Liver segmentation: indications, techniques and future directions

Explainable and Robust Deep Learning for Liver Segmentation Through U-Net Network

Background/Objectives: Clinical imaging techniques, such as magnetic resonance imaging and computed tomography, play a vital role in supporting clinicians by aiding disease diagnosis and facilitating the planning of appropriate interventions. This is particularly important in malignant conditions like hepatocellular carcinoma, where accurate image segmentation, delineating the liver and tumor, is a critical initial step in optimizing diagnosis, staging, and treatment planning, including interventions like transplantation, surgical resection, radiotherapy, portal vein embolization, and other procedures. Therefore, effective segmentation methods can significantly influence both diagnostic accuracy and treatment outcomes. Method: In this paper, we propose a deep learning-based approach aimed at accurately segmenting the liver in medical images, thus addressing a critical need in hepatic disease diagnosis and treatment planning. We consider a U-Net architecture with residual connections to capture fine-grained anatomical details. We also take into account the prediction explainability, aiming to highlight, in the image under analysis, the areas that are symptomatic for a certain segmentation. In detail, by exploiting the U-Net architecture, two different models are trained with two annotated datasets of computed tomography medical images, resulting in four different experiments. Results: We consider two different datasets to improve robustness and generalization across diverse patient populations and imaging conditions. Experimental results demonstrate that the proposed method obtains interesting performances, with an accuracy ranging from 0.81 to 0.93. Conclusions: We thus show that the proposed method can provide a reliable and efficient solution for automated liver segmentation, promising significant advancements in clinical workflows and precision medicine.

Automated liver volumetry and hepatic steatosis quantification with magnetic resonance imaging proton density fat fraction

BACKGROUND

Preoperative imaging evaluation of liver volume and hepatic steatosis for the donor affects transplantation outcomes. However, computed tomography (CT) for liver volumetry and magnetic resonance spectroscopy (MRS) for hepatic steatosis are time consuming. Therefore, we investigated the correlation of automated 3D-multi-echo-Dixon sequence magnetic resonance imaging (ME-Dixon MRI) and its derived proton density fat fraction (MRI-PDFF) with CT liver volumetry and MRS hepatic steatosis measurements in living liver donors.

METHODS

This retrospective cross-sectional study was conducted from December 2017 to November 2022. We enrolled donors who received a dynamic CT scan and an MRI exam within 2 days. First, the CT volumetry was processed semiautomatically using commercial software, and ME-Dixon MRI volumetry was automatically measured using an embedded sequence. Next, the signal intensity of MRI-PDFF volumetric data was correlated with MRS as the gold standard.

RESULTS

We included the 165 living donors. The total liver volume of ME-Dixon MRI was significantly correlated with CT (r = 0.913, p < 0.001). The fat percentage measured using MRI-PDFF revealed a strong correlation between automatic segmental volume and MRS (r = 0.705, p < 0.001). Furthermore, the hepatic steatosis group (MRS ≥5%) had a strong correlation than the non-hepatic steatosis group (MRS <5%) in both volumetric (r = 0.906 vs. r = 0.887) and fat fraction analysis (r = 0.779 vs. r = 0.338).

CONCLUSION

Automated ME-Dixon MRI liver volumetry and MRI-PDFF were strongly correlated with CT liver volumetry and MRS hepatic steatosis measurements, especially in donors with hepatic steatosis.

Systematic Review: AI Applications in Liver Imaging with a Focus on Segmentation and Detection

The liver is a frequent focus in radiology due to its diverse pathology, and artificial intelligence (AI) could improve diagnosis and management. This systematic review aimed to assess and categorize research studies on AI applications in liver radiology from 2018 to 2024, classifying them according to areas of interest (AOIs), AI task and imaging modality used. We excluded reviews and non-liver and non-radiology studies. Using the PRISMA guidelines, we identified 6680 articles from the PubMed/Medline, Scopus and Web of Science databases; 1232 were found to be eligible. A further analysis of a subgroup of 329 studies focused on detection and/or segmentation tasks was performed. Liver lesions were the main AOI and CT was the most popular modality, while classification was the predominant AI task. Most detection and/or segmentation studies (48.02%) used only public datasets, and 27.65% used only one public dataset. Code sharing was practiced by 10.94% of these articles. This review highlights the predominance of classification tasks, especially applied to liver lesion imaging, most often using CT imaging. Detection and/or segmentation tasks relied mostly on public datasets, while external testing and code sharing were lacking. Future research should explore multi-task models and improve dataset availability to enhance AI's clinical impact in liver imaging.

Adaptive Evolutionary Optimization of Deep Learning Architectures for Focused Liver Ultrasound Image Segmentation

Background: Liver ultrasound segmentation is challenging due to low image quality and variability. While deep learning (DL) models have been widely applied for medical segmentation, generic pre-configured models may not meet the specific requirements for targeted areas in liver ultrasound. Quantitative ultrasound (QUS) is emerging as a promising tool for liver fat measurement; however, accurately segmenting regions of interest within liver ultrasound images remains a challenge. Methods: We introduce a generalizable framework using an adaptive evolutionary genetic algorithm to optimize deep learning models, specifically U-Net, for focused liver segmentation. The algorithm simultaneously adjusts the depth (number of layers) and width (neurons per layer) of the network, dropout, and skip connections. Various architecture configurations are evaluated based on segmentation performance to find the optimal model for liver ultrasound images. Results: The model with a depth of 4 and filter sizes of [16, 64, 128, 256] achieved the highest mean adjusted Dice score of 0.921, outperforming the other configurations, using three-fold cross-validation with early stoppage. Conclusions: Adaptive evolutionary optimization enhances the deep learning architecture for liver ultrasound segmentation. Future work may extend this optimization to other imaging modalities and deep learning architectures.

Magnetic Resonance Imaging Liver Segmentation Protocol Enables More Consistent and Robust Annotations, Paving the Way for Advanced Computer-Assisted Analysis

BACKGROUND/OBJECTIVES

Recent advancements in artificial intelligence (AI) have spurred interest in developing computer-assisted analysis for imaging examinations. However, the lack of high-quality datasets remains a significant bottleneck. Labeling instructions are critical for improving dataset quality but are often lacking. This study aimed to establish a liver MRI segmentation protocol and assess its impact on annotation quality and inter-reader agreement.

METHODS

This retrospective study included 20 patients with chronic liver disease. Manual liver segmentations were performed by a radiologist in training and a radiology technician on T2-weighted imaging (wi) and T1wi at the portal venous phase. Based on the inter-reader discrepancies identified after the first segmentation round, a segmentation protocol was established, guiding the second round of segmentation, resulting in a total of 160 segmentations. The Dice Similarity Coefficient (DSC) assessed inter-reader agreement pre- and post-protocol, with a Wilcoxon signed-rank test for per-volume analysis and an Aligned-Rank Transform (ART) for repeated measures analyses of variance (ANOVA) for per-slice analysis. Slice selection at extreme cranial or caudal liver positions was evaluated using the McNemar test.

RESULTS

The per-volume DSC significantly increased after protocol implementation for both T2wi (p < 0.001) and T1wi (p = 0.03). Per-slice DSC also improved significantly for both T2wi and T1wi (p < 0.001). The protocol reduced the number of liver segmentations with a non-annotated slice on T1wi (p = 0.04), but the change was not significant on T2wi (p = 0.16).

CONCLUSIONS

Establishing a liver MRI segmentation protocol improves annotation robustness and reproducibility, paving the way for advanced computer-assisted analysis. Moreover, segmentation protocols could be extended to other organs and lesions and incorporated into guidelines, thereby expanding the potential applications of AI in daily clinical practice.

3-D reconstruction in liver surgery: a systematic review

BACKGROUND

Three-dimensional reconstruction of the liver offers several advantages to the surgeon before and during liver resection. This review discusses the factors behind the use of liver 3-D reconstruction.

METHODS

Systematic electronic search, according to PRISMA criteria, was performed. A literature search of scientific papers was performed until October 2023. Articles were chosen based on reference to 3-D liver reconstruction and their use in liver surgery. GRADE methodology and the modified Newcastle-Ottawa scale were used to assess the quality of the studies.

