Enhancing CAR-T Cell Tumor Targeting via Advanced Computational Perception Networks for Improved Recognition in Heterogeneous Tumors

Trends in Immunotherapy

Article

Enhancing CAR-T Cell Tumor Targeting via Advanced Computational Perception Networks for Improved Recognition in Heterogeneous Tumors

Downloads

https://doi.org/10.54963/ti.v9i3.1288
Sennan, S., Sridevi, S., Shree, A. N. R., Babu, K. S., Channabasava, U., & K, I. A. J. (2025). Enhancing CAR-T Cell Tumor Targeting via Advanced Computational Perception Networks for Improved Recognition in Heterogeneous Tumors. Trends in Immunotherapy, 9(3), 252–270. https://doi.org/10.54963/ti.v9i3.1288
Volume 9 Issue 3 (September 2025) (in progress)
Copyright (c) 2025 Selvaganapathi Sennan, S Sridevi, A N Ramya Shree, Kunchala Suresh Babu, Ugranada Channabasava, Immanuvel Arokia James K
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright

The authors shall retain the copyright of their work but allow the Publisher to publish, copy, distribute, and convey the work.

License

Trends in Immunotherapy (TI)  publishes accepted manuscripts under Creative Commons Attribution 4.0 International (CC BY 4.0). Authors who submit their papers for publication by TI agree to have the CC BY 4.0 license applied to their work, and that anyone is allowed to reuse the article or part of it free of charge for any purpose, including commercial use. As long as the author and original source are properly cited, anyone may copy, redistribute, reuse, and transform the content.

Authors

  • Selvaganapathi Sennan

    Hexaware Technologies, Secaucus, NJ 07094‑3675, USA
  • S Sridevi

    Department of IoT, Koneru Lakshmaiah Education Foundation, Green Fields, Vaddeswaram, Andhra Pradesh 522302, India
  • A N Ramya Shree

    Department of CSEn(AI&ML), Ramaiah Institute of Technology, Bengaluru, Karnataka 560054, India
  • Kunchala Suresh Babu

    PSCMR College of Engineering and Technology, Vijayawada, Andhra Pradesh 520001, India
  • Ugranada Channabasava

    Department of Artificial intelligence and Data science, Global Academy of Technology, Bangalore, Karnataka 560098, India
  • Immanuvel Arokia James K

    Department of Artificial Intelligence and Data Science, Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College, Chennai, Tamil Nadu 600062, India

Received: 31 May 2025; Revised: 16 June 2025; Accepted: 09 July 2025; Published: 10 September 2025

In cancer treatments, the efficacy of Chimeric Antigen Receptor T (CAR-T) cell therapy is affected in heterogeneous tumors due to ambiguous tumor boundaries, morphological variability, and similarity between tumor and non-tumor tissues in medical imaging. Accurate tumor localization and classification are crucial for optimizing CAR-T targeting and therapeutic success. Traditional segmentation networks struggle with intensity similarity, shape variability, and contextual complexity in heterogeneous tumors. Further, robust classification of tumor regions using limited medical data remains a key challenge. We propose a dual-component Computational Perception Architecture composed of a novel segmentation-classification framework. The segmentation backbone is a U-Net enhanced with a Visual Perception Module (VPM) for ROI-level feature refinement. Multi-Head Self-Dilated Attention (MHSDA) in the encoder to capture multi-scale dependencies. ResNet50 with Dense Attention Modules in skip connections for improved feature continuity. Group Receptive Large Kernel (GRLK) Blocks for diverse receptive field decoding. The classification network utilizes edge-perception, morphological, and positional images, and segmentation maps. Deep ensemble learning for decision robustness and transfer learning to boost generalization on breast cancer labeled datasets. The proposed method is tested on the publicly available PBC and CAR-T datasets from Kaggle. The research model achieved a Dice Score of 0.901, an IoU of 0.856, a Precision of 0.882, a Classification Accuracy of 93.7%, and an F1-Score of 0.915. These outcomes show the superior capacity for precision tumor detection and classification, thus offering a potent computational aid in enhancing the targeting precision of CAR-T therapies.

