Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames
Simple Summary
Abstract
1. Introduction
Related Work
2. Materials and Methods
2.1. Data Preparation
2.2. Evaluation Metrics
2.3. Pre-Processing
2.4. Proposed Methodology
3. Results
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- World Cancer Research Fund International. “Liver Cancer Stat”. Available online: https://www.wcrf.org/cancer-trends/liver-cancer-statistics/ (accessed on 28 May 2023).
- Wei, W.; Haishan, X.; Alpers, J.; Rak, M.; Hansen, C. A deep learning approach for 2D ultrasound and 3D CT/MR image registration in liver tumor ablation. Comput. Methods Programs Biomed. 2021, 206, 106117. [Google Scholar] [CrossRef] [PubMed]
- Barash, Y.; Klang, E.; Lux, A.; Konen, E.; Horesh, N.; Pery, R.; Zilka, N.; Eshkenazy, R.; Nachmany, I.; Pencovich, N. Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography. Langenbeck’s Arch. Surg. 2022, 407, 3553–3560. [Google Scholar] [CrossRef]
- Arita, J.; Ono, Y.; Takahashi, M.; Inoue, Y.; Takahashi, Y.; Matsueda, K.; Saiura, A. Routine preoperative liver-specific magnetic resonance imaging does not exclude the necessity of contrast-enhanced intraoperative ultrasound in hepatic resection for colorectal liver metastasis. Ann. Surg. 2015, 262, 1086–1091. [Google Scholar] [CrossRef]
- Jrearz, R.; Hart, R.; Jayaraman, S. Intraoperative ultrasonography and surgical strategy in hepatic resection: What difference does it make? Can. J. Surg. 2015, 58, 318–322. [Google Scholar] [CrossRef] [PubMed]
- Scaife, C.L.; Ng, C.S.; Ellis, L.M.; Vauthey, J.N.; Charnsangavej, C.; Curley, S.A. Accuracy of preoperative imaging of hepatic tumors with helical computed Tomography. Ann. Surg. Oncol. 2006, 13, 542–546. [Google Scholar] [CrossRef] [PubMed]
- Solomon, M.J.; Stephen, M.S.; Gallinger, S.; White, G.H. Does intraoperative hepatic ultrasonography change surgical decision malting during liver resection? Am. J. Surg. 1994, 168, 307–310. [Google Scholar] [CrossRef]
- Romic, I.; Augustin, G.; Pavlek, G.; Kresic, E. Correlation between the liver transection line localization and future liver remnant hypertrophy in associating liver partition and portal vein ligation for staged hepatectomy. Front. Surg. 2024, 11, 1369962. [Google Scholar] [CrossRef] [PubMed]
- D’Hondt, M.; Vandenbroucke-Menu, F.; Préville-Ratelle, S.; Turcotte, S.; Chagnon, M.; Plasse, M.; Létourneau, R.; Dagenais, M.; Roy, A.; Lapointe, R. Is intra-operative ultrasound still useful for the detection of a hepatic tumour in the era of modern pre-operative imaging? HPB 2011, 13, 665–669. [Google Scholar] [CrossRef]
- Lubner, M.G.; Mankowski Gettle, L.; Kim, D.H.; Ziemlewicz, T.J.; Dahiya, N.; Pickhardt, P. Diagnostic and procedural intraoperative ultrasound: Technique, tips and tricks for optimizing results. Br. J. Radiol. 2021, 94, 20201406. [Google Scholar] [CrossRef]
- Zhou, L.-Q.; Wang, J.-Y.; Yu, S.-Y.; Wu, G.-G.; Wei, Q.; Deng, Y.-B.; Wu, X.-L.; Cui, X.-W.; Dietrich, C.F. Artificial intelligence in medical imaging of the liver. World J. Gastroenterol. 2019, 25, 672–682. [Google Scholar] [CrossRef]
- Fusaglia, M.; Tinguely, P.; Banz, V.; Weber, S.; Lu, H. A Novel Ultrasound-Based Registration for Image-Guided Laparoscopic Liver Ablation. Surg. Innov. 2016, 23, 397–406. [Google Scholar] [CrossRef] [PubMed]
