Combination of Image Enhancement and Double U-Net Architecture for Liver Segmentation in CT-Scan Images
Abstract
Liver cancer can be identified using CT-Scan liver image segmentation. Liver segmentation can be performed using CNN architecture like U-Net. However, the segmentation results using U-Net architecture are affected by image quality. Low image quality can affect the accuracy of segmentation results. This study proposes a combination of image enhancement and segmentation stages on CT-Scan liver images. Image enhancement is achieved by using a combination of CLAHE to enhance contrast and Bilateral Filter to reduce noise. The segmentation architecture proposed in this study is Double U-Net which is a development of U-Net architecture by adding a second U-Net block with the same structure as a single U-Net. The first U-Net is used to extract simple features, while the second U-Net is used to extract more complex features and enhance the segmentation results of the first U-Net. PSNR and SSIM measure the results of image enhancement. The PSNR is more than 40dB and the SSIM result is close to 1. These results show that the proposed image enhancement method can enhance the quality of original images. The segmentation results were measured by calculating accuracy, sensitivity, specificity, dice score, and IoU. The result of liver segmentation obtained 99% for accuracy, 98% for sensitivity, 99% for specificity, 98% for dice score, and 90% for IoU. This shows that liver segmentation using Double U-Net obtained good segmentation. Results of image enhancement and image segmentation show that the proposed method is very good for enhancing image quality and performing liver segmentation accurately.
Downloads
References
X. Li, P. Ramadori, D. Pfister, M. Seehawer, L. Zender, and M. Heikenwalder, “The Immunological and Metabolic Landscape in Primary and Metastatic Liver Cancer,” Nat. Rev. Cancer, vol. 21, no. 9, pp. 541–557, 2021.
J. Ferlay et al., “Global Cancer Observatory : Cancer Today,” International Journal of Cancer, 2024.
K. Sridhar, K. C, W.-C. Lai, and B. P. Kavin, “Detection of Liver Tumour Using Deep Learning Based Segmentation with Coot Extreme Learning Model,” Biomedicines, vol. 11, no. 3, 2023.
J. D. L. Araújo et al., “An automatic method for segmentation of liver lesions in computed tomography images using deep neural networks,” Expert Syst. Appl., vol. 180, p. 115064, 2021.
Q. Gu, H. Zhang, R. Cai, S. Y. Sui, and R. Wang, “Segmentation of liver CT images based on weighted medical transformer model,” Sci. Rep., vol. 14, no. 1, p. 9887, 2024.
A. V. Vardhan, K. S. Roy, K. Reddy, K. Sainadh, and M. Nannapeni, “Liver Tumor Segmentation using Deep Learning Techniques,” Int. J. Food Nutr. Sci., vol. 11, no. 12, pp. 1585–1592, 2023.
D. Mitrea et al., “Liver Tumor Segmentation From Computed Tomography Images Through Convolutional Neural Networks,” in 2023 9th International Conference on Systems and Informatics (ICSAI), 2023, pp. 1–6.
M. Rahimpour, A. Radwan, H. Vandermeulen, S. Sunaert, K. Goffin, and M. Koole, “Investigating certain choices of CNN configurations for brain lesion segmentation,” arXiv Prepr. arXiv2212.01235, 2022.
F. Zohourian, J. Siegemund, M. Meuter, and J. Pauli, “Efficient fine-grained road segmentation using superpixel-based CNN and CRF models,” arXiv Prepr. arXiv2207.02844, 2022.
M. Krithika alias AnbuDevi and K. Suganthi, “Review of Semantic Segmentation of Medical Images Using Modified Architectures of UNET,” Diagnostics, vol. 12, no. 12. 2022.
N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, “U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications,” IEEE Access, vol. 9, pp. 82031–82057, 2021.
D. U. N. Qomariah, H. Tjandrasa, and C. Fatichah, “Segmentation of Microaneurysms for Early Detection of Diabetic Retinopathy using MResUNet,” Int. J. Intell. Eng. Syst., vol. 14, no. 3, pp. 359–373, 2021.
J. Qin, X. Wang, D. Mi, Q. Wu, Z. He, and Y. Tang, “CI-UNet: Application of Segmentation of Medical Images of the Human Torso,” Appl. Sci., vol. 13, no. 12, 2023.
