浏览全部资源
扫码关注微信
Received：20 June 2023，
Revised：2023-09-22，
Published：16 March 2024
移动端阅览
目的
2
前列腺图像精确分割对评估患者健康和制定治疗方案至关重要。然而传统U-Net模型在前列腺MR（magnetic resonance）图像分割上存在过拟合、边缘信息丢失等问题。针对上述问题，提出一种改进的U-Net 2D分割模型，旨在增强边缘信息、降低噪声影响，进而提高前列腺分割效果。
方法
2
为缓解过拟合现象，新模型通过对标准U-Net架构进行修改，将普通卷积替换为深度可分离卷积，重新设计编码器和解码器结构，降低模型参数量；为保存分割结果中的边缘信息，新模型通过ECA（efficient channel attention ）注意力机制对U-Net解码器特征进行优化，以放大并保存小尺度目标的信息，并提出边缘信息模块和边缘信息金字塔模块，恢复并增强边缘信息，以缓解频繁下采样带来的边缘信息衰退以及编码器和解码器特征之间的语义差距问题；利用空洞空间金字塔池化（atrous spatial pyramid pooling，ASPP）模块对特征进行重采样，扩大感受野，以消除特征噪声。
结果
2
在PROMISE12（prostate MR image segmentation 2012）数据集上验证模型的有效性，并与6种基于U-Net的图像分割方法进行对比，实验证明其分割结果在Dice系数（Dice coefficient，DC）、HD95（95% Hausdorff distance）、召回率（recall）、Jaccard系数和准确度（accuracy）等指标上均有提高，DC较U-Net提高了8.87%，HD95较U-Net++和Attention U-Net分别降低了12.04 mm和3.03 mm。
结论
2
提出一种基于边缘信息增强的前列腺MR图像分割网络（attention mechanism and marginal information fusion U-Net，AIM-U-Net），其生成的分割图像具有丰富的边缘信息和空间信息，其主观效果和客观评价指标均优于其他同类方法，为提高临床诊断的准确度提供帮助。
Objective
2
Prostate cancer， which is an epithelial malignancy that occurs in the prostate， is one of the most common malignant diseases. Early detection of potentially cancerous prostate is important to reduce the prostate cancer mortality. Magnetic resonance imaging （MRI） is one of the most commonly used imaging methods for detecting prostate in clinical practice and commonly used for the detection， localization， and segmentation of prostate cancer. Formulating suitable medical plans for patients and postoperative record is important. In computer-aided diagnosis， extracting the prostate region from the image and further calculating the corresponding characteristics are often necessary for physiological analysis and pathological research to assist clinicians in making accurate judgments. The current methods of MRI prostate segmentation can be divided into two categories： traditional and deep-learning-based methods. The traditional segmentation method is based on the analysis of the features extracted from the image with knowledge of image processing. The effect of this kind of method depends on the performance of the extracted features， and this method sometimes requires manual interaction. In recent years， deep learning technology has been widely applied to image segmentation with the continuous development of computer technology. Unlike visible light images， medical images have special characteristics： large grayscale range， unclear boundaries， and the human organs have a relatively stable distribution in the human body. Considering these characteristics of medical images， a fully convolution-based U-Net was first proposed in 2015， which is a neural network model for solving the problem of medical image segmentation. Compared with other networks， U-Net has obvious advantages for medical image segmentation， but it still has some weaknesses that must be overcome. On the one hand， the dataset of medical images is not huge， but the traditional U-Net model has numerous parameters， which can easily lead to network overfitting. On the other hand， during feature extraction， the edge information of the image is lost. Furthermore， the small-scale information of the target object is difficult to save. The feature map obtained by U-Net’s skip connections usually contains noise， resulting in low model segmentation accuracy. To solve the above problems， this paper proposes an improved U-Net 2D prostate segmentation model， that is， AIM-U-Net， which can enhance the edge information between tissues and organs. AIM-U-Net can also reduce the influence of image noise， thereby improving the effect of prostate segmentation.
