A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality
Ultrasound imaging is widely used as a noninvasive lesion detection method in diagnostic medicine. Improving the quality of these ultrasound images is very important for accurate diagnosis, and deep learning-based algorithms have gained significant attention. This study proposes a multiscale deep en...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/23/12928 |
| _version_ | 1797400426840064000 |
|---|---|
| author | Ryeonhui Kim Kyuseok Kim Youngjin Lee |
| author_facet | Ryeonhui Kim Kyuseok Kim Youngjin Lee |
| author_sort | Ryeonhui Kim |
| collection | DOAJ |
| description | Ultrasound imaging is widely used as a noninvasive lesion detection method in diagnostic medicine. Improving the quality of these ultrasound images is very important for accurate diagnosis, and deep learning-based algorithms have gained significant attention. This study proposes a multiscale deep encoder–decoder with phase congruency (MSDEPC) algorithm based on deep learning to improve the quality of diagnostic ultrasound images. The MSDEPC algorithm included low-resolution (LR) images and edges as inputs and constructed a multiscale convolution and deconvolution network. Simulations were conducted using the Field 2 program, and data from real experimental research were obtained using five clinical datasets containing images of the carotid artery, liver hemangiomas, breast malignancy, thyroid carcinomas, and obstetric nuchal translucency. LR images, bicubic interpolation, and super-resolution convolutional neural networks (SRCNNs) were modeled as comparison groups. Through visual assessment, the image processed using the MSDEPC was the clearest, and the lesions were clearly distinguished. The structural similarity index metric (SSIM) value of the simulated ultrasound image using the MSDEPC algorithm improved by approximately 38.84% compared to LR. In addition, the peak signal-to-noise ratio (PSNR) and SSIM values of clinical ultrasound images using the MSDEPC algorithm improved by approximately 2.33 times and 88.58%, respectively, compared to LR. In conclusion, the MSDEPC algorithm is expected to significantly improve the spatial resolution of ultrasound images. |
| first_indexed | 2024-03-09T01:55:21Z |
| format | Article |
| id | doaj.art-fa13f4c9efde4be88c700635cf10b247 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T01:55:21Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fa13f4c9efde4be88c700635cf10b2472023-12-08T15:12:11ZengMDPI AGApplied Sciences2076-34172023-12-0113231292810.3390/app132312928A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image QualityRyeonhui Kim0Kyuseok Kim1Youngjin Lee2Department of Radiology, Sunchonhyang University Bucheon Hospital, 170, Jomaru-ro, Bucheon-si 14584, Gyeonggi-do, Republic of KoreaDepartment of Biomedical Engineering, Eulji University, 553, Sanseong-daero, Sujeong-gu, Seongnam-si 13135, Gyeonggi-do, Republic of KoreaDepartment of Radiological Science, Gachon University, 191, Hambakmoero, Yeonsu-gu, Incheon 21936, Republic of KoreaUltrasound imaging is widely used as a noninvasive lesion detection method in diagnostic medicine. Improving the quality of these ultrasound images is very important for accurate diagnosis, and deep learning-based algorithms have gained significant attention. This study proposes a multiscale deep encoder–decoder with phase congruency (MSDEPC) algorithm based on deep learning to improve the quality of diagnostic ultrasound images. The MSDEPC algorithm included low-resolution (LR) images and edges as inputs and constructed a multiscale convolution and deconvolution network. Simulations were conducted using the Field 2 program, and data from real experimental research were obtained using five clinical datasets containing images of the carotid artery, liver hemangiomas, breast malignancy, thyroid carcinomas, and obstetric nuchal translucency. LR images, bicubic interpolation, and super-resolution convolutional neural networks (SRCNNs) were modeled as comparison groups. Through visual assessment, the image processed using the MSDEPC was the clearest, and the lesions were clearly distinguished. The structural similarity index metric (SSIM) value of the simulated ultrasound image using the MSDEPC algorithm improved by approximately 38.84% compared to LR. In addition, the peak signal-to-noise ratio (PSNR) and SSIM values of clinical ultrasound images using the MSDEPC algorithm improved by approximately 2.33 times and 88.58%, respectively, compared to LR. In conclusion, the MSDEPC algorithm is expected to significantly improve the spatial resolution of ultrasound images.https://www.mdpi.com/2076-3417/13/23/12928super resolution (SR)deep learningmultiscale deep encoder–decoder with phase congruency (MSDEPC)diagnostic ultrasound imagequantitative evaluation of image quality |
| spellingShingle | Ryeonhui Kim Kyuseok Kim Youngjin Lee A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality Applied Sciences super resolution (SR) deep learning multiscale deep encoder–decoder with phase congruency (MSDEPC) diagnostic ultrasound image quantitative evaluation of image quality |
| title | A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality |
| title_full | A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality |
| title_fullStr | A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality |
| title_full_unstemmed | A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality |
| title_short | A Multiscale Deep Encoder–Decoder with Phase Congruency Algorithm Based on Deep Learning for Improving Diagnostic Ultrasound Image Quality |
| title_sort | multiscale deep encoder decoder with phase congruency algorithm based on deep learning for improving diagnostic ultrasound image quality |
| topic | super resolution (SR) deep learning multiscale deep encoder–decoder with phase congruency (MSDEPC) diagnostic ultrasound image quantitative evaluation of image quality |
| url | https://www.mdpi.com/2076-3417/13/23/12928 |
| work_keys_str_mv | AT ryeonhuikim amultiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality AT kyuseokkim amultiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality AT youngjinlee amultiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality AT ryeonhuikim multiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality AT kyuseokkim multiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality AT youngjinlee multiscaledeepencoderdecoderwithphasecongruencyalgorithmbasedondeeplearningforimprovingdiagnosticultrasoundimagequality |