RESULTS

The research included 47 articles and 7724 patients were analyzed. Preoperative planning was performed with 3-D liver reconstruction in the 87.2% of the studies. Most of preoperative 3-D liver reconstructions were performed in the planning of complex or major hepatectomies. Complex hepatectomies were performed in 64.3% patients. The 55.3% of the studies reported an improved navigation and accuracy during liver resection. Four studies (8.6%) on living donor liver transplant (LDLT) concluded that 3-D liver reconstruction is useful for graft selection and vascular preservation. Nine papers (19.1%) reported an accurate measurement of future liver remnant.

CONCLUSION

Liver 3-D reconstruction helps surgeons in the planning of liver surgery, especially in liver graft and complex liver resections, increasing the accuracy of the surgical resection.

Cross-Professional Evaluation of 3D Visualization of Liver Malignancies in the Decade of AI and Automatic Segmentation: A Benefit for Multidisciplinary Teams and Tumor Board Decisions?

Purpose To investigate whether automatic 3D visualization of computed tomography (CT) data sets with singular liver tumor compared to 2D images could foster a broader understanding of tumor localization and resectability in the liver within a multidisciplinary team and might therefore be a useful tool in multidisciplinary decision-making. Material and methods The study was configured as a web-based questionnaire. Physicians of all levels of medical training from surgery, radiology, and gastroenterology departments were recruited. A total of seven cases with singular liver tumor CT images with adequate quality were selected. Automatic 3D segmentation was performed using Universal Atlas (Release 5.0) as part of the Brainlab of Elements software suite (Brainlab AG, Munich, Germany). All cases were randomly presented in a 2D and 3D manner. After every case-presentation, multiple choice (single answer) questions concerning tumor extent and resectability were asked. The questions as well as the answers defined to be correct, were evaluated by two senior consultants from the radiology and surgery department. The primary outcome parameters were the correctness of answers stratified for medical specialty and for the level of medical training. The secondary outcome was the time needed for the evaluation of seven liver cases using 2D versus 3D images. Six additional questions were tailored to evaluate the subjective value of the 3D visualization.  Results A total of 92 participants participated in the study, 31.5% of them were abdominal surgeons, 34.8% gastroenterologists, and 33.7% radiologists. Based on the level of medical training, 66 were residents (71.7%) and 26 consultants (28.3%). Only radiologists answered more questions correctly using 2D imaging compared to the 3D method (p = 0.006). There was no statistically significant difference between correctly answered questions when using 2D vs. 3D visualization in the gastroenterologist and surgeon groups (p > 0.05). The resident subgroup showed no statistically significant difference when using the 2D vs. 3D images (p > 0.05), the consultant subgroup answered more questions correctly using 2D imaging (p = 0.009). Physicians with elementary experience of liver pathology also showed no difference in 2D vs. 3D (p = 0.332), physicians with proficient experience of liver pathology answered more questions correctly using 2D imaging (p = 0.010). The median time taken for the evaluation of the seven liver cases was only significantly faster for the gastroenterologist group (p = 0.006) using the 3D analysis (median: 9.1 minutes) than the 2D analysis (median: 10.7 minutes).  Over 80% of the participants found the 3D presentation to be a helpful additional tool for the clinical routine according to the subjective questionnaire. Conclusion In this study 3D visualization of liver tumors was evaluated as helpful within a multidisciplinary team of radiologists, surgeons, and gastroenterologists. However, significantly superior results in the understanding of liver anatomy could not be demonstrated by means of 3D visualization. It may be that more immersive technologies such as augmented reality or virtual reality will lead to a superior understanding compared to conventional presentation of information in 2D cross-sectional images.

A Review of Advancements and Challenges in Liver Segmentation

Liver segmentation technologies play vital roles in clinical diagnosis, disease monitoring, and surgical planning due to the complex anatomical structure and physiological functions of the liver. This paper provides a comprehensive review of the developments, challenges, and future directions in liver segmentation technology. We systematically analyzed high-quality research published between 2014 and 2024, focusing on liver segmentation methods, public datasets, and evaluation metrics. This review highlights the transition from manual to semi-automatic and fully automatic segmentation methods, describes the capabilities and limitations of available technologies, and provides future outlooks.

Translating contrast enhanced computed tomography images to liver radioembolization dose distribution for more comprehensively indicating patients

Objective.Contrast-enhanced computed tomography (CECT) is commonly used in the pre-treatment evaluation of liver Y-90 radioembolization feasibility. CECT provides detailed imaging of the liver and surrounding structures, allowing healthcare providers to assess the size, location, and characteristics of liver tumors prior to the treatment. Here we propose a method for translating CECT images to an expected dose distribution for tumor(s) and normal liver tissue.Approach.A pre-procedure CECT is used to obtain an iodine arterial-phase distribution by subtracting the non-contrast CT from the late arterial phase. The liver segments surrounding the targeted tumor are selected using Couinaud's method. The resolution of the resulting images is then degraded to match the resolution of the positron emission tomography (PET) images, which can image the Y-90 activity distribution post-treatment. The resulting images are then used in the same way as PET images to compute doses using the local deposition method. CECT images from three patients were used to test this method retrospectively and were compared with Y-90 PET-based dose distributions through dose volume histograms.Main results.Results show a concordance between predicted and delivered Y-90 dose distributions with less than 10% difference in terms of mean dose, for doses greater than 10% of the 98th percentile (D2%).Significance.CECT-derived predictions of Y-90 radioembolization dose distributions seem promising as a supplementary tool for physicians when assessing treatment feasibility. This dosimetry prediction method could provide a more comprehensive pre-treatment evaluation-offering greater insights than a basic assessment of tumor opacification on CT images.

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.

Parenchymal volume preservation during partial nephrectomy: improved methodology to assess impact and predictive factors

OBJECTIVE

To rigorously evaluate the impact of the percentage of parenchymal volume preserved (PPVP) and how well the preserved parenchyma recovers from ischaemia (Recischaemia) on functional outcomes after partial nephrectomy (PN) using an accurate and objective software-based methodology for estimating parenchymal volumes and split renal function (SRF). A secondary objective was to assess potential predictors of the PPVP.

PATIENTS AND METHODS

A total of 894 PN patients with available studies (2011-2014) were evaluated. The PPVP was measured from cross-sectional imaging at ≤3 months before and 3-12 months after PN using semi-automated software. Pearson correlation evaluated relationships between continuous variables. Multivariable linear regression evaluated predictors of ipsilateral glomerular filtration rate (GFR) preserved and the PPVP. Relative-importance analysis was used to evaluate the impact of the PPVP on ipsilateral GFR preserved. Recischaemia was defined as the percentage of ipsilateral GFR preserved normalised by the PPVP.

RESULTS

The median tumour size and R.E.N.A.L. nephrometry score were 3.4 cm and 7, respectively. In all, 49 patients (5.5%) had a solitary kidney. In all, 538 (60%)/251 (28%)/104 (12%) patients were managed with warm/cold/zero ischaemia, respectively. The median pre/post ipsilateral GFRs were 40/31 mL/min/1.73 m2, and the median (interquartile range [IQR]) percentage of ipsilateral GFR preserved was 80% (71-88%). The median pre/post ipsilateral parenchymal volumes were 181/149 mL, and the median (IQR) PPVP was 84% (76-92%). In all, 330 patients (37%) had a PPVP of <80%, while only 34 (4%) had a Recischaemia of <80%. The percentage of ipsilateral GFR preserved correlated strongly with the PPVP (r = 0.83, P < 0.01) and loss of parenchymal volume accounted for 80% of the loss of ipsilateral GFR. Multivariable analysis confirmed that the PPVP was the strongest predictor of ipsilateral GFR preserved. Greater tumour size and endophytic and nearness properties of the R.E.N.A.L. nephrometry score were associated with a reduced PPVP (all P ≤ 0.01). Solitary kidney and cold ischaemia were associated with an increased PPVP (all P < 0.05).

CONCLUSIONS

A reduced PPVP predominates regarding functional decline after PN, although a low Recischaemia can also contribute. Tumour-related factors strongly influence the PPVP, while surgical efforts can improve the PPVP as observed for patients with solitary kidneys.

Automated segmentation of liver and hepatic vessels on portal venous phase computed tomography images using a deep learning algorithm

BACKGROUND

CT-image segmentation for liver and hepatic vessels can facilitate liver surgical planning. However, time-consuming process and inter-observer variations of manual segmentation have limited wider application in clinical practice.

