MRgRT real-time target localization using foundation models for contour point tracking and promptable mask refinement DOI Creative Commons

T. Blöcker,

Elia Lombardo, Sebastian Marschner

и другие.

Physics in Medicine and Biology, Год журнала: 2024, Номер 70(1), С. 015004 - 015004

Опубликована: Дек. 11, 2024

Abstract Objective . This study aimed to evaluate two real-time target tracking approaches for magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) based on foundation artificial intelligence models. Approach The first approach used a point-tracking model that propagates points from reference contour. second video-object-segmentation model, segment anything 2 (SAM2). Both were evaluated and compared against each other, inter-observer variability, transformer-based image registration TransMorph, with without patient-specific (PS) fine-tuning. evaluation was carried out 2D cine MRI datasets institutions, containing scans 33 patients 8060 labeled frames, annotations 5 observers per frame, totaling 29179 ground truth segmentations. segmentations produced assessed using the Dice similarity coefficient (DSC), 50% 95% Hausdorff distances (HD50 / HD95), Euclidean center distance (ECD). Main results showed contour (median DSC 0.92 ± 0.04 ECD 1.9 1.0 mm) SAM2-based 0.93 0.03 1.6 1.1 comparable or superior TransMorph w/o PS fine-tuning 0.91 0.07 2.6 1.4 slightly inferior w/ 0.94 0.8 mm). Between novel approaches, one SAM2 performed marginally better at higher computational cost (inference times 92 ms 109 SAM2). exceeded variability 0.90 0.06 1.7 0.7 Significance demonstrates potential of models achieve high-quality in MRgRT, offering performance matches state-of-the-art methods requiring

Язык: Английский

A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities DOI

Theodore Zhao,

裕二 池谷, Jianwei Yang

и другие.

Nature Methods, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 18, 2024

Язык: Английский

Процитировано

15

PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts DOI
Hao Li, Han Liu, Dewei Hu

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 389 - 399

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

3

Filters, Thresholds, and Geodesic Distances for Scribble-Based Interactive Segmentation of Medical Images DOI
Zdravko Marinov, Alexander Jaus, Jens Kleesiek

и другие.

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 39 - 56

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

BATseg: Boundary-Aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans DOI
Hua Song, Zi‐Hui Zhang,

Yanpeng Zhou

и другие.

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 172 - 188

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

P2ED: A four-quadrant framework for progressive prompt enhancement in 3D interactive medical imaging segmentation DOI

Allan Chang,

Tao Xing, Yuhao Huang

и другие.

Neural Networks, Год журнала: 2024, Номер 183, С. 106973 - 106973

Опубликована: Дек. 3, 2024

Язык: Английский

Процитировано

1

Interactive Segmentation Model for Placenta Segmentation from 3D Ultrasound Images DOI
Hao Li, Baris Oguz,

Gabriel Arenas

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 132 - 142

Опубликована: Окт. 4, 2024

Язык: Английский

Процитировано

0

MRgRT real-time target localization using foundation models for contour point tracking and promptable mask refinement DOI Creative Commons

T. Blöcker,

Elia Lombardo, Sebastian Marschner

и другие.

Physics in Medicine and Biology, Год журнала: 2024, Номер 70(1), С. 015004 - 015004

Опубликована: Дек. 11, 2024

Abstract Objective . This study aimed to evaluate two real-time target tracking approaches for magnetic resonance imaging (MRI) guided radiotherapy (MRgRT) based on foundation artificial intelligence models. Approach The first approach used a point-tracking model that propagates points from reference contour. second video-object-segmentation model, segment anything 2 (SAM2). Both were evaluated and compared against each other, inter-observer variability, transformer-based image registration TransMorph, with without patient-specific (PS) fine-tuning. evaluation was carried out 2D cine MRI datasets institutions, containing scans 33 patients 8060 labeled frames, annotations 5 observers per frame, totaling 29179 ground truth segmentations. segmentations produced assessed using the Dice similarity coefficient (DSC), 50% 95% Hausdorff distances (HD50 / HD95), Euclidean center distance (ECD). Main results showed contour (median DSC 0.92 ± 0.04 ECD 1.9 1.0 mm) SAM2-based 0.93 0.03 1.6 1.1 comparable or superior TransMorph w/o PS fine-tuning 0.91 0.07 2.6 1.4 slightly inferior w/ 0.94 0.8 mm). Between novel approaches, one SAM2 performed marginally better at higher computational cost (inference times 92 ms 109 SAM2). exceeded variability 0.90 0.06 1.7 0.7 Significance demonstrates potential of models achieve high-quality in MRgRT, offering performance matches state-of-the-art methods requiring

Язык: Английский

Процитировано

0