PRACA PRZEGLĄDOWA
Zastosowania sztucznej inteligencji (AI) w medycynie
Więcej
Ukryj
1
Uniwersytet Medyczny w Lublinie, Polska
Med Og Nauk Zdr. 2021;27(3):213-219
SŁOWA KLUCZOWE
DZIEDZINY
STRESZCZENIE
Wprowadzenie i cel:
Problematyka sztucznej inte-ligencji jest stosunkowo nowym zagadnieniem w naukach medycznych. Regularnie pojawiają się publikacje dotyczące jej zastosowań w medycynie. Często dotyczą one wykorzystania algorytmów głębokiego uczenia, opartego na sieciach neuronowych, które są w stanie rozpoznać zmiany chorobowe widoczne na obrazie. Celem pracy jest omówienie możliwości wykorzystania sztucznej inteligencji w medycynie, szczególnie w radiologii i patomorfologii, oraz przedstawienie osiąganych dzięki niej wyników.
Metody przeglądu:
W marcu 2021 roku przeszukano bazę danych Medline (PubMed) oraz Google Scholar przy użyciu słów kluczowych: „artificial intelligence”, „deep learning”, „machine learning”, „digital pathology”, „convolutional neural network”. Wybrano prace opublikowane w języku angielskim, w latach 2015–2021.
Opis stanu wiedzy:
Istnieje wiele doniesień o zastosowaniach sztucznej inteligencji w medycynie, głównie w dziedzinie radiologii i patomorfologii. Badania pokazują, że samouczące się algorytmy są w stanie z dokładnością zbliżoną do oceny przeprowadzonej przez lekarzy, a niekiedy nawet większą, wykryć zmiany chorobowe na zdjęciu rentgenowskim, tomografii komputerowej czy na zdjęciu preparatu mikroskopowego. W przedstawionych badaniach zauważalne są istotne korzyści wynikające z synergistycznego działania lekarzy i sztucznej inteligencji.
Podsumowanie:
Wyniki uzyskiwane przez algorytmy oparte na sztucznej inteligencji świadczą o tym, że może ona usprawniać proces diagnozowania pacjentów, głównie dzięki uzupełnianiu wiedzy i doświadczenia lekarzy. Ważną kwestią jest również to, że korzystanie przez lekarzy z samouczących się algorytmów zmniejsza ryzyko popełnienia błędu ludzkiego, np. niezauważenia zmiany chorobowej widocznej na zdjęciu rentgenowskim.
Introduction and objective:
Artificial intelligence is a relatively new field of medical sciences. Its application in medicine is described in regularly appearing publications, which often focus on the use of deep learning algorithms based on neural networks that are capable of recognizing pathological changes in images. The aim of this study is to discuss possibilities of application of artificial intelligence in medicine, particularly radiology and pathomorphology, and to present the results achieved.
Review methods:
Databases of Medline (PubMed) and Google Scholar were searched using keywords: ‘artificial intelligence’, ‘deep learning’, ‘machine learning’, ‘digital pathology’, and ‘convolutional neural network’. The search was undertaken in March 2021. Studies published in English during 2015–2021 were selected.
Brief description of the state of knowledge:
There are many reports concerning the use of artificial intelligence in various fields of medicine, such as radiology and pathomorphology. Multiple research shows that self-learning algorithms are capable of finding pathologies in radiograms, computed tomography scans, or microscopic slides with accuracy equal to or even better than physicians. The study indicates significant advantages resulting from synergic cooperation of artificial intelligence and physicians.
Summary:
Results achieved by artificial intelligence based algorithms provide evidence for improvement of patient diagnosis, predominantly by supplementation of physicians’ knowledge and experience. It is also an important fact that the use of AI decreases the risk of medical error, e.g. failure to recognize a pathological change visible on RTG.
REFERENCJE (48)
5.
He J, Baxter SL, Xu J, et al. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019; 25(1): 30–3.
https://doi.org/10.1038/s41591....
6.
Holzinger A, Langs G, Denk H, et al. Causability and explainability of artificial intelligence in medicine. WIREs Data Mining Knowl Discov. 2019; 9: e1312.
https://doi.org/10.1002/widm.1....
9.
Liang G, Zheng L. A transfer learning method with deep residual ne-twork for pediatric pneumonia diagnosis. Comput Methods Programs Biomed. 2020; 187: 104964.
https://doi.org/10.1016/j.cmpb....
