RESUMO
Improving soybean (Glycine max L. (Merr.)) yield is crucial for strengthening national food security. Predicting soybean yield is essential to maximize the potential of crop varieties. Non-destructive methods are needed to estimate yield before crop maturity. Various approaches, including the pod-count method, have been used to predict soybean yield, but they often face issues with the crop background color. To address this challenge, we explored the application of a depth camera to real-time filtering of RGB images, aiming to enhance the performance of the pod-counting classification model. Additionally, this study aimed to compare object detection models (YOLOV7 and YOLOv7-E6E) and select the most suitable deep learning (DL) model for counting soybean pods. After identifying the best architecture, we conducted a comparative analysis of the model's performance by training the DL model with and without background removal from images. Results demonstrated that removing the background using a depth camera improved YOLOv7's pod detection performance by 10.2% precision, 16.4% recall, 13.8% mAP@50, and 17.7% mAP@0.5:0.95 score compared to when the background was present. Using a depth camera and the YOLOv7 algorithm for pod detection and counting yielded a mAP@0.5 of 93.4% and mAP@0.5:0.95 of 83.9%. These results indicated a significant improvement in the DL model's performance when the background was segmented, and a reasonably larger dataset was used to train YOLOv7.
Assuntos
Glycine max , Melhoramento VegetalRESUMO
Objective: There is dearth of data regarding the outcomes of coronavirus disease 2019 (COVID-19) among rheumatic and musculoskeletal disease (RMD) patients from Southeast Asia. We report the clinicodemographic profile and identify predictors of COVID-19 outcomes in a large cohort of Indian RMD patients. Methods: This prospective cohort study, carried out at the Postgraduate Institute of Medical Education and Research, Chandigarh (a tertiary care centre in India), included RMD patients affected with COVID-19 between April 2020 and October 2021. Demographic and clinical and laboratory details of COVID-19 and underlying RMD were noted. Predictors of mortality, hospitalization and severe COVID-19 were identified using stepwise multivariable logistic regression. Results: A total of 64 severe acute respiratory syndrome coronavirus-2-infected RMD patients [age 41.5 (19-85) years; 46 (72%) females] were included. Eighteen (28%) patients had severe COVID-19. Twenty-three (36%) required respiratory support [11 (17%) required mechanical ventilation]. Thirty-six (56%) patients required hospitalization [median duration of stay 10 (1-42) days]; 17 (27%) required intensive care unit admission. Presence of co-morbidities [odds ratio (OR) = 4.5 (95% CI: 1.4, 14.7)] was found to be an independent predictor of COVID-19 severity. Co-morbidities [OR = 10.7 (95% CI: 2.5, 45.4)] and underlying lupus [OR = 7.0 (95% CI: 1.2, 40.8)] were independently associated with COVID-19 hospitalization. Ongoing rheumatic disease activity [OR = 6.8 (95% CI: 1.3, 35.4)] and underlying diagnosis of lupus [OR = 7.1 (95% CI: 1.2, 42.4)] and SSc [OR = 9.5 (95% CI: 1.5, 61.8)] were found to be strong independent predictors of mortality. Age, sex, underlying RMD-associated interstitial lung disease and choice of immunosuppressive therapy were not associated with COVID-19 severity or adverse outcomes. Conclusion: The presence of co-morbidities was independently associated with COVID-19 severity and hospitalization. Ongoing rheumatic disease activity and the presence of lupus or SSc independently predicted mortality. Age, sex, type of immunosuppressive therapy and presence of RMD-associated interstitial lung disease did not affect COVID-19 severity or outcomes in Indian RMD patients.
RESUMO
A 16-year-old girl presented with grade 3 hepatic encephalopathy (HE) following suicide attempt after consuming a lethal dose of yellow phosphorus containing rodenticide. Although she was a candidate for liver transplantation, it could not be done. In the absence of a specific antidote for yellow phosphorus poisoning, the patient was managed conservatively. In addition, low volume-therapeutic plasma exchange (LV-TPE) was initiated, which resulted in a dramatic improvement in HE. Although liver transplantation is the definitive treatment, this case has shown that TPE has a promising role as a 'bridge to recovery' in situations where transplantation is not feasible. We describe our experience with the above-mentioned case, along with the sequence of clinical recovery and the trend in biochemical parameters during follow-up. The patient made a full recovery and is doing well.