The integration of artificial intelligence (AI) technology within the health industry is increasing. This educational piece discusses the implementation of AI and its impact on sonography. The authors investigate how AI may influence the profession and provide examples of how ultrasound imaging may be enhanced and innovated by integrating AI technology. This article highlights challenges related to the application of AI and provides insight into how they could be addressed. The critical distinction between the role of a sonographer and the reporting specialist in the context of AI is highlighted as a key issue for those developing, researching, and evaluating AI systems. A key recommendation is for the sonography community to address ultrasound education, particularly how AI knowledge could be incorporated into university education. This is an important consideration that should be extended to practising professionals as they may be involved in evaluating the efficiency and methodologies used in new research that may incorporate AI technologies.
BuchVHAhmedIMaruthappuM. Artificial intelligence in medicine: current trends and future possibilities. Br J Gen Pract2018; 68: 143–144.
2.
DreyerKAllenB. Artificial intelligence in health care: brave new world or golden opportunity?J Am Coll Radiol2018; 15: 655–657.
3.
ThrallJHLiXLiQ, et al. Artificial intelligence and machine learning in radiology: opportunities, challenges, pitfalls, and criteria for success. J Am Coll Radiol2018; 15: 504–508.
American College of Radiology Data Science Institute® (DSI), https://www.acrdsi.org/ (accessed 30 July 2021).
6.
WangKLuXZhouH, et al. Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut2019; 68: 729–741.
7.
Jo DelaneyL. Patient-centred care as an approach to improving health care in Australia. Collegian2018; 25: 119–123.
ChoiRYCoynerASKalpathy-CramerJ, et al. Introduction to machine learning, neural networks, and deep learning. Transl Vis Sci Technol2020; 9: 14.
13.
AltmanDG. Practical statistics for medical research. London: Chapman & Hall/CRC, 1999.
14.
EdwardsCAllenHChamunyongaC. Correlation does not imply agreement: a cautionary tale for researchers and reviewers. Melbourne, VIC, Australia: Australasian Sonographers Association, 2021.
15.
BreimanL. Statistical modeling: the two cultures (with comments and a rejoinder by the author). Statist Sci2001; 16: 199–231.
16.
ObermeyerZEmanuelEJ. Predicting the future – big data, machine learning, and clinical medicine. N Engl J Med2016; 375: 1216–1219.
17.
BanerjeeIBhimireddyARBurnsJL, et al. Reading race: AI recognises patient’s racial identity in medical images, 2021, https://arxiv.org/abs/2107.10356
18.
LeCunYBengioYHintonG. Deep learning. Nature2015; 521: 436–444.
19.
CurrieGHawkKERohrenE, et al. Machine learning and deep learning in medical imaging: intelligent imaging. J Med Imag Radiat Sci2019; 50: 477–487.
20.
ZhangQZhangMChenT, et al. Recent advances in convolutional neural network acceleration. Neurocomputing2019; 323: 37–51.
21.
FourcadeAKhonsariRH. Deep learning in medical image analysis: a third eye for doctors. J Stomatol Oral Maxillofac Surg2019; 120: 279–288.
22.
SofferSBen-CohenAShimonO, et al. Convolutional neural networks for radiologic images: a radiologist’s guide. Radiology2019; 290: 590–606.
23.
OrenOGershBJBhattDL. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. Lancet Digit Health2020; 2: e486–e488.
24.
ItriJNTappouniRRMcEachernRO, et al. Fundamentals of diagnostic error in imaging. Radiographics2018; 38: 1845–1865.
25.
Van LeeuwenKGSchalekampSRuttenMJCM, et al. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence. Eur Radiol2021; 31: 3797–3804.
26.
YiPHArunAHafezi-NejadN, et al. Can AI distinguish a bone radiograph from photos of flowers or cars? Evaluation of bone age deep learning model on inappropriate data inputs. Skeletal Radiol2021; 51: 401–406.
27.
ShenYTChenLYueWW, et al. Artificial intelligence in ultrasound. Eur J Radiol2021; 139: 109717.
28.
BrattainLJTelferBADhyaniM, et al. Machine learning for medical ultrasound: status, methods, and future opportunities. Abdom Radiol2018; 43: 786–799.
29.
KimKSongMKKimEK, et al. Clinical application of S-detect to breast masses on ultrasonography: a study evaluating the diagnostic performance and agreement with a dedicated breast radiologist. Ultrasonography2017; 36: 3–9.
30.
LooneyPStevensonGNNicolaidesKH, et al. Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning. JCI Insight2018; 3: 120178.
31.
