Liver Lesion Detect SSD: Liver Lesion Detection with Single Shot Detector Utilizing ResNet-50 and ResNet-34 Backbones
Keywords:
LiverLesionDetect SSD, Single Shot Detection, Liver Lesion Detection, CT Images, mean Average Precision, ResNet backbone ModelAbstract
Liver Lesion detection is a critical task in medical imaging, essential for early diagnosis and treatment planning, requiring high accuracy and efficiency to ensure effective patient care. This paper presents a robust approach to liver lesion detection using a Single Shot Detector (SSD) framework with ResNet-50 and ResNet-34 as a backbone networks. The SSD model, known for its object detection capabilities, is enhanced by the deep feature extraction power of ResNet architectures, enabling precise and fast identification of liver lesions. We comprehensively evaluate the performance of the proposed method on the DeepLesion dataset from the National Institutes of Health, demonstrating significant improvements in detection accuracy compared to conventional approaches. The ResNet-34 backbone achieves an impressive Mean Average Precision (mAP) of 91%, with ResNet-50 achieving 85%, demonstrating their effectiveness in accurately localizing liver lesions. The ResNet-50 and ResNet-34 backbones provide a balanced trade-off between computational complexity and detection accuracy, making the model suitable for practical medical applications. This research showcases the potential of SSD with ResNet architectures for accurate and efficient liver lesion detection, offering promising advancements for clinical applications.
Downloads
References
Zhang, Z., Chen, H., and Zheng, Y., Deep Learning-based Detection and Segmentation of Lesions in CT Images Using Single Shot Multibox Detector, Medical Image Analysis, 2019
Wang, L., Zhang, Y., Single Shot Multibox Detector for Automated Detection of Colorectal Polyps in CT Colonography, IEEE Transactions on Medical Imaging, 2019.
Chen, J., Wu, Y., Automated Detection of Pancreatic Tumors in CT Images Using SSD, Computers in Biology and Medicine, 2020.
Dou, Q., Chen, H., Yu, L., Detection of Small Lung Nodules Using a Hybrid Approach Based on SSD and 3D CNNs, International Journal of Computer Assisted Radiology and Surgery, 2020.
Li, J., Wang, X., Zhang, S., A Transfer Learning Approach for Lesion Detection in CT Images Using Single Shot Multibox Detector, IEEE Access, 2020.
Zhao, X., Zheng, H., Detection of Liver Lesions in CT Images Using Single Shot Multibox Detector, Journal of Digital Imaging, 2021.
Song, Y., Wei, C., SSDL-CT: Single Shot MultiBox Detector for Liver Tumor Detection in CT Images, Pattern Recognition Letters, 2021.
Wu, X., Li, L., Wang, J., Comparative Study of YOLO and SSD for Detecting Lung Nodules in CT Images, IEEE Access, 2021.
Rushikesh Chopade, Aditya Stanam, Shrikant Pawar “Single shot detector application for image disease localization”, biorxiv 2021.
Ranjbarzadeh, R.; Bagherian Kasgari, A.; Jafarzadeh Ghoushchi, S.; Anari, S.; Naseri, M.; Bendechache, M. Brain Tumor Segmentation Based on Deep Learning and an Attention Mechanism Using MRI Multi-Modalities Brain Images. Sci. Rep. 2021.
Zhu, X.; Lyu, S.; Wang, X.; Zhao, Q. TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios. arXiv 2021.
Zhao, X., Evaluation of YOLO and SSD for Detection of Pancreatic Tumors in CT Images, Computers in Biology and Medicine, 2022.
Shokofeh, A.; Nazanin, T.S.; Negin, M.; Shadi, D.; Amirali, R. Review of Deep Learning Approaches for Thyroid Cancer Diagnosis. Math. Probl. Eng. 2022.
Mansour Alhlalat, Ahmad Sharieh, Mohammed Alzoubi “Lung Disease Detection and Classification Using Single Shot Multi-Box Detector Network: A Comprehensive Study”, JMCS Journal,2023.
Jian Ni,Rui Wang and Jing Tang,” ADSSD: Improved Single-Shot Detector with Attention Mechanism and Dilated Convolution”, March 2023.
Downloads
Published
How to Cite
Issue
Section
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.
