Computerized liver volumetry on MRI by using 3D geodesic active contour segmentation

Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics

OBJECTIVES

To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI).

MATERIALS AND METHODS

This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC).

RESULTS

In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets.

CONCLUSION

Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction.

CLINICAL RELEVANCE STATEMENT

Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI.

KEY POINTS

• This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.

Prediction of post-hepatectomy liver failure by preoperative gadoxetate disodium-enhanced magnetic resonance imaging

BACKGROUND

Approximately 15% of patients experience post-hepatectomy liver failure after major hepatectomy. Poor hepatocyte uptake of gadoxetate disodium, a magnetic resonance imaging contrast agent, may be a predictor of post-hepatectomy liver failure.

METHODS

A retrospective cohort study of patients undergoing major hepatectomy (≥3 segments) with a preoperative gadoxetate disodium-enhanced magnetic resonance imaging was conducted. The liver signal intensity (standardized to the spleen) and the functional liver remnant was calculated to determine if this can predict post-hepatectomy liver failure after major hepatectomy.

RESULTS

In 134 patients, low signal intensity of the remnant liver standardized by signal intensity of the spleen in post-contrast images was associated with post-hepatectomy liver failure in multiple logistic regression analysis (Odds Ratio 0.112; 95% CI 0.023-0.551). In a subgroup of 33 patients with lower quartile of functional liver remnant, area under the curve analysis demonstrated a diagnostic accuracy of functional liver remnant to predict post-hepatectomy liver failure of 0.857 with a cut-off value for functional liver remnant of 1.4985 with 80.0% sensitivity and 89.3% specificity.

CONCLUSION

Functional liver remnant determined by gadoxetate disodium-enhanced magnetic resonance imaging is a predictor of post-hepatectomy liver failure which may help identify patients for resection, reducing morbidity and mortality.

Recent advances in computerized imaging and its vital roles in liver disease diagnosis, preoperative planning, and interventional liver surgery: A review

The earliest and most accurate detection of the pathological manifestations of hepatic diseases ensures effective treatments and thus positive prognostic outcomes. In clinical settings, screening and determining the extent of a pathology are prominent factors in preparing remedial agents and administering appropriate therapeutic procedures. Moreover, in a patient undergoing liver resection, a realistic preoperative simulation of the subject-specific anatomy and physiology also plays a vital part in conducting initial assessments, making surgical decisions during the procedure, and anticipating postoperative results. Conventionally, various medical imaging modalities, e.g., computed tomography, magnetic resonance imaging, and positron emission tomography, have been employed to assist in these tasks. In fact, several standardized procedures, such as lesion detection and liver segmentation, are also incorporated into prominent commercial software packages. Thus far, most integrated software as a medical device typically involves tedious interactions from the physician, such as manual delineation and empirical adjustments, as per a given patient. With the rapid progress in digital health approaches, especially medical image analysis, a wide range of computer algorithms have been proposed to facilitate those procedures. They include pattern recognition of a liver, its periphery, and lesion, as well as pre- and postoperative simulations. Prior to clinical adoption, however, software must conform to regulatory requirements set by the governing agency, for instance, valid clinical association and analytical and clinical validation. Therefore, this paper provides a detailed account and discussion of the state-of-the-art methods for liver image analyses, visualization, and simulation in the literature. Emphasis is placed upon their concepts, algorithmic classifications, merits, limitations, clinical considerations, and future research trends.

Expert-level segmentation using deep learning for volumetry of polycystic kidney and liver

Purpose

Volumetry is used in polycystic kidney and liver diseases (PKLDs), including autosomal dominant polycystic kidney disease (ADPKD), to assess disease progression and drug efficiency. However, since no rapid and accurate method for volumetry has been developed, volumetry has not yet been established in clinical practice, hindering the development of therapies for PKLD. This study presents an artificial intelligence (AI)-based volumetry method for PKLD.

Materials and Methods

The performance of AI was first evaluated in comparison with ground-truth (GT). We trained a V-net-based convolutional neural network on 175 ADPKD computed tomography (CT) segmentations, which served as the GT and were agreed upon by 3 experts using images from 214 patients analyzed with volumetry. The dice similarity coefficient (DSC), interobserver correlation coefficient (ICC), and Bland–Altman plots of 39 GT and AI segmentations in the validation set were compared. Next, the performance of AI on the segmentation of 50 random CT images was compared with that of 11 PKLD specialists based on the resulting DSC and ICC.

Results

The DSC and ICC of the AI were 0.961 and 0.999729, respectively. The error rate was within 3% for approximately 95% of the CT scans (error<1%, 46.2%; 1%≤error<3%, 48.7%). Compared with the specialists, AI showed moderate performance. Furthermore, an outlier in our results confirmed that even PKLD specialists can make mistakes in volumetry.

Conclusions

PKLD volumetry using AI was fast and accurate. AI performed comparably to human specialists, suggesting its use may be practical in clinical settings.

Assessment of liver metastases radiomic feature reproducibility with deep-learning-based semi-automatic segmentation software

BACKGROUND

Good feature reproducibility enhances model reliability. The manual segmentation of gastric cancer with liver metastasis (GCLM) can be time-consuming and unstable.

PURPOSE

To assess the value of a semi-automatic segmentation tool in improving the reproducibility of the radiomic features of GCLM.

