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

MRISegmenter: A Fully Accurate and Robust Automated Multiorgan and Structure Segmentation Tool for T1-weighted Abdominal MRI

Background There is a pressing demand to develop an automated segmentation tool for abdominal MRI that can provide accurate and robust segmentation in more than 60 abdominal organs and structures. Purpose To develop and evaluate the accuracy and robustness of an automated multiorgan and structure segmentation tool for T1-weighted abdominal MRI. Materials and Methods In this retrospective study, a T1-weighted abdominal MRI dataset composed of axial precontrast T1-weighted and contrast-enhanced T1-weighted arterial, portal venous, and delayed phases for each patient in a randomly selected sample was included at the National Institutes of Health Clinical Center. Each MRI series contained voxel-level annotations of 62 abdominal organs and structures. A three-dimensional segmentation (nnU-Net) model, called MRISegmenter, was trained on this dataset. This internal dataset was then randomly split into training and internal test sets. Evaluation was conducted on the internal test set and two external test sets (Abdominal Multi-Organ Segmentation Challenge 2022 [AMOS22] and Duke Liver). The predicted segmentations were compared against the radiologist-verified reference standard annotations using means ± SDs for the Dice similarity coefficient (Dice score) and normalized surface distance (NSD). The segmentation tool and dataset are publicly available at https://github.com/rsummers11/MRISegmenter. Results A total of 195 patients (training set, 135 patients [mean age, 54.7 years ± 16.3 {SD}; 72 male patients, 63 female patients]; internal test set, 60 patients [mean age, 51.1 years ± 14.4; 26 male patients, 34 female patients]) with 780 MRI scans containing 62 annotations each were included. On the internal test set, MRISegmenter achieved a mean Dice score of 0.861 ± 0.118 and a mean NSD of 0.924 ± 0.073. On external test sets AMOS22 (60 MRI scans) and Duke Liver (95 patients; 172 MRI scans), MRISegmenter attained a mean Dice score of 0.829 ± 0.133 and a mean NSD of 0.908 ± 0.067 and a mean Dice score of 0.933 ± 0.015 and a mean NSD of 0.929 ± 0.021, respectively. Conclusion MRISegmenter provided accurate and robust segmentation of 62 organs and structures at T1-weighted abdominal MRI. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Murphy in this issue.

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.

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.

Classification of Multi-Parametric Body MRI Series Using Deep Learning

Multi-parametric magnetic resonance imaging (mpMRI) exams have various series types acquired with different imaging protocols. The DICOM headers of these series often have incorrect information due to the sheer diversity of protocols and occasional technologist errors. To address this, we present a deep learning-based classification model to classify 8 different body mpMRI series types so that radiologists read the exams efficiently. Using mpMRI data from various institutions, multiple deep learning-based classifiers of ResNet, EfficientNet, and DenseNet are trained to classify 8 different MRI series, and their performance is compared. Then, the best-performing classifier is identified, and its classification capability under the setting of different training data quantities is studied. Also, the model is evaluated on the out-of-training-distribution datasets. Moreover, the model is trained using mpMRI exams obtained from different scanners in two training strategies, and its performance is tested. Experimental results show that the DenseNet-121 model achieves the highest F1-score and accuracy of 0.966 and 0.972 over the other classification models with p-value 0.05. The model shows greater than 0.95 accuracy when trained with over 729 studies of the training data, whose performance improves as the training data quantities grow larger. On the external data with the DLDS and CPTAC-UCEC datasets, the model yields 0.872 and 0.810 accuracy for each. These results indicate that in both the internal and external datasets, the DenseNet-121 model attains high accuracy for the task of classifying 8 body MRI series types.

AI-Generated Annotations Dataset for Diverse Cancer Radiology Collections in NCI Image Data Commons

The National Cancer Institute (NCI) Image Data Commons (IDC) offers publicly available cancer radiology collections for cloud computing, crucial for developing advanced imaging tools and algorithms. Despite their potential, these collections are minimally annotated; only 4% of DICOM studies in collections considered in the project had existing segmentation annotations. This project increases the quantity of segmentations in various IDC collections. We produced high-quality, AI-generated imaging annotations dataset of tissues, organs, and/or cancers for 11 distinct IDC image collections. These collections contain images from a variety of modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). The collections cover various body parts, such as the chest, breast, kidneys, prostate, and liver. A portion of the AI annotations were reviewed and corrected by a radiologist to assess the performance of the AI models. Both the AI's and the radiologist's annotations were encoded in conformance to the Digital Imaging and Communications in Medicine (DICOM) standard, allowing for seamless integration into the IDC collections as third-party analysis collections. All the models, images and annotations are publicly accessible.

