No abstract

Ovarian cancer is a common malignant gynecological disease. Molecular target therapy, i.e., antiangiogenesis with bevacizumab, was found to be effective in some patients of epithelial ovarian cancer (EOC). Although careful patient selection is essential, there are currently no biomarkers available for routine therapeutic usage. To the authors’ best knowledge, this is the first automated precision oncology framework to effectively identify and select EOC and peritoneal serous papillary carcinoma (PSPC) patients with positive therapeutic effect. From March 2013 to January 2021, we have a database, containing four kinds of immunohistochemical tissue samples, including AIM2, c3, C5 and NLRP3, from patients diagnosed with EOC and PSPC and treated with bevacizumab in a hospital-based retrospective study. We developed a hybrid deep learning framework and weakly supervised deep learning models for each potential biomarker, and the experimental results show that the proposed model in combination with AIM2 achieves high accuracy 0.92, recall 0.97, F-measure 0.93 and AUC 0.97 for the first experiment (66% training and 34%testing) and high accuracy 0.86 ± 0.07, precision 0.9 ± 0.07, recall 0.85 ± 0.06, F-measure 0.87 ± 0.06 and AUC 0.91 ± 0.05 for the second experiment using five-fold cross validation, respectively. Both Kaplan-Meier PFS analysis and Cox proportional hazards model analysis further confirmed that the proposed AIM2-DL model is able to distinguish patients gaining positive therapeutic effects with low cancer recurrence from patients with disease progression after treatment (p<0.005).

Antiangiogenic therapy, such as bevacizumab (BEV), has improved progression-free survival (PFS) and overall survival (OS) in high-risk patients with epithelial ovarian cancer (EOC) according to several clinical trials. Clinically, no reliable molecular biomarker is available to predict the treatment response to antiangiogenic therapy. Immune-related proteins can indirectly contribute to angiogenesis by regulating stromal cells in the tumor microenvironment. This study was performed to search biomarkers for prediction of the BEV treatment response in EOC patients. We conducted a hospital-based retrospective study from March 2013 to May 2020. Tissues from 78 Taiwanese patients who were newly diagnosed with EOC and peritoneal serous papillary carcinoma (PSPC) and received BEV therapy were collected. We used immunohistochemistry (IHC) staining and analyzed the expression of these putative biomarkers (complement component 3 (C3), complement component 5 (C5), and absent in melanoma 2 (AIM2)) based on the staining area and intensity of the color reaction to predict BEV efficacy in EOC patients. The immunostaining scores of AIM2 were significantly higher in the BEV-resistant group (RG) than in the BEV-sensitive group (SG) (355.5 vs. 297.1, p < 0.001). A high level of AIM2 (mean value > 310) conferred worse PFS after treatment with BEV than a low level of AIM2 (13.58 vs. 19.36 months, adjusted hazard ratio (HR) = 4.44, 95% confidence interval (CI) = 2.01–9.80, p < 0.001). There were no significant differences in C3 (p = 0.077) or C5 (p = 0.326) regarding BEV efficacy. AIM2 inflammasome expression can be a histopathological biomarker to predict the antiangiogenic therapy benefit in EOC patients. The molecular mechanism requires further investigation.