1
|
Senthilvelan J, Jamshidi N. A pipeline for automated deep learning liver segmentation (PADLLS) from contrast enhanced CT exams. Sci Rep 2022; 12:15794. [PMID: 36138084 PMCID: PMC9500060 DOI: 10.1038/s41598-022-20108-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2021] [Accepted: 09/08/2022] [Indexed: 11/23/2022] Open
Abstract
Multiple studies have created state-of-the-art liver segmentation models using Deep Convolutional Neural Networks (DCNNs) such as the V-net and H-DenseUnet. Oversegmentation however continues to be a problem. We set forth to address these limitations by developing a an automated workflow that leverages the strengths of different DCNN architectures, resulting in a pipeline that enables fully automated liver segmentation. A Pipeline for Automated Deep Learning Liver Segmentation (PADLLS) was developed and implemented that cascades multiple DCNNs that were trained on more than 200 CT scans. First, a V-net is used to create a rough liver, spleen, and stomach mask. After stomach and spleen pixels are removed using their respective masks and ascites is removed using a morphological algorithm, the scan is passed to a H-DenseUnet to yield the final segmentation. The segmentation accuracy of the pipleline was compared to the H-DenseUnet and the V-net using the SLIVER07 and 3DIRCADb datasets as benchmarks. The PADLLS Dice score for the SLIVER07 dataset was calculated to be 0.957 ± 0.033 and was significantly better than the H-DenseUnet's score of 0.927 ± 0.044 (p = 0.0219) and the V-net's score of 0.872 ± 0.121 (p = 0.0067). The PADLLS Dice score for the 3DIRCADb dataset was 0.965 ± 0.016 and was significantly better than the H-DenseUnet's score of 0.930 ± 0.041 (p = 0.0014) the V-net's score of 0.874 ± 0.060 (p < 0.001). In conclusion, our pipeline (PADLLS) outperforms existing liver segmentation models, serves as a valuable tool for image-based analysis, and is freely available for download and use.
Collapse
Affiliation(s)
- Jayasuriya Senthilvelan
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, 757 Westwood Ave, Suite 2125, Los Angeles, CA, 90095, USA
| | - Neema Jamshidi
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, 757 Westwood Ave, Suite 2125, Los Angeles, CA, 90095, USA.
| |
Collapse
|
2
|
Ahmad M, Qadri SF, Ashraf MU, Subhi K, Khan S, Zareen SS, Qadri S. Efficient Liver Segmentation from Computed Tomography Images Using Deep Learning. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:2665283. [PMID: 35634046 PMCID: PMC9132625 DOI: 10.1155/2022/2665283] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/31/2021] [Accepted: 04/06/2022] [Indexed: 12/11/2022]
Abstract
Segmentation of a liver in computed tomography (CT) images is an important step toward quantitative biomarkers for a computer-aided decision support system and precise medical diagnosis. To overcome the difficulties that come across the liver segmentation that are affected by fuzzy boundaries, stacked autoencoder (SAE) is applied to learn the most discriminative features of the liver among other tissues in abdominal images. In this paper, we propose a patch-based deep learning method for the segmentation of a liver from CT images using SAE. Unlike the traditional machine learning methods, instead of anticipating pixel by pixel learning, our algorithm utilizes the patches to learn the representations and identify the liver area. We preprocessed the whole dataset to get the enhanced images and converted each image into many overlapping patches. These patches are given as input to SAE for unsupervised feature learning. Finally, the learned features with labels of the images are fine tuned, and the classification is performed to develop the probability map in a supervised way. Experimental results demonstrate that our proposed algorithm shows satisfactory results on test images. Our method achieved a 96.47% dice similarity coefficient (DSC), which is better than other methods in the same domain.