H. Lu, Y. She, J. Tie, and S. Xu, “Half-UNet: A Simplified U-Net Architecture for Medical Image Segmentation,” Front. Neuroinform., vol. 16, no. June, pp. 1–10, 2022.
C. Li, X. Liu, W. Li, C. Wang, H. Liu, and Y. Yuan, “U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation,” arXiv Prepr. arXiv2406.02918, 2024.
A. Desiani et al., “Multi-Stage CNN: U-Net and Xcep-Dense of Glaucoma Detection in Retinal Images,” J. Electron. Electromed. Eng. Med. Informatics, vol. 5, no. 4, pp. 211–222, 2023.
F. Özcan, O. N. Uçan, S. Karaçam, and D. Tunçman, “Fully Automatic Liver and Tumor Segmentation from CT Image Using an AIM-Unet,” Bioengineering, vol. 10, no. 2, 2023.
Y. A. Ayalew, K. A. Fante, and M. A. Mohammed, “Modified U-Net for liver cancer segmentation from computed tomography images with a new class balancing method.,” BMC Biomed. Eng., vol. 3, no. 1, p. 4, Mar. 2021.
Z. Liu et al., “Liver CT sequence segmentation based with improved U-Net and graph cut,” Expert Syst. Appl., vol. 126, pp. 54–63, 2019.
Z. Sun, Y. Pang, Y. Sun, and X. Liu, “DMFF-Net: Densely Macroscopic Feature Fusion Network for Fast Magnetic Resonance Image Reconstruction,” Electron., vol. 11, no. 23, 2022.
L. Qi et al., “High Quality Entity Segmentation,” Proc. IEEE Int. Conf. Comput. Vis., pp. 4024–4033, 2023.
S. U. Saeed et al., “Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation,” arXiv Prepr. arXiv2202.09798, 2022.
S. Almotairi, G. Kareem, M. Aouf, B. Almutairi, and M. A. M. Salem, “Liver tumor segmentation in CT scans using modified segnet,” Sensors (Switzerland), vol. 20, no. 5, 2020.
V. Gavini and G. R. J. Lakshmi, “CT Image Denoising Model Using Image Segmentation for Image Quality Enhancement for Liver Tumor Detection Using CNN,” Trait. du Signal, vol. 39, no. 5, pp. 1807–1814, 2022.
C. T. Jensen et al., “Reduced-Dose Deep Learning Reconstruction for Abdominal CT of Liver Metastases,” Radiology, vol. 303, no. 1, pp. 90–98, 2022.
R. Naseem, Z. A. Khan, N. Satpute, A. Beghdadi, F. A. Cheikh, and J. Olivares, “Cross-Modality Guided Contrast Enhancement for Improved Liver Tumor Image Segmentation,” IEEE Access, vol. 9, pp. 118154–118167, 2021.
A. Desiani, M. Erwin, B. Suprihatin, S. Yahdin, A. I. Putri, and F. R. Husein, “Bi-Path Architecture of CNN Segmentation and Classification Method for Cervical Cancer Disorders Based on Pap-smear Images,” Int. J. Comput. Sci., vol. 48, no. 3, pp. 1–9, 2021.
A. A. Siddiqi, G. B. Narejo, M. Tariq, and A. Hashmi, “Investigation of Histogram Equalization Filter for CT Scan Image Enhancement,” Biomed. Eng. - Appl. Basis Commun., vol. 31, no. 5, pp. 1–10, 2019.
T. P. H. Nguyen, Z. Cai, K. Nguyen, S. Keth, N. Shen, and M. Park, “Pre-processing Image using Brightening, CLAHE and RETINEX,” arXiv Prepr. arXiv2003.10822, 2020.
M. Hayati et al., “Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning,” Procedia Comput. Sci., vol. 216, pp. 57–66, 2023.
D. R. I. M. Setiadi, “PSNR vs SSIM: Imperceptibility Quality Assessment for Image Steganography,” Multimed. Tools Appl., vol. 80, no. 6, pp. 8423–8444, 2021.
