Accurate detection for dental implant and peri-implant tissue by transfer learning of faster R-CNN: a diagnostic accuracy study.

BACKGROUND: The diagnosis of dental implants and the periapical tissues using periapical radiographs is crucial. Recently, artificial intelligence has shown a rapid advancement in the field of radiographic imaging. PURPOSE: This study attempted to detect dental implants and peri-implant tissues by using a deep learning method known as object detection on the implant image of periapical radiographs. METHODS: After implant treatment, the periapical images were collected and data were processed by labeling the dental implant and peri-implant tissue together in the images. Next, 300 images of the periapical radiographs were split into 80:20 ratio (i.e. 80% of the data were used for training the model while 20% were used for testing the model). These were evaluated using an object detection model known as Faster R-CNN, which simultaneously performs classification and localization. This model was evaluated on the classification performance using metrics, including precision, recall, and F1 score. Additionally, in order to assess the localization performance, an evaluation through intersection over union (IoU) was utilized, and, Average Precision (AP) was used to assess both the classification and localization performance. RESULTS: Considering the classification performance, precision = 0.977, recall = 0.992, and F1 score = 0.984 were derived. The indicator of localization was derived as mean IoU = 0.907. On the other hand, considering the indicators of both classification and localization performance, AP showed an object detection level of AP@0.5 = 0.996 and AP@0.75 = 0.967. CONCLUSION: Thus, the implementation of Faster R-CNN model for object detection on 300 periapical radiographic images including dental implants, resulted in high-quality object detection for dental implants and peri-implant tissues.

API5 induces cisplatin resistance through FGFR signaling in human cancer cells.

Most tumors frequently undergo initial treatment with a chemotherapeutic agent but ultimately develop resistance, which limits the success of chemotherapies. As cisplatin exerts a high therapeutic effect in a variety of cancer types, it is often used in diverse strategies, such as neoadjuvant, adjuvant and combination chemotherapies. However, cisplatin resistance has often manifested regardless of cancer type, and it represents an unmet clinical need. Since we found that API5 expression was positively correlated with chemotherapy resistance in several specimens from patients with cervical cancer, we decided to investigate whether API5 is involved in the development of resistance after chemotherapy and to explore whether targeting API5 or its downstream effectors can reverse chemo-resistance. For this purpose, cisplatin-resistant cells (CaSki P3 CR) were established using three rounds of in vivo selection with cisplatin in a xenografted mouse. In the CaSki P3 CR cells, we observed that API5 acted as a chemo-resistant factor by rendering cancer cells resistant to cisplatin-induced apoptosis. Mechanistic investigations revealed that API5 mediated chemo-resistance by activating FGFR1 signaling, which led to Bim degradation. Importantly, FGFR1 inhibition using either an siRNA or a specific inhibitor disrupted cisplatin resistance in various types of API5high cancer cells in an in vitro cell culture system as well as in an in vivo xenograft model. Thus, our results demonstrated that API5 promotes chemo-resistance and that targeting either API5 or its downstream FGFR1 effectors can sensitize chemo-refractory cancers.