机器学习在影像组学分析中的应用综述

doi:10.3778/j.issn.1002-8331.2210-0435

摘要/Abstract

摘要： 影像组学（radiomics）是一种从标准医学影像中定量地提取特征的技术。借助机器学习构建预测或诊断模型，能够在临床决策支持系统中提取和应用数据，以提高诊断的准确性，该技术在肿瘤分期、癌症检测、生存分析等任务中得到了广泛的应用。回顾了机器学习在影像组学分析中的相关应用和研究进展；重点论述了机器学习算法在影像组学分析中各阶段的适用性和局限性，在原理和应用效果上对代表性算法进行了深入梳理与分析；综合介绍了在影像组学分析中对各阶段工作的评估方法；整理了公开的医学影像数据集以及用于影像组学特征提取的软件与工具包；最后讨论了机器学习在影像组学中的未来发展。

关键词: 机器学习, 影像组学, 特征工程, 深度学习, 医学影像

Abstract: Radiomics is a technique for quantitatively extracting features from standard medical images. The construction of predictive or diagnostic models with the assistance of machine learning enables data to be extracted and applied in clinical decision support systems to improve diagnostic accuracy, which has been widely used in tumor staging, cancer detection, survival analysis and other tasks. The application and research progress of machine learning in radiomics analysis are reviewed. The applicability and limitations of machine learning algorithms in each stage of radiomics analysis are emphatically discussed, and the representative algorithms are thoroughly sorted out and analyzed in terms of principles and application effects. The evaluation methods to the work of each stage in the radiomics analysis are comprehensively introduced. The publicly available medical image datasets and software toolkits for radiomics feature extraction are organized. Finally, the future development of machine learning in radiomics is discussed.

Key words: machine learning, radiomics, feature engineering, deep learning, medical images

鲁慧民, 薛涵, 王奕龙, 王贵增, 桑鹏程. 机器学习在影像组学分析中的应用综述[J]. 计算机工程与应用, 2023, 59(17): 22-34.

LU Huimin, XUE Han, WANG Yilong, WANG Guizeng, SANG Pengcheng. Review of Application of Machine Learning in Radiomics Analysis[J]. Computer Engineering and Applications, 2023, 59(17): 22-34.

