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

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.

Towards more precise automatic analysis: a systematic review of deep learning-based multi-organ segmentation

Accurate segmentation of multiple organs in the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation methods have far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. We searched Google Scholar for papers published from January 1, 2016 to December 31, 2023, using keywords "multi-organ segmentation" and "deep learning", resulting in 327 papers. We followed the PRISMA guidelines for paper selection, and 195 studies were deemed to be within the scope of this review. We summarized the two main aspects involved in multi-organ segmentation: datasets and methods. Regarding datasets, we provided an overview of existing public datasets and conducted an in-depth analysis. Concerning methods, we categorized existing approaches into three major classes: fully supervised, weakly supervised and semi-supervised, based on whether they require complete label information. We summarized the achievements of these methods in terms of segmentation accuracy. In the discussion and conclusion section, we outlined and summarized the current trends in multi-organ segmentation.

Prognostication of Hepatocellular Carcinoma Using Artificial Intelligence

Hepatocellular carcinoma (HCC) is a biologically heterogeneous tumor characterized by varying degrees of aggressiveness. The current treatment strategy for HCC is predominantly determined by the overall tumor burden, and does not address the diverse prognoses of patients with HCC owing to its heterogeneity. Therefore, the prognostication of HCC using imaging data is crucial for optimizing patient management. Although some radiologic features have been demonstrated to be indicative of the biologic behavior of HCC, traditional radiologic methods for HCC prognostication are based on visually-assessed prognostic findings, and are limited by subjectivity and inter-observer variability. Consequently, artificial intelligence has emerged as a promising method for image-based prognostication of HCC. Unlike traditional radiologic image analysis, artificial intelligence based on radiomics or deep learning utilizes numerous image-derived quantitative features, potentially offering an objective, detailed, and comprehensive analysis of the tumor phenotypes. Artificial intelligence, particularly radiomics has displayed potential in a variety of applications, including the prediction of microvascular invasion, recurrence risk after locoregional treatment, and response to systemic therapy. This review highlights the potential value of artificial intelligence in the prognostication of HCC as well as its limitations and future prospects.

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.

Deep-Learning Models for Abdominal CT Organ Segmentation in Children: Development and Validation in Internal and Heterogeneous Public Datasets

Background: Deep-learning abdominal organ segmentation algorithms have shown excellent results in adults; validation in children is sparse. Objective: To develop and validate deep-learning models for liver, spleen, and pancreas segmentation on pediatric CT examinations. Methods: This retrospective study developed and validated deep-learning models for liver, spleen, and pancreas segmentation using 1731 CT examinations (1504 training, 221 testing), derived from three internal institutional pediatric (age ≤18) datasets (n=483) and three public datasets comprising pediatric and adult examinations with various pathologies (n=1248). Three deep-learning model architectures (SegResNet, DynUNet, and SwinUNETR) from the Medical Open Network for AI (MONAI) framework underwent training using native training (NT), relying solely on institutional datasets, and transfer learning (TL), incorporating pre-training on public datasets. For comparison, TotalSegmentator (TS), a publicly available segmentation model, was applied to test data without further training. Segmentation performance was evaluated using mean Dice similarity coefficient (DSC), with manual segmentations as reference. Results: For internal pediatric data, DSC for normal liver was 0.953 (TS), 0.964-0.965 (NT models), and 0.965-0.966 (TL models); normal spleen, 0.914 (TS), 0.942-0.945 (NT models), and 0.937-0.945 (TL models); normal pancreas, 0.733 (TS), 0.774-0.785 (NT models), and 0.775-0.786 (TL models); pancreas with pancreatitis, 0.703 (TS), 0.590-0.640 (NT models), and 0.667-0.711 (TL models). For public pediatric data, DSC for liver was 0.952 (TS), 0.876-0.908 (NT models), and 0.941-0.946 (TL models); spleen, 0.905 (TS), 0.771-0.827 (NT models), and 0.897-0.926 (TL models); pancreas, 0.700 (TS), 0.577-0.648 (NT models), and 0.693-0.736 (TL models). For public primarily adult data, DSC for liver was 0.991 (TS), 0.633-0.750 (NT models), and 0.926-0.952 (TL models); spleen, 0.983 (TS), 0.569-0.604 (NT models), and 0.923-0.947 (TL models); pancreas, 0.909 (TS), 0.148-0.241 (NT models), and 0.699-0.775 (TL models). DynUNet-TL was selected as the best-performing NT or TL model and was made available as an opensource MONAI bundle (https://github.com/cchmc-dll/pediatric_abdominal_segmentation_bundle.git). Conclusion: TL models trained on heterogeneous public datasets and fine-tuned using institutional pediatric data outperformed internal NT models and TotalSegmentator across internal and external pediatric test data. Segmentation performance was better in liver and spleen than in pancreas. Clinical Impact: The selected model may be used for various volumetry applications in pediatric imaging.

Fully-automated multi-organ segmentation tool applicable to both non-contrast and post-contrast abdominal CT: deep learning algorithm developed using dual-energy CT images

A novel 3D nnU-Net-based of algorithm was developed for fully-automated multi-organ segmentation in abdominal CT, applicable to both non-contrast and post-contrast images. The algorithm was trained using dual-energy CT (DECT)-obtained portal venous phase (PVP) and spatiotemporally-matched virtual non-contrast images, and tested using a single-energy (SE) CT dataset comprising PVP and true non-contrast (TNC) images. The algorithm showed robust accuracy in segmenting the liver, spleen, right kidney (RK), and left kidney (LK), with mean dice similarity coefficients (DSCs) exceeding 0.94 for each organ, regardless of contrast enhancement. However, pancreas segmentation demonstrated slightly lower performance with mean DSCs of around 0.8. In organ volume estimation, the algorithm demonstrated excellent agreement with ground-truth measurements for the liver, spleen, RK, and LK (intraclass correlation coefficients [ICCs] > 0.95); while the pancreas showed good agreements (ICC = 0.792 in SE-PVP, 0.840 in TNC). Accurate volume estimation within a 10% deviation from ground-truth was achieved in over 90% of cases involving the liver, spleen, RK, and LK. These findings indicate the efficacy of our 3D nnU-Net-based algorithm, developed using DECT images, which provides precise segmentation of the liver, spleen, and RK and LK in both non-contrast and post-contrast CT images, enabling reliable organ volumetry, albeit with relatively reduced performance for the pancreas.

Three-dimensional Liver Model Application for Liver Transplantation

BACKGROUND

Children are removed from the liver transplant waitlist because of death or progressive illness. Size mismatch accounts for 30% of organ refusal. This study aimed to demonstrate that 3-dimensional (3D) technology is a feasible and accurate adjunct to organ allocation and living donor selection process.

