外科手術(shù)的進步對急性和慢性疾病的管理，延長壽命和不斷擴大生存范圍都產(chǎn)生了重大影響。如圖1所示，這些進步得益于診斷，成像和外科器械的持續(xù)技術(shù)發(fā)展。這些技術(shù)中，深度學習對推動術(shù)前手術(shù)規(guī)劃尤其重要。手術(shù)規(guī)劃中要根據(jù)現(xiàn)有的醫(yī)療記錄來計劃手術(shù)程序，而成像對于手術(shù)的成功至關(guān)重要。在現(xiàn)有的成像方式中，X射線，CT，超聲和MRI是實際中最常用的方式。基于醫(yī)學成像的常規(guī)任務包括解剖學分類，檢測，分割和配準。

圖1：概述了流行的AI技術(shù)，以及在術(shù)前規(guī)劃，術(shù)中指導和外科手術(shù)機器人學中使用的AI的關(guān)鍵要求，挑戰(zhàn)和子區(qū)域。

1、分類

分類輸出輸入的診斷值，該輸入是單個或一組醫(yī)學圖像或器官或病變體圖像。除了傳統(tǒng)的機器學習和圖像分析技術(shù)，基于深度學習的方法正在興起[1]。對于后者，用于分類的網(wǎng)絡架構(gòu)由用于從輸入層提取信息的卷積層和用于回歸診斷值的完全連接層組成。

例如，有人提出了使用GoogleInception和ResNet架構(gòu)的分類管道來細分肺癌，膀胱癌和乳腺癌的類型[2]。Chilamkurthy等證明深度學習可以識別顱內(nèi)出血，顱骨骨折，中線移位和頭部CT掃描的質(zhì)量效應[3]。與標準的臨床工具相比，可通過循環(huán)神經(jīng)網(wǎng)絡（RNN）實時預測心臟外科手術(shù)后患者的死亡率，腎衰竭和術(shù)后出血[4]。ResNet-50和Darknet-19已被用于對超聲圖像中的良性或惡性病變進行分類，顯示出相似的靈敏度和更高的特異性[5]。

2、檢測

檢測通常以邊界框或界標的形式提供感興趣區(qū)域的空間定位，并且還可以包括圖像或區(qū)域級別的分類。同樣，基于深度學習的方法在檢測各種異常或醫(yī)學狀況方面也顯示出了希望。用于檢測的DCNN通常由用于特征提取的卷積層和用于確定邊界框?qū)傩缘幕貧w層組成。

為了從4D正電子發(fā)射斷層掃描（PET）圖像中檢測前列腺癌，對深度堆疊的卷積自動編碼器進行了訓練，以提取統(tǒng)計和動力學生物學特征[6]。對于肺結(jié)節(jié)的檢測，提出了具有旋轉(zhuǎn)翻譯組卷積（3D G-CNN）的3D CNN，具有良好的準確性，靈敏度和收斂速度[7]。對于乳腺病變的檢測，基于深度Q網(wǎng)絡擴展的深度強化學習（DRL）用于從動態(tài)對比增強MRI中學習搜索策略[8]。為了從CT掃描中檢測出急性顱內(nèi)出血并改善網(wǎng)絡的可解釋性，Lee等人[9]使用注意力圖和迭代過程來模仿放射科醫(yī)生的工作流程。

3、分割

分割可被視為像素級或體素級圖像分類問題。由于早期作品中計算資源的限制，每個圖像或卷積都被劃分為小窗口，并且訓練了CNN來預測窗口中心位置的目標標簽。通過在密集采樣的圖像窗口上運行CNN分類器，可以實現(xiàn)圖像或體素分割。例如，Deepmedic對MRI的多模式腦腫瘤分割顯示出良好的性能[10]。但是，基于滑動窗口的方法效率低下，因為在許多窗口重疊的區(qū)域中會重復計算網(wǎng)絡功能。由于這個原因，基于滑動窗口的方法最近被完全卷積網(wǎng)絡（FCN）取代[11]。關(guān)鍵思想是用卷積層和上采樣層替換分類網(wǎng)絡中的全連接層，這大大提高了分割效率。對于醫(yī)學圖像分割，諸如U-Net [12][13]之類的編碼器-解碼器網(wǎng)絡已顯示出令人鼓舞的性能。編碼器具有多個卷積和下采樣層，可提取不同比例的圖像特征。解碼器具有卷積和上采樣層，可恢復特征圖的空間分辨率，并最終實現(xiàn)像素或體素密集分割。在[14]中可以找到有關(guān)訓練U-Net進行醫(yī)學圖像分割的不同歸一化方法的綜述。