参考文献

[1] LAMBIN P，RIOS-VELAZQUEZ E，LEIJENAAR R，et al.Radiomics：extracting more information from medical images using advanced feature analysis[J].European Journal of Cancer，2012，48（4）：441-446.
[2] 刘士远.加强医学影像数据库建设推动行业快速发展[J].中华放射学杂志，2022，56（9）：931-934.
LIU S Y.Attach importance to and strengthen the construction of medical image database to promote the rapid development of medical imaging[J].Chinese Journal of Radiology，2022，56（9）：931-934.
[3] GILLIES R J，KINAHAN P E，HRICAK H.Radiomics：images are more than pictures，they are data[J].Radiology，2016，278（2）：563-577.
[4] ATTENBERGER U I，LANGS G.How does radiomics actually work?-review[J].R?Fo，2021，193（6）：652-657.
[5] CUI Y，YIN F F.Impact of image quality on radiomics applications[J].Physics in Medicine & Biology，2022，67（15）：1-22.
[6] SHINOHARA R T，OH J，NAIR G，et al.Volumetric analysis from a harmonized multisite brain MRI study of a single subject with multiple sclerosis[J].American Journal of Neuroradiology，2017，38（8）：1501-1509.
[7] MADABHUSHI A，UDUPA J K.New methods of MR image intensity standardization via generalized scale[J].Medical Physics，2006，33（9）：3426-3434.
[8] NYL L G，UDUPA J K.On standardizing the MR image intensity scale[J].Magnetic Resonance in Medicine，1999，42（6）：1072-1081.
[9] ISAKSSON L J，RAIMONDI S，BOTTA F，et al.Effects of MRI image normalization techniques in prostate cancer radiomics[J].Physica Medica，2020，71（1）：7-13.
[10] HU Z，ZHUANG Q，XIAO Y，et al.MIL normalization- prerequisites for accurate MRI radiomics analysis[J].Computers in Biology and Medicine，2021，133（6）：1-12.
[11] RONNEBERGER O，FISCHER P，BROX T.U-Net：convolutional networks for biomedical image segmentation[C]//Processing of the International Conference on Medical Image Computing and Computer-Assisted Intervention.Cham：Springer，2015：234-241.
[12] LOI S，MORI M，BENEDETTI G，et al.Robustness of CT radiomic features against image discretization and interpolation in characterizing pancreatic neuroendocrine neoplasms[J].Physica Medica，2020，76（3）：125-133.
[13] PARK S H，LIM H，BAE B K，et al.Robustness of magnetic resonance radiomic features to pixel size resampling and interpolation in patients with cervical cancer[J].Cancer Imaging，2021，21（1）：1-11.
[14] YANG S，WU N，ZHANG L，et al.Evaluation of the linear interpolation method in correcting the influence of slice thicknesses on radiomic feature values in solid pulmonary nodules：a prospective patient study[J].Annals of Translational Medicine，2021，9（4）：279.
[15] YANG P，XU L，WAN Y，et al.Deep neural network-based approach to improving radiomics analysis reproducibility in liver cancer：effect on image resampling[J].Physics in Medicine & Biology，2021，66（16）：1-10.
[16] MEYER M，RONALD J，VERNUCCIO F，et al.Reproducibility of CT radiomic features within the same patient：influence of radiation dose and CT reconstruction settings[J].Radiology，2019，293（3）：583-591.
[17] FERNANDEZ P M，CERDA A L，SANGUESA N C，et al.MR denoising increases radiomic biomarker precision and reproducibility in oncologic imaging[J].Journal of Digital Imaging，2021，34（5）：1134-1145.
[18] JAUDET C，WEYTS K，LECHERVY A，et al.The impact of artificial intelligence CNN based denoising on FDG PET radiomics[J].Frontiers in Oncology，2021，11：1-9.
[19] CHEN J，WEE L，DEKKER A，et al.Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs[J].Journal of Applied Clinical Medical Physics，2022，23（10）：1-17.
[20] PAN Y，LIU M，LIAN C，et al.Synthesizing missing pet from MRI with cycle-consistent generative adversarial networks for Alzheimer’s disease diagnosis[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Cham：Springer，2018：455-463.
[21] MCCORMICK M，LIU X，JOMIER J，et al.ITK：enabling reproducible research and open science[J].Frontiers in Neuroinformatics，2014，8（13）：1-11.