METHODS

This prospective multicenter study included pediatric liver transplant candidates and living donors from January 2020 to February 2023. Patient-specific, 3D-printed liver models were used for anatomic planning, real-time evaluation during organ procurement, and surgical navigation. The primary outcome was to determine model accuracy. The secondary outcome was to determine the impact of outcomes in living donor hepatectomy. Study groups were analyzed using propensity score matching with a retrospective cohort.

RESULTS

Twenty-eight recipients were included. The median percentage error was -0.6% for 3D models and had the highest correlation to the actual liver explant (Pearson's R = 0.96, P < 0.001) compared with other volume calculation methods. Patient and graft survival were comparable. From 41 living donors, the median percentage error of the allograft was 12.4%. The donor-matched study group had lower central line utilization (21.4% versus 75%, P = 0.045), shorter length of stay (4 versus 7 d, P = 0.003), and lower mean comprehensive complication index (3 versus 21, P = 0.014).

CONCLUSIONS

Three-dimensional volume is highly correlated with actual liver explant volume and may vary across different allografts for living donation. The addition of 3D-printed liver models during the transplant evaluation and organ procurement process is a feasible and safe adjunct to the perioperative decision-making process.

Evaluation of manual and automated approaches for segmentation and extraction of quantitative indices from [18F]FDG PET-CT images

Utilisation of whole organ volumes to extract anatomical and functional information from computed tomography (CT) and positron emission tomography (PET) images may provide key information for the treatment and follow-up of cancer patients. However, manual organ segmentation, is laborious and time-consuming. In this study, a CT-based deep learning method and a multi-atlas method were evaluated for segmenting the liver and spleen on CT images to extract quantitative tracer information from Fluorine-18 fluorodeoxyglucose ([18F]FDG) PET images of 50 patients with advanced Hodgkin lymphoma (HL). Manual segmentation was used as the reference method. The two automatic methods were also compared with a manually defined volume of interest (VOI) within the organ, a technique commonly performed in clinical settings. Both automatic methods provided accurate CT segmentations, with the deep learning method outperforming the multi-atlas with a DICE coefficient of 0.93 ± 0.03 (mean ± standard deviation) in liver and 0.87 ± 0.17 in spleen compared to 0.87 ± 0.05 (liver) and 0.78 ± 0.11 (spleen) for the multi-atlas. Similarly, a mean relative error of -3.2% for the liver and -3.4% for the spleen across patients was found for the mean standardized uptake value (SUVmean) using the deep learning regions while the corresponding errors for the multi-atlas method were -4.7% and -9.2%, respectively. For the maximum SUV (SUVmax), both methods resulted in higher than 20% overestimation due to the extension of organ boundaries to include neighbouring, high-uptake regions. The conservative VOI method which did not extend into neighbouring tissues, provided a more accurate SUVmaxestimate. In conclusion, the automatic, and particularly the deep learning method could be used to rapidly extract information of the SUVmeanwithin the liver and spleen. However, activity from neighbouring organs and lesions can lead to high biases in SUVmaxand current practices of manually defining a volume of interest in the organ should be considered instead.

Liver volumetric and anatomic assessment in living donor liver transplantation: The role of modern imaging and artificial intelligence

The shortage of deceased donor organs has prompted the development of alternative liver grafts for transplantation. Living-donor liver transplantation (LDLT) has emerged as a viable option, expanding the donor pool and enabling timely transplantation with favorable graft function and improved long-term outcomes. An accurate evaluation of the donor liver's volumetry (LV) and anatomical study is crucial to ensure adequate future liver remnant, graft volume and precise liver resection. Thus, ensuring donor safety and an appropriate graft-to-recipient weight ratio. Manual LV (MLV) using computed tomography has traditionally been considered the gold standard for assessing liver volume. However, the method has been limited by cost, subjectivity, and variability. Automated LV techniques employing advanced segmentation algorithms offer improved reproducibility, reduced variability, and enhanced efficiency compared to manual measurements. However, the accuracy of automated LV requires further investigation. The study provides a comprehensive review of traditional and emerging LV methods, including semi-automated image processing, automated LV techniques, and machine learning-based approaches. Additionally, the study discusses the respective strengths and weaknesses of each of the aforementioned techniques. The use of artificial intelligence (AI) technologies, including machine learning and deep learning, is expected to become a routine part of surgical planning in the near future. The implementation of AI is expected to enable faster and more accurate image study interpretations, improve workflow efficiency, and enhance the safety, speed, and cost-effectiveness of the procedures. Accurate preoperative assessment of the liver plays a crucial role in ensuring safe donor selection and improved outcomes in LDLT. MLV has inherent limitations that have led to the adoption of semi-automated and automated software solutions. Moreover, AI has tremendous potential for LV and segmentation; however, its widespread use is hindered by cost and availability. Therefore, the integration of multiple specialties is necessary to embrace technology and explore its possibilities, ranging from patient counseling to intraoperative decision-making through automation and AI.

Machine Learning Radiomics Signature for Differentiating Lymphoma versus Benign Splenomegaly on CT

BACKGROUND

We aimed to develop and validate a preoperative CT-based radiomics signature for differentiating lymphoma versus benign splenomegaly.

METHODS

We retrospectively analyzed CT studies from 139 patients (age range 26-93 years, 43% female) between 2011 and 2019 with histopathological diagnosis of the spleen (19 lymphoma, 120 benign) and divided them into developing (n = 79) and testing (n = 60) datasets. The volumetric radiomic features were extracted from manual segmentation of the whole spleen on venous-phase CT imaging using PyRadiomics package. LASSO regression was applied for feature selection and development of the radiomic signature, which was interrogated with the complete blood cell count and differential count. All p values < 0.05 were considered to be significant.

RESULTS

Seven features were selected for constructing the radiomic signature after feature selection, including first-order statistics (10th percentile and Robust Mean Absolute Deviation), shape-based (Surface Area), and texture features (Correlation, MCC, Small Area Low Gray-level Emphasis and Low Gray-level Zone Emphasis). The radiomic signature achieved an excellent diagnostic accuracy of 97%, sensitivity of 89%, and specificity of 98%, distinguishing lymphoma versus benign splenomegaly in the testing dataset. The radiomic signature significantly correlated with the platelet and segmented neutrophil percentage.

CONCLUSIONS

CT-based radiomics signature can be useful in distinguishing lymphoma versus benign splenomegaly and can reflect the changes in underlying blood profiles.

