2022
DOI: 10.21203/rs.3.rs-2019639/v1
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Use of artificial intelligence in the classification of elementary orallesions from clinical images

Abstract: Objectives: The Artificial Intelligence has generated a significant impact in health´s field. The aim of this study was to perform the training and validation of a convolutional neural network (CNN) based model to automatically classify six clinical representations categories of oral lesions images. Method: The CNN model was developed with the objective of automatically classifying the images into six categories of elementary lesions, which are: 1) papule/nodule; 2) macule/spot; 3) vesicle/bullae; 4) erosion;… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 25 publications
0
1
0
Order By: Relevance
“…Besides SML, labeling is important also for other AI methods, such as convolutional neural networks (CNNs). In the study of Gomes et al (2023) 14 , the authors performed a manual delimitation and cropping of a rectangle ROI including the whole lesion, which was then used in the training CNN process, which was presented in a labeled and supervised way. In the end, it could be suggested that the labeling phase, before going on to the real AI algorithm creation and training, could be challenging and may need a team of experts and students to perform the manual drawing of the lesions, something that could be really time-consuming.…”
Section: Discussionmentioning
confidence: 99%
“…Besides SML, labeling is important also for other AI methods, such as convolutional neural networks (CNNs). In the study of Gomes et al (2023) 14 , the authors performed a manual delimitation and cropping of a rectangle ROI including the whole lesion, which was then used in the training CNN process, which was presented in a labeled and supervised way. In the end, it could be suggested that the labeling phase, before going on to the real AI algorithm creation and training, could be challenging and may need a team of experts and students to perform the manual drawing of the lesions, something that could be really time-consuming.…”
Section: Discussionmentioning
confidence: 99%