U. Sara, M. Akter, and M. S. Uddin, “Image Quality Assessment through FSIM, SSIM, MSE and PSNR—A Comparative Study,” J. Comput. Commun., vol. 07, no. 03, pp. 8–18, 2019.
A. Gutub and F. Al-Shaarani, “Efficient Implementation of Multi-image Secret Hiding Based on LSB and DWT Steganography Comparisons,” Arab. J. Sci. Eng., vol. 45, no. 4, pp. 2631–2644, 2020.
H. H. Liu, P. C. Su, and M. H. Hsu, “An Improved Steganography Method Based on Least-Significant-Bit Substitution and Pixel-Value Differencing,” KSII Trans. Internet Inf. Syst., vol. 14, no. 11, pp. 4537–4556, 2020.
A. Desiani et al., “Denoised Non-Local Means with BDDU-Net Architecture for Robust Retinal Blood Vessel Segmentation,” Int. J. Pattern Recognit. Artif. Intell., vol. 37, no. 16, pp. 1–27, 2023.
I. Bakurov, M. Buzzelli, R. Schettini, M. Castelli, and L. Vanneschi, “Structural similarity index ( SSIM ) revisited : A data-driven approach,” vol. 189, 2022.
N. Umilizah, P. Octavia, L. I. Kesuma, I. Rayani, and M. Suedarmin, “Combination of Image Improvement on Segmentation Using a Convolutional Neural Network in Efforts to Detect Liver Disease,” J. Informatics Telecommun. Eng., vol. 7, no. 2, pp. 375–384, 2024.
M. Elhoseny and K. Shankar, “Optimal bilateral filter and Convolutional Neural Network based denoising method of medical image measurements,” Meas. J. Int. Meas. Confed., vol. 143, pp. 125–135, 2019.
B. C. Rao, S. S. Rani, K. Shashidhar, G. Satyanarayana, and K. Raju, “An effective image-denoising method with the integration of thresholding and optimized bilateral filtering,” Multimed. Tools Appl., vol. 82, no. 28, pp. 43923–43943, 2023.
A. Asokan and J. Anitha, “Adaptive Cuckoo Search based optimal bilateral filtering for denoising of satellite images,” ISA Trans., vol. 100, pp. 308–321, 2020.
H. T. Nguyen, M. N. Nguyen, T. Q. Duong, and P. H. D. Bui, “Denoising with Median and Bilateral on CT images for Liver segmentation,” in Proceedings - 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022, 2022, pp. 59–64.
J. Muthuswamy, “New Edge Preserving Hybrid Method for Better Enhancement of Liver CT Images,” Indian J. Sci. Technol., vol. 10, no. 10, pp. 1–7, 2017.
J. Kugelman et al., “A comparison of deep learning U-Net architectures for posterior segment OCT retinal layer segmentation,” Sci. Rep., vol. 12, no. 1, pp. 1–14, 2022.
D. Jha, M. A. Riegler, D. Johansen, P. Halvorsen, and H. D. Johansen, “DoubleU-Net: A deep convolutional neural network for medical image segmentation,” in Proceedings - IEEE Symposium on Computer-Based Medical Systems, 2020, vol. 2020-July, no. 1, pp. 558–564.
A. Farasin, L. Colomba, and P. Garza, “Double-step U-Net: A deep learning-based approach for the estimation ofwildfire damage severity through sentinel-2 satellite data,” Appl. Sci., vol. 10, no. 12, 2020,
Y. Liu et al., “Double-branch U-Net for multi-scale organ segmentation,” Methods, vol. 205, pp. 220–225, 2022.
W. Guo, H. Zhou, Z. Gong, and G. Zhang, “Double U-Nets for Image Segmentation by Integrating the Region and Boundary Information,” IEEE Access, vol. 9, pp. 69382–69390, 2021.
P. Sangeeta, L. S. Jayanth, K. Chinni, K. J. Chandran, and K. Teja, “Replenishing the Facial Features Behind the Mask Using Unet,” Interantional J. Sci. Res. Eng. Manag., vol. 08, no. 06, pp. 1–5, 2024.
Stevenazy, “Liver Dataset,” Kaggle, 2020.