Reporting Quality of Research Studies on AI Applications in Medical Images According to the CLAIM Guidelines in a Radiology Journal With a Strong Prominence in Asia

OBJECTIVE

We aimed to evaluate the reporting quality of research articles that applied deep learning to medical imaging. Using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines and a journal with prominence in Asia as a sample, we intended to provide an insight into reporting quality in the Asian region and establish a journal-specific audit.

MATERIALS AND METHODS

A total of 38 articles published in the Korean Journal of Radiology between June 2018 and January 2023 were analyzed. The analysis included calculating the percentage of studies that adhered to each CLAIM item and identifying items that were met by ≤ 50% of the studies. The article review was initially conducted independently by two reviewers, and the consensus results were used for the final analysis. We also compared adherence rates to CLAIM before and after December 2020.

RESULTS

Of the 42 items in the CLAIM guidelines, 12 items (29%) were satisfied by ≤ 50% of the included articles. None of the studies reported handling missing data (item #13). Only one study respectively presented the use of de-identification methods (#12), intended sample size (#19), robustness or sensitivity analysis (#30), and full study protocol (#41). Of the studies, 35% reported the selection of data subsets (#10), 40% reported registration information (#40), and 50% measured inter and intrarater variability (#18). No significant changes were observed in the rates of adherence to these 12 items before and after December 2020.

CONCLUSION

The reporting quality of artificial intelligence studies according to CLAIM guidelines, in our study sample, showed room for improvement. We recommend that the authors and reviewers have a solid understanding of the relevant reporting guidelines and ensure that the essential elements are adequately reported when writing and reviewing the manuscripts for publication.

Artificial Intelligence for Improved Hepatosplenomegaly Diagnosis

Hepatosplenomegaly is commonly diagnosed by radiologists based on single dimension measurements and heuristic cut-offs. Volumetric measurements may be more accurate for diagnosing organ enlargement. Artificial intelligence techniques may be able to automatically calculate liver and spleen volume and facilitate more accurate diagnosis. After IRB approval, 2 convolutional neural networks (CNN) were developed to automatically segment the liver and spleen on a training dataset comprised of 500 single-phase, contrast-enhanced CT abdomen and pelvis examinations. A separate dataset of ten thousand sequential examinations at a single institution was segmented with these CNNs. Performance was evaluated on a 1% subset and compared with manual segmentations using Sorensen-Dice coefficients and Pearson correlation coefficients. Radiologist reports were reviewed for diagnosis of hepatomegaly and splenomegaly and compared with calculated volumes. Abnormal enlargement was defined as greater than 2 standard deviations above the mean. Median Dice coefficients for liver and spleen segmentation were 0.988 and 0.981, respectively. Pearson correlation coefficients of CNN-derived estimates of organ volume against the gold-standard manual annotation were 0.999 for the liver and spleen (P < 0.001). Average liver volume was 1556.8 ± 498.7 cc and average spleen volume was 194.6 ± 123.0 cc. There were significant differences in average liver and spleen volumes between male and female patients. Thus, the volume thresholds for ground-truth determination of hepatomegaly and splenomegaly were determined separately for each sex. Radiologist classification of hepatomegaly was 65% sensitive, 91% specific, with a positive predictive value (PPV) of 23% and an negative predictive value (NPV) of 98%. Radiologist classification of splenomegaly was 68% sensitive, 97% specific, with a positive predictive value (PPV) of 50% and a negative predictive value (NPV) of 99%. Convolutional neural networks can accurately segment the liver and spleen and may be helpful to improve radiologist accuracy in the diagnosis of hepatomegaly and splenomegaly.

Estimation of right lobe graft weight for living donor liver transplantation using deep learning-based fully automatic computed tomographic volumetry

This study aimed at developing a fully automatic technique for right lobe graft weight estimation using deep learning algorithms. The proposed method consists of segmentation of the full liver region from computed tomography (CT) images, classification of the entire liver region into the right and left lobes, and estimation of the right lobe graft weight from the CT-measured right lobe graft volume using a volume-to-weight conversion formula. The first two steps were performed with a transformer-based deep learning model. To train and evaluate the model, a total of 248 CT datasets (188 for training, 40 for validation, and 20 for testing and clinical evaluation) were used. The Dice similarity coefficient (DSC), mean surface distance (MSD), and the 95th percentile Hausdorff distance (HD95) were used for evaluating the segmentation accuracy of the full liver region and the right liver lobe. The correlation coefficient (CC), percentage error (PE), and percentage absolute error (PAE) were used for the clinical evaluation of the estimated right lobe graft weight. The proposed method achieved high accuracy in segmentation for DSC, MSD, and HD95 (95.9% ± 1.0%, 1.2 ± 0.4 mm, and 5.2 ± 1.9 mm for the entire liver region; 92.4% ± 2.7%, 2.0 ± 0.7 mm, and 8.8 ± 2.9 mm for the right lobe) and in clinical evaluation for CC, PE, and PAE (0.859, - 1.8% ± 9.6%, and 8.6% ± 4.7%). For the right lobe graft weight estimation, the present study underestimated the graft weight by - 1.8% on average. A mean difference of - 21.3 g (95% confidence interval: - 55.7 to 13.1, p = 0.211) between the estimated graft weight and the actual graft weight was achieved in this study. The proposed method is effective for clinical application.

Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review

OBJECTIVES

Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging?

METHODS

A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography.

RESULTS

One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy.

CONCLUSION

Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this.

KEY POINTS

• ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.

CT Rule-in and Rule-out Criteria for Clinically Significant Portal Hypertension in Chronic Liver Disease

Background The value of CT in assessment of clinically significant portal hypertension (CSPH) has not been well determined. Purpose To evaluate the performance of CT features that have been associated with portal hypertension for diagnosing CSPH in patients with chronic liver disease (CLD). Materials and Methods This retrospective study included patients with CLD who underwent contrast-enhanced CT and subsequent hepatic venous pressure gradient (HVPG) measurement within 3 months at two tertiary institutions from January 2001 to December 2019. Two readers independently evaluated the presence of gastroesophageal varix, spontaneous portosystemic shunt (SPSS), and ascites on CT images. Splenomegaly at CT was determined using three methods, as follows: personalized or fixed volume criteria, based on spleen volume as measured by a deep learning algorithm, or manually measured spleen diameter. The diagnostic performance of these findings alone or in combination for detecting CSPH (HVPG ≥10 mm Hg) was evaluated. Results A total of 235 patients (mean age, 53.2 years ± 13.0 [SD]; 155 male patients), including 110 (46.8%) with CSPH, were included. Detection of CSPH according to the presence of both splenomegaly and at least one other CT feature (ie, gastroesophageal varix, SPSS, and ascites) achieved specificities of 94.4%-97.6%, whereas detection of CSPH according to the presence of any feature (ie, splenomegaly, gastroesophageal varix, SPSS, or ascites) achieved sensitivities of 94.5%-98.2%. When employing the former as rule-in criteria with the absence of splenomegaly, gastroesophageal varix, SPSS, and ascites as rule-out criteria for CSPH, 171-185 (range, 72.8%-78.7%) of 235 patients were correctly classified as either having CSPH or not, seven to 13 (range, 3%-5.5%) of 235 patients were incorrectly classified, and 42-54 (range, 17.9%-23%) of 235 patients were unclassified. Conclusion The presence or absence of splenomegaly, gastroesophageal varix, SPSS, and/or ascites on CT images may be useful for ruling in and ruling out CSPH in patients with CLD. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Fraum in this issue.