- Spinczyk, D. Towards the clinical integration of an image-guided navigation system for percutaneous liver tumor ablation using freehand 2D ultrasound images. Comput. Aided Surg. 2015, 20, 61–72. [Google Scholar] [CrossRef] [PubMed]
- Rai, P.; Dakua, S.; Abinahed, J.; Balakrishnan, S. Feasibility and Efficacy of Fusion Imaging Systems for Immediate Post Ablation Assessment of Liver Neoplasms: Protocol for a Rapid Systematic Review. Int. J. Surg. Protoc. 2021, 25, 209–215. [Google Scholar] [CrossRef]
- Mohanty, S.; Dakua, S.P. Toward Computing Cross-Modality Symmetric Non-Rigid Medical Image Registration. IEEE Access 2022, 10, 24528–24539. [Google Scholar] [CrossRef]
- Mishra, D.; Chaudhury, S.; Sarkar, M.; Soin, A.S.; Mishra, D.; Chaudhury, S.; Sarkar, M.; Soin, A.S. Ultrasound Image Segmentation: A Deeply Supervised Network with Attention to Boundaries. IEEE Trans. Biomed. Eng. 2018, 66, 1637–1648. [Google Scholar] [CrossRef]
- Gao, Q.; Almekkawy, M. ASU-Net++: A nested U-Net with adaptive feature extractions for liver tumor segmentation. Comput. Biol. Med. 2021, 136, 104688. [Google Scholar] [CrossRef] [PubMed]
- Vaze, S.; Xie, W.; Namburete, A.I.L. Low-Memory CNNs Enabling Real-Time Ultrasound Segmentation Towards Mobile Deployment. IEEE J. Biomed. Heal. Inform. 2020, 24, 1059–1069. [Google Scholar] [CrossRef]
- Ferrari, V.; Hebert, M.; Sminchisescu, C.; Weiss, Y. (Eds.) ICNet for Real-Time Semantic Segmentation on High-Resolution Images. In Proceedings of the 15th European Conference, Munich, Germany, 8–14 September 2018; Volume 11207. [Google Scholar] [CrossRef]
- Nosrati, M.S.; Hamarneh, G. Incorporating prior knowledge in medical image segmentation: A survey. arXiv 2016, arXiv:1607.01092. [Google Scholar]
- BenTaieb, A.; Hamarneh, G. Topology Aware Fully Convolutional Networks for Histology Gland Segmentation. In Lecture Notes in Computer Science; Springer International Publishing: Cham, Switzerland, 2016; Volume 9901. [Google Scholar] [CrossRef]
- Ravishankar, H.; Venkataramani, R.; Thiruvenkadam, S.; Sudhakar, P.; Vaidya, V. Learning and incorporating shape models for semantic segmentation. In Lecture Notes in Computer Science; Springer International Publishing: Cham, Switzerland, 2017; Volume 10433. [Google Scholar] [CrossRef]
- Oktay, O.; Schlemper, J.; Folgoc, L.L.; Lee, M.; Heinrich, M.; Misawa, K.; Mori, K.; McDonagh, S.; Hammerla, N.Y.; Kainz, B.; et al. Attention U-Net: Learning where to look for the pancreas. arXiv 2018, arXiv:1804.03999. [Google Scholar]
- Oktay, O.; Ferrante, E.; Kamnitsas, K.; Heinrich, M.; Bai, W.; Caballero, J.; Cook, S.A.; De Marvao, A.; Dawes, T.; O’Regan, D.P.; et al. Anatomically constrained neural networks (ACNNs): Application to cardiac image enhancement and segmentation. IEEE Trans. Med. Imaging 2017, 37, 384–395. [Google Scholar] [CrossRef]
- Vakanski, A.; Xian, M.; Freer, P.E. Attention-enriched deep learning model for breast tumor segmentation in ultrasound images. Ultrasound Med. Biol. 2020, 46, 2819–2833. [Google Scholar] [CrossRef] [PubMed]
