浏览全部资源
扫码关注微信
收稿日期：2024-11-13，
修回日期：2025-03-14，
录用日期：2025-03-24，
网络出版日期：2025-03-26，
移动端阅览
目的
2
在组织病理切片制备过程中，不可避免地会产生伪影，可能严重影响病理医生诊断准确性及计算机辅助诊断系统效能。现有伪影分类算法在处理相似伪影时，因缺乏全局分布规律学习能力，导致分类准确度并不理想。为此，本文提出了一种改善病理图像伪影多分类的局部与全局信息交互融合网络MoLiNet（mobile linear net）
方法
2
首先，构建了一个基于HSV颜色域的边缘检测模块以增强对裂缝的关注。然后在双分支架构的基础上，结合门控线性单元（gated linear unit，GLU）与移动倒残差瓶颈卷积模块（mobile inverted bottleneck convolution，MBConv）构建出一种新型前馈层，以自适应地筛选出关键特征，同时提高整体计算效率。此外，还提出了线性聚焦交叉注意力，以对全局特征和局部特征进行充分交互，从而增强特征表达能力。
结果
2
本文提出的网络在分类精度和计算效率方面均超越同类先进方法。在NCPDCSAD（ningbo clinical pathology diagnosis center similar artifact dataset）数据集测试中，我们的模型取得了94.24%准确率（Accuracy），超越了专门用于伪影分类的DKL网络。另一方面，本文构建的网络在参数量（Params）和计算量（Flops）上相较于DKL分别减少了80.91%和96.94%。此外，通过热力图可视化分析，进一步验证了本文提出的伪影分类网络对伪影特征具有敏锐捕捉能力。
结论
2
本方法不仅能够有效地区分组织病理切片中相似伪影，而且在计算资源消耗上实现了显著降低。这一研究成果为病理图像质量评估领域带来了一种有效解决方案。
Objective
2
The analysis of histopathological images provides essential pathological information for tumor diagnosis and treatment， and is widely regarded by experts as the gold standard for tumor diagnosis. Prior to digitization， histopathological images undergo a complex， multi-step process that includes sampling， fixation， dehydration， embedding， sectioning， staining， and mounting. This process is labor-intensive， has limited automation， and is subject to pathologists' subjective actions， which can introduce artifacts. These artifacts may obscure normal tissue and complicate the assessment of true lesions， leading to potential misdiagnoses or missed diagnoses that can impact patient treatment and prognosis. Furthermore， artifacts in histopathological images can hinder the performance of computer-aided diagnostic systems， underscoring the importance of effective artifact detection in finalized images. Deep learning methods for identifying and differentiating artifacts with prominent morphological and color distinctions， such as ink marks， tissue folds， and blurriness， have shown promising results. However， certain artifact types， such as looseness and tissue bubbles， are visually similar， making them particularly challenging to differentiate. Effective differentiation requires models that can maintain sensitivity to local features while also achieving a comprehensive understanding of global patterns and structures， ensuring the robust integration of local and global information. Nonetheless， current methods for artifact detection have not fully addressed the challenges posed by these visually similar artifacts， indicating an urgent need for further investigation in this area. To address the limitations of existing methods in integrating and interacting with local and global information for the detection of highly similar artifacts， this paper proposes a local and global information interactive fusion network MoLiNet （mobile linear net） to improve the multi-classification of pathological image artifacts.
