Skripsi
NTERPRETASI OTOMATIS DAN PENINGKATAN KINERJA PADA CITRA MEDIS ULTRASONOGRAFI DENGAN MENGGUNAKAN METODE DEEP LEARNING.
Ultrasonography (USG) is a medical method that uses high-frequency sound waves to produce dynamic visual images in the health sector, especially in prenatal cases. Although ultrasound imaging is a routine examination in medical treatment, medical ultrasound images often have problems such as low resolution, noise, and artifacts. Technological constraints and conventional methods for improving the image quality of medical images open up opportunities for the development of more sophisticated solutions. This study proposes an approach that focuses on the use of advanced technology, especially deep learning, preprocessing, and image enhancement, to improve the image quality of ultrasound medical images. This approach has several main objectives. First, improve the accuracy of diagnosis, time, and cost efficiency in medical practice. Second, overcoming complex image quality problems in medical images through deep learning, image enhancement, and preprocessing technologies. Third, reducing human involvement in the interpretation process by utilizing the proposed technology. This research method will combine the results of preprocessing and image enhancement on various medical image datasets. Deep learning technology will be used to measure improvements in image quality and diagnostic performance. The results of this study are expected to make a significant contribution to the development of medical technology by increasing diagnostic accuracy, efficiency, and productivity in clinics and hospitals. Overall, this study underscores the importance of the image quality of medical ultrasound images, the challenges faced in enhancing them, and the potential of proposed solutions using advanced technologies such as deep learning, preprocessing, and image enhancement. With this approach, it is expected that accuracy and efficiency in patient diagnosis can be significantly improved.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407000560 | T138566 | T1385662023 | Central Library (Referens) | Available |
No other version available