Segmentation of liver tumors in multiphase computed tomography images using hybrid method
Introduction
According to data from the Global Cancer Statistics 2020, liver cancer ranks third among the causes of neoplasm-related deaths worldwide [1]. Medical-image-based technology provides a conventional and valid non-invasive procedure for liver cancer diagnosis. Computed tomography (CT) imaging is one of the most typically used modalities for this task. The detection of liver tumors from CT is essential step in the diagnosis. However, tumors appear similar to the surrounding tissues, which increases the difficulty of tumor detection. To enhance the appearance of different tissues in a CT image, a multiphase CT angiography technique is introduced to provide physicians with multi-degree information as well as tissue differences based on the temporal resolutions [2]. The imaging time of CT is sufficiently short, thereby allowing each of the phases to be captured at a high resolution within a few seconds. A series of phase signals, i.e., non-contrast-enhanced (NC), arterial (ART), portal venous (PV), and delay phase signals, are obtained successively after contrast injection [3]. These characteristic variations from multiphase CT images allow radiologists to distinguish liver tumors [4], [5], [6].
Although the appearance of tumors is enhanced in a multiphase CT image, when compared with CT images without contrast enhancement, the detection of liver tumor regions remains challenging because of the wide variety of tumors appearing in the images from different patients. In fact, the intensity, texture, shape, size, and other features of the tumors are similar to their surrounding tissues or other independent tumors.
Recently, deep learning techniques have been introduced to medical image analysis and have provided new solutions for the segmentation task of liver tumor regions in multiphase CT. Conze et al. used the random forest classifier and multiphase supervoxel-based features to segment hepatocellular carcinoma liver tumors [7]. The multiphase visual features extracted from registered multiphase CT images have been proven to improve the accuracy of the classification result. Sun et al. [8] considered distinctive pathological information from different phases. They proposed a multichannel fully convolutional network with separate fully convolutional network (FCN) channels for each phase individually. The features of liver tumors, which involve different phases, are extracted in the deeper layers to improve the accuracy of segmentation. The efficacy of information and the features pertaining to the liver tissue from different phases can be corroborated in the study by Ouhmich et al. [9], where a dimensional multiphase was implemented on NC, ART, and PV slices. Linked single-phase images were formed as a feature map of multiple dimensions. Meanwhile, multiphase fusion was applied. The outputs from the single phases were combined to obtain the final results. To mine complementary information across images of multiple phases, a modality-weighted U-Net [10] was proposed to combine features learned from different phases using dynamically weighted feature maps. Meanwhile, Xu et al. substantiated the efficiency of information extracted from multiple phases in a residual network [11]. They used a phase-attention residual network to exploit the ART phase and then extracted tumors from the PV phase. The phase attention modules were separated to obtain channel-wise and cross-phase interdependencies. In addition, to enhance sensitivity to the edges, a three-dimensional (3-D) boundary-enhanced loss was used in the training.
However, these methods present two disadvantages. First, because the tumors appear tuberous, multiple tumor regions are likely to aggregate and form a single region. When the gap between the tumor regions is extremely narrow, as shown in Fig. 1, the segmentation method may fail. Second, insufficient data quantity restricts the application of relatively deep learning methods in medical image processing, particularly in abdominal multiphase CT images. Herein, a hybrid method that incorporates a deep learning method is proposed to improve the accuracy of liver tumor segmentation. A cascade region-based convolutional neural network (R-CNN) with expanded head sections was introduced to detect tumor regions separately. Based on the regions, tumor boundaries were segmented using an improved level-set algorithm.
Section snippets
Related studies
In the early stage, conventional methods, including region growing, the watershed algorithm, and machine-learning-based methods, have been introduced to solve problems pertaining to liver tumor segmentation from CT images [13], [14], [15], [16], [17], [18]. However, the segmentation performance is affected by the custom-developed feature extractors. Recently, deep learning methods, which are characterized by convolutional neural networks, have been applied extensively and outperform
Fast marching
The originally proposed fast marching method was derived from the level-set method (LSM) [33]. It considers a curved surface model that is one dimension higher than the dimension of the target image, evolves the curved surface model over time, and eliminates the curved surface model at a point with increased dimensions to extract the target object region. Considering the case where a closed curve γ (t = 0) appears as the outline of an object on the image, the level-set function φ (x, y, t
Dataset and environment
Information regarding the testing images used in the experiment is shown in Table 2. Eleven cases of the ART phase, nine cases of the PV phase, and six cases of equilibrium phase were included in the training set. At least one tumor area was present in each case. The size of all images was 512 × 512 pixels. Window transformations were preprocessed on the CT images in the dataset. In the ART phase, we set the window width and windowing level to 350 and 40, respectively. In the PV and equilibrium
Discussion
Herein, we proposed a hybrid method to efficiently extract liver tumor regions from dynamic CT images. Specifically, an improved cascade R-CNN was used to obtain the initial ROIs of tumors in the first step, and a level-set framework involving phase-sensitive noise filtering was performed to obtain precise segmentation results of the liver tumor regions from the ROIs.
