Abstract
Accurate diagnosis and treatment planning for medical conditions rely heavily on the results of medical image segmentation. Medical images are available in many modalities like CT scans, MRI, histopathological, and ultrasound images. Among all, the real-time analysis of the ultrasound is the most complex as the internal organ’s visualization requires experience from the radiologist. Diagnosing the medical conditions and unavailability of experienced radiologists during an emergency requires automated segmentation which heavily depends on computer-aided diagnostic systems. The new generation CAD systems are found to incorporate advanced deep learning algorithms to produce accurate segmentation results. While most of the segmentation models relate to the encoder-decoder model as the base architecture and thus evolve a variety of modifications in its pipeline architecture. This paper presents the analytical study of the various Encoder- Decoder based models like UNet, Residual UNet (Res-U-Net), Dense UNet (DenseUNet), Attention UNet, UNet + +, Double UNet, and U2Net (U-Squared-Net) on ultrasound image segmentation. Further, the paper presents the various trade-offs, application areas, open challenges, and performance analysis of these models on benchmark datasets, namely the HC18 Challenge dataset, CUM dataset, and B-mode Ultrasound Nerve Segmentation dataset. The performance analysis of these models is presented using the six state-of-the-art metrics like Dice coefficient, Jaccard index, sensitivity, specificity, Mean Absolute distance, and Housdorff Distance. Based on the above parameters U2-Net (U-Squared-Net) outperformed all other neural network models for all three datasets. In terms of all four criteria (Dice Coefficient: 0.92, 0.89, 0.9, Jaccard Index: 0.81, 0.79, 0.81, Sensitivity: 0.86, 0.84, 0.86, Specificity: 0.97, 0.95, 0.96), the U2-Net (U-Squared-Net) model performed the best. Over the HC18 Challenge dataset, the CUM dataset, and the B-Mode Ultrasound nerve segmentation dataset, U2-Net (U-Squared-Net) model achieved the best HD results (HC18: 3.8, CUM Dataset: 4, B-mode US Dataset: 3.6) and the lowest MAD values (HC18: 2.1, CUM Dataset: 3, B-mode US Dataset: 2.15). In addition, the analysis also highlights the architectural differences between these models, focusing on their type of connections, number of layers, and additional components. The outcome of this research provides valuable perception into the strengths and limitations of each encoder-decoder-based model, aiding researchers and practitioners in selecting the most appropriate model for Ultrasound image segmentation tasks.
Similar content being viewed by others
Data Availability
The dataset and code generated during and/or analyzed during the current study are available from the corresponding author at a reasonable request.
References
Pham DL, Xu C, Prince JL (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2(1):315–337
Litjens G, Kooi T, Bejnordi BE, Setio AA, Ciompi F, Ghafoorian M, Van Der Laak JA, Van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Ronneberger O, Fischer P, Brox T (2015) UNet: convolutional networks for biomedical image segmentation. MICCAI 2015(9351):234–241
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D UNet: Learning dense volumetric segmentation from sparse annotation. MICCAI 2016(9901):424–432
Drozdzal M, Vorontsov E, Chartrand G, Kadoury S, Pal C (2016) The Importance of Skip Connections in Biomedical Image Segmentation. MICCAI 2016(10008):179–187
Zhang Z, Chen P, McGough M, Xie Y (2021) A review on deep learning for ultrasound image segmentation. Med Image Anal 70:101977
Fakhry A, Sayed GI, El-Baz A (2020) Automated ultrasound image segmentation: a review. Biomed Signal Process Control 55:101626
Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B (2018). Attention UNet: learning where to look for the pancreas. arXiv preprint arXiv:1804.03999.
Li X, Chen H, Qi X, Dou Q, Fu CW, Heng PA (2018) H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT Volumes. IEEE Trans Med Imag 37(12):2663–2674
Zhou Z, Siddiquee MMR, Tajbakhsh N, and Liang J. (2020). UNet++: A nested UNet architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, (pp 3–11)
Pravitasari AA, Iriawan N, Almuhayar M, Azmi T, Irhamah I, Fithriasari K, Purnami SW, Ferriastuti W. (2020). UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation. In: TELKOMNIKA (Telecommunication computing electronics and control. Vol. 18, Issue 3, pp 1310. Universitas Ahmad Dahlan. https://doi.org/10.12928/telkomnika.v18i3.14753
Jha D, Riegler MA, Johansen D, Halvorsen P, Johansen HD. (2020). DoubleUNet: A deep convolutional neural network for medical image segmentation. arXiv preprint arXiv:2006.04868
Qin X, Zhang Z, Huang C, Dehghan M, Zaiane O, Jagersand M (2020) U2-Net: Going deeper with nested U-structure for salient object detection. Pattern Recogn 106:107404
Zheng T, Qin H, Cui Y, Wang R, Zhao W, Zhang S, Zhao L (2023) Segmentation of thyroid glands and nodules in ultrasound images using the improved U-net architecture. BMC Med Imag 23(1):56. https://doi.org/10.1186/s12880-023-01011-8
