Kim J, et al. J Vet Sci. 2016 Dec;17(4):435-444. https://doi.org/10.4142/jvs.2016.17.4.435

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.

Recent studies report that inflammatory diseases of the large intestine are associated with colorectal cancer. Geijigajakyak Decoction (GJD) has antispasmodic and anti-inflammatory effects on the gastrointestinal tract. Thus, in light of the connection between chronic bowel inflammation and colorectal cancer (CRC), we asked whether GJD inhibits colorectal tumorigenesis. The effects of GJD on the viability and proliferation of CRC cells were evaluated using MTT and BrdU assays, respectively. The motility of CRC cells was examined by a Transwell migration/invasion assay and immunoblot analysis was used to examine the signaling pathways associated with migration. A syngeneic Balb/c mice allograft model, in which CT26 cells were injected into the dorsum, was used to evaluate the anti-tumor effects of GJD in vivo. GJD had no cytotoxic effects against HCT116 CRC cells, although it did inhibit their proliferation. GJD inhibited the migration of HCT116 cells, and suppressed the invasion of HCT116, Caco2, and CSC221 CRC cells. In addition, GJD downregulated the expression of p-JNK and p-p38 MAPK, which are downstream signaling molecules associated with invasiveness. Furthermore, oral administration of GJD (333 mg/kg, twice a day) inhibited tumor growth in a mouse xenograft model. GJD inhibited the motility of human CRC cells and suppressed tumorigenesis in a mouse model. These results suggest that GJD warrants further study as a potential adjuvant anti-cancer therapy.

Licorice and dried ginger decoction (Gancao-ganjiang-tang, LGD) is used for nausea and anorexia, accompanied by excessive sweating in Traditional Chinese Medicine. Herein, we investigated the therapeutic effects of LGD using the activity-based anorexia (ABA) in a mouse model. Six-week-old female BALB/c AnNCrl mice were orally administered LGD, water, licorice decoction, dried ginger decoction, or chronic olanzapine, and their survival, body weight, food intake, and wheel activity were compared in ABA. Additionally, dopamine concentration in brain tissues was evaluated. LGD significantly reduced the number of ABA mice reaching the drop-out criterion of fatal body weight loss. However, LGD showed no significant effects on food intake and wheel activity. We found that in the LGD group the rise of the light phase activity rate inhibited body weight loss. Licorice or dried ginger alone did not improve survival rates, they only showed longer survival periods than chronic olanzapine when combined. In addition, LGD increased the dopamine concentration in the brain. The results from the present study showed that LGD improves the survival of ABA mice and its mechanism of action might be related to the alteration of dopamine concentration in the brain.