Impact of Image Pre-Processing and Optimizers on U-Net Segmentation of Prostate Cancer in MRI
Article Sidebar
Main Article Content
Abstract
Prostate cancer remains among the most frequently diagnosed cancers in men and is a major issue in achieving timely and accurate diagnosis. Magnetic Resonance Imaging (MRI) is widely applied because it is capable of picking up high-resolution anatomical information, but cancer regions must be manually segmented, which is time-consuming and prone to the variability of experts. This study proposes an automated segmentation algorithm using the U-Net deep learning model with image pre-processing techniques to address these deficiencies. Median filtering was done to remove salt-and-pepper noise, followed by brightness enhancement to improve the intensity contrast of images. The pre-processed images were used to train a U-Net model for prostate cancer segmentation. The Dice Similarity Coefficient (DSC) metric was used to evaluate the segmentation accuracy. Three optimizers, Adam, RMSprop, and Adagrad, were tested. All of them were trained between 10 and 100 epochs. Adam optimizer obtained the highest segmentation performance at epoch 90 with the highest DSC value of 0.9907, while RMSprop and Adagrad produced 0.9888 and 0.9655, respectively. Pre-processing raised the mean DSC from 0.8206 to 0.8733, confirming its impact on image quality enhancement. Overall, the proposed method demonstrates high accuracy and reliability, offering a practical solution to support radiologists in prostate cancer diagnosis and treatment planning.
Manuscript received: 9 Oct 2025 | Revised: 5 Dec 2025 | Accepted: 26 Feb 2026 | Published: 31 Mar 2026
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
M. Anzidei, A. Bazzocchi, C. Gagliardo, C. Catalano, A. Napoli and R. Scipione, "HIFU for Bone Metastases and other Musculoskeletal Applications," Seminars in Interventional Radiology, vol. 35, no. 04, pp. 261-267, 2018.
DOI: https://doi.org/10.1055/s-0038-1673363
Z. Khan, N. Yahya, K. Alsaih, M.I. Al-Hiyali and F. Meriaudeau, "Recent Automatic Segmentation Algorithms of MRI Prostate Regions: A Review," IEEE Access, vol. 9, pp. 97878-97905, 2021.
DOI: https://doi.org/10.1109/ACCESS.2021.3090825
B. Shaw, F.M. Walter, W. Hamilton and T. Martins, "Symptom appraisal and help seeking in males with symptoms of possible prostate cancer: a qualitative study with an ethnically diverse sample in London," British Journal of General Practice, vol. 73, no. 732, pp. e502-e510, 2023.
DOI: https://doi.org/10.3399/BJGP.2022.0554
N.F. Wasserman, P. Murguan, B. Spilseth, G.J. Metzger and T. Sanghvi, "Peripheral Zone Enlargement: a newly described entity on MRI," medRxiv, 2020.
DOI: https://doi.org/10.1101/2020.04.03.20052290
H. Gong, SLIC segmentation and texture feature extraction for a radiomic analysis of prostate cancer using multiparametric MRI Master thesis, Eindhoven University of Technology, 2024.
K. Shanmugalingam, “Prostate Image Segmentation Using Deep Learning”, PhD Thesis, UNSW Sydney, 2024. DOI:https://doi.org/10.26190/unsworks/30491
H. Chen, L. Kumaralingam, S. Zhang, S. Song, F. Zhang, H. Zhang, T. Pham, K. Punithakumar, E.H. Lou, Y. Zhang, L.H. Le and R. Zheng, "Neural implicit surface reconstruction of freehand 3D ultrasound volume with geometric constraints," Medical Image Analysis, vol. 98, pp. 103305, 2024.
DOI: https://doi.org/10.1016/J.MEDIA.2024.103305
L. Anand, S. Mewada, W. Shamsi, M. Ritonga, N. Aflisia, P. KumarSarangi and M. NdoleArthur, "[Retracted] Diagnosis of Prostate Cancer Using GLCM Enabled KNN Technique by Analyzing MRI Images," BioMed Research International, vol. 2023, no. 1, 2023.
DOI: https://doi.org/10.1155/2023/3913351
L. Wang, R. Sun, X. Wei, J. Chen, S. Jia, G. Wu and S. Nie, "Enhancing prostate cancer segmentation on multiparametric magnetic resonance imaging with background information and gland masks," Medical Physics, vol. 51, no. 11, pp. 8179-8191, 2024.