Andreasen LA, Feragen A, Christensen AN, Thybo JK, Svendsen MBS, Zepf K, Tolsgaard MG (2023) Multi-center deep learning for placenta segmentation in obstetric ultrasound with multi-observer and cross-country generalization. Sci Reports 13(1):2221. https://doi.org/10.1038/s41598-023-29105-x
Bi H, Cai C, Sun J, Jiang Y, Lu G, Shu H, Ni X (2023) BPAT-UNet: Boundary preserving assembled transformer UNet for ultrasound thyroid nodule segmentation. Comput Methods Programs Biomed 238:107614. https://doi.org/10.1016/j.cmpb.2023.107614
Iqbal A, Sharif M (2023) PDF-UNet: A semi-supervised method for segmentation of breast tumor images using a U-shaped pyramid-dilated network. Expert Syst Appl 221:119718. https://doi.org/10.1016/j.eswa.2023.119718
Balachandran S, Qin X, Jiang C, Blouri ES, Forouzandeh A, Dehghan M, Punithakumar K (2023) ACU2E-net: A novel predicts–refine attention network for segmentation of soft-tissue structures in ultrasound images. Comput Biol Med 157:106792. https://doi.org/10.1016/j.compbiomed.2023.106792
Chen G, Li L, Dai Y, Zhang J, Yap MH (2023) AAU-net: An adaptive attention U-net for breast lesions segmentation in ultrasound images. IEEE Trans Med Imag 42(5):1289–1300. https://doi.org/10.1109/TMI.2022.3226268
He Q, Yang Q, Xie M (2023) HCTNet: A hybrid CNN-transformer network for breast ultrasound image segmentation. Computer Biol Med 155:10669. https://doi.org/10.1016/j.compbiomed.2023.106629
Lyu Y, Xu Y, Jiang X, Liu J, Zhao X, Zhu X (2023) AMS-PAN: Breast ultrasound image segmentation model combining attention mechanism and multi-scale features. Biomed Signal Process Control 81:10445. https://doi.org/10.1016/j.bspc.2022.104425
Krithika Alias AnbuDevi M, Suganthi K (2022) Review of semantic segmentation of medical images using modified architectures of UNET. Diagnostics 12(12):3064. https://doi.org/10.3390/diagnostics12123064
Joharah F, Mohideen K (2022) Evaluation of fetal head circumference (HC) and biparietal diameter (BPD (biparietal diameter)) in ultrasound images using multi-task deep convolutional neural network. Curr Signal Transduct Ther 17(3):57–66. https://doi.org/10.2174/1574362417666220513151926
Mămuleanu M, Urhuț CM, Săndulescu LD, Kamal C, Pătrașcu AM, Ionescu AG, Șerbănescu MS, Streba CT (2022) Deep learning algorithms in the automatic segmentation of liver lesions in ultrasound investigations. Life 12(11):1877
Zhu F, Gao Z, Zhao C, Zhu H, Nan J, Tian Y, Zhou W (2022) A deep learning-based method to extract lumen and media-adventitia in intravascular ultrasound images. Ultrason Imag 44(5–6):191–203. https://doi.org/10.1177/01617346221114137
Zeng W, Luo J, Cheng J, Lu Y (2022) Efficient fetal ultrasound image segmentation for automatic head circumference measurement using a lightweight deep convolutional neural network. Med Phys 49(8):5081–5092. https://doi.org/10.1002/mp.15700
AshkaniChenarlogh V, GhelichOghli M, Shabanzadeh A, Sirjani N, Akhavan A, Shiri I, Arabi H, Sanei Taheri M, Tarzamni MK (2022) Fast and accurate U-net model for fetal ultrasound image segmentation. Ultrason Imag 44(1):25–38. https://doi.org/10.1177/01617346211069882
Moccia S, Fiorentino MC, Frontoni E (2021) Mask-R 2 CNN: A distance-field regression version of mask-RCNN for fetal-head delineation in ultrasound images. Int J Comput Assist Radiol Surg 16(10):1711–1718. https://doi.org/10.1007/s11548-021-02430-0
Zeng Y, Tsui PH, Wu W, Zhou Z, Wu S (2021) Fetal ultrasound image segmentation for automatic head circumference biometry using deeply supervised attention-gated V-net. J Digit Imaging 34(1):134–148. https://doi.org/10.1007/s10278-020-00410-5
Qiao D, and Zulkernine F (2020) Dilated squeeze-and-excitation U-net for fetal ultrasound image segmentation. In: Paper presented at the 2020 IEEE conference on computational intelligence in bioinformatics and computational biology, CIBCB 2020, doi:https://doi.org/10.1109/CIBCB48159.2020.9277667 Retrieved from www.scopus.com
Xing Y, Yang F, Tang Y, Zhang L (2020) Ultrasound fetal head edge detection using fusion UNet++. J Image Graph 25(2):366–377. https://doi.org/10.11834/jig.190242
Funding
The author declares that there is no funding associated with this project.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors of this manuscript declare that there is no conflict of interest.
Ethical approval
The author of this manuscript confirms that: (i) Informed, written consent has been obtained from the relevant sources wherever required; (ii) All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and its later amendments. (iii) Approval and/or informed consent were not required for the study as the dataset is collected from an open-source website which is freely available.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Srivastava, S., Vidyarthi, A. & Jain, S. Analytical study of the encoder-decoder models for ultrasound image segmentation. SOCA 18, 81–100 (2024). https://doi.org/10.1007/s11761-023-00373-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11761-023-00373-9