MATERIAL AND METHODS

Patients who underwent dual-source computed tomography were retrospectively reviewed. As an intra-observer analysis, one radiologist segmented metastatic liver lesions manually and semi-automatically twice. Another radiologist re-segmented the lesions once as an inter-observer analysis. A total of 1691 features were extracted. Spearman rank correlation was used for feature reproducibility analysis. The times for manual and semi-automatic segmentation were recorded and analyzed.

RESULTS

Seventy-two patients with 168 lesions were included. Most of the GCLM radiomic features became more reliable with the tool than the manual method. For the intra-observer feature reproducibility analysis of manual and semi-automatic segmentation, the rates of features with good reliability were 45.5% and 62.3% (P < 0.02), respectively; for the inter-observer analysis, the rates were 29.3% and 46.0% (P < 0.05), respectively. For feature types, the semi-automatic method increased reliability in 6/7 types in the intra-observer analysis and 5/7 types in the inter-observer analysis. For image types, the reliability of the square and exponential types was significantly increased. The mean time of semi-automatic segmentation was significantly shorter than that of the manual method (P < 0.05).

CONCLUSION

The application of semi-automated software increased feature reliability in the intra- and inter-observer analyses. The semi-automatic process took less time than the manual process.

Deep Learning Algorithm for Automated Segmentation and Volume Measurement of the Liver and Spleen Using Portal Venous Phase Computed Tomography Images

Objective

Measurement of the liver and spleen volumes has clinical implications. Although computed tomography (CT) volumetry is considered to be the most reliable noninvasive method for liver and spleen volume measurement, it has limited application in clinical practice due to its time-consuming segmentation process. We aimed to develop and validate a deep learning algorithm (DLA) for fully automated liver and spleen segmentation using portal venous phase CT images in various liver conditions.

Materials and Methods

A DLA for liver and spleen segmentation was trained using a development dataset of portal venous CT images from 813 patients. Performance of the DLA was evaluated in two separate test datasets: dataset-1 which included 150 CT examinations in patients with various liver conditions (i.e., healthy liver, fatty liver, chronic liver disease, cirrhosis, and post-hepatectomy) and dataset-2 which included 50 pairs of CT examinations performed at ours and other institutions. The performance of the DLA was evaluated using the dice similarity score (DSS) for segmentation and Bland-Altman 95% limits of agreement (LOA) for measurement of the volumetric indices, which was compared with that of ground truth manual segmentation.

Results

In test dataset-1, the DLA achieved a mean DSS of 0.973 and 0.974 for liver and spleen segmentation, respectively, with no significant difference in DSS across different liver conditions (p = 0.60 and 0.26 for the liver and spleen, respectively). For the measurement of volumetric indices, the Bland-Altman 95% LOA was −0.17 ± 3.07% for liver volume and −0.56 ± 3.78% for spleen volume. In test dataset-2, DLA performance using CT images obtained at outside institutions and our institution was comparable for liver (DSS, 0.982 vs. 0.983; p = 0.28) and spleen (DSS, 0.969 vs. 0.968; p = 0.41) segmentation.

Conclusion

The DLA enabled highly accurate segmentation and volume measurement of the liver and spleen using portal venous phase CT images of patients with various liver conditions.

Cross-sectional imaging in patients with primary sclerosing cholangitis: Single time-point liver or spleen volume is associated with survival

AIM

To evaluate the association between single time-point quantitative liver and spleen volumes in patients with PSC and transplant-free survival, independent of Mayo risk score.

MATERIALS AND METHODS

This HIPAA-compliant retrospective study included 165 PSC patients in a hospital. Total (T), and lobar (right [R], left [L], and caudate [C]) liver volumes and spleen volume (S) were measured. Adverse outcome was identified as being on liver transplantation list, transplantation or death (outcome 1), and transplantation or death (outcome 2). Cox-regression was performed to assess the predictive value of volumetric parameters to predict transplant-free survival with and without Mayo risk score. Stratified analysis by Mayo risk score categories was performed to assess the discriminative value of volumes in the model. Prediction models were developed dependent of Mayo score, based on patients demographics, lab values and volumetric measures for both defined outcomes. Kaplan-Meier curves were depicted for different liver and spleen volumes. P value <0.05 was considered statistically significant.

RESULTS

In this cohort (age 43 ± 17 years; 59 % men) 51 % of patients had adverse outcome. Cox-regression analysis demonstrated statistically significant association between values of T, L, R, C, S, L/T, and C/T and outcome 1; and also statistically significant association between values C, S, and C/T and outcome 2. Prediction models included age, INR, total bilirubin, AST, variceal bleeding, S, and C for outcome 1 and age, INR, total bilirubin, AST, variceal bleeding, and S for outcome 2.

CONCLUSIONS

Based on our observational study, quantitative liver and spleen volumes may be associated with transplant-free survival in patients with PSC and may have the potential for predicting the outcome but this should be validated by randomized clinical trial studies.

A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI

PURPOSE

 To create a fully automated, reliable, and fast segmentation tool for Gd-EOB-DTPA-enhanced MRI scans using deep learning.

MATERIALS AND METHODS

 Datasets of Gd-EOB-DTPA-enhanced liver MR images of 100 patients were assembled. Ground truth segmentation of the hepatobiliary phase images was performed manually. Automatic image segmentation was achieved with a deep convolutional neural network.

RESULTS

 Our neural network achieves an intraclass correlation coefficient (ICC) of 0.987, a Sørensen-Dice coefficient of 96.7 ± 1.9 % (mean ± std), an overlap of 92 ± 3.5 %, and a Hausdorff distance of 24.9 ± 14.7 mm compared with two expert readers who corresponded to an ICC of 0.973, a Sørensen-Dice coefficient of 95.2 ± 2.8 %, and an overlap of 90.9 ± 4.9 %. A second human reader achieved a Sørensen-Dice coefficient of 95 % on a subset of the test set.

CONCLUSION

 Our study introduces a fully automated liver volumetry scheme for Gd-EOB-DTPA-enhanced MR imaging. The neural network achieves competitive concordance with the ground truth regarding ICC, Sørensen-Dice, and overlap compared with manual segmentation. The neural network performs the task in just 60 seconds.

KEY POINTS

  · The proposed neural network helps to segment the liver accurately, providing detailed information about patient-specific liver anatomy and volume.. · With the help of a deep learning-based neural network, fully automatic segmentation of the liver on MRI scans can be performed in seconds.. · A fully automatic segmentation scheme makes liver segmentation on MRI a valuable tool for treatment planning..

CITATION FORMAT

· Winther H, Hundt C, Ringe KI et al. A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI. Fortschr Röntgenstr 2021; 193: 305 - 314.

Validation of a fully automated liver segmentation algorithm using multi-scale deep reinforcement learning and comparison versus manual segmentation

PURPOSE

To evaluate the performance of an artificial intelligence (AI) based software solution tested on liver volumetric analyses and to compare the results to the manual contour segmentation.

MATERIALS AND METHODS

We retrospectively obtained 462 multiphasic CT datasets with six series for each patient: three different contrast phases and two slice thickness reconstructions (1.5/5 mm), totaling 2772 series. AI-based liver volumes were determined using multi-scale deep-reinforcement learning for 3D body markers detection and 3D structure segmentation. The algorithm was trained for liver volumetry on approximately 5000 datasets. We computed the absolute error of each automatically- and manually-derived volume relative to the mean manual volume. The mean processing time/dataset and method was recorded. Variations of liver volumes were compared using univariate generalized linear model analyses. A subgroup of 60 datasets was manually segmented by three radiologists, with a further subgroup of 20 segmented three times by each, to compare the automatically-derived results with the ground-truth.

RESULTS

The mean absolute error of the automatically-derived measurement was 44.3 mL (representing 2.37 % of the averaged liver volumes). The liver volume was neither dependent on the contrast phase (p = 0.697), nor on the slice thickness (p = 0.446). The mean processing time/dataset with the algorithm was 9.94 s (sec) compared to manual segmentation with 219.34 s. We found an excellent agreement between both approaches with an ICC value of 0.996.

CONCLUSION

The results of our study demonstrate that AI-powered fully automated liver volumetric analyses can be done with excellent accuracy, reproducibility, robustness, speed and agreement with the manual segmentation.

A workflow for automated segmentation of the liver surface, hepatic vasculature and biliary tree anatomy from multiphase MR images

Accurate assessment of 3D models of patient-specific anatomy of the liver, including underlying hepatic and biliary tree, is critical for preparation and safe execution of complex liver resections, especially due to high variability of biliary and hepatic artery anatomies. Dynamic MRI with hepatospecific contrast agents is currently the only type of diagnostic imaging that provides all anatomical information required for generation of such a model, yet there is no information in the literature on how the complete 3D model can be generated automatically. In this work, a new automated segmentation workflow for extraction of patient-specific 3D model of the liver, hepatovascular and biliary anatomy from a single multiphase MRI acquisition is developed and quantitatively evaluated. The workflow incorporates course 4D k-means clustering estimation and geodesic active contour refinement of the liver boundary, based on organ's characteristic uptake of gadolinium contrast agents overtime. Subsequently, hepatic vasculature and biliary ducts segmentations are performed using multiscale vesselness filters. The algorithm was evaluated using 15 test datasets of patients with liver malignancies of various histopathological types. It showed good correlation with expert manual segmentation, resulting in an average of 1.76 ± 2.44 mm Hausdorff distance for the liver boundary, and 0.58 ± 0.72 and 1.16 ± 1.98 mm between centrelines of biliary ducts and liver veins, respectively. A workflow for automatic segmentation of the liver, hepatic vasculature and biliary anatomy from a single diagnostic MRI acquisition was developed. This enables automated extraction of 3D models of patient-specific liver anatomy, and may facilitating better perception of organ's anatomy during preparation and execution of liver surgeries. Additionally, it may help to reduce the incidence of intraoperative biliary duct damage due to an unanticipated variation in the anatomy.

Comparison of semi-automatic and deep learning-based automatic methods for liver segmentation in living liver transplant donors

PURPOSE

To compare the accuracy and repeatability of emerging machine learning based (i.e. deep) automatic segmentation algorithms with those of well-established semi-automatic (interactive) methods for determining liver volume in living liver transplant donors at computerized tomography (CT) imaging.

