Artificial intelligence-based diagnostics of molar-incisor-hypomineralization (MIH) on intraoral photographs

Schönewolf, Jule; Meyer, Ole; Engels, Paula; Schlickenrieder, Anne; Hickel, Reinhard; Gruhn, Volker; Hesenius, Marc; Kühnisch, Jan

doi:10.1007/s00784-022-04552-4

Cited by 8 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be concluded that the ACC was very high, which is in line with the available literature evaluating transformers 16 – 18 , and finally, the initially formulated goal was reached. When comparing the documented ACC values (>95%) from the image-related analysis (Table 3 ) to those from previously published data using CNNs, ACC values of approximately 90% were achieved for caries 10 – 12 and MIH detection 13 , 14 . This comparison indicates that the use of exact annotations and a powerful transformer network, as well as other improvements such as pixelwise analysis and the inclusion of commonly used caries and MIH categories, may surpass CNN-based algorithms in terms of diagnostic performance.…”

Section: Discussionmentioning

confidence: 84%

“…In brief, clinical image acquisition included the use of professional single reflex lens cameras (Nikon D200, D300, D7100 or D7200, Nikon, Tokyo, Japan) equipped with a macro lens (Nikon AF-S Micro Nikkor 105 mm 1:2.8 G, Nikon, Tokyo, Japan) and a macro flash (EM-140DG, Sigma, Rödermark, Germany) after tooth cleaning and drying. Posterior teeth were photographed indirectly using intraoral mirrors 10 , 14 , 22 , 23 .…”

Section: Methodsmentioning

confidence: 99%

“…Following this aim, the use of teeth photographs—a digital and machine-readable equivalent to a clinical examination—and artificial intelligence (AI) methods may potentially contribute to accurate diagnostic evaluations in the future. Recently, a few study groups have used and evaluated convolutional neural networks (CNNs) with digital photographs for the detection of caries 10 – 12 and MIH 13 , 14 . All studies proved the concept of using AI-based methods for dental photographs, and promising results were published.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model

Felsch,

Meyer,

Schlickenrieder

et al. 2023

npj Digit. Med.

Self Cite

View full text Add to dashboard Cite

Caries and molar-incisor hypomineralization (MIH) are among the most prevalent diseases worldwide and need to be reliably diagnosed. The use of dental photographs and artificial intelligence (AI) methods may potentially contribute to realizing accurate and automated diagnostic visual examinations in the future. Therefore, the present study aimed to develop an AI-based algorithm that can detect, classify and localize caries and MIH. This study included an image set of 18,179 anonymous photographs. Pixelwise image labeling was achieved by trained and calibrated annotators using the Computer Vision Annotation Tool (CVAT). All annotations were made according to standard methods and were independently checked by an experienced dentist. The entire image set was divided into training (N = 16,679), validation (N = 500) and test sets (N = 1000). The AI-based algorithm was trained and finetuned over 250 epochs by using image augmentation and adapting a vision transformer network (SegFormer-B5). Statistics included the determination of the intersection over union (IoU), average precision (AP) and accuracy (ACC). The overall diagnostic performance in terms of IoU, AP and ACC were 0.959, 0.977 and 0.978 for the finetuned model, respectively. The corresponding data for the most relevant caries classes of non-cavitations (0.630, 0.813 and 0.990) and dentin cavities (0.692, 0.830, and 0.997) were found to be high. MIH-related demarcated opacity (0.672, 0.827, and 0.993) and atypical restoration (0.829, 0.902, and 0.999) showed similar results. Here, we report that the model achieves excellent precision for pixelwise detection and localization of caries and MIH. Nevertheless, the model needs to be further improved and externally validated.

show abstract

Section: Discussionmentioning

confidence: 84%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model

Felsch,

Meyer,

Schlickenrieder

et al. 2023

npj Digit. Med.

Self Cite

View full text Add to dashboard Cite

show abstract

“…It should investigate the accuracy of deep learning models for different severity levels of white spot lesions and extend multi-class detections towards more detailed disease classifications. The CNN developed by Schönewolf et al [ 21 ] for automatic detection and classification of teeth affected by molar-incisor-hypomineralization (MIH) in intraoral photographs was able to accurately categorize teeth with MIH with an overall diagnostic accuracy of 95.2%. Based on these studies, it is technically feasible to develop CNNs with significant precision using software development.…”

Section: Discussionmentioning

confidence: 99%

Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study

Ozsunkar,

Özen,

Abdelkarim

et al. 2024

BMC Oral Health

View full text Add to dashboard Cite

Background Deep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future. Methods A total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 × 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined. Results Among the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model’s performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425. Conclusions The model’s accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm. Clinical revelance Deep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.

show abstract

“…A deep learning-based convolutional neural network (CNN) was developed for the automatic detection and classification of teeth affected by MIH in intraoral photographs. It could accurately categorize teeth with MIH with an overall diagnostic accuracy of 95.2% [88].…”

Section: Pediatric Dentistrymentioning

confidence: 99%

Artificial Intelligence in Dentistry

Gokdeniz¹,

Büyüksungur²,

Kolsuz³

2023

Dentistry

View full text Add to dashboard Cite

Artificial intelligence (AI) is the branch of computer science dedicated to building systems to perform tasks that normally require human intelligence. AI tries to solve problems and learn similar to humans. The field of AI has experienced phenomenal development and growth over the past two decades; with the latest developments in digitized data collection, machine learning, and computing infrastructure, AI applications are expanding rapidly, especially in areas that are thought to be reserved for experts in their fields. Artificial intelligence has started to take place rapidly in dental clinical applications. The use of artificial intelligence in dentistry has enormous potential to improve patient care and drive major advances in healthcare. AI in dentistry is being researched for various purposes, such as identifying anatomical and pathological structures, diagnosing diseases and predicting treatment results, and selecting materials to be used. Advances in AI offer healthcare benefits, such as reducing postoperative complications, improving quality of life, and reducing the number of unnecessary procedures. It can also play a great helping role for dentists in increasing the accuracy of diagnosis. This chapter aims to explain the current applications and future predictions of artificial intelligence in dentistry, which is one of the most current topics of recent times.

show abstract

Artificial intelligence-based diagnostics of molar-incisor-hypomineralization (MIH) on intraoral photographs

Cited by 8 publications

References 34 publications

Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model

Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model

Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study

Artificial Intelligence in Dentistry

Contact Info

Product

Resources

About