Evaluating the performance of convolutional neural networks with direct acyclic graph architectures in automatic segmentation of breast lesion in US images
| Autor: | Gustavo de Aquino e Aquino, João Paulo Mendes Campos, Marly Guimarães Fernandes Costa, Cicero Ferreira Fernandes Costa Filho, Wagner Coelho de Albuquerque Pereira |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
lcsh:Medical technology
Breast imaging Computer science Breast Neoplasms 02 engineering and technology Convolutional neural network 03 medical and health sciences 0302 clinical medicine Sørensen–Dice coefficient Image Interpretation Computer-Assisted Breast lesion 0202 electrical engineering electronic engineering information engineering Humans Radiology Nuclear Medicine and imaging Segmentation Layer (object-oriented design) business.industry Pattern recognition lcsh:R855-855.5 030220 oncology & carcinogenesis Metric (mathematics) Path (graph theory) Ultrasound images 020201 artificial intelligence & image processing Female Convolutional neural networks Artificial intelligence Neural Networks Computer Ultrasonography Mammary business Focus (optics) Algorithms Research Article |
| Zdroj: | BMC Medical Imaging, Vol 19, Iss 1, Pp 1-13 (2019) BMC Medical Imaging |
| ISSN: | 1471-2342 |
| DOI: | 10.1186/s12880-019-0389-2 |
| Popis: | Background Outlining lesion contours in Ultra Sound (US) breast images is an important step in breast cancer diagnosis. Malignant lesions infiltrate the surrounding tissue, generating irregular contours, with spiculation and angulated margins, whereas benign lesions produce contours with a smooth outline and elliptical shape. In breast imaging, the majority of the existing publications in the literature focus on using Convolutional Neural Networks (CNNs) for segmentation and classification of lesions in mammographic images. In this study our main objective is to assess the ability of CNNs in detecting contour irregularities in breast lesions in US images. Methods In this study we compare the performance of two CNNs with Direct Acyclic Graph (DAG) architecture and one CNN with a series architecture for breast lesion segmentation in US images. DAG and series architectures are both feedforward networks. The difference is that a DAG architecture could have more than one path between the first layer and end layer, whereas a series architecture has only one path from the beginning layer to the end layer. The CNN architectures were evaluated with two datasets. Results With the more complex DAG architecture, the following mean values were obtained for the metrics used to evaluate the segmented contours: global accuracy: 0.956; IOU: 0.876; F measure: 68.77%; Dice coefficient: 0.892. Conclusion The CNN DAG architecture shows the best metric values used for quantitatively evaluating the segmented contours compared with the gold-standard contours. The segmented contours obtained with this architecture also have more details and irregularities, like the gold-standard contours. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink