Shallow and deep learning classifiers in medical image analysis

Francesco Prinzi1,2, Tiziana Currieri2, Salvatore Gaglio3,4, Salvatore Vitabile2
1Department of Computer Science and Technology, University of Cambridge, Cambridge, UK
2Department of Biomedicine, Neuroscience and Advanced Diagnostics (BiND), University of Palermo, Palermo, Italy
3Institute for High-Performance Computing and Networking, National Research Council (ICAR-CNR), Palermo, Italy
4Department of Engineering, University of Palermo, Palermo, Italy

Tóm tắt

An increasingly strong connection between artificial intelligence and medicine has enabled the development of predictive models capable of supporting physicians’ decision-making. Artificial intelligence encompasses much more than machine learning, which nevertheless is its most cited and used sub-branch in the last decade. Since most clinical problems can be modeled through machine learning classifiers, it is essential to discuss their main elements. This review aims to give primary educational insights on the most accessible and widely employed classifiers in radiology field, distinguishing between “shallow” learning (i.e., traditional machine learning) algorithms, including support vector machines, random forest and XGBoost, and “deep” learning architectures including convolutional neural networks and vision transformers. In addition, the paper outlines the key steps for classifiers training and highlights the differences between the most common algorithms and architectures. Although the choice of an algorithm depends on the task and dataset dealing with, general guidelines for classifier selection are proposed in relation to task analysis, dataset size, explainability requirements, and available computing resources. Considering the enormous interest in these innovative models and architectures, the problem of machine learning algorithms interpretability is finally discussed, providing a future perspective on trustworthy artificial intelligence. Relevance statement The growing synergy between artificial intelligence and medicine fosters predictive models aiding physicians. Machine learning classifiers, from shallow learning to deep learning, are offering crucial insights for the development of clinical decision support systems in healthcare. Explainability is a key feature of models that leads systems toward integration into clinical practice. Key points • Training a shallow classifier requires extracting disease-related features from region of interests (e.g., radiomics). • Deep classifiers implement automatic feature extraction and classification. • The classifier selection is based on data and computational resources availability, task, and explanation needs.

Từ khóa


Tài liệu tham khảo

Shah SM, Khan RA, Arif S, Sajid U (2022) Artificial intelligence for breast cancer analysis: trends & directions. Comput Biol Med 142:105221. https://doi.org/10.1016/j.compbiomed.2022.105221 Martin-Isla C, Campello VM, Izquierdo C et al (2020) Image-based cardiac diagnosis with machine learning: a review. Front Cardiovasc Med 7:1. https://doi.org/10.3389/fcvm.2020.00001 Liang X, Yu X, Gao T (2022) Machine learning with magnetic resonance imaging for prediction of response to neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis. Eur J Radiol 150:110247. https://doi.org/10.1016/j.ejrad.2022.110247 Hosny A, Parmar C, Quackenbush J et al (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510. https://doi.org/10.1038/s41568-018-0016-5 Rezazade Mehrizi MH, van Ooijen P, Homan M (2021) Applications of artificial intelligence (AI) in diagnostic radiology: a technography study. Eur Radiol 31:1805–1811. https://doi.org/10.1007/s00330-020-07230-9 Xu Y, Zhou Y, Sekula P, Ding L (2021) Machine learning in construction: from shallow to deep learning. Dev Built Environ 6:100045. https://doi.org/10.1016/j.dibe.2021.100045 Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88. https://doi.org/10.1016/j.media.2017.07.005 Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169 Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446. https://doi.org/10.1016/j.ejca.2011.11.036 Erickson BJ, Korfiatis P, Akkus Z, Kline TL (2017) Machine learning for medical imaging. Radiographics 37:505–515. https://doi.org/10.1148/rg.2017160130 Militello C, Rundo L, Dimarco M et al (2022) Robustness analysis of DCE-MRI-derived radiomic features in breast masses: assessing quantization levels and segmentation agreement. Appl Sci 12:5512. https://doi.org/10.3390/app12115512 Goodfellow I, Bengio Y, Courville A (2016) Deep learning, vol. 1.MIT press, Cambridge Kocak