Anaslisis Penggunan Super Image Resolution Dengan Menggunakan EDSR dan WDSR Pada Sel Manusia
Abstrak
Teknologi digital berkembang secara cepat dan masif. Salah satunya pada proses pengamatan sel pada manusia. Teknologi tingkat tinggi yang digunakan untuk proses tersebut adalah menggunakan PET Scan. Namun teknologi tersebut masih memiliki kekurangan, yaitu buruknya citra yang dihasilkan. Penelitian ini berfungsi untuk memperbaiki permasalahan tersebut. Dengan menjadikan output dari PET Scan sebagai data masukan (dataset) ke dalam sebuah model jaringan super-resolution, yaitu model Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) dan Wide Activation for Efficient and Accurate Image Super-Resolution (WDSR). Tipe dataset yang digunakan adalah PET Y-90. Model kemudian ditraining untuk melihat seberapa baik model bekerja pada dataset. Proses training dilakukan dengan steps sebanyak 300.000 kali dan batch size 16, serta Scalling dari kedua model adalah 4. Hasil dari proses training akan dianalisis untuk melihat efektifitas perbaikan citra yang dihasilkan model. Dengan membandingkan PSNR dan SSIM yang dihasilkan dapat melihat kualitas citra yang dihasilkan oleh kedua model . Hasil PSNR dari EDSR dan WDSR masing-masing sebesar … dB dan … dB, serta SSIM sebesar … dan … . Setelah dataset di training, citra dengan kualitas rendah dari dataset dapat diubah menjadi citra dengan kualitas Super Resolution.
Kata kunci : EDSR,WDSR,Super-Resolution,Deep Learning
Referensi
Hon, C. C., Shin, J. W., Carninci, P., & Stubbington,
M. J. T. (2018). The human cell atlas: Technical approaches
and challenges. https://doi.org/10.1093/bfgp/elx029.
Regev, A., Teichmann, S., Lander, E., Amit, I.,
Benoist, C., Birney, E., Bodenmiller, B., Campbell, P.,
Carninci, P., & Enard, W. (2017). Science Forum: The
Human Cell Atlas. ELife.
Ledig, C., Theis, L., Huszár, F., Caballero, J.,
Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J.,
Wang, Z., & Shi, W. (2017). Photo-realistic single image
super-resolution using a generative adversarial network.
https://doi.org/10.1109/CVPR.2017.19
Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate
image super-resolution using very deep convolutional
networks. Proceedings of the IEEE Computer Society
Conference on Computer Vision and Pattern Recognition.
https://doi.org/10.1109/CVPR.2016.182
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A.,
& Chen, L. C. (2018). Inverted Residuals and Linear
Bottlenecks:Mobile Networks for Classification, Detection
and Segmentation. Proceedings of the IEEE Computer
Society Conference on Computer Vision and Pattern
Recognition.
Simonyan, K., & Zisserman, A. (2015). Very deep
convolutional networks for large-scale image recognition. 3rd
International Conference on Learning Representations, ICLR
- Conference Track Proceedings.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu,
B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y.
(2020). Generative adversarial networks. Communications of
the ACM, 63(11). https://doi.org/10.1145/3422622.
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep
residual learning for image recognition. Proceedings of the
IEEE Computer Society Conference on Computer Vision and
Pattern Recognition, 2016-December.
https://doi.org/10.1109/CVPR.2016.90
Yu, J., Fan, Y., & Huang, T. (2020). Wide activation
for efficient image and video super-resolution.
https://doi.org/10.1016/j.nima.2020.164293
Nenclares, P., & Harrington, K. J. (2020). The
biology of cancer. In Medicine (United Kingdom) (Vol. 48,
Issue 2). https://doi.org/10.1016/j.mpmed.2019.11.001
Roizen, M. F. (2012). Hallmarks of Cancer: The
Next Generation. Yearbook of Anesthesiology and Pain
Management, 2012.
https://doi.org/10.1016/j.yane.2012.02.046.
Rosilawati, N. E., Nasution, I., & Murni, T. W.
(2018). PENGGUNAAN RADIOFARMAKA UNTUK
DIAGNOSA DAN TERAPI DI INDONESIA DAN ASAS
KEAMANAN PENGGUNAAN OBAT. SOEPRA, 3(1).
https://doi.org/10.24167/shk.v3i1.697.
Fendler, W. P., Czernin, J., Herrmann, K., & Beyer,
T. (2016). Variations in PET/MRI operations: Results from
an international survey among 39 active sites.
https://doi.org/10.2967/jnumed.116.174169.
Mayerhoefer, M. E., Prosch, H., Beer, L., Tamandl,
D., Beyer, T., Hoeller, C., Berzaczy, D., Raderer, M.,
Preusser, M., Hochmair, M., Kiesewetter, B., Scheuba, C.,
Ba-Ssalamah, A., Karanikas, G., Kesselbacher, J., Prager, G.,
Dieckmann, K., Polterauer, S., Weber, M., … Haug, A. R.
