Development and validation of a deep learning model for predicting gastric cancer recurrence based on CT Imaging: a multicenter study.

INTRODUCTION: The postoperative recurrence of gastric cancer has a significant impact on the overall prognosis of patients. Therefore, accurately predicting the postoperative recurrence of gastric cancer is crucial. METHODS: This retrospective study gathered data from 2,813 gastric cancer 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 non-recurrent 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 CT images, based on a pre-trained 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 gastric cancer (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.

Development and validation of nomogram for predicting early recurrence after radical gastrectomy of gastric cancer.

BACKGROUND: After radical surgery, early detection of recurrence and metastasis is a crucial factor in enhancing the prognosis and survival of patients with gastric cancer (GC). Therefore, assessing the risk of recurrence in gastric cancer patients and determining the timing for postoperative recurrence is crucial. METHODS: The clinicopathological data of 521 patients with recurrent gastric cancer, who underwent radical gastrectomy at Zhejiang Cancer Hospital between January 2010 and January 2017, were retrospectively analyzed. These patients were randomly divided into two groups: a training group (n = 365) and a validation group (n = 156). In the training set, patients were further categorized into early recurrence (n = 263) and late recurrence (n = 102) groups based on a 2-year boundary. Comparative analyses of clinicopathological features and prognoses were conducted between these two groups. Subsequently, a nomogram for predicting early recurrence was developed and validated. RESULTS: In this study, the developed nomogram incorporated age, serous infiltration, lymph node metastasis, recurrence mode, and the tumour marker CA19-9. In the training cohort, the area under the curve (AUC value) was 0.739 (95% CI, 0.682-0.798), with a corresponding C-index of 0.739. This nomogram was subsequently validated in an independent validation cohort, yielding an AUC of 0.743 (95% CI, 0.652-0.833) and a C-index of 0.743. Furthermore, independent risk factors for prognosis were identified, including age, absence of postoperative chemotherapy, early recurrence, lymph node metastasis, abdominal metastasis, and vascular cancer embolus. CONCLUSION: Independent risk factors for gastric cancer recurrence following radical surgery were utilized to construct a nomogram for predicting early relapse. This nomogram effectively assesses the risk of recurrence, aids in treatment decision-making and follow-up planning in clinical settings, and demonstrated strong performance in the validation cohort.

The role of macrophages in gastric cancer.

As one of the deadliest cancers of the gastrointestinal tract, there has been limited improvement in long-term survival rates for gastric cancer (GC) in recent decades. The poor prognosis is attributed to difficulties in early detection, minimal opportunity for radical resection and resistance to chemotherapy and radiation. Macrophages are among the most abundant infiltrating immune cells in the GC stroma. These cells engage in crosstalk with cancer cells, adipocytes and other stromal cells to regulate metabolic, inflammatory and immune status, generating an immunosuppressive tumour microenvironment (TME) and ultimately promoting tumour initiation and progression. In this review, we summarise recent advances in our understanding of the origin of macrophages and their types and polarisation in cancer and provide an overview of the role of macrophages in GC carcinogenesis and development and their interaction with the GC immune microenvironment and flora. In addition, we explore the role of macrophages in preclinical and clinical trials on drug resistance and in treatment of GC to assess their potential therapeutic value in this disease.

The percentages of signet-ring cells (SRCs) affects the prognosis after radical gastrectomy for advanced gastric cancer.

