A Comprehensive Review of Deep Learning-Based Image Segmentation Architectures Applied to Various Diseases

Hafsa Laçi – University of Tirana, Faculty of Economy, Street Arben Broci 1, 1001, Tirana, Albania

Kozeta Sevrani – University of Tirana, Faculty of Economy, Street Arben Broci 1, 1001, Tirana, Albania

Abstract: Image segmentation plays a significant role in facilitating the ar­duous process of medical image analysis. There are numerous ways to per­form image segmentation, but deep learning architectures have brought about a revolution in this field by automating it and improving the accuracy of the results. However, due to the complex nature of X-ray, MRI, or Ultrasound medical image modalities used for diagnosis, selecting the appropriate seg­mentation architecture becomes a challenging task.

This review follows a systematic methodology to screen the literature and ex­plore the available deep learning-based segmentation architectures applied across different diseases. It aims to contribute to existing research by identify­ing if in the state-of-art exists any approach that can be adaptive for a broad­er range of diseases. Furthermore, it seeks to evaluate computational and per­formance efficiency when there is evidence

8th International Scientific Conference – EMAN 2024 – Economics and Management: How to Cope With Disrupted Times, Rome, Italy, March 21, 2024, CONFERENCE PROCEEDINGS, published by: Association of Economists and Managers of the Balkans, Belgrade, Serbia; ISBN 978-86-80194-83-7, ISSN 2683-4510, DOI: https://doi.org/10.31410/EMAN.2024

Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution-Non-Commercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission. 

REFERENCES

Ali, O., Ali, H., Shah, S. A. A., & Shahzad, A. (2022). Implementation of a Modified U-Net for Medical Image Segmentation on Edge Devices. IEEE Transactions on Circuits and Sys­tems II: Express Briefs, 69(11), 4593 – 4597. https://doi.org/10.1109/TCSII.2022.3181132 

Almajalid, R., Shan, J., Du, Y., & Zhang, M. (2018). Development of a Deep-Learning-Based Method for Breast Ultrasound Image Segmentation. 2018 17th IEEE International Confer­ence on Machine Learning and Applications (ICMLA). Orlando, FL, USA: IEEE.

Alsenan, A., Youssef, B. B., & Alhichri, H. (2021). A Deep Learning Model based on Mobile­NetV3 and UNet for Spinal Cord Gray Matter Segmentation. 2021 44th International Con­ference on Telecommunications and Signal Processing (TSP) (244-248). Brno, Czech Re­public: IEEE.

Baniasadi, M., Petersen, M. V., Gonçalves, J., Horn, A., Vlasov, V., Hertel, F., & Husch, A. (2022). DBSegment: Fast and robust segmentation of deep brain structures consider­ing domain generalization. Human Brain Mapping Journal, 44(2), 762–778. https://doi.org/10.1002/hbm.26097  

Benjelloun, M., El Adoui, M., & Larhmam, M. A. (2019). Automated Breast Tumor Segmen­tation in DCE-MRI Using Deep Learning. 2018 4th International Conference on Cloud Computing Technologies and Applications (Cloudtech). Brussels, Belgium: IEEE.

Bnouni, N., Amor, H. B., Rekik, I., Rhim, M. S., Solaiman, B., & Amara, N. E. B. (2021). Boosting CNN Learning by Ensemble Image Preprocessing Methods for Cervical Cancer Segmentation. 2021 18th International Multi-Conference on Systems, Signals & Devices (SSD). Monastir, Tunisia: IEEE.