Method
2
To solve the overfitting problem， we redesign the encoder and decoder structure of the original U-Net， and the ordinary convolution is replaced with deep separable convolution. Deep separable convolution can effectively reduce the number of parameters in the network， thereby improving the computational efficiency， generalization ability， and accuracy of the model. In addition， we optimize the decoder features through the efficient channel attention module to amplify and retain information on small-scale targets. Moreover， edge information can provide fine-grained constraints to guide the feature extraction during segmentation. The features of shallow coding units retain sufficient edge information due to their high resolution， while the features extracted by the deep coding unit capture global feature information. Therefore， we designed the edge information module （EIM） to integrate the shallow features of the encoder and the high-level semantic information to obtain and enhance the edge information. Therefore， the obtained feature map has rich edge information and advanced semantic information. The EIM has two main functions. First， it can provide edge information and guide the segmentation process in the decoding path. Second， the edge detection loss of early convolutional layers is supervised by adopting a deep supervision mechanism. Moreover， the features extracted from different modules have their own advantage. The features of the deep coding unit can capture the global high-level discriminant feature information of the prostate， which is extremely helpful for the segmentation of small lesions. The multi-scale feature of the decoding unit has rich spatial semantic information， which can improve the accuracy of segmentation. The fusion information obtained by the EIM has rich edge information and advanced semantic information. Therefore， we design an edge information pyramid module （EIPM）， which comprehensively uses the above different information by fusing the edge information， the deep features of the coding unit， and the multi-scale features of the decoding unit， so that the segmentation model can understand the image more comprehensively and improve the accuracy and robustness of segmentation. The EIPM can guide the segmentation process in the decoding path by fusing multi-scale information and can supervise the region segmentation loss of the decoder’s convolutional layer using the deep supervision mechanism. In the neural network segmentation task， the feature map obtained by feature fusion usually contains noise， decreasing the segmentation accuracy. To solve this problem， we use the atrous spatial pyramid pooling （ASPP） to process the enhanced edge feature map obtained by the EIPM， and the obtained multi-scale features are concatenated. ASPP resamples the fusion feature map through dilation convolution with different dilation rates， which can capture multi-scale context information， eliminate the noise of multi-scale features， and obtain a more accurate prostate representation. Hence， the segmentation result is obtained by 1 × 1 convolution with one output channels， whose dimension is the same as that of the input image. Finally， to accelerate the convergence speed of the network， we design a deep supervision mechanism to improve the convergence speed of the model and realize deep supervision mechanism through 1 × 1 convolution and activation function. Regarding the loss function of the whole model， we used a hybrid function of Dice loss and cross entropy loss. The total loss of the model includes the final segmentation loss， the edge segmentation loss， and the four region segmentation losses.
Result
2
We use the PROMISE12 dataset to verify the effectiveness of the model and compare the result with those of six other medical image segmentation methods based on U-Net. The experimental results show that the segmented images are remarkably improved in Dice coefficient （DC）， 95% Hausdorff distance （HD95）， recall， Jaccard coefficient （Jac）， and accuracy. The DC is 8.87% higher than that of U-Net， and the HD95 value is 12.04 mm and 3.03 mm lower than those of U-Net++ and Attention U-Net， respectively.
Conclusion
2
