0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
A Novel Approach to Pulmonary Embolism Segmentation: Increasing an Attention-based U-Net
نویسندگان :
Hanie Arabian
1
Alireza Karimian
2
Hosein Arabi
3
Marjan Mansourian
4
1- دانشگاه اصفهان
2- دانشگاه اصفهان
3- University of Geneva
4- دانشگاه علوم پزشکی اصفهان
کلمات کلیدی :
deep learning،image segmentation،pulmonary embolism،squeeze-and-attention block،u-net architecture
چکیده :
Pulmonary embolism (PE) is a life-threatening condition, often leading to late diagnoses. Diagnostic tools like Computed Tomography Pulmonary Angiography (CTPA) rely on radiologist skills, resulting in variable sensitivity and specificity. This study aims to leverage deep learning, specifically a convolutional neural network with U-net architecture enhanced by Squeeze-and-Attention and Long Short-Term Memory (LSTM) blocks, to improve the segmentation of emboli in CTPA images. Utilizing two datasets, CAD-PE (91 cases, 89 with PE) and FUMPE (35 cases, 33 with PE), the research assesses how increasing the number of network layers (57, 67, and 103) affects segmentation performance. The results demonstrated that the slice-wise sensitivity improved from 76.73±21.94 with a 57-layer architecture to 80.36±21.42 with a 67-layer architecture, indicating better pulmonary embolism detection (with a significant difference due to paired T-test P-value of less than 0.05). In addition, the patient-wise AUC slightly increases from 81.68±10.94 (57 layers) to 85.09±10.69 (67 layers) with a Kruskal-Wallis P-value of 0.0189, which indicates a significant difference between the networks’ performance. However, no significant improvement was observed with the 103-layer model, highlighting the potential for overfitting. Results from this study demonstrate the potential of deep learning algorithms in enhancing the accurate diagnosis of pulmonary embolism. Finally, the neural network's performance in segmenting pulmonary embolisms from CT images demonstrates promising directions with particular specificity and overall AUC strengths.
لیست مقالات
لیست مقالات بایگانی شده
SGG-Net: Skeleton and Graph-Based Neural Network Approaches for Grasping Objects
AliReza Beigy - Farbod Azimmohseni - Ali Sabzejou - Mehdi Tale Masouleh - Ahmad Kalhor
Thermo-optically Adjustment of Stimulated Brillouin Scattering in Integrated Slot Ring Resonators
Mahdi Piri - Bijan Abbasi Arand - Sayyed Reza Mirnaziry
An Optimal Investigation into A Preventive Maintenance Scheduling Scheme for Electric Power Transmission Networks
Seyed Sina Taheri Otaghsara - Masoud Asghari Gharakheili
Adaptive Smooth Super Twisting Sliding Mode Control for Parkinson's Tremor Treatment
Reyhaneh Valibeik - ّFatemeh Jahangiri - Mostafa Abedi
طراحی و ساخت یک سیستم مخابرات نور مرئی مبتنی بر دوربین
شادی خسروی - فروغ السادات طباطباء - شهاب الدین رحمانیان
شبیه سازی یک حسگر با استفاده از یک میکرو تشدیدگر اویلری
مریم دهقانیان - محسن حاتمی
Fast Subdomain Approximation of Brushless Electrical Machines with Spoke-Hub Permanent Magnets
Meisam Pourahmadinakhli - Seyed Hassan Daryanavard - Masoud Jokar-Kohanjani - Sina Soltani
Achieving a Wide Range of Voltage Gain in Three-Phase LLC Resonant Converter Using Hybrid Control of Variable Frequency and Variable Magnetizing Inductor
Saeed Ramezani darvish - Salar Sadeghian - Adib Abrishamifar
A Graphene Terahertz Detector based on the Photo-Thermoelectric Effect with Frequency Selectivity
Faramarz Alihosseini - Zahra Heshmatpanah - Hesam Zandi
Physics-Based Learning Approach Using Self-Terms for Electromagnetic Scattering in Multi-Object Scenarios
Arefeh Nikdast - Amir ahmad Shishegar
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2