Coroamă, D. M., Dioșan, L., Telecan, T., Andras, I., Crișan, N., Medan, P., Andreica, A., Cara­iani, C., Lebovici, A., Boca, B., & Bálint, Z. (2023). Fully automated bladder tumor segmentation from T2 MRI images using 3D U-Net algorithm. Frontiers in Oncology, 13. https://doi.org/10.3389/fonc.2023.1096136 

Du, G., Cao, X., Liang, J., Chen, X., & Zhan, Y. (2020). Medical Image Segmentation based on U-Net: A Review. Journal of Imaging Science and Technology, 64(2). https://doi.org/10.2352/J.ImagingSci.Technol.2020.64.2.020508 

Estrada, S., Lu, R., Diers, K., Zeng, W., Ehses, Ph., Stöcker, T., Breteler, M. M. B., & Reuter, M. (2021). Automated olfactory bulb segmentation on high resolutional T2-weighted MRI. Neu­roImage, 242. https://doi.org/10.1016/j.neuroimage.2021.118464 

Guerroumi, N., Playout, C., Laporte, C., & Cheriet, F. (2019). Automatic Segmentation of the Sco­liotic Spine from Mr Images. 2019 IEEE 16th International Symposium on Biomedical Imag­ing (ISBI 2019). Venice, Italy: IEEE.

Gupta, M., & Mishra, A. (2024). A systematic review of deep learning based image segmentation to detect polyp. Artificial Intelligence Review, 57(7). https://doi.org/10.1007/s10462-023-10621-1 

Hasan, S. M. K., & Linte, C. A. (2018). A Modified U-Net Convolutional Network Featuring a Nearest-neighbor Re-sampling-based Elastic-Transformation for Brain Tissue Characteriza­tion and Segmentation. 2018 IEEE Western New York Image and Signal Processing Work­shop (WNYISPW). Rochester, NY, USA: IEEE.

Huang, A., Jiang, L., Zhang, J., & Wang, Q. (2022). Attention-VGG16-UNet: a novel deep learning approach for automatic segmentation of the median nerve in ultrasound images. Quantitative Imaging in Medicine and Surgery, 12(6), 3138-3150. https://doi.org/10.21037/qims-21-1074 

Joshi, A., & Sharma, K. K. (2021). Hybrid Topology of Graph Convolution and Autoencoder Deep Network For Multiple Sclerosis Lesion Segmentation. 2021 International Conference on Ar­tificial Intelligence and Smart Systems (ICAIS). Coimbatore, India: IEEE.

Karimzadeh, R., Fatemizadeh, E., & Arabi, H. (2021). Attention-based deep learning segmenta­tion: Application to brain tumor delineation. 2021 28th National and 6th International Irani­an Conference on Biomedical Engineering (ICBME). Tehran, Iran, Islamic Republic: IEEE.

Khouy, M., Jabrane, Y., Ameur, M., & El Hassani, A. H. (2023). Medical Image Segmentation Us­ing Automatic Optimized U-Net Architecture Based on Genetic Algorithm. Journal of Per­sonalized Medicine, 13(9). https://doi.org/10.3390/jpm13091298 

Kumar, P., Nagar, P., Arora, Ch., & Gupta, A. (2018). U-Segnet: Fully Convolutional Neural Net­work Based Automated Brain Tissue Segmentation Tool. 2018 25th IEEE International Con­ference on Image Processing (ICIP). Athens, Greece: IEEE.

Liu, H., Hu, D., & Li, H. (2023). Medical Image Segmentation Using Deep Learning (T. 197). Ma­chine Learning for Brain Disorders. https://doi.org/https://doi.org/10.1007/978-1-0716-3195-9

Liu, X., Song, L., Liu, Sh., & Zhang, Y. (2021). A Review of Deep-Learning-Based Medical Im­age Segmentation Methods. Sustainability, MDPI, 13(3). https://doi.org/10.3390/su13031224

Orlando, N., Gillies, D. J., Gyacskov, I., Romagnoli, C., D’Souza, D., & Fenster, A. (2020). Auto­matic prostate segmentation using deep learning on clinically diverse 3D transrectal ultra­sound images. The International Journal of Medical Physics Research and Practice, 47(6), 2413-2426. https://doi.org/10.1002/mp.14134 

Qamar, S., Jin, H., Zheng, R., & Ahmad, P. (2018). 3D Hyper-Dense Connected Convolutional Neural Network for Brain Tumor Segmentation. 2018 14th International Conference on Se­mantics, Knowledge and Grids (SKG). Guangzhou, China: IEEE.