B, Baessler B, Bakas S et al (2023) CheckList for EvaluAtion of Radiomics research (CLEAR): a step-by-step reporting guideline for authors and reviewers endorsed by ESR and EuSoMII. Insights Imaging 14:1–13. https://doi.org/10.1186/s13244-023-01415-8 Mongan J, Moy L, Kahn CE Jr (2020) Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029. https://doi.org/10.1148/ryai.2020200029 Luo G (2016) A review of automatic selection methods for machine learning algorithms and hyper-parameter values. Netw Model Anal Health Inform Bioinforma 5:1–16. https://doi.org/10.1007/s13721-016-0125-6 Probst P, Boulesteix A-L, Bischl B (2019) Tunability: importance of hyperparameters of machine learning algorithms. J Mach Learn Res 20:1934–1965. https://doi.org/10.48550/arXiv.1802.09596 Reed R, MarksII RJ (1999) Neural smithing: supervised learning in feedforward artificial neural networks. MIT Press, Cambridge Prinzi F, Militello C, Scichilone N et al (2023) Explainable machine-learning models for COVID-19 prognosis prediction using clinical, laboratory and radiomic features. IEEE Access 11:121492–121510. https://doi.org/10.1109/ACCESS.2023.3327808 Junior JRF, Koenigkam-Santos M, Cipriano FEG et al (2018) Radiomics-based features for pattern recognition of lung cancer histopathology and metastases. Comput Methods Programs Biomed 159:23–30. https://doi.org/10.1016/j.cmpb.2018.02.015 Nam KJ, Park H, Ko ES et al (2019) Radiomics signature on 3T dynamic contrast-enhanced magnetic resonance imaging for estrogen receptor-positive invasive breast cancers: preliminary results for correlation with oncotype DX recurrence scores. Medicine (Baltimore) 98:e15871. https://doi.org/10.1097/MD.0000000000015871 Lee S-H, Park H, Ko ES (2020) Radiomics in breast imaging from techniques to clinical applications: a review. Korean J Radiol 21:779. https://doi.org/10.3348/kjr.2019.0855 Liu M, Mao N, Ma H et al (2020) Pharmacokinetic parameters and radiomics model based on dynamic contrast enhanced MRI for the preoperative prediction of sentinel lymph node metastasis in breast cancer. Cancer Imaging 20:1–8. https://doi.org/10.1186/s40644-020-00342-x Zhou J, Zhang Y, Chang K-T et al (2020) Diagnosis of benign and malignant breast lesions on DCE-MRI by using radiomics and deep learning with consideration of peritumor tissue. J Magn Reson Imaging 51:798–809. https://doi.org/10.1002/jmri.26981 Militello C, Rundo L, Dimarco M et al (2022) 3D DCE-MRI radiomic analysis for malignant lesion prediction in breast cancer patients. Acad Radiol 29:830–840. https://doi.org/10.1016/j.acra.2021.08.024 Papanikolaou N, Matos C, Koh DM (2020) How to develop a meaningful radiomic signature for clinical use in oncologic patients. Cancer Imaging 20:1–10. https://doi.org/10.1186/s40644-020-00311-4 Santhosh Baboo S, Amirthapriya M (2022) Comparison of machine learning techniques on Twitter emotions classification. SN Comput Sci 3:1–8. https://doi.org/10.1007/s42979-021-00889-x Vallieres M, Kay-Rivest E, Perrin LJ et al (2017) Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep 7:10117. https://doi.org/10.1038/s41598-017-10371-5 Wang M, Feng Z, Zhou L et al (2021) Computed-tomography-based radiomics model for predicting the malignant potential of gastrointestinal stromal tumors preoperatively: a multi-classifier and multicenter study. Front Oncol 11:582847. https://doi.org/10.3389/fonc.2021.582847 Wu S, Zheng J, Li Y et al (2018) Development and validation of an MRI-based radiomics signature for the preoperative prediction of lymph node metastasis in bladder cancer. EBioMedicine 34:76–84. https://doi.org/10.1016/j.ebiom.2018.07.029 Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. https://doi.org/10.1007/BF00994018 Joachims T (2002) Learning to classify text using support vector machines, vol. 668. Springer, Berlin Rokach L (2010) Ensemble-based classifiers. Artif Intell Rev 33:1–39. https://doi.org/10.1007/s10462-009-9124-7 Ghiasi MM, Zendehboudi S (2021) Application of decision tree-based ensemble learning in the classification of breast cancer. Comput Biol Med 128:104089. https://doi.org/10.1016/j.compbiomed.2020.104089 Podgorelec V, Kokol P, Stiglic B, Rozman I (2002) Decision trees: an overview and their use in medicine. J Med Syst 26:445–463. https://doi.org/10.1023/a:1016409317640 Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324 Oshiro TM, Perez PS, Baranauskas JA (2012) How many trees in a random forest? In: Mach Learn Data Min Pattern Recognit 8th Int Conf MLDM 2012 Berl Ger July 13-20 2012 Proc 8. pp 154–168. https://doi.org/10.1007/978-3-642-31537-4_13 Probst P, Boulesteix A-L (2017) To tune or