Citations

Abstract Ovarian cancer is the deadliest gynecologic malignancy worldwide, with a 5-year overall survival rate of approximately 49%. Although complete resection is associated with the most favorable prognosis following primary debulking surgery, accurately assessing tumor resectability at diagnosis remains a major clinical challenge. We propose a decision support system (DSS) designed to predict residual tumor after primary debulking surgery, based on clinical and imaging data available at diagnosis. The system was developed and validated using a retrospective cohort of 465 patients with high-grade serous ovarian cancer, collected at the European Institute of Oncology in Milan, Italy. We developed a deep learning (DL) model that combines pre-trained Vision Transformer encoders with an attention mechanism and a classification head. When evaluated on an independent test cohort of 75 cases, our best-performing model achieved an area under the curve (AUC) of 0.80 (95% CI: 0.68–0.89) and a recall of 0.86 (95% CI: 0.71–0.97), demonstrating discriminatory ability with a particularly low rate of false negatives. Clinically, the model correctly identified 24 out of 28 patients (86%) with non-resectable disease, who would not have benefited from primary debulking surgery. Notably, within this subgroup, the model accurately predicted 93% (13 out of 14) of cases in which surgery was aborted intraoperatively due to unforeseen unresectable disease. These findings suggest that the model could have potential in preventing unnecessary and inappropriate surgical interventions. The proposed DSS is a fully automated, DL–based system for predicting tumor resectability at diagnosis, without the need for manual segmentation or expert evaluation of radiological features and structured clinical parameters. This approach could facilitate and accelerate personalized treatment planning in ovarian cancer. The work is part of the project Under-XAI: understanding ovarian cancer initiation and progression through explainable AI. Project code: PNRR-MAD-2022-12376574.

e13701 Background: The optimal therapeutic strategy for advanced epithelial ovarian cancer (EOC) — primary debulking surgery (PDS) followed by adjuvant chemotherapy vs. neoadjuvant chemotherapy (NACT) followed by interval debulking surgery — remains debated. NACT is often chosen for unresectable disease, typically identified only during surgery. This study aims to develop a deep learning (DL) model to predict tumor resectability from pre-operative computed tomography (CT) scans. Methods: We retrospectively included EOC patients, FIGO stage III-IV, who underwent PDS between 01/ 2016 and 12/2023 at the European Institute of Oncology, Milan, Italy. The dataset included anonymized portal venous phase contrast-enhanced CT scans. Residual tumor (RT) annotations were extracted from operative reports and categorized as optimal RT (< 1cm) and suboptimal RT (≥1cm). A DL segmentation model (based on open-source TotalSegmentator) was used to identify pelvic/abdominal organ volumes and to remove couch artifacts. The dataset was split into training/validation (80%) and testing (20%) sets. A pre-trained Vision Transformer (ViT) encoder was adapted for 3D imaging, converting CT volumes into features refined by an attention mechanism and classified as optimal RT or suboptimal RT . We trained two ViT configurations (vit-base-patch16-224 and dinov2-small-imagenet1k-1-layer) and compared them with DenseNet121, a widely used Convolutional Neural Network (CNN) for image classification. Performance metrics included accuracy and F1 score. Results: Out of 521 patients, 416 (80%) had optimal RT and 105 (20%) suboptimal RT , the proportion being respected througouth the training/validation and testing groups. The median age at diagnosis was 60.0 years (IQR, 53.0-67.0). ViT models showed better performance compared to CNN in terms of accuracy (0.80 and 0.77 vs. 0.62) and F1 score (0.43 and 0.33 vs. 0.12). Conclusions: A pioneering ViT-based model was capable to predict tumor resectability from pre-operative CT scans in patients with advanced EOC. This improvement in performance, compared to CNN, might be due to the ViTs' ability to capture long-range dependencies and global context, which are crucial for predicting tumor resectability. In contrast, CNNs are limited by localized feature extraction and inductive bias, hindering their ability to capture the complex spatial relationships. By addressing the limitations of current radiological assessments, the model has the potential to serve as a clinical decision-support tool, enabling personalized management strategies for patients. Future work will focus on further improving the model performance.

