Several solid tumors (for example leiomyosarcoma, melanoma and hepatocellular carcinoma) possess areas of hypoxia, which underlies one of the primary reasons of failure of conventional anticancer therapies. The areas of poor vascularization are insensitive to radiotherapy and chemotherapeutic drugs. Conversely, the hypoxic regions of tumors provide an ideal environment for anaerobic bacteria. The attenuated anaerobic bacterium, Clostridium novyi‑NT (C. novyi‑NT), is highly sensitive to oxygen and can target the destruction of hypoxic and necrotic areas of tumors, inducing oncolysis and characteristics indicative of an immune response. Theoretically, chemotherapy, radiotherapy and immunotherapy combined with bacterial therapy can be used as a novel means of treating solid tumors, promoting tumor regression and inhibiting metastasis formation with a notable beneficial effect. The present review discusses the molecular mechanisms of combined bacteriolytic therapy, predominantly focusing on C. novyi‑NT, and summarizes the findings of previous studies on experimental animal models, including its efficacy and safety via different drug delivery routes. This strategy has great potential to overcome the limitations of conventional cancer therapy, resulting in improved treatments, and thus potentially improved outcomes for patients.

Liver image segmentation has been increasingly employed for key medical purposes, including liver functional assessment, disease diagnosis, and treatment. In this work, we introduce a liver image segmentation method based on generative adversarial networks (GANs) and mask region‐based convolutional neural networks (Mask R‐CNN). Firstly, since most resulting images have noisy features, we further explored the combination of Mask R‐CNN and GANs in order to enhance the pixel‐wise classification. Secondly, k‐means clustering was used to lock the image aspect ratio, in order to get more essential anchors which can help boost the segmentation performance. Finally, we proposed a GAN Mask R‐CNN algorithm which achieved superior performance in comparison with the conventional Mask R‐CNN, Mask‐CNN, and k‐means algorithms in terms of the Dice similarity coefficient (DSC) and the MICCAI metrics. The proposed algorithm also achieved superior performance in comparison with ten state‐of‐the‐art algorithms in terms of six Boolean indicators. We hope that our work can be effectively used to optimize the segmentation and classification of liver anomalies.