Collapse
Affiliation(s)
- Mubashir Ahmad
- College of Computer Science and Software Engineering, Computer Vision Institute, Shenzhen University, Shenzhen, Guangdong Province 518060, China
- Department of Computer Science and IT, The University of Lahore, Sargodha Campus, 40100, Lahore, Pakistan
| | - Syed Furqan Qadri
- College of Computer Science and Software Engineering, Computer Vision Institute, Shenzhen University, Shenzhen, Guangdong Province 518060, China
| | - M. Usman Ashraf
- Department of Computer Science, GC Women University, Sialkot 51310, Pakistan
| | - Khalid Subhi
- Department of Computer Science, King Abdulaziz University, Jeddah 21589, Saudi Arabia
| | - Salabat Khan
- College of Computer Science and Software Engineering, Computer Vision Institute, Shenzhen University, Shenzhen, Guangdong Province 518060, China
| | - Syeda Shamaila Zareen
- Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
| | - Salman Qadri
- Department of Computer Science, MNS University of Agriculture, Multan 60650, Pakistan
| |
Collapse
|
3
|
A Lightweight Convolutional Neural Network Model for Liver Segmentation in Medical Diagnosis. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:7954333. [PMID: 35755754 PMCID: PMC9225858 DOI: 10.1155/2022/7954333] [Citation(s) in RCA: 22] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Revised: 02/15/2022] [Accepted: 02/21/2022] [Indexed: 12/24/2022]
Abstract
Liver segmentation and recognition from computed tomography (CT) images is a warm topic in image processing which is helpful for doctors and practitioners. Currently, many deep learning methods are used for liver segmentation that takes a long time to train the model which makes this task challenging and limited to larger hardware resources. In this research, we proposed a very lightweight convolutional neural network (CNN) to extract the liver region from CT scan images. The suggested CNN algorithm consists of 3 convolutional and 2 fully connected layers, where softmax is used to discriminate the liver from background. Random Gaussian distribution is used for weight initialization which achieved a distance-preserving-embedding of the information. The proposed network is known as Ga-CNN (Gaussian-weight initialization of CNN). General experiments are performed on three benchmark datasets including MICCAI SLiver’07, 3Dircadb01, and LiTS17. Experimental results show that the proposed method performed well on each benchmark dataset.
Collapse
|
4
|
Solomon J, Aiosa N, Bradley D, Castro MA, Reza S, Bartos C, Sayre P, Lee JH, Sword J, Holbrook MR, Bennett RS, Hammoud DA, Johnson RF, Feuerstein I. Atlas-based liver segmentation for nonhuman primate research. Int J Comput Assist Radiol Surg 2020; 15:1631-1638. [PMID: 32648161 PMCID: PMC7502527 DOI: 10.1007/s11548-020-02225-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2020] [Accepted: 06/30/2020] [Indexed: 10/23/2022]
Abstract
PURPOSE Certain viral infectious diseases cause systemic damage and the liver is an important organ affected directly by the virus and/or the hosts' response to the virus. Medical imaging indicates that the liver damage is heterogenous, and therefore, quantification of these changes requires analysis of the entire organ. Delineating the liver in preclinical imaging studies is a time-consuming and difficult task that would benefit from automated liver segmentation. METHODS A nonhuman primate atlas-based liver segmentation method was developed to support quantitative image analysis of preclinical research. A set of 82 computed tomography (CT) scans of nonhuman primates with associated manual contours delineating the liver was generated from normal and abnormal livers. The proposed technique uses rigid and deformable registrations, a majority vote algorithm, and image post-processing operations to automate the liver segmentation process. This technique was evaluated using Dice similarity, Hausdorff distance measures, and Bland-Altman plots. RESULTS Automated segmentation results compare favorably with manual contouring, achieving a median Dice score of 0.91. Limits of agreement from Bland-Altman plots indicate that liver changes of 3 Hounsfield units (CT) and 0.4 SUVmean (positron emission tomography) are detectable using our automated method of segmentation, which are substantially less than changes observed in the host response to these viral infectious diseases. CONCLUSION The proposed atlas-based liver segmentation technique is generalizable to various sizes and species of nonhuman primates and facilitates preclinical infectious disease research studies. While the image analysis software used is commercially available and facilities with funding can access the software to perform similar nonhuman primate liver quantitative analyses, the approach can be implemented in open-source frameworks as there is nothing proprietary about these methods.
Collapse
Affiliation(s)
- Jeffrey Solomon
- Clinical Monitoring Research Program Directorate, Frederick National Laboratory for Cancer Research Sponsored by the National Cancer Institute, Frederick, MD, USA.
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA.
