Abstract
Deep learning has become ubiquitous in the field of computer vision for tasks such as image classification and segmentation. A Computer-Aided Diagnostic (CAD) system for lung cancer detection and diagnosis works by identifying lung nodules and characterizing the same. Transfer learning allows for pre-trained weights to be ported from one model to another. Replacement of pre-trained encoders in encoder-decoder networks opens up the number of possibilities of such networks and motivates us to check the possibility of each combination for a segmentation task of interest. This paper reports the experiments carried out using such combinations and presents the various observations as a result of the experiments for the nodule segmentation task on the LIDC-IDRI dataset. This work also examines the effect of network parameters on some of the deep learning semantic segmentation architectures in the context of the lung cancer dataset, LIDC-IDRI. The efficient network architecture, based on observations, is determined to be UNet with the backbone architecture, Efficientnet-b3 trained on the ImageNet dataset. This specific network presents an IoU score of 0.59 on the training dataset and 0.45 on the validation dataset. The architectures were compared and analyzed in terms of the time and space taken as well.
Similar content being viewed by others
Data Availability
The datasets generated during and/or analysed during the current study are available in the LIDC-IDRI repository, https://wiki.cancerimagingarchive.net/display/Public/LIDC-IDRI.
Code availability
The code for this work is available in https://github.com/sujijenkin/LIDC-IDRI-NoduleSeg_SEGMODELS.
References
Abedalla A, Abdullah M, Al-Ayyoub M, Benkhelifa E (2021) Chest x-ray pneumothorax segmentation using U-net with efficientnet and resnet architectures. PeerJ Computer Science 7:e607
Ali Z, Irtaza A, Maqsood M (2022) An efficient U-net framework for lung nodule detection using densely connected dilated convolutions. J Supercomput 78(2):1602–1623
Banu SF, Sarker MMK, Abdel-Nasser M, Rashwan HA, Puig D (2021) Weu-net: a weight excitation U-net for lung nodule segmentation. In: CCIA, pp 349–356
Banu SF, Sarker M, Kamal M, Abdel-Nasser M, Puig D, Raswan HA (2021) Aweu-net: an attention-aware weight excitation U-net for lung nodule segmentation. Appl Sci 11(21):10132
Bianconi F, Fravolini ML, Pizzoli S, Palumbo I, Minestrini M, Rondini M, Nuvoli S, Spanu A, Palumbo B (2021) Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT. Quant Imaging Med Surg 11(7):3286
Bizopoulos P, Vretos N, Daras P (2020) Comprehensive comparison of deep learning models for lung and COVID-19 lesion segmentation in CT scans. Preprint at http://arxiv.org/abs/2009.06412
Chaurasia A, Culurciello E (2017) Linknet: exploiting encoder representations for efficient semantic segmentation. In: 2017 IEEE Visual Communications and Image Processing (VCIP). IEEE, pp 1–4
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1251–1258
Dhalla S, Maqbool J, Mann TS, Gupta A, Mittal A, Aggarwal P, Saluja K, Kumar M, Saini SS (2023) Semantic segmentation of palpebral conjunctiva using predefined deep neural architectures for anemia detection. Procedia Comput Sci 218:328–337
Fernandez K, Korinek M, Camp J, Lieske J, Holmes D (2019) Automatic detection of calcium phosphate deposit plugs at the terminal ends of kidney tubules. Healthc Technol Lett 6(6):271–274
Fernandez-Moral E, Martins R, Wolf D, Rives P (2018) A new metric for evaluating semantic segmentation: leveraging global and contour accuracy. In: 2018 IEEE Intelligent Vehicles Symposium (IV). IEEE, pp 1051–1056
Hammad M, Alkinani MH, Gupta BB, Abd El-Latif AA (2021) Myocardial infarction detection based on deep neural network on imbalanced data. Multimed Syst pp 1–13
Handani SW, Wijaya F, Sung F-Y (2021) COVID-19 CT image segmentation. In: 2021 IEEE 5th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE). IEEE, pp 109–114
Haque IRI, Neubert J (2020) Deep learning approaches to biomedical image segmentation. Inform Med Unlocked 18:100297
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 770–778
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 4700–4708
Jiao R, Wang S, Zhang T, Lu H, He H, Gupta BB (2021) Adaptive feature selection and construction for day-ahead load forecasting use deep learning method. IEEE Trans Netw Serv Manag 18(4):4019–4029
Lalitha S (2021) An automated lung cancer detection system based on machine learning algorithm. J Intell Fuzzy Syst 40(4):6355–6364
