Identification of Toxic Herbs Using Deep Learning with Focus on the Sinomenium Acutum, Aristolochiae Manshuriensis Caulis, Akebiae Caulis

Goya Choi,Dohyun Kim,Soongin Lee,Suyeon Jeon,Jongkil Jeong,Jaeseong Cho,Seokyeong Kim,Siyoung Song

doi:10.3390/app9245456

Goya Choi, Dohyun Kim + Show 6 more

Open Access

https://doi.org/10.3390/app9245456

Copy DOI

Abstract

Toxic herbs are similar in appearance to those known to be safe, which can lead to medical accidents caused by identification errors. We aimed to study the deep learning models that can be used to distinguish the herb Aristolochiae Manshuriensis Caulis (AMC), which contains carcinogenic and nephrotoxic ingredients from Akebiae Caulis (AC) and Sinomenium acutum (SA). Five hundred images of each herb without backgrounds, captured with smartphones, and 100 images from the Internet were used as learning materials. The study employed the deep-learning models VGGNet16, ResNet50, and MobileNet for the identification. Two additional techniques were tried to enhance the accuracy of the models. One was extracting the edges from the images of the herbs using canny edge detection (CED) and the other was applying transfer learning (TL) to each model. In addition, the sensitivity and specificity of AMC, AC, and SA identification were assessed by experts with a Ph.D. degree in herbology, undergraduates and clinicians of oriental medicine, and the ability was compared with those of MobileNet-TL′s. The identification accuracies of VGGNet16, ResNet50, and MobileNet were 93.9%, 92.2%, and 95.6%, respectively. After adopting the CED technique, the accuracy was 95.0% for VGGNet16, 63.9% for ResNet50, and 80.0% for MobileNet. After using TL without the CED technique, the accuracy was 97.8% for VGGNet16-TL, 98.9% for ResNet50-TL, and 99.4% for MobileNet-TL. Finally, MobileNet-TL showed the highest accuracy among three models. MobileNet-TL had higher identification accuracy than experts with a Ph.D. degree in herbology in Korea. The result identifying AMC, AC, and SA in MobileNet-TL has demonstrated a great capability to distinguish those three herbs beyond human identification accuracy. This study indicates that the deep-learning model can be used for herb identification.

Highlights

As of 2015, there were 602 herbs mentioned in The Korean Herbal Pharmacopoeia, 618 herbs in the Pharmacopoeia of the People0 s Republic of China, and 215 herbs in the Japanese Pharmacopoeia [1].Some toxic herbs are similar in appearance to other herbs, which is a matter of grave concern, as this may lead to drug-related accidents caused by mistake in visual discrimination
After training each model with transfer learning (TL), we evaluated the performance of identification accuracy ofmodel the models improved, but prediction98.9%
Deep learning is an artificial neural network consisting of several hidden layers between the input layer and the output layer

Summary

Introduction

As of 2015, there were 602 herbs mentioned in The Korean Herbal Pharmacopoeia, 618 herbs in the Pharmacopoeia of the People0 s Republic of China, and 215 herbs in the Japanese Pharmacopoeia [1].Some toxic herbs are similar in appearance to other herbs, which is a matter of grave concern, as this may lead to drug-related accidents caused by mistake in visual discrimination. The development of better herb identification technology is one of the most important and urgent tasks in herbal medicine. Sci. 2019, 9, x FOR PEER REVIEW development of better herb identification technology is one of the most important and urgent 2tasks of 11 in herbal medicine. Weight was assigned to the histological shape of the cut surface, similar to the method followed in the identification with the naked eye (Figure 5a). The focus was on the entire image, including the appearance of the herb (Figure 5c). This showed that the identification method in the deep-learning model was not the same as followed by humans and the same type of herb could be estimated by weighting in different patterns

Objectives

Methods

Conclusion