Exploring prognostic indicators in the pathological images of ovarian cancer based on a deep survival network

Abstract

Background: Tumor pathology can assess patient prognosis based on a morphological deviation of tumor tissue from normal. Digitizing whole slide images (WSIs) of tissue enables the use of deep learning (DL) techniques in pathology, which may shed light on prognostic indicators of cancers, and avoid biases introduced by human experience.Purpose: We aim to explore new prognostic indicators of ovarian cancer (OC) patients using the DL framework on WSIs, and provide a valuable approach for OC risk stratification.Methods: We obtained the TCGA-OV dataset from the NIH Genomic Data Commons Data Portal database. The preprocessing of the dataset was comprised of three stages: 1) The WSIs and corresponding clinical data were paired and filtered based on a unique patient ID; 2) a weakly-supervised CLAM WSI-analysis tool was exploited to segment regions of interest; 3) the pre-trained model ResNet50 on ImageNet was employed to extract feature tensors. We proposed an attention-based network to predict a hazard score for each case. Furthermore, all cases were divided into a high-risk score group and a low-risk one according to the median as the threshold value. The multi-omics data of OC patients were used to assess the potential applications of the risk score. Finally, a nomogram based on risk scores and age features was established.Results: A total of 90 WSIs were processed, extracted, and fed into the attention-based network. The mean value of the resulting C-index was 0.5789 (0.5096–0.6053), and the resulting p-value was 0.00845. Moreover, the risk score showed a better prediction ability in the HRD + subgroup.Conclusion: Our deep learning framework is a promising method for searching WSIs, and providing a valuable clinical means for prognosis.

Comprehensive analysis for the immune related biomarkers of platinum-based chemotherapy in ovarian cancer

“…Platinum-based chemotherapy is the essential treatment for OC [27] . Most patients with OC will experience repeated recurrence and gradually progress from platinum-sensitive to platinum-resistant [28] .…”

Recent Advancements in Deep Learning Using Whole Slide Imaging for Cancer Prognosis

“…This group includes diverse studies by Liang et al [ 55 ], Zheng et al [ 49 ], and Jiang et al [ 48 ]. Residual networks, a form of CNN, have been frequently implemented, as seen in works by Liu et al [ 69 ], Wu et al [ 72 ], and Knuutila et al [ 76 ], who utilized the ResNet model due to its ability to effectively train very deep neural networks. Of late, there has been an uptick in the application of attention mechanisms, which allocate varying levels of importance to different parts of the image.…”

“…Of late, there has been an uptick in the application of attention mechanisms, which allocate varying levels of importance to different parts of the image. For instance, Jiang et al [ 83 ] employed a multihead attention mechanism and Wu et al [ 72 ] combined ResNet with attention mechanisms. Such models have been increasingly favored due to their capability to focus on crucial regions of an image while simultaneously considering the context, thus improving their interpretability and prediction accuracy.…”

“…Focusing on specific cancer types, deep learning methods have been deployed for early-stage lung adenocarcinoma prognosis (Shim et al [ 60 ]), ovarian cancer prognosis (Wu et al [ 72 ]), and recurrence-free survival prediction in hepatocellular carcinoma (Qu et al [ 56 ]). Additional efforts include a CNN-based system for identifying gastric mucosa abnormalities (Ma et al [ 74 ]), and the use of CNNs for classifying renal cell carcinoma subtypes (Tabibu et al [ 67 ]).…”

Advances in artificial intelligence for the diagnosis and treatment of ovarian cancer (Review)

“…The proposed DL model could effectively distinguish patients who would respond well from the patients whose recurrence rate would be low after treatment and those whose disease was likely to deteriorate after treatment. Wu et al ( 103 ) appraised the WSI results of patients with OC through DL, and developed risk scores for these patients. The AUC of the time-dependent ROC curve verified the good predictive performance of risk scores.…”