ABSTRACT
Accurate detection and discovery of early lung cancer is the most effective measure to reduce lung cancer mortality with high clinical value. However, existing common object detectors show unsatisfactory detection accuracy for pulmonary nodule detection, due to the textureless appearance and small size of nodules. To address the textureless appearance problem, we propose a dedicated Nodule-Learning C3 module, which helps to extract more informative structures from limited textures of nodules. Considering that nodules’ sizes are small, we further design a tiny object detection layer that performs object detection on larger feature maps, where more nodule features are preserved. Moreover, the balance between speed and accuracy is also critical for the pulmonary nodule diagnostic system. Therefore, we choose the famous one-stage detection framework YOLO [13] as our baseline and implement our proposed module and layer based on it. Extensive experimental results on the widely used benchmark LUNA16 demonstrate the superior performance of our method, in terms of both accuracy and speed. Specifically, our model improves the mAP accuracy by over and is faster than the YOLO baseline.
- Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao. 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020).Google Scholar
- David S Ettinger. 2012. Ten years of progress in non–small cell lung cancer. Journal of the National Comprehensive Cancer Network 10, 3 (2012), 292–295.Google ScholarCross Ref
- Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2019. Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 558–567.Google ScholarCross Ref
- Tao Hu, Chunhua Zhang, Qiongling Tang, Yanan Su, Bo Li, Long Chen, Zheng Zhang, Tianchi Cai, and Yuechun Zhu. 2013. Variant G6PD levels promote tumor cell proliferation or apoptosis via the STAT3/5 pathway in the human melanoma xenograft mouse model. BMC cancer 13 (2013), 1–11.Google ScholarCross Ref
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision. 2980–2988.Google ScholarCross Ref
- Zhe Lin. 2022. Interpretability study of pretrained models via transfer learning on ImageNet for lung cancer prediction. In 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), Vol. 12451. SPIE, 1158–1163.Google ScholarCross Ref
- Jie Mei, Ming-Ming Cheng, Gang Xu, Lan-Ruo Wan, and Huan Zhang. 2021. SANet: A slice-aware network for pulmonary nodule detection. IEEE transactions on pattern analysis and machine intelligence 44, 8 (2021), 4374–4387.Google Scholar
- Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019).Google Scholar
- ZHOU Qinghua, FAN Yaguang, WANG Ying, QIAO Youlin, WANG Guiqi, Yunchao Huang, WANG Xingyun, WU Ning, Guozhen Zhang, Xiangpeng Zheng, 2016. China national guideline of classification, diagnosis and treatment for lung nodules (2016 version). Zhongguo Fei Ai Za Zhi 19, 12 (2016).Google Scholar
- Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018).Google Scholar
- Arnaud Arindra Adiyoso Setio, Alberto Traverso, Thomas De Bel, Moira SN Berens, Cas Van Den Bogaard, Piergiorgio Cerello, Hao Chen, Qi Dou, Maria Evelina Fantacci, Bram Geurts, 2017. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. Medical image analysis 42 (2017), 1–13.Google Scholar
- Wei Shen, Mu Zhou, Feng Yang, Caiyun Yang, and Jie Tian. 2015. Multi-scale convolutional neural networks for lung nodule classification. In Information Processing in Medical Imaging: 24th International Conference, IPMI 2015, Sabhal Mor Ostaig, Isle of Skye, UK, June 28-July 3, 2015, Proceedings 24. Springer, 588–599.Google ScholarCross Ref
- Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696 (2022).Google Scholar
- P Zhang, X Xu, H Wang, 2018. Computer-aided lung cancer diagnosis approaches based on deep learning. J Comput Aided Design Comput Graph 30 (2018), 90.Google ScholarCross Ref
- Qikui Zhu, Yanqing Wang, Xiangpeng Chu, Xiongwen Yang, and Wenzhao Zhong. 2022. Multi-View Coupled Self-Attention Network for Pulmonary Nodules Classification. In Proceedings of the Asian Conference on Computer Vision. 995–1009.Google Scholar
- Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, and Jieping Ye. 2023. Object detection in 20 years: A survey. Proc. IEEE (2023).Google Scholar
Index Terms
- Tiny Object Detector for Pulmonary Nodules based on YOLO
Recommendations
Detection of CT Pulmonary Nodule Based on Improved Yolo Using Attention Mechanism
CSAI '22: Proceedings of the 2022 6th International Conference on Computer Science and Artificial IntelligenceLung cancer is a leading malignant tumor in morbidity and mortality. Early diagnosis of lung cancer can effectively improve the prognosis. Pulmonary nodules are an essential feature of early symptoms of lung cancer. Therefore, the detection of pulmonary ...
An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images
Lung cancer is still the most concerned disease around the world. Lung nodule generates in the pulmonary parenchyma which indicates the latent risk of lung cancer. Computer-aided pulmonary nodules detection system is necessary, which can reduce ...
Early detection and classification of abnormality in prior mammograms using image-to-image translation and YOLO techniques
Highlights- Early breast cancer diagnosis requires accurate abnormality detection and classification
Abstract Background and ObjectiveComputer-aided-detection (CAD) systems have been developed to assist radiologists on finding suspicious lesions in mammogram. Deep Learning technology have recently succeeded to increase the chance ...
Comments