METHODS

A total of 12 (6 semi-, 6 full-automatic) methods are evaluated. The semi-automatic segmentation algorithms are based on both traditional iterative models including watershed, fast marching, region growing, active contours and modern techniques including robust statistical segmenter and super-pixels. These methods entail some sort of interaction mechanism such as placing initialization seeds on images or determining a parameter range. The automatic methods are based on deep learning and they include three framework templates (DeepMedic, NiftyNet and U-Net) the first two of which are applied with default parameter sets and the last two involve adapted novel model designs. For 20 living donors (6 training and 12 test datasets), a group of imaging scientists and radiologists created ground truths by performing manual segmentations on contrast material-enhanced CT images. Each segmentation is evaluated using five metrics (i.e. volume overlap and relative volume errors, average/RMS/maximum symmetrical surface distances). The results are mapped to a scoring system and a final grade is calculated by taking their average. Accuracy and repeatability were evaluated using slice by slice comparisons and volumetric analysis. Diversity and complementarity are observed through heatmaps. Majority voting and Simultaneous Truth and Performance Level Estimation (STAPLE) algorithms are utilized to obtain the fusion of the individual results.

RESULTS

The top four methods are determined to be automatic deep models having 79.63, 79.46 and 77.15 and 74.50 scores. Intra-user score is determined as 95.14. Overall, deep automatic segmentation outperformed interactive techniques on all metrics. The mean volume of liver of ground truth is found to be 1409.93 mL ± 271.28 mL, while it is calculated as 1342.21 mL ± 231.24 mL using automatic and 1201.26 mL ± 258.13 mL using interactive methods, showing higher accuracy and less variation on behalf of automatic methods. The qualitative analysis of segmentation results showed significant diversity and complementarity enabling the idea of using ensembles to obtain superior results. The fusion of automatic methods reached 83.87 with majority voting and 86.20 using STAPLE that are only slightly less than fusion of all methods that achieved 86.70 (majority voting) and 88.74 (STAPLE).

CONCLUSION

Use of the new deep learning based automatic segmentation algorithms substantially increases the accuracy and repeatability for segmentation and volumetric measurements of liver. Fusion of automatic methods based on ensemble approaches exhibits best results almost without any additional time cost due to potential parallel execution of multiple models.

Estimation of split renal function using different volumetric methods: inter- and intraindividual comparison between MRI and CT

PURPOSE

This study aims to determine whether contrast-enhanced (CE)-magnetic resonance imaging (MRI) is comparable to CE-computed tomography (CT) for estimation of split renal function (SRF). For this purpose, two different kidney volumetry methods, the renal cortex volumetry (RCV) and modified ellipsoid volume (MELV), are compared for both acquisition types (CT vs. MRI) with regard to accuracy and reliability, subsequently referred to as RCV_CT/RCV_MRI and MELV_CT/MELV_MRI.

METHODS

This retrospective study included 29 patients (18 men and 11 women; mean age 62.8 ± 12.4 years) who underwent CE-MRI and CE-CT of the abdomen within a period of 3 months. Two independent readers (R1/R2) performed RCV and MELV in all datasets with corresponding semiautomated software tools. RCV was performed with datasets in the arterial phase and MELV in the venous phase. Statistics were calculated using one-way ANOVA, two-tailed Student's t test, Pearson´s correlation, and Bland-Altman plots with p ≤ 0.05 being considered statistically significant.

RESULTS

In all datasets, SRF was almost identical for both volumetry methods with a mean difference of < 1%. Bland-Altman analysis comparing RCV in CT and MRI showed very good agreement for R1/R2. Interreader agreement was strong for RCV_CT and good for RCV_MRI (r = 0.89; r = 0.69). MELV_CT/MRI interreader agreement was only moderate (r = 0.54; r = 0.50) with a high range of values. Intrareader agreement was excellent for all measurements, except MELV_MRI which showed a high mean bias and range of values (RCV_CT: r = 0.93, RCV_MRI: r = 0.98, MELV_CT: r = 0.89, MELV_MRI: r = 0.54).

CONCLUSION

Renal volumetric estimates of SRF are almost as accurate and reliable with CE-MRI as with CE-CT using RCV method. In distinction, the calculation of SRF using MELV was inferior to RCV with respect to accuracy and reliability. Thus, RCV method is recommended to estimate SRF, primarily using CT datasets. However, RCV with MRI datasets for kidney volumetry allows for comparable accuracy and reliability while sparing patients and healthy donors of unnecessary radiation exposure.

Correlation between quantitative liver and spleen volumes and disease severity in primary sclerosing cholangitis as determined by Mayo risk score

OBJECTIVES

To correlate total and lobar liver and spleen volume with disease severity in primary sclerosing cholangitis (PSC) as determined by Mayo risk score.

METHODS

This HIPAA-compliant single center retrospective study included 147 PSC patients with available imaging studies (MRCP/CT) and laboratory data between January 2003 and January 2018. Total and lobar (right, left and caudate) liver volume and spleen volume were measured. ANOVA test was performed to assess the differences in volumes between low, intermediate and high-risk groups (Mayo risk score <0, >0 and <2, >2, respectively). Correlations between volumes and Mayo risk score were calculated. ROC analysis was performed to assess the accuracy of the variable with the strongest correlation to PSC severity to predict Mayo risk score. P value <0.05 was considered statistically significant.

RESULTS

The mean age of this cohort was 45 ± 17 years; 58% were men. Absolute volumes of left lobe, caudate and spleen and volume ratios of left lobe and caudate to total liver volume of the high-risk group were significantly higher compared to those of low and intermediate risk groups (p < 0.05). Left lobe to total liver volume ratio had the highest correlation to Mayo risk score (Pearson correlation coefficient 0.61, p < 0.05) and on ROC analysis it had 84.4% accuracy in detecting high-risk PSC.