PURPOSE: Only recently has the percentage of signet-ring cells (SRCs) been shown to affect the prognosis following gastric cancer surgery. It is uncertain whether the SRC percentage has a role in tumour biology or prognosis of gastric signet-ring cell carcinoma (GSRCC). For this research, we assessed the effect of the SRC percentage on the clinicopathological and prognostic characteristics of gastric cancer (GC) tumours and created and verified a prognostic nomogram to assess the overall survival (OS) of GSRCC patients. METHODS: In our study, 1100 GC patients with signet-ring cell carcinoma (SRCC) at Zhejiang Cancer Hospital from December 2013 to December 2018 who underwent curative gastric cancer resection were retrospectively analysed. The patients were separated into two groups: those with SRCC (SRC percentage >50%; n = 157) and those with partial signet-ring cell carcinoma (PSRCC) (SRC percentage ≤50%; n = 943). We compared the clinicopathological characteristics of both groups. To estimate OS and determine correlations with the SRC percentage, the Kaplan-Meier method and log-rank test were used. To develop the prognostic nomogram, independent prognostic indicators for OS were identified using Cox regression analyses. Predictions were assessed using the calibration curve and C-index. RESULTS: Our research showed that there was no discernible difference in OS between the two groups. The preoperative CA242 level, pT stage, pN stage, age, nerve invasion, neoadjuvant chemotherapy, postoperative chemotherapy, and maximum tumour diameter were independent prognostic risk factors for OS for GC (all p < 0.05). However, for advanced GC, the SRC percentage (HR = 1.571, 95% CI 1.072-2.302, p = 0.020) was an independent prognostic factor of OS. Other independent prognostic risk factors were age, pT stage, pN stage, nerve invasion, tumour location, neoadjuvant chemotherapy, postoperative chemotherapy, preoperative CA50 level, and preoperative CEA level (all p < 0.05). On these bases, nomograms were constructed for GC and advanced GC, with C-indexes of 0.806 (95%CI 0.782-0.830) and 0.728 (95%CI 0.697-0.759), respectively. CONCLUSIONS: In cases of advanced gastric cancer, the SRC percentage served as a standalone prognostic indicator for OS. An effective tool for assessing the prognosis of GSRCC was offered by the nomogram.

A Novel Method for Dynamically Assessing the Prognosis of Patients with pT1 Gastric Cancer: A Large Population-Based Dynamic Prognostic Analysis.

Background: While early gastric cancer (EGC) patients are likely to experience relatively long postoperative survival, certain disease-related findings are associated with a poorer prognosis. This study sought to develop and validate a novel predictive model capable of estimating conditional disease-specific survival (CDSS) in EGC patients. Methods: A total of 3016 patients diagnosed with pT1NxM0 GC after gastrectomy between 1998 and 2016 were selected from the Surveillance, Epidemiology, and End Results (SEER) database and were separated into training and validation cohorts. Kaplan‒Meier curves and log-rank tests were employed to evaluate DSS, after which univariate and multivariate Cox regression analyses were used to construct a predictive nomogram and to estimate CDSS at 1, 2, and 3 years postoperatively in these patients. Results: In the training cohort, the 3-year CDSS rose from 89.1% to 94.6% from 0 to 5 years postoperatively, while the 5-year CDSS rose from 84.5% to 92.0%. Cox regression analyses led to the construction of a nomogram that was able to reliably predict 3- and 5-year CDSS at 1, 2, and 3 years postoperatively (all P < 0.05) based upon patient age, tumor size, pT stage, pN stage, and the number of retrieved lymph nodes. This model exhibited good discriminative power in the training and validation cohorts (concordance index: 0.791 and 0.813, respectively), and nomogram calibration curves confirmed that actual and predicted survival outcomes were close to one another. Conclusions: We herein developed a nomogram capable of accurately predicting the CDSS of EGC patients that had survived for multiple years after undergoing surgery.

Prognostic significance of inflammatory and nutritional markers in perioperative period for patients with advanced gastric cancer.

BACKGROUND: It has been reported that inflammatory and nutritional markers are related to prognosis in numerous malignancies. The present study analyzed the significance of these markers' alterations during neoadjuvant chemotherapy in the long-term outcomes in patients with advanced gastric cancer. METHODS: A retrospective review was performed of 437 advanced gastric cancer patients who underwent a neoadjuvant chemotherapy (NACT) regimen followed by surgical treatment. Inflammatory and nutritional markers measured from the blood samples collected from the patients before the first neoadjuvant chemotherapy and after the last neoadjuvant chemotherapy were used for analysis. Statistical analysis, including Mann-Whitney U or chi-square tests, the Kaplan-Meier method and Cox multivariate analysis, were performed to analyze the predictive value of these markers for overall survival outcomes (OS). RESULTS: Most biomarkers, including lymphocyte, leucocyte, neutrophil, monocyte, platelet, LMR, PLR, SII, CRP, CAR, hemoglobulin and albumin levels, changed during NACT (P <  0.05). After separately grouping the patients based on the normal range of hematologic indexes and the change rate (α) of systemic inflammatory and nutritional markers by the cutoff value derived from X-tile (P <  0.05), we found that differentiation, TRG, pre-NACT BMI, pre-NACT platelet counts, post-NACT lymphocyte counts, the change in lymphocyte counts, change in platelet counts and LMR(α), PLR(α), SII(α), and CAR(α) were associated with OS. Multivariate analysis revealed that PLR (α) > - 19% was correlated with a 3.193-fold (95% CI: 2.194-4.649) higher risk of death (P <  0.001) than others. CONCLUSION: NACT could significantly change several inflammatory and nutritional markers in the perioperative period; the platelet counts before NACT, and the change in lymphocytes during NACT truly correlated with long-term outcomes among patients with advanced gastric cancer. The systemic inflammatory marker PLR may be a reliable marker for the prediction of prognosis.

