Application and Research Progress of Artificial Intelligence in Digital Pathological Image Analysis of Colorectal Cancer
-
摘要: 计算机人工智能技术在数字病理中应用广泛、发展迅速,是肿瘤精准诊疗时代的一个里程碑。传统病理学作为肿瘤诊断的金标准具有高度主观性及不可重复性,且工作繁琐。基于人工智能技术对数字病理图像进行特征提取及定量分析,并转变为高保真、高通量的可挖掘/分析的数据,在肿瘤早期诊断、分级及构建预后模型等方面表现出独特优势。数字病理人工智能的发展为病理学科带来了难得的机遇,也是精准诊疗的未来发展趋势。本文概述人工智能在结直肠癌数字化病理图像分析中的应用现状和潜在价值,以期为临床诊疗提供参考。Abstract: The artificial intelligence technology of computer science is widely used in digital pathology and develops rapidly, which is a milestone in the era of accurate diagnosis and treatment of tumors. As the gold standard of tumor diagnosis, traditional pathology is highly subjective and unrepeatable, and the work is cumbersome. Feature extraction and quantitative analysis of digital pathological images based on artificial intelligence technology are transformed into data with high fidelity and high-throughput that can be mined and analyzed. It shows unique advantages in early diagnosis, grading, and constructing the prognostic model of tumors. The development of artificial intelligence in digital pathology has brought a unique opportunity for pathology, and it is also the trend of the development of precise diagnosis and treatment in the future. In order to provide reference for clinical diagnosis and treatment, we review the current status and the value of potential application of artificial intelligence in digital pathological image analysis of colorectal cancer.
-
Key words:
- artificial intelligence /
- deep learning /
- digital pathology /
- colorectal cancer
作者贡献:李晓燕负责查阅文献、撰写初稿;李晨、陈灏源负责修订论文;张勇、张敬东构思论文框架,审核并修订论文。利益冲突:所有作者均声明不存在利益冲突 -
图 1 计算机辅助诊断方法进行结直肠癌全视野数字图像分析的工作结构图[25]
-
[1] Bray F, Ferlay J, Soerjomataram I, et al. Erratum: Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2020, 68: 394-424. [2] Zhang S, Sun K, Zheng R, et al. Cancer incidence and mortality in China, 2015[J]. Chin J Cancer Res, 2020, 1: 2-11. [3] Kumar N, Gupta R, Gupta S. Whole Slide Imaging (WSI) in Pathology: Current Perspectives and Future Directions[J]. J Digit Imaging, 2020, 33: 1034-1040. doi: 10.1007/s10278-020-00351-z [4] Mukhopadhyay S, Feldman MD, Abels E, et al. Whole slide imaging versus microscopy for primary diagnosis in surgical pathology: a multicenter blinded randomized noninferiority study of 1992 cases (Pivotal Study)[J]. Am J Surg Pathol, 2018, 42: 39-52. doi: 10.1097/PAS.0000000000000948 [5] Mayo RC, Leung J. Artificial intelligence and deep learning-Radiology's next frontier?[J]. Clin Imaging, 2018, 49: 87-88. doi: 10.1016/j.clinimag.2017.11.007 [6] Jiang Z, Song L, Lu H, et al. The Potential Use of DCE-MRI Texture Analysis to Predict HER2 2+ Status[J]. Front Oncol, 2019, 9: 242. doi: 10.3389/fonc.2019.00242 [7] Huang S, Yang J, Fong S, et al. Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges[J]. Cancer Lett, 2020, 471: 61-71. doi: 10.1016/j.canlet.2019.12.007 [8] Hubel DH, Wiesel TN. Early exploration of the visual cortex[J]. Neuron, 1998, 20: 401-412. doi: 10.1016/S0896-6273(00)80984-8 [9] Janowczyk A, Madabhushi A. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases[J]. J Pathol Inform, 2016, 7: 29. doi: 10.4103/2153-3539.186902 [10] Lu C, Xu H, Xu J, et al. Multi-Pass Adaptive Voting for Nuclei Detection in Histopathological Images[J]. Sci Rep, 2016, 6: 33985. doi: 10.1038/srep33985 [11] Höfener H, Homeyer A, Weiss N, et al. Deep learning nuclei detection: A simple approach can deliver state-of-the-art results[J]. Comput Med Imaging Graph, 2018, 70: 43-52. doi: 10.1016/j.compmedimag.2018.08.010 [12] Rahaman MM, Li C, Yao Y, et al. DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques[J]. Comput Biol Med, 2021, 136: 104649 doi: 10.1016/j.compbiomed.2021.104649 [13] Senaras C, Niazi MKK, Lozanski G, et al. DeepFocus: Detection of out-of-focus regions in whole slide digital images using deep learning[J]. PLoS One, 2018, 13: e0205387. doi: 10.1371/journal.pone.0205387 [14] Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]. Computer Vision and Pattern Recognition, 2015: 1-9. [15] He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]. Computer Vision and Pattern Recognition, 2016: 770-778. [16] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. Medical Image Computing and Computer-Assisted Intervention, 2015: 234-241. [17] Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39: 640-651. doi: 10.1109/TPAMI.2016.2572683 [18] Campanella G, Hanna MG, Geneslaw L, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images[J]. Nat Med, 2019, 25: 1301-1309. doi: 10.1038/s41591-019-0508-1 [19] Senaras C, Niazi MKK, Sahiner B, et al. Optimized generation of high-resolution phantom images using cGAN: Application to quantification of Ki67 breast cancer images[J]. PLoS One, 2018, 13: e0196846. doi: 10.1371/journal.pone.0196846 [20] Klimov S, Miligy IM, Gertych A, et al. A whole slide image-based machine learning approach to predict ductal carcinoma in situ (DCIS) recurrence risk[J]. Breast Cancer Res, 2019, 21: 83. doi: 10.1186/s13058-019-1165-5 [21] Wei JW, Suriawinata AA, Vaickus LJ, et al. Evaluation of a Deep Neural Network for Automated Classification of Colorectal Polyps on Histopathologic Slides[J]. JAMA Netw Open, 2020, 3: e203398. doi: 10.1001/jamanetworkopen.2020.3398 [22] Sturm B, Creytens D, Smits J, et al. Computer-Aided Assessment of Melanocytic Lesions by Means of a Mitosis Algorithm[J]. Diagnostics (Basel), 2022, 12: 436. doi: 10.3390/diagnostics12020436 [23] Bera K, Schalper KA, Rimm DL, et al. Artificial intelligence in digital pathology-new tools for diagnosis and precision oncology[J]. Nat Rev Clin Oncol, 2019, 16: 703-715. doi: 10.1038/s41571-019-0252-y [24] Hanna MG, Parwani A, Sirintrapun SJ. Whole Slide Imaging: Technology and Applications[J]. Adv Anat Pathol, 2020, 27: 251-259. [25] Jordan MI, Mitchell TM. Machine learning: Trends, perspectives, and prospects[J]. Science, 2015, 349: 255-260. doi: 10.1126/science.aaa8415 [26] Kainz P, Pfeiffer M, Urschler M. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization[J]. Peer J, 2017, 5: e3874. doi: 10.7717/peerj.3874 [27] Chen H, Li C, Li X, et al. IL-MCAM: An interactive learning and multi-channel attention mechanism-based weakly supervised colorectal histopathology image classification approach[J]. Comput Biol Med, 2022, 143: 105265. doi: 10.1016/j.compbiomed.2022.105265 [28] Lugli A, Kirsch R, Ajioka Y, et al. Recommendations for reporting tumor budding in colorectal cancer based on the International Tumor Budding Consensus Conference (ITBCC) 2016[J]. Mod Pathol, 2017, 30: 1299-1311. doi: 10.1038/modpathol.2017.46 [29] Fonseca GM, de Mello ES, Faraj SF, et al. Prognostic significance of poorly differentiated clusters and tumor budding in colorectal liver metastases[J]. J Surg Oncol, 2018, 117: 1364-1375. doi: 10.1002/jso.25017 [30] Liu S, Zhang Y, Ju Y, et al. Establishment and Clinical Application of an Artificial Intelligence Diagnostic Platform for Identifying Rectal Cancer Tumor Budding[J]. Front Oncol, 2021, 11: 626626. doi: 10.3389/fonc.2021.626626 [31] Gupta P, Chiang SF, Sahoo PK, et al. Prediction of colon cancer stages and survival period with machine learning approach[J]. Cancers (Basel), 2019, 11: 2007. doi: 10.3390/cancers11122007 [32] Reichling C, Taieb J, Derangere V, et al. Artificial intelligence-guided tissue analysis combined with immune infiltrate assessment predicts stage Ⅲ colon cancer outcomes in PETACC08 study[J]. Gut, 2020, 69: 681-690. doi: 10.1136/gutjnl-2019-319292 [33] Guinney J, Dienstmann R, Wang X, et al. The consensus molecular subtypes of colorectal cancer[J]. Nat Med, 2015, 21: 1350-1356. doi: 10.1038/nm.3967 [34] Popovici V, Budinská E, Dušek L, et al. Image-based surrogate biomarkers for molecular subtypes of colorectal cancer[J]. Bioinformatics, 2017, 33: 2002-2009. doi: 10.1093/bioinformatics/btx027 [35] 廖俊, 冯小兵, 王玉红, 等. 基于深度学习的结直肠癌全视野数字病理切片分子分型识别研究[J]. 四川大学学报(医学版), 2021, 52: 686-692. doi: 10.12182/20210760501 Liao J, Feng XB, Wang YH, et al. Identifying Molecular Subtypes of Whole-Slide Image in Colorectal Cancer via Deep Learning[J]. Sichuan Daxue Xuebao(Yixueban), 2021, 52: 686-692. doi: 10.12182/20210760501 [36] Gette I, Emelyanov V, Danilova I, et al. Correction to: Abstracts: 30th European Congress of Pathology[J]. Virchows Archiv, 2019, 474: 135-135. doi: 10.1007/s00428-018-2491-1 [37] Cercek A, Dos Santos Fernandes G, Roxburgh CS, et al. Mismatch Repair-Deficient Rectal Cancer and Resistance to Neoadjuvant Chemotherapy[J]. Clin Cancer Res, 2020, 26: 3271-3279. doi: 10.1158/1078-0432.CCR-19-3728 [38] Echle A, Grabsch HI, Quirke P, et al. Clinical-Grade Detection of Microsatellite Instability in Colorectal Tumors by Deep Learning[J]. Gastroenterology, 2020, 159: 1406-1416. e11. doi: 10.1053/j.gastro.2020.06.021 [39] Yamashita R, Long J, Longacre T, et al. Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study[J]. Lancet Oncol, 2021, 22: 132-141. doi: 10.1016/S1470-2045(20)30535-0 [40] Zhao Y, Ge X, He J, et al. The prognostic value of tumor-infiltrating lymphocytes in colorectal cancer differs by anatomical subsite: a systematic review and meta-analysis[J]. World J Surg Oncol, 2019, 17: 85. doi: 10.1186/s12957-019-1621-9 [41] Kather JN, Pearson AT, Halama N, et al. Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer[J]. Nat Med, 2019, 25: 1054-1056. doi: 10.1038/s41591-019-0462-y [42] Väyrynen JP, Lau MC, Haruki K, et al. Prognostic Significance of Immune Cell Populations Identified by Machine Learning in Colorectal Cancer Using Routine Hematoxylin and Eosin-Stained Sections[J]. Clin Cancer Res, 2020, 26: 4326-4338. doi: 10.1158/1078-0432.CCR-20-0071 [43] Sun R, Limkin EJ, Vakalopoulou M, et al. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study[J]. Lancet Oncol, 2018, 19: 1180-1191. doi: 10.1016/S1470-2045(18)30413-3 [44] Wang Q, Wei J, Chen Z, et al. Establishment of multiple diagnosis models for colorectal cancer with artificial neural networks[J]. Oncol Lett, 2019, 17: 3314-3322. [45] Ferrari R, Mancini-Terracciano C, Voena C, et al. MR-based artificial intelligence model to assess response to therapy in locally advanced rectal cancer[J]. Eur J Radiol, 2019, 118: 1-9. doi: 10.1016/j.ejrad.2019.06.013