Deep Neural Network Regression to Assist Non-Invasive Diagnosis of Portal Hypertension

Portal hypertension is a complex medical condition characterized by elevated blood pressure in the portal venous system. The conventional diagnosis of such disease often involves invasive procedures such as liver biopsy, endoscopy, or imaging techniques with contrast agents, which can be uncomfortable for patients and carry inherent risks. This study presents a deep neural network method in support of the non-invasive diagnosis of portal hypertension in patients with chronic liver diseases. The proposed method utilizes readily available clinical data, thus eliminating the need for invasive procedures. A dataset composed of standard laboratory parameters is used to train and validate the deep neural network regressor. The experimental results exhibit reasonable performance in distinguishing patients with portal hypertension from healthy individuals. Such performances may be improved by using larger datasets of high quality. These findings suggest that deep neural networks can serve as useful auxiliary diagnostic tools, aiding healthcare professionals in making timely and accurate decisions for patients suspected of having portal hypertension.

The effect of hepatic steatosis on liver volume determined by proton density fat fraction and deep learning-measured liver volume

OBJECTIVES

We aimed to evaluate the effect of hepatic steatosis (HS) on liver volume and to develop a formula to estimate lean liver volume correcting the HS effect.

METHODS

This retrospective study included healthy adult liver donors who underwent gadoxetic acid-enhanced MRI and proton density fat fraction (PDFF) measurement from 2015 to 2019. The degree of HS was graded at 5% PDFF intervals from grade 0 (no HS; PDFF < 5.5%). Liver volume was measured with hepatobiliary phase MRI using deep learning algorithm, and standard liver volume (SLV) was calculated as the reference lean liver volume. The association between liver volume and SLV ratio with PDFF grades was evaluated using Spearman's correlation (ρ). The effect of PDFF grades on liver volume was evaluated using the multivariable linear regression model.

RESULTS

The study population included 1038 donors (mean age, 31 ± 9 years; 689 men). Mean liver volume to SLV ratio increased according to PDFF grades (ρ = 0.234, p < 0.001). The multivariable analysis indicated that SLV (β = 1.004, p < 0.001) and PDFF grade*SLV (β = 0.044, p < 0.001) independently affected liver volume, suggesting a 4.4% increase in liver volume per one-point increment in the PDFF grade. PDFF-adjusted lean liver volume was estimated using the formula, liver volume/[1.004 + 0.044 × PDFF grade]. The mean estimated lean liver volume to SLV ratio approximated to one for all PDFF grades, with no significant association with PDFF grades (p = 0.851).

CONCLUSION

HS increases liver volume. The formula to estimate lean liver volume may be useful to adjust for the effect of HS on liver volume.

KEY POINTS

• Hepatic steatosis increases liver volume. • The presented formula to estimate lean liver volume using MRI-measured proton density fat fraction and liver volume may be useful to adjust for the effect of hepatic steatosis on measured liver volume.

Eldar Y. A Deep-Learning Approach to Spleen Volume Estimation in Patients with Gaucher Disease

The enlargement of the liver and spleen (hepatosplenomegaly) is a common manifestation of Gaucher disease (GD). An accurate estimation of the liver and spleen volumes in patients with GD, using imaging tools such as magnetic resonance imaging (MRI), is crucial for the baseline assessment and monitoring of the response to treatment. A commonly used method in clinical practice to estimate the spleen volume is the employment of a formula that uses the measurements of the craniocaudal length, diameter, and thickness of the spleen in MRI. However, the inaccuracy of this formula is significant, which, in turn, emphasizes the need for a more precise and reliable alternative. To this end, we employed deep-learning techniques, to achieve a more accurate spleen segmentation and, subsequently, calculate the resulting spleen volume with higher accuracy on a testing set cohort of 20 patients with GD. Our results indicate that the mean error obtained using the deep-learning approach to spleen volume estimation is 3.6 ± 2.7%, which is significantly lower than the common formula approach, which resulted in a mean error of 13.9 ± 9.6%. These findings suggest that the integration of deep-learning methods into the clinical routine practice for spleen volume calculation could lead to improved diagnostic and monitoring outcomes.

Clinical impact of artificial intelligence-based solutions on imaging of the pancreas and liver

Artificial intelligence (AI) has experienced substantial progress over the last ten years in many fields of application, including healthcare. In hepatology and pancreatology, major attention to date has been paid to its application to the assisted or even automated interpretation of radiological images, where AI can generate accurate and reproducible imaging diagnosis, reducing the physicians’ workload. AI can provide automatic or semi-automatic segmentation and registration of the liver and pancreatic glands and lesions. Furthermore, using radiomics, AI can introduce new quantitative information which is not visible to the human eye to radiological reports. AI has been applied in the detection and characterization of focal lesions and diffuse diseases of the liver and pancreas, such as neoplasms, chronic hepatic disease, or acute or chronic pancreatitis, among others. These solutions have been applied to different imaging techniques commonly used to diagnose liver and pancreatic diseases, such as ultrasound, endoscopic ultrasonography, computerized tomography (CT), magnetic resonance imaging, and positron emission tomography/CT. However, AI is also applied in this context to many other relevant steps involved in a comprehensive clinical scenario to manage a gastroenterological patient. AI can also be applied to choose the most convenient test prescription, to improve image quality or accelerate its acquisition, and to predict patient prognosis and treatment response. In this review, we summarize the current evidence on the application of AI to hepatic and pancreatic radiology, not only in regard to the interpretation of images, but also to all the steps involved in the radiological workflow in a broader sense. Lastly, we discuss the challenges and future directions of the clinical application of AI methods.