Method
2
In pathology， histopathological images are generally stored as whole-slide images （WSIs） organized in a pyramid structure. Researchers typically preprocess WSIs by segmenting them into smaller image patches. After patch segmentation， we further process these patches using an HSV color space-based edge detection module， HSVEF， designed to improve the network's attention to fissures. In this work， we extend the concept of a parallel framework by employing a dual-branch network. The CNN branch utilizes the lightweight convolutional neural network MobileNetV3， which enables efficient feature extraction while enhancing the network's capacity to capture local details. As image patches pass through this branch， features are progressively refined from low-level to higher-level representations. The Transformer branch is constructed using MGL-Trans （mobile gated linear Transformer）， which takes dimensionally compressed image features as input. Within the MGL-Trans module， the conventional feedforward layer is replaced by the MobileGLU （mobile gated linear unit）， leveraging a gated linear unit （GLU）. The MobileGLU design enables the model to selectively amplify or suppress features at different stages， thereby enhancing its ability to recognize complex image patterns. A focused linear Cross-attention （FLCA） mechanism is incorporated between the two branches， enabling effective interaction between local and global features. In our model， this attention mechanism is concretely implemented as the feature gather module （FGM） and the feature diffusion module （FDM）. Finally， the features extracted from both branches are concatenated and fed into a classification head for categorization. This architecture not only enriches the model’s overall understanding of image features but also enhances its performance in complex image analysis tasks.
Result
2
The proposed network surpasses comparable state-of-the-art methods in both classification accuracy and computational efficiency. On the NCPDCSAD （ningbo clinical pathology diagnosis center similar artifact dataset）， our model achieved Accuracy， Precision， Recall， and F1-Score values of 0.9424， 0.9477， 0.9498， and 0.9486， respectively， outperforming the dual-branch architecture Dyn-Perceiver as well as artifact classification methods AR-Classifier and DKL. Notably， our network reduces parameters and computational load by 80.91% and 96.94%， respectively， compared to DKL. Additionally， heatmap visualization analysis confirms that our method accurately identifies critical regions of pathological artifacts and assigns higher weights to these areas， greatly enhancing the accuracy of multi-class artifact detection tasks.
Conclusion
2
Compared to similar methods， our approach effectively extracts artifact information from images. In this network， we designed the MGL-Trans based on Transformer principles， allowing the model to selectively enhance or suppress features at various stages， thereby improving its ability to recognize complex image patterns. Additionally， we developed a focused linear Cross-attention mechanism based on Cross-attention. FLCA utilizes an efficient focusing function to better capture dependencies between two input sequences while maintaining both computational efficiency and high performance. These innovations enable the model to effectively distinguish similar artifacts in histopathological slides， while significantly reducing computational resource consumption. This achievement offers an innovative and efficient solution for the quality assessment of pathological images.