The edge of the segmented prostate is more refined using our proposed AIM-U-Net than that using other methods. AIM-U-Net can extract more edge details of the prostate by utilizing the EIM and the EIPM and effectively suppress similar background information and the noise surrounding the prostate.
Alom M Z ， Hasan M ， Yakopcic T M ， Taha T M and Asari V K . 2018 . Recurrent residual convolutional neural network based on U-Net （R2U-Net） for medical image segmentation ［EB/OL］.［ 2023-06-05 ］. https://arxiv.org/pdf/1802.06955.pdf https://arxiv.org/pdf/1802.06955.pdf
Asadi aghbolaghi M ， Azad R ， Fathy M and Escalera S . 2020 . Multi-level context gating of embedded collective knowledge for medical image segmentation ［EB/OL］. ［ 2023-06-05 ］. http://arxiv.org/pdf/2003.05056.pdf http://arxiv.org/pdf/2003.05056.pdf
Badrinarayanan V ， Kendall A and Cipolla R . 2017 . SegNet： a deep convolutional encoder-decoder architecture for image segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 39 （ 12 ）： 2481 - 2495 ［ DOI： 10.1109/TPAMI.2016.2644615 http://dx.doi.org/10.1109/TPAMI.2016.2644615 ］
Chen L C ， Papandreou G ， Schroff F and Adam J . 2017 . Rethinking Atrous convolution for semantic image segmentation ［EB/OL］. ［ 2023-06-05 ］. http://arxiv.org/pdf/1706.05587.pdf http://arxiv.org/pdf/1706.05587.pdf
Chollet F . 2017 . Xception： deep learning with depthwise separable convolutions // Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu， USA ： IEEE： 1800 - 1807 ［ DOI： 10.1109/CVPR.2017.195 http://dx.doi.org/10.1109/CVPR.2017.195 ］
Çiçek Ö ， Abdulkadir A ， Lienkamp S S ， Brox T and Ronneberger O . 2016 . 3D U-Net： learning dense volumetric segmentation from sparse annotation // Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention . Athens， Greece ： Springer： 424 - 432 ［ DOI： 10.1007/978-3-319-46723-8_49 http://dx.doi.org/10.1007/978-3-319-46723-8_49 ］
Fu Y L ， Gao W P and Wang S G . 2005 . Study of segmentation algorithm of brain MRI based on K-nearest neighbour rule with threshold segmentation . Journal of Medical Imaging ， 15 （ 8 ）： 644 - 647
付宜利 ， 高文朋 ， 王树国 . 2005 . 基于阈值分割的K-最近邻规则的磁共振脑图像分割算法的研究 . 医学影像学杂志 ， 15 （ 8 ）： 644 - 647 ［ DOI： 10.3969/j.issn.1006-9011.2005.08.006 http://dx.doi.org/10.3969/j.issn.1006-9011.2005.08.006 ］
Huang H Y ， Qi F H and Zhao X C . 2000 . Active contour model based on multi-scale image analysis . Journal of Computer Research and Development ， （ 10 ）： 1240 - 1245
黄海赟 ， 戚飞虎 ， 赵雪春 . 2000 . 基于多尺度图像的主动轮廓线模型 . 计算机研究与发展 ， （ 10 ）： 1240 - 1245
Leng Y Y . 2022 . Method of image processing based on Gaussian mixture model . Modern Information Technology ， 6 （ 19 ）： 57 - 60
冷月妍 . 2022 . 基于高斯混合模型的图像处理方法 . 现代信息科技 ， 6 （ 19 ）： 57 - 60 ［ DOI： 10.19850/j.cnki.2096-4706.2022.19.014 http://dx.doi.org/10.19850/j.cnki.2096-4706.2022.19.014 ］
Li Y C ， Lin C ， Zhang Y ， Feng S L ， Huang M X and Bai Z M . 2023 . Automatic segmentation of prostate MRI based on 3D pyramid pooling UNet . Medical Physics ， 50 （ 2 ）： 906 - 921 ［ DOI： 10.1002/mp.15895 http://dx.doi.org/10.1002/mp.15895 ］
Litjens G ， Toth R ， Van de Ven W ， Hoeks C ， Kerkstra S ， van Ginneken B ， Vincent G ， Guillard G ， Birbeck N ， Zhang J D ， Strand R ， Malmberg F ， Ou Y M ， Davatzikos C ， Kirschner M ， Jung F ， Yuan J ， Qiu W ， Gao Q Q ， Edwards P ， Maan B ， van der Heijden F ， Ghose S ， Mitra J ， Dowling J ， Barratt D ， Huisman H and Madabhushi A . 2014 . Evaluation of prostate segmentation algorithms for MRI： the PROMISE12 challenge . Medical Image Analysis ， 18 （ 2 ）： 359 - 373 ［ DOI： 10.1016/j.media.2013.12.002 http://dx.doi.org/10.1016/j.media.2013.12.002 ］
Liu D ， Wang L ， Du Y ， Cong M and Li Y Y . 2022 . 3-D prostate MR and TRUS images detection and segmentation for puncture biopsy . IEEE Transactions on Instrumentation and Measurement ， 71 ： # 5016613 ［ DOI： 10.1109/TIM.2022.3192292 http://dx.doi.org/10.1109/TIM.2022.3192292 ］
Luo J C ， Wang Q M ， Ma J H ， Zhou C H and Liang Y . 2002 . The EM-based maximum likelihood classifier for remotely sensed data . Acta Geodaetica et Cartographica Sinica ， 31 （ 3 ）： 234 - 239
骆剑承 ， 王钦敏 ， 马江洪 ， 周成虎 ， 梁怡 . 2002 . 遥感图像最大似然分类方法的EM改进算法 . 测绘学报 ， 31 （ 3 ）： 234 - 239 ［ DOI： 10.3321/j.issn：1001-1595.2002.03.010 http://dx.doi.org/10.3321/j.issn：1001-1595.2002.03.010 ］
Minaee S ， Boykov Y ， Porikli F ， Plaza A ， Kehtarnavaz N and Terzopoulos D . 2022 . Image segmentation using deep learning： a survey . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 44 （ 7 ）： 3523 - 3542 ［ DOI： 10.1109/TPAMI.2021.3059968 http://dx.doi.org/10.1109/TPAMI.2021.3059968 ］