Usefulness of deep learning-based noise reduction for 1.5 T MRI brain images

AIM

To evaluate 1.5 T magnetic resonance imaging (MRI) brain images with denoising procedures using deep learning-based reconstruction (dDLR) relative to the original 1.5 and 3 T images.

MATERIALS AND METHODS

Eleven volunteers underwent MRI at 3 and 1.5 T. Two-dimensional fast spin-echo T2-weighted imaging (T2WI), fluid-attenuated inversion recovery (FLAIR) imaging and diffusion-weighted imaging (DWI) sequences were performed. The dDLR method was applied to the 1.5 T data (dDLR-1.5 T), then the image quality of the dDLR-1.5 T data relative to the original 1.5 T and 3 T data was qualitatively and quantitatively assessed based on the structure similarity (SSIM) index; the signal-to-noise ratios (SNRs) of the grey matter (GM) and white matter (WM); and the contrast-to-noise ratios (CNRs) between the GM and WM (CNRgm-wm) and between the striatum (ST) and WM (CNRst-wm).

RESULTS

The perceived image quality, and SNRs and CNRs were significantly higher for the dDLR-1.5 T images versus the 1.5 T images for all sequences and almost comparable or even superior to those of the 3 T images. For DWI, the SNRs and CNRst-wm were significantly higher for the dDLR-1.5 T images versus the 3 T images.

CONCLUSION

The dDLR technique improved the image quality of 1.5 T brain MRI images. With respect to qualitative and quantitative measurements, the denoised 1.5 T brain images were almost equivalent or even superior to the 3 T brain images.

Noninvasive staging of liver fibrosis: review of current quantitative CT and MRI-based techniques

Liver fibrosis features excessive protein accumulation in the liver interstitial space resulting from repeated tissue injury due to chronic liver disease. Liver fibrosis eventually proceeds to cirrhosis and associated complications. So, early diagnosis and staging of liver fibrosis are of vital importance for clinical treatment. Liver biopsy remains the gold standard for the diagnosing and staging of fibrosis, but it is suboptimal due to various limitations. Recently, efforts have been made to migrate toward noninvasive techniques for assessing liver fibrosis. CT is relatively easy to perform, relatively standardized for different scanners, and does not require additional hardware in liver fibrosis staging. MRI is frequently performed to characterize indeterminate liver lesions. Because it does not use ionizing radiation and features high image contrast, its role has increased in the staging of liver fibrosis. More recently, several studies on liver fibrosis staging using deep learning algorithms in CT or MRI have been proposed and have shown meaningful results. In this review, we summarize the basic concept, diagnostic performance, and advantages and limitations of each technique to noninvasively stage liver fibrosis.

Noncirrhotic Portal Hypertension after Trastuzumab Emtansine in HER2-positive Breast Cancer as Determined by Deep Learning-measured Spleen Volume at CT

Background Trastuzumab emtansine (T-DM1) is an antibody-drug conjugate approved for use in human epidermal growth factor receptor 2 (HER2)-positive breast cancer. Case reports have suggested an association between T-DM1 and portal hypertension. Purpose To evaluate the association of T-DM1 therapy with spleen volume changes and portal hypertension on CT scans and clinical findings compared with lapatinib and capecitabine therapy. Materials and Methods Patients with HER2-positive breast cancer who were administered at least two cycles of T-DM1 or lapatinib and capecitabine (controls) in a tertiary institution from 2001 to 2020 and who underwent CT before initial treatment and at least once during treatment were retrospectively enrolled. Spleen volume changes and the signs of portal hypertension (gastroesophageal varix [GEV], spontaneous portosystemic shunt [SPSS], and ascites) were evaluated at contrast-enhanced CT. Patients were followed until treatment ended or for 2 years after the start of treatment. Spleen volume changes were measured with a deep learning algorithm and evaluated by using a linear mixed model. The incidences of splenomegaly and portal hypertension were compared between the T-DM1 and control groups by using a χ² test or Fisher exact test. Results The T-DM1 group included 111 patients (mean age, 54 years ± 11 [SD]; 111 women) and the control group included 122 patients (mean age, 50 years ± 9; 121 women). Spleen volume progressively increased with T-DM1 therapy but was constant in the control group (104% ± 5 vs -1% ± 6 at the 33rd treatment cycle, respectively; P < .001). Incidences of splenomegaly (46% [51 of 111] vs 3% [four of 122] of patients; P < .001), GEV (11% [12 of 111] vs 1% [one of 122] of patients; P < .001), and SPSS (27% [30 of 111] vs 1% [one of 122] of patients; P < .001) were higher in the T-DM1 group than in the control group. Conclusion Trastuzumab emtansine therapy was associated with noncirrhotic portal hypertension at CT, with higher incidences of splenomegaly, gastroesophageal varix, and spontaneous portosystemic shunt than those with lapatinib and capecitabine therapy. © RSNA, 2022 Online supplemental material is available for this article.

nnU-Net Deep Learning Method for Segmenting Parenchyma and Determining Liver Volume From Computed Tomography Images

Background

Recipient donor matching in liver transplantation can require precise estimations of liver volume. Currently utilized demographic-based organ volume estimates are imprecise and nonspecific. Manual image organ annotation from medical imaging is effective; however, this process is cumbersome, often taking an undesirable length of time to complete. Additionally, manual organ segmentation and volume measurement incurs additional direct costs to payers for either a clinician or trained technician to complete. Deep learning-based image automatic segmentation tools are well positioned to address this clinical need.

Objectives

To build a deep learning model that could accurately estimate liver volumes and create 3D organ renderings from computed tomography (CT) medical images.

Methods

We trained a nnU-Net deep learning model to identify liver borders in images of the abdominal cavity. We used 151 publicly available CT scans. For each CT scan, a board-certified radiologist annotated the liver margins (ground truth annotations). We split our image dataset into training, validation, and test sets. We trained our nnU-Net model on these data to identify liver borders in 3D voxels and integrated these to reconstruct a total organ volume estimate.

Results

The nnU-Net model accurately identified the border of the liver with a mean overlap accuracy of 97.5% compared with ground truth annotations. Our calculated volume estimates achieved a mean percent error of 1.92% + 1.54% on the test set.

Conclusions

Precise volume estimation of livers from CT scans is accurate using a nnU-Net deep learning architecture. Appropriately deployed, a nnU-Net algorithm is accurate and quick, making it suitable for incorporation into the pretransplant clinical decision-making workflow.