Automated selection of abdominal MRI series using a DICOM metadata classifier and selective use of a pixel-based classifier

Accurate, automated MRI series identification is important for many applications, including display ("hanging") protocols, machine learning, and radiomics. The use of the series description or a pixel-based classifier each has limitations. We demonstrate a combined approach utilizing a DICOM metadata-based classifier and selective use of a pixel-based classifier to identify abdominal MRI series. The metadata classifier was assessed alone as Group metadata and combined with selective use of the pixel-based classifier for predictions with less than 70% certainty (Group combined). The overall accuracy (mean and 95% confidence intervals) for Groups metadata and combined on the test dataset were 0.870 CI (0.824,0.912) and 0.930 CI (0.893,0.963), respectively. With this combined metadata and pixel-based approach, we demonstrate accurate classification of 95% or greater for all pre-contrast MRI series and improved performance for some post-contrast series.

Training robust T1-weighted magnetic resonance imaging liver segmentation models using ensembles of datasets with different contrast protocols and liver disease etiologies

Image segmentation of the liver is an important step in treatment planning for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a generalizable deep learning model to segment the liver on T1-weighted MR images. In particular, three distinct deep learning architectures (nnUNet, PocketNet, Swin UNETR) were considered using data gathered from six geographically different institutions. A total of 819 T1-weighted MR images were gathered from both public and internal sources. Our experiments compared each architecture's testing performance when trained both intra-institutionally and inter-institutionally. Models trained using nnUNet and its PocketNet variant achieved mean Dice-Sorensen similarity coefficients>0.9 on both intra- and inter-institutional test set data. The performance of these models suggests that nnUNet and PocketNet liver segmentation models trained on a large and diverse collection of T1-weighted MR images would on average achieve good intra-institutional segmentation performance.

AUTOMATED CLASSIFICATION OF MULTI-PARAMETRIC BODY MRI SERIES

Multi-parametric MRI (mpMRI) studies are widely available in clinical practice for the diagnosis of various diseases. As the volume of mpMRI exams increases yearly, there are concomitant inaccuracies that exist within the DICOM header fields of these exams. This precludes the use of the header information for the arrangement of the different series as part of the radiologist's hanging protocol, and clinician oversight is needed for correction. In this pilot work, we propose an automated framework to classify the type of 8 different series in mpMRI studies. We used 1,363 studies acquired by three Siemens scanners to train a DenseNet-121 model with 5-fold cross-validation. Then, we evaluated the performance of the DenseNet-121 ensemble on a held-out test set of 313 mpMRI studies. Our method achieved an average precision of 96.6%, sensitivity of 96.6%, specificity of 99.6%, and F 1 score of 96.6% for the MRI series classification task. To the best of our knowledge, we are the first to develop a method to classify the series type in mpMRI studies acquired at the level of the chest, abdomen, and pelvis. Our method has the capability for robust automation of hanging protocols in modern radiology practice.

Training Robust T1-Weighted Magnetic Resonance Imaging Liver Segmentation Models Using Ensembles of Datasets with Different Contrast Protocols and Liver Disease Etiologies

Image segmentation of the liver is an important step in several treatments for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a deep learning model to segment the liver on T1w MR images. We sought to determine the best architecture by training, validating, and testing three different deep learning architectures using a total of 819 T1w MR images gathered from six different datasets, both publicly and internally available. Our experiments compared each architecture's testing performance when trained on data from the same dataset via 5-fold cross validation to its testing performance when trained on all other datasets. Models trained using nnUNet achieved mean Dice-Sorensen similarity coefficients > 90% when tested on each of the six datasets individually. The performance of these models suggests that an nnUNet liver segmentation model trained on a large and diverse collection of T1w MR images would be robust to potential changes in contrast protocol and disease etiology.