CONCLUSIONS

In this single institution large cohort study, the left lobe to total liver volume ratio was the best quantifiable volumetric biomarker to correlate with severity of PSC as identified by Mayo risk score.

Prediction of Posthepatectomy Liver Failure: MRI With Hepatocyte-Specific Contrast Agent Versus Indocyanine Green Clearance Test

OBJECTIVE

The objective of our study was to identify whether quantitative measurements from gadoxetic acid-enhanced MRI are useful for predicting posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC) compared with and in combination with future remnant liver volume (FRLV) and an indocyanine green (ICG) clearance test.

MATERIALS AND METHODS

Preoperative gadoxetic acid-enhanced MR images were retrospectively evaluated in 73 patients who underwent anatomic liver resection for HCC between 2011 and 2013. For quantitative measurement of hepatocyte function, relative liver enhancement (RLE) and remnant hepatocyte uptake index (rHUI) were measured using hepatobiliary phase MR images. FRLV was determined using measurements from preoperative CT scans. Univariate and multivariate analyses of measurements from gadoxetic acid-enhanced MRI, ICG clearance tests, and FRLV for finding predictors of PHLF were performed. To compare the diagnostic performance of predictors, ROC analyses were also performed.

RESULTS

Eighteen (25%) of 73 patients met the criteria for PHLF. Univariate analysis revealed that all measurements related to MRI including RLE, rHUI, ICG clearance, and FRLV were significantly associated with PHLF. Multivariate analysis showed that RLE, FRLV, ICG-plasma disappearance rate (ICG-PDR), rHUI, and rHUI corrected for body weight (rHUI-BW) were independent predictors of PHLF (p = 0.011, p = 0.034, p = 0.003, p < 0.001, and p = 0.001, respectively). In ROC analyses, AUCs of rHUI and rHUI-BW were larger than those of other independent predictors; the differences were statistically significant (for rHUI-BW vs RLE, ICG-PDR, and FRLV, p = 0.016, 0.007, and 0.046, respectively; for rHUI vs RLE and ICG-PDR, p = 0.045 and 0.016, respectively).

CONCLUSION

Measurements from gadoxetic acid-enhanced MRI predicted PHLF better than the ICG clearance test in patients with HCC who underwent hepatectomy.

A variational approach to liver segmentation using statistics from multiple sources

Medical image segmentation plays an important role in digital medical research, and therapy planning and delivery. However, the presence of noise and low contrast renders automatic liver segmentation an extremely challenging task. In this study, we focus on a variational approach to liver segmentation in computed tomography scan volumes in a semiautomatic and slice-by-slice manner. In this method, one slice is selected and its connected component liver region is determined manually to initialize the subsequent automatic segmentation process. From this guiding slice, we execute the proposed method downward to the last one and upward to the first one, respectively. A segmentation energy function is proposed by combining the statistical shape prior, global Gaussian intensity analysis, and enforced local statistical feature under the level set framework. During segmentation, the shape of the liver shape is estimated by minimization of this function. The improved Chan-Vese model is used to refine the shape to capture the long and narrow regions of the liver. The proposed method was verified on two independent public databases, the 3D-IRCADb and the SLIVER07. Among all the tested methods, our method yielded the best volumetric overlap error (VOE) of [Formula: see text], the best root mean square symmetric surface distance (RMSD) of [Formula: see text] mm, the best maximum symmetric surface distance (MSD) of [Formula: see text] mm in 3D-IRCADb dataset, and the best average symmetric surface distance (ASD) of [Formula: see text] mm, the best RMSD of [Formula: see text] mm in SLIVER07 dataset, respectively. The results of the quantitative comparison show that the proposed liver segmentation method achieves competitive segmentation performance with state-of-the-art techniques.

Liver segmentation: indications, techniques and future directions

OBJECTIVES

Liver volumetry has emerged as an important tool in clinical practice. Liver volume is assessed primarily via organ segmentation of computed tomography (CT) and magnetic resonance imaging (MRI) images. The goal of this paper is to provide an accessible overview of liver segmentation targeted at radiologists and other healthcare professionals.

METHODS

Using images from CT and MRI, this paper reviews the indications for liver segmentation, technical approaches used in segmentation software and the developing roles of liver segmentation in clinical practice.

RESULTS

Liver segmentation for volumetric assessment is indicated prior to major hepatectomy, portal vein embolisation, associating liver partition and portal vein ligation for staged hepatectomy (ALPPS) and transplant. Segmentation software can be categorised according to amount of user input involved: manual, semi-automated and fully automated. Manual segmentation is considered the "gold standard" in clinical practice and research, but is tedious and time-consuming. Increasingly automated segmentation approaches are more robust, but may suffer from certain segmentation pitfalls. Emerging applications of segmentation include surgical planning and integration with MRI-based biomarkers.

CONCLUSIONS

Liver segmentation has multiple clinical applications and is expanding in scope. Clinicians can employ semi-automated or fully automated segmentation options to more efficiently integrate volumetry into clinical practice.

TEACHING POINTS

• Liver volume is assessed via organ segmentation on CT and MRI examinations. • Liver segmentation is used for volume assessment prior to major hepatic procedures. • Segmentation approaches may be categorised according to the amount of user input involved. • Emerging applications include surgical planning and integration with MRI-based biomarkers.

