浏览全部资源
扫码关注微信
纸质出版日期： 2024-10-16 ，
移动端阅览
丁维龙， 廖婉茵， 朱伟， 汪春年， 祝行琴， 朱红波. 2024. 低倍率病理全切片图像伪影检测. 中国图象图形学报， 29(10):3157-3170
Ding Weilong， Liao Wanyin， Zhu Wei， Wang Chunnian， Zhu Xingqin， Zhu Hongbo. 2024. Artifact detection of low-magnification pathology whole-slide images. Journal of Image and Graphics， 29(10):3157-3170
目的
2
高质量的病理切片对人工诊断和计算机辅助诊断至关重要。当前基于图像块的伪影检测方法存在着计算资源消耗巨大以及伪影检测过程的完整性缺失问题。为此，本文提出了一种适用于低倍率病理全切片图像的伪影检测算法WRC_Net（window-row-col_net）。
方法
2
首先，将低倍率的全切片图像输入到ResNet50（residual neural network）网络中，以提取图像的低级特征。随后，这些低级特征被传入特征融合模块，用于聚合来自不同深度和方向的特征。此外，在特征提取模块中，引入了WRC模块，包括WRC注意力和多尺度扩张模块，其能够同时捕捉全局和局部信息，提取多尺度特征，从而增强了特征的表达能力。最后，将融合后的特征传入单一检测头，以获取最终的检测结果。
结果
2
在SPDPSD（Shanghai Pudong department of pathology slide dataset）和NCPDCSD（Ningbo clinical pathology diagnosis center slide dataset）两个数据集上，所提方法的平均精度（mean average precision，mAP）分别达到了63.1%和55.0%，与目前主流的目标检测算法相比具有一定竞争力。
结论
2
本文提出的病理切片伪影检测算法能够准确识别数字病理切片中的不同种类伪影，为病理图像质量评估提供了一种有效的技术解决方案。
Objective
2
High-quality pathological slides are crucial for manual diagnosis and computer-aided diagnosis. However， pathology slides may contain artifacts that can affect their quality and consequently influence expert diagnostic judgment. Currently， the assessment of pathology slide quality often depends on manual sampling， which is time consuming and cannot encompass all slides. Additionally， despite relatively standardized detection criteria across different institutions， different quality control personnel may have varying interpretations， leading to subjective differences. These limitations restrict the traditional quality control process. Current methods typically involve analyzing image patches cropped at high magnifications， resulting in considerable consumption of computational resources. Moreover， certain artifacts， such as hole and tremor， often have larger dimensions and are better suited for learning on low-resolution images. However， cropping image blocks at high magnifications may exclude artifacts that coexist in tissue and background regions， such as ink and bubble， which compromise the integrity of artifact detection and analysis. To tackle these challenges， the process of assessing the quality of pathology slides must be digitized to enhance efficiency and accuracy. Therefore， this study introduces a novel algorithm， Window-Row-Col_Net （WRC_Net）， designed for the detection of artifacts in digital pathology slides， specifically tailored for low-magnification pathological whole slide images.
Method
2
This study primarily consists of four components： pathological slide preprocessing， feature extraction module， feature fusion module， and single detection head. First， we tackle the problem of artifacts in pathological slides by performing preprocessing， which involves transforming the tissue pathological slides into lower-pixel-resolution versions of whole-slide images （thumbnails）. This step helps reduce computational resource consumption and is well-suited for addressing larger-sized artifacts， such as holes and wrinkles. Afterward， these thumbnails are input into the feature extraction network to acquire the low-level feature representation of the slides. Moreover， to integrate effectively feature information from different levels， we devised a feature fusion module. This module plays a crucial role in the entire model， facilitating the aggregation of features from varying depths and directions. Additionally， we introduce the Window-Row-Col （WRC） module， which encompasses two vital components： the WRC attention module and the multiscale dilated module （MSDM）. The WRC attention module dynamically aggregates features within square windows， spanning horizontal and vertical directions， capturing global and local contextual information， and establishing long-range dependencies. The MSDM incorporates dilated convolutions with varying dilation rates to extract multiscale information and enhance the model's perception of artifacts of different sizes. Through this feature fusion， we boost the expressive capability of features， thus giving the model with a competitive advantage in object detection tasks. Finally， the fused features are directed into a single detection head to produce the ultimate detection outcomes. The design of a single detection head structure streamlines the model's architecture， rendering it more succinct and efficient and also diminishing storage and computational burdens， thereby expediting the detection process.
