Lung Semantic Segmentation using Convolutional Neural Networks
N. Sarada1, K. Thirupathi Rao2
1N. Sarada, Research Scholar, Department of Compute Science and Engineering, K L E F, Guntur (Andhra Pradesh), India.
2Dr. K.Thirupathi Rao, Professor & BOS Chairman, Associate Dean Academics, Department of Compute Science and Engineering, K L E F, Guntur (Andhra Pradesh), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 244-249 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3467048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In the fields of computer vision, semantic segmentation is widely used to build a broad range of applications, specifically, medical image processing is where it majorly impacts. It helps in the prediction of abnormalities and the description of accurate analysis on CT-Scans and X-Rays. With the rise of deep learning, neural networks are performing and achieving accurate results with respect to the metrics in the fields of image classification and segmentation. In this work, we use the Convolutional Neural Network on Chest-X-Rays for segmenting the lungs. The architecture being used for image segmentation is U-Net which applies on the train and test data of NIH dataset. The outputs of the model include preprocessed images, accuracies on the test and train dataset, loss and prediction with intersection over union values (how dynamically the images are segmented) of Chest X Rays over two thousand examples.
Keyword: Convolutional Neural Networks, Deep Learning, Image Segmentation, Lung Abnormalities, Medical Image Processing, Tensorflow.
Scope of the Article: Neural Information Processing