10.
Schwyzer M, Martini K, Skawran S, et al. Pneumonia Detection in Chest X-Ray Dose-Equivalent CT: Impact of Dose Reduction on Detectability by Artificial Intelligence. Acad Radiol. 2020; S1076-6332(20)30338-X.
https://doi.org/10.1016/j.acra....
11.
Shih G, Wu CC, Halabi SS. Augmenting the National Institutes of Health Chest Radiograph Dataset with Expert Annotations of Possible Pneumonia. Radiology: Artificial Intelligence. 2019; 1(1): e180041.
https://doi.org/10.1148/ryai.2....
12.
Depeursinge A, Chin AS, Leung AN, et al. Automated classification of usual interstitial pneumonia using regional volumetric texture analysis in high-resolution computed tomography. Invest Radiol. 2015; 50(4): 261–267.
https://doi.org/10.1097/RLI.00....
13.
Luján-García JE, Yáñez-Márquez C, Villuendas-Rey Y, et al. A Transfer Learning Method for Pneumonia Classification and Visualization. Applied Sciences. 2020; 10(8): 2908.
https://doi.org/10.3390/app100....
14.
Gabruseva T, Poplavskiy D, Kalinin A. Deep Learning for Automatic Pneumonia Detection. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 1436–1443.
https://doi.org/10.1109/CVPRW5....
15.
Warjri L, Shah A. India and Africa: Charting a Post-COVID-19 Future. ORF Special Report No. 111, June 2020, Observer Research Foundation.
https://www.orfonline.org/wp-c... (access: 2021.03.30).
16.
Schwyzer M, Martini K, Skawran S, et al. Pneumonia Detection in Chest X-Ray Dose-Equivalent CT: Impact of Dose Reduction on Detectabi-lity by Artificial Intelligence. Academic Radiology. 2020.
https://doi.org/10.1016/j.acra....
17.
Xiong F, Wang Y, You T, et al. The clinical classification of patients with COVID-19 pneumonia was predicted by Radiomics using chest CT. Medicine (Baltimore). 2021; 100(12): e25307.
https://doi.org/10.1097/md.000....
18.
Liu C, Wang X, Liu C, et al. Differentiating novel coronavirus pneu-monia from general pneumonia based on machine learning. BioMed Eng OnLine. 2020; 19: 66.
https://doi.org/10.1186/s12938....
19.
Wang H, Wang L, Lee EH, et al. Decoding COVID-19 pneumonia: comparison of deep learning and radiomics CT image signatures. Eur J Nucl Med Mol Imaging. 2020; 1–9.
https://doi.org/10.1007/s00259....
20.
Tan W, Liu P, Li X, et al. Classification of COVID-19 pneumonia from chest CT images based on reconstructed super resolution images and VGG neural network. Health Inf Sci Syst. 2021; 9(1): 10.
https://doi.org/10.1007/s13755....
22.
Fischer AM, Varga-Szemes A, van Assen M, et al. Comparison of Artificial Intelligence-Based Fully Automatic Chest CT Emphysema Quantification to Pulmonary Function Testing. AJR Am J Roentgenol. 2020; 214(5): 1065–1071.
https://doi.org/10.2214/AJR.19....
23.
Labaki WW, Han MK. Artificial Intelligence and Chest Imaging. Will Deep Learning Make Us Smarter?. Am J Respir Crit Care Med. 2018; 197(2): 148–150.
https://doi.org/10.1164/rccm.2....
24.
Taylor AG, Mielke C, Mongan J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolu-tional neural networks: A retrospective study. PLoS Med. 2018; 15(11): e1002697.
https://doi.org/10.1371/journa....
25.
Kitamura G, Deible C. Retraining an open-source pneumothorax de-tecting machine learning algorithm for improved performance to medical images. Clin Imaging. 2020; 61: 15–19.
https://doi.org/10.1016/j.clin....
26.
Diab N, Gershon AS, Sin DD, et al. Underdiagnosis and Overdiagnosis of Chronic Obstructive Pulmonary Disease. Am J Respir Crit Care Med. 2018; 198(9): 1130–1139.
https://doi.org/10.1164/rccm.2....
27.
Tang LYW, Coxson HO, Lam S, Leipsic J, Tam RC, Sin DD. Towards large-scale case-finding: training and validation of residual networks for detection of chronic obstructive pulmonary disease using low-dose CT. Lancet Digit Health. 2020; 2(5): e259-e267.
https://doi.org/10.1016/S2589-...-.
