A Survey of Non-Invasive Techniques and Artificial Intelligence Approaches for Blood Vessel Blockage Detection

A Survey of Non-Invasive Techniques and Articial Intelligence Approaches for Blood Vessel Blockage Detection

Prof. Nikita Gosavi

Department of Computer Engineering JSPMs JSCOE, Pune

Samarth Ghorpade

Department of Computer Engineering JSPMs JSCOE, Pune

Varun Chaudhari

Department of Computer Engineering JSPMs JSCOE, Pune

Nayan Pawar

Department of Computer Engineering JSPMs JSCOE, Pune

Vaibhav Raul

Department of Computer Engineering JSPMs JSCOE, Pune

Abstract – Blood vessel blockage is one of the major causes of cardiovascular diseases worldwide. Traditional diagnostic meth- ods such as angiography provide accurate results but are invasive, expensive, and may cause discomfort to patients. Recent advance- ments in medical signal processing, wearable sensors, machine learning, and articial intelligence have enabled the development of non-invasive techniques for vascular health assessment.

This survey reviews existing approaches including Photo- plethysmography (PPG), Electrocardiography (ECG), Infrared Thermography, Ultrasound Imaging, Electrical Impedance To- mography (EIT), wearable healthcare devices, and AI-based diagnostic systems.

Index TermsBlood Vessel Blockage, Non-Invasive Diagnosis, Articial Intelligence, Machine Learning, PPG, ECG, Cardiovas- cular Disease

TABLE I

Comparative Analysis of Existing Non-Invasive Blood Vessel Blockage Detection Systems

1. Introduction

   Blood vessel blockage is a serious medical condition that restricts normal blood ow through arteries and veins. If left untreated, it can result in heart attacks, strokes, and peripheral artery disease. Angiography is considered the gold standard for diagnosing arterial blockages; however, it is invasive, costly, and requires specialized medical facilities.

   Recent developments in biomedical sensors, signal process- ing, and articial intelligence have enabled the creation of non- invasive diagnostic systems capable of identifying vascular abnormalities without surgical procedures.

2. Literature Review

   The literature indicates signicant progress in non-invasive vascular diagnosis through signal processing, wearable sen- sors, and machine learning technologies.

3. Methodology

   The methodology adopted in this survey focuses on analyz- ing existing non-invasive techniques for blood vessel block- age detection. Various studies based on PPG, ECG, thermal

   imaging, ultrasound imaging, wearable sensors, and articial intelligence are examined and compared.

   The proposed smart diagnostic framework collects physio- logical signals using non-invasive sensors. Signal preprocess- ing removes noise and artifacts. Feature extraction techniques identify important cardiovascular indicators, which are then analyzed using machine learning algorithms to predict possible blood vessel blockages.

   The generated results are compared with medical thresholds and used to estimate blockage severity and associated risks.

   Fig. 1. Methodology of Smart Diagnostic System for Blood Vessel Blockage Detection Using Non-Invasive Methods

4. Research Gap

   Although numerous non-invasive diagnostic techniques have been developed, most systems focus on a single sensing modality. Existing methods often require expensive equipment or expert interpretation. There remains a need for an inte- grated AI-based diagnostic framework that combines multiple physiological signals for accurate and affordable blood vessel blockage detection without angiography.

5. Comparative Analysis

   Machine learning methods provide improved diagnostic accuracy, while wearable sensors enable continuous monitor- ing. Thermal imaging and EIT offer additional physiological insights. However, limitations such as cost, data availability, and interpretability still exist.

6. Future Scope

   Future research should focus on integrating wearable health- care devices, cloud computing, Internet of Things (IoT) technology, and advanced deep learning models. Real-time monitoring and personalized risk prediction can signicantly improve early diagnosis and patient care.

7. Conclusion

This survey reviewed various non-invasive approaches for blood vessel blockage detection, including PPG, ECG, thermal imaging, EIT, and AI-based diagnostic systems. The analysis

highlights the potential of intelligent healthcare technologies to provide early, cost-effective, and accessible cardiovascular di- agnosis. Future developments are expected to further improve diagnostic accuracy and clinical adoption.

References

1. Kumar S. et al., Non-invasive Detection of Vascular Diseases Using Machine Learning, 2021.

2. Allen J., Photoplethysmography: A Novel Tool for Vascular Diagnos- tics, 2007.

3. Lahiri B.B. et al., Infrared Thermal Imaging for Peripheral Vascular Disorder Detection, 2012.

4. Adler A. et al., Electrical Impedance Tomography for Cardiovascular Applications, 2014.

5. Rajpurkar P. et al., Deep Learning for Cardiovascular Disease Predic- tion Using Wearable Signals, 2019.

6. M. Osama, A. Khan, and S. Ali, YOLOv8 deep learning model for real-time visual analysis, in Proc. IEEE Int. Conf. Articial Intelligence, Dubai, UAE, 2024, pp. 8894.

7. M. Ramamoorthy and K. Srinivasan, Morphological Hessian-based segmentation and Otsu thresholding for medical image processing, International Journal of Computer Applications, vol. 179, no. 21, pp. 1522, 2018.

8. R. Kumar, P. Singh, and A. Verma, Two-step CNN with transfer learning and data augmentation for biomedical image analysis, Journal of Healthcare Engineering, vol. 2023, pp. 111, 2023.

9. E. Hagyma´si, Integration of MRI, ultrasound, CT, and AI-driven molecular diagnostics for accurate disease detection, IEEE Reviews in Biomedical Engineering, vol. 17, pp. 210225, 2024.

10. H Edrisnia, M. Rahman, and T. Joseph, Computational uid dynamics model with Windkessel boundary conditions for vascular ow analysis, Computer Methods in Biomechanics and Biomedical Engineering, vol. 27, no. 2, pp. 98110, 2024.

11. A. Rostam-Alilou, S. Ahmadi, and K. Rezaei, One-class support vector machine trained on hemodynamic and CTA data for detecting coronary artery aneurysm, Biomedical Physics and Engineering Express, vol. 8, no. 4, pp. 19, 2022.

12. A. Krizhevsky, I. Sutskever, and G. E. Hinton, ImageNet classication with deep convolutional neural networks, in Advances in Neural Infor- mation Processing Systems (NIPS), Lake Tahoe, NV, USA, 2012, pp. 10971105.