Use of Deep Neural Networks in the Detection and Automated Classification of Lesions Using Clinical Images in Ophthalmology, Dermatology, and Oral Medicine—A Systematic Review

Gomes, Rita Fabiane Teixeira; Schuch, Lauren Frenzel; Martins, Manoela Domingues; Honório, Emerson Ferreira; Figueiredo, Rodrigo Marques de; Schmith, Jean; Machado, Giovanna Nunes; Carrard, Vinícius Coelho

doi:10.1007/s10278-023-00775-3

Cited by 9 publications

(8 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the results of Mazur et al 5 , further studies are needed to explore the role of technique-based image analysis to identify a non-invasive early detection method. There are very promising results with artificial intelligence already being applied in the medical area 32 . However, to date, there is no technique based on the evaluation of oral images that can replace biopsy, which remains the gold standard in the diagnosis of malignant lesions.…”

Section: Discussionmentioning

confidence: 99%

Experiences, perceptions, and decision-making capacity towards oral biopsy among dental students and dentists

Cassol Spanemberg,

Velázquez Cayón,

Romanini

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The dentist plays a crucial role in identifying oral lesions as it is their responsibility to conduct the clinical examination for diagnosing diseases in this anatomical region. Dentists should be able to perform simple oral biopsies when this procedure is necessary. However, several studies point out that dentists lack experience and perceive themselves incapable of performing biopsies. This analytical cross-sectional study aimed to assess participants' experiences and perceptions regarding a continuing education activity focused on the biopsy procedure. The secondary aim was to evaluate their ability to determine when a biopsy is indicated. The sample consisted of 228 individuals: 143 dentists and 85 undergraduate dental students who completed questionnaires related to a lecture held in May/2021, as part of the continuing educational activities of the “Red May” Project. Participants completed two questionnaires: the first assessed their experience and self-confidence in performing oral biopsies, whereas the second evaluated their capacity to define when the biopsy is indicated by means the evaluation of 10 clinical cases. The results reveal no significant difference in the percentage of correct answers between dental students and dentists. Regarding the frequency of performing the biopsy procedure, most respondents (69.7%) reported doing so rarely or never. Furthermore, while 31.6% of the participants stated that they perform biopsies depending on the case, 68.4% prefer to refer patients to specialists, such as professionals in Stomatology/Oral Medicine. These findings highlight limitations in the educational preparation of the study population concerning biopsy procedures, oral lesions, and their management. They also indicate a concerning tendency to overestimate knowledge in this area. Thus, this study emphasizes the importance of continuing education and underscores the need to revise academic curricula and provide complementary education for all dental professionals.

show abstract

Section: Discussionmentioning

confidence: 99%

Experiences, perceptions, and decision-making capacity towards oral biopsy among dental students and dentists

Cassol Spanemberg,

Velázquez Cayón,

Romanini

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Neural networks specialize in identifying patterns in large and complex data sets, outperforming humans. 4…”

Section: A View Of Neural Network In Artificial Intelligence In Oral ...mentioning

confidence: 99%

A view of neural networks in artificial intelligence in oral pathology

Tripathy,

Mathur,

Mehta

2023

Oral Surgery

View full text Add to dashboard Cite

“…The reproducibility of the performance models in real-life practice has been reported as a critical point. 4 As mentioned prior, AI has already become the forerunner in health care in terms of precision, speed, and safety. According to some studies, the use of virtual reality (VR) in health care provides the benefit of 230% improvement in surgical performance in comparison with traditional training methods; procedures are completed 29% faster when trained in VR, and the risk of errors is 6 times lower.…”

mentioning

confidence: 92%

“…The performance of AI models is promising due to their high accuracy, sensitivity, and specificity. The reproducibility of the performance models in real‐life practice has been reported as a critical point 4 . As mentioned prior, AI has already become the forerunner in health care in terms of precision, speed, and safety.…”

mentioning

confidence: 94%