Diagnosis of Liver Cirrhosis and Liver Fibrosis by Artificial Intelligence Algorithm-Based Multislice Spiral Computed Tomography

This research was aimed at investigating the artificial intelligence (AI) segmentation algorithm-based multislice spiral computed tomography (MSCT) in the diagnosis of liver cirrhosis and liver fibrosis. Besides, it was aimed at providing new methods for the diagnosis of liver cirrhosis and liver fibrosis. All patients were divided into the control group, mild liver fibrosis group, and significant liver fibrosis group. A total of 112 patients were included, with 40 cases in the mild liver fibrosis group, 48 cases in the significant liver fibrosis group, and 24 cases who underwent computed tomography (CT) examination in the control group. In the research, deconvolution algorithm of AI segmentation algorithm was adopted to process the images. The average hepatic arterial fraction (HAF) values of patients in the control group, mild liver fibrosis group, and severe liver fibrosis group were 17.59 ± 10.03%, 18.23 ± 5.57%, and 20.98 ± 6.63%, respectively. The average MTT values of patients in the control group, mild liver fibrosis group, and severe liver fibrosis group were 12.69 ± 1.78S, 12.53 ± 2.05S, and 12.04 ± 1.57S, respectively. The average blood flow (BF) values of patients in the control group, mild liver fibrosis group, and severe liver fibrosis group were 105.68 ± 15.57 mL 100 g-1·min-1, 116.07 ± 16.5 mL·100 g-1·min-1, and 110.39 ± 16.32 mL·100 g-1·min-1, respectively. Besides, the average blood volume (BV) values of patients in the control group, mild liver fibrosis group, and significant liver fibrosis group were 15.69 ± 4.35 mL·log-1, 16.97 ± 2.68 mL·log-1, and 16.11 ± 4.87 mL·100 g-1, respectively. According to statistics, the differences among the average HAF, MTT, BF, and BV values showed no statistical meaning. AI segmentation algorithm-based MSCT imaging could promote the diagnosis of liver cirrhosis and liver fibrosis effectively and offer new methods to clinical diagnosis of liver cirrhosis and liver fibrosis.

Accuracy and Efficiency of Right-Lobe Graft Weight Estimation Using Deep-Learning-Assisted CT Volumetry for Living-Donor Liver Transplantation

CT volumetry (CTV) has been widely used for pre-operative graft weight (GW) estimation in living-donor liver transplantation (LDLT), and the use of a deep-learning algorithm (DLA) may further improve its efficiency. However, its accuracy has not been well determined. To evaluate the efficiency and accuracy of DLA-assisted CTV in GW estimation, we performed a retrospective study including 581 consecutive LDLT donors who donated a right-lobe graft. Right-lobe graft volume (GV) was measured on CT using the software implemented with the DLA for automated liver segmentation. In the development group (n = 207), a volume-to-weight conversion formula was constructed by linear regression analysis between the CTV-measured GV and the intraoperative GW. In the validation group (n = 374), the agreement between the estimated and measured GWs was assessed using the Bland–Altman 95% limit-of-agreement (LOA). The mean process time for GV measurement was 1.8 ± 0.6 min (range, 1.3–8.0 min). In the validation group, the GW was estimated using the volume-to-weight conversion formula (estimated GW [g] = 206.3 + 0.653 × CTV-measured GV [mL]), and the Bland–Altman 95% LOA between the estimated and measured GWs was −1.7% ± 17.1%. The DLA-assisted CT volumetry allows for time-efficient and accurate estimation of GW in LDLT.

Evaluation of AI-Based Segmentation Tools for COVID-19 Lung Lesions on Conventional and Ultra-low Dose CT Scans

A reliable diagnosis and accurate monitoring are pivotal steps for treatment and prevention of COVID-19. Chest computed tomography (CT) has been considered a crucial diagnostic imaging technique for the injury assessment of the viral pneumonia. Furthermore, the automatization of the segmentation methods for lung alterations helps to speed up the diagnosis and lighten radiologists' workload. Considering the assiduous pathology monitoring, ultra-low dose (ULD) chest CT protocols have been implemented to drastically reduce the radiation burden. Unfortunately, the available AI technologies have not been trained on ULD-CT data and validated and their applicability deserves careful evaluation. Therefore, this work aims to compare the results of available AI tools (BCUnet, CORADS AI, NVIDIA CLARA Train SDK and CT Pneumonia Analysis) on a dataset of 73 CT examinations acquired both with conventional dose (CD) and ULD protocols. COVID-19 volume percentage, resulting from each tool, was statistically compared. This study demonstrated high comparability of the results on CD-CT and ULD-CT data among the four AI tools, with high correlation between the results obtained on both protocols (R > .68, P < .001, for all AI tools).

Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen

The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively (p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 (p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen.

Spleen Size and Thrombocytopenia After Transcatheter Aortic Valve Implantation

The pathophysiology of thrombocytopenia after transcatheter aortic valve implantation (TAVI) thrombocytopenia is still poorly understood. We assessed the association of spleen size with acquired thrombocytopenia in patients undergoing TAVI. We included 732 patients who underwent TAVI with new generation transcatheter heart valves (THVs) at our center from February 2016 to July 2019. We measured splenic volume index in consecutive patients derived from multidetector row computed tomographic datasets. Patients were stratified according to post-TAVI thrombocytopenia, which was defined as a decline in platelet count (DPC) ≥50% at nadir, and evaluated regarding baseline characteristics and outcome parameters. After the procedure, platelet counts declined from 212.9 ± 67.4 × 10⁹/L at baseline to 138.8 ± 49.8 × 10⁹/L at nadir after a median of 2 days (interquartile range [IQR] 2 to 3). Of all patients, 10.1% showed a DPC ≥50%. Compared with patients with DPC <50%, patients with DPC ≥50% had significantly lower splenic volume index (95.5 ml/m² [IQR 78.0 to 123.7] vs 85.8 ml/m² [IQR 71.4 to 102.6], p = 0.008). A multivariable analysis revealed that the splenic volume index was negatively associated with a DPC ≥50% (OR 0.89, 95% CI 0.82 to 0.97, p = 0.005), independent of the type of THV (balloon-expandable THV: OR 2.06, 95% CI 1.13 to 3.76, p = 0.02), major bleeding (OR 13.40, 95% CI 3.58 to 50.40, p <0.001), blood transfusion (OR 3.63, 95% CI 1.54 to 8.56, p = 0.003), or postprocedural paravalvular leakage ≥moderate (OR 5.48, 95% CI 1.23 to 24.40, p = 0.03). Furthermore, DPC ≥50% was independently associated with 1-year mortality (HR 3.36, 95% CI 1.66 to 6.81, p <0.001). In conclusion, acquired thrombocytopenia remains prevalent in modern TAVI patients. Spleen size appears to be associated with the occurrence of thrombocytopenia after TAVI, which is independently correlated with 1-year mortality.