Rich, J. M., Bhardwaj, L. N., Shah, A., Gangal, K., Rapaka, M. S., Oberai, A. A., Fields, B. K. K., Matcuk Jr, G. R., & Duddalwar, V. A. (2023). Deep learning image segmentation approach­es for malignant bone lesions: a systematic review and meta-analysis. Frontiers in Radiolo­gy, 3. https://doi.org/10.3389/fradi.2023.1241651

Shapey, J., Kujawa, A., Dorent, R., Wang, G., Dimitriadis, A., Grishchuk, D., Paddick, I., Kitch­en, N., Bradford, R., Saeed, Sh. R., Bisdas, S., Ourselin, S., & Vercauteren, T. (2021). Seg­mentation of vestibular schwannoma from MRI, an open annotated dataset and baseline al­gorithm. Scientific Data-Nature, 286. https://www.nature.com/articles/s41597-021-01064-w 

Siddique, N., Paheding, S., Elkin, C. P., & Devabhaktuni, V. (2021). U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications. IEEE Access, 9, 82031 – 82057. https://doi.org/10.1109/ACCESS.2021.3086020 

Sun, L., Shao, W., Zhang, D., & Liu, M. (2019). Anatomical Attention Guided Deep Networks for ROI Segmentation of Brain MR Images. IEEE Transactions on Medical Imaging, 39(6), 2000 – 2012. https://doi.org/10.1109/TMI.2019.2962792 

Tricco, A. C., Lillie, E., Zarin, W., O’Brien, K. K., Colquhoun, H., Levac, D., Moher, D., Peters, M. D. J., Horsley, T., Weeks, L., Hempel, S., Akl, E. A., Chang, Ch., McGowan , J., Stew­art, L., Hartling, L., Aldcroft, A., Wilson, M. G., Garritty, Ch., Lewin, S., Godfrey, Ch. M., Macdonald, M. T., Langlois, E. V., Soares-Weiser, K., Moriarty, J., Clifford, T., Tunçalp, Ö., & Straus, Sh. E. (2018). PRISMA Extension for Scoping Reviews (PRISMA-ScR): Check­list and Explanation. Annals of Internal Medicine, 169(7), 467-473. https://doi.org/10.7326/M18-0850   

Wang, Ch., Guo, Y., Chen, W., & Yu, Z. (2019). Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net. 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC). Milwaukee, WI, USA: IEEE.

Wang, Q., Liu, Q., Luo, G., Liu, Zh., Huang, J., Zhou, Y., Xu, W., & Cheng, J. (2020). Automat­ed segmentation and diagnosis of pneumothorax on chest X-rays with fully convolutional multi-scale ScSE-DenseNet: a retrospective study. BMC Medical Informatics and Decision Making, 20(14). https://doi.org/10.1186/s12911-020-01325-5 

Yang, J., Faraji, M., & Basu, A. (2019). Robust segmentation of arterial walls in intravascular ultrasound images using Dual Path U-Net. Ultrasonics, 96, 24-33. https://doi.org/10.1016/j.ultras.2019.03.014 

Zhang, L., Zhang, K., & Pan, H. (2023). SUNet++: A Deep Network with Channel Attention for Small-Scale Object Segmentation on 3D Medical Images. Tsinghua Science and Technolo­gy, 28(4), 628 – 638. https://doi.org/10.26599/TST.2022.9010023 

Zhang, W., Cheng, H., & Gan, J. (2020). MUNet: A Multi-scale U-Net Framework for Medical Image Segmentation. 2020 International Joint Conference on Neural Networks (IJCNN). Glasgow, UK: IEEE.

Zhao, L., Zhou, D., Jin, X., & Zhu, W. (2022). nn-TransUNet: An Automatic Deep Learning Pipe­line for Heart MRI Segmentation. Life, MDPI, 12(10). https://doi.org/10.3390/life12101570 

Zhu, Q., Du, B., Wu, J., & Yan, P. (2018). A Deep Learning Health Data Analysis Approach: Au­tomatic 3D Prostate MR Segmentation with Densely-Connected Volumetric ConvNets. 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil: IEEE.