Skin Lesion Detection Using Convolutional Neural Network

Haque, Syed Tousiful; Akash, Ibnun Nur; Nasif, Abu Sayeed Md.; Mahmud, Mirza Abid

IUT Repository Home
→
Electrical and Electronics Engineering (EEE)
→
Thesis
→
Undergraduate
→
2019
→
View Item

dc.contributor.author	Haque, Syed Tousiful
dc.contributor.author	Akash, Ibnun Nur
dc.contributor.author	Nasif, Abu Sayeed Md.
dc.contributor.author	Mahmud, Mirza Abid
dc.date.accessioned	2020-12-26T05:08:01Z
dc.date.available	2020-12-26T05:08:01Z
dc.date.issued	2019-11-15
dc.identifier.citation	[1] U. o. M. Gamage P.T .Faculty of Information technology, Identification of brain tumor using image segmentation techniques. [2] S. B. T. u. A.-B. Features, Mark Schmidt, Ilya Levner, Russell Greiner Department of Computing Science University of Alberta Edmonton, Albert Murtha, Aalo Bistritz Department of Oncology Cross Cancer Institute Edmonton AB, Canada. [3] Y. B. a. A. C. Ian Goodfellow, Deep Learning. [4] C. D. ,. M. ù. Ali IúÕna, Review of MRI-based Brain Tumor Image Segmentation Using Deep Learning Methods. [5] C. X. ,. J. L. P. D. o. E. a. C. E. T. J. H. U. B. M. 2. y. .. o. P. a. C. Dzung L. Phamy, "A SURVEY OF CURRENT METHODS IN MEDICAL IMAGE SEGMENTATION". [6] G. A. Woods, Digital Image Processing. [7] Y. W. J. C. Q. W. X. &. C. P. Xu, "Medical breast ultrasound image segmentation by machine learning .," ELSEVER.Ultrasound, (2019). [8] O. P. ,. B. T. Ronneberger, "U-Net: Convolutional Networks for Biomedical Image Segmentation," MICCAI, 2015. [9] Z. R. S. M. T. L. J. Zhou, "UNet++: A Nested U-Net architecture for Medical Image Segmentation .," 2018. [10] S. K. K. &. S. Al Arif, "SPNet: Shape Prediction Using a Fully Convolutional Neural Network," 2018. [11] F. N. N. &. A. S.-A. Milletari, "V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image segmentation," in Fourth International Conference on 3D Vision (3DV), 2016. [12] M. K. N. N.-E. E. S. S. S. W. K. &. N. K. Jafari, " Skin lesion segmentation in clinical images using deep learning," IEEE, 2016. [13] P. Kim, Matlab Deep Learning with Machine Learning , Neural Network & Artificial Intelligence By. 62 [14] G. E. David E. Rumelhart, "Learning representation by back popagation errors," Nature, 1986. [15] https://towardsdatascience.com/activation-functions-neural-networks-1cbd9f8d91d6, . [16] https://medium.com/datadriveninvestor/overview-of-different-optimizers-for-neural-networks-e0ed119440c3. [17] http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture11.pdf. [Online]. [18] [Online]. Available: https://www.kaggle.com/suryanshdabas/skinlesionsegmentation. [19] Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance, 2017. [20] https://towardsdatascience.com/activation-functions-and-its-types-which-is-better-a9a5310cc8f. [21] J. B. P.Kingma, Adam: A method for Stochastic Optimization. [22] https://towardsdatascience.com/types-of-optimization-algorithms-used-in-neural-networks-and-ways-to-optimize-gradient-95ae5d39529f. [23] D. E. Rumelhart, Learning representations by back-propagating errors. [24] P. F. a. T. B. Olaf Ronneberger, "U-Net: Convolutional Networks for Biomedical Image Segmentation.". [25] https://www.mathworks.com/help/images/boundary-tracing-in-images.html. [26] J. L. a. T. D. Evan Shelhamer, "Fully Convolutional Networksfor Semantic Segmentation," IEEE. [27] I. S. a. G. E. H. A. Krizhevsky, "Imagenet classification with deep convolutional neural networks," NIPS, 2012. [28] " https://computersciencewiki.org/index.php/Max-pooling/Pooling," [Online]. [29] C. C. J. &. M. J. Darken, "Learning rate schedules for faster stochastic gradient search. Neural Networks for Signal Processing," Proceedings of the 1992 IEEE Workshop(September), 1992. [30] D. G. L. G. A. S. J. Ciresan, "Deep neural networks segment neuronal membranes in electron microscopy images," NIPS, 2012. 63 [31] N. Qian, "On the momentum term in gradient descent learning algorithms. Neural Networks," The Official Journal of the International Neural Network Society, Vols. 12,, no. 1, 1999.	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/739
dc.description	Supervised by Prof. Dr. Md. Ruhul Amin Professor, Department of Electrical and Electronic Engineering, Islamic University of Technology.	en_US
dc.description.abstract	Skin tumor segmentation is the preliminary step for medical diagnosis and consequent treatment of skin cancer. This writeup discusses our thesis work that utilizes deep CNN for skin tumor segmentation. The network uses down sampling and up sampling layers. The dense function or the fully connected layer has been used twice after the final down sampling in order to save computational time and system memory. To facilitate concatenation of matrices from the up sampling region and down sampling region, zero padding is provided during convolution and transpose convolution. Our network has depth comparatively lower than other contemporary deep neural networks used for image segmentation. In spite of that our model has performed well with satisfactory accuracy of 55% after 5 epochs and 62.23% after 10 epochs. It is worth mentioning that our model was trained with 1000 images, tested on 1000 and validated on 600 medical images containing(or not) skin tumors	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Electrical and Electronic Engineering, Islamic University of Technology,Board Bazar, Gazipur, Bangladesh	en_US
dc.title	Skin Lesion Detection Using Convolutional Neural Network	en_US
dc.type	Thesis	en_US