M3Net: A multi-scale multi-view framework for multi-phase pancreas segmentation based on cross-phase non-local attention

The complementation of arterial and venous phases visual information of CTs can help better distinguish the pancreas from its surrounding structures. However, the exploration of cross-phase contextual information is still under research in computer-aided pancreas segmentation. This paper presents M³Net, a framework that integrates multi-scale multi-view information for multi-phase pancreas segmentation. The core of M³Net is built upon a dual-path network in which individual branches are set up for two phases. Cross-phase interactive connections bridging the two branches are introduced to interleave and integrate dual-phase complementary visual information. Besides, we further devise two types of non-local attention modules to enhance the high-level feature representation across phases. First, we design a location attention module to generate cross-phase reliable feature correlations to suppress the misalignment regions. Second, the depth-wise attention module is used to capture the channel dependencies and then strengthen feature representations. The experiment data consists of 224 internal CTs (106 normal and 118 abnormal) with 1 mm slice thickness, and 66 external CTs (29 normal and 37 abnormal) with 5 mm slice thickness. We achieve new state-of-the-art performance with average DSC of 91.19% on internal data, and promising result with average DSC of 86.34% on external data.

Liver-to-Spleen Volume Ratio Automatically Measured on CT Predicts Decompensation in Patients with B Viral Compensated Cirrhosis

Objective

Although the liver-to-spleen volume ratio (LSVR) based on CT reflects portal hypertension, its prognostic role in cirrhotic patients has not been proven. We evaluated the utility of LSVR, automatically measured from CT images using a deep learning algorithm, as a predictor of hepatic decompensation and transplantation-free survival in patients with hepatitis B viral (HBV)-compensated cirrhosis.

Materials and Methods

A deep learning algorithm was used to measure the LSVR in a cohort of 1027 consecutive patients (mean age, 50.5 years; 675 male and 352 female) with HBV-compensated cirrhosis who underwent liver CT (2007–2010). Associations of LSVR with hepatic decompensation and transplantation-free survival were evaluated using multivariable Cox proportional hazards and competing risk analyses, accounting for either the Child-Pugh score (CPS) or Model for End Stage Liver Disease (MELD) score and other variables. The risk of the liver-related events was estimated using Kaplan-Meier analysis and the Aalen-Johansen estimator.

Results

After adjustment for either CPS or MELD and other variables, LSVR was identified as a significant independent predictor of hepatic decompensation (hazard ratio for LSVR increase by 1, 0.71 and 0.68 for CPS and MELD models, respectively; p < 0.001) and transplantation-free survival (hazard ratio for LSVR increase by 1, 0.8 and 0.77, respectively; p < 0.001). Patients with an LSVR of < 2.9 (n = 381) had significantly higher 3-year risks of hepatic decompensation (16.7% vs. 2.5%, p < 0.001) and liver-related death or transplantation (10.0% vs. 1.1%, p < 0.001) than those with an LSVR ≥ 2.9 (n = 646). When patients were stratified according to CPS (Child-Pugh A vs. B–C) and MELD (< 10 vs. ≥ 10), an LSVR of < 2.9 was still associated with a higher risk of liver-related events than an LSVR of ≥ 2.9 for all Child-Pugh (p ≤ 0.045) and MELD (p ≤ 0.009) stratifications.

Conclusion

The LSVR measured on CT can predict hepatic decompensation and transplantation-free survival in patients with HBV-compensated cirrhosis.

Population-based and Personalized Reference Intervals for Liver and Spleen Volumes in Healthy Individuals and Those with Viral Hepatitis

Background Reference intervals guiding volumetric assessment of the liver and spleen have yet to be established. Purpose To establish population-based and personalized reference intervals for liver volume, spleen volume, and liver-to-spleen volume ratio (LSVR). Materials and Methods This retrospective study consecutively included healthy adult liver donors from 2001 to 2013 (reference group) and from 2014 to 2016 (healthy validation group) and patients with viral hepatitis from 2007 to 2017. Liver volume, spleen volume, and LSVR were measured with CT by using a deep learning algorithm. In the reference group, the reference intervals for the volume indexes were determined by using the population-based (ranges encompassing the central 95% of donors) and personalized (quantile regression modeling of the 2.5th and 97.5th percentiles as a function of age, sex, height, and weight) approaches. The validity of the reference intervals was evaluated in the healthy validation group and the viral hepatitis group. Results The reference and healthy validation groups had 2989 donors (mean age ± standard deviation, 30 years ± 9; 1828 men) and 472 donors (mean age, 30 years ± 9; 334 men), respectively. The viral hepatitis group had 158 patients (mean age, 48 years ± 12; 95 men). The population-based reference intervals were 824.5-1700.0 cm³ for liver volume, 81.1-322.0 cm³ for spleen volume, and 3.96-13.78 for LSVR. Formulae and a web calculator (https://i-pacs.com/calculators) were presented to calculate the personalized reference intervals. In the healthy validation group, both the population-based and personalized reference intervals were used to classify the volume indexes of 94%-96% of the donors as falling within the reference interval. In the viral hepatitis group, when compared with the population-based reference intervals, the personalized reference intervals helped identify more patients with volume indexes outside the reference interval (liver volume, 21.5% [34 of 158] vs 13.3% [21 of 158], P = .01; spleen volume, 29.1% [46 of 158] vs 22.2% [35 of 158], P = .01; LSVR, 35.4% [56 of 158] vs 26.6% [42 of 158], P < .001). Conclusion Reference intervals derived from a deep learning approach in healthy adults may enable evidence-based assessments of liver and spleen volume in clinical practice. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Ringl in this issue.

Identifying Periampullary Regions in MRI Images Using Deep Learning

Background

Development and validation of a deep learning method to automatically segment the peri-ampullary (PA) region in magnetic resonance imaging (MRI) images.

Methods

A group of patients with or without periampullary carcinoma (PAC) was included. The PA regions were manually annotated in MRI images by experts. Patients were randomly divided into one training set, one validation set, and one test set. Deep learning methods were developed to automatically segment the PA region in MRI images. The segmentation performance of the methods was compared in the validation set. The model with the highest intersection over union (IoU) was evaluated in the test set.

Results

The deep learning algorithm achieved optimal accuracies in the segmentation of the PA regions in both T1 and T2 MRI images. The value of the IoU was 0.68, 0.68, and 0.64 for T1, T2, and combination of T1 and T2 images, respectively.

