Twelve Fused Models by Fusing Four Types of Transformer-Based Tuners on Three Base UNet Architectures for Carotid Wall Segmentation and Plaque Burden/Intima-Media Thickness Measurements in Ultrasound Scans: A Scientific Validation Study.
Authors
Affiliations (15)
Affiliations (15)
- Department of Electronics and Communication Engineering, Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India.
- Stroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA.
- Department of Computer Science Engineering, Samrat Ashok Rajkiya Engineering College (SAREC), New Delhi 23100, India.
- Division of Cardiology, Department of Medicine, Queen's University, Kingston, ON K7L 3N6, Canada.
- Department of Biomedical and Molecular Sciences, Queen's University, Kingston, ON K7L 3N6, Canada.
- Department of Radiobiology and Molecular Genetics, "VINČA" Institute of Nuclear Sciences-National Institute of the Republic of Serbia, University of Belgrade, 11001 Belgrade, Serbia.
- Department of Cardiology, St. Helena Hospital, St. Helena, CA 94574, USA.
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, ON M5G 1N8, Canada.
- MV Diabetes Center, Chennai 600013, India.
- Electrical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia.
- Department of Pathology, University of Cagliari, 09124 Cagliari, Italy.
- Department of Biomedical and Radiology, Columbia University, New York, NY 10027, USA.
- Department of Radiology, Azienda Ospedaliero-Universitaria (A.O.U.) di Cagliari, 09124 Cagliari, Italy.
- Department of Electrical and Computer Engineering, Idaho State University, Pocatello, ID 83209, USA.
- Symbiosis Institute of Technology, Symbiosis International (Deemed University), Nagpur Campus, Pune 440008, India.
Abstract
<b>Background/Objectives:</b> UNet-based models dominate medical image segmentation. Transformers have been added as an internal variant to these UNet-based architectures to improve feature learning. However, they have limitations in generalization and computational efficiency. Motivated by this idea, we have designed a two-stage novel hybrid segmentation framework, where tuners are added in cascade to the base architectures. <b>Methods:</b> Three sets of base UNets were designed, namely: B1: UNet1p, B2: UNet2p, and B3:UNet3p, and four sets of transformer-based tuners were designed, namely: T1:Transformer-augmented UNet, T2: Attention-guided UNet, T3: Swin Transformer-based UNet, and T4: Pyramid-based network, leading to 12 fused systems that combine three base UNets and four Tuners, namely: F1: B1 + T1, F2: B1 + T2, F3: B1 + T3, F4: B1 + T4; F5: B2 + T1, F6: B2 + T2, F7: B2 + T3, F8: B2 + T4, F9: B3 + T1, F10: B3 + T2, F11: B3 + T3, F12: B3 + T4. <b>Results:</b> The two-hybrid segmentation models are more effective and reliable than the single-stage UNet architecture. B3 + T4 achieved a Dice of 94.14% and Jaccard of 88.7%, surpassing prior baselines by 4.2% and 6.8%. It reduced cIMTE to 0.014 mm, a 36% improvement and the lowest reported to date, with cLIE and cMAE errors lowered by 40%. <b>Conclusions:</b> All 12 hybrid automated transformer-based models are highly accurate and reliable for wall segmentation in carotid ultrasound; they are a powerful paradigm for cardiovascular risk.