tsta

فارسی

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Attentive Temporal Fusion Network (ATFNet) for Multi-frame Coronary Vessel Segmentation in X-ray Angiography

Authors :

Pouya Babaei¹ Farshad Almasganj²

1- Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran 2- Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran

Keywords :

Attentive Temporal Fusion Network،Coronary vessel segmentation،X-ray coronary angiography،Spatial Attention Temporal Squeeze،Structured sparsity loss

Abstract :

X-ray coronary angiography remains the clinical gold standard for visualizing coronary lumen but presents major challenges for automated analysis: low vessel contrast, overlapping anatomy, catheter occlusion, breathing/heartbeat motion and extremely thin branching vessels that fracture easily in segmentation maps. To address these issues we propose ATFNet (Attentive Temporal Fusion Network), a compact UNet++–inspired architecture that ingests short temporal stacks (four successive frames) and fuses motion and appearance cues into a single 2-D prediction. Key components are (i) SATS (Spatial Attention Temporal Squeeze), a per-frame directional spatial attention and learned temporal fusion that compresses four frames into a channel-recalibrated 2-D representation; (ii) SE_ResBlock3D/2D units that provide residual learning with squeeze-and-excitation attention in the 3D encoder and 2D decoder; (iii) DSF (Deep Supervision Fusion), which combines coarse (spatial merge) and attentive (channel-reweighted) fine kernels from multiple decoder depths into one robust output; and (iv) a topology-aware StructuredSparsityLoss (BCE–Dice base + multi-scale tree norm) together with the Lion optimizer and scheduler to stabilise and accelerate training on modest clinical data. On a manually annotated clinical XCA set, ATFNet produces noticeably more continuous, less fragmented vessel masks and improved temporal stability compared with single-frame baselines; ablation studies confirm that SATS, DSF, SE-Res blocks and the Lion optimizer each contribute to the observed gains. These results indicate that compact, attention-augmented temporal fusion, combined with a tree-aware loss, can substantially improve coronary vessel continuity and segmentation fidelity in angiographic sequences.

Papers List

List of archived papers

.Deep Learning-based Segmentation of Human Sperm Heads using YOLOv8 and SAM

Hadis Aligoo Zanjany - Maryam Pashaiasl - Ata Jodeiri

Structural Insights into the Molecular Mechanism of Cancer Regulator BRCA1 Methylation

Shadi Asadi - Maryam Azimzadeh Irani

یادگیری عمیق مبتنی بر مکانیسم توجه جمعیت برای تحلیل احساسات بلادرنگ در چت‌های زنده یوتیوب

علی فرزین

Patient-Specific TMJ Implants: A Finite Element Study on Placement and Material Effects

Aryana Tavakoulnia - Mohadese Rajaeirad - Nima Jamshidi - Sandipan Roy

An Automatic Pipeline for Simultaneous EEG-fMRI Artifact-removal (SEFA)

Farid Hosseinzadeh - Amin Mohammad Mohammadi - Mehrdad Anvarifard - ُSasan Keshavarz - Elias Ebrahimzadeh - Hamid Soltanian-Zadeh

The Impact of an Interactive Rehabilitation Protocol ‎on Reorganization of Brain Networks in Children ‎with Cerebral Palsy: A Pilot Study

Shahed Salehzehi - Mahdi Mollaei - Parisa Hosseini - Ali Koohian Mohammad abadi - Mohammad Ebrahim Hashemi - Hamid Reza Kobravi - Narges Hashemi - Mehran Beiraghi Toosi - Javad Akhondian

Late Fusion-Based Deep Learning for Breast Cancer Classification in Mammography

Mehdi Baharloo - Ata Jodeiri

آمایش گردشگری مناطق ایران و هوش مصنوعی

محمدعلی فیض پور - مهدیه پیروی

Evaluation of Mechanical and Biological Properties of PCL-coated Magnesium Scaffolds

Fatemeh Sharifabadi - Sayed Khatiboleslam Sadrnezhaad

Synthesis and Characterization of an Injectable Magnetic Scaffold Based on Alginate/Chitosan and Zero-Valent Iron for Hyperthermia

Mohammad Jafari Fashtami - Bahareh Khalilivavdareh - Delaram Dezfoulian - Maryam Tajabadi

Samin Hamayesh - Version 42.5.2