Automated prediction of endometriosis using deep learning | ||
| International Journal of Nonlinear Analysis and Applications | ||
| دوره 12، شماره 2، بهمن 2021، صفحه 2403-2416 اصل مقاله (1.36 M) | ||
| نوع مقاله: Research Paper | ||
| شناسه دیجیتال (DOI): 10.22075/ijnaa.2021.5383 | ||
| نویسندگان | ||
| S Visalaxi* ؛ T Sudalai Muthu | ||
| Department of Computer Science and Engineering, Hindustan Institute of Technology and Science, Padur, Chennai, India. | ||
| چکیده | ||
| Endometriosis is the anomalous progress of cells at the outer part of the uterus. Generally, this endometrial tissue stripes the uterine cavity. The existence of endometriosis is identified through procedures known as Transvaginal Ultra Sound Scan (TVUS), Magnetic Resonance Imaging (MRI), Laparoscopic procedures, and Histopathological slides. Minimal Invasive Surgery (MIS) Laparo-scopic images are recorded in a small camera. To assist the surgeon in identifying their presence of endometriosis, image quality (characteristics) was enhanced for more visual clarity. Deep learning has the ability in recognising the images for classification. The Convolutional Neural Networks (CNNs) perform classification of images on large datasets. The proposed system evaluates the performance by a novel approach that implements the transfer learning model on a well-known architecture called ResNet50. The proposed system train the model on ResNet50 architecture and yielded a training accuracy of 91%, validation accuracy of 90%, precision of 83%, and recall of 82%, which can be applied for larger datasets with better performance. The presented system yields higher Area Under Curve (AUC) of about 0.78. The proposed method yields better performance using ResNet50 compared to other transfer learning techniques. | ||
| کلیدواژهها | ||
| TVUS؛ MRI؛ Laparoscopic images Deep Learning؛ Convolution neural network (CNN)؛ Transfer Learning؛ ResNet50 | ||
| مراجع | ||
|
| ||
|
آمار تعداد مشاهده مقاله: 17,613 تعداد دریافت فایل اصل مقاله: 11,254 |
||
| تعداد نشریات | 22 |
| تعداد شمارهها | 723 |
| تعداد مقالات | 10,402 |
| تعداد مشاهده مقاله | 72,892,311 |
| تعداد دریافت فایل اصل مقاله | 64,570,094 |