Keywords:

CAR‑T Therapy Tumor Segmentation Computational Perception Deep Learning Attention Networks

References

  1. Sterner, R.C.; Sterner, R.M. EGFRVIII and EGFR Targeted Chimeric Antigen Receptor T Cell Therapy in Glioblastoma. Front. Oncol. 2024, 14, 1434495.
  2. Shi, T.; Sun, M.; Tuerhong, S.; et al. Acidity-Targeting Transition-Aided Universal Chimeric Antigen Receptor T-Cell (ATT-CAR-T) Therapy for the Treatment of Solid Tumors. Biomaterials 2024, 309, 122607.
  3. Aggeletopoulou, I.; Kalafateli, M.; Triantos, C. Chimeric Antigen Receptor T Cell Therapy for Hepatocellular Carcinoma: Where Do We Stand? Int. J. Mol. Sci. 2024, 25, 2631.
  4. Yalavarthi, S.; Makkapati, S.S.; Murari, H.; et al. Advanced Breast Cancer Diagnostics Through a Comparative Analysis of SVM, Random Forests, and Neural Networks in MRI Image Analysis. In Proceedings of the 2024 Asian Conference on Communication and Networks (ASIANComNet), Bangkok, Thailand, 30 December 2024.
  5. Missaoui, R.; Hechkel, W.; Saadaoui, W.; et al. Advanced Deep Learning and Machine Learning Techniques for MRI Brain Tumor Analysis: A Review. Sensors 2025, 25, 2746.
  6. Prakash, U.M.; Iniyan, S.; Dutta, A.K.; et al. Multi-Scale Feature Fusion of Deep Convolutional Neural Networks on Cancerous Tumor Detection and Classification Using Biomedical Images. Sci. Rep. 2025, 15, 1105.
  7. Ko, J.; Song, J.; Choi, N.; et al. Patient‐Derived Microphysiological Systems for Precision Medicine. Adv. Healthc. Mater. 2024, 13, 2303161.
  8. Hussain, D.; Al-Masni, M.A.; Aslam, M.; et al. Revolutionizing Tumor Detection and Classification in Multimodality Imaging Based on Deep Learning Approaches: Methods, Applications and Limitations. J. X-Ray Sci. Technol. 2024, 32, 857–911.
  9. Batool, A.; Byun, Y.C. A Lightweight Multi-Path Convolutional Neural Network Architecture Using Optimal Features Selection for Multiclass Classification of Brain Tumor Using Magnetic Resonance Images. Results Eng. 2025, 25, 104327.
  10. Qureshi, S.A.; Sadiq, T.; Usman, A.; et al. SAlexNet: Superimposed AlexNet Using Residual Attention Mechanism for Accurate and Efficient Automatic Primary Brain Tumor Detection and Classification. Results Eng. 2025, 25, 104025.
  11. Pande, Y.; Chaki, J. Brain Tumor Detection Across Diverse MR Images: An Automated Triple-Module Approach Integrating Reduced Fused Deep Features and Machine Learning. Results Eng. 2025, 25, 103832.
  12. Zafar, W.; Husnain, G.; Iqbal, A.; et al. Enhanced TumorNet: Leveraging YOLOv8s and U-Net for Superior Brain Tumor Detection and Segmentation Utilizing MRI Scans. Results Eng. 2024, 24, 102994.
  13. Gupta, A.; Yadav, S.K.; Kuamr, V.; et al. Enhanced Breast Tumor Localization With DRA Antenna Backscattering and GPR Algorithm in Microwave Imaging. Results Eng. 2024, 24, 103044.
  14. Aljohani, M.; Bahgat, W.M.; Balaha, H.M.; et al. An Automated Metaheuristic-Optimized Approach for Diagnosing and Classifying Brain Tumors Based on a Convolutional Neural Network. Results Eng. 2024, 23, 102459.
  15. Ioannidis, G.S.; Trivizakis, E.; Metzakis, I.; et al. Pathomics and Deep Learning Classification of a Heterogeneous Fluorescence Histology Image Dataset. Appl. Sci. 2021, 11(9), 3796.
