Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks
| Autor: | Moi Hoon, Yap, Gerard, Pons, Joan, Marti, Sergi, Ganau, Melcior, Sentis, Reyer, Zwiggelaar, Adrian K, Davison, Robert, Marti, Moi Hoon Yap |
|---|---|
| Přispěvatelé: | Manchester Metropolitan University, Universitat de Girona, Aberystwyth University, University of Manchester, Universitat Oberta de Catalunya (UOC) |
| Rok vydání: | 2018 |
| Předmět: |
Databases
Factual detección de lesiones transferencia de aprendizaje 02 engineering and technology transfer learning cáncer de mama redes neuronales convolucionales Convolutional neural network 030218 nuclear medicine & medical imaging ultrasound imaging 0302 clinical medicine Health Information Management càncer de mama convolutional neural networks 0202 electrical engineering electronic engineering information engineering False positive paradox Medicine Computer vision Breast Breast -- Cancer Breast ultrasound medicine.diagnostic_test Artificial neural network Ultrasound Computer Science Applications Female 020201 artificial intelligence & image processing Ultrasonography Mammary Transfer of learning Algorithms Biotechnology Breast Neoplasms detecció de lesions xarxes neuronals convolucionals 03 medical and health sciences breast cancer imagen de ultrasonido Image Interpretation Computer-Assisted Humans Electrical and Electronic Engineering Mama -- Cáncer business.industry Deep learning Pattern recognition imatges per ultrasò lesion detection transferir l'aprenentatge Ranking Mama -- Càncer Neural Networks Computer Artificial intelligence business |
| Zdroj: | O2, repositorio institucional de la UOC Universitat Oberta de Catalunya (UOC) Yap, M H, Pons, G, Martí, J, Ganau, S, Sentís, M, Zwiggelaar, R, Davison, A K & Martí, R 2018, ' Automated Breast Ultrasound Lesions Detection Using Convolutional Neural Networks ', IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 4, pp. 1218-1226 . https://doi.org/10.1109/JBHI.2017.2731873 |
| ISSN: | 2168-2208 2168-2194 |
| DOI: | 10.1109/jbhi.2017.2731873 |
| Popis: | Breast lesion detection using ultrasound imaging is considered an important step of computer-aided diagnosis systems. Over the past decade, researchers have demonstrated the possibilities to automate the initial lesion detection. However, the lack of a common dataset impedes research when comparing the performance of such algorithms. This paper proposes the use of deep learning approaches for breast ultrasound lesion detection and investigates three different methods: a Patch-based LeNet, a U-Net, and a transfer learning approach with a pretrained FCN-AlexNet. Their performance is compared against four state-of-the-art lesion detection algorithms (i.e., Radial Gradient Index, Multifractal Filtering, Rule-based Region Ranking, and Deformable Part Models). In addition, this paper compares and contrasts two conventional ultrasound image datasets acquired from two different ultrasound systems. Dataset A comprises 306 (60 malignant and 246 benign) images and Dataset B comprises 163 (53 malignant and 110 benign) images. To overcome the lack of public datasets in this domain, Dataset B will be made available for research purposes. The results demonstrate an overall improvement by the deep learning approaches when assessed on both datasets in terms of True Positive Fraction, False Positives per image, and F-measure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|