| | - Nina Aiosa
- Center for Infectious Disease Imaging, Clinical Center, Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Dara Bradley
- Center for Infectious Disease Imaging, Clinical Center, Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Marcelo A Castro
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Syed Reza
- Center for Infectious Disease Imaging, Clinical Center, Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Christopher Bartos
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Philip Sayre
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Ji Hyun Lee
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Jennifer Sword
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Michael R Holbrook
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Richard S Bennett
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Dima A Hammoud
- Center for Infectious Disease Imaging, Clinical Center, Radiology and Imaging Sciences, National Institutes of Health, Bethesda, MD, USA
| | - Reed F Johnson
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| | - Irwin Feuerstein
- Division of Clinical Research, Integrated Research Facility, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Frederick, MD, USA
| |
Collapse
|
5
|
Chen Y, Wang K, Liao X, Qian Y, Wang Q, Yuan Z, Heng PA. Channel-Unet: A Spatial Channel-Wise Convolutional Neural Network for Liver and Tumors Segmentation. Front Genet 2019; 10:1110. [PMID: 31827487 PMCID: PMC6892404 DOI: 10.3389/fgene.2019.01110] [Citation(s) in RCA: 44] [Impact Index Per Article: 8.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2019] [Accepted: 10/16/2019] [Indexed: 01/28/2023] Open
Abstract
It is a challenge to automatically and accurately segment the liver and tumors in computed tomography (CT) images, as the problem of over-segmentation or under-segmentation often appears when the Hounsfield unit (Hu) of liver and tumors is close to the Hu of other tissues or background. In this paper, we propose the spatial channel-wise convolution, a convolutional operation along the direction of the channel of feature maps, to extract mapping relationship of spatial information between pixels, which facilitates learning the mapping relationship between pixels in the feature maps and distinguishing the tumors from the liver tissue. In addition, we put forward an iterative extending learning strategy, which optimizes the mapping relationship of spatial information between pixels at different scales and enables spatial channel-wise convolution to map the spatial information between pixels in high-level feature maps. Finally, we propose an end-to-end convolutional neural network called Channel-UNet, which takes UNet as the main structure of the network and adds spatial channel-wise convolution in each up-sampling and down-sampling module. The network can converge the optimized mapping relationship of spatial information between pixels extracted by spatial channel-wise convolution and information extracted by feature maps and realizes multi-scale information fusion. The proposed ChannelUNet is validated by the segmentation task on the 3Dircadb dataset. The Dice values of liver and tumors segmentation were 0.984 and 0.940, which is slightly superior to current best performance. Besides, compared with the current best method, the number of parameters of our method reduces by 25.7%, and the training time of our method reduces by 33.3%. The experimental results demonstrate the efficiency and high accuracy of Channel-UNet in liver and tumors segmentation in CT images.
Collapse
Affiliation(s)
- Yilong Chen
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Kai Wang
- AI Research Center, Peng Cheng Laboratory, Shenzhen, China
| | - Xiangyun Liao
- Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Yinling Qian
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Shenzhen, China
- Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Shenzhen, China
| | - Qiong Wang
- CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Shenzhen, China
- Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Shenzhen, China
| | - Zhiyong Yuan
- School of Computer Science, Wuhan University, Wuhan, China
| | - Pheng-Ann Heng
- T Stone Robotics Institute and Department of Computer Science and Engineering, The Chinese University of Hong Kong, Shatin, Hong Kong
| |
Collapse
|
6
|
Nayak A, Baidya Kayal E, Arya M, Culli J, Krishan S, Agarwal S, Mehndiratta A. Computer-aided diagnosis of cirrhosis and hepatocellular carcinoma using multi-phase abdomen CT. Int J Comput Assist Radiol Surg 2019; 14:1341-1352. [PMID: 31062266 DOI: 10.1007/s11548-019-01991-5] [Citation(s) in RCA: 35] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2019] [Accepted: 04/25/2019] [Indexed: 12/15/2022]
Abstract
PURPOSE High mortality rate due to liver cirrhosis has been reported over the globe in the previous years. Early detection of cirrhosis may help in controlling the disease progression toward hepatocellular carcinoma (HCC). The lack of trained CT radiologists and increased patient population delays the diagnosis and further management. This study proposes a computer-aided diagnosis system for detecting cirrhosis and HCC in a very efficient and less time-consuming approach. METHODS Contrast-enhanced CT dataset of 40 patients (n = 40; M:F = 5:3; age = 25-55 years) with three groups of subjects: healthy (n = 14), cirrhosis (n = 12) and cirrhosis with HCC (n = 14), were retrospectively analyzed in this study. A novel method for the automatic 3D segmentation of liver using modified region-growing segmentation technique was developed and compared with the state-of-the-art deep learning-based technique. Further, histogram parameters were calculated from segmented CT liver volume for classification between healthy and diseased (cirrhosis and HCC) liver using logistic regression. Multi-phase analysis of CT images was performed to extract 24 temporal features for detecting cirrhosis and HCC liver using support vector machine (SVM). RESULTS The proposed method produced improved 3D segmentation with Dice coefficient 90% for healthy liver, 86% for cirrhosis and 81% for HCC subjects compared to the deep learning algorithm (healthy: 82%; cirrhosis: 78%; HCC: 70%). Standard deviation and kurtosis were found to be statistically different (p < 0.05) among healthy and diseased liver, and using logistic regression, classification accuracy obtained was 92.5%. For detecting cirrhosis and HCC liver, SVM with RBF kernel obtained highest slice-wise and patient-wise prediction accuracy of 86.9% (precision = 0.93, recall = 0.7) and 80% (precision = 0.86, recall = 0.75), respectively, than that of linear kernel (slice-wise: accuracy = 85.4%, precision = 0.92, recall = 0.67; patient-wise: accuracy = 73.33%, precision = 0.75, recall = 0.75). CONCLUSIONS The proposed computer-aided diagnosis system for detecting cirrhosis and hepatocellular carcinoma (HCC) showed promising results and can be used as effective screening tool in medical image analysis.