Lin T-Y, Dollár P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 2117–2125
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 3431–3440
Loverdos K, Fotiadis A, Kontogianni C, Iliopoulou M, Gaga M (2019) Lung nodules: a comprehensive review on current approach and management. Ann Thorac Med 14(4):226
Martin CH, Mahoney MW (2019) Traditional and heavy-tailed self regularization in neural network models. Preprint at http://arxiv.org/abs/1901.08276
Micikevičius M (2023) Corrosion detection on steel panels using semantic segmentation models. PhD thesis, Vilniaus universitetas
Nagarkar H (2020) Evaluating machine learning models for semantic segmentation over cloud images for classification
Parmar V, Bhatia N, Negi S, Suri M (2020) Exploration of optimized semantic segmentation architectures for edge-deployment on drones. Preprint at http://arxiv.org/abs/2007.02839
Rajalakshmi TS, Senthilnathan R (2023) Dataset and performance metrics towards semantic segmentation. Int J Eng Manag Res 13(1):40–49
Rajesh MN, Chandrasekar BS (2022) Prostate gland segmentation using semantic segmentation models u-net and linknet. Int J Eng Trends Technol 70(20):252–271
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, pp 234–241
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 4510–4520
Setio AAA, Ciompi F, Litjens G, Gerke P, Jacobs C, Van Riel SJ, Wille MMW, Naqibullah M, Sánchez CI, Van Ginneken B (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35(5):1160–1169
Shariaty F, Mousavi M (2019) Application of cad systems for the automatic detection of lung nodules. Informatics in Medicine Unlocked 15:100173
Shuo Wang M, Zhou ZL, Liu Z, Dongsheng G, Zang Y, Dong D, Gevaert O, Tian J (2017) Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation. Med Image Anal 40:172–183
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Preprint at http://arxiv.org/abs/1409.1556
Singadkar G, Mahajan A, Thakur M, Talbar S (2020) Deep deconvolutional residual network based automatic lung nodule segmentation. J Digit Imaging 1–7
Singh A, Lall B, Panigrahi BK, Agrawal A, Agrawal A, Thangakunam B, Christopher DJ (2021) Deep LF-net: semantic lung segmentation from indian chest radiographs including severely unhealthy images. Biomedical Signal Processing and Control 68:102666
Suji RJ, Godfrey WW, Dhar J (2021) Comparing different deep learning backbones for segmentation of lung nodules. In: 2021 5th conference on information and communication technology (CICT). IEEE, pp 1–5
Sukegawa S, Yoshii K, Hara T, Matsuyama T, Yamashita K, Nakano K, Takabatake K, Kawai H, Nagatsuka H, Furuki Y (2021) Multi-task deep learning model for classification of dental implant brand and treatment stage using dental panoramic radiograph images. Biomolecules 11(6):815
Szegedy C, Ioffe S, Vanhoucke V, Alemi A (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 31
Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning. PMLR, pp 6105–6114
Wang Z, Song R, Duan P, Li X (2021) Efnet: enhancement-fusion network for semantic segmentation. Pattern Recogn 08023
Wang S, Zhou M, Gevaert O, Tang Z, Dong D, Liu Z, Jie T (2017) A multi-view deep convolutional neural networks for lung nodule segmentation. In: 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, pp 1752–1755
Wenqing Sun, Xia Huang, Tzu-Liang Bill Tseng, and Wei Qian (2017) Automatic lung nodule graph cuts segmentation with deep learning false positive reduction. In: Medical Imaging 2017: Computer-Aided Diagnosis, vol 10134. International Society for Optics and Photonics, pp 101343M
Zhang Y, Mehta S, Caspi A (2021) Rethinking semantic segmentation evaluation for explainability and model selection. Preprint at http://arxiv.org/abs/2101.08418
Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 2881–2890
Funding
The authors would like to acknowledge the Kiran Division, Department of Science and Technology, Govt. of India, for funding this research work through the SR/WOSA/ET-153/2017 Research Grant. The authors also thank the anonymous reviewers for their encouraging reviews and recommendations.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Conflict of interest
All the authors declare that he/she has no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Graphs
Appendix: Graphs
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Suji, R.J., Godfrey, W.W. & Dhar, J. Exploring pretrained encoders for lung nodule segmentation task using LIDC-IDRI dataset. Multimed Tools Appl 83, 9685–9708 (2024). https://doi.org/10.1007/s11042-023-15871-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15871-3