A histopathology aware DINO model with attention based representation enhancement
Yazarlar (4)
Öğr. Gör. Merve ÖZKAN Kastamonu Üniversitesi, Türkiye
Caner Ozcan Karabük Üniversitesi, Türkiye
V. K.Cody Bumgardner
Stanley And Karen Pigman College of Engineering, Amerika Birleşik Devletleri
Stanley And Karen Pigman College of Engineering, Amerika Birleşik Devletleri
Mahmut S. Gokmen
Stanley And Karen Pigman College of Engineering, Amerika Birleşik Devletleri
Stanley And Karen Pigman College of Engineering, Amerika Birleşik Devletleri
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Scientific Reports (Q1) | ||
| Dergi ISSN | 2045-2322 Dergi Bilgileri (2025) | ||
| Dergi Tarandığı Indeksler | SSCI, AHCI, SCI, SCI-Exp, ESCI, Scopus | ||
| Makale Dili | İngilizce | Basım Tarihi | 12-2025 |
| Kabul Tarihi | 02-12-2025 | Yayınlanma Tarihi | 22-12-2025 |
| Cilt / Sayı / Sayfa | 15 / 1 / 45083–0 | DOI | 10.1038/s41598-025-31438-8 |
| Makale Linki | https://doi.org/10.1038/s41598-025-31438-8 | ||
| UAK Araştırma Alanları |
Yapay Zeka
Görüntü İşleme
Makine Öğrenmesi
|
||
| Özet |
| Histopathological image analysis plays a critical role in modern medical diagnostics, particularly in the detection and classification of various types of cancer. This study proposes a method called HistoDARE (Histopathology-Aware DINO with Attention-based Representation Enhancement), which offers an innovative approach to the attention module used in the Vision Transformers architecture. Unlike conventional attention mechanisms, HistoDARE introduces a novel three-stage AttentionWrapper module that sequentially applies spatial and channel attention followed by a residual refinement stage, enabling the extraction of spatially-aware and semantically distinctive feature representations. HistoDARE is a method integrated into the DINOv2 model, which uses the ViT-L/14 architecture. The obtained features were interpreted using Logistic Regression, and 5-fold stratified cross-validation was applied on the NCT … |
| Anahtar Kelimeler |
| Biyomedikal Görüntü İşleme |
| Atıf Sayıları | |
| Web of Science | 1 |
| Scopus | 2 |
| Google Scholar | 3 |