Result
2
We created two new datasets for pathology slide artifacts， known as the Shanghai Pudong Department of Pathology slide dataset （SPDPSD） and the Ningbo Clinical Pathology Diagnosis Center slide dataset （NCPDCSD）. The SPDPSD dataset originates from the Pathology Department of Pudong Hospital in Shanghai and comprises two types of tissue artifacts： ink and bubble. The NCPDCSD dataset is obtained from the Clinical Pathological Diagnosis Center in Ningbo and encompasses six types of tissue artifacts， including hole， tremor， incompleteness， ink， appearance， and bubble. Through comprehensive experiments on these two datasets， we conducted an extensive comparison between our proposed WRC_Net algorithm and the current state-of-the-art object detection methods. The WRC_Net algorithm demonstrated superior detection performance on the SPDPSD dataset， yielding remarkable improvements in metrics， such as mean average precision （mAP）， mAP@IoU = 0.75 （mAP75）， small object mAP （mAPs）， medium object mAP （mAPm）， and large object mAP （mAPl）. Additionally， on the NCPDCSD dataset， our method displayed competitive performance. The results indicate that compared with other methods， WRC_Net achieved remarkable enhancements in multiple performance metrics while maintaining low computational complexity， striking a balance between speed and accuracy.
Conclusion
2
The proposed algorithm for detecting pathology slide artifacts accurately identifies various types of artifacts in digital pathology slides， offering a more comprehensive and dependable quality assessment tool for the domain of medical image analysis. By striking a balance between efficiency and accuracy， our algorithm is anticipated to enhance the pathology diagnosis process and usher in a more efficient and precise workflow within pathology departments.
数字病理学数字病理切片伪影检测多尺度特征融合
digital pathologywhole slide imagesartifact detectionmulti-scalefeature fusion
Babaie M and Tizhoosh H R. 2019. Deep features for tissue-fold detection in histopathology images//Proceedings of the 15th European Congress on Digital Pathology. Warwick， UK： Springer International Publishing： 125-132 ［DOI： 10.1007/978-3-030-23937-4_15http://dx.doi.org/10.1007/978-3-030-23937-4_15］
Bautista P A and Yagi Y. 2010. Improving the visualization and detection of tissue folds in whole slide images through color enhancement. Journal of Pathology Informatics， 1（1）： #25 ［DOI： 10.4103/2153-3539.73320http://dx.doi.org/10.4103/2153-3539.73320］
Bochkovskiy A， Wang C Y and Liao H Y M. 2020. YOLOv4： optimal speed and accuracy of object detection ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/2004.10934.pdfhttps://arxiv.org/pdf/2004.10934.pdf
Deng Y， Feng M， Jiang Y， Zhou Y Y， Qin H Y， Xiang F， Wang Y Z， Bu H and Bao J. 2020. Development of pathological reconstructed high-resolution images using artificial intelligence based on whole slide image. MedComm， 1（3）： 410-417 ［DOI： 10.1002/mco2.39http://dx.doi.org/10.1002/mco2.39］
Dosovitskiy A， Beyer L， Kolesnikov A， Weissenborn D， Zhai X H， Unterthiner T， Dehghani M， Minderer M， Heigold G， Gelly S， Uszkoreit J and Houlsby N. 2021. An image is worth 16 × 16 words： Transformers for image recognition at scale ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/2010.11929.pdfhttps://arxiv.org/pdf/2010.11929.pdf
Everingham M， Van Gool L， Williams C K I， Winn J and Zisserman A. 2010. The Pascal visual object classes （VOC） challenge. International Journal of Computer Vision， 88（2）： 303-338 ［DOI： 10.1007/s11263-009-0275-4http://dx.doi.org/10.1007/s11263-009-0275-4］
