0% Complete
صفحه اصلی
/
International Conference on Artificial Intelligence; City, Industry and Health
Comparative Analysis of U-Net and U-Net (Xception) for CT-Based Segmentation of Target Volume and Organs At-Risk in Left Breast Cancer
نویسندگان :
Hajar Ahmadi
1
Azimeh NV Dehkordi
2
Farhad Azimifar
3
Seied Rabi Mahdavi
4
Mahnaz Roayaei
5
1- Department of Biomedical Engineering, Isf.C., Islamic Azad University, Isfahan, Iran, ahmadierfane@yahoo.com
2- Department of Computer Engineering, Na.C., Islamic Azad University, Najafabad, Iran, nourizadeh@iau.ir
3- Department of Biomedical Engineering, Isf.C., Islamic Azad University, Isfahan, Iran, f.azimifar@khisf.ac.ir
4- 1. Department of Medical Physics and Radio-Oncology, Faculty of Medicine, Iran University of Medical Science, Tehran, Iran, srmahdavi@hotmail.com .2. d2 Radiation Biology Research Center, Iran University of Medical Science, Tehran, Iran, srmahdavi@hotmail.com
5- Department of Radiation Oncology, Omid Hospital, Esfahan University of Medical Sciences, Isfahan, Iran, roayaeimahnaz@gmail.com
کلمات کلیدی :
Breast Cancer،Radiotherapy treatment Planning،Segmentation،U-Net،Xception
چکیده :
Accurate segmentation of anatomical structures in breast cancer imaging is crucial for effective diagnosis and treatment planning. This study investigates the performance of U-Net and a novel U-Net variant that incorporates the Xception architecture as an encoder, aiming to enhance segmentation accuracy and efficiency. We conducted a comprehensive evaluation of both models using a diverse dataset, focusing on key metrics such as Dice similarity score, global accuracy, and prediction time. The U-Net model achieved a mean Dice score of 0.7434 with a global accuracy of 0.95109, demonstrating strong performance in segmenting structures such as the "Lung Left" and "Skin." However, the approach utilizing Xception significantly improved overall performance, yielding a mean Dice score of 0.78299 and a remarkable global accuracy of 0.98335, particularly excelling in clearly defined regions. both models facing challenges with the "GTV" class. This research underscores the potential of integrating advanced deep learning techniques in medical imaging, offering valuable insights for developing efficient tools to support oncological diagnostics and treatment strategies.
لیست مقالات
لیست مقالات بایگانی شده
Impact of Using ChatGPT as an AI Tool on Speaking Complexity, Accuracy, and Fluency Among Iranian EFL Learners
Samira Beheshti - Omid Tabatabaei - Hadi Salehi
اثر تصحیح خطای مثبت ترانسفورماتورهای ولتاژ خازنی بر بهینهسازی مصرف انرژی و کاهش هزینههای برق در شرکت فولاد خوزستان
علی سالم دزفولی - محمود جورابیان - ناصر حمیدی - مجتبی آزادی اردکانی
مقایسه کارایی کنترلهای فازی و PID در کاهش ریپل و نوسانات ناخواسته در کنترل رباتهای دو لینک انعطافپذیر
مصطفی مکی شهرضایی - عباس چترائی
Impacts of Placement and Control Modes of Large-Scale PV Systems on the Steady-State Performance of the IEEE 39-Bus
Mohammadreza Azizi - Amirreza Rezaei
نقش انرژیهای نو در توسعه هوشمند و پایدار شهری
زهرا حسنی - فرشته احمدی
Enhancing Multilingual Spam Detection Using Machine Learning and Synthetic Data Augmentation
Mohamad Hosein Ghojavand - Hamid Rastegari
Bridging the Gap: Understanding Adult Learners' Fear of AI in Language Classrooms and How to Overcome It
Bahareh Assarzadegan - Oimd Tabatabaei - Ali Yousefi
Artificial Intelligence, Armed Conflict, and the International Obligations of States
Masoud Raei Dehaghi
Self-Adapting Urban Digital Twins: A Cost-Effective Optimization Approach for Long-Term Infrastructure Management
Shohreh Ajoudanian - Maryam Nooraei Abadeh - Hamid Reza Aboutalebi
The Application of Artificial Intelligence in Optimizing and Forecasting the Performance of Renewable Energy Systems
Behzad Ghadiri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.6.0