I2IReg–ClfNet: a cascaded multi-task deep learning framework for ROI-aware kidney stone detection in abdominal CT images
Yazarlar (6)
Coşku Öksüz Izmir Bakircay University, Türkiye
Artun Narter
Izmir Bakircay University, Türkiye
Izmir Bakircay University, Türkiye
Doç. Dr. Bünyamin ECE Kastamonu Üniversitesi, Türkiye
Prof. Dr. Mustafa Koyun Kastamonu Training And Research Hospital, Türkiye
Doç. Dr. İsmail TAŞKENT Kastamonu Üniversitesi, Türkiye
M. Kemal Güllü
Izmir Bakircay University, Türkiye
Izmir Bakircay University, Türkiye
| Makale Türü | Özgün Makale (SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale) | ||
| Dergi Adı | Biomedical Signal Processing and Control (Q2) | ||
| Dergi ISSN | 1746-8094 Wos Dergi Scopus Dergi | ||
| Dergi Tarandığı Indeksler | SCI-Expanded | ||
| Makale Dili | Türkçe | Basım Tarihi | 06-2026 |
| Cilt / Sayı / Sayfa | 119 / 1 / – | DOI | 10.1016/j.bspc.2026.109857 |
| Makale Linki | https://doi.org/10.1016/j.bspc.2026.109857 | ||
| UAK Araştırma Alanları |
Radyoloji
|
||
| Özet |
| Accurate detection of kidney stones from abdominal CT images is a challenging task due to anatomical complexity, low-density stones, imaging artifacts, and the presence of stone-like formations in non-renal regions. Although non-contrast computed tomography (NCCT) is considered the gold standard imaging modality for kidney stone detection, interpreting such scans—especially in emergency settings without expert support—can be error-prone and time-consuming. Hence, there is a growing need for automated, region-aware computer-aided diagnostic systems to assist clinical decision-making. This study introduces a novel multi-task deep learning framework, termed I2IReg–ClfNet, which fundamentally differs from classical multi-task networks by combining an image-to-image regression network and a classification network in a cascaded configuration. Unlike conventional multi-branch architectures that … |
| Anahtar Kelimeler |
| Abdominal CT | Deep learning | Image regression | Interpretability | Kidney stones | Multi-task learning | ROI classification |
Science Direct
I2IReg–ClfNet: a cascaded multi-task deep learning framework for ROI-aware kidney stone detection in abdominal CT images
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Scopus | 1 |
| Google Scholar | 1 |