[22] SZCZYPINSKI P M，STRZELECKI M，MATERKA A.Mazda-a software for texture analysis[C]//2007 International Symposium on Information Technology Convergence（ISITC 2007），2007：245-249.
[23] SZCZYPINSKI P M，STRZELECKI M，MATERKA A，et al.MaZda—a software package for image texture analysis[J].Computer Methods and Programs in Biomedicine，2009，94（1）：66-76.
[24] STRZELECKI M，SZCZYPINSKI P，MATERKA A，et al.A software tool for automatic classification and segmentation of 2D/3D medical images[J].Nuclear Instruments and Methods in Physics Research Section A：Accelerators，Spectrometers，Detectors and Associated Equipment，2013，702（4）：137-140.
[25] FEDOROV A，BEICHEL R，KALPATHY-CRAMER J，et al.3D Slicer as an image computing platform for the quantitative imaging network[J].Magnetic Resonance Imaging，2012，30（9）：1323-1341.
[26] 彭璟，罗浩宇，赵淦森，等.深度学习下的医学影像分割算法综述[J].计算机工程与应用，2021，57（3）：44-57.
PENG J，LUO H Y，ZHAO G S，et al.Survey of medical image segmentation algorithm in deep learning[J].Computer Engineering and Applications，2021，57（3）：44-57.
[27] HELLER N，ISENSEE F，MAIER-HEIN K H，et al.The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging：results of the KiTS19 challenge[J].Medical Image Analysis，2021，67（1）：1-16.
[28] PRATONDO A，CHUI C K，ONG S H.Integrating machine learning with region-based active contour models in medical image segmentation[J].Journal of Visual Communication and Image Representation，2017，43（1）：1-9.
[29] ZHENG Q，LI H，FAN B，et al.Integrating support vector machine and graph cuts for medical image segmentation[J].Journal of Visual Communication and Image Representation，2018，55（3）：157-165.
[30] LONG J，SHELHAMER E，DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2015：3431-3440.
[31] NIE D，WANG L，GAO Y，et al.STRAINet：spatially varying stochastic residual adversarial networks for MRI pelvic organ segmentation[J].IEEE Transactions on Neural Networks and Learning Systems，2019，30（5）：1552-1564.
[32] SCHLEMPER J，OKTAY O，SCHAAP M，et al.Attention gated networks：learning to leverage salient regions in medical images[J].Medical Image Analysis，2019，53（2）：197-207.
[33] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[34] HARALICK R M，SHANMUGAM K，DINSTEIN I H.Textural features for image classification[J].IEEE Transactions on Systems，Man，and Cybernetics，1973，SMC-3（6）：610-621.
[35] NANNI L，LUMINI A，BRAHNAM S.Local binary patterns variants as texture descriptors for medical image analysis[J].Artificial Intelligence in Medicine，2010，49（2）：117-125.
[36] THIBAULT G，ANGULO J，MEYER F.Advanced statistical matrices for texture characterization：application to cell classification[J].IEEE Transactions on Biomedical Engineering，2013，61（3）：630-637.
[37] MAYERHOEFER M E，MATERKA A，LANGS G，et al.Introduction to radiomics[J].Journal of Nuclear Medicine，2020，61（4）：488-495.
[38] JAYENDER J，GOMBOS E，CHIKARMANE S，et al.Statistical learning algorithm for in situ and invasive breast carcinoma segmentation[J].Computerized Medical Imaging and Graphics，2013，37（4）：281-292.
[39] VAN GRIETHUYSEN J J M，FEDOROV A，PARMAR C，et al.Computational radiomics system to decode the radiographic phenotype[J].Cancer Research，2017，77（21）：104-107.
[40] NIOCHE C，ORLHAC F，BOUGHDAD S，et al.LIFEx：a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity[J].Cancer Research，2018，78（16）：4786-4789.
[41] ZHANG L，FRIED D V，FAVE X J，et al.IBEX：an open infrastructure software platform to facilitate collaborative work in radiomics[J].Medical Physics，2015，42（3）：1341-1353.
[42] YANG M，YAN Y，WANG H.IMAge/enGINE：a freely available software for rapid computation of high-dimensional quantification[J].Quantitative Imaging in Medicine and Surgery，2019，9（2）：210-218.
