ObjectiveTo explore the mechanism of postoperative recurrence of hepatocellular carcinoma(HCC) and predicting the candidate drug. MethodsThe differently expressed genes of the human gene expression profiles with 35 postoperative recurrence of HCC tissues and 41 no recurrence of HCC tissues were identified. Then enriched these genes with gene ontology(GO) terms and KEGG pathway, and predicting the candidate drugs for suppress the postoperative recurrence using Connectivity Map(cmap) database. ResultsSeveral pathways such as Focal adhesion and MAPK signaling pathway were found involve in postoperative recurrence of HCC. Moreover, two candidate small molecule drugs(bambuterol and lovastatin) were found may suppress and postoperative recurrence of HCC. ConclusionFocal adhesion and MAPK signaling pathway may involve in the postoperative recurrence of HCC, bambuterol and lovastatin may candidate drugs for treat postoperative recurrence of HCC.
Computed tomography (CT) imaging is a vital tool for the diagnosis and assessment of lung adenocarcinoma, and using CT images to predict the recurrence-free survival (RFS) of lung adenocarcinoma patients post-surgery is of paramount importance in tailoring postoperative treatment plans. Addressing the challenging task of accurate RFS prediction using CT images, this paper introduces an innovative approach based on self-supervised pre-training and multi-task learning. We employed a self-supervised learning strategy known as “image transformation to image restoration” to pretrain a 3D-UNet network on publicly available lung CT datasets to extract generic visual features from lung images. Subsequently, we enhanced the network’s feature extraction capability through multi-task learning involving segmentation and classification tasks, guiding the network to extract image features relevant to RFS. Additionally, we designed a multi-scale feature aggregation module to comprehensively amalgamate multi-scale image features, and ultimately predicted the RFS risk score for lung adenocarcinoma with the aid of a feed-forward neural network. The predictive performance of the proposed method was assessed by ten-fold cross-validation. The results showed that the consistency index (C-index) of the proposed method for predicting RFS and the area under curve (AUC) for predicting whether recurrence occurs within three years reached 0.691 ± 0.076 and 0.707 ± 0.082, respectively, and the predictive performance was superior to that of existing methods. This study confirms that the proposed method has the potential of RFS prediction in lung adenocarcinoma patients, which is expected to provide a reliable basis for the development of individualized treatment plans.