Albuquerque T ， Moreira A ， Barros B ， Montezuma D ， Oliveira S and Neto P . 2022 . Quality Control in Digital Pathology： Automatic Fragment Detection and Counting // 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society . Glasgow， Scotland， United Kingdom ： IEEE： 588 - 593 ［ DOI： 10.1109/EMBC48229.2022.9871208 http://dx.doi.org/10.1109/EMBC48229.2022.9871208 ］
Babaie M and Tizhoosh H R . 2019 . Deep features for tissue-fold detection in histopathology images // Digital Pathology： 15th European Congress . Warwick， UK ： Springer： 125 - 132 ［ DOI： 10.1007/978-3-030-23937-4_15 http://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： 10.4103/2153-3539.73320 http://dx.doi.org/10.4103/2153-3539.73320 ］
Chen C F R ， Fan Q and Panda R . 2021 . Crossvit： Cross-attention multi-scale vision transformer for image classification // Proceedings of the IEEE/CVF international conference on computer vision . Montreal， QC， Canada ： IEEE： 357 - 366 ［ DOI： 10.1109/ICCV48922.2021.00041 http://dx.doi.org/10.1109/ICCV48922.2021.00041 ］
Chen H ， Wang Y ， Guo J and Tao D . 2023 . Vanillanet： the power of minimalism in deep learning // Advances in Neural Information Processing Systems . Vancouver， British Columbia， Canada ： Curran Associates： 7050 - 7064 ［ DOI： 10.48550/arXiv.2305.12972 http://dx.doi.org/10.48550/arXiv.2305.12972 ］
Chen Y ， Dai X ， Chen D ， Liu M ， Dong X ， Yuan L and Liu Z . 2022 . Mobile-former： Bridging mobilenet and transformer // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition （CVPR） . New Orleans， USA ： IEEE： 5270 - 5279 ［ DOI： 10.1109/CVPR52688.2022.00520 http://dx.doi.org/10.1109/CVPR52688.2022.00520 ］
Dauphin Y N ， Fan A ， Auli M and Grangier D . 2017 . Language modeling with gated convolutional networks // International conference on machine learning . Sydney， Australia ： PMLR： 933 - 941 ［ DOI： Arxiv-1612.08083 http://dx.doi.org/Arxiv-1612.08083 ］
Ding W L ， Liu J L ， Zhu W and Liao W Y . 2024 . Review of quality control algorithms for pathological slides based on deep learning . Computer Science ， 51 （ 10 ）： 276 - 286
丁维龙 ， 刘津龙 ， 朱伟 ， 廖皖茵 . 2024 . 基于深度学习的病理切片质量控制算法综述 . 计算机科学 ， 51 （ 10 ）： 276 - 286 ［ DOI： 10.11896/jsjkx.231000167 http://dx.doi.org/10.11896/jsjkx.231000167 ］
Dosovitskiy A ， Beyer L ， Kolesnikov A ， Weissenborn D ， Zhai X ， Unterthiner T ， Dehghani M ， Minderer M ， Heigold G ， Gelly S ， Uszkoreit J and Houlsby N . 2021 . An image is worth 16 x 16 words： Transformers for image recognition at scale ［EB/OL］. ［ 2021-06-03 ］. https://arxiv.org/pdf/2010.11929.pdf https://arxiv.org/pdf/2010.11929.pdf
Gao D ， Padfield D ， Rittscher J and Mckay R . 2010 . Automated training data generation for microscopy focus classification // International Conference on Medical Image Computing and Computer-Assisted Intervention . Berlin， Heidelberg ： Springer： 446 - 453 ［ DOI： 10.1007/978-3-642-15745-5_55 http://dx.doi.org/10.1007/978-3-642-15745-5_55 ］
Guo Y F ， Hu M H ， Min X K ， Wang Y ， Dai M and Zhai G T . 2023 . Blind image quality assessment for pathological microscopic image under screen and immersion scenarios . IEEE Transactions on Medical Imaging ， 42 （ 11 ）： 3295 - 3306 ［ DOI： 10.1109/TMI.2023.3282387 http://dx.doi.org/10.1109/TMI.2023.3282387 ］