not to tune the number of trees in random forest. J Mach Learn Res 18:6673–6690. https://doi.org/10.48550/arXiv.1705.0565 Tang F, Ishwaran H (2017) Random forest missing data algorithms. Stat Anal Data Min ASA Data Sci J 10:363–377. https://doi.org/10.1002/sam.11348 Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38:367–378. https://doi.org/10.1016/S0167-9473(01)00065-2 Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proc 22nd Acm Sigkdd Int Conf Knowl Discov Data Min. pp 785–794. https://doi.org/10.48550/arXiv.1603.02754 Sheridan RP, Wang WM, Liaw A et al (2016) Extreme gradient boosting as a method for quantitative structure–activity relationships. J Chem Inf Model 56:2353–2360. https://doi.org/10.1021/acs.jcim.6b00591 Davies T, Louie JCY, Ndanuko R et al (2022) A machine learning approach to predict the added-sugar content of packaged foods. J Nutr 152:343–349. https://doi.org/10.1093/jn/nxab341 Abu Alfeilat HA, Hassanat AB, Lasassmeh O et al (2019) Effects of distance measure choice on k-nearest neighbor classifier performance: a review. Big Data 7:221–248. https://doi.org/10.1089/big.2018.0175 Deng L, Yu D (2014) Deep Learning: methods and applications. Found Trends Signal Process 7:197–387. https://doi.org/10.1561/2000000039 McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133. https://doi.org/10.1007/BF02478259 Apicella A, Donnarumma F, Isgrò F, Prevete R (2021) A survey on modern trainable activation functions. Neural Netw 138:14–32. https://doi.org/10.1016/j.neunet.2021.01.026 Li Z, Liu F, Yang W et al (2021) A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2021.3084827 Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2:303–314. https://doi.org/10.1007/BF02551274 Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4:251–257. https://doi.org/10.1016/0893-6080(91)90009-T Prinzi F, Militello C, Conti V, Vitabile S (2023) Impact of wavelet kernels on predictive capability of radiomic features: a case study on COVID-19 chest X-ray images. J Imaging 9:32. https://doi.org/10.3390/jimaging9020032 Anwar SM, Majid M, Qayyum A et al (2018) Medical image analysis using convolutional neural networks: a review. J Med Syst 42:226. https://doi.org/10.1007/s10916-018-1088-1 Kharazmi P, Zheng J, Lui H et al (2018) A computer-aided decision support system for detection and localization of cutaneous vasculature in dermoscopy images via deep feature learning. J Med Syst 42:33. https://doi.org/10.1007/s10916-017-0885-2 Premaladha J, Ravichandran K (2016) Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algorithms. J Med Syst 40:1–12. https://doi.org/10.1007/s10916-016-0460-2 Yu H, Yang LT, Zhang Q et al (2021) Convolutional neural networks for medical image analysis: state-of-the-art, comparisons, improvement and perspectives. Neurocomputing 444:92–110. https://doi.org/10.1016/j.neucom.2020.04.157 Coady J, O’Riordan A, Dooly G et al (2019) An overview of popular digital image processing filtering operations. In: 2019 13th International conference on sensing technology (ICST), Sydney, NSW, Australia, pp. 1-5 Nirthika R, Manivannan S, Ramanan A, Wang R (2022) Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study. Neural Comput Appl 34:5321–5347. https://doi.org/10.1007/s00521-022-06953-8 Dosovitskiy A, Beyer L, Kolesnikov A, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. ArXiv Prepr ArXiv201011929. https://doi.org/10.48550/arXiv.2010.11929 Shamshad F, Khan S, Zamir SW, et al (2023) Transformers in medical imaging: a survey. Med Image Anal 102802. https://doi.org/10.48550/arXiv.2201.09873 Li J, Chen J, Tang Y, et al (2023) Transforming medical imaging with transformers? A comparative review of key properties, current progresses, and future perspectives. Med Image Anal 102762. https://doi.org/10.48550/arXiv.2206.01136 Wu B, Xu C, Dai X, et al (2020) Visual transformers: token-based image representation and processing for computer vision. ArXiv Prepr ArXiv200603677. https://doi.org/10.48550/arXiv.2006.03677 Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? https://doi.org/10.48550/arXiv.1411.1792 Torrey L, Shavlik J (2009) Transfer learning. In: Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. Imprint of: IGI Publishing. Hershey, PA Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1:67–82. https://doi.org/10.1109/4235.585893 Safdari R, Deghatipour A, Gholamzadeh M, Maghooli K (2022) Applying data mining techniques to classify patients with suspected hepatitis C virus infection. Intell Med 2:193–198. https://doi.org/10.1016/j.imed.2021.12.003 Bishop CM, Nasrabadi NM (2006) Pattern recognition and machine learning. Springer-Verlag