對于內(nèi)窺鏡胰管和膽道手術(shù)中的導航，Gibson等人 [15]使用膨脹的卷積和融合的圖像特征在多個尺度上分割來自CT掃描的腹部器官。為了從MRI進行胎盤和胎兒大腦的交互式分割，將FCN與用戶定義的邊界框和涂鴉結(jié)合起來，其中FCN的最后幾層根據(jù)用戶輸入進行了微調(diào)[16]。手術(shù)器械界標的分割和定位被建模為熱圖回歸模型，并且使用FCN幾乎實時地跟蹤器械[17]。對于肺結(jié)節(jié)分割，F(xiàn)eng等通過使用候選篩選方法從弱標記的肺部CT中學習辨別區(qū)域來訓練FCN，解決了需要精確的手動注釋的問題[18]。Bai等提出了一種自我監(jiān)督的學習策略，以有限的標記訓練數(shù)據(jù)來提高U-Net的心臟分割精度[19]。

4、配準

配準是兩個醫(yī)學圖像，體積或模態(tài)之間的空間對齊，這對于術(shù)前和術(shù)中規(guī)劃都特別重要。傳統(tǒng)算法通常迭代地計算參數(shù)轉(zhuǎn)換，即彈性，流體或B樣條曲線模型，以最小化兩個醫(yī)療輸入之間的給定度量（即均方誤差，歸一化互相關(guān)或互信息）。最近，深度回歸模型已被用來代替?zhèn)鹘y(tǒng)的耗時和基于優(yōu)化的注冊算法。

示例性的基于深度學習的配準方法包括VoxelMorph，它通過利用基于CNN的結(jié)構(gòu)和輔助分割來將輸入圖像對映射到變形場，從而最大化標準圖像匹配目標函數(shù)[20]。提出了一個用于3D醫(yī)學圖像配準的端到端深度學習框架，該框架包括三個階段：仿射變換預測，動量計算和非參數(shù)細化，以結(jié)合仿射配準和矢量動量參數(shù)化的固定速度場[21]。提出了一種用于多模式圖像配準的弱監(jiān)督框架，該框架對具有較高級別對應關(guān)系的圖像（即解剖標簽）進行訓練，而不是用于預測位移場的體素級別轉(zhuǎn)換[22]。每個馬爾科夫決策過程都由經(jīng)過擴張的FCN訓練的代理商進行，以使3D體積與2D X射線圖像對齊[23]。RegNet是通過考慮多尺度背景而提出的，并在人工生成的位移矢量場（DVF）上進行了培訓，以實現(xiàn)非剛性配準[24]。3D圖像配準也可以公式化為策略學習過程，其中將3D原始圖像作為輸入，將下一個最佳動作（即向上或向下）作為輸出，并將CNN作為代理[25]。

