Background: Early noninvasive screening of patients who would benefit from neoadjuvant chemotherapy (NCT) is essential for personalized treatment of locally advanced gastric cancer (LAGC). The aim of this study was to identify a radioclinical signatures from pretreatment oversampled CT images to predict the response to NCT and prognosis of LAGC patients. Methods: LAGC patients were retrospectively recruited from six hospitals from January 2008 to December 2021. An SE-ResNet50-based chemotherapy response prediction system was developed from pretreatment CT images preprocessed with an imaging oversampling method (i.e., DeepSMOTE). Then, the Deep learning (DL) signature and clinic-based features were fed into the deep learning radioclinical signature (DLCS). The predictive performance of the model was evaluated based on discrimination, calibration and clinical usefulness. An additional model was built to predict overall survival (OS) and explore the survival benefit of the proposed DL signature and clinicopathological characteristics. Result: A total of 1060 LAGC patients were recruited from six hospitals, the training cohort (TC) and internal validation cohort (IVC) patients were randomly selected from center I. An external validation cohort (EVC) of 265 patients from 5 other centers was also included. The DLCS exhibited excellent performance in predicting the response to NCT in the IVC (AUC, 0.86) and EVC (AUC, 0.82), with good calibration in all cohorts (P>0.05). Moreover, the DLCS model outperformed the clinical model (P<0.05). Additionally, we found that the DL signature could serve as an independent factor for prognosis (HR, 0.828, P=0.004). The C-index, iAUC, and IBS for the OS model were 0.64, 1.24 and 0.71 in the test set. Conclusion: We proposed a DLCS model that combined imaging features with clinical risk factors to accurately predict tumor response and identify the risk of OS in LAGC patients priors to NCT that can then be used to guide personalized treatment plans with the help of computerized tumor-level characterization.

Introduction: The postoperative recurrence of gastric cancer (GC) has a significant impact on the overall prognosis of patients. Therefore, accurately predicting the postoperative recurrence of GC is crucial. Methods: This retrospective study gathered data from 2813 GC patients who underwent radical surgery between 2011 and 2017 at two medical centers. Follow-up was extended until May 2023, and cases were categorized as recurrent or nonrecurrent based on postoperative outcomes. Clinical pathological information and imaging data were collected for all patients. A new deep learning signature (DLS) was generated using pretreatment computed tomography images, based on a pretrained baseline (a customized Resnet50), for predicting postoperative recurrence. The deep learning fusion signature (DLFS) was created by combining the score of DLS with the weighted values of identified clinical features. The predictive performance of the model was evaluated based on discrimination, calibration, and clinical usefulness. Survival curves were plotted to investigate the differences between DLFS and prognosis. Results: In this study, 2813 patients with GC were recruited and allocated into training, internal validation, and external validation cohorts. The DLFS was developed and assessed for its capability in predicting the risk of postoperative recurrence. The DLFS exhibited excellent performance with AUCs of 0.833 (95% CI: 0.809–0.858) in the training set, 0.831 (95% CI: 0.792–0.871) in the internal validation set, and 0.859 (95% CI: 0.806–0.912) in the external validation set, along with satisfactory calibration across all cohorts (P>0.05). Furthermore, the DLFS model significantly outperformed both the clinical model and DLS (P<0.05). High-risk recurrent patients exhibit a significantly poorer prognosis compared to low-risk recurrent patients (P<0.05). Conclusions: The integrated model developed in this study, focusing on GC patients undergoing radical surgery, accurately identifies cases at high-risk of postoperative recurrence and highlights the potential of DLFS as a prognostic factor for GC patients.

Objective: The therapeutic effects of surgical resection in gastric cancer with liver metastasis remain largely unclear. We sought to examine surgical resection combined with chemotherapy for survival benefit in cases of synchronous liver metastases from gastric cancer (LMGC), and to identify factors affecting patient prognosis. Methods: Patients diagnosed with synchronous LMGC between January 2010 and December 2015 were enrolled in this study. The effects of gastrectomy and metastasectomy combined with chemotherapy (surgical resection group) and palliative chemotherapy (palliative chemotherapy group) on survival were comparatively assessed. Results: Of the 132 included cases, 57 (43.2%) and 75 (56.8%) were treated with surgical resection/chemotherapy and palliative chemotherapy, respectively. Overall survival (OS) was markedly prolonged in the surgical resection group compared with the palliative chemotherapy group (33.6 vs 12.4 months, P< 0.001). In patients who underwent surgical resection, R0 resection resulted in prolonged OS in comparison with the non-R0 resection subgroup (45.1 vs 13.5 months, P< 0.001). Surgical resection (hazard ratio [HR]=0.453; 95% confidence interval [CI] 0.276– 0.813; P=0.009) and solitary liver metastasis (HR=0.540; 95% CI 0.315– 0.796; P =0.043) were independent predictors of OS. Conclusion: Patients with synchronous LMGC might benefit from radical surgical resection combined with appropriate chemotherapy. Additional well-designed prospective studies are required to verify the above findings.

