Efficient and accurate diagnosis from CT images is a crucial step in liver cancer diagnosis and treatment. Currently, liver cancer diagnosis mainly relies on manual work, which is heavily dependent on doctors' experience and susceptible to their subjective factors. This paper will explore in-depth automatic segmentation methods for the liver and liver tumors in CT images based on deep learning. By implementing architectures such as Unet and its variants, and simultaneously calling the Qwen-VL-Max multimodal large model to evaluate segmentation results, and using the PYQT framework to build an interface, the system achieves precise segmentation of liver and tumor regions in CT images. Thus, an efficient, easy-to-operate, and highly interactive liver tumor segmentation system is constructed to provide technical support for doctors' auxiliary diagnosis.

Wei Gao. Liver Health: A Deep Learning-Based Auxiliary Diagnostic System for Liver Tumor Segmentation in CT Images. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 10: 90-98. https://doi.org/10.25236/AJCIS.2025.081012.

[1] Wang Peiyu, Huang Qi, Wang Shaodong, et al. Key Points Interpretation of *Global Cancer Statistics 2022*[J]. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2024, 31(07): 933-954. 

[2] Zhao Haichao, Gao Qiang. New Progress in Liver Cancer Research and Diagnosis and Treatment in 2022[J]. Chinese Journal of Cancer, 2023, 33(04): 315-326. 

[3] Cui Hui, Guo Yinghui, Cai Xiaohong, et al. Progress in the Application of Deep Learning in Liver and Liver Tumor Segmentation[J/OL]. Computer Engineering and Applications, 1-16[2025-06-02]. http: //kns.cnki.net/kcms/detail/11.2127.TP.20250328.1606.004.html. 

[4] Hao Boqun. Design of Liver Image Segmentation System Based on Region Growing[J]. Journal of Tonghua Normal University, 2024, 45(10): 1-9. 

[5] Xie Chang, Liu Changhong, Jiao Zhan. System Function Design and Software Implementation of Computer-Aided Method Research[J]. Information Recording Materials, 2023, 24(12): 201-204. 

[6] Li Shufeng, Li Xiaolei, Wang Anshan. Design of Medical Image Automatic Diagnosis System Based on Deep Learning[J]. China New Technologies and Products, 2025, (01): 32-34. 

[7] Xie E, Wang W, Yu Z, et al. SegFormer: Simple and efficient design for semantic segmentation with transformers[J]. Advances in Neural Information Processing Systems, 2021, 34: 12077-12090.

[8] Li Mingyang. Research on CT Image Segmentation Algorithm for Liver and Tumor Based on Semi-Supervised Learning[D]. Southwest University of Science and Technology, 2024. 

[9] Wang Rongmiao. Research on Liver Segmentation Algorithm Based on Multi-Phase CT Images and Construction of Visualization Platform[D]. Soochow University, 2020. 

[10] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer International Publishing, 2015: 234-241. 

[11] Zhou Z, Siddiquee M M R, Tajbakhsh N, et al. Unet++: Redesigning skip connections to exploit multiscale features in imagesegmentation[J]. IEEE Transactions on Medical Imaging, 2019, 39(6): 1856-1867. 

[12] Huang H, Lin L, Tong R, et al. Unet 3+: A full-scale connected unet for medical image segmentation[C]//ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020: 1055-1059.