REVIEW 13 cited by
TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Since the introduction of TotalSegmentator CT, there is demand for a similar robust automated MRI segmentation tool that can be applied across all MRI sequences and anatomic structures. In this retrospective study, a nnU-Net model (TotalSegmentator) was trained on MRI and CT examinations to segment 80 anatomic structures relevant for use cases such as organ volumetry, disease characterization, surgical planning and opportunistic screening. Examinations were randomly sampled from routine clinical studies to represent real-world examples. Dice scores were calculated between the predicted segmentations and expert radiologist reference standard segmentations to evaluate model performance on an internal test set, two external test sets and against two publicly available models, and TotalSegmentator CT. The model was applied to an internal dataset containing abdominal MRIs to investigate age-dependent volume changes. A total of 1143 examinations (616 MRIs, 527 CTs) (median age 61 years, IQR 50-72) were split into training (n=1088, CT and MRI) and an internal test set (n=55; only MRI), two external test sets (AMOS, n=20; CHAOS, n=20; only MRI), and an internal aging-study dataset of 8672 abdominal MRIs (median age 59 years, IQR 45-70) were included. The model showed a Dice Score of 0.839 on the internal test set and outperformed two other models (Dice Score, 0.862 versus 0.759; and 0.838 versus 0.560; p<.001 for both). The proposed open-source, easy-to-use model allows for automatic, robust segmentation of 80 structures, extending the capabilities of TotalSegmentator to MRIs of any sequence. The ready-to-use online tool is available at https://totalsegmentator.com, the model at https://github.com/wasserth/TotalSegmentator, and the dataset at https://zenodo.org/records/14710732.
Forward citations
Cited by 13 Pith papers
-
DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
A new five-level medical imaging benchmark, DrVD-Bench, shows that vision-language models lose accuracy sharply as reasoning complexity grows and often diagnose without grounding in lesion evidence.
-
SLIP: Segmentation with Low-latency Interactive Prompting for 3D Medical Images
SLIP decouples image encoding from prompt refinement via a patch memory bank, achieving 0.06s latency and reversible prompting for interactive 3D medical segmentation.
-
Depth to Anatomy: Organ Localization from Depth Images for Automated Patient Table Positioning in Radiology Workflow
A hybrid 2D-to-3D CNN localizes 41 anatomical structures volumetrically from a single depth image, reaching mean Dice 0.44–0.48 on synthetic MRI-derived data.
-
Curia: A Multi-Modal Foundation Model for Radiology
A DINOv2 vision transformer pre-trained on 200M unlabeled CT/MRI slices matches or beats prior foundation models and radiology residents on a new 19-task benchmark.
-
Large-scale Multi-sequence Pretraining for Generalizable MRI Analysis in Versatile Clinical Applications
A four-objective self-supervised pretraining recipe on a 336k-volume multi-sequence MRI corpus yields first-rank transfer on 39 of 44 downstream MRI tasks.
-
Rethink Domain Generalization in Heterogeneous Sequence MRI Segmentation
A semi-supervised pretraining method improves cross-sequence pancreas segmentation Dice from 43.55% to 70.39% (NU) and from 35.62% to 66.61% (IH) on the new PancreasDG benchmark.
-
Adaptive Particle-Based Shape Modeling for Anatomical Surface Correspondence
A neighborhood correspondence loss and a geodesic correction algorithm let particle-based shape models adapt to local geometry while preserving cross-shape correspondence, matching or beating PSM at half the particle count.
-
Structure-aware Semantic Discrepancy and Consistency for 3D Medical Image Self-supervised Learning
S2DC combines dual-softmax patch correspondence with Sharpe-ratio-weighted structural consistency to learn structure-aware representations for 3D medical image self-supervised learning.
-
BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
Splitting the background into anatomical sub-classes during training improves small-lesion segmentation in medical images across architectures and datasets.
-
Spatial-Aware Self-Supervision for Medical 3D Imaging with Multi-Granularity Observable Tasks
A 3D medical self-supervised pretraining method trains on physical spatial relationships between image sub-regions, and visualizes the learned anatomical layout.
-
Benchmarking of Deep Learning Methods for Generic MRI Multi-Organ Abdominal Segmentation
In a head-to-head benchmark on three public MRI datasets, MRSegmentator was the most accurate and generalizable abdominal multi-organ segmentation tool, and ABDSynth, trained only on CT segmentations, proved a viable ...
-
A Comprehensive Pipeline for Aortic Segmentation and Shape Analysis
An MRI aortic pipeline with nnUNet segmentation, mesh reconstruction, and gradient-descent registration produces a 599-subject healthy shape model with reported PCA modes.
-
Diffusion-Assisted Frequency Attention Model for Whole-body Low-field MRI Reconstruction
A diffusion-assisted frequency attention network reconstructs whole-body low-field MRI from undersampled data, using a compressed 1D feature vector and wavelet attention.
Discussion (0). Continue with ORCID to comment.