PURPOSE

Our study aimed to propose an automated deep learning (DL) segmentation algorithm for liver and hepatic vessels on portal venous phase CT images.

METHODS

This retrospective study was performed to develop a coarse-to-fine DL-based algorithm that was trained, validated, and tested using private 413, 52, and 50 portal venous phase CT images, respectively. Additionally, the performance of the DL algorithm was extensively evaluated and compared with manual segmentation using an independent clinical dataset of preoperative contrast-enhanced CT images from 44 patients with hepatic focal lesions. The accuracy of DL-based segmentation was quantitatively evaluated using the Dice Similarity Coefficient (DSC) and complementary metrics [Normalized Surface Dice (NSD) and Hausdorff distance_95 (HD95) for liver segmentation, Recall and Precision for hepatic vessel segmentation]. The processing time for DL and manual segmentation was also compared.

RESULTS

Our DL algorithm achieved accurate liver segmentation with DSC of 0.98, NSD of 0.92, and HD95 of 1.52 mm. DL-segmentation of hepatic veins, portal veins, and inferior vena cava attained DSC of 0.86, 0.89, and 0.94, respectively. Compared with the manual approach, the DL algorithm significantly outperformed with better segmentation results for both liver and hepatic vessels, with higher accuracy of liver and hepatic vessel segmentation (all p < 0.001) in independent 44 clinical data. In addition, the DL method significantly reduced the manual processing time of clinical postprocessing (p < 0.001).

CONCLUSIONS

The proposed DL algorithm potentially enabled accurate and rapid segmentation for liver and hepatic vessels using portal venous phase contrast CT images.

Fully automated assessment of the future liver remnant in a blood-free setting via CT before major hepatectomy via deep learning

OBJECTIVES

To develop and validate a deep learning (DL) model for automated segmentation of hepatic and portal veins, and apply the model in blood-free future liver remnant (FLR) assessments via CT before major hepatectomy.

METHODS

3-dimensional 3D U-Net models were developed for the automatic segmentation of hepatic veins and portal veins on contrast-enhanced CT images. A total of 170 patients treated from January 2018 to March 2019 were included. 3D U-Net models were trained and tested under various liver conditions. The Dice similarity coefficient (DSC) and volumetric similarity (VS) were used to evaluate the segmentation accuracy. The use of quantitative volumetry for evaluating resection was compared between blood-filled and blood-free settings and between manual and automated segmentation.

RESULTS

The DSC values in the test dataset for hepatic veins and portal veins were 0.66 ± 0.08 (95% CI: (0.65, 0.68)) and 0.67 ± 0.07 (95% CI: (0.66, 0.69)), the VS values were 0.80 ± 0.10 (95% CI: (0.79, 0.84)) and 0.74 ± 0.08 (95% CI: (0.73, 0.76)), respectively No significant differences in FLR, FLR% assessments, or the percentage of major hepatectomy patients were noted between the blood-filled and blood-free settings (p = 0.67, 0.59 and 0.99 for manual methods, p = 0.66, 0.99 and 0.99 for automated methods, respectively) according to the use of manual and automated segmentation methods.

CONCLUSION

Fully automated segmentation of hepatic veins and portal veins and FLR assessment via blood-free CT before major hepatectomy are accurate and applicable in clinical cases involving the use of DL.

CRITICAL RELEVANCE STATEMENT

Our fully automatic models could segment hepatic veins, portal veins, and future liver remnant in blood-free setting on CT images before major hepatectomy with reliable outcomes.

KEY POINTS

Fully automatic segmentation of hepatic veins and portal veins was feasible in clinical practice. Fully automatic volumetry of future liver remnant (FLR)% in a blood-free setting was robust. No significant differences in FLR% assessments were noted between the blood-filled and blood-free settings.

Hepatic grooves: An observational study at laparoscopic surgery

BACKGROUND

In traditional descriptions, the upper surface of the liver is smooth and convex, but deep depressions are variants that are present in 5%-40% of patients. We sought to determine the relationship between surface depressions and the diaphragm.

AIM

To use exploratory laparoscopy to determine the relationship between surface depressions and the diaphragm.

METHODS

An observational study was performed in all patients undergoing laparoscopic upper gastro-intestinal operations between January 1, 2023 and January 20, 2024. A thirty-degree laparoscope was used to inspect the liver and diaphragm. When surface depressions were present, we recorded patient demographics, presence of diaphragmatic bands, rib protrusions and/or any other source of compression during inspection.

RESULTS

Of 394 patients, 343 had normal surface anatomy, and 51 (12.9%) had prominent surface depressions on the liver. There was no significant relationship between the presence of surface depressions and gender nor the presence of rib projections. However, there was significant association between the presence of surface depressions and diaphragmatic muscular bands (P < 0.001).

CONCLUSION

With these data, the diaphragmatic-band theory has gained increased importance over other theories for surface depressions. Further studies are warranted using cross sectional imaging to confirm relationships with intersectional planes as well as beta-catenin assays in the affected liver parenchyma.

The impact of hepatic and splenic volumetric assessment in imaging for chronic liver disease: a narrative review

Chronic liver disease is responsible for significant morbidity and mortality worldwide. Abdominal computed tomography (CT) and magnetic resonance imaging (MRI) can fully visualise the liver and adjacent structures in the upper abdomen providing a reproducible assessment of the liver and biliary system and can detect features of portal hypertension. Subjective interpretation of CT and MRI in the assessment of liver parenchyma for early and advanced stages of fibrosis (pre-cirrhosis), as well as severity of portal hypertension, is limited. Quantitative and reproducible measurements of hepatic and splenic volumes have been shown to correlate with fibrosis staging, clinical outcomes, and mortality. In this review, we will explore the role of volumetric measurements in relation to diagnosis, assessment of severity and prediction of outcomes in chronic liver disease patients. We conclude that volumetric analysis of the liver and spleen can provide important information in such patients, has the potential to stratify patients' stage of hepatic fibrosis and disease severity, and can provide critical prognostic information. CRITICAL RELEVANCE STATEMENT: This review highlights the role of volumetric measurements of the liver and spleen using CT and MRI in relation to diagnosis, assessment of severity, and prediction of outcomes in chronic liver disease patients. KEY POINTS: Volumetry of the liver and spleen using CT and MRI correlates with hepatic fibrosis stages and cirrhosis. Volumetric measurements correlate with chronic liver disease outcomes. Fully automated methods for volumetry are required for implementation into routine clinical practice.

Radiomics Analysis of Preprocedural CT Imaging for Outcome Prediction after Transjugular Intrahepatic Portosystemic Shunt Creation

PURPOSE

To evaluate the role of radiomics in preoperative outcome prediction in cirrhotic patients who underwent transjugular intrahepatic portosystemic shunt (TIPS) using "controlled expansion covered stents".

MATERIALS AND METHODS

This retrospective institutional review board-approved study included cirrhotic patients undergoing TIPS with controlled expansion covered stent placement. From preoperative CT images, the whole liver was segmented into Volumes of Interest (VOIs) at the unenhanced and portal venous phase. Radiomics features were extracted, collected, and analyzed. Subsequently, receiver operating characteristic (ROC) curves were drawn to assess which features could predict patients' outcomes. The endpoints studied were 6-month overall survival (OS), development of hepatic encephalopathy (HE), grade II or higher HE according to West Haven Criteria, and clinical response, defined as the absence of rebleeding or ascites. A radiomic model for outcome prediction was then designed.

RESULTS

A total of 76 consecutive cirrhotic patients undergoing TIPS creation were enrolled. The highest performances in terms of the area under the receiver operating characteristic curve (AUROC) were observed for the "clinical response" and "survival at 6 months" outcome with 0.755 and 0.767, at the unenhanced and portal venous phase, respectively. Specifically, on basal scans, accuracy, specificity, and sensitivity were 66.42%, 63.93%, and 73.75%, respectively. At the portal venous phase, an accuracy of 65.34%, a specificity of 62.38%, and a sensitivity of 74.00% were demonstrated.

CONCLUSIONS

A pre-interventional machine learning-based CT radiomics algorithm could be useful in predicting survival and clinical response after TIPS creation in cirrhotic patients.

Clinician overconfidence in visual estimation of the posthepatectomy liver remnant volume: A proximal source of liver failure after major hepatic resection?

