Mass segmentation and classification from film mammograms using cascaded deep transfer learning
| dc.contributor.author | Tiryaki, Volkan Müjdat | |
| dc.date.accessioned | 2023-05-18T08:34:44Z | |
| dc.date.available | 2023-05-18T08:34:44Z | |
| dc.date.issued | 2023 | en_US |
| dc.department | Rektörlük, Bilişim Teknolojileri Uygulama ve Araştırma Merkezi | en_US |
| dc.description.abstract | Breast cancer is the most common type of cancer among women worldwide. Early breast cancers have a high chance of cure so early diagnosis is critical. Mammography screening allows early detection of breast cancer. There has been an increasing interest in the investigation of computer-aided breast cancer diagnosis recently due in part to the development of the novel high-performing deep learning models. In this study, cascaded deep transfer learning (DTL)-based segmentation methods were investigated to segment mass lesions using mammograms of Breast Cancer Digital Repository. In the first stage, the noise sources in the mammogram background were removed by deep learning-based breast segmentation. In the second stage, the mass segmentation performances of five-layer U-net and U-nets having pre-trained weights from VGG16, ResNet50, and Xception networks in the encoding path were investigated. The performances of attention U-net, residual U-net, MultiResUnet, DeepLabV3Plus, and Unet++ were also investigated. A Unet++ model that uses Xception network weights in the encoder region is proposed. The mass segmentation model predictions were used to estimate mass lesion characterization using DTL. On the test data, an AUC of 0.7829, Dice's similarity coefficient of 0.6356 and intersection over union of 0.5408 were obtained for mass segmentation using the proposed U-net++Xception model. An AUC of 0.8188 and accuracy of 0.7619 were obtained for mass classification into benign versus malignant. The results show that the proposed DTL pipeline can be used for automatic mass segmentation and classification without using clinical data and may reduce the workload of radiologists. | en_US |
| dc.identifier.doi | 10.1016/j.bspc.2023.104819 | en_US |
| dc.identifier.scopus | 2-s2.0-85150305176 | en_US |
| dc.identifier.scopusquality | N/A | en_US |
| dc.identifier.uri | https://hdl.handle.net/11467/6611 | |
| dc.identifier.uri | https://doi.org/10.1016/j.bspc.2023.104819 | |
| dc.identifier.volume | 84 | en_US |
| dc.identifier.wos | WOS:000953923400001 | en_US |
| dc.identifier.wosquality | Q1 | en_US |
| dc.indekslendigikaynak | Web of Science | en_US |
| dc.indekslendigikaynak | Scopus | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | Elsevier Ltd | en_US |
| dc.relation.ispartof | Biomedical Signal Processing and Control | en_US |
| dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
| dc.rights | info:eu-repo/semantics/embargoedAccess | en_US |
| dc.subject | Benign; Malignant; Mammography; Nodule; Radiomics | en_US |
| dc.title | Mass segmentation and classification from film mammograms using cascaded deep transfer learning | en_US |
| dc.type | Article | en_US |