Foucart A ， Debeir O and Decaestecker C . 2018 . Artifact identification in digital pathology from weak and noisy supervision with deep residual networks // 2018 4th International Conference on Cloud Computing Technologies and Applications （Cloudtech） . Brussels， Belgium ： IEEE： 1 - 6 ［ DOI： 10.1109/CloudTech.2018.8713350 http://dx.doi.org/10.1109/CloudTech.2018.8713350 ］
Haghighat M ， Browning L ， Sirinukunwattana K ， Malacrino S ， Alham N K ， Colling R ， Cui Y ， Rakha E ， Hamdy F C ， Verrill C and Rittscher J . 2022 . Automated quality assessment of large digitised histology cohorts by artificial intelligence . Scientific Reports ， 12 （ 1 ）： 5002 ［ DOI： 10.1038/s41598-022-08351-5 http://dx.doi.org/10.1038/s41598-022-08351-5 ］
Han D C ， Pan X R ， Han Y Z ， Song S J and Huang G . 2023 . Flatten transformer： Vision transformer using focused linear attention // Proceedings of the IEEE/CVF international conference on computer vision . Paris， France ： IEEE： 5961 - 5971 ［ DOI： 10.1109/ICCV51070.2023.00548 http://dx.doi.org/10.1109/ICCV51070.2023.00548 ］
Han Y Z ， Han D C ， Liu Z Y ， Wang Y L ， Pan X R ， Pu Y F ， Deng C ， Feng J L Song S J and Huang G . 2023 . Dynamic perceiver for efficient visual recognition // Proceedings of the IEEE/CVF International Conference on Computer Vision . Paris， France ： IEEE： 5992 - 6002 ［ DOI： 10.1109/ICCV51070.2023.00551 http://dx.doi.org/10.1109/ICCV51070.2023.00551 ］
Hashimoto N ， Bautista P A ， Yamaguchi M ， Ohyama N and Yagi Y . 2012 . Referenceless image quality evaluation for whole slide imaging . Journal of pathology informatics ， 3 （ 1 ）： 9 ［ DOI： 10.4103/2153-3539.93891 http://dx.doi.org/10.4103/2153-3539.93891 ］
He K M ， Zhang X Y ， Ren S Q and Sun J . 2016 . Deep residual learning for image recognition // Proceedings of the IEEE conference on computer vision and pattern recognition . Las Vegas， NV， USA ： IEEE： 770 - 778 ［ DOI： 10.1109/CVPR.2016.90 http://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 . // IEEE 10th International Conference on Healthcare Informatics （ICHI） . Rochester， MN， USA ： IEEE： 282 - 287 ［ DOI： 10.1109/ICHI54592.2022.00049 http://dx.doi.org/10.1109/ICHI54592.2022.00049 ］
Hossain M S ， Shahriar G M ， Syeed M M M ， Uddin M F ， Hasan M and Hossain M S . 2023 . Tissue artifact segmentation and severity assessment for automatic analysis using wsi . IEEE Access ， 11 ： 21977 - 21991 ［ DOI： 10.1109/ACCESS.2023.3250556 http://dx.doi.org/10.1109/ACCESS.2023.3250556 ］
Hosseini M S ， Zhang Y and Plataniotis K N . 2019 . Encoding visual sensitivity by maxpol convolution filters for image sharpness assessment . IEEE Transactions on Image Processing ， 28 （ 9 ）： 4510 - 4525 ［ DOI： 10.1109/TIP.2019.2906582 http://dx.doi.org/10.1109/TIP.2019.2906582 ］
Howard A ， Sandler M ， Chen B ， Wang W ， Chen L and Tan M . 2019 . Searching for mobilenetv3//Proceedings of the IEEE/CVF international conference on computer vision . Seoul， Korea （South） ： IEEE ： 1314 - 1324 ［ DOI： 10.1109/ICCV.2019.00140 http://dx.doi.org/10.1109/ICCV.2019.00140 ］
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 ： 1 - 7 ［ DOI： 10.1200/CCI.18.00157 http://dx.doi.org/10.1200/CCI.18.00157 ］
Jin X ， Wen K ， Lyu G F ， Shi J ， Chi M X ， Wu Z and An H ． 2020 ． Survey on the applications of deep learning in histopathology ． Journal of Image and Graphics ， 25 （ 10 ） ： 1982 - 1993
金旭 ， 文可 ， 吕国锋 ， 石军 ， 迟孟贤 ， 武铮 ， 安虹 ． 2020 ． 深度学习在组织病理学中的应用综述 ． 中国图象图形学报 ， 25 （ 10 ） ： 1982 - 1993 ［ DOI： 10. 11834 /jig. 200460 http://dx.doi.org/10.11834/jig.200460 ］