Comparison of MRI- and CT-based semiautomated liver segmentation: a validation study

PURPOSE

To compare the repeatability, agreement, and efficiency of MRI- and CT-based semiautomated liver segmentation for the assessment of total and subsegmental liver volume.

METHODS

This retrospective study was conducted in 31 subjects who underwent contemporaneous liver MRI and CT. Total and subsegmental liver volumes were segmented from contrast-enhanced 3D gradient-recalled echo MRI sequences and CT images. Semiautomated segmentation was based on variational interpolation and Laplacian mesh optimization. All segmentations were repeated after 2 weeks. Manual segmentation of CT images using an active contour tool was used as the reference standard. Repeatability and agreement of the methods were evaluated with intra-class correlation coefficients (ICC) and Bland-Altman analysis. Total interaction time was recorded.

RESULTS

Intra-reader ICC were ≥0.987 for MRI and ≥0.995 for CT. Intra-reader repeatability was 30 ± 217 ml (bias ± 1.96 SD) (95% limits of agreement: -187 to 247 ml) for MRI and -10 ± 143 ml (-153 to 133 ml) for CT. Inter-method ICC between semiautomated and manual volumetry were ≥0.995 for MRI and ≥0.986 for CT. Inter-method segmental ICC varied between 0.584 and 0.865 for MRI and between 0.596 and 0.890 for CT. Inter-method agreement was -14 ± 136 ml (-150 to 122 ml) for MRI and 50 ± 226 ml (-176 to 276 ml) for CT. Inter-method segmental agreement ranged from 10 ± 47 ml (-37 to 57 ml) to 2 ± 214 ml (-212 to 216 ml) for MRI and 9 ± 45 ml (-36 to 54 ml) to -46 ± 183 ml (-229 to 137 ml) for CT. Interaction time (mean ± SD) was significantly shorter for MRI-based semiautomated segmentation (7.2 ± 0.1 min, p < 0.001) and for CT-based semiautomated segmentation (6.5 ± 0.2 min, p < 0.001) than for CT-based manual segmentation (14.5 ± 0.4 min).

CONCLUSION

MRI-based semiautomated segmentation provides similar repeatability and agreement to CT-based segmentation for total liver volume.

Liver Segmentation on CT and MR Using Laplacian Mesh Optimization

OBJECTIVE

The purpose of this paper is to describe a semiautomated segmentation method for the liver and evaluate its performance on CT-scan and MR images.

METHODS

First, an approximate 3-D model of the liver is initialized from a few user-generated contours to globally outline the liver shape. The model is then automatically deformed by a Laplacian mesh optimization scheme until it precisely delineates the patient's liver. A correction tool was implemented to allow the user to improve the segmentation until satisfaction.

RESULTS

The proposed method was tested against 30 CT-scans from the SLIVER07 challenge repository and 20 MR studies from the Montreal University Hospital Center, covering a wide spectrum of liver morphologies and pathologies. The average volumetric overlap error was 5.1% for CT and 7.6% for MRI and the average segmentation time was 6 min.

CONCLUSION

The obtained results show that the proposed method is efficient, reliable, and could effectively be used routinely in the clinical setting.

SIGNIFICANCE

The proposed approach can alleviate the cumbersome and tedious process of slice-wise segmentation required for precise hepatic volumetry, virtual surgery, and treatment planning.

Fully automated MR liver volumetry using watershed segmentation coupled with active contouring

PURPOSE

Our purpose is to develop a fully automated scheme for liver volume measurement in abdominal MR images, without requiring any user input or interaction.

METHODS

The proposed scheme is fully automatic for liver volumetry from 3D abdominal MR images, and it consists of three main stages: preprocessing, rough liver shape generation, and liver extraction. The preprocessing stage reduced noise and enhanced the liver boundaries in 3D abdominal MR images. The rough liver shape was revealed fully automatically by using the watershed segmentation, thresholding transform, morphological operations, and statistical properties of the liver. An active contour model was applied to refine the rough liver shape to precisely obtain the liver boundaries. The liver volumes calculated by the proposed scheme were compared to the "gold standard" references which were estimated by an expert abdominal radiologist.

RESULTS

The liver volumes computed by using our developed scheme excellently agreed (Intra-class correlation coefficient was 0.94) with the "gold standard" manual volumes by the radiologist in the evaluation with 27 cases from multiple medical centers. The running time was 8.4 min per case on average.

CONCLUSIONS

We developed a fully automated liver volumetry scheme in MR, which does not require any interaction by users. It was evaluated with cases from multiple medical centers. The liver volumetry performance of our developed system was comparable to that of the gold standard manual volumetry, and it saved radiologists' time for manual liver volumetry of 24.7 min per case.

Comparison of liver volumetry on contrast-enhanced CT images: one semiautomatic and two automatic approaches

