CT Images Segmentation of Lungs with COVID-۱۹ Infection Using Mask R-CNN

سال انتشار: 1400
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 388

فایل این مقاله در 9 صفحه با فرمت PDF قابل دریافت می باشد

این مقاله در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

AREEI02_003

تاریخ نمایه سازی: 6 تیر 1401

چکیده مقاله:

The coronavirus (COVID-۲۰۱۹) pandemic has caused a catastrophic effect on health and global economy. The most common standard for confirming the virus relies on RT-PCR tests. As a complement to RT-PCR, Computed tomography (CT) can be used for diagnosing COVID-۱۹. We describe the R-CNN (area-based torsional neural network) approach to segmentation of CT images of the lungs of people with COVID-۱۹ using a variety of augmentation methods. The class imbalance problem leads to inefficient training, which makes model degenerated. In this paper, we have used a method based on Mask R-CNN to segment Left lung, right lung, Covid-۱۹ infection. In our model, the Focal Loss function is used to suppress well-classified examples.The model is tested on COVID-۱۹-CT-Seg-۲۰cases dataset and the results showed that the accuracy reaches ۸۷.۹۳%. Compared with the smooth loss function in Mask R-CNN it improves by ۵%. Therefore, this model will aid health professionals to fasten the screening and validation of the initial assessment towards COVID-۱۹ patients.

نویسندگان

Pariya Ghasemifard

School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran

Mehran Yazdi

School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran

Alireza Zolghadrasli

School of Electrical and Computer Engineering, Shiraz University, Shiraz, Iran