Kanwal N ， López-Pérez M ， Kiraz U ， Zuiverloon T C M ， Molina R and Engan K . 2024 . Are you sure it’s an artifact？ Artifact detection and uncertainty quantification in histological images . Computerized Medical Imaging and Graphics ， 112 ： 102321 ［ DOI： 10.1016/j.compmedimag.2023.102321 http://dx.doi.org/10.1016/j.compmedimag.2023.102321 ］
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.2022.3176091 http://dx.doi.org/10.1109/ACCESS.2022.3176091 ］
Ke J ， Liu K ， Sun Y X ， Xue Y Y ， Huang J X and Lu Y Z . 2023 . Artifact Detection and Restoration in Histology Images with Stain-Style and Structural Preservation . IEEE Transactions on Medical Imaging ， 42 （ 12 ）： 3487 - 3500 ［ DOI： 10.1109/TMI.2023.3288940 http://dx.doi.org/10.1109/TMI.2023.3288940 ］
Khan S ， Naseer M ， Hayat M ， Zamir S W ， Khan F S and Shah M . 2022 . Transformers in vision： A survey . ACM computing surveys （CSUR） ， 54 （ 10 s）： 1 - 41 ［ DOI： 10.1145/3505244 http://dx.doi.org/10.1145/3505244 ］］
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 Pathology Informatics ， 4 （ 1 ）： 1 - 11 ［ DOI： 10.4103/2153-3539.117448 http://dx.doi.org/10.4103/2153-3539.117448 ］
Liang Z Y ， Wang Q Y ， Liao H W ， Zhao M ， Lee J ， Yang C ， Li F Y and Ling D S . 2021 . Artificially engineered antiferromagnetic nanoprobes for ultra-sensitive histopathological level magnetic resonance imaging . Nature Communications ， 12 （ 1 ）： 3840 ［ DOI： 10.1038/s41467-021-24055-2 http://dx.doi.org/10.1038/s41467-021-24055-2 ］
Li J X ， Sun J ， Li C and Bilal Ahmad . 2022 . A MHA-based integrated diagnosis and segmentation method for COVID-19 pandemic . Journal of Image and Graphics ， 27 （ 12 ）： 3651 - 3662
李金星 ， 孙俊 ， 李超 ， Bilal Ahmad . 2022 . 融合多头注意力机制的新冠肺炎联合诊断与分割 . 中国图象图形学报 ， 27 （ 12 ）： 3651 - 3662 ［ DOI： 10. 11834 / jig. 211015 http://dx.doi.org/10.11834/jig.211015 ］
Mehta S and Rastegari M . 2022 . MobileViT： Light-weight ， General-purpose， and Mobile-friendly Vision Transformer. International Conference on Learning Representations ［EB/OL］. ［ 2022-03-04 ］. https://arxiv.org/pdf/2110.02178 https://arxiv.org/pdf/2110.02178
Najjar F H ， Khudhair K T ， Khudhair Z N ， Alwan H H and AI-khaykan A . 2023 . Acute lymphoblastic leukemia image segmentation based on modified HSV model // Journal of Physics： Conference Series . Geneva， Switzerland ： IOP Publishing： 2432 （ 1 ）： 012020 ［ DOI： 10.1088/1742-6596/2432/1/012020 http://dx.doi.org/10.1088/1742-6596/2432/1/012020 ］
Pizarro R ， Assemlal H E ， Jegathambal S K B ， Jubault T ， Antel S ， Arnold D and Shmuel A . 2023 . Deep learning， data ramping， and uncertainty estimation for detecting artifacts in large， imbalanced databases of MRI images . Medical Image Analysis ， 90 ： 102942 ［ DOI： 10.1016/j.media.2023.102942 http://dx.doi.org/10.1016/j.media.2023.102942 ］
Palokangas S ， Selinummi J and Yli-Harja O . 2007 . Segmentation of folds in tissue section images // 29th annual international Conference of the IEEE Engineering in Medicine and biology society . Lyon， France ： IEEE： 5641 - 5644 ［ DOI： 10.1109/IEMBS.2007.4353626 http://dx.doi.org/10.1109/IEMBS.2007.4353626 ］
Sandler M ， Howard A ， Zhu M ， Zhmoginov and Chen L . 2018 . Mobilenetv 2 ： Inverted residuals and linear bottlenecks //Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City， UT， USA ： IEEE： 4510 - 4520 ［ DOI： 10.1109/CVPR.2018.00474 http://dx.doi.org/10.1109/CVPR.2018.00474 ］