Foucart A， Debeir O and Decaestecker C. 2018. Artifact identification in digital pathology from weak and noisy supervision with deep residual networks//Proceedings of the 4th International Conference on Cloud Computing Technologies and Applications. Brussels， Belgium： IEEE： 1-6 ［DOI： 10.1109/CloudTech.2018.8713350http://dx.doi.org/10.1109/CloudTech.2018.8713350］
Ge Z， Liu S T， Wang F， Li Z M and Sun J. YOLOX： exceeding YOLO series in 2021 ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/2107.08430.pdfhttps://arxiv.org/pdf/2107.08430.pdf
He K M， Zhang X Y， Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 770-778 ［DOI： 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90］
Hemmatirad K， Babaie M， Afshari M， Maleki D， Saiadi M and Tizhoosh H R. 2022. Quality control of whole slide images using the YOLO concept//Proceedings of the 10th IEEE International Conference on Healthcare Informatics （ICHI）. Rochester， USA： IEEE： 282-287 ［DOI： 10.1109/ICHI54592.2022.00049http://dx.doi.org/10.1109/ICHI54592.2022.00049］
Ho J， Kalchbrenner N， Weissenborn D and Salimans T. 2019. Axial attention in multidimensional transformers［EB/OL］. ［2023-09-28］. http://arxiv.org/pdf/1912.12180.pdfhttp://arxiv.org/pdf/1912.12180.pdf， 2019-12-20
Hossain M S， Shahriar G M， Syeed M M M， Uddin M F， Hasan M， Hossain M S and Bari R. 2023. Tissue artifact segmentation and severity assessment for automatic analysis using WSI. IEEE Access， 11： 21977-21991 ［DOI： 10.1109/ACCESS.2023.3250556http://dx.doi.org/10.1109/ACCESS.2023.3250556］
Hu J， Shen L and Sun G. 2018. Squeeze-and-excitation networks//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 7132-7141 ［DOI： 10.1109/CVPR.2018.00745http://dx.doi.org/10.1109/CVPR.2018.00745］
Huang G， Liu Z， van der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Honolulu， USA： IEEE： 2261-2269 ［DOI： 10.1109/CVPR.2017.243http://dx.doi.org/10.1109/CVPR.2017.243］
Janowczyk A， Zuo R， Gilmore H， Feldman M and Madabhushi A. 2019. HistoQC： an open-source quality control tool for digital pathology slides. JCO Clinical Cancer Informatics， 3（3）： 1-7 ［DOI： 10.1200/CCI.18.00157http://dx.doi.org/10.1200/CCI.18.00157］
Kanwal N， Pérez-Bueno F， Schmidt A， Engan K and Molina R. 2022. The devil is in the details： whole slide image acquisition and processing for artifacts detection， color variation， and data augmentation： a review. IEEE Access， 10： 58821-58844 ［DOI： 10.1109/ACCESS.2022.3176091http://dx.doi.org/10.1109/ACCESS.2022.3176091］
Kothari S， Phan J H and Wang M D. 2013. Eliminating tissue-fold artifacts in histopathological whole-slide images for improved image-based prediction of cancer grade. Journal of Pathology Informatics， 4（1）： #22 ［DOI： 10.4103/2153-3539.117448http://dx.doi.org/10.4103/2153-3539.117448］
Law H and Deng J. 2018. CornerNet： detecting objects as paired keypoints//Proceedings of the 15th European Conference on Computer Vision. Munich， Germany： Springer： 734-750 ［DOI： 10.1007/978-3-030-01264-9_45http://dx.doi.org/10.1007/978-3-030-01264-9_45］
Law H， Teng Y， Russakovsky O and Deng J. 2020. CornerNet-Lite： efficient keypoint based object detection ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/1904.08900.pdfhttps://arxiv.org/pdf/1904.08900.pdf
Ma N N， Zhang X Y， Zheng H T and Sun J. 2018. ShuffleNet v2： practical guidelines for efficient CNN architecture design//Proceedings of the 15th European Conference on Computer Vision. Munich， Germany： Springer： 122-138 ［DOI： 10.1007/978-3-030-01264-9_8http://dx.doi.org/10.1007/978-3-030-01264-9_8］
Ma X H. 2022. FastestDet： ultra lightweight anchor-free real-time object detection algorithm ［CP/OL］. ［2023-09-28］. https://github.com/dog-qiuqiu/FastestDethttps://github.com/dog-qiuqiu/FastestDet
