دانلود مقاله سیستم تشخیص سرطان پستان مبتنی بر یادگیری عمیق با محاسبات مه
چکیده
مقدمه
مطالعات مرتبط
طراحی سیستم
ارزیابی
نتیجه گیری
منابع
Abstract
Introduction
Related Work
System Design
Evaluation
Conclusion
References
چکیده
در میان انواع مختلف سرطان، زنان بیشتری از سرطان سینه رنج می برند. سرطان سینه را می توان با ماموگرافی یا با استفاده از سونوگرافی تشخیص داد. تشخیص زودهنگام سرطان می تواند برای به حداقل رساندن پیچیدگی هایی که زنان با آن مواجه خواهند شد، مورد استفاده قرار گیرد. تکنیک های مبتنی بر یادگیری عمیق مانند شبکه های عصبی کانولوشن (CNN) برای تشخیص سرطان از طریق ماموگرافی یا اسکن اولتراسوند استفاده می شود. در این مطالعه از CNN مبتنی بر VGGNet برای شناسایی سلول های سرطانی استفاده شده است. یک معماری جدید برای جمع آوری، پردازش و ذخیره داده های بیمار در این مطالعه پیشنهاد شده است که شامل یک لایه مه است. این مطالعه در مقایسه با مطالعات قبلی از دقت، حساسیت و ویژگی بالایی برخوردار بود.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Among the different types of cancers, more women are suffering from breast cancer. Breast cancer can be identified by mammograms or using ultrasounds. Early detection of the cancer can be used to minimize the complexities the women will face. Deep learning based techniques such as convolutional neural networks (CNN) are used to detect the cancer from mammograms or ultrasound scans. In this study, VGGNet based CNN is used to detect the cancer cells. A novel architecture for collecting, processing and storing of patient data is proposed in this study involving a fog layer. This study achieved a high accuracy, sensitivity and specificity compared to previous studies.
Introduction
Breast cancer is the most common cancer among women worldwide. 19.3 million new cases of cancer are reported in 2020. 2.3 million new cases of breast cancer are found among them [1]. In 2018 the most common cancer was lung cancer and breast cancer came in second place. But in 2020 that situation is changed. This can be due to unhealthy habits of the people. By increasing the awareness of people, the causes for breast cancer can be reduced. The number of deaths can be reduced by early detection and diagnosis of the disease. Mammography is one method of screening for breast cancer. It can be used to detect the cancer before physical symptoms appear [2]. This method uses radiation to take a breast image. Radiation is harmful to the patient as well as to the radiologist. Apart from that the accuracy of the diagnosis depends on the radiologist’s experience. According to [3], the error rate is 30% when radiologists interpret the results.
Conclusion
Breast cancer is one of the most common cancers in the world. More women are suffering from this disease and early diagnosis can be used to reduce the fatalities. For this purpose a VGGNet based CNN is used in this study. A major problem of using DL in healthcare is the amount of data generated per person. As a solution to the storing problem of these data, a novel architecture involving three layers is proposed in this paper. The data received from the edge devices are sent to the fog layer for processing and the results are stored in the cloud for long term storage. This study achieved better accuracy compared with previous studies.