Mass segmentation and classification from film mammograms using cascaded deep transfer learning

Basit Öğe Kaydı
dc.authoridTIRYAKI, VOLKAN MUJDAT/0000-0003-1824-5260
dc.contributor.authorTiryaki, Volkan Muejdat
dc.date.accessioned2024-12-24T19:25:23Z
dc.date.available2024-12-24T19:25:23Z
dc.date.issued2023
dc.departmentSiirt Üniversitesi
dc.description.abstractBreast 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 mam-mograms 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 per-formances 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, Multi-ResUnet, 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.
dc.description.sponsorshipSiirt University Scientific Research Projects Directorate Grant [2021-SI??, M?H-01]
dc.description.sponsorshipFunding Information This work was supported by Siirt University Scientific Research Projects Directorate Grant No. 2021-SI??M?H-01 (VMT) .
dc.identifier.doi10.1016/j.bspc.2023.104819
dc.identifier.issn1746-8094
dc.identifier.issn1746-8108
dc.identifier.scopus2-s2.0-85150305176
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.bspc.2023.104819
dc.identifier.urihttps://hdl.handle.net/20.500.12604/6387
dc.identifier.volume84
dc.identifier.wosWOS:000953923400001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Sci Ltd
dc.relation.ispartofBiomedical Signal Processing and Control
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241222
dc.subjectMammography
dc.subjectRadiomics
dc.subjectNodule
dc.subjectMalignant
dc.subjectBenign
dc.titleMass segmentation and classification from film mammograms using cascaded deep transfer learning
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu