different pathological types are not entirely clear. Here, we retrospectively collected eligible EC patients to explore their differences regarding clinical characteristics and prognosis. Methods: Five hundred seventy EC patients from the First Affiliated Hospital of Zhengzhou University were included. Prognostic factors were measured using the univariate/multivariate Cox models. Overall survival (OS) and progression-free survival (PFS) were the primary and secondary endpoints, respectively. Results: In total, 396 patients with uterine endometrioid carcinoma (UEC), 106 patients with uterine serous carcinoma (USC), 34 patients with uterine mixed carcinoma (UMC), and 34 patients with uterine clear cell carcinoma (UCCC) were included. Comparison of baseline characteristics revealed patients diagnosed with UEC were younger, had more early clinical stage, and had lower incidence of menopause and lymph node metastasis. Compared to UEC, other pathological EC obtained more unfavorable OS (UCCC: HR = 12.944, 95%CI = 4.231–39.599, P < 0.001; USC: HR = 5.958, 95%CI = 2.404–14.765, P < 0.001; UMC: HR = 1.777, 95%CI = 0.209–15.114, P = 0.599) and PFS (UCCC: HR = 8.696, 95%CI = 1.972–38.354, P = 0.004; USC: HR = 4.131, 95%CI = 1.243–13.729, P = 0.021; UMC: HR = 5.356, 95%CI = 0.935–30.692, P = 0.060). Compared with UEC patients, the OS of UCCC patients in stage I–II and USC patients in stage III–IV were significantly worse, while UMC patients in stage I–II favored poorer PFS. The OS of UCCC patients receiving no postoperative adjuvant therapy or chemotherapy alone were significantly worse. Conclusions: The baseline characteristics of UEC and other rare EC types varied greatly, and the prognostic significance of different pathological types on EC patients depended on clinical tumor stages and therapeutic options.

4 August 2021 in Future Oncology
Verified
Journal Article
Closed access
ZWZizheng Wang
Zizheng Wang
WZWenbo Zou
Wenbo Zou
FWFei Wang
Fei Wang
GZGong Zhang
Gong Zhang
KCKuang Chen
Kuang Chen
RLRong Liu
Rong Liu
Background: A malignant tumor's immune environment, including infiltrating immune cell status, can be critical to patient outcomes. Recent studies have shown that immune cell infiltration (ICI) in ... Lay abstract Pancreatic cancer (PC) is a lethal malignancy with a higher mortality rate. Currently, immunotherapy is increasingly interesting to clinical researchers and considered a novel and effi...

19 September 2023 in Frontiers in Oncology
Verified
Journal Article
Open access
GZGong Zhang
Gong Zhang
WCWeixiang Chen
Weixiang Chen
ZWZizheng Wang
Zizheng Wang
FWFei Wang
Fei Wang
RLRong Liu
Rong Liu
JFJianjiang Feng
Jianjiang Feng
Background: Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people’s self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.Purpose: MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.Methods: A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.Results: The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.Conclusions: Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.