Maleki D， Afshari M， Babaie M and Tizhoosh H R. 2020. Ink marker segmentation in histopathology images using deep learning//15th International Symposium on Visual Computing. San Diego， USA： Springer： 359-368 ［DOI： 10.1007/978-3-030-64556-4_28http://dx.doi.org/10.1007/978-3-030-64556-4_28］
Noman M， Fiaz M， Cholakkal H， Narayan S， Anwer R M， Khan S and Khan F S. 2023. Remote sensing change detection with transformers trained from scratch ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/2304.06710.pdfhttps://arxiv.org/pdf/2304.06710.pdf
Sandler M， Howard A， Zhu M L， Zhmoginov A and Chen L C. 2018. MobileNetV2： inverted residuals and linear bottlenecks//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City， USA： IEEE： 4510-4520 ［DOI： 10.1109/CVPR.2018.00474http://dx.doi.org/10.1109/CVPR.2018.00474］
Shakarami A， Nicolè L， Terreran M， Tos A P D and Ghidoni S. 2023. TCNN： a transformer convolutional neural network for artifact classification in whole slide images. Biomedical Signal Processing and Control， 84： #104812 ［DOI： https://doi.org/10.1016/j.bspc.2023.104812https://doi.org/10.1016/j.bspc.2023.104812］
Szegedy C， Vanhoucke V， Ioffe S， Shlens J and Wojna Z. 2016. Rethinking the inception architecture for computer vision//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition （CVPR）. Las Vegas， USA： IEEE： 2818-2826 ［DOI： 10.1109/CVPR.2016.308http://dx.doi.org/10.1109/CVPR.2016.308］
Tan M X and Le Q V. 2020. EfficientNet： rethinking model scaling for convolutional neural networks ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/1905.11946.pdfhttps://arxiv.org/pdf/1905.11946.pdf
Tong L， Sha Y and Wang M D. 2019. Improving classification of breast cancer by utilizing the image pyramids of whole-slide imaging and multi-scale convolutional neural networks//Proceedings of the 43rd IEEE Annual Computer Software and Applications Conference （COMPSAC）. Milwaukee， USA： IEEE： 696-703 ［DOI： 10.1109/COMPSAC.2019.00105http://dx.doi.org/10.1109/COMPSAC.2019.00105］
Ultralytics. 2020. Yolov5 ［EB/OL］. ［2023-09-23］. https://github.com/ultralytics/yolov5https://github.com/ultralytics/yolov5
Wang C Y， Bochkovskiy A and Liao H Y M. 2023. YOLOv7： trainable bag-of-freebies sets new state-of-the-art for real-time object detectors//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Vancouver， Canada： IEEE： 7464-7475 ［DOI： 10.1109/CVPR52729.2023.00721http://dx.doi.org/10.1109/CVPR52729.2023.00721］
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 （CVPR）. Seattle， USA： IEEE： 11531-11539 ［DOI： 10.1109/CVPR42600.2020.01155http://dx.doi.org/10.1109/CVPR42600.2020.01155］
Woods A E and Ellis R C. 1994. Laboratory Histopathology： A Complete Reference. Edinburgh： Churchill Livingstone
Yun S， Han D， Chun S， Oh S J， Yoo Y and Choe J. 2019. CutMix： regularization strategy to train strong classifiers with localizable features//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Seoul， Korea （South）： IEEE： 6022-6031 ［DOI： 10.1109/ICCV.2019.00612http://dx.doi.org/10.1109/ICCV.2019.00612］
Zhao Y L， Ding W L， You Q H， Zhu F L， Zhu X J， Zheng K and Liu D D. 2023. Classification of whole slide images of breast histopathology based on spatial correlation characteristics. Journal of Image and Graphics， 28（4）： 1134-1145
赵樱莉， 丁维龙， 游庆华， 朱峰龙， 朱筱婕， 郑魁， 刘丹丹. 2023. 融合空间相关性特征的乳腺组织病理全切片分类. 中国图象图形学报， 28（4）： 1134-1145 ［DOI： 10.11834/jig.211133http://dx.doi.org/10.11834/jig.211133］
Zhou X Y， Koltun V and Krähenbühl P. 2021. Probabilistic two-stage detection ［EB/OL］. ［2023-09-28］. https://arxiv.org/pdf/2103.07461.pdfhttps://arxiv.org/pdf/2103.07461.pdf
相关作者
相关机构
京公网安备11010802024621