(2020). PET/MRI versus PET/CT in oncology: a prospective
single-center study of 330 examinations focusing on
implications for patient management and cost considerations.
https://doi.org/10.1007/s00259-019-04452-y.
Kim, J., Lee, J. K., & Lee, K. M. (2016). Accurate
image super-resolution using very deep convolutional
networks. Proceedings of the IEEE Computer Society
Conference on Computer Vision and Pattern Recognition.
https://doi.org/10.1109/CVPR.2016.182.
Lim, B., Son, S., Kim, H., Nah, S., & Lee, K. M.
(2017). Enhanced Deep Residual Networks for Single Image
Super-Resolution. IEEE Computer Society Conference on
Computer Vision and Pattern Recognition Workshops, 2017-
July. https://doi.org/10.1109/CVPRW.2017.151
Shelhamer, E., Long, J., & Darrell, T. (2017). Fully
Convolutional Networks for Semantic Segmentation. IEEE
Transactions on Pattern Analysis and Machine Intelligence,
(4). 2016. https://doi.org/10.1109/TPAMI.
Xie, S., Girshick, R., Dollár, P., Tu, Z., & He, K.
(2017). Aggregated residual transformations for deep neural
networks. Proceedings - 30th IEEE Conference on Computer
Vision and Pattern Recognition, CVPR 2017, 2017-January.
https://doi.org/10.1109/CVPR.2017.634
Osendorfer, C., Soyer, H., & van der Smagt, P.
(2014). Image super-resolution with fast approximate
convolutional sparse coding. https://doi.org/10.1007/978-3-
-12643-2_31.
Shi, W., Caballero, J., Huszar, F., Totz, J., Aitken,
A. P., Bishop, R., Rueckert, D., & Wang, Z. (2016). RealTime Single Image and Video Super-Resolution Using an
Efficient Sub-Pixel Convolutional Neural Network.
Proceedings of the IEEE Computer Society Conference on
Computer Vision and Pattern.
Salimans, T., & Kingma, D. P. (2016). Weight
normalization: A simple reparameterization to accelerate
training of deep neural networks.
Wang, Q., Ma, Y., Zhao, K., & Tian, Y. (2022). A
Comprehensive Survey of Loss Functions in Machine
Learning. Annals of Data Science,.
https://doi.org/10.1007/s40745-020-00253-5
Wang, Z., Bovik, A. C., Sheikh, H. R., &
Simoncelli, E. P. (2004). Image quality assessment: From
error visibility to structural similarity. IEEE Transactions on
Image Processing). https://doi.org/10.1109/TIP.2003.819861
Afaq, S., & Rao, S. (2020). Significance Of Epochs
On Training A Neural Network. International Journal of
Scientific & Technology Research, 9(06).
Mujilahwati, S., Sholihin, M., & Wardhani, R.
(2021). Optimasi Hyperparameter TensorFlow dengan
Menggunakan Optuna di Python: Study Kasus Klasifikasi
Dokumen Abstrak Skripsi. JURNAL MEDIA
INFORMATIKA BUDIDARMA,.
https://doi.org/10.30865/mib.v5i3.3090.
Abdelaziz Ismael, S. A., Mohammed, A., & Hefny,
H. (2020). An enhanced deep learning approach for brain
cancer MRI images classification using residual networks.
Artificial Intelligence in Medicine, 102.
https://doi.org/10.1016/j.artmed.2019.101779.
Refianti, R., Mutiara, A. B., & Priyandini, R. P.
(2019). Classification of melanoma skin cancer using
convolutional neural network.
https://doi.org/10.14569/IJACSA.2019.0100353.
Yuliani, E., Aini, A. N., & Khasanah, C. U. (2020).
Perbandingan Jumlah Epoch Dan Steps Per Epoch Pada
Convolutional Neural Network Untuk Meningkatkan Akurasi
Dalam Klasifikasi Gambar.
https://doi.org/10.46808/informa.v5i3.140
Mujilahwati, S., Sholihin, M., & Wardhani, R.
(2021). Optimasi Hyperparameter TensorFlow dengan
Menggunakan Optuna di Python: Study Kasus Klasifikasi
Dokumen Abstrak Skripsi. JURNAL MEDIA
INFORMATIKA BUDIDARMA, 5(3).
https://doi.org/10.30865/mib.v5i3.3090.
Nurfita, R. D., & Ariyanto, G. (2018). Implementasi
Deep Learning berbasis Tensorflow untuk Pengenalan Sidik
Jari. Emitor: Jurnal Teknik Elektro.
https://doi.org/10.23917/emitor.v18i01.6236
Wang, Y. R. (Joyce), Wang, P., Adams, L. C.,
Sheybani, N. D., Qu, L., Sarrami, A. H., Theruvath, A. J.,
Gatidis, S., Ho, T., Zhou, Q., Pribnow, A., Thakor, A. S.,
Rubin, D., & Daldrup-Link, H. E. (2023). Low-count wholebody PET/MRI restoration: an evaluation of dose reduction
spectrum and five state-of-the-art artificial intelligence
