Deep Learning Framework for Liver Tumor Segmentation

Khushi Gupta; Shrey Aggarwal; Avinash Jha; Aamir Habib; Jayant Jagtap; Shrikrishna Kolhar; Shruti Patil; Ketan Kotecha; Tanupriya Choudhury

doi:10.4108/eetpht.10.5561

Authors

Khushi Gupta Symbiosis International University
Shrey Aggarwal Symbiosis International University
Avinash Jha Symbiosis International University
Aamir Habib Symbiosis International University
Jayant Jagtap Symbiosis International University
Shrikrishna Kolhar Symbiosis International University
Shruti Patil Symbiosis International University
Ketan Kotecha Symbiosis International University
Tanupriya Choudhury Graphic Era University

DOI:

https://doi.org/10.4108/eetpht.10.5561

Keywords:

Computed Tomography Scans, CT Scans, Deep Learning, Liver Tumor Segmentation, ResUNet, Support Vector Machine, Deep Neural Network

Abstract

INTRODUCTION: Segregating hepatic tumors from the liver in computed tomography (CT) scans is vital in hepatic surgery planning. Extracting liver tumors in CT images is complex due to the low contrast between the malignant and healthy tissues and the hazy boundaries in CT images. Moreover, manually detecting hepatic tumors from CT images is complicated, time-consuming, and needs clinical expertise.

OBJECTIVES: An automated liver and hepatic malignancies segmentation is essential to improve surgery planning, therapy, and follow-up evaluation. Therefore, this study demonstrates the creation of an intuitive approach for segmenting tumors from the liver in CT scans.

METHODS: The proposed framework uses residual UNet (ResUNet) architecture and local region-based segmentation. The algorithm begins by segmenting the liver, followed by malignancies within the liver envelope. First, ResUNet trained on labeled CT images predicts the coarse liver pixels. Further, the region-level segmentation helps determine the tumor and improves the overall segmentation map. The model is tested on a public 3D-IRCADb dataset.

RESULTS: Two metrics, namely dice coefficient and volumetric overlap error (VOE), were used to evaluate the performance of the proposed method. ResUNet model achieved dice of 0.97 and 0.96 in segmenting liver and tumor, respectively. The value of VOE is also reduced to 1.90 and 0.615 for liver and tumor segmentation.

CONCLUSION: The proposed ResUNet model performs better than existing methods in the literature. Since the proposed model is built using U-Net, the model ensures quality and precise dimensions of the output.

Downloads

Download data is not yet available.

References

Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023;73(1). DOI: https://doi.org/10.3322/caac.21763

Bilic P, Christ P, Li HB, Vorontsov E, Ben-Cohen A, Kaissis G, Szeskin A, Jacobs C, Mamani GE, Chartrand G, Lohöfer F. The liver tumor segmentation benchmark (lits). Medical Image Analysis. 2023 Feb 1;84:102680. DOI: https://doi.org/10.1016/j.media.2022.102680

Rela M, Suryakari NR, Reddy PR. Liver tumor segmentation and classification: A systematic review. 2020 IEEE-HYDCON. 2020 Sep 11:1-6. DOI: https://doi.org/10.1109/HYDCON48903.2020.9242757

Huang SY, Hsu WL, Hsu RJ, Liu DW. Fully convolutional network for the semantic segmentation of medical images: A survey. Diagnostics. 2022 Nov 11;12(11):2765. DOI: https://doi.org/10.3390/diagnostics12112765

Galicia-Moreno M, Silva-Gomez JA, Lucano-Landeros S, Santos A, Monroy-Ramirez HC, Armendariz-Borunda J. Liver cancer: therapeutic challenges and the importance of experimental models. Canadian Journal of Gastroenterology and Hepatology. 2021 Feb 28;2021. DOI: https://doi.org/10.1155/2021/8837811

Talukdar J, Singh TP, Barman B. Tools and Technologies for Implementing AI Approaches in Healthcare. InArtificial Intelligence in Healthcare Industry 2023 Jul 2 (pp. 169-178). Singapore: Springer Nature Singapore. DOI: https://doi.org/10.1007/978-981-99-3157-6_10

Sudhakar P, Satapathy SC. A novel skin cancer Detection based transfer learning with optimization algorithm using Dermatology Dataset. EAI Endorsed Transactions on Pervasive Health and Technology. 2023 Oct 30;9. DOI: https://doi.org/10.4108/eetpht.9.4277

Agarwal N, Kumar N, Abrol V, Garg Y. Enhancing Image Recognition: Leveraging Machine Learning on Specialized Medical Datasets. EAI Endorsed Transactions on Pervasive Health and Technology. 2023 Nov 8;9. DOI: https://doi.org/10.4108/eetpht.9.4336

Sharma S, Aggarwal A, Choudhury T. Breast cancer detection using machine learning algorithms. In2018 International conference on computational techniques, electronics and mechanical systems (CTEMS) 2018 Dec 21 (pp. 114-118). IEEE. DOI: https://doi.org/10.1109/CTEMS.2018.8769187

