《電子技術(shù)應用》
您所在的位置:首頁 > 人工智能 > 設(shè)計應用 > 基于多尺度注意力融合網(wǎng)絡(luò)的胃癌病理圖像分割方法*
基于多尺度注意力融合網(wǎng)絡(luò)的胃癌病理圖像分割方法*
電子技術(shù)應用
張婷1,秦涵書1,趙若璇2
(1.重慶醫(yī)科大學附屬第一醫(yī)院 信息中心,重慶 400016;2.重慶大學 光電技術(shù)與系統(tǒng)教育部重點實驗室,重慶 400044)
摘要: 近年來,隨著深度學習技術(shù)的發(fā)展,基于編解碼的圖像分割方法在病理圖像自動化分析上的研究與應用也逐漸廣泛,但由于胃癌病灶復雜多變、尺度變化大,加上數(shù)字化染色圖像時易導致的邊界模糊,目前僅從單一尺度設(shè)計的分割算法往往無法獲得更精準的病灶邊界。為優(yōu)化胃癌病灶圖像分割準確度,基于編解碼網(wǎng)絡(luò)結(jié)構(gòu),提出一種基于多尺度注意力融合網(wǎng)絡(luò)的胃癌病灶圖像分割算法。編碼結(jié)構(gòu)以EfficientNet作為特征提取器,在解碼器中通過對多路徑不同層級的特征進行提取和融合,實現(xiàn)了網(wǎng)絡(luò)的深監(jiān)督,在輸出時采用空間和通道注意力對多尺度的特征圖進行注意力篩選,同時在訓練過程中應用綜合損失函數(shù)來優(yōu)化模型。實驗結(jié)果表明,該方法在SEED數(shù)據(jù)集上Dice系數(shù)得分達到0.806 9,相比FCN和UNet系列網(wǎng)絡(luò)一定程度上實現(xiàn)了更精細化的胃癌病灶分割。
中圖分類號:TP391 文獻標志碼:A DOI: 10.16157/j.issn.0258-7998.233934
中文引用格式: 張婷,秦涵書,趙若璇. 基于多尺度注意力融合網(wǎng)絡(luò)的胃癌病理圖像分割方法[J]. 電子技術(shù)應用,2023,49(9):46-52.
英文引用格式: Zhang Ting,Qin Hanshu,Zhao Ruoxuan. Gastric cancer pathological image segmentation method based on multi-scale attention fusion network[J]. Application of Electronic Technique,2023,49(9):46-52.
Gastric cancer pathological image segmentation method based on multi-scale attention fusion network
Zhang Ting1,Qin Hanshu1,Zhao Ruoxuan2
(1.Information Center, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China; 2.Key Laboratory of Optoelectronic Technique System of the Ministry of Education, Chongqing University, Chongqing 400044,China)
Abstract: In recent years, with the development of deep learning technology, the research and application of image segmentation methods based on coding and decoding in the automatic analysis of pathological images have gradually become widespread. However, due to the complexity and variability of gastric cancer lesions, large scale changes, and the blurring of boundaries caused by digital staining images, segmentation algorithms designed solely from a single scale often cannot obtain more accurate lesion boundaries. To optimize the accuracy of gastric cancer lesion image segmentation, this paper proposes a gastric cancer image segmentation algorithm based on multi-scale attention fusion network using the coding and decoding network structure. The coding structure uses EfficientNet as the feature extractor. In the decoder, the deep supervision of the network is realized by extracting and fusing the features of different levels of multi-path. When outputting, the spatial and channel attention is used to screen the multi-scale feature map for attention. At the same time, the integrated loss function is used in the training process to optimize the model.The experimental results show that the Dice coefficient score of this method on the SEED data set is 0.806 9, which to some extent achieves more refined gastric cancer lesion segmentation compared to FCN and UNet series networks.
Key words : pathological image;image segmentation;attention fusion

0 引言

胃癌是全球第5位的常見癌癥和第4位的癌癥死亡原因[1],臨床上目前主要根據(jù)胃鏡活檢和醫(yī)生人工經(jīng)驗來判斷切片病灶發(fā)展情況。臨床人工病理篩查需要花費專業(yè)病理醫(yī)生大量的時間,且由于臨床經(jīng)驗的差異和醫(yī)療資源的限制,也存在一定的漏診和誤診比率。近年來,隨著深度學習在計算機視覺領(lǐng)域的成功應用,計算機輔助檢測在醫(yī)學上的應用也越來越廣泛。

基于深度學習的醫(yī)用圖像分割方法可以有效提取病灶目標區(qū)域,輔助醫(yī)生決策,提升診斷效率和準確性。這些方法主要包括基于經(jīng)典的全卷積神經(jīng)網(wǎng)絡(luò)(Fully Convolution Networks ,FCN),以及UNet、UNet++系列和DeepLab系列等基于編解碼的分割網(wǎng)絡(luò)[2-7]。常用的基于編解碼的病理圖像分割網(wǎng)絡(luò)基本流程如圖1所示。以胃癌病灶圖像為例,首先輸入獲取的病理圖像,經(jīng)過圖像預處理(預處理階段一般包括圖像增強和圖像增廣等),之后送到編碼解碼網(wǎng)絡(luò),進行圖像特征提取和圖像恢復,對于網(wǎng)絡(luò)直接預測的分割結(jié)果可適當增加部分后處理操作,包括形態(tài)學后處理等降噪方式來提升分割結(jié)果的精確性。其中特征提取網(wǎng)絡(luò)主要由卷積層、下采樣模塊和激活函數(shù)等組成,圖像恢復模塊是對特征提取后的特征圖進行重點區(qū)域捕捉定位和大小恢復,得到與輸入大小相對應的輸出圖像,主要包括上采樣模塊、特征融合模塊和激活函數(shù)。最后輸出經(jīng)過反向傳播計算預測結(jié)果與標注值之間的誤差,通過梯度下降設(shè)置合適的學習率迭代訓練,得到損失函數(shù)極小值以優(yōu)化預測結(jié)果。



本文詳細內(nèi)容請下載:http://ihrv.cn/resource/share/2000005636




作者信息:

張婷1,秦涵書1,趙若璇2

(1.重慶醫(yī)科大學附屬第一醫(yī)院 信息中心,重慶 400016;2.重慶大學 光電技術(shù)與系統(tǒng)教育部重點實驗室,重慶 400044)

微信圖片_20210517164139.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。