黑料网

These architectures provide excellent prediction accuracy in addition to being computationally effective. DNNs were chosen by researchers to serve as COVID-19's AI diagnosis algorithms as a consequence [10]. This method has the advantages of efficiency and universal accessibility. Numerous uses of AI are being used to combat COVID-19 at the moment [11]. Several studies in the literature use CT COVID-19 because radiographic patterns on computed tomography chest scans have been shown to have superior sensitivity and specificity compared to the RT-PCR testing method [12]. Additionally, the feature of COVID-19 on CT chest scans can be distinguished from other types of pneumonia by utilising the predictive power of an AI technology [13]. In particular, it is possible to accurately identify COVID-19 cases from those of other viral forms of pneumonia by applying deep learning algorithms [14]. As a result, many of these efforts integrate transfer learning on the chest X-ray dataset with pretrained convolutional neural network architectures to create such a classifier. As a result, scientists began to compile datasets of chest X-ray and CT images and make them accessible to the general public [15]. A dataset known as COVID-x was compiled by Wang and Wong and included four classes: normal, bacterial pneumonia, viral non- COVID19 pneumonia, and COVID-19 cases. However, the primary issue with such works is In this study, we provide deep learningbased methods for COVID-19 diagnosis and detection in patients. We presented two AI-based techniques for classifying and diagnosing lung MRI images from patients and healthy individuals in order to address the diagnosis challenge. The first method uses ANN and fractal algorithms for classification and feature extraction. Finally, we provided CNN-based segmentation approaches for solving detection issues that may distinguish infected tissue based on Lung MRI images. In the second stage, we used traditional CNN methods and then examined the accuracy and sensitivity of the strategy. The introduction of the science-based procedures that are described in other sections of the study. The results and discussion section of the paper presents and evaluates the findings. We discuss some of the related research employing AI algorithms to combat COVID-19 in this part. We talk about a few publicly accessible datasets first. Next, we discuss the work done to create an AI-based classifier employing X-ray and CT chest scan pictures. We also discuss some of the other cutting-edge ways AI is being used to solve this issue. On the basis of CT imaging, there have been numerous investigations on COVID-19 detection. The most widely applied method in this regard has been CNN architectures. Two CNN designs were examined by the authors, the first of which was based on the ResNet-23 architecture and the second of which added a location attention mechanism to the fully connected layer.

Discussion

This architecture classified with an overall accuracy of 86.7%. The goal of feature extraction is to reduce the number of resources needed to fully explain a huge set of data. The large number of variables used in sophisticated data analysis is one of the main issues. A classification technique that employs the instructive sample and generalises to the new instances is typically needed for analysis with a high number of variables. A approach for creating a set of variables to tackle highprecision problems is referred to as feature extraction. Image analysis looks for a distinctive approach to display the essential elements of photographs. A grey surface matrix was created in the fractal method to achieve statistical features. Visual characteristics of the probability distribution in statistical analysis the characteristic is extracted in this work using a fractal model. Feature selection has been utilised to lower the dimensions and find the most pertinent features that may adequately divide the various classes in order to deal with high input features. Covariance analysis has been used to apply the fractal method in order to extract the image's eigenvalues and decrease its dimension. The input images for the fractal method must all be the same size, and one image is known as both a single vector and a two-dimensional matrix. Images must have a particular resolution and be grey. By reshaping matrices, each image is transformed into a column vector, and m the pictures are loaded from a M x N matrix. Greeting and significance: An uncommon type of cancer with a dismal prognosis is soft tissue sarcoma. Improved treatment outcomes depend on early diagnosis and treatment. Presentation of a case We describe a number of high-grade soft tissue sarcomas of the lower extremity with delayed diagnosis in order to learn more about the symptoms, prognoses, and treatments of this uncommon condition and to assess whether limbsalvage surgery produces acceptable results. Clinical conversation: The success of any particular disease's therapy is impacted by timely health seeking. Socioeconomic variables frequently contribute to patient delays. Soft tissue sarcomas are uncommon malignant tumours with a low 5-year survival rate, even when properly treated. Salvation of the limb is put in doubt, particularly when patients arrive late and have negative symptoms. Conclusion this collection The question of what is late and what is in time still lingers, even if an early visit to the doctor might often mean the difference between life and death. Early health seeking affects the effectiveness of a particular disease's therapy, for example, three months for breast cancer and two hours for a heart attack. The "period of time between the development of signs and symptoms and the patient's initial visit to a health care provider" is a common way to define the patient's delay.

