Shaoyu Hao

Dr. Shaoyu Hao


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
20 September 2024 in Frontiers in Immunology
Verified
Journal Article
Open access
PDF file
DHDan Han
Dan Han
HLHao Li
Hao Li
XZXin Zheng
Xin Zheng
SFShenbo Fu
Shenbo Fu
RWRan Wei
Ran Wei
SHShaoyu Hao
Shaoyu Hao
Objective: Develop a predictive model utilizing weakly supervised deep learning techniques to accurately forecast major pathological response (MPR) in patients with resectable non-small cell lung cancer (NSCLC) undergoing neoadjuvant chemoimmunotherapy (NICT), by leveraging whole slide images (WSIs).Methods: This retrospective study examined pre-treatment WSIs from 186 patients with non-small cell lung cancer (NSCLC), using a weakly supervised learning framework. We employed advanced deep learning architectures, including DenseNet121, ResNet50, and Inception V3, to analyze WSIs on both micro (patch) and macro (slide) levels. The training process incorporated innovative data augmentation and normalization techniques to bolster the robustness of the models. We evaluated the performance of these models against traditional clinical predictors and integrated them with a novel pathomics signature, which was developed using multi-instance learning algorithms that facilitate feature aggregation from patch-level probability distributions.Results: Univariate and multivariable analyses confirmed histology as a statistically significant prognostic factor for MPR (P-value< 0.05). In patch model evaluations, DenseNet121 led in the validation set with an area under the curve (AUC) of 0.656, surpassing ResNet50 (AUC = 0.626) and Inception V3 (AUC = 0.654), and showed strong generalization in external testing (AUC = 0.611). Further evaluation through visual inspection of patch-level data integration into WSIs revealed XGBoost’s superior class differentiation and generalization, achieving the highest AUCs of 0.998 in training and robust scores of 0.818 in validation and 0.805 in testing. Integrating pathomics features with clinical data into a nomogram yielded AUC of 0.819 in validation and 0.820 in testing, enhancing discriminative accuracy. Gradient-weighted Class Activation Mapping (Grad-CAM) and feature aggregation methods notably boosted the model’s interpretability and feature modeling.Conclusion: The application of weakly supervised deep learning to WSIs offers a powerful tool for predicting MPR in NSCLC patients treated with NICT.

14 July 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
DHDan Han
Dan Han
BLBaosheng Li
Baosheng Li
QZQian Zhao
Qian Zhao
HSHongfu Sun
Hongfu Sun
JDJinling Dong
Jinling Dong
WHWei Huang
Wei Huang
Over 50% of individuals with esophageal cancer (EC) present with advanced stages of the disease; therefore, their outcome following surgery alone is poor, with only 25%–36% being alive 5 years post-surgery. Based on the evidence that the CROSS and NEOCRTEC5010 trials provided, neoadjuvant chemoradiotherapy (nCRT) is now the standard therapy for patients with locally advanced EC. However, there are still many concerning clinical questions that remain controversial such as radiation dose, appropriate patient selection, the design of the radiation field, the time interval between chemoradiotherapy (CRT) and surgery, and esophageal retention. With immune checkpoint inhibitors (ICIs) rapidly becoming a mainstay of cancer therapy, along with radiation, chemotherapy, and surgery, the combination mode of immunotherapy is also becoming a hot topic of discussion. Here, we try to provide constructive suggestions to answer the perplexing problems and clinical concerns for the progress of nCRT for EC in the future.

1 November 2023 in International Journal of General Medicine
Verified
Journal Article
Open access
PDF file
DHDan Han
Dan Han
JTJing Tian
Jing Tian
JZJunfeng Zhao
Junfeng Zhao
SHShaoyu Hao
Shaoyu Hao
Purpose: This study aims to identify the most effective treatment approach and compares the survival rates, along with complications, in patients with locally resectable esophageal squamous cell carcinoma (ESCC) who were treated with one of the three treatment patterns: neoadjuvant chemotherapy followed by surgery (NCT+S), neoadjuvant chemoradiotherapy followed by surgery (NCRT+S), or surgery followed by chemoradiotherapy (S+CRT). Methods: We conducted a retrospective analysis of the medical records of ESCC patients who received one of these treatments between March 2015 and March 2022. This analysis aimed to identify differences in long-term survival, pathological responses, and complications across the three treatment groups. To address potential confounding factors, propensity score matching (PSM) and Cox proportional hazards models were utilized. Results: This study included a cohort of 715 patients: 197 in the NCT+S group, 188 in the NCRT+S group, and 330 in the S+CRT group, all meeting the selection criteria. After PSM, the median disease-free survival (DFS) time was 38.9 months, 25.6 months, and 15.3 months for NCRT+S, NCT+S, and S+CRT groups, respectively. There were statistically significant differences in the 5-year DFS and 5-year OS among the three groups (P=0.04 and P=0.02, post-matching, respectively). Notably, neoadjuvant therapy showed a correlation with increased postoperative anastomotic leakage rates (17.5% in NCRT+S, 10% in NCT+S, and 5% in S+CRT; P=0.03, post-matching), regardless of the PSM adjustment. Conclusion: The findings indicate that neoadjuvant therapy before surgery offers a significant survival advantage over postoperative adjuvant therapy for patients with locally advanced resectable ESCC. Despite similar safety profiles, neoadjuvant therapy appears to be associated with a higher incidence of anastomotic leakage after surgery.