BACKGROUND

Post-hepatectomy liver failure is a source of morbidity and mortality after major hepatectomy and is related to the volume of the future liver remnant. The accuracy of a clinician's ability to visually estimate the future liver remnant without formal computed tomography liver volumetry is unknown.

METHODS

Twenty physicians in diagnostic radiology, interventional radiology, and hepatopancreatobiliary surgery reviewed 20 computed tomography scans of patients without underlying liver pathology who were not scheduled for liver resection. We evaluated clinician accuracy to estimate the future liver remnant for 3 hypothetical major hepatic resections: left hepatectomy, right hepatectomy, and right trisectionectomy. The percent-difference between the mean and actual computed tomography liver volumetry (mean percent difference) was tested along with specialty differences using mixed-effects regression analysis.

RESULTS

The actual future liver remnant (computed tomography liver volumetry) remaining after a hypothetical left hepatectomy ranged from 59% to 75% (physician estimated range: 50%-85%), 23% to 40% right hepatectomy (15%-50%), and 13% to 29% right trisectionectomy (8%-39%). For right hepatectomy, the mean future liver remnant was overestimated by 95% of clinicians with a mean percent difference of 22% (6%-45%; P < .001). For right trisectionectomy, 90% overestimated the future liver remnant by a mean percent difference of 25% (6%-50%; P < .001). Hepatopancreatobiliary surgeons overestimated the future liver remnant for proposed right hepatectomy and right trisectionectomy by a mean percent difference of 25% and 34%, respectively. Based on years of experience, providers with <10 years of experience had a greater mean percent difference than providers with 10+ years of experience for hypothetical major hepatic resections, but was only significantly higher for left hepatectomy (9% vs 6%, P = .002).

CONCLUSION

A clinician's ability to visually estimate the future liver remnant volume is inaccurate when compared to computed tomography liver volumetry. Clinicians tend to overestimate the future liver remnant volume, especially in patients with a small future liver remnant where the risk of posthepatectomy liver failure is greatest.

Application of Laennec extrathecal blockade combined with indocyanine green fluorescence imaging in laparoscopic anatomic hepatectomy

OBJECTIVE

To investigate the safety and application value of combining Laennec extracapsular occlusion with ICG fluorescence imaging in laparoscopic anatomic hepatectomy.

METHODS

Complete laparoscopic dissection was performed outside the Laennec sheath, blocking Glisson's pedicle of the corresponding liver segment or lobe. An appropriate amount of indocyanine green (ICG) dye was intravenously injected, and the boundary line between the pre-cut liver segment and liver lobe was identified using fluorescence laparoscopy. Complete resection of the liver segment or lobe was performed based on anatomical markers. Clinical data, including operation time, intraoperative blood loss, postoperative hospital stay, and postoperative complications, were collected.

RESULTS

A total of 14 cases were included in the study, including seven cases of primary liver cancer, three cases of metastatic liver cancer, three cases of intrahepatic bile duct calculi, and one case of hepatic hemangioma. All 14 patients underwent anatomic hepatectomy under fluorescent laparoscopy, with four cases involving the right liver, seven cases involving the left liver, two cases involving the right anterior lobe, and one case involving the right posterior lobe.

CONCLUSION

Combining laparoscopic follow-up of the Laennec membrane with Glisson outer sheath block and intraoperative ICG fluorescence imaging provides real-time guidance for locating the resection boundaries during anatomic hepatectomy. This approach helps in controlling intraoperative bleeding, reducing operation time, and ensuring high safety. It holds significant value in clinical application.

Signal Intensity Trajectories Clustering for Liver Vasculature Segmentation and Labeling (LiVaS) on Contrast-Enhanced MR Images: A Feasibility Pilot Study

This study aims to develop a semiautomated pipeline and user interface (LiVaS) for rapid segmentation and labeling of MRI liver vasculature and evaluate its time efficiency and accuracy against manual reference standard. Retrospective feasibility pilot study. Liver MR images from different scanners from 36 patients were included, and 4/36 patients were randomly selected for manual segmentation as referenced standard. The liver was segmented in each contrast phase and masks registered to the pre-contrast segmentation. Voxel-wise signal trajectories were clustered using the k-means algorithm. Voxel clusters that best segment the liver vessels were selected and labeled by three independent radiologists and a research scientist using LiVaS. Segmentation times were compared using a paired-sample t-test on log-transformed data. The agreement was analyzed qualitatively and quantitatively using DSC for hepatic and portal vein segmentations. The mean segmentation time among four readers was significantly shorter than manual (3.6 ± 1.4 vs. 70.0 ± 29.2 min; p < 0.001), even when using a higher number of clusters to enhance accuracy. The DSC for portal and hepatic veins reached up to 0.69 and 0.70, respectively. LiVaS segmentations were overall of good quality, with variations in performance related to the presence/severity of liver disease, acquisition timing, and image quality. Our semi-automated pipeline was robust to different MRI vendors in producing segmentation and labeling of liver vasculature in agreement with expert manual annotations, with significantly higher time efficiency. LiVaS could facilitate the creation of large, annotated datasets for training and validation of neural networks for automated MRI liver vascularity segmentation. HIGHLIGHTS: Key Finding: In this pilot feasibility study, our semiautomated pipeline for segmentation of liver vascularity (LiVaS) on MR images produced segmentations with simultaneous labeling of portal and hepatic veins in good agreement with the manual reference standard but at significantly shorter times (mean LiVaS 3.6 ± 1.4 vs. mean manual 70.0 ± 29.2 min; p < 0.001). Importance: LiVaS was robust in producing liver MRI vascular segmentations across images from different scanners in agreement with expert manual annotations, with significant ly higher time efficiency, and therefore potential scalability.

Body Weight as a Preferred Method for Normalizing the Computed Tomography-Derived Liver Volume in Dogs without Hepatic Disease

The assessment of liver size is usually performed using radiography in dogs. However, due to wide variations in patients' sizes and body conformations, accurate diagnosis of hepatomegaly or microhepatia is difficult. Computed tomographic (CT) volumetry can quantitatively and accurately measure liver volume. However, a reliable method for the standardization or normalization of volume in dogs without hepatic disease using CT has not yet been established. The purpose of this study was to assess seven different anatomic measures for normalizing liver volume in dogs and determine the tentative range of liver volume in dogs without hepatic disease. We retrospectively searched medical records from 1 January 2017 through to 1 June 2020 and included dogs with abdominal computed tomography without hepatic disease. The liver volume, lengths of four vertebrae (T11, T12, L2, L3), diameter of the abdominal aorta, body weight, and body condition scores (BCSs) of the dogs were recorded. Forty-one client-owned dogs without evidence of hepatic disease were included. The CT-derived liver volume was 813.8 ± 326.5 cm3 (mean ± SD). Body weight was determined to be the most reliable single-variable method for normalizing liver volume, with a raw CT-derived liver-volume-to-body-weight ratio of 22.1 cm3/kg (95% CI: 12.9-31.3 cm3/kg) and regression prediction model of volume = 19 × BWkg + 97. However, a better normalizing factor would likely be provided by the fat-free mass if it can be accurately measured.

Liver fibrosis classification from ultrasound using machine learning: a systematic literature review

PURPOSE

Liver biopsy was considered the gold standard for diagnosing liver fibrosis; however, with advancements in medical technology and increasing awareness of potential complications, the reliance on liver biopsy has diminished. Ultrasound is gaining popularity due to its wider availability and cost-effectiveness. This study examined the machine learning / deep learning (ML/DL) models for non-invasive liver fibrosis classification from ultrasound.

METHODS

Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol, we searched five academic databases using the query. We defined population, intervention, comparison, outcomes, and study design (PICOS) framework for the inclusion. Furthermore, Joana Briggs Institute (JBI) checklist for analytical cross-sectional studies is used for quality assessment.

RESULTS

Among the 188 screened studies, 17 studies are selected. The methods are categorized as off-the-shelf (OTS), attention, generative, and ensemble classifiers. Most studies used OTS classifiers that combined pre-trained ML/DL methods with radiomics features to determine fibrosis staging. Although machine learning shows potential for fibrosis classification, there are limited external comparisons of interventions and prospective clinical trials, which limits their applicability.

