سامانه همایش ها

English

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

Lightweight 3D U-Net for Robust Liver Segmentation in Multi-Institutional CT Datasets

نویسندگان :

Seyyed Mohammad Hosseini¹ Faeze Salahshour² Ahmadreza Sebzari³ Masoomeh Safaei⁴ Hossein Ghadiri Harvani⁵

1- دانشگاه علوم پزشکی تهران 2- دانشگاه علوم پزشکی تهران 3- دانشگاه علوم پزشکی بیرجند 4- دانشگاه علوم پزشکی تهران 5- دانشگاه علوم پزشکی تهران

کلمات کلیدی :

Liver،Segmentation،Computed Tomography (CT)،3D U-Net

چکیده :

A computed tomography (CT) image of the liver and surrounding structures provides detailed cross-sectional images, which highlight anatomical variations and pathological conditions. The combination of CT and U-Net networks is a well-known method for liver segmentation, which is vital for accurate diagnosis, treatment planning, and surgical intervention. However, the high computational demands of recent 3D U-Net–based architectures prevent their deployment in resource-constrained environments. A lightweight 3D U-Net optimized for liver segmentation is proposed in this study, maintaining high performance while reducing computational complexity drastically. Several institutional datasets of 250 abdominal CT volumes were compiled from public benchmarks (LiTS, IRCAD) and local clinical sources, encompassing anatomical, pathological, and protocol variations. An isotropic resampling procedure was used to resample, normalize intensity, standardize crops, and augment data on-the-fly. With fewer than two million parameters, the proposed model retains the encoder-decoder and skip-connection designs of conventional 3D U-Nets. An evaluation of a 30% independent set of tests achieved Dice similarity coefficients of 0.85 ± 0.02, intersect-over-unions of 0.82 ± 0.03, inference times under 0.7 s and GPU memory consumption below 2 GB. The performance was consistent across public and local datasets, highlighting the importance of heterogeneous training data. Even though the proposed model is slightly less accurate than heavy architecture, it delivers near-real-time segmentation with minimal resource consumption, so it can be integrated into clinical workflows, especially in environments where computational resources are limited.

لیست مقالات

لیست مقالات بایگانی شده

Skin Thermomechanical Modeling: Assessing the Influence of Water and Ambient Air

Pezhman Namashiri - Akbar Allahverdizadeh - Fatemeh Khodadoost - Farid Vakili-Tahami

Static and Dynamic WPLI on Stressful Scenarios: an EEG Study

Nasrin Dehghani - Negin Joghataei - Zahra Ghanbari - Mohammad Hassan Moradi

Natural Language Processing and Speech Processing Integration: Toward A Point-of-Care Framework for Early Detection of Alzheimer’s Disease

Aslan Modir - Fatemeh Shalchizadeh - Armin Ghasimi - Sina Shamekhi

TransFuse++: A Hybrid CNN-Transformer Architecture with Cross-Attention, Temporal Modeling, and Uncertainty Estimation for Medical Image Segmentation

Masoud Noroozi - Sayna Jamaati - Hamed Aghapanah - Ali Saeeidi Rad - Mahsa Asadi Anar - Ali Darzi - Mahla Shokouhfar - Helia Sadat Kazemi - Mohammadreza Ghahari - Mohammad Saeed Soleimani Meigoli - Jafar Majidpour - Hossein Arabi - Ali Reza Karimian

Dynamic Modeling of a Cable-Driven Series Elastic Upper Extremity Exoskeleton for Post-Stroke Rehabilitation

Ali Selk Ghafari - Omid Kalantari

بررسی رابطه مدیریت سرمایه در گردش با عملکرد مالی در بورس اوراق بهادار تهران

علی مبارکی

Functionally Graded Material Vertebroplasty Screws: A Finite Element Biomechanical Study

Maryam Rahimi - Mohammad Hosein Zadeh-Posti - َAisan Rafiei - Nima Jamshidi

مکان یابی ایستگاه‌های آتش‌نشانی با استفاده از الگوریتم بهینه‌سازی ازدحام ذرات

مهدی عزیزمحمدی - سید محسن میرحسینی - آرش شعبانی

Goniometry and Electromyography Data Analysis for Knee Health Diagnosis using Machine Learning

Mohammad-Reza Sayyed Noorani - Zahra Mahmoudi Anzabi - Sara Sharifi

نقش یادگیری عمیق در توسعه هوش مصنوعی و کاربردهای آن در صنعت، تجارت و زنجیره تأمین

آیدا مهرنیا

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.2