Improving segmentation and classification of renal tumors in small sample 3D CT images using transfer learning with convolutional neural networks.

PURPOSE: Computed tomography (CT) images can display internal organs of patients and are particularly suitable for preoperative surgical diagnoses. The increasing demands for computer-aided systems in recent years have facilitated the development of many automated algorithms, especially deep convolutional neural networks, to segment organs and tumors or identify diseases from CT images. However, performances of some systems are highly affected by the amount of training data, while the sizes of medical image data sets, especially three-dimensional (3D) data sets, are usually small. This condition limits the application of deep learning. METHODS: In this study, given a practical clinical data set that has 3D CT images of 20 patients with renal carcinoma, we designed a pipeline employing transfer learning to alleviate the detrimental effect of the small sample size. A dual-channel fine segmentation network (FS-Net) was constructed to segment kidney and tumor regions, with 210 publicly available 3D images from a competition employed during the training phase. We also built discriminative classifiers to classify the benign and malignant tumors based on the segmented regions, where both handcrafted and deep features were tested. RESULTS: Our experimental results showed that the Dice values of segmented kidney and tumor regions were 0.9662 and 0.7685, respectively, which were better than those of state-of-the-art methods. The classification model using radiomics features can classify most of the tumors correctly. CONCLUSIONS: The designed FS-Net was demonstrated to be more effective than simply fine-tuning on the practical small size data set given that the model can borrow knowledge from large auxiliary data without diluting the signal in primary data. For the small data set, radiomics features outperformed deep features in the classification of benign and malignant tumors. This work highlights the importance of architecture design in transfer learning, and the proposed pipeline is anticipated to provide a reference and inspiration for small data analysis.

Bone marrow mesenchymal stem cells promote prostate cancer cell stemness via cell-cell contact to activate the Jagged1/Notch1 pathway.

BACKGROUND: Mesenchymal stem cells (MSCs) play a crucial role in cancer development and tumor resistance to therapy in prostate cancer, but the influence of MSCs on the stemness potential of PCa cells by cell-cell contact remains unclear. In this study, we investigated the effect of direct contact of PCa cells with MSCs on the stemness of PCa and its mechanisms. METHODS: First, the flow cytometry, colony formation, and sphere formation were performed to determine the stemness of PCaMSCs, and the expression of stemness-related molecules (Sox2, Oct4, and Nanog) was investigated by western blot analysis. Then, we used western blot and qPCR to determine the activity levels of two candidate pathways and their downstream stemness-associated pathway. Finally, we verified the role of the significantly changed pathway by assessing the key factors in this pathway via in vitro and in vivo experiments. RESULTS: We established that MSCs promoted the stemness of PCa cells by cell-cell contact. We here established that the enhanced stemness of PCaMSCs was independent of the CCL5/CCR5 pathway. We also found that PCaMSCs up-regulated the expression of Notch signaling-related genes, and inhibition of Jagged1-Notch1 signaling in PCaMSCs cells significantly inhibited MSCs-induced stemness and tumorigenesis in vitro and in vivo. CONCLUSIONS: Our results reveal a novel interaction between MSCs and PCa cells in promoting tumorigenesis through activation of the Jagged1/Notch1 pathway, providing a new therapeutic target for the treatment of PCa.