Abstract Background Cardiovascular disease remains the leading cause of death and burden globally, warranting the need to explore novel predictors of major adverse cardiovascular events (MACE) using new technologies. Artificial Intelligence (AI)-enhanced ECG (AI-ECG) algorithms can provide information on cardiovascular health of individuals, independent of conventional risk factors. Purpose The current study aimed to understand whether a previously described AI-ECG sex estimation algorithm could be applied for risk stratification of major adverse cardiovascular events (MACE), with a focus on a population without previous history of MACE. Methods Patients having 12-lead ECGs between 2018-2019 were included and followed up until August 2023. Exclusion criterion was a prior history of MACE. AI-ECG sex estimation was determined using a previously described algorithm predicting sex based on 12-lead ECGs. The algorithm generates outputs ranging from 0 to 1, representing the estimated probability of being male. Outputs above 0.5 were considered as AI-ECG-estimated male, and below as AI-ECG-estimated female. This was compared with biological sex to determine whether the two matched. Inconsistency between AI-ECG estimated sex and biological sex was defined as discordance. MACE was defined as myocardial infarction, coronary revascularization, non-fatal stroke, and all-cause death. Results Among 80,578 subjects (mean age 59.1 ± 16.1 years, 52.4% female), 9.7% exhibited sex discordance in AI-ECG estimation. Discordance was associated with a 56% higher risk of MACE (HR, 1.56, 95% CI 1.46-1.65, p &lt;0.001), and remained significant in multivariable analysis with traditional risk factors (HR 1.35, 95% CI 1.27-1.43, p &lt;0.001) (Figure 1). Sex-specific analysis showed increased MACE risk in both discordant males and females (Figure 2). Conclusion In patients with no history of MACE, discordance in AI-ECG sex estimation is associated with increased risk of MACE. These findings suggest the potential of AI-ECG sex estimation algorithm for risk assessment, especially in patients with no history of MACE.Figure 1.Cox proportional hazard modelFigure 2.Kaplan-Meier of MACE by sex

Abstract Metastasis causes poor prognosis and yet remains the least understood aspect of cancer. To identify key regulators of ovarian cancer metastasis that drive early colonization and are also essential for advanced metastasis, we have applied a novel, comprehensive approach of combining the analysis of an organotypic 3D culture model of early metastasis with ovarian cancer patient tumors. Using matched primary and metastatic tumors from 42 OC patients, we have compared the fully formed metastatic tumors with the primary tumor of the same patient. Since this is an end-point analysis and reveals little about the intermediated regulatory steps, we have also studied the changes occurring during early metastatic colonization as a result of the interactions with the metastatic microenvironment by using an organotypic 3D culture model of omental metastasis. By combining these two approaches, we have identified key master regulators of metastasis that are essential for early metastatic colonization and remain important in the fully formed metastatic tumor. We specifically focused on microRNAs because of their pleotropic effects through translational inhibition of multiple targets, and also our previous studies have demonstrated their important role in metastasis. Using this approach, we identified a novel microRNA miR-4454, downregulated in the metastasizing ovarian cancer cells through their specific paracrine interactions with fibroblasts in the metastatic microenvironment. The downregulation of miR-4454 promoted high-grade serous ovarian cancer cell migration, invasion, proliferation, and clonogenic growth as well as metastasis in xenografts. The targets of miR-4454 were identified by RNA-seq in high-grade serous ovarian cancer cells overexpressing the microRNA. SPARC and BAG5 were found to be the functional effectors of miR-4454. SPARC activated FAK signaling and promoted metastasis, while BAG5 inhibited apoptosis and helped the metastasizing cancer cells tide over adverse conditions in the microenvironment. Since miR-4454 is essential for early metastatic colonization as well as in advanced metastasis, targeting it is a promising approach to treat metastatic ovarian cancer. Citation Format: Subramanyam Dasari, Taruni Pandhiri, Tommaso Grassi, Daniel W. Visscher, Francesco Multinu, Komal Agarwal, Andrea Mariani, Viji Shridhar, Anirban K. Mitra. Paracrine interactions with microenvironmental fibroblasts promote ovarian cancer metastasis through downregulation of miR-4454 [abstract]. In: Proceedings of the AACR Special Conference on Advances in Ovarian Cancer Research; 2019 Sep 13-16, 2019; Atlanta, GA. Philadelphia (PA): AACR; Clin Cancer Res 2020;26(13_Suppl):Abstract nr B66.