ZhangJGajjalaSAgrawalP, et al. Fully automated echocardiogram interpretation in clinical practice. Circulation2018; 138: 1623–1635.
32.
BridgePBridgeR. Artificial intelligence in radiotherapy: a philosophical perspective. J Med Imag Radiat Sci2019; 50: S27–S31.
33.
ChaichanalapRHanprasertpongT. Success rate to complete optimal 20 + 2 ISUOG planes for foetal ultrasonographic structural screening during early second trimester pregnancy in Thailand. Ultrasound J2021; 13: 36.
34.
NarangAMor-AviVPradoA, et al. Machine learning based automated dynamic quantification of left heart chamber volumes. Eur Heart J Cardiovasc Imag2019; 20: 541–549.
35.
MedvedofskyDMor-AviVAmzulescuM, et al. Three-dimensional echocardiographic quantification of the left-heart chambers using an automated adaptive analytics algorithm: multicentre validation study. Eur Heart J Cardiovasc Imag2018; 19: 47–58.
36.
JaremkoJLMabeeMSwamiVG, et al. Potential for change in US diagnosis of hip dysplasia solely caused by changes in probe orientation: patterns of alpha-angle variation revealed by using three-dimensional US. Radiology2014; 273: 870–878.
37.
BurnettMRawlingsELReddanT. An audit of referral time frames for ultrasound screening of developmental hip dysplasia in neonates with a normal antenatal clinical examination. Sonography2018; 5: 61–66.
38.
PatonRW. Screening in developmental dysplasia of the hip (DDH). Surgeon2017; 15: 290–296.
39.
ShorterDHongTOsbornDA. Cochrane review: screening programmes for developmental dysplasia of the hip in newborn infants. Evid Based Child Health2013; 8: 11–54.
40.
ZonoobiDHareendranathanAMostofiE, et al. Developmental hip dysplasia diagnosis at three-dimensional US: a multicenter study. Radiology2018; 287: 1003–1015.
41.
MostofiEChahalBZonoobiD, et al. Reliability of 2D and 3D ultrasound for infant hip dysplasia in the hands of novice users. Eur Radiol2019; 29: 1489–1495.
42.
KimYH. Artificial intelligence in medical ultrasonography: driving on an unpaved road. Ultrasonography2021; 40: 313–317.
43.
FungAMoulsonNBalthazaarS, et al. Can Artificial Intelligence assess image quality in point-of-care ultrasound?Can J Cardiol2019; 35: S146.
44.
EdwardsCChamunyongaCClarkeJ. The role of deliberate practice in development of essential sonography skills. Sonography2018; 5: 76–81.
45.
NarangABaeRHongH, et al. Utility of a deep-learning algorithm to guide novices to acquire echocardiograms for limited diagnostic use. JAMA Cardiol2021; 6: 624–632.
AkbariMCarriereJMeyerT, et al. Robotic ultrasound scanning with real-time image-based force adjustment: quick response for enabling physical distancing during the COVID-19 pandemic. Front Robot AI2021; 8: 645424.
48.
CrewB. Worth the cost? A closer look at the da Vinci robot’s impact on prostate cancer surgery. Nature2020; 580: S5–S7.
49.
CampsSMHoubenTCarneiroG, et al. Automatic quality assessment of transperineal ultrasound images of the male pelvic region, using deep learning. Ultrasound Med Biol2020; 46: 445–454.
50.
KremkauFW. Your new paradigm for understanding and applying sonographic principles. J Diagn Med Sonograph2019; 35: 439–446.
51.
NairAATranTDReiterA, et al. A deep learning based alternative to beamforming ultrasound images. In: Proceedings of the 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), Calgary, AB, Canada, 15–20 April 2018, pp. 3359–3363. New York: IEEE.
52.
HarveyHTopolEJ. More than meets the AI: refining image acquisition and resolution. Lancet2020; 396: 1479.
53.
EdwardsCCavanaghEKumarS, et al. Intra-system reliability assessment of 2-dimensional shear wave elastography. Appl Sci2021; 11: 2992.
54.
ChamunyongaCEdwardsCCaldwellP, et al. The impact of artificial intelligence and machine learning in radiation therapy: considerations for future curriculum enhancement. J Med Imag Radiat Sci2020; 51: 214–220.
55.
PesapaneFVolontéCCodariM, et al. Artificial intelligence as a medical device in radiology: ethical and regulatory issues in Europe and the United States. Insights Imaging2018; 9: 745–753.
56.
Artificial intelligence: guidance for clinical imaging and therapeutic radiography workforce professionals, www.sor.org
57.
MulkeyA. Sonography clinical education: a sonographer’s perspective. J Diagn Med Sonograph2005; 21: 273–275.
