Tubule-U-Net [Elektronisk resurs] a novel dataset and deep learning-based tubule segmentation framework in whole slide images of breast cancer
-
Tekin, Eren (författare)
-
Yazıcı, Çisem (författare)
-
Kusetogullari, Hüseyin, 1981- (författare)
-
Tokat, Fatma (författare)
-
Yavariabdi, Amir (författare)
-
Iheme, Leonardo Obinna (författare)
-
Çayır, Sercan (författare)
-
Bozaba, Engin (författare)
-
Solmaz, Gizem (författare)
-
Darbaz, Berkan (författare)
-
Özsoy, Gülşah (författare)
-
Ayaltı, Samet (författare)
-
Kayhan, Cavit Kerem (författare)
-
İnce, Ümit (författare)
-
Uzel, Burak (författare)
-
Blekinge Tekniska Högskola Fakulteten för datavetenskaper (utgivare)
- Publicerad: Nature Research, 2023
- Engelska.
-
Ingår i: Scientific Reports. ; 13:1
-
Läs hela texten
-
Läs hela texten
-
Läs hela texten
- Relaterad länk:
-
http://www.bth.se/ (Värdpublikation)
Sammanfattning
Ämnesord
Stäng
- The tubule index is a vital prognostic measure in breast cancer tumor grading and is visually evaluated by pathologists. In this paper, a computer-aided patch-based deep learning tubule segmentation framework, named Tubule-U-Net, is developed and proposed to segment tubules in Whole Slide Images (WSI) of breast cancer. Moreover, this paper presents a new tubule segmentation dataset consisting of 30820 polygonal annotated tubules in 8225 patches. The Tubule-U-Net framework first uses a patch enhancement technique such as reflection or mirror padding and then employs an asymmetric encoder-decoder semantic segmentation model. The encoder is developed in the model by various deep learning architectures such as EfficientNetB3, ResNet34, and DenseNet161, whereas the decoder is similar to U-Net. Thus, three different models are obtained, which are EfficientNetB3-U-Net, ResNet34-U-Net, and DenseNet161-U-Net. The proposed framework with three different models, U-Net, U-Net++, and Trans-U-Net segmentation methods are trained on the created dataset and tested on five different WSIs. The experimental results demonstrate that the proposed framework with the EfficientNetB3 model trained on patches obtained using the reflection padding and tested on patches with overlapping provides the best segmentation results on the test data and achieves 95.33%, 93.74%, and 90.02%, dice, recall, and specificity scores, respectively. © 2023, The Author(s).
Ämnesord
- Engineering and Technology (hsv)
- Medical Engineering (hsv)
- Medical Image Processing (hsv)
- Teknik och teknologier (hsv)
- Medicinteknik (hsv)
- Medicinsk bildbehandling (hsv)
Genre
- government publication (marcgt)
Indexterm och SAB-rubrik
- Breast Neoplasms
- Deep Learning
- Female
- Humans
- Image Processing
- Computer-Assisted
- Semantics
- breast tumor
- diagnostic imaging
- human
- image processing
- procedures
Inställningar
Hjälp
Ingår i annan publikation. Gå till titeln
Scientific Reports