Keywords
Segmentation
PSO
Deep learning
How to Cite
Abstract
The detection and treatment of cancerous tumors in the liver are considered one of the most challenging health issues for patients globally. There is a need for fully automated systems that can precisely detect and segment the tumorous regions in medical images. This work aims to develop an automated system which utilizes a hybrid- deep- learning framework with fusion multi-scale inception feature extraction called HSCS-NET (Hawk-Swarm Ception Segmentation Network). In the proposed model, the encoder comprises of Hawk Gating with SE (squeeze-and-excitation) attention while decoders consist of adaptive attention skip fusion which comprises of Swarm ception Residual ASPP bridges. These components allow the model to recover important details of the boundaries of the tumors irrespective to their shape, size, and the tissue contrast in CT scans.In order to improve segmentation, the HSCS-NET framework is equipped with a hybrid optimization module based on PSO (Particle Swarm Optimization) and GWO (Grey Wolf Optimization) for dynamic feature selection and reliable convergence. The model was evaluated against the 3DIRCADb1 Liver Tumor Segmentation Challenge (LiTS) dataset and significantly outperformed all other models achieving a Dice coefficient value of 0.98, Accuracy of 0.9891, and Precision of 0.9901.This marks a substantial improvement over prior models such as Christ et al.’s CNN (Dice: 0.823), Wu et al.’s Fuzzy C-means + GC (Dice: 0.83), Muhammad et al.’s ResNet (Dice: 0.87, Accuracy: 0.945, Precision: 0.93), and Kaur et al.’s PSO-PSP-Net (Accuracy: 0.9754, Precision: 0.9632).The HSCS-NET architecture is mathematically grounded, modularly extensible, and validated through rigorous cross-validation and confidence refinement. With its high segmentation performance, clinical reliability, and computational efficiency, HSCS-NET stands as a superior advancement in automated liver cancer diagnostics, reducing clinician workload and improving patient prognoses through precision imaging.
References
Banerjee, T., 2025a. Attentive CNN EEG or ACE-SeizNet: An Attention-Enhanced CNN Model for Automated EEG-Based Seizure Detection.
Banerjee, T., 2025b. IMATX: An Integrated Multi-Context Pyramidal Framework for Explainable AI Predictions.
Banerjee, T., 2025c. Towards Automated and Reliable Lung Cancer Detection Using DY-FSPAN. Computational Biology and Chemistry, p. 108500.
Banerjee, T., D. Batta, A. Jain, S. Karthikeyan, H. Mehndiratta, et al., 2021a. Deep Belief CNN with GAN-Based Diagnosis of Pneumonia. In ICEEE 2021, Springer.
Banerjee, T., D. Butta, A. Jain, K. S. Biradar, R. R. Koripally, et al., 2021b. Deep Belief CNN for Diagnosis of Pneumonia. In ICAECT 2021, IEEE.
Banerjee, T., A. Jain, S. C. Sethuraman, S. C. Satapathy, S. Karthikeyan, et al., 2022a. Deep CNN (Falcon) and Transfer Learning-Based Approach to Detect Malarial Parasite. Multimedia Tools and Applications, 81, 13237–13251.
Banerjee, T., Y. F. Khan, T. Rafiq, S. Singh, R. Wason, et al., 2025. HHO-UNet-IAA: Harris Hawks Optimization Based UNet Architecture for Glaucoma Segmentation. International Journal of Information Technology.
Banerjee, T., A. Sharma, K. Charvi, S. Raman, and S. Karthikeyan, 2022b. Attention-Based Discrimination of Mycoplasma Pneumonia. In ICCIDE 2021, Springer.
Banerjee, T., A. Sharma, K. Charvi, S. Raman, R. G. Regalla, et al., 2022c. Journey of Letters to Vectors Through Neural Networks. In ICDAM 2021, Springer.
Banerjee, T., K. V. P. Srikar, S. A. Reddy, K. S. Biradar, R. R. Koripally, et al., 2021c. Hand Sign Recognition Using Infrared Imagery. In ICIPTM 2021, IEEE.
Bilic, P., P. F. Christ, E. Vorontsov, G. Chlebus, H. Chen, et al., 2019. The Liver Tumor Segmentation Benchmark (LiTS). arXiv preprint arXiv:1901.04056.
Cakmak, Y., I. Pacal, et al., 2026. A Comparative Analysis of Transformer Architectures for Automated Lung Cancer Detection in CT Images. Journal of Intelligent Decision Making and Information Science, 3, 528–539.
Christ, P. F., 2017. Convolutional Neural Networks for Classification and Segmentation of Medical Images. Ph.D. thesis, Technische Universität München, Munich, Germany.
Christ, P. F., M. E. A. Elshaer, F. Ettlinger, S. Tatavarty, M. Bickel, et al., 2016. Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields. In MICCAI, pp. 415–423, Springer.
