Deep Learning-Based Multiclass Instance Segmentation for Dental Lesion Detection.

Automated dental imaging interpretation is one of the most prolific areas of research using artificial intelligence. X-ray imaging systems have enabled dental clinicians to identify dental diseases. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, as well as machine and deep learning models for dental disease diagnoses using X-ray imagery. In this regard, a lightweight Mask-RCNN model is proposed for periapical disease detection. The proposed model is constructed in two parts: a lightweight modified MobileNet-v2 backbone and region-based network (RPN) are proposed for periapical disease localization on a small dataset. To measure the effectiveness of the proposed model, the lightweight Mask-RCNN is evaluated on a custom annotated dataset comprising images of five different types of periapical lesions. The results reveal that the model can detect and localize periapical lesions with an overall accuracy of 94%, a mean average precision of 85%, and a mean insection over a union of 71.0%. The proposed model improves the detection, classification, and localization accuracy significantly using a smaller number of images compared to existing methods and outperforms state-of-the-art approaches.

Interaction between seed size and NaCl on germination and early seedling growth of some Turkish cultivars of chickpea (Cicer arietinum L.) / 浙江大学学报（英文版）（B辑：生物医学和生物技术）

Chickpea is an important food legume crop of Turkey and is largely grown for human consumption on low moisture or salt-affected soils. The objective of the study was to find the effects of NaCl stress at electrical conductivities of 4.5, 8.6, 12.7 and 16.3 dS/m and seed sizes (7, 8 and 9 mm) on germination and early seedling growth of three popular chickpea cultivars (AKN-97, Gokce and Uzunlu-99). Mean frequency of germination, germination time, germination index, root length, shoot length and seedling fresh weight showed seed size-dependent responses of cultivars to salt stress. In general, small seeds germinated and grew more rapidly compared to medium and large seeds of the same cultivars against all levels of salt stress, with the best results in cultivar Uzunlu-99. No effect of NaCl treatments was observed on frequency of germination; however, a drastic decrease in early seedling growth was recorded at increased NaCl concentrations. Regression analysis results showed a significantly positive relationship (P<0.01) between seed size and mean germination time, whereas a significantly negative relationship was recorded between seed size and germination index, root length, shoot length. Moreover, linear regression values apparently confirmed that increased seed size in each cultivar affected decreased germination index, root and shoot lengths with enhanced mean germination time. Thus, it was concluded that the use of small seeds could considerably reduce the production costs of chickpea in salt-affected soils.