CONCLUSION

With the recent success of ML/DL toward biomedical image analysis, automated solutions using ultrasound are developed for predicting liver diseases. However, their applicability is bounded by the limited and imbalanced retrospective studies having high heterogeneity. This challenge could be addressed by generating a standard protocol for study design by selecting appropriate population, interventions, outcomes, and comparison.

Progress and clinical translation in hepatocellular carcinoma of deep learning in hepatic vascular segmentation

This paper reviews the advancements in deep learning for hepatic vascular segmentation and its clinical implications in the holistic management of hepatocellular carcinoma (HCC). The key to the diagnosis and treatment of HCC lies in imaging examinations, with the challenge in liver surgery being the precise assessment of Hepatic vasculature. In this regard, deep learning methods, including convolutional neural networksamong various other approaches, have significantly improved accuracy and speed. The review synthesizes findings from 30 studies, covering aspects such as network architectures, applications, supervision techniques, evaluation metrics, and motivations. Furthermore, we also examine the challenges and future prospects of deep learning technologies in enhancing the comprehensive diagnosis and treatment of HCC, discussing anticipated breakthroughs that could transform patient management. By combining clinical needs with technological advancements, deep learning is expected to make greater breakthroughs in the field of hepatic vascular segmentation, thereby providing stronger support for the diagnosis and treatment of HCC.

Volumetric graft changes after liver transplantation: evidence of adaptation to recipient body size

It is believed that whole liver grafts adjust their size to fit the body size of the recipient after transplantation, despite a lack of evidence. The aim of this study was to test this hypothesis. This was a retrospective cohort study of 113 liver transplantations performed at Karolinska University Hospital. The cohort was divided based on graft volume-to-standard liver volume ratio (GV/SLV) into quartiles of small, mid, and large grafts. Serial volumetric assessment was performed on the day of transplantation and at posttransplant check-ups early (<2 mo) and late (9-13 mo) after transplantation using computed tomography (CT) volumetry. Change in GV/SLV ratio over time was analyzed with ANOVA repeated measures. A multiple regression model was used to investigate the influence of intraoperative blood flow, recipient body size, age, and relative sickness on graft volume changes. Between the three time points, mean GV/SLV ratio adapted to 0.55-0.94-1.00 in small grafts (n = 29, P < 0.001); 0.87-1.18-1.13 in midgrafts (n = 56, P < 0.001); 1.11-1.51-1.18 in large grafts (n = 28, P < 0.001). Regression analysis showed a positive correlation between posttransplant graft growth and portal flow (β = 1.18, P = 0.005), arterial flow (β = 0.17, P = 0.001), and recipient body surface area (β = 59.85, P < 0.001). A negative correlation was observed for graft weight-to-recipient weight ratio (GRWR; β = -33.12, P < 0.001). Grafts with initial GV/SLV-ratio < 0.6 adapt toward the ideal volume for recipient body size 1 year after transplantation. The disparity between graft size relative to recipient body size, and the portal and arterial perfusion, influence volumetric graft changes.NEW & NOTEWORTHY This is the first and largest human study to verify the hypothesis that whole liver grafts adjust their size to match recipient body size 1 year after transplantation-a phenomenon that has previously only been observed in experimental animal studies and human case reports. The direction of volumetric changes is driven by the disparity between graft size relative to recipient body surface area and weight, as well as the intraoperative portal- and arterial graft perfusion.

Preoperative Computed Tomography Volumetry and Graft Weight Estimation of Left Lateral Segment in Pediatric Living Donor Liver Transplant

OBJECTIVES

Liver volumetry based on a computed tomography scan is widely used to estimate liver volume before any liver resection, especially before living donorliver donation. The 1-to-1 conversion rule for liver volume to liver weight has been widely adopted; however, debate continues regarding this approach. Therefore, we analyzed the relationship between the left-lateral lobe liver graft volume and actual graft weight.

MATERIALS AND METHODS

This study retrospectively included consecutive donors who underwent left lateral hepatectomy for pediatric living donor liver transplant from December 2008 to September 2020. All donors were healthy adults who met the evaluation criteria for pediatric living donor liver transplant and underwent a preoperative contrast-enhanced computed tomography scan. Manual segmentation of the leftlateral liverlobe for graft volume estimation and intraoperative measurement of an actual graft weight were performed. The relationship between estimated graft volume and actual graft weight was analyzed.

RESULTS

Ninety-four living liver donors were included in the study. The mean actual graft weight was ~283.4 ± 68.5 g, and the mean graft volume was 244.9 ± 63.86 mL. A strong correlation was shown between graft volume and actual graft weight (r = 0.804; P < .001). Bland-Altman analysis revealed an interobserver agreement of 38.0 ± 97.25, and intraclass correlation coefficient showed almost perfect agreement(r = 0.840; P < .001). The conversion formula for calculating graft weight based on computed tomography volumetry was determined based on regression analysis: 0.88 × graft volume + 41.63.

CONCLUSIONS

The estimation of left liver graft weight using only the 1-to-1 rule is subject to measurable variability in calculated graft weights and tends to underestimate the true graft weight. Instead, a different, improved conversion formula should be used to calculate graft weight to more accurately determine donor graft weight-to-recipient body weightratio and reduce the risk of underestimation of liver graft weightin the donor selection process before pediatric living donor liver transplant.

Duke Liver Dataset: A Publicly Available Liver MRI Dataset with Liver Segmentation Masks and Series Labels

The Duke Liver Dataset contains 2146 abdominal MRI series from 105 patients, including a majority with cirrhotic features, and 310 image series with corresponding manually segmented liver masks.

Magnetic Resonance Imaging for Monitoring of Hepatic Disease Induced by Ebola Virus: a Nonhuman Primate Proof-of-Concept Study

Severe liver impairment is a well-known hallmark of Ebola virus disease (EVD). However, the role of hepatic involvement in EVD progression is understudied. Medical imaging in established animal models of EVD (e.g., nonhuman primates [NHPs]) can be a strong complement to traditional assays to better investigate this pathophysiological process in vivo and noninvasively. In this proof-of-concept study, we used longitudinal multiparametric magnetic resonance imaging (MRI) to characterize liver morphology and function in nine rhesus monkeys after exposure to Ebola virus (EBOV). Starting 5 days postexposure, MRI assessments of liver appearance, morphology, and size were consistently compatible with the presence of hepatic edema, inflammation, and congestion, leading to significant hepatomegaly at necropsy. MRI performed after injection of a hepatobiliary contrast agent demonstrated decreased liver signal on the day of euthanasia, suggesting progressive hepatocellular dysfunction and hepatic secretory impairment associated with EBOV infection. Importantly, MRI-assessed deterioration of biliary function was acute and progressed faster than changes in serum bilirubin concentrations. These findings suggest that longitudinal quantitative in vivo imaging may be a useful addition to standard biological assays to gain additional knowledge about organ pathophysiology in animal models of EVD. IMPORTANCE Severe liver impairment is a well-known hallmark of Ebola virus disease (EVD), but the contribution of hepatic pathophysiology to EVD progression is not fully understood. Noninvasive medical imaging of liver structure and function in well-established animal models of disease may shed light on this important aspect of EVD. In this proof-of-concept study, we used longitudinal magnetic resonance imaging (MRI) to characterize liver abnormalities and dysfunction in rhesus monkeys exposed to Ebola virus. The results indicate that in vivo MRI may be used as a noninvasive readout of organ pathophysiology in EVD and may be used in future animal studies to further characterize organ-specific damage of this condition, in addition to standard biological assays.

Predicting vasospasm risk using first presentation aneurysmal subarachnoid hemorrhage volume: A semi-automated CT image segmentation analysis using ITK-SNAP

PURPOSE

Cerebral vasospasm following aneurysmal subarachnoid hemorrhage (aSAH) is a significant complication associated with poor neurological outcomes. We present a novel, semi-automated pipeline, implemented in the open-source medical imaging analysis software ITK-SNAP, to segment subarachnoid blood volume from initial CT head (CTH) scans and use this to predict future radiological vasospasm.

METHODS

42 patients were admitted between February 2020 and December 2021 to our tertiary neurosciences center, and whose initial referral CTH scan was used for this retrospective cohort study. Blood load was segmented using a semi-automated random forest classifier and active contour evolution implemented in ITK-SNAP. Clinical data were extracted from electronic healthcare records in order to fit models aimed at predicting radiological vasospasm risk.