Conclusions

Deep learning algorithm is promising with accuracies of concordance with manual human assessment in segmentation of the PA region in MRI images. This automated non-invasive method helps clinicians to identify and locate the PA region using preoperative MRI scanning.

An Overview of Artificial Intelligence Applications in Liver and Pancreatic Imaging

Artificial intelligence (AI) is one of the most promising fields of research in medical imaging so far. By means of specific algorithms, it can be used to help radiologists in their routine workflow. There are several papers that describe AI approaches to solve different problems in liver and pancreatic imaging. These problems may be summarized in four different categories: segmentation, quantification, characterization and image quality improvement. Segmentation is usually the first step of successive elaborations. If done manually, it is a time-consuming process. Therefore, the semi-automatic and automatic creation of a liver or a pancreatic mask may save time for other evaluations, such as quantification of various parameters, from organs volume to their textural features. The alterations of normal liver and pancreas structure may give a clue to the presence of a diffuse or focal pathology. AI can be trained to recognize these alterations and propose a diagnosis, which may then be confirmed or not by radiologists. Finally, AI may be applied in medical image reconstruction in order to increase image quality, decrease dose administration (referring to computed tomography) and reduce scan times. In this article, we report the state of the art of AI applications in these four main categories.

What's New in Hepatic Steatosis

Hepatic steatosis can lead to liver cancer, cirrhosis, and portal hypertension. There are two main types, non-alcoholic fatty liver disease (NAFLD) and alcoholic liver disease. The detection and quantification of hepatic steatosis with lifestyle changes can slow the evolution from NAFLD to steatohepatitis. Currently, the gold standard for the quantification of fat in the liver is biopsy, has some limitations. Hepatic steatosis is frequently detected during cross sectional imaging. Ultrasound (US), Computed Tomography (CT), and Magnetic Resonance Imaging (MRI) provide noninvasive assessment of liver parenchyma and can detect fat infiltration in the liver. However, the non-invasive quantification of hepatic steatosis by imaging has been challenging. Recent MRI techniques show great promise in the detection and quantification of liver fat. The aim of this article is to review the utilization of non-invasive imaging modalities for the detection and quantification of hepatic steatosis, to evaluate their advantages and limitations.

Artificial intelligence in precision medicine in hepatology

The advancement of investigation tools and electronic health records (EHR) enables a paradigm shift from guideline-specific therapy toward patient-specific precision medicine. The multiparametric and large detailed information necessitates novel analyses to explore the insight of diseases and to aid the diagnosis, monitoring, and outcome prediction. Artificial intelligence (AI), machine learning, and deep learning (DL) provide various models of supervised, or unsupervised algorithms, and sophisticated neural networks to generate predictive models more precisely than conventional ones. The data, application tasks, and algorithms are three key components in AI. Various data formats are available in daily clinical practice of hepatology, including radiological imaging, EHR, liver pathology, data from wearable devices, and multi-omics measurements. The images of abdominal ultrasonography, computed tomography, and magnetic resonance imaging can be used to predict liver fibrosis, cirrhosis, non-alcoholic fatty liver disease (NAFLD), and differentiation of benign tumors from hepatocellular carcinoma (HCC). Using EHR, the AI algorithms help predict the diagnosis and outcomes of liver cirrhosis, HCC, NAFLD, portal hypertension, varices, liver transplantation, and acute liver failure. AI helps to predict severity and patterns of fibrosis, steatosis, activity of NAFLD, and survival of HCC by using pathological data. Despite of these high potentials of AI application, data preparation, collection, quality, labeling, and sampling biases of data are major concerns. The selection, evaluation, and validation of algorithms, as well as real-world application of these AI models, are also challenging. Nevertheless, AI opens the new era of precision medicine in hepatology, which will change our future practice.

Radiomics and deep learning in liver diseases

Recently, radiomics and deep learning have gained attention as methods for computerized image analysis. Radiomics and deep learning can perform diagnostic or predictive tasks using high-dimensional image-derived features and have the potential to expand the capabilities of liver imaging beyond the scope of traditional visual image analysis. Recent research has demonstrated the potential of these techniques in various fields of liver imaging, including staging of liver fibrosis, prognostication of malignant liver tumors, automated detection and characterization of liver tumors, automated abdominal organ segmentation, and body composition analysis. However, because most of the previous studies were preliminary and focused mainly on technical feasibility, further clinical validation is required for the application of radiomics and deep learning in clinical practice. In this review, we introduce the technical aspects of radiomics and deep learning and summarize the recent studies on the application of these techniques in liver radiology.

An index based on deep learning-measured spleen volume on CT for the assessment of high-risk varix in B-viral compensated cirrhosis

OBJECTIVES

Deep learning enables an automated liver and spleen volume measurements on CT. The purpose of this study was to develop an index combining liver and spleen volumes and clinical factors for detecting high-risk varices in B-viral compensated cirrhosis.

METHODS

This retrospective study included 419 patients with B-viral compensated cirrhosis who underwent endoscopy and CT from 2007 to 2008 (derivation cohort, n = 239) and from 2009 to 2010 (validation cohort, n = 180). The liver and spleen volumes were measured on CT images using a deep learning algorithm. Multivariable logistic regression analysis of the derivation cohort developed an index to detect endoscopically confirmed high-risk varix. The cumulative 5-year risk of varix bleeding was evaluated with patients stratified by their index values.

RESULTS

The index of spleen volume-to-platelet ratio was devised from the derivation cohort. In the validation cohort, the cutoff index value for balanced sensitivity and specificity (> 3.78) resulted in the sensitivity of 69.4% and the specificity of 78.5% for detecting high-risk varix, and the cutoff index value for high sensitivity (> 1.63) detected all high-risk varices. The index stratified all patients into the low (index value ≤ 1.63; n = 118), intermediate (n = 162), and high (index value > 3.78; n = 139) risk groups with cumulative 5-year incidences of varix bleeding of 0%, 1.0%, and 12.0%, respectively (p < .001).

CONCLUSION

The spleen volume-to-platelet ratio obtained using deep learning-based CT analysis is useful to detect high-risk varices and to assess the risk of varix bleeding.

KEY POINTS

• The criterion of spleen volume to platelet > 1.63 detected all high-risk varices in the validation cohort, while the absence of visible varix did not exclude all high-risk varices. • Visual varix grade ≥ 2 detected high-risk varix with a high specificity (96.5-100%). • Combining spleen volume-to-platelet ratio ≤ 1.63 and visual varix grade of 0 identified low-risk patients who had no high-risk varix and varix bleeding on 5-year follow-up.