Enhancing Medical Image Analysis Through Deep Learning-Based Lesion Detection

Authors

  • Anant Nagesh Kaulage Assistant Professor, Department of Computer Engineering, Vishwakarma Institute of Technology, Pune, Maharashtra, India
  • Raju M. Sairise Principal, Yadavrao Tasgaonkar college of Engineering and Management, Karjat, Raigad, Pune, Maharashtra, India
  • Niket Pundlikrao Tajne Symbiosis School for Online and Digital Learning, Pune, Maharashtra, India
  • Pallawi Unmesh Bulakh Assistant Professor, Department of Computer Science, Modern College of Arts, Science and Commerce, Shivaji Nagar, Pune, Maharashtra, India
  • Sarika T. Deokate Assistant Professor, Department of Computer Engineering, Pimpri Chinchwad College of Engineering Nigdi, Pune, Maharashtra, India
  • Satpalsing D. Rajput Assistant Professor, Department of Computer Engineering, Pimpri Chinchwad College of Engineering Nigdi, Pune, Maharashtra, India

Keywords:

Lesion Detection, Medical Imaging, Deep Learning, Genetic Algorithm, Healthcare

Abstract

Medical image analysis plays a pivotal role in modern healthcare, aiding clinicians in the timely and accurate diagnosis of various ailments. Lesion detection, in particular, is a critical component of this process, where the need for improved efficiency and accuracy remains a pressing concern. This paper presents a novel approach that leverages the power of deep learning and genetic algorithms to address these challenges and enhance lesion detection in medical images.

Existing lesion detection methods often struggle with two major limitations: the demand for extensive labeled data and the ability to capture intricate lesion boundaries. This work aims to overcome these challenges by proposing a Unified Neural Network (UNet) architecture, a popular choice in medical image analysis, coupled with a Genetic Algorithm (GA) optimization technique. This synergistic combination facilitates significant improvements in both efficiency and accuracy.

Our proposed method begins by training a UNet model on a limited dataset of annotated medical images, reducing the need for extensive manual labeling. To address the issue of precise boundary delineation, the Genetic Algorithm is employed to fine-tune the model, optimizing its parameters for lesion detection. This dynamic approach empowers the model to adapt and learn from the data, enhancing its ability to identify lesions with higher precision. The advantages of our approach are manifold. Firstly, it substantially reduces the labeling burden on medical experts, making it more feasible to scale up lesion detection efforts across diverse medical domains. Secondly, the integration of the Genetic Algorithm ensures that the UNet model reaches optimal performance, resulting in more accurate and reliable lesion detection. Additionally, our method exhibits robustness across different imaging modalities, making it adaptable for a wide range of medical image analysis tasks.

Downloads

Download data is not yet available.

References

Z. Ning, S. Zhong, Q. Feng, W. Chen and Y. Zhang, "SMU-Net: Saliency-Guided Morphology-Aware U-Net for Breast Lesion Segmentation in Ultrasound Image," in IEEE Transactions on Medical Imaging, vol. 41, no. 2, pp. 476-490, Feb. 2022, doi: 10.1109/TMI.2021.3116087.

X. Chen et al., "Dual Adversarial Attention Mechanism for Unsupervised Domain Adaptive Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 41, no. 11, pp. 3445-3453, Nov. 2022, doi: 10.1109/TMI.2022.3186698.

S. Zhang et al., "MRI Information-Based Correction and Restoration of Photoacoustic Tomography," in IEEE Transactions on Medical Imaging, vol. 41, no. 9, pp. 2543-2555, Sept. 2022, doi: 10.1109/TMI.2022.3165839.

J. Lin et al., "CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer with Modality-Correlated Cross-Attention for Brain Tumor Segmentation," in IEEE Transactions on Medical Imaging, vol. 42, no. 8, pp. 2451-2461, Aug. 2023, doi: 10.1109/TMI.2023.3250474.

C. You, Y. Zhou, R. Zhao, L. Staib and J. S. Duncan, "SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 41, no. 9, pp. 2228-2237, Sept. 2022, doi: 10.1109/TMI.2022.3161829.

L. Xie, W. Cai and Y. Gao, "DMCGNet: A Novel Network for Medical Image Segmentation With Dense Self-Mimic and Channel Grouping Mechanism," in IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 10, pp. 5013-5024, Oct. 2022, doi: 10.1109/JBHI.2022.3192277.

C. Ouyang, C. Biffi, C. Chen, T. Kart, H. Qiu and D. Rueckert, "Self-Supervised Learning for Few-Shot Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 41, no. 7, pp. 1837-1848, July 2022, doi: 10.1109/TMI.2022.3150682.

X. Zhao et al., "Prior Attention Network for Multi-Lesion Segmentation in Medical Images," in IEEE Transactions on Medical Imaging, vol. 41, no. 12, pp. 3812-3823, Dec. 2022, doi: 10.1109/TMI.2022.3197180.

D. Gut, Z. Tabor, M. Szymkowski, M. Rozynek, I. Kucybała and W. Wojciechowski, "Benchmarking of Deep Architectures for Segmentation of Medical Images," in IEEE Transactions on Medical Imaging, vol. 41, no. 11, pp. 3231-3241, Nov. 2022, doi: 10.1109/TMI.2022.3180435.

J. Du, K. Guan, Y. Zhou, Y. Li and T. Wang, "Parameter-Free Similarity-Aware Attention Module for Medical Image Classification and Segmentation," in IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 7, no. 3, pp. 845-857, June 2023, doi: 10.1109/TETCI.2022.3199733.

W. Cai, L. Xie, W. Yang, Y. Li, Y. Gao and T. Wang, "DFTNet: Dual-Path Feature Transfer Network for Weakly Supervised Medical Image Segmentation," in IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 20, no. 4, pp. 2530-2540, 1 July-Aug. 2023, doi: 10.1109/TCBB.2022.3198284.

J. Du, X. Zhang, P. Liu and T. Wang, "Coarse-Refined Consistency Learning Using Pixel-Level Features for Semi-Supervised Medical Image Segmentation," in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 8, pp. 3970-3981, Aug. 2023, doi: 10.1109/JBHI.2023.3278741.

J. Xian et al., "Unsupervised Cross-Modality Adaptation via Dual Structural-Oriented Guidance for 3D Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 42, no. 6, pp. 1774-1785, June 2023, doi: 10.1109/TMI.2023.3238114.

B. Huang et al., "3D Lightweight Network for Simultaneous Registration and Segmentation of Organs-at-Risk in CT Images of Head and Neck Cancer," in IEEE Transactions on Medical Imaging, vol. 41, no. 4, pp. 951-964, April 2022, doi: 10.1109/TMI.2021.3128408.

W. Zou, X. Qi, W. Zhou, M. Sun, Z. Sun and C. Shan, "Graph Flow: Cross-Layer Graph Flow Distillation for Dual Efficient Medical Image Segmentation," in IEEE Transactions on Medical Imaging, vol. 42, no. 4, pp. 1159-1171, April 2023, doi: 10.1109/TMI.2022.3224459.

Thatikonda, R., Vaddadi, S.A., Arnepalli, P.R.R. et al. Securing biomedical databases based on fuzzy method through blockchain technology. Soft Comput (2023). https://doi.org/10.1007/s00500-023-08355-x

Khetani, V., Gandhi, Y, Bhattacharya, S, Ajani, S. N, & Limkar, S. (2023). Cross-Domain Analysis of ML and DL: Evaluating their Impact in Diverse Domains. International Journal of Intelligent Systems and Applications in Engineering, 11(7s), 253–262

Ashtagi, R., Dhumale, P., Mane, D., Naveen, H. M, Bidwe, R. V, & Zope, B (2023). IoT-Based Hybrid Ensemble Machine Learning Model for Efficient Diabetes Mellitus Prediction. International Journal of Intelligent Systems and Applications in Engineering, 11(10s), 714–726.

Patil, R., Mote, A., Mane, D. (2023). Detection of Malignant Melanoma Using Hybrid Algorithm. In: Singh, P., Singh, D., Tiwari, V., Misra, S. (eds) Machine Learning and Computational Intelligence Techniques for Data Engineering. MISP 2022. Lecture Notes in Electrical Engineering, vol 998. Springer, Singapore. https://doi.org/10.1007/978-981-99-0047-3_65

Yogesh J. Gaikwad, "A Review on Self Learning based Methods for Real World Single Image Super Resolution", 2021, In Rahul Srivastava & Aditya Kumar Singh Pundir (eds.), New Frontiers in Communication and Intelligent Systems, 1–10. Computing & Intelligent Systems, SCRS, India. https://doi.org/10.52458/978-81-95502-00-4-1

Saxena, K. ., & Gupta, Y. K. . (2023). Analysis of Image Processing Strategies Dedicated to Underwater Scenarios. International Journal on Recent and Innovation Trends in Computing and Communication, 11(3s), 253–258. https://doi.org/10.17762/ijritcc.v11i3s.6232

Andrew Hernandez, Stephen Wright, Yosef Ben-David, Rodrigo Costa,. Enhancing Decision Support Systems through Machine Learning Algorithms. Kuwait Journal of Machine Learning, 2(3). Retrieved from http://kuwaitjournals.com/index.php/kjml/article/view/194

Dhabliya, D. Security analysis of password schemes using virtual environment (2019) International Journal of Advanced Science and Technology, 28 (20), pp. 1334-1339.

Downloads

Published

27.10.2023

How to Cite

Kaulage, A. N. ., Sairise, R. M. ., Tajne, N. P. ., Bulakh, P. U. ., Deokate, S. T. ., & Rajput, S. D. . (2023). Enhancing Medical Image Analysis Through Deep Learning-Based Lesion Detection. International Journal of Intelligent Systems and Applications in Engineering, 12(2s), 27–36. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/3556

Issue

Vol. 12 No. 2s (2024)

Section

Research Article

License

Creative Commons License

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

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.

Most read articles by the same author(s)