D. N. A, S. G, D. D. J, and S. P. Kashyap, “Retinopathy Based Multistage Classification of Diabeties,” in Proceedings of the 3rd International Conference on Integrated Intelligent Computing Communication & Security (ICIIC 2021), 2021, pp. 54–60.
M. Arhami, Y. R. Fachri, H. Hendrawaty, and A. Adriana, “A Semantic Segmentation of Nucleus and Cytoplasm in Pap-smear Images using Modified U-Net Architecture,” Infotel, vol. 16, no. 2, pp. 273–288, 2024.
C. Y. Jeong, H. C. Shin, and M. Kim, “Sensor-Data Augmentation for Human Activity Recognition with Time-Warping and Data Masking,” Multimed. Tools Appl., vol. 80, no. 14, pp. 20991–21009, 2021.
G. Iglesias, E. Talavera, Á. González-Prieto, A. Mozo, and S. Gómez-Canaval, “Data Augmentation Techniques in Time Series Domain: A Survey and Taxonomy,” Neural Comput. Appl., vol. 35, no. 14, pp. 10123–10145, 2023.
K. Chaitanya et al., “Semi-Supervised Task-Driven Data Augmentation for Medical Image Segmentation,” Med. Image Anal., vol. 68, p. 101934, 2021.
T. Nemoto et al., “Effects of Sample Size and Data Augmentation on U-Net-Based Automatic Segmentation of Various Organs,” Radiol. Phys. Technol., vol. 14, no. 3, pp. 318–327, 2021.
N. P. Sutramiani, N. Suciati, and D. Siahaan, “MAT-AGCA: Multi Augmentation Technique on Small Dataset for Balinese Character Recognition using Convolutional Neural Network,” ICT Express, vol. 7, no. 4, pp. 521–529, 2021.
Y. Jiang, P. Malliaras, B. Chen, and D. Kulić, “Model-Based Data Augmentation for User-Independent Fatigue Estimation,” Comput. Biol. Med., vol. 137, no. September, pp. 1–11, 2021.
K. Maharana, S. Mondal, and B. Nemade, “A Review: Data Pre-processing and Data Augmentation Techniques,” Glob. Transitions Proc., vol. 3, no. 1, pp. 91–99, 2022.
C. Bhardwaj, S. Jain, and M. Sood, “Diabetic Retinopathy Severity Grading Employing Quadrant-Based Inception-V3 Convolution Neural Network Architecture,” Int. J. Imaging Syst. Technol., vol. 31, no. 2, pp. 592–608, 2021.
A. Desiani, D. A. Zayanti, R. Primartha, F. Efriliyanti, and N. A. C. Andriani, “Variasi Thresholding untuk Segmentasi Pembuluh Darah Citra Retina,” J. Edukasi dan Penelit. Inform., vol. 7, no. 2, p. 255, 2021.
B. Kim, R. O. Serfa Juan, D. E. Lee, and Z. Chen, “Importance of Image Enhancement and CDF for Fault Assessment of Photovoltaic Module using IR Thermal Image,” Appl. Sci., vol. 11, no. 18, 2021.
J. Dash and N. Bhoi, “Retinal Blood Vessel Segmentation using Otsu Thresholding with Principal Component Analysis,” Proc. 2nd Int. Conf. Inven. Syst. Control. ICISC 2018, no. Icisc, pp. 933–937, 2018.
S. Singh, N. Mittal, and H. Singh, “Multifocus Image Fusion Based on Multiresolution Pyramid and Bilateral Filter,” IETE J. Res., vol. 68, no. 4, pp. 2476–2487, 2022.
A. B. A., A. P. P., and V. Maik, “Contrast and Luminance Enhancement Technique for Fundus Images Using Bi-Orthogonal Wavelet Transform and Bilateral Filter,” ECS J. Solid State Sci. Technol., vol. 10, no. 7, p. 071010, 2021.
P. Naveen and P. Sivakumar, “Adaptive Morphological and Bilateral Filtering with Ensemble Convolutional Neural Network for Pose-Invariant Face Recognition,” J. Ambient Intell. Humaniz. Comput., vol. 12, no. 11, pp. 10023–10033, 2021.
T. Guo, J. Dong, H. Li, and Y. Gao, “Simple Convolutional Neural Network on Image Classification,” in International Conference on Big Data Analysis, 2017, pp. 721–724.
