Text
DETEKSI TRANSVENTRIKULAR PADA KEPALA JANIN DARI CITRA ULTRASONOGRAFI 2 DIMENSI MENGGUNAKAN CONVOLUTION NEURAL NETWORK (CNN) DENGAN ARSITEKTUR U-NET DAN FASTER R-CNN
Fetal head detection is usually used by doctors a process to determine the condition of the fetus. This process takes a very long time and draining the mind, because to do this process is very prioritizing the expertise and experience of the gynecologist. This is a particular challenge to determine the condition of the fetus that is preferred to detect objects in the fetal head that is transventricular there are several factors that mark such as Cavum Septi Pelucidi (CSP), Frontal Horn, and Choroid Plexus. Therefore, the process will be carried out to design the algorithm of deep learning method for transventricular object detection system in medical images to obtain objects that are in the fetal head accurately. Then this research will do segmentation with U-Net and will be continued on the object detection process using Faster R-CNN. The best model results obtained in the 5th model is on the parameters epoch 1000, batch size 64 and for detection accuracy obtained in the experiment by producing mAP 65%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2207003633 | T78716 | T787162022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available