Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme

Lèbre, Marie-Ange; Vacavant, Antoine; Grand-Brochier, Manuel; Rositi, Hugo; Abergel, Armand; Chabrot, P.; Magnin, Benoît

doi:10.1016/j.compbiomed.2019.04.014

Cited by 53 publications

(35 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic methods for bone segmentation are very important in order to get 3D surfaces. It helps surgeons in making correct diagnoses, in performing accurate and quicker VSP and in the evaluation of postoperative follow-up without the influence of surgeon's experience [23][24][25][26][27]. The aim of this study was to evaluate method's accuracy for bone segmentation in CBCT data sets.…”

Section: Discussionmentioning

confidence: 99%

Automatic Method for Bone Segmentation in Cone Beam Computed Tomography Data Set

Vaitiekūnas

Jegelevičius

Sakalauskas³

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Due to technical aspects of Cone Beam Computed Tomography (CBCT), the automatic methods for bone segmentation are not widely used in the clinical practice of endodontics, orthodontics, oral and maxillofacial surgery. The aim of this study was to evaluate method’s accuracy for bone segmentation in CBCT data sets. The sliding three dimensional (3D) window, histogram filter and Otsu’s method were used to implement the automatic segmentation. The results of automatic segmentation were compared with the results of segmentation performed by an experienced oral and maxillofacial surgeon. Twenty patients and their forty CBCT data sets were used in this study (20 preoperative and 20 postoperative). Intraclass Correlation Coefficients (ICC) were calculated to prove the reliability of surgeon segmentations. ICC was 0.958 with 95% confidence interval [0.896 ... 0.983] in preoperative data sets and 0.931 with 95% confidence interval [0.836 ... 0.972] in postoperative data sets. Three basic metrics were used in order to evaluate the accuracy of the automatic method—Dice Similarity Coefficient (DSC), Root Mean Square (RMS), Average Distance Error (ADE) of surfaces mismatch and additional metric in order to evaluate computation time of segmentation was used. The mean value of preoperative DSC was 0.921, postoperative—0.911, the mean value of preoperative RMS was 0.559 mm, postoperative—0.647 mm, the ADE value of preoperative cases was 0.043 mm, postoperative—0.057 mm, the mean computational time to perform the segmentation was 46 s. The automatic method showed clinically acceptable accuracy results and thus can be used as a new tool for automatic bone segmentation in CBCT data. It can be applied in oral and maxillofacial surgery for performance of 3D Virtual Surgical Plan (VSP) or for postoperative follow-up.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Method for Bone Segmentation in Cone Beam Computed Tomography Data Set

Vaitiekūnas

Jegelevičius

Sakalauskas³

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The following features were evaluated and recorded: (1) the location of the tumor: segment I–IV vs. segment V–VIII, based on the Couinaud criteria ( 21 ); (2) the contour of the tumor: lobular (defined as a tumor with one or more indentation with an acute angle) or non-lobular (no indentations with an acute angle) ( 22 ); (3) the presence or absence of enhanced rim on AP or PVP appearing as a peritumoral, complete ring with higher intensity relative to adjacent liver parenchyma, as well as the solid component of the lesion ( 11 ); and (4) the maximum diameter of the tumor (in millimeters) in the axial PVP images.…”

Section: Methodsmentioning

confidence: 99%

Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis

et al. 2020

View full text Add to dashboard Cite

Developing an MRI-based radiomics model to effectively and accurately predict the predominant histopathologic growth patterns (HGPs) of colorectal liver metastases (CRLMs). Materials and Methods: In this study, 182 resected and histopathological proven CRLMs of chemotherapy-naive patients from two institutions, including 123 replacement CRLMs and 59 desmoplastic CRLMs, were retrospectively analyzed. Radiomics analysis was performed on two regions of interest (ROI), the tumor zone and the tumor-liver interface (TLI) zone. Decision tree (DT) algorithm was used for radiomics modeling on each MR sequence, and fused radiomics model was constructed by combining the radiomics signature of each sequence. The clinical and combination models were developed through multivariate logistic regression method. The performance of the developed models was assessed by receiver operating characteristic (ROC) curves with indicators of area under curve (AUC), accuracy, sensitivity, and specificity. A nomogram was constructed to evaluate the discrimination, calibration, and usefulness. Results: The fused radiomics tumor and radiomics TLI models showed better performance than any single sequence and clinical model. In addition, the radiomics TLI model exhibited better performance than radiomics tumor model (AUC of 0.912 vs. 0.879) in internal validation cohort. The combination model showed good discrimination, and the AUC of nomogram was 0.971, 0.909, and 0.905 in the training, internal validation, and external validation cohorts, respectively. Han et al. Radiomics in CRLM's HGP Prediction Conclusion: MRI-based radiomics method has high potential in predicting the predominant HGPs of CRLM. Preoperative non-invasive identification of predominant HGPs could further explore the ability of HGPs as a potential biomarker for clinical treatment strategy, reflecting different biological pathways.

show abstract

“…More consistent approach is to do so on salient features, e.g., those on main vascular networks. Provided skeletonized HVs and PV, but with their small branches removed, Lebre et al [25] computed four corresponding directional vectors. The first three vectors originated from HV root and pointed along respective hepatic veins, within close proximity to their root.…”

Section: B Surface-based Approachmentioning

confidence: 99%

“…Although Zhang et al [21] specifically followed Couinaud's theory, but their empirical assumptions on vasculature were not adequate to completely avoid post-process correction by an expert. With much less data involved, when only extracted liver surface and vascular outlines were considered, even greater user interaction was inevitable for methods in the second group [22][23][24][25][26][27]. Take Butdee's and Rusko's method [24,27] for examples.…”

Section: Summary Of Latest Algorithmsmentioning

confidence: 99%

Functional Segmentation for Preoperative Liver Resection Based on Hepatic Vascular Networks

Chansangrat

Keeratibharat

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Successful liver resection relies on accurate estimation of future liver remnant volume (FLRV). According to Couinaud's scheme, a liver is composed of eight functionally independent segments, each of which has its own vascular in-and out-flow tracks. Segmenting a liver by this scheme is vital to postoperative regeneration and hence prognosis outcome. Conventionally, estimation of liver segments was often done by hand on 3D computed tomography. The process is generally tedious, time consuming, and prone to observer variability. Alternatively, computerized methods had been proposed but impeded by anatomically irrelevant approximation and manually specified markers. To resolve the issues, this paper presents a novel method for functional liver segmentation. Its main contribution was performing analyses of differential geometry directly on a liver surface and interior venous system. Except for a few points being placed on major vessels, anatomical references required for defining all separating surfaces were automatically identified. To demonstrate its merits, virtual liver resection was implemented on the standard MICCAI SLIVER07 dataset, and the resultant segments were benchmarked against four most related works. Visual and numerical assessments reported herein indicated that our method could faithfully label all Couinaud's segments, especially the caudate, with lesser degree of user interaction. The preliminary findings suggested that it can be integrated into augmented surgical planning and intervention.

show abstract

Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaud scheme

Cited by 53 publications

References 26 publications

Automatic Method for Bone Segmentation in Cone Beam Computed Tomography Data Set

Automatic Method for Bone Segmentation in Cone Beam Computed Tomography Data Set

Identification of Predominant Histopathological Growth Patterns of Colorectal Liver Metastasis by Multi-Habitat and Multi-Sequence Based Radiomics Analysis

Functional Segmentation for Preoperative Liver Resection Based on Hepatic Vascular Networks

Contact Info

Product

Resources

About