Artificial intelligence in radiography: Where are we now and what does the future hold?

Malamateniou, Christina; Knapp, Karen; Pergola, M.; Woznitza, N.; Hardy, Maryann

doi:10.1016/j.radi.2021.07.015

Cited by 40 publications

(23 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…23 The contextual nature of results will persist for as long as AI implementation in medical imaging is heterogenous between different sectors, modalities and functions. 51…”

Section: Understanding Of How An Ai System Reaches Its Decisionmentioning

confidence: 99%

UK reporting radiographers’ perceptions of AI in radiographic image interpretation – Current perspectives and future developments

Rainey¹,

O’Regan

Matthew

et al. 2022

Radiography

Self Cite

View full text Add to dashboard Cite

“…23 The contextual nature of results will persist for as long as AI implementation in medical imaging is heterogenous between different sectors, modalities and functions. 51…”

Section: Understanding Of How An Ai System Reaches Its Decisionmentioning

confidence: 99%

UK reporting radiographers’ perceptions of AI in radiographic image interpretation – Current perspectives and future developments

Rainey¹,

O’Regan

Matthew

et al. 2022

Radiography

Self Cite

View full text Add to dashboard Cite

“…This may indicate some confusion regarding what we define as 'AI'. Technology enabled assistance is already present in many aspects of general clinical practice, for instance in the digitisation and archiving of images to computer assisted diagnosis, although many of these applications may not represent what we understand by 'modern AI', such as deep and machine learning systems [25] . Supporting this notion, although respondents to this survey indicated that they were not sure if AI was being used in their daily practice, most were able to identify areas where AI was being used, for example, in 'reporting' and 'treatment planning'.…”

Section: Definitions Of Aimentioning

confidence: 99%

An insight into the current perceptions of UK radiographers on the future impact of AI on the profession: A cross-sectional survey

Rainey¹,

O’Regan²,

Matthew³

et al. 2022

Journal of Medical Imaging and Radiation Sciences

Self Cite

View full text Add to dashboard Cite

“…In recent years, AI, especially CNN has developed rapidly in the medical world. AI has been proven to be able to detect disease, analyze treatment results, analyze radiographic images, analyze histopathological images, and so on so that AI can improve patient care and reduce misdiagnosis in daily practice [18]. In the field of oncology, many studies have been carried out regarding the CNN application to help make a diagnosis quickly and accurately.…”

Section: Artificial Intelligencementioning

confidence: 99%

Utilization of artificial intelligence-assisted histopathological detection in surveillance of oral squamous cell carcinoma staging: A narrative review

Sosiawan¹,

Chusnita²,

Laksanti³

et al. 2022

World J. Adv. Res. Rev.

View full text Add to dashboard Cite

Background: Oral squamous cell carcinoma (OSCC) is defined as an oral malignancy with worldwide prevalence of 90%. In 2018, the number of cases observed is 354.864 with 177.384 deaths globally. Early diagnosis for determining OSCC stage due to histopathological examination is required to sustain prognosis and minimize mortality. Determining the stage is mostly done manually and highly dependent on skill and experiences of the pathologist thus having a high tendency of misdiagnosis. Artificial intelligence (AI) is a technology that modifies machines with human-like intelligence thus making them able to solve the tasks. Utilization of AI in analyzing histopathological samples is known to give such a precision analysis then diagnosing the OSCC stage accurately Purpose: This study describes utilization of AI-assisted histopathological detection in determining OSCC staging. Review: Developmental process of OSCC begins with gene damage causing disruption of cell regulation, manifesting in impaired differentiation and proliferation of keratinocytes in the epithelium which is characterized by keratin pearl formation. AI-assisted histopathological detection is able to identify the percentage of keratinization and keratin pearls in histopathological images by convolutional neural network (CNN). CNN is a deep learning architecture specifically designed to recognize two-dimensional visual patterns with minimal preprocessing. CNN works by analyzing input in the form of visual images from histopathological images and producing output as keratinization percentage in related samples then being used to determine the staging of OSCC. Conclusion: AI-assisted histopathological detection may potential to be used in determining OSCC staging.

show abstract

Artificial intelligence in radiography: Where are we now and what does the future hold?

Cited by 40 publications

References 34 publications

UK reporting radiographers’ perceptions of AI in radiographic image interpretation – Current perspectives and future developments

UK reporting radiographers’ perceptions of AI in radiographic image interpretation – Current perspectives and future developments

An insight into the current perceptions of UK radiographers on the future impact of AI on the profession: A cross-sectional survey

Utilization of artificial intelligence-assisted histopathological detection in surveillance of oral squamous cell carcinoma staging: A narrative review

Contact Info

Product

Resources

About