Abstract Treatment of ovarian cancer is limited by extensive metastasis and yet it remains poorly understood. We have studied the critical step of metastatic colonization in the context of the productive interactions with the metastatic microenvironment with a goal of identifying key regulators. By combining miRNA expression analysis using an organotypic 3D culture model of early ovarian cancer metastasis with that of matched primary and metastatic tumors from 42 patients with ovarian cancer, we identified miR-4454 as a key regulator of both early colonization and advanced metastasis in patients with ovarian cancer. miR-4454 was downregulated in the metastasizing ovarian cancer cells through paracrine signals from microenvironmental fibroblasts, which promoted migration, invasion, proliferation, and clonogenic growth in ovarian cancer cells as well as their ability to penetrate through the outer layers of the omentum. Stable overexpression of miR-4454 decreased metastasis in ovarian cancer xenografts. Its mechanism of action was through the upregulation of its targets, secreted protein acidic and cysteine rich (SPARC) and BCL2 associated athanogene 5 (BAG5), which activated focal adhesion kinase (FAK) signaling, promoted mutant p53 gain of function by its stabilization, and inhibited apoptosis. Because microenvironment-induced downregulation of miR-4454 is essential for early and advanced metastasis, targeting it could be a promising therapeutic approach. Implications: This study identifies a miRNA, miR-4454, which is downregulated by signals from the microenvironment and promotes early and advanced ovarian cancer metastasis through its effects on FAK activation, mutant p53 stabilization, and apoptosis inhibition.

The genomic DNA input for stool samples utilized for microbiome composition has not been determined. In this study, we determined the reliable threshold level under which conclusions drawn from the data may be compromised. We also determined the type of microbial bias introduced by less-than-ideal genomic input.

Abstract Endometrial cancer studies have led to a number of well-defined but mechanistically unconnected genetic and environmental risk factors. One of the emerging modulators between environmental triggers and genetic expression is the microbiome. Because of the inflammatory display in endometrial cancer, we set out to inquire about the composition of the uterine microbiome and its putative role in endometrial cancer. We undertook a pilot study of the microbiome in 238 samples taken from different locations along the entire female reproductive tract in hysterectomy patients with endometrial cancer (n=17), patients with endometrial hyperplasia (n=4) and patients afflicted with a benign uterine condition (n=10). Samples were collected aseptically both in the operating room and the pathology laboratory. Following DNA extraction, the 16S rDNA (V3-V5 region) microbial gene was amplified and sequenced to identify the microbiota present. The microbiome sequencing revealed a structural microbiome shift in the cancer and hyperplasia cases, distinguishable from the benign cases (p=0.01). Several taxa were found to be significantly enriched in samples belonging to the endometrial cancer cohort: Firmicutes (Anaerostipes, ph2, Dialister, Peptoniphilus, 1-68, Ruminococcus, and Anaerotruncus), Spirochaetes (Treponema), Actinobacteria (Atopobium), Bacteroidetes (Bacteroides and Porphyromonas), and Proteobacteria (Arthrospira). Of particular relevance, the simultaneous presence of Atopobium vaginae and an uncultured representative of the Porphyromonas sp. (99% match to P.somerae) were found to be predictive of the disease status (sensitivity 73-93%; specificity 67-90%, AUC 0.918). Sensitivity is increased to 100% if combined with a high vaginal pH (&gt;4.5), although specificity is decreased to 60%. Although our numbers are low, the microbiome signature of hyperplasia was even more distinct from benign disease than endometrial cancer itself. This is suggestive of an early microbiome role in the disease. Given the pathogenic profile of the identified microorganisms these findings raise the possibility of a microbiome role in the etiology or progression of endometrial cancer that should be further investigated. Citation Format: Marina Walther-Antonio, Jun Chen, Francesco Multinu, Alexis Hokenstad, Tammy Distad, Heidi Cheek, Gary Keeney, Douglas Creedon, Heidi Nelson, Andrea Mariani, Nicholas Chia. Endometrial cancer microbiome signature and its implications for carcinogenesis. [abstract]. In: Proceedings of the AACR Precision Medicine Series: Targeting the Vulnerabilities of Cancer; May 16-19, 2016; Miami, FL. Philadelphia (PA): AACR; Clin Cancer Res 2017;23(1_Suppl):Abstract nr B45.