Conclusion

Typically, sociodemographic characteristics like age, gender, socioeconomic level, or marital status are linked to patient delays. Here, we present and discuss three cases of soft tissue sarcoma from our tertiary centre that appeared late and were therefore diagnosed later, which had an adverse influence on limb salvage. A 45-year-old woman who had a mass on the front of her left leg for seven months and was in agony and unable to utilise the limb presented as a referral. After an animal injury, a little mass developed; it was removed, but two months later, it returned. With bleeding and pus leakage present, the lump gradually grew larger. She claimed that she tried natural remedies but got no comfort. On admission, she did mention feeling lightheaded, being aware of heartbeats, and having overall bodily weakness, but she ruled out headaches, fevers, breathing problems, or coughing. The other systems were ordinary. There was no history of a chronic condition. She raises livestock and doesn't use smoke or alcohol. She was found to be completely awake and only slightly pale. A 20-year-old man complained that his right knee has been painful and difficult to flex for two years. This began with the knee's inability to bend past 90 degrees. Although it wasn't terrible at first, he gradually started to experience considerable agony, and his ability to flex his knees was severely restricted. He denied having experienced trauma, or having developed a tumour or an ulcer while unwell. The past medical history was unremarkable, as was the family and social history. He had steady vital signs and was clinically stable upon evaluation. On closer inspection, his right knee's conventional markings had healed, it wasn't sore, and his neuromuscular status was unharmed. The majority of the systemic assessment was typical. The results of the histopathology analysis showed pleomorphic rhabdomyosarcoma. Several are treated with radiation and broad local excision, whereas others.

Acknowledgement

None

Conflict of Interest

None

References

1. Lee JB, Miyake S, Umetsu RHK, Chijimatsu T, Hayashi T, et al. (2012) Food Chem 134: 2164-2168.

, ,

2. Lanciotti RS, Kerst AJ, Nasci RS, Godsey MS, Mitchell CJ, et al. (2000) J Clin Microbiol 38: 4066-4071.

, ,

3. Awan MJ, Rahim MMS, Salim N, Mohammed MA, Garcia Zapirain B, et al. (2021) Diagnostics 11: 105.

, ,

4. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, et al. (2017) Comput Biol Med 89: 389-396.

, ,

5. Dantas G, Siciliano B, França BB, da Silva CM, Arbilla G, et al. (2020) Sci Total Environ 729.

, ,

6. Lanciotti RS, Kerst AJ, Nasci RS, Godsey MS, Mitchell CJ, et al (2000) J Clin Microbiol 38: 4066-4071.

, ,

7. Pérez Ruiz M, Pedrosa Corral I, Sanbonmatsu Gámez S, Navarro Marí M (2012) Open Virol J 6:151-159.

, ,

8. Cadogan A, McNair P, Laslett M, Hing W (2013) BMC Musculoskelet Disord 14: 156-166.

, ,

9. Li L (2020) Radiology.

, ,

10. Rahimzadeh M, Attar A (2020) IMU 19: 100360.

, ,

11. Bai HX, Hsieh B, Xiong Z, Halsey K, Choi JW, et al. (2020) Radiology.

, ,

12. Caruso D, Zerunian M, Polici M (2020) Radiology 2020: 201237.

, ,

13. Pan Y, Guan H, Zhou S (2020) Eur Radiol.

, ,

14. Kallianos K (2019) Clin Radiol. 74: 338-345.

, ,

15. Burdick H, Lam C, Mataraso S, Siefkas A, Braden G, et al. (2020) Comput Biol Med 124: 103949.

, ,