- Jetley, S.; Lord, N.A.; Lee, N.; Torr, P.H. Learn to pay attention. In Proceedings of the 6th International Conference on Learning Representations, ICLR, Vancouver, BC, Canada, 30 April–3 May 2018. [Google Scholar]
- Xian, M.; Zhang, Y.; Cheng, H.D.; Xu, F.; Ding, J. Neutro-connectedness cut. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016. [Google Scholar]
- Zhang, Y.; Xian, M.; Cheng, H.-D.; Shareef, B.; Ding, J.; Xu, F.; Huang, K.; Zhang, B.; Ning, C.; Wang, Y. BUSIS: A benchmark for breast ultrasound image segmentation. Healthcare 2022, 10, 729. [Google Scholar] [CrossRef] [PubMed]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional networks for biomedical image segmentation. In Proceedings of the 18th International Conference, Munich, Germany, 5–9 October 2015. [Google Scholar]
- Abdollahi, A.; Pradhan, B.; Alamri, A. VNet: An End-to-end fully convolutional neural network for Road extraction from high-resolution remote sensing data. IEEE Access 2020, 8, 179424–179436. [Google Scholar] [CrossRef]
PID | Sex | BMI | Age, y | Pathology Report | Type of Liver Resections |
---|---|---|---|---|---|
1 | F | 24.6 | 66 | Secondary malignant neoplasm of liver | Right Hepatectomy |
2 | M | 25.8 | 47 | Secondary malignant neoplasm of liver | MPS: SV, VI, VIII, anatomic Ivb |
3 | M | 22.3 | 84 | Secondary malignant neoplasm of liver | MPS: SVIII × 3 |
4 | M | 20.5 | 58 | Secondary malignant neoplasm of liver | Extended left hepatectomy + Partial SV, VII, VIII |
5 | M | 25.1 | 59 | Intrahepatic cholangiocarcinoma | MPS: SIVa, IVb, SII |
6 | M | 30.5 | 52 | Secondary malignant neoplasm of liver | MPS: SII × 3 |
7 | F | 21.4 | 44 | Secondary malignant neoplasm of liver | MPS: SVI & VII |
8 | F | 27.9 | 60 | Cholangiocarcinoma of the biliary tract, | Trisegmentectomy |
9 | F | 21.2 | 46 | Secondary malignant neoplasm of liver | MPS: SIII, Ivb |
10 | M | 22.4 | 39 | -- | MPS: SV, VI |
11 | F | 19.0 | 69 | Secondary malignant neoplasm of liver. | MPS: SIII, VII, VIII |
12 | M | 19.2 | 65 | Secondary malignant neoplasm of liver | Partial hepatectomy SVI/VII |
13 | F | 36.5 | 50 | Secondary malignant neoplasm of liver | MPS: SI, II, III/IV × 2, VIII × 2, III, VI, V/VIII |
14 | F | 20.9 | 75 | Primary low-grade serous adenocarcinoma | MPS: SIII, IV |
15 | F | 24.2 | 82 | Secondary malignant neoplasm of liver | MPS: SV, II × 2 + posterior hepatectomy |
16 | M | 27.8 | 69 | Intrahepatic cholangiocarcinoma | Partial hepatectomy SII |
17 | M | 32.6 | 48 | Secondary malignant neoplasm of liver | Partial hepatectomy SII/III |
18 | F | 21.6 | 56 | Cholangiocarcinoma of the biliary tract | Left Lobectomy |
19 | M | 27.4 | 47 | Secondary malignant neoplasm of liver | Right Hepatectomy |
20 | F | 26.9 | 53 | Intrahepatic cholangiocarcinoma | MPS: SV, VI, VIII, anatomic Ivb |
21 | F | 25.9 | 69 | Secondary malignant neoplasm of liver | MPS: SVIII × 3 |
22 | M | 18.2 | 40 | Secondary malignant neoplasm of liver | Extended left hepatectomy + Partial SV, VII, VIII |
Liver Vessel | Number of Patients with Specific Vessel Types | Count of Video Clips for Specific Vessels |
---|---|---|
IVC | 22 | 204 |
RHV | 19 | 66 |
LHV | 16 | 58 |
MHV | 17 | 82 |
MPV | 10 | 45 |
PRPV | 8 | 22 |
RPV | 11 | 41 |
LPV | 15 | 74 |
ARPV | 7 | 28 |
Vessels | Dice Score | IOU Score | Recall | Precision | Accuracy | AUC–ROC |
