U-Net جدید با ترکیب ویژگی های چند جریانی
ترجمه نشده

U-Net جدید با ترکیب ویژگی های چند جریانی

عنوان فارسی مقاله: M-Net: یک U-Net جدید با ترکیب ویژگی های چند جریانی و حلقه های متسع چند مقیاسی برای تقسیم بندی مجاری صفرا و سنگ کبد
عنوان انگلیسی مقاله: M-Net: A Novel U-Net With Multi-Stream Feature Fusion and Multi-Scale Dilated Convolutions for Bile Ducts and Hepatolith Segmentation
مجله/کنفرانس: دسترسی – IEEE Access
رشته های تحصیلی مرتبط: مهندسی پزشکی
گرایش های تحصیلی مرتبط: بیوالکتریک
کلمات کلیدی فارسی: تقسیم بندی مجاری صفرا و سنگ کبد، U-Net، حلقه های متسع چند مقیاسی، ترکیب ویژگی های چند جریانی، عملکرد از دست دادن راه انداز آنلاین، آنتروپی متقاطع
کلمات کلیدی انگلیسی: Segmentation of bile ducts and hepatolith, U-Net, multi-scale dilated convolution, multistream feature fusion, online bootstrapped loss function, cross entropy
نوع نگارش مقاله: مقاله پژوهشی (Research Article)
شناسه دیجیتال (DOI): https://doi.org/10.1109/ACCESS.2019.2946582
دانشگاه: School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China
صفحات مقاله انگلیسی: 13
ناشر: آی تریپل ای - IEEE
نوع ارائه مقاله: ژورنال
نوع مقاله: ISI
سال انتشار مقاله: 2019
ایمپکت فاکتور: 4.641 در سال 2018
شاخص H_index: 56 در سال 2019
شاخص SJR: 0.609 در سال 2018
شناسه ISSN: 2169-3536
شاخص Quartile (چارک): Q2 در سال 2018
فرمت مقاله انگلیسی: PDF
وضعیت ترجمه: ترجمه نشده است
قیمت مقاله انگلیسی: رایگان
آیا این مقاله بیس است: خیر
آیا این مقاله مدل مفهومی دارد: ندارد
آیا این مقاله پرسشنامه دارد: ندارد
آیا این مقاله متغیر دارد: ندارد
کد محصول: E13860
رفرنس: دارای رفرنس در داخل متن و انتهای مقاله
فهرست مطالب (انگلیسی)

ABSTRACT

I. INTRODUCTION

II. METHODS

III. EXPERIMENTAL RESULT

IV. DISCUSSION

V. CONCLUSION

REFERENCES

بخشی از مقاله (انگلیسی)

ABSTRACT

Automatically segmenting bile ducts and hepatolith in abdominal CT scans is helpful to assist hepatobiliary surgeons for minimally invasive surgery. High-deformation characteristics of bile ducts and small-size characteristics of hepatolith make this segmentation task challenging. To the best of our knowledge, we make the first attempt to simultaneously segment bile ducts and hepatolith in this paper. Inspired by U-Net, a novel two-dimensional end-to-end fully convolutional network named M-Net is designed to implement this segmentation task. The M-Net is composed of four streams involving two encoder-decoder processes. Multi-scale dilated convolutions are designed to extract abundant semantic features and multi-scale context information at different scales. To make full advantages of multi-scale feature maps, a multi-stream feature fusion strategy is proposed to transfer the most abundant semantic features produced in the first stream to the other streams. To further improve the segmentation performance, a novel loss function is defined to focus the M-Net on hard pixels (difficultly distinguished) in the edges of bile ducts and hepatolith, which is based on the online bootstrapped method and cross entropy. By discarding pixels (easy to distinguish) with higher probability of class, the decline of loss is focused on hard pixels so that the training become more efficient and directional. Experimental results indicate that our proposed M-Net is superior to the state-of-the-art deep-learning methods for simultaneously segmenting bile ducts and hepatolith in the abdominal CT scans. The M-Net can simultaneously segment bile ducts and hepatolith in abdominal CT scans at a high performance with 98.678% Recall, 84.427% Precision, 89.831% DICE and 90.998% F1-score for bile ducts, and 99.894% Recall, 55.132% Precision, 71.248% DICE and 71.051% F1-score for hepatolith.

INTRODUCTION

Hepatobiliary stone disease is one of the most common surgical conditions in the world, especially in Asia [1]. At present, minimally invasive surgery for hepatolith removal is the dominate surgical method for the treatment of hepatolithiasis. Bile ducts and hepatolith should be well positioned in CT scans for preoperative plans so that hepatobiliary surgeons can make accurate surgical plans. This task should be cautiously done by the experienced hepatobiliary surgeons to achieve successful minimally invasive surgery. If an automatic segmentation method for bile ducts and hepatolith is designed, it will assist hepatobiliary surgeons to obtain accurate positions of bile ducts and hepatolith in CT scans so that they can achieve more intuitive judgments to improve the success rate of surgery. Fig. 1 illustrates an automatic segmentation example for bile ducts and hepatolith in abdominal CT scans. Bile ducts and hepatolith should be simultaneously and automatically segmented from the input original CT image. Here, bile ducts are marked with the red region, and the hepatolith is marked with the green region.