Classification for Breast Ultrasound Using Convolutional Neural Network with Multiple Time-Domain Feature Maps
| Autor: | Hakjoon Lee, Hyungsuk Kim, Geuntae Im, Jong-Soo Lee, Ju-Young Park, Heung Jae Lee, Kibaek Lee |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Technology
Image quality Generalization Computer science QH301-705.5 QC1-999 convolutional neural network Convolutional neural network medical ultrasound medicine phase image General Materials Science Entropy (energy dispersal) Biology (General) Instrumentation Breast ultrasound QD1-999 Network model Fluid Flow and Transfer Processes medicine.diagnostic_test business.industry Process Chemistry and Technology Deep learning Physics General Engineering deep learning Pattern recognition Engineering (General). Civil engineering (General) Computer Science Applications breast US images entropy image Chemistry Feature (computer vision) B-mode image Artificial intelligence TA1-2040 business |
| Zdroj: | Applied Sciences, Vol 11, Iss 10216, p 10216 (2021) Applied Sciences Volume 11 Issue 21 |
| ISSN: | 2076-3417 |
| Popis: | Ultrasound (US) imaging is widely utilized as a diagnostic screening method, and deep learning has recently drawn attention for the analysis of US images for the pathological status of tissues. While low image quality and poor reproducibility are the common obstacles in US analysis, the small size of the dataset is a new limitation for deep learning due to lack of generalization. In this work, a convolutional neural network (CNN) using multiple feature maps, such as entropy and phase images, as well as a B-mode image, was proposed to classify breast US images. Although B-mode images contain both anatomical and textual information, traditional CNNs experience difficulties in abstracting features automatically, especially with small datasets. For the proposed CNN framework, two distinct feature maps were obtained from a B-mode image and utilized as new inputs for training the CNN. These feature maps can also be made from the evaluation data and applied to the CNN separately for the final classification decision. The experimental results with 780 breast US images in three categories of benign, malignant, and normal, showed that the proposed CNN framework using multiple feature maps exhibited better performances than the traditional CNN with B-mode only for most deep network models. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|