參考文獻： 
[1]   G. Litjens, T. Kooi, B. E.Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J. A. Van Der Laak, B. VanGinneken, and C. I. Sa′nchez, “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017.
[2]   P. Khosravi, E. Kazemi, M.Imielinski, O. Elemento, and I. Hajirasouliha, “Deep convolutional neural networks enable discrimination of heterogeneous digital pathology images,” EBioMedicine, vol. 27, pp. 317–328, 2018.
[3]   S. Chilamkurthy, R. Ghosh, S.Tanamala, M. Biviji, N. G. Campeau, V. K. Venugopal, V. Mahajan, P. Rao, and P.Warier, “Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study,” The Lancet, vol. 392, no. 10162, pp. 2388–2396,2018.
[4]   A. Meyer, D. Zverinski, B.Pfahringer, J. Kempfert, T. Kuehne, S. H. Su¨ndermann, C. Stamm, T. Hofmann, V.Falk, and C. Eickhoff, “Machine learning for real-time prediction of complications in critical care: a retrospective study,” The Lancet RespiratoryMedicine, vol. 6, no. 12, pp. 905–914, 2018.
[5]   X. Li, S. Zhang, Q. Zhang, X.Wei, Y. Pan, J. Zhao, X. Xin, C. Qin, X. Wang, J. Li et al., “Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study,” The LancetOncology, vol. 20, no. 2, pp. 193–201, 2019.
[6]   E. Rubinstein, M. Salhov, M.Nidam-Leshem, V. White, S. Golan, J. Baniel, H. Bernstine, D. Groshar, and A.Averbuch, “Unsupervised tumor detection in dynamic PET/CT imaging of the prostate,” Medical Image Analysis, vol. 55, pp. 27–40, 2019.
[7]   M. Winkels and T. S. Cohen,“Pulmonary nodule detection in CT scan with equivariant CNNs,” Medical image analysis, vol. 55, pp. 15–26, 2019.
[8]   G. Maicas, G. Carneiro, A. P.Bradley, J. C. Nascimento, and I. Reid,“Deep reinforcement learning for active breast lesion detection from DCE-MRI,” in Proceedings of International Conference on Medical image computing and Computer-Assisted Intervention (MICCAI). Springer, 2017, pp.665–673.
[9]   H. Lee, S. Yune, M. Mansouri,M. Kim, S. H. Tajmir, C. E. Guerrier, S. A. Ebert, S. R. Pomerantz, J. M.Romero, S. Kamalian et al., “An explainable deep-learning algorithm for the detection of acute intracranial hemorrhage from small datasets,” NatureBiomedical Engineering, vol. 3, no. 3, p. 173, 2019.
[10]K. Kamnitsas, C. Ledig, V. F.Newcombe, J. P. Simpson, A. D. Kane, D. K. Menon, D. Rueckert, and B. Glocker, “Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation,” Medical image analysis, vol. 36, pp. 61–78, 2017.
[11]J. Long, E. Shelhamer, and T.Darrell, “Fully convolutional networks for semantic segmentation,” in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015, pp. 3431–3440.
[12]O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proceedings of International Conference on Medical Image Computing and computer-Assisted Intervention (MICCAI). Springer, 2015, pp. 234–241.
[13]O. C¸i¸cek, A. Abdulkadir, S.S. Lienkamp, T. Brox, and O. Ronneberger,¨ “3D U-Net: learning dense volumetric segmentation from sparse annotation,” in Proceedings of InternationalConference on Medical Image Computing and Computer-Assisted Intervention(MICCAI). Springer, 2016, pp. 424–432.
[14]X.-Y. Zhou and G.-Z. Yang,“Normalization in training U-Net for 2D biomedical semantic segmentation,” IEEERobotics and Automation Letters, vol. 4, no. 2, pp. 1792–1799, 2019.
[15]E. Gibson, F. Giganti, Y. Hu,E. Bonmati, S. Bandula, K. Gurusamy, B. Davidson, S. P. Pereira, M. J.Clarkson, and D. C. Barratt, “Automatic multi-organ segmentation on abdominal CT with dense networks,” IEEE Transactions on Medical Imaging, vol. 37, no. 8,pp.1822–1834, 2018.
[16]G. Wang, W. Li, M. A. Zuluaga,R. Pratt, P. A. Patel, M. Aertsen, T. Doel, A. L. David, J. Deprest, S.Ourselin et al., “Interactive medical image segmentation using deep learning with image-specific fine-tuning,” IEEE Transactions on Medical Imaging, vol.37, no. 7, pp. 1562–1573, 2018.
[17]I. Laina, N. Rieke, C.Rupprecht, J. P. Vizca′ıno, A. Eslami, F. Tombari, and N. Navab, “Concurrentsegmentation and localization for tracking of surgical instruments,” in Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI).Springer, 2017, pp. 664–672.
[18]X. Feng, J. Yang, A. F. Laine,and E. D. Angelini, “Discriminative localization in CNNs for weakly-supervised segmentation of pulmonary nodules,” in Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer, 2017,pp. 568–576.
[19]W. Bai, C. Chen, G. Tarroni,J. Duan, F. Guitton, S. E. Petersen, Y. Guo, P. M. Matthews, and D. Rueckert,“Self-supervised learning for cardiac MR image segmentation by anatomical position prediction,” in International Conference on Medical Image Computing and ComputerAssisted Intervention. Springer, 2019, pp. 541–549.
[20]G. Balakrishnan, A. Zhao, M.R. Sabuncu, J. Guttag, and A. V. Dalca, “VoxelMorph: a learning framework for deformable medical image registration,” IEEE Transactions on Medical Imaging,2019.
[21]Z. Shen, X. Han, Z. Xu, and M.Niethammer, “Networks for joint affine and non-parametric image registration,”in Proceedings of the IEEE Conference on Computer Vision and pattern recognition (CVPR), 2019, pp. 4224–4233.
[22]Y. Hu, M. Modat, E. Gibson, W.Li, N. Ghavami, E. Bonmati, G. Wang, S. Bandula, C. M. Moore, M. Emberton etal., “Weaklysupervised convolutional neural networks for multimodal image registration,” Medical Image Analysis, vol. 49, pp. 1–13, 2018.
[23]S. Miao, S. Piat, P. Fischer,A. Tuysuzoglu, P. Mewes, T. Mansi, and R. Liao, “Dilated FCN for multi-agent2D/3D medical image registration,” in Proceedings of AAAI Conference on artificial intelligence, 2018.
[24]H. Sokooti, B. de Vos, F.Berendsen, B. P. Lelieveldt, I. Iˇsgum, and M. Staring, “Nonrigid image registration using multi-scale 3D convolutional neural networks,” in Proceedings of International Conference on Medical Image Computing and computer-Assisted Intervention (MICCAI). Springer, 2017, pp. 232–239.
[25]R. Liao, S. Miao, P. deTournemire, S. Grbic, A. Kamen, T. Mansi, and D. Comaniciu, “An artificial agent for robust image registration,” in Proceedings of AAAI Conference on Artificial Intelligence, 2017.