Khari S, Gupta D, Chaudhary A, Bhatla R. A Novel Approach to Identify the Brain Tumour Using Convolutional Neural Network. EAI Endorsed Transactions on Pervasive Health and Technology. 2023 Nov 8;9. DOI: https://doi.org/10.4108/eetpht.9.4337

Solanki S, Singh UP, Chouhan SS, Jain S. Brain Tumor Detection and Classification using Intelligence Techniques: An Overview. IEEE Access. 2023 Feb 6. DOI: https://doi.org/10.1109/ACCESS.2023.3242666

Roy S, Das D, Lal S, Kini J. Novel edge detection method for nuclei segmentation of liver cancer histopathology images. Journal of Ambient Intelligence and Humanized Computing. 2023 Jan;14(1):479-96. DOI: https://doi.org/10.1007/s12652-021-03308-4

Anter AM, Abualigah L. Deep Federated Machine Learning-Based Optimization Methods for Liver Tumor Diagnosis: A Review. Archives of Computational Methods in Engineering. 2023 Jun;30(5):3359-78. DOI: https://doi.org/10.1007/s11831-023-09901-4

Saha Roy S, Roy S, Mukherjee P, Halder Roy A. An automated liver tumour segmentation and classification model by deep learning based approaches. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization. 2023 May 4;11(3):638-50. DOI: https://doi.org/10.1080/21681163.2022.2099300

Sasirekha N, Anitha R, Vanathi T, Balakrishnan U. Automatic liver tumor segmentation from CT images using random forest algorithm. The Scientific Temper. 2023 Sep 27;14(03):696-702. DOI: https://doi.org/10.58414/SCIENTIFICTEMPER.2023.14.3.19

Luu MH, Mai HS, Pham XL, Le QA, Le QK, van Walsum T, Le NH, Franklin D, Le VH, Moelker A, Chu DT. Quantification of liver-Lung shunt fraction on 3D SPECT/CT images for selective internal radiation therapy of liver cancer using CNN-based segmentations and non-rigid registration. Computer Methods and Programs in Biomedicine. 2023 May 1;233:107453. DOI: https://doi.org/10.1016/j.cmpb.2023.107453

Chen PT, Wu T, Wang P, Chang D, Liu KL, Wu MS, Roth HR, Lee PC, Liao WC, Wang W. Pancreatic cancer detection on CT scans with deep learning: a nationwide population-based study. Radiology. 2023 Jan;306(1):172-82. DOI: https://doi.org/10.1148/radiol.220152

Chang CC, Chen HH, Chang YC, Yang MY, Lo CM, Ko WC, Lee YF, Liu KL, Chang RF. Computer-aided diagnosis of liver tumors on computed tomography images. Computer methods and programs in biomedicine. 2017 Jul 1;145:45-51. DOI: https://doi.org/10.1016/j.cmpb.2017.04.008

Song L, Wang H, Wang ZJ. Bridging the gap between 2D and 3D contexts in CT volume for liver and tumor segmentation. IEEE Journal of Biomedical and Health Informatics. 2021 Apr 27;25(9):3450-9. DOI: https://doi.org/10.1109/JBHI.2021.3075752

Barstugan M, Ceylan R, Sivri M, Erdogan H. Automatic liver segmentation in abdomen CT images using SLIC and AdaBoost algorithms. InProceedings of the 2018 8th International Conference on Bioscience, Biochemistry and Bioinformatics 2018 Jan 18 (pp. 129-133). DOI: https://doi.org/10.1145/3180382.3180383

Muthuswamy J, Kanmani B. Optimization Based Liver Contour Extraction of Abdominal CT Images. International Journal of Electrical & Computer Engineering (2088-8708). 2018 Dec 15;8(6). DOI: https://doi.org/10.11591/ijece.v8i6.pp5061-5070

Bi L, Kim J, Kumar A, Feng D. Automatic liver lesion detection using cascaded deep residual networks. arXiv preprint arXiv:1704.02703. 2017 Apr 10.

Chlebus G, Schenk A, Moltz JH, van Ginneken B, Hahn HK, Meine H. Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing. Scientific reports. 2018 Oct 19;8(1):15497. DOI: https://doi.org/10.1038/s41598-018-33860-7

Gruber N, Antholzer S, Jaschke W, Kremser C, Haltmeier M. A joint deep learning approach for automated liver and tumor segmentation. In2019 13th International conference on Sampling Theory and Applications (SampTA) 2019 Jul 8 (pp. 1-5). IEEE. DOI: https://doi.org/10.1109/SampTA45681.2019.9030909

Senthilvelan J, Jamshidi N. A pipeline for automated deep learning liver segmentation (PADLLS) from contrast enhanced CT exams. Scientific Reports. 2022 Sep 22;12(1):15794. DOI: https://doi.org/10.1038/s41598-022-20108-8