DOI: https://doi.org/10.1002/MP.17346
X. Li, Z. Liu and L. Yang, "The artificial intelligence automatic diagnosis model based on the needle tissue of prostate ultrasound," International Conference on Communication, Information, and Digital Technologies (CIDT2024), p. 23, 2024.
DOI: https://doi.org/10.1117/12.3033311
P. Mehta, M. Antonelli, S. Singh, N. Grondecka, E.W. Johnston, H.U. Ahmed, M. Emberton, S. Punwani and S. Ourselin, "AutoProstate: Towards Automated Reporting of Prostate MRI for Prostate Cancer Assessment Using Deep Learning," Cancers, vol. 13, no. 23, pp. 6138, 2021.
DOI: https://doi.org/10.3390/CANCERS13236138
O.J. Pellicer-Valero, J.L.M. Jiménez, V. Gonzalez-Perez, J.L.C. Ramón-Borja, I.M. García, M.B. Benito, P.P. Gómez, J. Rubio-Briones, M.J. Rupérez and J.D. Martín-Guerrero, "Deep learning for fully automatic detection, segmentation, and Gleason grade estimation of prostate cancer in multiparametric magnetic resonance images," Scientific Reports, vol. 12, no. 1, 2022.
DOI: https://doi.org/10.1038/S41598-022-06730-6
R. Jin, D. Li, D. Xiang, L. Zhang, H. Zhou, F. Shi, W. Zhu, J. Cai, T. Peng and X. Chen, “AI-based Automatic Segmentation of Prostate on Multi-modality Images: A Review”. 2024.
DOI:10.48550/arXiv.2407.06612
P. Lapa, M. Castelli, I. Gonçalves, E. Sala and L. Rundo, "A Hybrid End-to-End Approach Integrating Conditional Random Fields into CNNs for Prostate Cancer Detection on MRI," Applied Sciences, vol. 10, no. 1, pp. 338, 2020.
DOI: https://doi.org/10.3390/APP10010338
S.K. Reddy and K. Kathirvelu, "Hybrid Optimization Enabled Deep-Learning for Prostate Cancer Detection," Sensing and Imaging, vol. 25, no. 1, 2024.
DOI: https://doi.org/10.1007/S11220-024-00495-0
S. Iqbal, G.F. Siddiqui, A. Rehman, L. Hussain, T. Saba, U. Tariq and A.A. Abbasi, "Prostate Cancer Detection Using Deep Learning and Traditional Techniques," IEEE Access, vol. 9, pp. 27085-27100, 2021.
DOI: https://doi.org/10.1109/ACCESS.2021.3057654
R. Cuocolo, A. Stanzione, A. Castaldo, D.R.D. Lucia and M. Imbriaco, "Quality control and whole-gland, zonal and lesion annotations for the PROSTATEx challenge public dataset," European Journal of Radiology, vol. 138, pp. 109647, 2021.
DOI: https://doi.org/10.1016/j.ejrad.2021.109647
H. Liang, N. Li and S. Zhao, "Salt and Pepper Noise Removal Method Based on a Detail-Aware Filter," Symmetry, vol. 13, no. 3, pp. 515, 2021.
DOI: https://doi.org/10.3390/SYM13030515
J. Jian, L. Liu, Y. Zhang, K. Xu and J. Yang, "Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5," Remote Sensing, vol. 15, no. 17, pp. 4319, 2023.
DOI: https://doi.org/10.3390/RS15174319
L. Kong, M. Huang, L. Zhang and L.W.C. Chan, "Enhancing Diagnostic Images to Improve the Performance of the Segment Anything Model in Medical Image Segmentation," Bioengineering, vol. 11, no. 3, pp. 270, 2024.
DOI: https://doi.org/10.3390/BIOENGINEERING11030270
M. Montazerolghaem, Y. Sun, G. Sasso and A. Haworth, "U-Net Architecture for Prostate Segmentation: The Impact of Loss Function on System Performance," Bioengineering, vol. 10, no. 4, pp. 412, 2023.
DOI: https://doi.org/10.3390/BIOENGINEERING10040412
K.H. Zou, S.K. Warfield, A. Bharatha, C.M. Tempany, M.R. Kaus, S.J. Haker, W.M. Wells, F.A. Jolesz and R. Kikinis, "Statistical validation of image segmentation quality based on a spatial overlap index1," Academic Radiology, vol. 11, no. 2, pp. 178-189, 2004.