RESULTS

Semi-automated segmentations demonstrated excellent agreement with manual, expert-derived volumes (mean Dice coefficient = 0.92). Total normalized blood volume, extracted from CTH images at first presentation, was significantly associated with greater odds of later radiological vasospasm, increasing by approximately 7% for each additional cm3 of blood (OR = 1.069, 95% CI: 1.021-1.120; p < .005). Greater blood volume was also significantly associated with vasospasm of a higher Lindegaard ratio, of longer duration, and a greater number of discrete episodes. Total blood volume predicted radiological vasospasm with a greater accuracy as compared to the modified Fisher scale (AUC = 0.86 vs 0.70), and was of independent predictive value.

CONCLUSION

Semi-automated methods provide a plausible pipeline for the segmentation of blood from CT head images in aSAH, and total blood volume is a robust, extendable predictor of radiological vasospasm, outperforming the modified Fisher scale. Greater subarachnoid blood volume significantly increases the odds of subsequent vasospasm, its time course and its severity.

[Metastatic colorectal cancer-Modern treatment strategies and sequences]

The treatment of metastatic colorectal cancer (mCRC) has been considerably expanded and relevantly improved in recent years with new strategies, such as resection of liver and/or lung metastases, induction and maintenance treatment, the establishment of targeted therapies and molecularly defined strategies in defined subgroups. This article presents evidence-based treatment options and algorithms, with a focus on systemic treatment.

Liver Transplant in Patients with Hepatocarcinoma: Imaging Guidelines and Future Perspectives Using Artificial Intelligence

Hepatocellular carcinoma is the most common primary malignant hepatic tumor and occurs most often in the setting of chronic liver disease. Liver transplantation is a curative treatment option and is an ideal solution because it solves the chronic underlying liver disorder while removing the malignant lesion. However, due to organ shortages, this treatment can only be applied to carefully selected patients according to clinical guidelines. Artificial intelligence is an emerging technology with multiple applications in medicine with a predilection for domains that work with medical imaging, like radiology. With the help of these technologies, laborious tasks can be automated, and new lesion imaging criteria can be developed based on pixel-level analysis. Our objectives are to review the developing AI applications that could be implemented to better stratify liver transplant candidates. The papers analysed applied AI for liver segmentation, evaluation of steatosis, sarcopenia assessment, lesion detection, segmentation, and characterization. A liver transplant is an optimal treatment for patients with hepatocellular carcinoma in the setting of chronic liver disease. Furthermore, AI could provide solutions for improving the management of liver transplant candidates to improve survival.

Plan quality analysis of stereotactic ablative body radiotherapy treatment planning in liver tumor

PURPOSE

Stereotactic ablative body radiotherapy (SABR) in the liver, RTOG-1112 guides the treatment modalities including the dose constraints for this technique but not the plan parameters. This study is not only analyzing the plan quality by utilizing the plan parameters and indexes but also compares treatment modalities from the protocol implementation.

METHOD AND MATERIAL

Twenty-five patients treated in the period from February 2020 to September 2022 were recruited in this analysis. Two planners randomly selected the patients and modalities. The modalities employed were Volumetric-Modulated Arc Therapy (VMAT) and Helical Tomotherapy (HT). Various parameters and indexes were used to access not only the plan quality but also to compare each modality. The parameters and indexes studied were the homogeneity index (HI), conformity index (CI), gradient distance (GD), and the dose received by the organs at risk.

RESULT

The data reveals that the mean volume of PTV is 60.8 ± 53.9 cc where these targets exhibit no significant difference between each modality. The HI shows a consistent value for both modalities. Between each modality, the CI value shows less deviation, but the HT shows slightly higher performance than VMAT. The value of GD is 1.5 ± 0.3 cm where the HT provides a shorter distance compared to VMAT as well.

CONCLUSION

The parameters and indexes should be utilized for the plan evaluation although in the guidelines this was not required. Various modalities were employed for treatment. Both can achieve the treatment criteria with slightly low performance of VMAT.

Pilot Study: The Effects of Slice Parameters and the Interobserver Measurement Variability in Computed Tomographic Hepatic Volumetry in Dogs without Hepatic Disease

Manual computed tomographic (CT) hepatic volumetry is a non-invasive method for assessing liver volume. However, it is time-consuming with large numbers of slices. Reducing the slice number would expedite the process, but the effect of fewer slices on the accuracy of volumetric measurements in dogs has not been investigated. The objectives of this study were to evaluate the relationship between slice interval and the number of slices on hepatic volume in dogs using CT hepatic volumetry and the interobserver variability of CT volumetric measurements. We retrospectively reviewed medical records for dogs without evidence of hepatobiliary disease with abdominal CT from 2019 to 2020. Hepatic volumes were calculated by using all slices, and interobserver variability was calculated using the same dataset in 16 dogs by three observers. Interobserver variability was low, with a mean (±SD) percent difference in the hepatic volume of 3.3 (±2.5)% among all observers. The greatest percent differences in hepatic volume were decreased when using larger numbers of slices; the percent differences were <5% when using ≥20 slices for hepatic volumetry. Manual CT hepatic volumetry can be used in dogs to non-invasively assess liver volume with low interobserver variability, and a relatively reliable result can be acquired using ≥20 slices in dogs.

Fully Automatic Liver and Tumor Segmentation from CT Image Using an AIM-Unet

The segmentation of the liver is a difficult process due to the changes in shape, border, and density that occur in each section in computed tomography (CT) images. In this study, the Adding Inception Module-Unet (AIM-Unet) model, which is a hybridization of convolutional neural networks-based Unet and Inception models, is proposed for computer-assisted automatic segmentation of the liver and liver tumors from CT scans of the abdomen. Experimental studies were carried out on four different liver CT image datasets, one of which was prepared for this study and three of which were open (CHAOS, LIST, and 3DIRCADb). The results obtained using the proposed method and the segmentation results marked by the specialist were compared with the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and accuracy (ACC) measurement parameters. In this study, we obtained the best DSC, JSC, and ACC liver segmentation performance metrics on the CHAOS dataset as 97.86%, 96.10%, and 99.75%, respectively, of the AIM-Unet model we propose, which is trained separately on three datasets (LiST, CHAOS, and our dataset) containing liver images. Additionally, 75.6% and 65.5% of the DSC tumor segmentation metrics were calculated on the proposed model LiST and 3DIRCADb datasets, respectively. In addition, the segmentation success results on the datasets with the AIM-Unet model were compared with the previous studies. With these results, it has been seen that the method proposed in this study can be used as an auxiliary tool in the decision-making processes of physicians for liver segmentation and detection of liver tumors. This study is useful for medical images, and the developed model can be easily developed for applications in different organs and other medical fields.

Validation of a semi-automatic method to measure total liver volumes in polycystic liver disease on computed tomography - high speed and accuracy

OBJECTIVES

Polycystic liver disease (PLD) is characterized by growth of hepatic cysts, causing hepatomegaly. Disease severity is determined using total liver volume (TLV), which can be measured from computed tomography (CT). The gold standard is manual segmentation which is time-consuming and requires expert knowledge of the anatomy. This study aims to validate the commercially available semi-automatic MMWP (Multimodality Workplace) Volume tool for CT scans of PLD patients.

METHODS

We included adult patients with one (n = 60) or two (n = 46) abdominal CT scans. Semi-automatic contouring was compared with manual segmentation, using comparison of observed volumes (cross-sectional) and growth (longitudinal), correlation coefficients (CC), and Bland-Altman analyses with bias and precision, defined as the mean difference and SD from this difference. Inter- and intra-reader variability were assessed using coefficients of variation (CV) and we assessed the time to perform both procedures.

RESULTS

Median TLV was 5292.2 mL (IQR 3141.4-7862.2 mL) at baseline. Cross-sectional analysis showed high correlation and low bias and precision between both methods (CC 0.998, bias 1.62%, precision 2.75%). Absolute volumes were slightly higher for semi-automatic segmentation (manual 5292.2 (3141.4-7862.2) versus semi-automatic 5432.8 (3071.9-7960.2) mL, difference 2.7%, p < 0.001). Longitudinal analysis demonstrated that semi-automatic segmentation accurately measures liver growth (CC 0.908, bias 0.23%, precision 4.04%). Inter- and intra-reader variability were small (2.19% and 0.66%) and comparable to manual segmentation (1.21% and 0.63%) (p = 0.26 and p = 0.37). Semi-automatic segmentation was faster than manual tracing (19 min versus 50 min, p = 0.009).