This study was to evaluate the accuracy, consistency, and efficiency of three liver volumetry methods- one interactive method, an in-house-developed 3D medical Image Analysis (3DMIA) system, one automatic active shape model (ASM)-based segmentation, and one automatic probabilistic atlas (PA)-guided segmentation method on clinical contrast-enhanced CT images. Forty-two datasets, including 27 normal liver and 15 space-occupying liver lesion patients, were retrospectively included in this study. The three methods - one semiautomatic 3DMIA, one automatic ASM-based, and one automatic PA-based liver volumetry - achieved an accuracy with VD (volume difference) of -1.69%, -2.75%, and 3.06% in the normal group, respectively, and with VD of -3.20%, -3.35%, and 4.14% in the space-occupying lesion group, respectively. However, the three methods achieved an efficiency of 27.63 mins, 1.26 mins, 1.18 mins on average, respectively, compared with the manual volumetry, which took 43.98 mins. The high intraclass correlation coefficient between the three methods and the manual method indicated an excel-lent agreement on liver volumetry. Significant differences in segmentation time were observed between the three methods (3DMIA, ASM, and PA) and the manual volumetry (p < 0.001), as well as between the automatic volumetries (ASM and PA) and the semiautomatic volumetry (3DMIA) (p < 0.001). The semiautomatic interactive 3DMIA, automatic ASM-based, and automatic PA-based liver volum-etry agreed well with manual gold standard in both the normal liver group and the space-occupying lesion group. The ASM- and PA-based automatic segmentation have better efficiency in clinical use.

Cloud-Based Evaluation of Anatomical Structure Segmentation and Landmark Detection Algorithms: VISCERAL Anatomy Benchmarks

Variations in the shape and appearance of anatomical structures in medical images are often relevant radiological signs of disease. Automatic tools can help automate parts of this manual process. A cloud-based evaluation framework is presented in this paper including results of benchmarking current state-of-the-art medical imaging algorithms for anatomical structure segmentation and landmark detection: the VISCERAL Anatomy benchmarks. The algorithms are implemented in virtual machines in the cloud where participants can only access the training data and can be run privately by the benchmark administrators to objectively compare their performance in an unseen common test set. Overall, 120 computed tomography and magnetic resonance patient volumes were manually annotated to create a standard Gold Corpus containing a total of 1295 structures and 1760 landmarks. Ten participants contributed with automatic algorithms for the organ segmentation task, and three for the landmark localization task. Different algorithms obtained the best scores in the four available imaging modalities and for subsets of anatomical structures. The annotation framework, resulting data set, evaluation setup, results and performance analysis from the three VISCERAL Anatomy benchmarks are presented in this article. Both the VISCERAL data set and Silver Corpus generated with the fusion of the participant algorithms on a larger set of non-manually-annotated medical images are available to the research community.

Intra-individual comparison of CAIPIRINHA VIBE technique with conventional VIBE sequences in contrast-enhanced MRI of focal liver lesions

PURPOSE

To evaluate the impact of controlled aliasing in parallel imaging results in higher acceleration (CAIPIRINHA) volume interpolated breath-hold examination (VIBE) magnetic resonance imaging (MRI) technique on image quality, reader confidence, and inter-observer agreement for the assessment of focal liver lesions in comparison with the standard VIBE approach.

MATERIAL AND METHODS

In this IRB-approved intra-individual comparison study, abdominal arterial and portal-venous contrast-enhanced MRI studies were retrospectively analyzed in 38 patients with malignant liver lesions. Each patient underwent both CAIPIRINHA and conventional VIBE 3T MRI within 3 months, showing stable disease. Images were evaluated using 5-point rating scales by two blinded radiologists with more than 20 and 5 years of experience in MRI, respectively. Readers scored dignity of liver lesions and assessed which liver segments were affected by malignancy (ranging from 1=definitely benign/not affected to 5=definitely malignant/affected by malignancy). Readers also rated overall image quality, sharpness of intrahepatic veins, and diagnostic confidence (ranging from 1=poor to 5=excellent).

RESULTS

Reviewers achieved a higher inter-observer reliability using CAIPIRINHA when they reported which liver segments were affected by malignancy compared to traditional VIBE series (κ=0.62 and 0.54, respectively, p<0.05). Similarly, CAIPIRINHA showed a slightly higher inter-rater agreement for the dignity of focal liver lesions versus the standard VIBE images (κ=0.50 and 0.49, respectively, p<0.05). CAIPIRINHA series also scored higher in comparison to standard VIBE sequences (mean scores: image quality, 4.2 and 3.5; sharpness of intrahepatic vessels, 3.8 and 3.2, respectively, p<0.05) for both reviewers and allowed for higher subjective diagnostic confidence (ratings, 3.8 and 3.2, respectively, p<0.05).

CONCLUSION

Compared to the standard VIBE approach, CAIPIRINHA VIBE technique provides improved image quality and sharpness of intrahepatic veins, as well as higher diagnostic confidence. Additionally, this technique allows for higher inter-observer agreement when reporting focal liver lesions for both dignity and allocation.

Automated segmentation of liver and liver cysts from bounded abdominal MR images in patients with autosomal dominant polycystic kidney disease

Liver and liver cyst volume measurements are important quantitative imaging biomarkers for assessment of disease progression in autosomal dominant polycystic kidney disease (ADPKD) and polycystic liver disease (PLD). To date, no study has presented automated segmentation and volumetric computation of liver and liver cysts in these populations. In this paper, we proposed an automated segmentation framework for liver and liver cysts from bounded abdominal MR images in patients with ADPKD. To model the shape and variations in ADPKD livers, the spatial prior probability map (SPPM) of liver location and the tissue prior probability maps (TPPMs) of liver parenchymal tissue intensity and cyst morphology were generated. Formulated within a three-dimensional level set framework, the TPPMs successfully captured liver parenchymal tissues and cysts, while the SPPM globally constrained the initial surfaces of the liver into the desired boundary. Liver cysts were extracted by combined operations of the TPPMs, thresholding, and false positive reduction based on spatial prior knowledge of kidney cysts and distance map. With cross-validation for the liver segmentation, the agreement between the radiology expert and the proposed method was 84% for shape congruence and 91% for volume measurement assessed by the intra-class correlation coefficient (ICC). For the liver cyst segmentation, the agreement between the reference method and the proposed method was ICC  =  0.91 for cyst volumes and ICC  =  0.94 for % cyst-to-liver volume.