Collapse
Affiliation(s)
- Akash Nayak
- Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India.,IBM Research, Bangalore, India
| | - Esha Baidya Kayal
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India
| | - Manish Arya
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India
| | - Jayanth Culli
- Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India
| | - Sonal Krishan
- Department of Radiology, Medanta The Medicity, Gurgaon, India
| | - Sumeet Agarwal
- Department of Electrical Engineering, Indian Institute of Technology Delhi, New Delhi, India
| | - Amit Mehndiratta
- Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India. .,Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India.
| |
Collapse
|
7
|
Jafargholi Rangraz E, Coudyzer W, Maleux G, Baete K, Deroose CM, Nuyts J. Multi-modal image analysis for semi-automatic segmentation of the total liver and liver arterial perfusion territories for radioembolization. EJNMMI Res 2019; 9:19. [PMID: 30788640 PMCID: PMC6382918 DOI: 10.1186/s13550-019-0485-x] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2018] [Accepted: 01/29/2019] [Indexed: 12/15/2022] Open
Abstract
Purpose We have developed a multi-modal imaging approach for SIRT, combining 99mTc-MAA SPECT/CT and/or 90Y PET, 18F-FDG PET/CT, and contrast-enhanced CBCT for voxel-based dosimetry, as a tool for treatment planning and verification. For radiation dose prediction calculations, a segmentation of the total liver volume and of the liver perfusion territories is required. Method In this paper, we proposed a procedure for multi-modal image analysis to assist SIRT treatment planning. The pre-treatment 18F-FDG PET/CT, 99mTc-MAA SPECT/CT, and contrast-enhanced CBCT images were registered to a common space using an initial rigid, followed by a deformable registration. The registration was scored by an expert using Likert scores. The total liver was segmented semi-automatically based on the PET/CT and SPECT/CT images, and the liver perfusion territories were determined based on the CBCT images. The segmentations of the liver and liver lobes were compared to the manual segmentations by an expert on a CT image. Result Our methodology showed that multi-modal image analysis can be used for determination of the liver and perfusion territories using CBCT in SIRT using all pre-treatment studies. The results for image registration showed acceptable alignment with limited impact on dosimetry. The image registration performs well according to the expert reviewer (scored as perfect or with little misalignment in 94% of the cases). The semi-automatic liver segmentation agreed well with manual liver segmentation (dice coefficient of 0.92 and an average Hausdorff distance of 3.04 mm). The results showed disagreement between lobe segmentation using CBCT images compared to lobe segmentation based on CT images (average Hausdorff distance of 14.18 mm), with a high impact on the dosimetry (differences up to 9 Gy for right and 21 Gy for the left liver lobe). Conclusion This methodology can be used for pre-treatment dosimetry and for SIRT planning including the determination of the activity that should be administered to achieve the therapeutical goal. The inclusion of perfusion CBCT enables perfusion-based definition of the liver lobes, which was shown to be markedly different from the anatomical definition in some of the patients.
Collapse
Affiliation(s)
| | - Walter Coudyzer
- Radiology Section, Department of imaging and pathology, UZ Leuven, Leuven, Belgium
| | - Geert Maleux
- Radiology Section, Department of imaging and pathology, UZ & KU Leuven, Leuven, Belgium
| | - Kristof Baete
- Nuclear Medicine, Department of imaging and pathology, UZ & KU Leuven, Leuven, Belgium
| | - Christophe M Deroose
- Nuclear Medicine, Department of imaging and pathology, UZ & KU Leuven, Leuven, Belgium
| | - Johan Nuyts
- Nuclear Medicine, Department of imaging and pathology, UZ & KU Leuven, Leuven, Belgium
| |
Collapse
|
8
|
Bolt HM. Highlight report: The pseudolobule in liver fibrosis. EXCLI JOURNAL 2017; 16:1321-1322. [PMID: 29333134 PMCID: PMC5763089 DOI: 10.17179/excli2017-1038] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Download PDF] [Subscribe] [Scholar Register] [Received: 12/13/2017] [Accepted: 12/19/2017] [Indexed: 12/15/2022]
Affiliation(s)
- H M Bolt
- IfADo, Leibniz Research Centre for Working Environment and Human Factors, Dortmund
| |
Collapse
|