[43] WANG Y，SHAO J，WANG P，et al.Deep learning radiomics to predict regional lymph node staging for hilar cholangiocarcinoma[J].Frontiers in Oncology，2021，11（10）：1-10.
[44] TRINH D L，KIM S H，YANG H J，et al.The efficacy of shape radiomics and deep features for glioblastoma survival prediction by deep learning[J].Electronics，2022，11（7）：1-13.
[45] XIE X，NIU J，LIU X，et al.A survey on incorporating domain knowledge into deep learning for medical image analysis[J].Medical Image Analysis，2021，69（1）：1-25.
[46] DASH M，LIU H.Feature selection for classification：a review[J].Intelligent Data Analysis，1997，1（3）：131-156.
[47] ABDI H，WILLIAMS L J.Principal component analysis[J].Wiley Interdisciplinary Reviews：Computational Statistics，2010，2（4）：433-459.
[48] DEMIRCIOGLU A.Benchmarking feature selection methods in radiomics[J].Investigative Radiology，2022，57（7）：433-443.
[49] TIAN Q，YAN L F，ZHANG X，et al.Radiomics strategy for glioma grading using texture features from multiparametric MRI[J].Journal of Magnetic Resonance Imaging，2018，48（6）：1518-1528.
[50] DE JONG E E C，SANDERS K J C，DEIST T M，et al.Can radiomics help to predict skeletal muscle response to chemotherapy in stage IV non-small cell lung cancer?[J].European Journal of Cancer，2019，120（19）：107-113.
[51] NASIEF H，ZHENG C，SCHOTT D，et al.A machine learning based delta-radiomics process for early prediction of treatment response of pancreatic cancer[J].NPJ Precision Oncology，2019，3（1）：1-10.
[52] MA Y，MA W，XU X，et al.How does the delta-radiomics better differentiate pre-invasive GGNs from invasive GGNs?[J].Frontiers in Oncology，2020，10（7）：1-7.
[53] ZHANG G M，HAN Y Q，WEI J W，et al.Radiomics based on mri as a biomarker to guide therapy by predicting upgrading of prostate cancer from biopsy to radical prostatectomy[J].Journal of Magnetic Resonance Imaging，2020，52（4）：1239-1248.
[54] WU Q，WANG S，LI L，et al.Radiomics analysis of computed tomography helps predict poor prognostic outcome in COVID-19[J].Theranostics，2020，10（16）：7231-7244.
[55] HUANG X，SHU J，YAN Y，et al.Feasibility of magnetic resonance imaging-based radiomics features for preoperative prediction of extrahepatic cholangiocarcinoma stage[J].European Journal of Cancer，2021，155（17）：227-235.
[56] TONG X，FENG X，PENG F，et al.Morphology-based radiomics signature：a novel determinant to identify multiple intracranial aneurysms rupture[J].Aging（Albany NY），2021，13（9）：13195-13210.
[57] EERTINK J J，VAN DE BRUG T，WIEGERS S E，et al. 18F-FDG PET baseline radiomics features improve the prediction of treatment outcome in diffuse large B-cell lymphoma[J].European Journal of Nuclear Medicine and Molecular Imaging，2022，49（3）：932-942.
[58] VAN DER LUBBE M，VAIDYANATHAN A，DE WIT M，et al.A non-invasive，automated diagnosis of Meniere’s disease using radiomics and machine learning on conventional magnetic resonance imaging：a multicentric，case-controlled feasibility study[J].Radiologia Medica，2022，127（1）：72-82.
[59] LI Z，HOLZGREVE A，UNTERRAINER L M，et al.Combination of pre-treatment dynamic[18F] FET PET radiomics and conventional clinical parameters for the survival stratification in patients with IDH-wildtype glioblastoma[J].European Journal of Nuclear Medicine and Molecular Imaging，2022：1-11.
[60] JOLISSAINT J S，WANG T，SOARES K C，et al.Machine learning radiomics can predict early liver recurrence after resection of intrahepatic cholangiocarcinoma[J].HPB（Oxford），2022，24（8）：1341-1350.
[61] BAO D，ZHAO Y，LI L，et al.A MRI-based radiomics model predicting radiation-induced temporal lobe injury in nasopharyngeal carcinoma[J].European Radiology，2022，32（10）：6910-6921.
[62] ZARAGORI T，OSTER J，ROCH V，et al.18F-FDOPA PET for the noninvasive prediction of glioma molecular parameters：a radiomics study[J].Journal of Nuclear Medicine，2022，63（1）：147-157.