3D active surfaces for liver segmentation in multisequence MRI images

Biopsies for diagnosis can sometimes be replaced by non-invasive techniques such as CT and MRI. Surgeons require accurate and efficient methods that allow proper segmentation of the organs in order to ensure the most reliable intervention planning. Automated liver segmentation is a difficult and open problem where CT has been more widely explored than MRI. MRI liver segmentation represents a challenge due to the presence of characteristic artifacts, such as partial volumes, noise and low contrast. In this paper, we present a novel method for multichannel MRI automatic liver segmentation. The proposed method consists of the minimization of a 3D active surface by means of the dual approach to the variational formulation of the underlying problem. This active surface evolves over a probability map that is based on a new compact descriptor comprising spatial and multisequence information which is further modeled by means of a liver statistical model. This proposed 3D active surface approach naturally integrates volumetric regularization in the statistical model. The advantages of the compact visual descriptor together with the proposed approach result in a fast and accurate 3D segmentation method. The method was tested on 18 healthy liver studies and results were compared to a gold standard made by expert radiologists. Comparisons with other state-of-the-art approaches are provided by means of nine well established quality metrics. The obtained results improve these methodologies, achieving a Dice Similarity Coefficient of 98.59.

Quantitative radiology: automated measurement of polyp volume in computed tomography colonography using Hessian matrix-based shape extraction and volume growing

BACKGROUND

Current measurement of the single longest dimension of a polyp is subjective and has variations among radiologists. Our purpose was to develop a computerized measurement of polyp volume in computed tomography colonography (CTC).

METHODS

We developed a 3D automated scheme for measuring polyp volume at CTC. Our scheme consisted of segmentation of colon wall to confine polyp segmentation to the colon wall, extraction of a highly polyp-like seed region based on the Hessian matrix, a 3D volume growing technique under the minimum surface expansion criterion for segmentation of polyps, and sub-voxel refinement and surface smoothing for obtaining a smooth polyp surface. Our database consisted of 30 polyp views (15 polyps) in CTC scans from 13 patients. Each patient was scanned in the supine and prone positions. Polyp sizes measured in optical colonoscopy (OC) ranged from 6-18 mm with a mean of 10 mm. A radiologist outlined polyps in each slice and calculated volumes by summation of volumes in each slice. The measurement study was repeated 3 times at least 1 week apart for minimizing a memory effect bias. We used the mean volume of the three studies as "gold standard".

RESULTS

Our measurement scheme yielded a mean polyp volume of 0.38 cc (range, 0.15-1.24 cc), whereas a mean "gold standard" manual volume was 0.40 cc (range, 0.15-1.08 cc). The "gold-standard" manual and computer volumetric reached excellent agreement (intra-class correlation coefficient =0.80), with no statistically significant difference [P (F≤f) =0.42].

CONCLUSIONS

We developed an automated scheme for measuring polyp volume at CTC based on Hessian matrix-based shape extraction and volume growing. Polyp volumes obtained by our automated scheme agreed excellently with "gold standard" manual volumes. Our fully automated scheme can efficiently provide accurate polyp volumes for radiologists; thus, it would help radiologists improve the accuracy and efficiency of polyp volume measurements in CTC.

Quantitative imaging: quantification of liver shape on CT using the statistical shape model to evaluate hepatic fibrosis

RATIONALE AND OBJECTIVES

To investigate the usefulness of the statistical shape model (SSM) for the quantification of liver shape to evaluate hepatic fibrosis.

MATERIALS AND METHODS

Ninety-one subjects (45 men and 46 women; age range, 20-75 years) were included in this retrospective study: 54 potential liver donors and 37 patients with chronic liver disease. The subjects were classified histopathologically according to the fibrosis stage as follows: F0 (n = 55); F1 (n = 6); F2 (3); F3 (n = 1); and F4 (n = 26). Each subject underwent contrast-enhanced computed tomography (CT) using a 64-channel scanner (0.625-mm slice thickness). An abdominal radiologist manually traced the liver boundaries on every CT section using an image workstation; the boundaries were used for subsequent analyses. An SSM was constructed by the principal component analysis of the subject data set, which defined a parametric model of the liver shapes. The shape parameters were calculated by fitting SSM to the segmented liver shape of each subject and were used for the training of a linear support vector regression (SVR), which classifies the liver fibrosis stage to maximize the area under the receiver operating characteristic curve (AUC). SSM/SVR models were constructed and were validated in a leave-one-out manner. The performance of our technique was compared to those of two previously reported types of caudate-right lobe ratios (C/RL-m and C/RL-r).

RESULTS

In our SSM/SVR models, the AUC values for the classification of liver fibrosis were 0.96 (F0 vs. F1-4), 0.95 (F0-1 vs. F2-4), 0.96 (F0-2 vs. F3-4), and 0.95 (F0-3 vs. F4). These values were significantly superior to AUC values using the C/RL-m or C/RL-r ratios (P < .005).

CONCLUSIONS

SSM was useful for estimating the stage of hepatic fibrosis by quantifying liver shape.