English español
Search
 

Repositorio de la Universidad de Oviedo. > Producción Bibliográfica de UniOvi: RECOPILA > Capítulos de libros >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10651/53601

Title: Fast and Accurate Lung Tumor Spotting and Segmentation for Boundary Delineation on CT Slices In A Coarse-To-Fine Framework
Author(s): Pang, S.
Du, A.
He, X.
Díez Peláez, Jorge
Orgun, M. A.
Keywords: Boundary delineation
Lung tumor segmentation
Fully convolutional neural networks
Issue date: 2019
Publisher: Springer
Publisher version: https://doi.org/10.1007/978-3-030-36808-1_64
Format extent: p. 589-597
Abstract: Label noise and class imbalance are two of the critical challenges when training image-based deep neural networks, especially in the biomedical image processing domain. Our work focuses on how to address the two challenges effectively and accurately in the task of lesion segmentation from biomedical/medical images. To address the pixel-level label noise problem, we propose an advanced transfer training and learning approach with a detailed DICOM pre-processing method. To address the tumor/non-tumor class imbalance problem, we exploit a self-adaptive fully convolutional neural network with an automated weight distribution mechanism to spot the Radiomics lung tumor regions accurately. Furthermore, an improved conditional random field method is employed to obtain sophisticated lung tumor contour delineation and segmentation. Finally, our approach has been evaluated using several well-known evaluation metrics on the Lung Tumor segmentation dataset used in the 2018 IEEE VIP-CUP Challenge. Experimental results show that our weakly supervised learning algorithm outperforms other deep models and state-of-the-art approaches
URI: http://hdl.handle.net/10651/53601
ISBN: 978-3-030-36807-4
Appears in Collections:Capítulos de libros
Informática

Files in This Item:

File Description SizeFormat
Pang2019.pdf2,61 MBAdobe PDFView/Open


Exportar a Mendeley


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Base de Datos de Autoridades Biblioteca Universitaria Consultas / Sugerencias