Feasibility Study of Google’s Teachable Machine in Diagnosis of Tooth-Marked Tongue
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google’s Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle’s web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google’s Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue’s diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li’s experimental results calculated with convolution neural network. Google’s Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.
Abstract
Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google’s Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle’s web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google’s Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue’s diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li’s experimental results calculated with convolution neural network. Google’s Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.
참고문헌 (18)
- López-Úbeda P, "Detection of unexpected findings in radiology reports: a comparative study of machine learning approaches", Expert Syst Appl, 160, pp.113647~ (2020)[DOI]
- Chamunyonga C, "The impact of artificial intelligence and machine learning in radiation therapy: considerations for future curriculum enhancement", J Med Imaging Radiat Sci, 51, pp.214~220 (2020)[DOI]
- Abdalla-Aslan R, "An artificial intelligence system using machine-learning for automatic detection and classification of dental restorations in panoramic radiography", Oral Surg Oral Med Oral Pathol Oral Radiol, 130, pp.593~602 (2020)[DOI]
- Lee JH, "Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm", J Dent, 77, pp.106~111 (2018)[DOI]
- "Train a computer to recognize your own images, sounds, & poses" (2019)[URL]
- Jang KH, "Oral anatomy", pp.47~142 (2005), Komoonsa
- Slavkin HC, "Relationship of dental and oral pathology to systemic illness", JAMA, 284, pp.1215~1217 (2000)[DOI]
- Shi D, "An annotated dataset of tongue images supporting geriatric disease diagnosis", Data Brief, 32, pp.106153~ (2020)[DOI]
- Solos I, "A historical evaluation of Chinese tongue diagnosis in the treatment of septicemic plague in the pre-antibiotic era, and as a new direction for revolutionary clinical research applications", J Integr Med, 16, pp.141~146 (2018)[DOI]
- Hong SS, "Diagnosis of oriental medicines", pp.54~55 (2009), Koonja
- Li X, "Tooth-marked tongue recognition using multiple instance learning and CNN features", IEEE Trans Cybern, 49, pp.380~387 (2019)[DOI]
- "Tooth-marked-tongue: Dataset" (2020)[URL]
- "Tour machine learning and data science community" (2010)[URL]
- Omar L, "Using theoretical ROC curves for analysing machine learning binary classifiers", Pattern Recognit Lett, 128, pp.447~451 (2019)[DOI]
- Cho KH, "Tongue diagnosis for clinicians: integrating oriental and western medicines", pp.4~49 (2007), Koonja
- Im YG, "Atlas of clinical diagnosis 2: tongue diagnosis", pp.74~76 (2003), Jungdam
- Ma J, "Complexity perception classification method for tongue constitution recognition", Artif Intell Med, 96, pp.123~133 (2019)[DOI]
- Marzia Hoque Tania, "Advances in automated tongue diagnosis techniques", Integrative Medicine Research, 8(1), pp.42~56 (2019), 한국한의학연구원[DOI]