CONCLUSIONS

Semi-automatic liver segmentation is a fast and accurate method to determine TLV and liver growth in PLD patients.

KEY POINTS

• Semi-automatic liver segmentation using the commercially available MMWP volume tool accurately determines total liver volume as well as liver growth over time in polycystic liver disease patients. • This method is considerably faster than manual segmentation through the use of Hounsfield unit settings. • We used a real-life CT set for the validation and showed that the semi-automatic tool measures accurately regardless of contrast used for the CT scan or not, presence of polycystic kidneys, liver volume, and previous invasive treatment for polycystic liver disease.

Liver volume based prediction model for patients with hepatitis B virus-related acute-on-chronic liver failure

BACKGROUND

Hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF) is a life-threatening disease with high short-term mortality. Early and accurate prognosis is significant for clinical decisions, in which liver volume (LV) imparts important information. However, LV has not been considered in current prognostic models for HBV-ACLF.

METHODS

Three hundred and twenty-three patients were recruited to the deriving cohort, while 163 were enrolled to validation cohort. The primary end-point was death within 28 days since admission. Estimated liver volume (ELV) was calculated by the formula based on healthy population. Logistic regression was used to develop a prediction model. Accuracy of models were evaluated by receiver operating characteristic (ROC) curves.

RESULTS

The ratio of LV to ELV (LV/ELV%) was significantly lower in non-survivors, and LV/ELV% ≤82% indicated poor prognosis. LV/ELV%, Age, prothrombin time (PT), the grade of hepatic encephalopathy (HE), ln-transformed total bilirubin (lnTBil), and log-transformed HBV DNA (Log₁₀ HBV DNA) were identified as independent predictors to develop an LV-based model, LEAP-HBV. The mean area under the ROC (AUC) of LEAP-HBV was 0.906 (95% CI, 0.904-0.908), higher than other non-LV-based models.

CONCLUSION

Liver volume was an independent predictor, and LEAP-HBV, a prediction model based on LV, was developed for the short-term mortality in HBV-ACLF. This study was registered on ClinicalTrails (NCT03977857).

Optimal surgical workup to ensure safe recovery of the donor after living liver donation - A systematic review of the literature and expert panel recommendations

BACKGROUND

The essential premise of living donor liver transplantation is the assurance that the donors will have a complication-free perioperative course and a prompt recovery. Selection of appropriate donors is the first step to support this premise and is based on tests that constitute the donor workup. The exclusion of liver pathologies and assessment of liver anatomy and volume in the donor candidate are the most important elements in the selection of the appropriate candidate.

OBJECTIVE

To determine whether there is evidence to define an optimal donor surgical workup that would improve short-term outcomes of the donor after living liver donation.

DATA SOURCES

Ovid Medline, Embase, Scopus, Google Scholar, and Cochrane Central.

METHODS

Systematic review following PRISMA guidelines and recommendations using the GRADE approach derived from an international expert panel.

RESULTS

Although a liver biopsy remains the only method to exactly determine the percentage and type of steatosis and to detect other liver pathologies, its routine use is not supported. Both magnetic resonance imaging (MRI) and computed tomography (CT) appear to be adequate for quantifying liver volume; the preference for one or the other is often based on center expertise. MRI is clearly a better technique to assess biliary anatomy, although aberrant biliary anatomy may not be clearly detected. MRI is also more accurate than CT in determining low grades of steatosis. CT angiography is the imaging test of choice to assess the vascular anatomy. There is no evidence of the need for catheter angiography in the modern evaluation of a living liver donor.

CONCLUSIONS

A donor liver biopsy is indicated if abnormalities are present in serological or imaging tests. Both MRI and CT imaging appear to be adequate methodologies. The routine use of catheter angiography is not supported in view of the adequacy of CT angiography in delineating liver vascular anatomy. No imaging modality available to quantify liver volume is superior to another. Biliary anatomy is better defined with MRI, although poor definition can be expected, particularly for abnormal ducts.

A pipeline for automated deep learning liver segmentation (PADLLS) from contrast enhanced CT exams

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.

Lightweight Compound Scaling Network for Nasopharyngeal Carcinoma Segmentation from MR Images

Nasopharyngeal carcinoma (NPC) is a category of tumours with a high incidence in head-and-neck. To treat nasopharyngeal cancer, doctors invariably need to perform focal segmentation. However, manual segmentation is time consuming and laborious for doctors and the existing automatic segmentation methods require large computing resources, which makes some small and medium-sized hospitals unaffordable. To enable small and medium-sized hospitals with limited computational resources to run the model smoothly and improve the accuracy of structure, we propose a new LW-UNet network. The network utilises lightweight modules to form the Compound Scaling Encoder and combines the benefits of UNet to make the model both lightweight and accurate. Our model achieves a high accuracy with a Dice coefficient value of 0.813 with 3.55 M parameters and 7.51 G of FLOPs within 0.1 s (testing time in GPU), which is the best result compared with four other state-of-the-art models.

Leberchirurgie 4.0 - OP-Planung, Volumetrie, Navigation und Virtuelle Realität

Durch die Optimierung der konservativen Behandlung, die Verbesserung der bildgebenden Verfahren und die Weiterentwicklung der Operationstechniken haben sich das operative Spektrum sowie der Maßstab für die Resektabilität in Bezug auf die Leberchirurgie in den letzten Jahrzehnten deutlich verändert.

Dank zahlreicher technischer Entwicklungen, insbesondere der 3-dimensionalen Segmentierung, kann heutzutage die präoperative Planung und die Orientierung während der Operation selbst, vor allem bei komplexen Eingriffen, unter Berücksichtigung der patientenspezifischen Anatomie erleichtert werden.

Neue Technologien wie 3-D-Druck, virtuelle und augmentierte Realität bieten zusätzliche Darstellungsmöglichkeiten für die individuelle Anatomie. Verschiedene intraoperative Navigationsmöglichkeiten sollen die präoperative Planung im Operationssaal verfügbar machen, um so die Patientensicherheit zu erhöhen.

Dieser Übersichtsartikel soll einen Überblick über den gegenwärtigen Stand der verfügbaren Technologien sowie einen Ausblick in den Operationssaal der Zukunft geben.

Reliability and accuracy of straightforward measurements for liver volume determination in ultrasound and computed tomography compared to real volumetry

To evaluate the suitability of volume index measurement (VI) by either ultrasound (US) or computed tomography (CT) for the assessment of liver volume. Fifty-nine patients, 21 women, with a mean age of 66.8 ± 12.6 years underwent US of the liver followed immediately by abdominal CT. In US and CT imaging dorsoventral, mediolateral and craniocaudal liver diameters in their maximum extensions were assessed by two observers. VI was calculated by multiplication of the diameters divided by a constant (3.6). The liver volume determined by a manual segmentation in CT ("true liver volume") served as gold standard. True liver volume and calculated VI determined by US and CT were compared using Bland-Altman analysis. Mean differences of VI between observers were - 34.7% (- 90.1%; 20.7%) for the US-based and 1.1% (- 16.1%; 18.2%) for the CT-based technique, respectively. Liver volumes determined by semi-automated segmentation, US-based VI and CT-based VI, were as follows: 1.500 ± 347cm³; 863 ± 371cm³; 1.509 ± 432cm³. Results showed a great discrepancy between US-based VI and true liver volume with a mean bias of 58.3 ± 66.9%, and high agreement between CT-based VI and true liver volume with a low mean difference of 4.4 ± 28.3%. Volume index based on CT diameters is a reliable, fast and simple approach for estimating liver volume and can therefore be recommended for clinical practice. The usage of US-based volume index for assessment of liver volume should not be used due to its low accuracy of US in measurement of liver diameters.