C. P. Parmo, L. I. Kesuma, and D. Geovani, “The Combination of Black Hat Transform and U-Net in Image Enhancement and Blood Vessel Segmentation in Retinal Images,” Comput. Eng. Appl., vol. 12, no. 3, pp. 129–145, 2023.
S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” Journal. Pract., vol. 10, no. 6, pp. 730–743, 2016.
S. Ngah and R. A. Bakar, “Sigmoid Function Implementation using The Unequal Segmentation of Differential Lookup Table and Second Order Nonlinear Function,” Telecommun. Electron. Comput. Eng., vol. 9, no. 2–8, pp. 103–108, 2017.
A. Panja, J. J. Christy, and Q. M. Abdul, “An Approach to Skin Cancer Detection using Keras and Tensorflow,” J. Phys. Conf. Ser., vol. 1911, no. 1, pp. 1–8, 2021.
U. Ruby, P. Theerthagiri, J. Jacob, and V. Vamsidhar, “Binary Cross Entropy with Deep Learning Technique for Image Classification,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 4, pp. 5393–5397, 2020.
R. Yu, Y. Wang, Z. Zou, and L. Wang, “Convolutional Neural Networks with Refined Loss Functions for The Real-time Crash Risk Analysis,” Transp. Res. Part C Emerg. Technol., vol. 119, no. April, p. 102740, 2020.
J. H. J. C. Ortega, A. C. Lagman, L. R. Q. Natividad, E. T. Bantug, M. R. Resureccion, and L. O. Manalo, “Analysis of Performance of Classification Algorithms in Mushroom Poisonous Detection using Confusion Matrix Analysis,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 1.3, pp. 451–456, 2020.
N. Maleki, Y. Zeinali, and S. T. A. Niaki, “A K-NN Method for Lung Cancer Prognosis with The Use of A Genetic Algorithm for Feature Selection,” Expert Syst. Appl., vol. 164, no. July 2019, p. 113981, 2021.
S. K. Hou, Z. G. Ou, P. X. Qin, Y. L. Wang, and Y. R. Liu, “Image-based Crack Recognition of Tunnel Lining using Residual U-Net Convolutional Neural Network,” IOP Conf. Ser. Earth Environ. Sci., vol. 861, no. 7, pp. 1–11, 2021.
S. M. González-collazo et al., “Santiago Urban Dataset SUD : Combination of Handled and Mobile Laser Scanning point clouds,” 2020.
J. Huang et al., “DBFU-Net: Double Branch Fusion U- Net with Hard Example Weighting Train Strategy to Segment Retinal Vessel,” PeerJ Comput. Sci., vol. 8, pp. 1–29, 2022.
F. Rahmad, Y. Suryanto, and K. Ramli, “Performance Comparison of Anti-Spam Technology Using Confusion Matrix Classification,” in IOP Conference Series: Materials Science and Engineering, 2020, vol. 879, no. 1.
H. Kaur, N. Kaur, and N. Neeru, “A Comparative Study of Image Enhancement Algorithms for Abdomen CT Images,” 2024 IEEE Int. Conf. Interdiscip. Approaches Technol. Manag. Soc. Innov. IATMSI 2024, vol. 2, pp. 1–6, 2024.
L. Li and H. Ma, “RDCTrans U-Net: A Hybrid Variable Architecture for Liver CT Image Segmentation,” Sensors, vol. 22, no. 7. 2022.
J. Wu et al., “U-Net combined with multi-scale attention mechanism for liver segmentation in CT images,” BMC Med. Inform. Decis. Mak., vol. 21, no. 1, pp. 1–12, 2021.
K. M. Napte and A. Mahajan, “Liver segmentation using marker controlled watershed transform,” Int. J. Electr. Comput. Eng., vol. 13, no. 2, pp. 1541–1549, 2023.
N. Sasirekha, R. Anitha, V. T, and U. Balakrishnan, “Automatic liver tumor segmentation from CT images using random forest algorithm,” Sci. Temper, vol. 14, no. 03, pp. 696–702, 2023.
Copyright (c) 2024 Dwi Fitri Brianna, Lucky Indra Kesuma, Dite Geovani, Puspa Sari
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