New York, Inc. Murphy KP (2012) Machine learning: a probabilistic perspective. MIT press, Cambridge Chalkidou A, O’Doherty MJ, Marsden PK (2015) False discovery rates in PET and CT studies with texture features: a systematic review. PLoS One 10:e0124165. https://doi.org/10.1371/journal.pone.0124165 Di Stefano V, Prinzi F, Luigetti M et al (2023) Machine learning for early diagnosis of ATTRv amyloidosis in non-endemic areas: a multicenter study from Italy. Brain Sci 13:805. https://doi.org/10.3390/brainsci13050805 Kabiraj S, Raihan M, Alvi N et al (2020) Breast cancer risk prediction using XGBoost and random forest algorithm. In: 2020 11th international conference on computing, communication and networking technologies (ICCCNT), Kharagpur, India, pp. 1-4 Xie X, Yang M, Xie S et al (2021) Early prediction of left ventricular reverse remodeling in first-diagnosed idiopathic dilated cardiomyopathy: a comparison of linear model, random forest, and extreme gradient boosting. Front Cardiovasc Med 8:684004. https://doi.org/10.3389/fcvm.2021.684004 Prinzi F, Orlando A, Gaglio S, et al (2022) ML-based radiomics analysis for breast cancer classification in DCE-MRI. Appl Intell Inform 144–158. https://doi.org/10.1007/978-3-031-24801-6_11 LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539 Sarker IH (2021) Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput Sci 2:420. https://doi.org/10.1007/s42979-021-00815-1 Soda P, D’Amico NC, Tessadori J et al (2021) AIforCOVID: predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. An Italian multicentre study. Med Image Anal 74:102216. https://doi.org/10.1016/j.media.2021.102216 Chugh G, Kumar S, Singh N (2021) Survey on machine learning and deep learning applications in breast cancer diagnosis. Cogn Comput 1–20. https://doi.org/10.1007/s12559-020-09813-6 Aly GH, Marey M, El-Sayed SA, Tolba MF (2021) YOLO based breast masses detection and classification in full-field digital mammograms. Comput Methods Programs Biomed 200:105823. https://doi.org/10.1016/j.cmpb.2020.105823 Sun C, Shrivastava A, Singh S, Gupta A (2017) Revisiting unreasonable effectiveness of data in deep learning era. Proc IEEE Int Conf Comput Vis 843–852. https://doi.org/10.1109/ICCV.2017.97 Prinzi F, Insalaco M, Orlando A, et al (2024) A YOLO-based model for breast cancer detection in mammograms. Cogn Comput 16:107–120. https://doi.org/10.1007/s12559-023-10189-6 Alwosheel A, van Cranenburgh S, Chorus CG (2018) Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis. J Choice Model 28:167–182. https://doi.org/10.1016/j.jocm.2018.07.002 Alicioglu G, Sun B (2022) A survey of visual analytics for explainable artificial intelligence methods. Comput Graph 102:502–520. https://doi.org/10.1016/j.cag.2021.09.002 Lepri B, Oliver N, Letouzé E et al (2018) Fair, transparent, and accountable algorithmic decision-making processes: the premise, the proposed solutions, and the open challenges. Philos Technol 31:611–627. https://doi.org/10.1007/s13347-017-0279-x Theunissen M, Browning J (2022) Putting explainable AI in context: institutional explanations for medical AI. Ethics Inf Technol 24:23. https://doi.org/10.1007/s10676-022-09649-8 Weld DS, Bansal G (2019) The challenge of crafting intelligible intelligence. Commun ACM 62:70–79. https://doi.org/10.48550/arXiv.1803.04263 Guidotti R, Monreale A, Ruggieri S et al (2018) A survey of methods for explaining black box models. ACM Comput Surv CSUR 51:1–42. https://doi.org/10.1145/3236009 Gu J, Tresp V (2019) Saliency methods for explaining adversarial attacks. ArXiv Prepr ArXiv190808413. https://doi.org/10.48550/arXiv.1908.08413 Zhang J, Chao H, Kalra MK, et al (2021) Overlooked trustworthiness of explainability in medical AI. medRxiv. https://doi.org/10.1101/2021.12.23.21268289 Chatila R, Dignum V, Fisher M, et al (2021) Trustworthy AI. Reflect Artif Intell Humanity 13–39. https://doi.org/10.1007/978-3-030-69128-8_2 Müller VC (2020) Ethics of artificial intelligence and robotics. In: Zalta EN (ed) The Stanford encyclopedia of philosophy, Fall 2020. Metaphysics Research Lab, Stanford University, Stanford, CA Addis C, Kutar M (2020) General Data Protection Regulation (GDPR), artificial intelligence (AI) and UK organisations: a year of implementation of GDPR. In: UK Academy for Information Systems Conference Proceedings 2020 Lipton ZC (2018) The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 16:31–57. https://doi.org/10.48550/arXiv.1606.03490 Ó Fathaigh R (2019) European Commission: high-level expert group on artificial intelligence publishes ethics guidelines for trustworthy AI. In: IRIS. pp 12–13