Nguyen T C ， Nguyen T P ， Diep G H ， Tran-Dinh A H ， Nguyen T V and Tran M V . 2021 . CCBANet： cascading context and balancing attention for polyp segmentation // Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention . Strasbourg， France ： Springer International Publishing： 633 - 643 ［ DOI： 10.1007/978-3-030-87193-2_60 http://dx.doi.org/10.1007/978-3-030-87193-2_60 ］
Oktay O ， Schlemper J ， Le Folgoc L ， Lee M ， Heinrich M ， Misawa K ， Mori K ， McDonagh S ， Hammerla K ， Kainz B ， Glocker B and Rueckert D . 2018 . Attention U-Net： learning where to look for the pancreas ［EB/OL］. ［ 2023-06-05 ］. http://arxiv.org/pdf/1804.03999.pdf http://arxiv.org/pdf/1804.03999.pdf
Ronneberger O ， Fischer P and Brox T . 2015 . U-Net： convolutional networks for biomedical image segmentation // Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention . Munich， Germany ： Springer ［ DOI： 10.1007/978-3-319-24574-4_28 http://dx.doi.org/10.1007/978-3-319-24574-4_28 ］
Song J H ， Chen X J ， Zhu Q L ， Shi F ， Xiang D H ， Chen Z Y ， Fan Y ， Pan L J and Zhu W F . 2022 . Global and local feature reconstruction for medical image segmentation . IEEE Transactions on Medical Imaging ， 41 （ 9 ）： 2273 - 2284 ［ DOI： 10.1109/TMI.2022.3162111 http://dx.doi.org/10.1109/TMI.2022.3162111 ］
Sun J K ， Zhang R ， Guo L J and Wang J H . 2023 . Multi-scale feature fusion and additive attention guide brain tumor MR image segmentation . Journal of Image and Graphics ， 28 （ 4 ）： 1157 - 1172
孙家阔 ， 张荣 ， 郭立君 ， 汪建华 . 2023 . 多尺度特征融合与加性注意力指导脑肿瘤MR图像分割 . 中国图象图形学报 ， 28 （ 4 ）： 1157 - 1172 ［ DOI： 10.11834/jig.211073 http://dx.doi.org/10.11834/jig.211073 ］
Wang Q L ， Wu B G ， Zhu P F ， Li P H ， Zuo W M and Hu Q H . 2020 . ECA-Net： efficient channel attention for deep convolutional neural networks // Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle， USA ： IEEE： 11534 - 11542 ［ DOI： 10.1109/CVPR42600.2020.01155 http://dx.doi.org/10.1109/CVPR42600.2020.01155 ］
Yin P S ， Yuan R ， Cheng Y M and Wu Q Y . 2020 . Deep guidance network for biomedical image segmentation . IEEE Access ， 8 ： 116106 - 116116 ［ DOI： 10.1109/ACCESS.2020.3002835 http://dx.doi.org/10.1109/ACCESS.2020.3002835 ］
Yu D ， Peng Y J and Guo Y F . 2023 . Ultrasonic image segmentation of thyroid nodules-relevant multi-scale feature based h-shape network . Journal of Image and Graphics ， 28 （ 7 ）： 2195 - 2207
于典 ， 彭延军 ， 郭燕飞 . 2023 . 面向甲状腺结节超声图像分割的多尺度特征融合“h”形网络 . 中国图象图形学报 ， 28 （ 7 ）： 2195 - 2207 ［ DOI： 10.11834/jig.220078 http://dx.doi.org/10.11834/jig.220078 ］
Zhang Z J ， Fu H Z ， Dai H ， Shen J B ， Pang Y W and Shao L . 2019 . ET-Net： a generic edge-attention guidance network for medical image segmentation // Proceedings of the 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention . Shenzhen， China ： Springer： 442 - 450 ［ DOI： 10.1007/978-3-030-32239-7_49 http://dx.doi.org/10.1007/978-3-030-32239-7_49 ］
Zhao X Q ， Zhang L H and Lu H C . 2021 . Automatic polyp segmentation via multi-scale subtraction network // Proceedings of the 24th International Conference on Medical Image Computing and Computer-Assisted Intervention . Strasbourg， France ： Springer： 120 - 130 ［ DOI： 10.1007/978-3-030-87193-2_12 http://dx.doi.org/10.1007/978-3-030-87193-2_12 ］
Zhong X Y . 2020 . Research of Medical Image Object Detection and Sematic Segmentation Based on Deep Learning . Hangzhou ： Zhejiang University of Technology
钟幸宇 . 2020 . 基于深度学习的医学图像目标检测与语义分割研究 . 杭州 ： 浙江工业大学 ［ DOI： 10.27463/d.cnki.gzgyu.2020.000994 http://dx.doi.org/10.27463/d.cnki.gzgyu.2020.000994 ］
Zhou Z W ， Siddiquee M M R ， Tajbakhsh N and Liang J M . 2018 . UNet++： a nested U-Net architecture for medical image segmentation // Proceedings of the 4th International Workshop ， and 8th International Workshop Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. Granada， Spain ： Springer： 3 - 11 ［ DOI： 10.1007/978-3-030-00889-5_1 http://dx.doi.org/10.1007/978-3-030-00889-5_1 ］
Zuo Q ， Chen S Y and Wang Z F . 2021 . R2AU-Net： attention recurrent residual convolutional neural network for multimodal medical image segmentation . Security and Communication Networks ， 2021 ： # 6625688 ［ DOI： 10.1155/2021/6625688 http://dx.doi.org/10.1155/2021/6625688 ］
相关文章
相关作者
相关机构
京公网安备11010802024621
