Automatic self-gated 4D-MRI construction from free-breathing 2D acquisitions applied on liver images

Romaguera, Liset Vázquez; Olofsson, Nils; Plantefève, Rosalie; Lugez, Elodie; Guise, Jacques A. de; Kadoury, Samuel

doi:10.1007/s11548-019-01941-1

Cited by 10 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 10%-30% of liver cancers with negative AFP test, the sensitivity and specificity of AFP-L3 were 41.5% and 85.1%, suggesting that AFP-L3 may potentiate the AFP test efficiency [ 24 ]. GP-73 is a type 2 Golgi transmembrane glycoprotein that has been reported to yield a higher sensitivity of 77.4-86.3% but a lower specificity than AFP assay in the early diagnosis of primary liver cancer [ 25 ]. Herein, the diagnostic accuracy of the experimental group (73/75, 95%) was significantly higher than that of the control group (76/85, 86%).…”

Section: Discussionmentioning

confidence: 99%

Magnetic Resonance Imaging and Serum AFP-L3 and GP-73 in the Diagnosis of Primary Liver Cancer

Yuan

Xu²,

et al. 2022

Journal of Oncology

View full text Add to dashboard Cite

Objective. To investigate the combined application value of magnetic resonance imaging (MRI) combined with serum alpha-fetoprotein (AFP)-L3 and Golgi protein (GP)-73 in the diagnosis of primary liver cancer. Methods. The data of 200 patients with suspected liver cancer admitted to our hospital from February 2020 to February 2021 were retrospectively analyzed, and they were randomly divided into an experimental group and a control group, with 100 cases in each group. The experimental group received a combined detection of MRI with serum AFP-L3 and GP-73, and the control group adopted traditional diagnostic methods (spiral computed tomography and serum AFP). The diagnostic yields of the two groups were compared. Surgical resection was performed after the diagnosis of primary liver cancer, and the correlation between the efficacy and combined detection of MRI with serum AFP-L3 and GP-73 levels was analyzed. Results. The two groups presented comparable general information (P >0.05). The surgical results showed 160 cases of primary liver cancer, including 75 cases in the experimental group and 85 cases in the control group, and 40 cases of benign liver lesions. The diagnostic accuracy of the experimental group (73/75, 95%) was significantly higher than that of the control group (76/85, 86%) ( P < 0.05 ). The serum levels of AFP-L3, GP-73, and AFP in patients with primary liver cancer were remarkably decreased after surgery ( P < 0.001 ). The preoperative and postoperative AFP-L3, GP-73, and AFP levels of patients with primary liver cancer were significantly higher than those of patients with benign liver lesions. The AUC (95% CI) for the combined detection of MRI and serum AFP-L3 and GP-73 levels in patients with surgically confirmed primary liver cancer was 0.747 (0.619-0.874). Conclusion. MRI combined with serum AFP-L3 and GP-73 presents favorable diagnostic efficiency in the diagnosis of primary liver cancer, which is worthy of clinical application.

show abstract

Section: Discussionmentioning

confidence: 99%

Magnetic Resonance Imaging and Serum AFP-L3 and GP-73 in the Diagnosis of Primary Liver Cancer

Yuan

Xu²,

et al. 2022

Journal of Oncology

View full text Add to dashboard Cite

show abstract

“…In contrast, other approaches propose to reconstruct one "representative" breathing cycle [1,19,14,20,16,12,22]. The notion of single representative breathing cycles is common in radiation therapy planning and execution.…”

Section: Introductionmentioning

confidence: 99%

Predicting 4D Liver MRI for MR-guided Interventions

Gulamhussene¹,

Meyer²,

Rak³

et al. 2022

Preprint

View full text Add to dashboard Cite

Organ motion poses an unresolved challenge in image-guided interventions.In the pursuit of solving this problem, the research field of time-resolved volumetric magnetic resonance imaging (4D MRI) has evolved. However, current techniques are unsuitable for most interventional settings because they lack sufficient temporal and/or spatial resolution or have long acquisition times. In this work, we propose a novel approach for real-time, high-resolution 4D MRI with large fields of view for MR-guided interventions. To this end, we trained a convolutional neural network (CNN) end-to-end to predict a 3D liver MRI that correctly predicts the liver's respiratory state from a live 2D navigator MRI of a subject. Our method can be used in two ways: First, it can reconstruct near real-time 4D MRI with high quality and high resolution (209 × 128 × 128 matrix size with isotropic 1.8 mm voxel size and 0.6 s/volume) given a dynamic interventional 2D navigator slice for guidance during an intervention. Second, it can be used for retrospective 4D reconstruction with a temporal resolution of below 0.2 s/volume for motion analysis and use in radiation therapy. We report a mean target registration error (TRE) of 1.19 ± 0.74mm, which is below voxel size. We compare our results with a state-of-the-art retrospective 4D MRI reconstruction. Visual evaluation shows comparable quality. We show that small training sizes with short acquisition times down to 2 min can already achieve promising results and 24 min are sufficient for high quality results. Because our method can be readily combined with earlier methods, acquisition time can be further

show abstract

Abdominal motion tracking with free-breathing XD-GRASP acquisitions using spatio-temporal geodesic trajectories

Mansour

Romaguera²,

Huët

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

Automatic self-gated 4D-MRI construction from free-breathing 2D acquisitions applied on liver images

Cited by 10 publications

References 23 publications

Magnetic Resonance Imaging and Serum AFP-L3 and GP-73 in the Diagnosis of Primary Liver Cancer

Magnetic Resonance Imaging and Serum AFP-L3 and GP-73 in the Diagnosis of Primary Liver Cancer

Predicting 4D Liver MRI for MR-guided Interventions

Abdominal motion tracking with free-breathing XD-GRASP acquisitions using spatio-temporal geodesic trajectories

Contact Info

Product

Resources

About