RESUMO
Tuberculosis (TB) is a widespread global disease that significantly impacts daily life. Skeletal TB comprises about 10-35% of all TB cases. Significant research on the spine and hip exists, but due to the rarity of cases, the management of TB is less explored. Furthermore, exercising the option of total knee arthroplasty (TKA) in TB knees is still in its initial stages. This systematic review aims to identify and comprehend the difficulties associated with diagnosing TB-affected knees, their treatment outcomes, and complications related to TKA. A systematic review of existing English literature retrieved from PubMed, Google Scholar, and Web of Science databases was performed using the PRISMA guidelines. A case series of arthroplasty performed on TB knees included a description of the diagnostic approach, clinical outcome, and complication rates. Moreover, studies involving case series with follow-up functional outcomes were included. The Coleman Methodology was used to assess the quality of the studies. A total of six studies (75 knees) were systematically reviewed in this study. The diagnosis of TB knee is multimodal, with MRI being a reliable tool. Administering anti-TB chemotherapy is essential during the perioperative period. Regarding recurrence, a two-stage TKA has a lower risk of recurrence. It is plausible to state that anti-TB chemotherapy needs to be initiated in the perioperative period to prevent the chances of recurrences. Two-stage TKA is reserved for patients who require soft tissue debridement despite adequate chemotherapy.
RESUMO
Currently, the application of deep learning in crop disease classification is one of the active areas of research for which an image dataset is required. Eggplant (Solanum melongena) is one of the important crops, but it is susceptible to serious diseases which hinder its production. Surprisingly, so far no dataset is available for the diseases in this crop. The unavailability of the dataset for these diseases motivated the authors to create a standard dataset in laboratory and field conditions for five major diseases. Pre-trained Visual Geometry Group 16 (VGG16) architecture has been used and the images have been converted to other color spaces namely Hue Saturation Value (HSV), YCbCr and grayscale for evaluation. Results show that the dataset created with RGB and YCbCr images in field condition was promising with a classification accuracy of 99.4%. The dataset also has been evaluated with other popular architectures and compared. In addition, VGG16 has been used as feature extractor from 8th convolution layer and these features have been used for classifying diseases employing Multi-Class Support Vector Machine (MSVM). The analysis depicted an equivalent or in some cases produced better accuracy. Possible reasons for variation in interclass accuracy and future direction have been discussed.