  16. Lee, A.; Kim, M.S.; Han, S.S.; et al. Deep Learning Neural Networks to Differentiate Stafne’s Bone Cavity From Pathological Radiolucent Lesions of the Mandible in Heterogeneous Panoramic Radiography. PLoS One 2021, 16, e0254997.
  17. Liang, Y.; Lee, K.; Bovi, J.A.; et al. Deep Learning-Based Automatic Detection of Brain Metastases in Heterogeneous Multi-Institutional Magnetic Resonance Imaging Sets: An Exploratory Analysis of NRG-CC001. Int. J. Radiat. Oncol. Biol. Phys. 2022, 114, 529–536.
  18. He, S.; Jin, Y.; Nazaret, A.; et al. Starfysh Integrates Spatial Transcriptomic and Histologic Data to Reveal Heterogeneous Tumor–Immune Hubs. Nat. Biotechnol. 2025, 43, 223–235.
  19. Qu, H.; Zhou, M.; Yan, Z.; et al. Genetic Mutation and Biological Pathway Prediction Based on Whole Slide Images in Breast Carcinoma Using Deep Learning. NPJ Precis. Oncol. 2021, 5, 87.
  20. Abhishek, A.; Jha, R.K.; Sinha, R.; et al. Automated Classification of Acute Leukemia on aHeterogeneous Dataset Using Machine Learning and Deep Learning Techniques. Biomed. Signal Process. Control 2022, 72, 103341.
  21. Geng, J.; Zhang, X.; Prabhu, S.; et al. 3D Microscopy and Deep Learning Reveal the Heterogeneity of Crown-Like Structure Microenvironments in Intact Adipose Tissue. Sci. Adv. 2021, 7, eabe2480.
  22. Yang, J.; Ju, J.; Guo, L.; et al. Prediction of HER2-Positive Breast Cancer Recurrence and Metastasis Risk From Histopathological Images and Clinical Information via Multimodal Deep Learning. Comput. Struct. Biotechnol. J. 2022, 20, 333–342.
  23. Jiao, Y.; Li, J.; Qian, C.; et al. Deep Learning-Based Tumor Microenvironment Analysis in Colon Adenocarcinoma Histopathological Whole-Slide Images. Comput. Methods Programs Biomed. 2021, 204, 106047.
  24. Kotei, E.; Thirunavukarasu, R. Visual Attention Condenser Model for Multiple Disease Detection From Heterogeneous Medical Image Modalities. Multimed. Tools Appl. 2024, 83, 30563–30585.
  25. Zhao, J.; Li, X.; Li, L.; et al. Identification of Neutrophil Extracellular Trap-Driven Gastric Cancer Heterogeneity and C5AR1 as a Therapeutic Target: Identification of NET-Driven GC Heterogeneity and C5AR1 as a Therapeutic Target. Acta Biochim. Biophys. Sin. 2024, 56, 538.
  26. Liu, Y.; Mei, Y.; Chen, Y.; et al. Resolving Engineering Challenges: Deep Learning in Frequency Domain for 3D Inverse Identification of Heterogeneous Composite Properties. Compos. Part B Eng. 2024, 276, 111353.
  27. Guo, Y.; Shen, Z.; Zhao, W.; et al. Rational Identification of Novel Antibody‐Drug Conjugate With High Bystander Killing Effect Against Heterogeneous Tumors. Adv. Sci. 2024, 11, 2306309.
  28. Wang, S.; Wu, C.Y.; He, M.M.; et al. Machine Learning-Based Extrachromosomal DNA Identification in Large-Scale Cohorts Reveals Its Clinical Implications in Cancer. Nat. Commun. 2024, 15, 1515.
  29. Gowthamy, J.; Ramesh, S. A Novel Hybrid Model for Lung and Colon Cancer Detection Using Pre-Trained Deep Learning and KELM. Expert Syst. Appl. 2024, 252, 124114.
  30. PBC_dataset. Available online: https://www.kaggle.com/datasets/kylewang1999/pbc-dataset (accessed on 6 April 2024)