Background: Survival benefit of adjuvant radiotherapy for locally advanced gastric cancer following gastrectomy plus D2 lymphadenectomy has always been controversial. Esophagogastric junction (EGJ) adenocarcinoma, which is usually classified as gastric cancer in East Asia, often has a higher locoregional recurrence rate after operation because of its special anatomical characteristics. The aim of this study is to determine whether adjuvant radiotherapy can improve survival of locally advanced EGJ adenocarcinoma after D2 radical resection. Methods: In this phase III, randomized, open label, controlled trial, we plan to recruit 378 patients with Siewert type II and III adenocarcinoma of EGJ, who had undergone transabdominal radical surgery and D2 lymphadenectomy, and were divided into pathological stage IIB to IIIC. All patients will be randomized 1:1 to receive either adjuvant chemotherapy alone (control group) or adjuvant chemotherapy plus chemoradiotherapy (experimental group). Patients allocated to control group will receive eight cycles of S-1 plus oxaliplatin (SOX), while the experimental group will receive two cycles of SOX followed by 45-Gy RT combined with S-1 and four additional cycles of SOX. The primary endpoint is 3-year disease-free survival rate (DFS). The secondary endpoints are 3-year overall survival rate (OS), 3-year locoregional recurrence-free survival rate (LRFS), 3-year distant metastasis-free survival rate (DMFS), and quality of life (QoL). Discussion: In the past, the adjuvant treatment of EGJ adenocarcinoma needs to draw on the experience of esophageal adenocarcinoma or gastric adenocarcinoma. In this study, EGJ adenocarcinoma is considered as an independent disease, and the conclusion will provide evidence for optimal adjuvant therapy of locally advanced EGJ adenocarcinoma after D2 radical resection. Trial registration: ClinicalTrials.gov NCT03973008. Registered on 1 June 2019 (retrospectively registered), URL: https://clinicaltrials.gov/ct2/show/NCT03973008?term=NCT03973008&draw=2&rank=1

Background: Lymph node metastases often occur in advanced gastric cancer, with some patients presenting with metastases in the para-aortic lymph nodes. There are persistent Controversies about the benefit of para-aortic lymph node dissection (PAND). Our purpose is to probe whether PAND following preoperative chemotherapy had any clinical significance in individuals with PALNs in gastric cancer. Material and methods: To retrospectively analyze the clinical data of 86 gastric cancer patients (40 in the D2 + PAND group and 46 in the D2 group) who attended the abdominal surgery department of Zhejiang Cancer Hospital between September 1, 2008, and July 30, 2018. Results: In the D2 + PAND group (40 cases), the average number of lymph nodes cleared per case was 4.3 in group 16 (16a2, 16b1), and the postoperative pathology confirmed lymph node positivity in 16 cases, with a metastasis rate of 40%. The median overall survival times were 63 and 34 months for the patients in the D2 + PAND group and D2 group, respectively. The 3-year overall survival (OS) compared to the D2 group (D2 + PAND 69.1% vs. D2 50%, P = 0.012) and a statistically significant difference in 3-year disease-free survival (DFS) (D2 + PAND 69.6% vs. D2 38.3%, P = 0.007). Lymph node dissection extent and recurrence of para-aortic lymph nodes were independent prognostic variables for the patients. The recurrence rate was reduced in the D2 + PAND group compared to the D2 group (D2 + PAND 7.5% vs. D2 26.1%, p = 0.023). Conclusions: For patients with gastric cancer whose imaging suggests metastasis in the para-aortic lymph nodes, preoperative chemotherapy combined with PAND is an effective and safe treatment that may benefit patient survival.

Objective. The aim of this study was to analyze the association between the expression of chromatin assembly factor 1 subunit A (CHAF1A) in gastric cancer (GC) and clinicopathological features, disease prognosis, and expression of programmed cell death-ligand 1 (PD-L1). Material and Methods. A total of 140 GC tissue specimens were collected between January 2013 and December 2017. CHAF1A expression in GC and paracancerous tissues was determined. Then, the associations between CHAF1A expression level in the collected tissues and clinicopathological features as well as PD-L1 expression level were investigated. Cox regression analyses were carried out to determine whether CHAF1A is an independent prognostic factor for GC. Finally, the association between CHAF1A expression levels and survival of the GC patients was investigated. Results. A significantly higher level of CHAF1A expression in GC tissues was found compared to that in paracancerous tissues ( ). CHAF1A expression level in GC tissues was found to be strongly associated with family history ( ), smoking history ( ), T stage ( ), tumor marker AFP ( ), tumor marker CEA ( ), and PD-L1 expression ( ). CHAF1A expression was also found to be positively correlated to PD-L1 expression ( ). Moreover, high CHAF1A expression levels were found to lead to poor prognosis ( ). Univariate and multivariate analyses all showed that CHAF1A was an independent poorer prognostic factor for gastric cancer ( , HR = 1.175, 95% CI: 1.090–2.890 for univariate analyses; , HR = 2.191, 95% CI:1.170–4.105 for multivariate analyses). A high level of CHAF1A expression was thus found to be an independent risk factor for GC prognosis. Conclusion. High CHAF1A expression is associated with poor GC prognosis and positively correlated to PD-L1 expression. Thus, CHAF1A expression level may be used as a novel biomarker for GC diagnosis.