[63] WANG T，SHE Y，YANG Y，et al.Radiomics for survival risk stratification of clinical and pathologic stage IA pure-solid non-small cell lung cancer[J].Radiology，2022，302（2）：425-434.
[64] WU W，LIAO S，LU Z.White blood cells image classification based on radiomics and deep learning[J].IEEE Access，2022，10：124036-124052.
[65] TIAN Y，KOMOLAFE T E，ZHENG J，et al.Assessing PD-L1 expression level via preoperative MRI in HCC based on integrating deep learning and Radiomics features[J].Diagnostics，2021，11（10）：1-15.
[66] LAMBIN P，LEIJENAAR R T H，DEIST T M，et al.Radiomics：the bridge between medical imaging and personalized medicine[J].Nature Reviews Clinical Oncology，2017，14（12）：749-762.
[67] PONSIGLIONE A，STANZIONE A，CUOCOLO R，et al.Cardiac CT and MRI radiomics：systematic review of the literature and radiomics quality score assessment[J].European Radiology，2022，32（11）：2629-2638.
[68] ZWANENBURG A，VALLIERES M，ABDALAH M A，et al.The image biomarker standardization initiative：standardized quantitative radiomics for high-throughput image-based phenotyping[J].Radiology，2020，295（2）：328-338.
[69] CRADDOCK C，BENHAJALI Y，CARLTON C，et al.The neuro bureau preprocessing initiative：open sharing of preprocessed neuroimaging data and derivatives[J].Frontiers in Neuroinformatics，2013，7（8）：27.
[70] BAID U，GHODASARA S，BILELLO M，et al.The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification[J].arXiv：2107.02314，2021.
[71] MENZE B H，JAKAB A，BAUER S，et al.The multimodal brain tumor image segmentation benchmark （BRATS）[J].IEEE Transactions on Medical Imaging，2014，34（10）：1993-2024.
[72] BAKAS S，AKBARI H，SOTIRAS A，et al.Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features[J].Scientific Data，2017，4（1）：1-13.
[73] WANG X，PENG Y，LU L，et al.ChestX-Ray8：hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2097-2106.
[74] HEATH M，BOWYER K，KOPANS D，et al.The digital database for screening mammography[C]//Proceedings of the Fifth International Workshop on Digital Mammography（IWDM-2000），2020：212-218.
[75] HEATH M，BOWYER K，KOPANS D，et al.Current status of the digital database for screening mammography[M]//Digital mammography.Dordrecht：Springer，1998：457-460.
[76] ARMATO III S G，MCLENNAN G，BIDAUT L，et al.The lung image database consortium（LIDC） and image database resource initiative（IDRI）：a completed reference database of lung nodules on CT scans[J].Medical Physics，2011，38（2）：915-931.
[77] RAJPURKAR P，IRVIN J，BAGUL A，et al.Mura：large dataset for abnormality detection in musculoskeletal radiographs[J].arXiv：1712.06957，2017.
[78] BAKR S，GEVAERT O，ECHEGARAY S，et al.A radiogenomic dataset of non-small cell lung cancer[J].Scientific Data，2018，5（1）：1-9.
[79] MARCUS D S，WANG T H，PARKER J，et al.Open access series of imaging studies（OASIS）：cross-sectional MRI data in young，middle aged，nondemented，and demented older adults[J].Journal of Cognitive Neuroscience，2007，19（9）：1498-1507.
[80] MARCUS D S，FOTENOS A F，CSERNANSKY J G，et al.Open access series of imaging studies：longitudinal MRI data in nondemented and demented older adults[J].Journal of Cognitive Neuroscience，2010，22（12）：2677-2684.
[81] LAMONTAGNE P J，BENZINGER T L S，MORRIS J C，et al.OASIS-3：longitudinal neuroimaging，clinical，and cognitive dataset for normal aging and Alzheimer disease[J].medRxiv，2019：1-37.
[82] KOENIG L N，DAY G S，SALTER A，et al.Select atrophied regions in Alzheimer disease（SARA）：an improved volumetric model for identifying Alzheimer disease dementia[J].NeuroImage：Clinical，2020，26（3）：1-33.
[83] YANG X，HE X，ZHAO J，et al.COVID-CT-dataset：a CT scan dataset about COVID-19[J].arXiv：2003.13865，2020.
[84] BULTEN W，KARTASALO K，CHEN P H C，et al.Artificial intelligence for diagnosis and Gleason grading of prostate cancer：the PANDA challenge[J].Nature Medi-cine，2022，28（1）：154-163.