Practical utility of liver segmentation methods in clinical surgeries and interventions

Clinical imaging (e.g., magnetic resonance imaging and computed tomography) is a crucial adjunct for clinicians, aiding in the diagnosis of diseases and planning of appropriate interventions. This is especially true in malignant conditions such as hepatocellular carcinoma (HCC), where image segmentation (such as accurate delineation of liver and tumor) is the preliminary step taken by the clinicians to optimize diagnosis, staging, and treatment planning and intervention (e.g., transplantation, surgical resection, radiotherapy, PVE, embolization, etc). Thus, segmentation methods could potentially impact the diagnosis and treatment outcomes. This paper comprehensively reviews the literature (during the year 2012-2021) for relevant segmentation methods and proposes a broad categorization based on their clinical utility (i.e., surgical and radiological interventions) in HCC. The categorization is based on the parameters such as precision, accuracy, and automation.

Liver Surgery: Important Considerations for Pre- and Postoperative Imaging

Liver surgery may be a curative treatment option not only for primary liver neoplasms but also for liver metastases in selected patients. The number of liver surgeries performed worldwide has increased, but surgical morbidity associated with these surgeries remains significant. Therefore, radiologists need to understand the terminology, surgical techniques, resectability and unresectability criteria, and possible postoperative complications as these are part of the decision-making process. Because vascular and biliary variations are common, an adequate preoperative anatomic evaluation determines the best surgical technique, helps identify patients in whom additional surgical steps will be required, and reduces the risk of inadvertent injury. The surgeon must ensure that the future liver remnant is sufficient to maintain adequate function, aided by the radiologist who can provide valuable information such as the presence of steatosis, biliary dilatation, signs of cirrhosis, and portal hypertension, in addition to the volume of the future liver remnant. Postoperative complications must also be understood and evaluated. The most common postoperative complications are vascular (bleeding, thrombosis, and ischemia), biliary (fistulas, bilomas, and strictures), infectious (incisional or deep), those related to liver failure, and even tumor recurrence. An invited commentary by Winslow is available online. Online supplemental material is available for this article. ^©RSNA, 2022.

Deep 3D attention CLSTM U-Net based automated liver segmentation and volumetry for the liver transplantation in abdominal CT volumes

In living-donor liver transplantation, the safety of the donor is critical. In addition, accurately measuring the liver volume is significant as the amount that can be resected from living donors is limited. In this paper, we propose an automated segmentation and volume estimation method for the liver in computed tomography imaging based on a deep learning-based segmentation network. Our framework was trained using the data of 191 donors, achieved a dice similarity coefficient of 0.789, 0.869, 0.955, and 0.899, respectively, in the segmentation task for the left lobe, right lobe, caudate lobe, and whole liver. Moreover, the R^2 score reached 0.980, 0.996, 0.953, and 0.996 in the volume estimation task. We demonstrate that our approach provides accurate and quantitative liver segmentation results, reducing the error in liver volume estimation. Therefore, we expected to be used as an aid in estimating liver volume from CT volume data for living-donor liver transplantation.

Non-Contrast-Enhanced and Contrast-Enhanced Magnetic Resonance Angiography in Living Donor Liver Vascular Anatomy

Background: Since the advent of a new generation of inflow-sensitive inversion recovery (IFIR) technology, three-dimensional non-contrast-enhanced magnetic resonance angiography is being used to obtain hepatic vessel images without applying gadolinium contrast agent. The purpose of this study was to explore the diagnostic efficacy of non-contrast-enhanced magnetic resonance angiography (non-CE MRA), contrast-enhanced magnetic resonance angiography (CMRA), and computed tomography angiography (CTA) in the preoperative evaluation of living liver donors. Methods: A total of 43 liver donor candidates who were evaluated for living donor liver transplantation completed examinations. Donors’ age, gender, renal function (eGFR), and previous CTA and imaging were recorded before non-CE MRA and CMRA. CTA images were used as the standard. Results: Five different classifications of hepatic artery patterns (types I, III, V, VI, VIII) and three different classifications of portal vein patterns (types I, II, and III) were identified among 43 candidates. The pretransplant vascular anatomy was well identified using combined non-CE MRA and CMRA of hepatic arteries (100%), PVs (98%), and hepatic veins (100%) compared with CTA images. Non-CE MRA images had significantly stronger contrast signal intensity of portal veins (p < 0.01) and hepatic veins (p < 0.01) than CMRA. No differences were found in signal intensity of the hepatic artery between non-CE MRA and CMRA. Conclusion: Combined non-CE MRA and CMRA demonstrate comparable diagnostic ability to CTA and provide enhanced biliary anatomy information that assures optimum donor safety.

Polycystic liver: automatic segmentation using deep learning on CT is faster and as accurate compared to manual segmentation

OBJECTIVE

This study aimed to develop and investigate the performance of a deep learning model based on a convolutional neural network (CNN) for the automatic segmentation of polycystic livers at CT imaging.

METHOD

This retrospective study used CT images of polycystic livers. To develop the CNN, supervised training and validation phases were performed using 190 CT series. To assess performance, the test phase was performed using 41 CT series. Manual segmentation by an expert radiologist (Rad1a) served as reference for all comparisons. Intra-observer variability was determined by the same reader after 12 weeks (Rad1b), and inter-observer variability by a second reader (Rad2). The Dice similarity coefficient (DSC) evaluated overlap between segmentations. CNN performance was assessed using the concordance correlation coefficient (CCC) and the two-by-two difference between the CCCs; their confidence interval was estimated with bootstrap and Bland-Altman analyses. Liver segmentation time was automatically recorded for each method.

RESULTS

A total of 231 series from 129 CT examinations on 88 consecutive patients were collected. For the CNN, the DSC was 0.95 ± 0.03 and volume analyses yielded a CCC of 0.995 compared with reference. No statistical difference was observed in the CCC between CNN automatic segmentation and manual segmentations performed to evaluate inter-observer and intra-observer variability. While manual segmentation required 22.4 ± 10.4 min, central and graphics processing units took an average of 5.0 ± 2.1 s and 2.0 ± 1.4 s, respectively.

CONCLUSION

Compared with manual segmentation, automated segmentation of polycystic livers using a deep learning method achieved much faster segmentation with similar performance.

KEY POINTS

• Automatic volumetry of polycystic livers using artificial intelligence method allows much faster segmentation than expert manual segmentation with similar performance. • No statistical difference was observed between automatic segmentation, inter-observer variability, or intra-observer variability.

Impact of Pretransplantation CT on Liver Donation in Potential Deceased Organ Donors

BACKGROUND

Computed tomography (CT) is routinely used to determine the suitability of potential living donor liver transplants, providing important information about liver size, vascular anatomy, and the presence of other diseases that would preclude it from safe donation. CT is not routinely used, however, when evaluating eligible deceased organ donors after brain death, a group which comprises most orthotopic liver transplants. After the installation of a CT scanner at a local procurement facility, CTs have been performed on potential deceased organ donors and used, in conjunction with other evaluative protocols, to help direct donation decisions and assist in procurement procedures.

STUDY DESIGN

A retrospective analysis of data from 373 cases spanning 5 years was systematically collected and analyzed, including information pertaining to patient's medical histories, biopsy results, operative findings, and CT results.

RESULTS

CT findings directly impacted the directive decision-making process in 29% of cases in this patient cohort, likely an underestimate, and reliably evaluated important factors including variant vascular anatomy and the presence and severity of hepatic steatosis and cirrhosis.

CONCLUSION

Overall, this study suggests that CT has the potential to play a significant role in procurement procedures and the directive decision-making process, thereby improving the efficiency and accuracy by which potential deceased organ donors are evaluated.

AttR2U-Net: A Fully Automated Model for MRI Nasopharyngeal Carcinoma Segmentation Based on Spatial Attention and Residual Recurrent Convolution

Radiotherapy is an essential method for treating nasopharyngeal carcinoma (NPC), and the segmentation of NPC is a crucial process affecting the treatment. However, manual segmentation of NPC is inefficient. Besides, the segmentation results of different doctors might vary considerably. To improve the efficiency and the consistency of NPC segmentation, we propose a novel AttR2U-Net model which automatically and accurately segments nasopharyngeal carcinoma from MRI images. This model is based on the classic U-Net and incorporates advanced mechanisms such as spatial attention, residual connection, recurrent convolution, and normalization to improve the segmentation performance. Our model features recurrent convolution and residual connections in each layer to improve its ability to extract details. Moreover, spatial attention is fused into the network by skip connections to pinpoint cancer areas more accurately. Our model achieves a DSC value of 0.816 on the NPC segmentation task and obtains the best performance compared with six other state-of-the-art image segmentation models.