The results of tumor ROIs detected by the faster R-CNN, cascade R-CNN, and the proposed improved cascade R-CNN are shown in
Conclusion
Herein, we proposed a hybrid method for the efficient segmentation of the liver tumor region using dynamic computed tomography images. Specifically, an improved cascade region-based convolutional network was employed to automatically extract the region of interest of tumors, and the tumor regions were segmented using a level-set framework combined with bilateral filtering. The proposed method efficiently improved the segmentation accuracy of the surrounding liver tumors in multiphase computed
CRediT authorship contribution statement
Jiaqi Wu: Conceptualization, Methodology, Software, Writing – review & editing. Muki Furuzuki: Conceptualization, Methodology, Software, Writing – review & editing. Guangxu Li: Supervision, Writing – review & editing. Tohru Kamiya: Supervision, Writing – review & editing. Shingo Mabu: Supervision, Writing – review & editing. Masahiro Tanabe: Supervision, Writing – review & editing. Katsuyoshi Ito: Supervision, Writing – review & editing. Shoji Kido: Supervision, Writing – review & editing.
Declaration of Competing Interest
We know of no conflicts of interest associated with this publication. As corresponding author, I confirm that the manuscript has been read and approved for submission by all the named authors.
Acknowledgments
This work was supported by Grants-in-Aid for Scientific Research of JSPS KAKENHI Grant No. 21H03840.
References (38)
Automatic segmentation of liver tumors from multiphase contrast enhanced CT images based on FCNs
Artif Intell Med
(2017)Computer-aided diagnosis of liver tumors on computed tomography images”
Comput Methods Progr Biomed
(2017)CT liver tumor segmentation hybrid approach using neutrosophic sets, fast fuzzy C-means and adaptive watershed algorithm
Artif Intell Med
(2019)Liver tumor segmentation in CT volumes using an adversarial densely connected network
BMC Bioinform
(2019)Incremental learning for exudate and hemorrhage segmentation on fundus images
Inf Fusion
(2021)Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
CA Cancer J Clin
(2021)Multiphase CT angiography: a new tool for the imaging triage of patients with acute ischemic stroke
Radiology
(2015)Three-dimensional spatiotemporal features for fast content-based retrieval of focal liver lesions
IEEE Trans Biomed Eng
(2014)Hepatic imaging with multidetector CT
radiographics, Radiographics
(2001)Surgically staged focal liver lesions: accuracy and reproducibility of dual-phase helical CT for detection and characterization
Radiology
(2003)
Transient hepatic attenuation differences in focal hepatic lesions: dynamic CT features
Am J Roentgenol
Scale-adaptive supervoxel-based random forests for liver tumor segmentation in dynamic contrast-enhanced CT scans
Int J Comput Assist Radiol Surg
Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural network
Int J Comput Assist Radiol Surg
Hepatic lesion segmentation by combining plain and contrast enhanced CT images with modality weighted U-Net
PA-ResSeg: a phase attention residual network for liver tumor segmentation from multiphase CT images
Med Phys
U-Net: convolutional networks for biomedical image segmentation
Fully automatic liver tumor segmentation from abdominal CT scans
Automated detection and classification of liver cancer from CT images using Hog-SVM Model
Detection of liver cancer using modified fuzzy clustering and decision tree classifier in CT images”
Pattern Recognit Image Anal
Cited by (4)
MS-FANet: Multi-scale feature attention network for liver tumor segmentation
2023, Computers in Biology and MedicineDCE-Net: A Dynamic Context Encoder Network for Liver Tumor Segmentation
2023, Research SquareDenoising with Median and Bilateral on CT images for Liver segmentation
2022, Proceedings - 2022 RIVF International Conference on Computing and Communication Technologies, RIVF 2022
Accepted by Huimin Lu.