Preoperative chemotherapy combined with para-aortic lymph node dissection has clinical value in the treatment of gastric cancer with para-aortic lymph node metastases.

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.

Aberrant Expression TFR1/CD71 in Gastric Cancer Identifies a Novel Potential Prognostic Marker and Therapeutic Target.

Background: Gastric cancer (GC) is one of the most common malignant tumors with poor prognosis. So far, other than the HER2, GC lacks effective therapeutic targets. Transferrin receptor 1 (TFR1) expressions are abnormally upregulated in various cancers for the satisfaction of iron demand increased. This study aimed to explore the expression and clinical value of TFR1 in GC. Methods: A tissue microarray including GC tissues and matched noncancerous tissues from 155 GC patients were collected. Moreover, the level of TFR1 expression was detected by immunohistochemistry, and we also evaluated the relationship between TFR1 expression and the clinicopathologic characteristics. What is more, univariate analysis and multivariate analysis were used to evaluate the risk factors and independent risk factors affecting the prognosis of GC. Results: We found that TFR1 was overexpressed in GC tissues compared with noncancerous tissues, and a significant relationship was found between TFR1 expression and age (P=0.001), Lauren type (P=0.008), T stage (P=0.003), HER2 (P=0.003), PD-L1 (P < 0.001), and the level of CA72-4 (P=0.028). Survival analysis confirmed that GC patients with positive TFR1 expression had a poorer OS than that with negative TFR1 expression, and TFR1 expression was an independent risk factor in GC. Furthermore, we also found that there was a significant difference between the TFR1-PD-L1- group and the TFR1+PD-L1+ group (P=0.023), while there was no significant difference between the TFR1-PD-L1- group and the TFR1+PD-L1- group (P=0.119), or between the TFR1-PD-L1- group and the TFR1-PD-L1+ group (P=0.396). Conclusions: TFR1 was overexpressed in GC and its aberrant expression identifies a novel potential prognostic marker and therapeutic target. In addition, TFR1 expression may be associated with the immune microenvironment and suppress the immune response via regulating the PD-L1 expression.

SFRP4 Is a Potential Biomarker for the Prognosis and Immunotherapy for Gastric Cancer.

Purpose: Secreted frizzled-related protein 4 (SFRP4) is a member of the SFRP family, which functions as either a tumor suppressor or a prooncogenic factor in distinct tumor types. Our research aimed to explore the expression of SFRP4 in gastric cancer, its prognostic significance, and its relationship with immune cell infiltration. Materials and Methods: Gastric cancer and paracancerous tissue specimens from surgically resected gastric cancer patients were collected to construct tissue microarrays, and immunohistochemistry was used to detect the expression of SFRP4, PD-L1, CD3+ T, CD4+ T, and CD8+ T in these microarrays. The differential expression of SFRP4 and its relationship with the immune microenvironment were evaluated using the TIMER and TISIDB databases. Finally, patient survival was assessed. Results: SFRP4 expression was elevated in gastric cancer tissues and linked to a poor prognosis (P=0.021). The 5-year survival rate for patients with high SFRP4 expression was only 39.81% but reached 60.02% for patients with low SFRP4 expression. Increased SFRP4 expression correlated with high CD8+ T-cell infiltration (P=0.015) and positive PD-L1 expression (P=0.036). High SFRP4 expression was an independent predictor of overall survival (P=0.024 in univariable analysis, P=0.011 in multivariable analysis). Using online databases, we found that SFRP4 expression was higher in gastric cancer tissues and substantially was associated with the immune microenvironment. Conclusion: SFRP4 is an oncogenic driver that can predict patient survival time in gastric cancer, as well as an important immune-related factor. SFRP4 may be important for guiding immunotherapy in gastric cancer patients.