Authors:
Bikash Chandra Bag,Hirak Kumar Maity,Chaitali Koley,DOI NO:
https://doi.org/10.26782/jmcms.2023.01.00002Keywords:
Deep Neural network,Semantic segmentation,UNet MobileNetV2,Abstract
In this paper, the framework of polyp image segmentation is developed using a Deep neural network (DNN). Here Unet Mobile NetV2 is considered to evaluate the performance of the image from the CVC-612 dataset for the segmentation method. The proposed model outperformed earlier results. To compare our results two parameters, normally Dice co-efficient and Intersection over Union (IoU) are considered. The proposed model may be used for accurate computer-aided polyp detection and segmentation during colonoscopy examinations to find out abnormal tissue and thereby decrease the chances of polyps growing into cancer. MobileNetV2 significantly outperforms U-Net and MobileNetV2, two key state-of-the-art deep learning architectures, by achieving high evaluation scores with a dice coefficient of 89.71%, and an IoU of 81.64%.Refference:
I. A. Arezzo, A. Koulaouzidis, A. Menciassi, D. Stoyanov, E. B. Mazomenos, F. Bianchi, G. Ciuti, P. Brandao, P. Dario, R. Caliò, Fully convolutional neural networks for polyp segmentation in colonoscopy. In: International Society for Optics and Photonics. Medical Imaging 2017: Computer-Aided Diagnosis, v. 10134, p. 101340F, 2017.
II. A. Howard, M. Zhu, A. Zhmoginov, L-C. Chen, M. Sandler, MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, p. 4510-4520, 2018.
III. A. Howard, M. Zhu, A. Zhmoginov, L-C. Chen, M. Sandler, MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, p. 4510-4520, 2018.
IV. A. V. Mamonov, I. N. Figueiredo, P. N. Figueiredo Y-H. R. Tsai, Automated polyp detection in colon capsule endoscopy. IEEE transactions on medical imaging, v. 33, n. 7, p. 1488–1502, 2014.
V. B. Paul, S. A. Fattah, T. Mahmud, Polypsegnet: A modified encoderdecoder architecture for automated polyp segmentation from colonoscopy images. Computers in Biology and Medicine, p. 104119, 2020.
VI. D-P. Fan, G. Chen, G-P. Ji, H. Fu, J. Shen, L. Pranet Shao, T. Zhou, : Parallel reverse attention network for polyp segmentation. In: SPRINGER.International Conference on Medical Image Computing and ComputerAssisted Intervention, p. 263–273, 2020.
VII. D. Jha, D. Johansen, H. D. CVC-612, Johansen, M. A. Riegler, P. Halvorsen, P. H. Smedsrud, T. Lange : A Segmented Polyp Dataset. In Proc. of International Conference on Multimedia Modeling (MMM), p. 451-462, 2019.
VIII. D. Jha, H. D. Johansen, M. A. Riegler, P. Halvorsen, P. H. Smedsrud, T. Lange, ResUNet++: An Advanced Architecture for Medical Image Segmentation. 2019 IEEE International Symposium on Multimedia (ISM),2019.
IX. E. Dekker, J. C. V. Rijn, J. B. Reitsma, J. Stoker, P. M. Bossuyt, S. J. V. Deventer, Polyp miss rate determined by tandem colonoscopy: a systematic review. The American journal of gastroenterology, v. 101, p. 343, 2006.
X. E. Nasr-Esfahani, K. Najarian, M. Akbari, M. Mohrekesh, N. Karimi, S. M. R. Soroushmehr, S. Samavi, Polyp segmentation in colonoscopy images using fully convolutional network. In: IEEE. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), p. 69–72, 2018.
XI. F. Chollet, Keras. https://github.com/fchollet/keras, 2015.
XII. J. Deng, K. Li, L. Fei-Fei, L-J. Li, R. Socher, W. Dong, Imagenet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, p. 248–255, 2009.
XIII. J. Liang, N. Tajbakhsh, S. R. Gurudu, Automated polyp detection in colonoscopy videos using shape and context information. IEEE transactions on medical imaging, v. 35, n. 2, p. 630–644, 2015.
XIV. O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks forbiomedical image segmentation. In: SPRINGER. International Conference on Medical image computing and computer-assisted intervention, p. 234–241, 2015.
XV. N. K. Tomar, Automatic Polyp Segmentation using Fully Convolutional Neural Network, 2021.