---|---|---|---|---|---|---|
IVC | 0.94 | 0.90 | 0.99 | 0.90 | 0.98 | 0.96 |
RHV | 0.85 | 0.77 | 0.98 | 0.78 | 0.99 | 0.82 |
LHV | 0.86 | 0.77 | 0.96 | 0.99 | 0.96 | 0.86 |
MHV | 0.83 | 0.90 | 0.80 | 0.890 | 0.98 | 0.91 |
MPV | 0.91 | 0.92 | 0.99 | 0.92 | 0.99 | 0.93 |
PRPV | 0.92 | 0.94 | 0.98 | 0.97 | 0.99 | 0.90 |
RPV | 0.85 | 0.76 | 0.98 | 0.79 | 0.99 | 0.91 |
LPV | 0.93 | 0.88 | 1.00 | 0.88 | 0.99 | 0.91 |
ARPV | 0.86 | 0.77 | 0.99 | 0.77 | 0.98 | 0.87 |
Vessels | Dice Score | IOU Score | Recall | Precision | Accuracy | AUC–ROC |
---|---|---|---|---|---|---|
IVC | 0.92 ± 0.03 | 0.87 ± 0.02 | 0.94 ± 0.02 | 0.93 ± 0.01 | 0.97 ± 0.02 | 0.96 ± 0.02 |
RHV | 0.90 ± 0.08 | 0.90 ± 0.09 | 0.91 ± 0.05 | 0.83 ± 0.08 | 0.99 ± 0.00 | 0.91 ± 0.03 |
LHV | 0.86 ± 0.02 | 0.80 ± 0.03 | 0.90 ± 0.02 | 0.82 ± 0.04 | 0.99 ± 0.00 | 0.76 ± 0.03 |
MHV | 0.89 ± 0.06 | 0.82 ± 0.08 | 0.93 ± 0.001 | 0.94 ± 0.03s | 0.99 ± 00 | 0.88 ± 0.05 |
MPV | 0.95 ± 0.05 | 0.91 ± 0.02 | 0.99 ± 0.001 | 0.92 ± 0.02 | 0.99 ± 0.001 | 0.92 ± 0.02 |
PRPV | 0.96 ± 0.05 | 0.93 ± 0.036 | 0.97 ± 0.05 | 0.89 ± 0.05 | 0.99 ± 0.01 | 0.88 ± 0.02 |
RPV | 0.84 ± 0.02 | 0.74 ± 0.04 | 1.00 ± 0.03 | 0.74 ± 0.02 | 0.99 ± 0.01 | 0.82 ± 0.05 |
LPV | 0.93 ± 0.00 | 0.89 ± 0.001 | 0.99 ± 0.01 | 0.89 ± 0.03 | 0.99 ± 0.001 | 0.89 ± 0.03 |
ARPV | 0.85 ± 0.03 | 0.78 ± 0.04 | 0.99 ± 0.00 | 0.78 ± 0.02 | 0.99 ± 0.00 | 0.84 ± 0.02 |
DL-Model | Vessels | Training Accuracy |
---|---|---|
U-Net * | IVC | 0.53 |
LHV | 0.51 | |
LPV | 0.55 | |
MPV | 0.50 | |
MHV | 0.52 | |
RPV | 0.53 | |
RHV | 0.54 | |
ARPV | 0.55 | |
PRPV | 0.51 | |
V-Net * | IVC | 0.52 |
LHV | 0.51 | |
LPV | 0.52 | |
MPV | 0.53 | |
MHV | 0.54 | |
RPV | 0.48 | |
RHV | 0.50 | |
ARPV | 0.51 | |
PRPV | 0.52 | |
VGG16-UNet * | IVC | 0.42 |
LHV | 0.49 | |
LPV | 0.46 | |
MPV | 0.42 | |
MHV | 0.40 | |
RPV | 0.42 | |
RHV | 0.43 | |
ARPV | 0.44 | |
PRPV | 0.46 | |
W-Net * | IVC | 0.53 |
LHV | 0.52 | |
LPV | 0.53 | |
MPV | 0.54 | |
MHV | 0.53 | |
RPV | 0.49 | |
RHV | 0.45 | |
ARPV | 0.41 | |
PRPV | 0.43 | |
Our proposed model | IVC | 0.96 |
LHV | 0.99 | |
LPV | 0.92 | |
MPV | 0.92 | |
MHV | 0.88 | |
RPV | 0.98 | |
RHV | 0.86 | |
ARPV | 0.87 | |
PRPV | 0.81 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Awais, M.; Al Taie, M.; O’Connor, C.S.; Castelo, A.H.; Acidi, B.; Tran Cao, H.S.; Brock, K.K. Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames. Cancers 2024, 16, 3674. https://doi.org/10.3390/cancers16213674
Awais M, Al Taie M, O’Connor CS, Castelo AH, Acidi B, Tran Cao HS, Brock KK. Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames. Cancers. 2024; 16(21):3674. https://doi.org/10.3390/cancers16213674
Chicago/Turabian StyleAwais, Muhammad, Mais Al Taie, Caleb S. O’Connor, Austin H. Castelo, Belkacem Acidi, Hop S. Tran Cao, and Kristy K. Brock. 2024. "Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames" Cancers 16, no. 21: 3674. https://doi.org/10.3390/cancers16213674
APA StyleAwais, M., Al Taie, M., O’Connor, C. S., Castelo, A. H., Acidi, B., Tran Cao, H. S., & Brock, K. K. (2024). Enhancing Surgical Guidance: Deep Learning-Based Liver Vessel Segmentation in Real-Time Ultrasound Video Frames. Cancers, 16(21), 3674. https://doi.org/10.3390/cancers16213674