Chilli leaf curl virus (ChiLCV) is a severe threat to the successful cultivation of the chilli peppers. Besides, the genetics and heterosis for important traits under the influence of ChiLCV infestation is not well studied. Therefore here, were crossed seven genotypes (lines) with high yield and quality attributes with four highly resistant genotypes (testers) in a line (L) × tester (T) mating design to produce 28 F1 hybrids. Parents and their hybrids were evaluated for yield attributes and ChiLCV resistance. All the four testers were symptomless and among seven lines, two were moderately resistant and five were moderately susceptible to the ChiLCV. Among 28 F1 hybrids, 12 showed a moderate resistant reaction, 11 were moderately susceptible and five susceptible to the ChiLCV disease. Based on per se performance, most promising hybrid combinations were L3 × T2, L6 × T1, and L3 × T1 for yield attributes. Whereas the superior crosses for ChiLCV resistance based on heterobeltosis, standard heterosis and specific combining ability test (SCA) effects were L6 × T1 and L7 × T3. Lines and testers showed significant differences for all the characters except for the plant height. The general combining ability (GCA) effects for testers were significant for all the traits except for days to first harvest. The ratio of σ2GCA/σ2SCA indicated the predominance of non-additive gene effects in the inheritance of traits studied in this experiment. The contribution of lines was more compared to testers for all the characters except for primary branches plant-1. Overall, this study provides valuable information regarding the genetics and heterosis in chilli with respect to ChiLCV infestation

Cervical cancer is a worldwide public health problem with a high rate of illness and mortality among women. In this study, we proposed a novel framework based on Faster RCNN-FPN ar-chitecture for the detection of abnormal cervical cells in cytology images from cancer screening test. We extended the Faster RCNN-FPN model by infusing deformable convolution layers into the feature pyramid network (FPN) to improve scalability. Furthermore, we introduced a global contextual aware module alongside the Region Proposal Network (RPN) to enhance the spatial correlation between the background and the foreground. Extensive experimentations with the proposed deformable and global context aware (DGCA) RCNN were carried out using the cer-vical image dataset of “Digital Human Body" Vision Challenge from the Alibaba Cloud TianChi Company. Performance evaluation based on the mean average precision (mAP) and receiver operating characteristic (ROC) curve has demonstrated considerable advantages of the proposed framework. Particularly, when combined with tagging of the negative image samples using tra-ditional computer-vision techniques, 6-9% increase in mAP has been achieved. The proposed DGCA-RCNN model has potential to become a clinically useful AI tool for automated detection of cervical cancer cells in whole slide images of Pap smear.