Objective:To investigate the utility of a computational pathology-based tumor microenvironment(TME)score derived from whole slide images(WSIs)in predicting the efficacy of epidermal growth factor receptor tyrosine kinase inhibitors(EGFR-TKIs)in patients with EGFR mutation-positive non-small cell lung cancer(NSCLC).Methods:This retrospective study collected 240 EGFR-mutant NSCLC pa-tients treated with EGFR-TKIs at The First Affiliated Hospital of Wannan Medical College and analyzed hematoxylin-eosin(H&E)-stained WSIs of biopsy specimens,along with clinical and imaging data.The patients were randomly assigned into a training cohort(n=160)and an inde-pendent validation cohort(n=80)in a 2:1 ratio.Treatment response was assessed based on CT findings at 3 months after EGFR-TKIs initi-ation.Computational pathology was employed to automatically quantify the proportions of four TME components(tumor epithelium,stroma,lymphocytes,and vasculature)within the tumor regions of WSIs.Multivariate Logistic regression in the training cohort identified TME components independently predictive of treatment response(P<0.05),which were then integrated into a TME-score.The predictive performance was evaluated using receiver operating characteristic(ROC)curve analysis and area under the curve(AUC).The TME-score model was compared with a clinical-feature-based model and a combined model(TME-score+clinical features).Finally,the models were val-idated in the independent cohort.Results:In the training cohort,the TME-score,incorporating epithelial and stromal proportions,achieved an AUC of 0.827(95%CI:0.749-0.892)for predicting treatment response,while the validation cohort yielded an AUC of 0.845(95%CI:0.735-0.937).Both outperformed the clinical model(AUCs=0.730[95%CI:0.645-0.804]and 0.712[95%CI:0.586-0.824],respectively).The combined model(TME-score+clinical features,including cytokeratin 19 fragment and non-contrast CT values)further improved predictive performance(AUCs=0.884[95%CI:0.827-0.932]and 0.882[95%CI:0.798-0.950],respectively).Delong's test for pairwise model comparis-ons showed significant differences(all P<0.05)except TME-score and the combined model in the validation cohort(P=0.289).Conclusions:TME-score outperformed clinical models in predicting EGFR-TKIs efficacy in EGFR mutation-positive NSCLC patients and may serve as a novel tool for identifying patients likely to benefit from targeted therapy.

Objective:To investigate the utility of a computational pathology-based tumor microenvironment(TME)score derived from whole slide images(WSIs)in predicting the efficacy of epidermal growth factor receptor tyrosine kinase inhibitors(EGFR-TKIs)in patients with EGFR mutation-positive non-small cell lung cancer(NSCLC).Methods:This retrospective study collected 240 EGFR-mutant NSCLC pa-tients treated with EGFR-TKIs at The First Affiliated Hospital of Wannan Medical College and analyzed hematoxylin-eosin(H&E)-stained WSIs of biopsy specimens,along with clinical and imaging data.The patients were randomly assigned into a training cohort(n=160)and an inde-pendent validation cohort(n=80)in a 2:1 ratio.Treatment response was assessed based on CT findings at 3 months after EGFR-TKIs initi-ation.Computational pathology was employed to automatically quantify the proportions of four TME components(tumor epithelium,stroma,lymphocytes,and vasculature)within the tumor regions of WSIs.Multivariate Logistic regression in the training cohort identified TME components independently predictive of treatment response(P<0.05),which were then integrated into a TME-score.The predictive performance was evaluated using receiver operating characteristic(ROC)curve analysis and area under the curve(AUC).The TME-score model was compared with a clinical-feature-based model and a combined model(TME-score+clinical features).Finally,the models were val-idated in the independent cohort.Results:In the training cohort,the TME-score,incorporating epithelial and stromal proportions,achieved an AUC of 0.827(95%CI:0.749-0.892)for predicting treatment response,while the validation cohort yielded an AUC of 0.845(95%CI:0.735-0.937).Both outperformed the clinical model(AUCs=0.730[95%CI:0.645-0.804]and 0.712[95%CI:0.586-0.824],respectively).The combined model(TME-score+clinical features,including cytokeratin 19 fragment and non-contrast CT values)further improved predictive performance(AUCs=0.884[95%CI:0.827-0.932]and 0.882[95%CI:0.798-0.950],respectively).Delong's test for pairwise model comparis-ons showed significant differences(all P<0.05)except TME-score and the combined model in the validation cohort(P=0.289).Conclusions:TME-score outperformed clinical models in predicting EGFR-TKIs efficacy in EGFR mutation-positive NSCLC patients and may serve as a novel tool for identifying patients likely to benefit from targeted therapy.

Objective To examine the effect of aqueous extracts of Scutellaria baicalensis Georgi and Radix paeoniae Alba on periodontitis mice and compare the results of the two herbs for the treatment of the periodontitis mice.Methods Sixty-four SPF 12-week-old male Kunming mice were selected and randomly divided into four groups:Control group (C) ;Experimental periodontitis group (P):the peridontitis models in Kunming mice were prepared by wrapping silk ligature and inoculating with putative periodontopathic bacteria; Scutellaria baicalensis Georgi treatment group(SG):periodontitis was induced by the same method described above,the mice were gavaged with Scutellaria baicalensis Georgi; Radix paeoniae Alba treatment group (RG):periodontitis was induced by the same method described above,the mice were gavaged with Radix paeoniae Alba.Four mice were sacrificed at each time point of the end of 4,6,8 and 10 weeks in each group.The histopathological changes of periodontal tissue were observed under microscope with HE staining.The level of serum IgG1 and IgG2a was measured by enzyme-linked immunosorbent assay(ELISA).Results A serious inflammatory response,alveolar progressive absorption and a large number of osteoclasts were observed in the experimental periodontitis group.However,in SG and RG,the inflammation of the periodontal tissue was decreased and tissue repair was significant.The level of serum IgG2a in SG(6 week:0.934 ± 0.006,8 week:0.743 ± 0.009,10 week:0.674 ± 0.008) and RG (6 week:1.023 ± 0.032,8 week:0.851 ± 0.032,10 week:0.790 ± 0.009) was significantly decreased after the mice were gavaged with the two herbs(P ＜ 0.01).The level of serum IgG2a in SG was significantly lower than that of RG(P ＜0.01).The level of serum IgG1 in SG(6 week:0.314 ±0.006,8 week:0.344 ± 0.004,10 week:0.367 ±0.006) and RG(6 week:0.287 ±0.005,8 week:0.303 ±0.058,10 week:0.336 ±0.006) were significantly increased(P ＜ 0.01).The level of serum IgG1 in SG was significantly higher than that of RG (P ＜ 0.0l).Conclusions Both the aqueous extracts of Scutellaria baicalensis Georgi and Radix paeoniae Alba showed therapeutic effect on periodontitis in mice.Scutellaria baicalensis Georgi was more effective than Radix paeoniae Alba.