Selvaraju R R ， Cogswell M ， Das A ， Vedantam R ， Parikh D and Batra D . 2017 . Grad-cam： Visual explanations from deep networks via gradient-based localization // Proceedings of the IEEE international conference on computer vision . Venice， Italy ： IEEE： 618 - 626 ［ DOI： 10.1109/ICCV.2017.74 http://dx.doi.org/10.1109/ICCV.2017.74 ］
Shaikh N N ， Wasag K and Nie Y . 2022 . Artifact identification in digital histopathology images using few-shot learning // IEEE 19th International Symposium on Biomedical Imaging （ISBI） . Kolkata， India ： IEEE： 1 - 4 ［ DOI： 10.1109/ISBI52829.2022.9761648 http://dx.doi.org/10.1109/ISBI52829.2022.9761648 ］
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： 10.1016/j.bspc.2023.104812 http://dx.doi.org/10.1016/j.bspc.2023.104812 ］
Shakhawat H M ， Nakamura T ， Kimura F ， Yagi Y and Yamaguchi M . 2020 . Automatic quality evaluation of whole slide images for the practical use of whole slide imaging scanner . ITE Transactions On Media Technology And Applications ， 8 （ 4 ）： 252 - 268 ［ DOI： 10.3169/mta.8.252 http://dx.doi.org/10.3169/mta.8.252 ］
Shi D . 2024 . TransNeXt： Robust Foveal Visual Perception for Vision Transformers // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle WA， USA ： IEEE： 17773 - 17783 ［ DOI： 10.1109/CVPR52733.2024.01683 http://dx.doi.org/10.1109/CVPR52733.2024.01683 ］
Sun J M ， Shen Z H ， Wang Y ， Bao H J and Zhou X W . 2021 . LoFTR： Detector-free local feature matching with transformers // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition （CVPR） . Online ： IEEE： 8922 - 8931 ［ DOI： 10.1109/CVPR46437.2021.00881 http://dx.doi.org/10.1109/CVPR46437.2021.00881 ］
Tellez D ， Litjens G ， Bándi P ， Bulten W ， Bokhorst J M ， Ciompi F and Laak J V D . 2019 . Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology . Medical image analysis ， 58 ： 101544 ［ DOI： 10.1016/j.media.2019.101544 http://dx.doi.org/10.1016/j.media.2019.101544 ］
Xu J ， Pan Y ， Pan X L ， Hoi S ， Yi Z and Xu Z L . 2022 . RegNet： Self-regulated network for image classification // IEEE Transactions on Neural Networks and Learning Systems . New Orleans， Louisiana ： IEEE： 34 （ 11 ）： 9562 - 9567 ［ DOI： 10.1109/TNNLS.2022.3158966 http://dx.doi.org/10.1109/TNNLS.2022.3158966 ］
Xia C F ， Dong X S ， Li H ， Cao M M ， Sun D Q ， He S Y ， Yang F ， Yan X X ， Zhang S L ， Li N and Chen W Q . 2022 . Cancer statistics in China and United States， 2022： profiles， trends， and determinants . Chinese medical journal ， 135 （ 5 ）： 584 - 590 ［ DOI： 10.1097/CM9.0000000000002108 http://dx.doi.org/10.1097/CM9.0000000000002108 ］
Yang S ， Lin G S ， Jiang Q P and Lin W S . 2019 . A dilated inception network for visual saliency prediction . IEEE Transactions on Multimedia ， 22 （ 8 ）： 2163 - 2176 ［ DOI： 10.1109/TMM.2019.2947352 http://dx.doi.org/10.1109/TMM.2019.2947352 ］
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 （ 04 ）： 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 （ 04 ）： 1134 - 1145 ［ DOI： 10.11834/jig.211133 http://dx.doi.org/10.11834/jig.211133 ］
Zhu L ， Wang X J ， Ke Z H ， Zhang W N and Lau R . 2023 . Biformer： Vision transformer with bi-level routing attention // Proceedings of the IEEE/CVF conference on computer vision and pattern recognition . Vancouver， BC， Canada ： IEEE： 10323 - 10333 ［ DOI： 10.1109/CVPR52729.2023.00995 http://dx.doi.org/10.1109/CVPR52729.2023.00995 ］
Zhu W . 2024 . Research and Development of Key Technologies of Detection System for Pathological Slide Artifacts in Scanning and Preparation Based on Deep Learning . Zhejiang ： Zhejiang University of Technology（朱伟） . 2024. 基于深度学习的病理扫描与制片伪影检测系统关键技术研发 . 浙江： 浙江工业大学）
相关作者
相关机构
京公网安备11010802024621