Jiang, H., T. Shi, Z. Bai, and L. Huang, 2019. AHCNet: An Application of Attention Mechanism and Hybrid Connection for Liver Tumor Segmentation in CT Volumes. IEEE Access, 7, 24898–24909.
Jin, Q., Z. Meng, C. Sun, H. Cui, and R. Su, 2020. RA-UNet: A Hybrid Deep Attention-Aware Network to Extract Liver and Tumor in CT Scans. Frontiers in Bioengineering and Biotechnology, 8, 1471.
Karthikeyan, S., S. Gopikrishnan, D. Batta, and T. Banerjee, 2021. Double Helical Ensemble Neural Network to Analyze Driving Pattern. Turkish Journal of Computer and Mathematics Education, 12, 6447–6458.
Kaur, J. and P. Kaur, 2024. PSO-PSP-Net + InceptionV3: An Optimized Hyper-Parameter Tuned CAD Model for Liver Tumor Detection. Biomedical Signal Processing and Control, 95, 106442.
Krizhevsky, A., I. Sutskever, and G. E. Hinton, 2017. ImageNet Classification with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84–90.
Li, D., L. Liu, J. Chen, H. Li, and Y. Yin, 2014. A Multistep Liver Segmentation Strategy by Combining Level Set Based Method with Texture Analysis for CT Images. In International Conference on Orange Technologies, pp. 109–112, IEEE.
Li, Q., M. Cao, L. Lei, F. Yang, H. Li, et al., 2022. Burden of Liver Cancer: From Epidemiology to Prevention. Chinese Journal of Cancer Research, 34, 554.
Li, X., H. Chen, X. Qi, Q. Dou, C.-W. Fu, et al., 2018. H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes. IEEE Transactions on Medical Imaging, 37, 2663–2674.
Lu, S., K. Xia, and S.-H. Wang, 2020. Diagnosis of Cerebral Microbleed via VGG and Extreme Learning Machine Trained by Gaussian Map Bat Algorithm. Journal of Ambient Intelligence and Humanized Computing, 14, 5395–5406.
Muhammad, S. and J. Zhang, 2024. Segmentation of Liver Tumors by MONAI and PyTorch in CT Images with Deep Learning Techniques. Applied Sciences, 14, 5144.
Pacal, I. and Y. Cakmak, 2025. A Comparative Analysis of U-Net-Based Architectures for Robust Segmentation of Bladder Cancer Lesions in Magnetic Resonance Imaging. Eurasian Journal of Medicine and Oncology, 9, 268–283.
Peesa, R. B., A. Satpathy, S. Karthikeyan, M. Bisht, T. Banerjee, et al., 2020. Single Node Hadoop Cluster for Small Scale Industrial Automation. In ICCCA 2020, IEEE.
Rehman, A., T. Mahmood, and T. Saba, 2025. Robust Kidney Carcinoma Prognosis Using Swin-ViT and DeepLabV3+. Applied Soft Computing, 170, 112518.
Saminathan, K., T. Banerjee, D. P. Rangasamy, and M. Vimal Cruz, 2024. Segmentation of Thoracic Organs Using Resio-Inception U-Net. Current Gene Therapy, 24, 217–238.
Singh, D. P., T. Banerjee, P. Kour, D. Swain, and Y. Narayan, 2025a. CICADA (UCX): Automated Breast Cancer Classification. Computational Biology and Chemistry, p. 108368.
Singh, D. P., P. Kour, T. Banerjee, and D. Swain, 2025b. Review of Machine Learning Models for Anti-Cancer Drug Response Prediction. Archives of Computational Methods in Engineering.
Soler, L. et al., 2010. 3D-IRCADb-01: A 3D Imaging Dataset of Liver Tumors. IRCAD, Strasbourg, France.
Song, X., M. Cheng, B. Wang, S. Huang, X. Huang, et al., 2013. Adaptive Fast Marching Method for Automatic Liver Segmentation from CT Images. Medical Physics, 40, 091917.
Sun, C., S. Guo, H. Zhang, J. Li, M. Chen, et al., 2017. Automatic Segmentation of Liver Tumors from Multiphase Contrast-Enhanced CT Images Based on FCNs. Artificial Intelligence in Medicine, 83, 58–66.
World Health Organization, 2021. Cancer. Available online.
Wu, W., S. Wu, Z. Zhou, R. Zhang, and Y. Zhang, 2017. 3D Liver Tumor Segmentation in CT Images Using Improved Fuzzy C-Means and Graph Cuts. BioMed Research International, p. 5207685.
Yasaka, K., H. Akai, O. Abe, and S. Kiryu, 2018. Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-Enhanced CT. Radiology, 286, 887–896.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.