29.
González G, Ash SY, Vegas-Sánchez-Ferrero G, et al. Disease Staging and Prognosis in Smokers Using Deep Learning in Chest Computed Tomography. Am J Respir Crit Care Med. 2018; 197(2): 193–203.
https://doi.org/10.1164/rccm.2....
30.
Rodriguez-Ruiz A, Lång K, Gubern-Merida A, et al. Stand-Alone Ar-tificial Intelligence for Breast Cancer Detection in Mammography: Comparison With 101 Radiologists. J Natl Cancer Inst. 2019; 111(9): 916–922.
https://doi.org/10.1093/jnci/d....
31.
Geras KJ, Mann RM, Moy L. Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Per-spectives. Radiology. 2019; 293(2): 246–259.
https://doi.org/10.1148/radiol....
32.
Watanabe AT, Lim V, Vu HX, et al. Improved Cancer Detection Using Artificial Intelligence: a Retrospective Evaluation of Missed Cancers on Mammography. J Digit Imaging. 2019; 32(4): 625–637.
https://doi.org/10.1007/s10278....
33.
Kim HE, Kim HH, Han BK, et al. Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study. Lancet Digit Health. 2020; 2(3): e138-e148.
https://doi.org/10.1016/S2589-....
34.
Langerhuizen DWG, Janssen SJ, Mallee WH, et al. What Are the Appli-cations and Limitations of Artificial Intelligence for Fracture Detection and Classification in Orthopaedic Trauma Imaging? A Systematic Review. Clin Orthop Relat Res. 2019; 477(11): 2482–2491.
https://doi.org/10.1097/CORR.0....
35.
Michelson JD. CORR Insights®: What Are the Applications and Limi-tations of Artificial Intelligence for Fracture Detection and Classifi-cation in Orthopaedic Trauma Imaging? A Systematic Review. Clin Orthop Relat Res. 2019; 477(11): 2492–2494.
https://doi.org/10.1097/CORR.0....
36.
Olczak J, Fahlberg N, Maki A, et al. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop. 2017; 88(6): 581–586.
https://doi.org/10.1080/174536....
37.
Murata K, Endo K, Aihara T, et al. Artificial intelligence for the detection of vertebral fractures on plain spinal radiography. Sci Rep. 2020; 10(1): 20031.
https://doi.org/10.1038/s41598....
38.
Gan K, Xu D, Lin Y, et al. Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta Orthop. 2019; 90(4): 394–400.
https://doi.org/10.1080/174536....
39.
Gyftopoulos S, Lin D, Knoll F, et al. Artificial Intelligence in Muscu-loskeletal Imaging: Current Status and Future Directions. AJR Am J Roentgenol. 2019; 213(3): 506–513.
https://doi.org/10.2214/AJR.19....
41.
Prochorec-Sobieszek M, Szumera-Ciećkiewicz A. Aktualny stan wiedzy na temat patomorfologii cyfrowej. Hematologia. 2017; 8(1): 1–11.
https://doi.org/10.5603/hem.20....
42.
Farahani N, Parwani A, Pantanowitz L. Whole slide imaging in pat-hology: advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine International. 2015; 7: 23–33.
https://doi.org/10.2147/PLMI.S....
43.
Bulten W, Balkenhol M, Belinga JA, et al. Artificial intelligence assi-stance significantly improves Gleason grading of prostate biopsies by pathologists. Mod Pathol. 2021; 34(3): 660–671.
https://doi.org/10.1038/s41379....
44.
Ström P, Kartasalo K, Olsson H, et al. Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagno-stic study. Lancet Oncol. 2020; 21(2): 222–232.
https://doi.org/10.1016/S1470-....
45.
Ertosun MG, Rubin DL. Automated grading of gliomas using deep learning in digital pathology images: a modular approach with en-semble of convolutional neural networks. AMIAAnnu Symp Proc. 2015; 1: 1899–1908.
46.
Yang H, Chen L, Cheng Z, et al. Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study. BMC Med. 2021; 19(1): 80.
https://doi.org/10.1186/s12916....
47.
Syrykh C, Abreu A, Amara N, et al. Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning. npj Digit Med. 2020; 3(1): 63.
https://doi.org/10.1038/s41746....