Fully Convolutional DenseNet with Multiscale Context for Automated Breast Tumor Segmentation

Autor: Hongna Tan, Kai Qiao, Dapeng Shi, Jingbo Xu, Bin Yan, Jian Chen, Lei Zeng, Jinjin Hai
Rok vydání: 2019
Předmět:
lcsh:Medical technology
Article Subject
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Biomedical Engineering
Breast Neoplasms
Health Informatics
Context (language use)
02 engineering and technology
Overfitting
030218 nuclear medicine & medical imaging
Convolution
03 medical and health sciences
0302 clinical medicine
Image Interpretation
Computer-Assisted
0202 electrical engineering
electronic engineering
information engineering
Humans
Preprocessor
Segmentation
Breast
lcsh:R5-920
Network architecture
Pixel
Artificial neural network
business.industry
Pattern recognition
ComputingMethodologies_PATTERNRECOGNITION
lcsh:R855-855.5
Female
020201 artificial intelligence & image processing
Surgery
Neural Networks
Computer
Artificial intelligence
lcsh:Medicine (General)
business
Algorithms
Research Article
Mammography
Biotechnology
Zdroj: Journal of Healthcare Engineering, Vol 2019 (2019)
Journal of Healthcare Engineering
ISSN: 2040-2309
2040-2295
Popis: Breast tumor segmentation plays a crucial role in subsequent disease diagnosis, and most algorithms need interactive prior to firstly locate tumors and perform segmentation based on tumor-centric candidates. In this paper, we propose a fully convolutional network to achieve automatic segmentation of breast tumor in an end-to-end manner. Considering the diversity of shape and size for malignant tumors in the digital mammograms, we introduce multiscale image information into the fully convolutional dense network architecture to improve the segmentation precision. Multiple sampling rates of atrous convolution are concatenated to acquire different field-of-views of image features without adding additional number of parameters to avoid over fitting. Weighted loss function is also employed during training according to the proportion of the tumor pixels in the entire image, in order to weaken unbalanced classes problem. Qualitative and quantitative comparisons demonstrate that the proposed algorithm can achieve automatic tumor segmentation and has high segmentation precision for various size and shapes of tumor images without preprocessing and postprocessing.
Databáze: OpenAIRE
Externí odkaz: