Objective:The tumor-stroma ratio(TSR)is considered an independent prognostic factor for gastric cancer.Traditionally,TSR as-sessments have relied on the visual evaluation of surgical specimens,which is a method that lacks objectivity.This study was conducted to investigate whether the TSR in preoperative biopsy specimens can be automatically quantified using deep learning methods and whether the TSR value can be used to predict the efficacy of neoadjuvant chemotherapy(NAC)in patients with gastric cancer.Methods:In total,148 preoperative biopsy slides and 43 surgical resection slides from patients with gastric cancer who underwent NAC treatment at Yunnan Can-cer Hospital between March 2013 and March 2020 were used in the study.Tumor region segmentation and epithelial-stromal segmentation models were developed.The surgical resection slides were used to trained and evaluate the model,and the biopsy slides were used to test their predictive abilities.The TSR values were determined on the basis of the intersection of predictions from both models.The postoperat-ive pathological tumor regression grade(TRG)was used to categorize patients into good responders(TRG 0-1)and poor responders(TRG 2-3).Univariate and multivariate Logistic regression analyses were conducted to determine the correlation between the TSR value and the ef-ficacy of NAC in gastric cancer.Results:The intersection over union(IOU)value was 0.94 for the tumor tissue segmentation model and 0.88 for the epithelial-stromal segmentation model.Using cutoff values of 44.93％and 70.22％,patients were classified into low,intermediate,and high TSR groups.The proportion of good responders was significantly different among these groups(P＜0.05).Multivariate Logistic re-gression analysis indicated that the TSR was an independent predictor of NAC response in gastric cancer(OR=0.10,95％CI:0.03-0.32).When the TSR three-category classification was added as a predictor of treatment response alongside conventional clinical information,the area under curve(AUC)increased from 0.71 to 0.85.Conclusions:This deep learning model is capable of automatically segmenting tumor,epi-thelial,and stromal regions based on pathological slides,accurately calculating TSR value,and predicting the efficacy of NAC on the basis of the automatically computed TSR values.

OBJECTIVE: To study the mechanism of tumor necrosis factor( TNF)-α and its receptor( TNFR) signal transduction pathways in regulating cell apoptosis of alveolar macrophage( AM) in coal workers' pneumoconiosis( CWP).METHODS: Twenty-four coal workers with pneumoconiosis at stage Ⅰ were selected as CWP group and four observation subjects exposed to coal were chosen as observation group by using simple random sampling method. The bronchoalveolar lavage fluids of whole-lung lavage of two groups were collected. AMs were separated and purified. Then they were divided into 6 groups: a control group,a superoxide dismutase( SOD) group,a TNF/TNFR group,an anti-TNF-α antibody group,a Caspase-8 suppression group and a nuclear factor-κB( NF-κB) suppression group. The AMs of 6 groups with corresponding treatment were cultivated. After 24 hours,the cells were harvested and proteins extracted. The relative expression of TNF-α,TNFR1,TNFR2,Caspase-8,Caspase-3,NF-κB P50 and NF-κB P65 protein was detected by Western blotting. RESULTS: The protein relative expression of TNF-α,TNFR2,Caspase-8,Caspase-3,NF-κB P50 and NF-κB P65 in CWP group was significantly higher than those in the observation group( P < 0. 05). The protein relative expression of TNF-α,TNFR1,Caspase-8,Caspase-3 and NF-κB P50 in the TNF/TNFR group and the anti-TNF-αantibody group was lower than that of the control group( P < 0. 05). The above indexes in the anti-TNF-α antibody group were lower than that of the NF-κB suppression group( P < 0. 05). The protein relative expression of TNFR1,Caspase-8and Caspase-3 in the TNF/TNFR group was higher than that of the SOD group and the Caspase-8 suppression group( P <0. 05). The protein relative expression of TNFR1,Caspase-8 and NF-κB P50 in the TNF/TNFR group was lower than that of the NF-κB suppression group( P < 0. 05). Among the CWP patients,the relative expression of TNFR2 and NF-κB P65 in the TNF/TNFR group was lower than that of the control group( P < 0. 05),and higher than that of the SOD group( P <0. 05). CONCLUSION: AM apoptosis mediated by TNF-α/TNFR/NF-κB signal transduction pathway plays an important role in the occurrence and development of CWP. The TNF-α/TNFR/NF-κB signal transduction pathways inhibited or blocked at different stages can affect the expression of proteins related to AM apoptosis.