1
|
Liu Z, Kainth K, Zhou A, Deyer TW, Fayad ZA, Greenspan H, Mei X. A review of self-supervised, generative, and few-shot deep learning methods for data-limited magnetic resonance imaging segmentation. NMR IN BIOMEDICINE 2024; 37:e5143. [PMID: 38523402 DOI: 10.1002/nbm.5143] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Revised: 02/15/2024] [Accepted: 02/16/2024] [Indexed: 03/26/2024]
Abstract
Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical-level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state-of-the-art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self-supervised learning, generative models, few-shot learning, and semi-supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field-including emerging algorithms, such as contrastive language-image pretraining, and potential combinations across the methods discussed-that can further increase the efficacy of image segmentation with limited labels.
Collapse
Affiliation(s)
- Zelong Liu
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Komal Kainth
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Alexander Zhou
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Timothy W Deyer
- East River Medical Imaging, New York, New York, USA
- Department of Radiology, Cornell Medicine, New York, New York, USA
| | - Zahi A Fayad
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
- Department of Diagnostic, Molecular, and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Hayit Greenspan
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
- Department of Diagnostic, Molecular, and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| | - Xueyan Mei
- BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, New York, New York, USA
- Department of Diagnostic, Molecular, and Interventional Radiology, Icahn School of Medicine at Mount Sinai, New York, New York, USA
| |
Collapse
|
3
|
Doss DJ, Johnson GW, Narasimhan S, Shless JS, Jiang JW, González HFJ, Paulo DL, Lucas A, Davis KA, Chang C, Morgan VL, Constantinidis C, Dawant BM, Englot DJ. Deep Learning Segmentation of the Nucleus Basalis of Meynert on 3T MRI. AJNR Am J Neuroradiol 2023; 44:1020-1025. [PMID: 37562826 PMCID: PMC10494939 DOI: 10.3174/ajnr.a7950] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2022] [Accepted: 06/25/2023] [Indexed: 08/12/2023]
Abstract
BACKGROUND AND PURPOSE The nucleus basalis of Meynert is a key subcortical structure that is important in arousal and cognition and has been explored as a deep brain stimulation target but is difficult to study due to its small size, variability among patients, and lack of contrast on 3T MR imaging. Thus, our goal was to establish and evaluate a deep learning network for automatic, accurate, and patient-specific segmentations with 3T MR imaging. MATERIALS AND METHODS Patient-specific segmentations can be produced manually; however, the nucleus basalis of Meynert is difficult to accurately segment on 3T MR imaging, with 7T being preferred. Thus, paired 3T and 7T MR imaging data sets of 21 healthy subjects were obtained. A test data set of 6 subjects was completely withheld. The nucleus was expertly segmented on 7T, providing accurate labels for the paired 3T MR imaging. An external data set of 14 patients with temporal lobe epilepsy was used to test the model on brains with neurologic disorders. A 3D-Unet convolutional neural network was constructed, and a 5-fold cross-validation was performed. RESULTS The novel segmentation model demonstrated significantly improved Dice coefficients over the standard probabilistic atlas for both healthy subjects (mean, 0.68 [SD, 0.10] versus 0.45 [SD, 0.11], P = .002, t test) and patients (0.64 [SD, 0.10] versus 0.37 [SD, 0.22], P < .001). Additionally, the model demonstrated significantly decreased centroid distance in patients (1.18 [SD, 0.43] mm, 3.09 [SD, 2.56] mm, P = .007). CONCLUSIONS We developed the first model, to our knowledge, for automatic and accurate patient-specific segmentation of the nucleus basalis of Meynert. This model may enable further study into the nucleus, impacting new treatments such as deep brain stimulation.
Collapse
Affiliation(s)
- D J Doss
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
| | - G W Johnson
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
| | - S Narasimhan
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| | - J S Shless
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| | - J W Jiang
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| | - H F J González
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
| | - D L Paulo
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| | - A Lucas
- Department of Bioengineering (A.L.), University of Pennsylvania, Philadelphia, Pennsylvania
| | - K A Davis
- Department of Neuroscience (K.A.D.), University of Pennsylvania, Philadelphia, Pennsylvania
- Center for Neuroengineering and Therapeutics (K.A.D.), University of Pennsylvania, Philadelphia, Pennsylvania
- Neurology (K.A.D.), University of Pennsylvania, Philadelphia, Pennsylvania
| | - C Chang
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
- Department of Electrical and Computer Engineering (C. Chang, B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Department of Computer Science (C. Chang), Vanderbilt University, Nashville, Tennessee
| | - V L Morgan
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
- Department of Neurology (V.L.M.), Vanderbilt University Medical Center, Nashville, Tennessee
- Department of Radiological Sciences (V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| | - C Constantinidis
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Department of Ophthalmology and Visual Sciences (C. Constantinidis), Vanderbilt University Medical Center, Nashville, Tennessee
- Department of Neuroscience (C. Constantinidis), Vanderbilt University, Nashville, Tennessee
| | - B M Dawant
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
- Department of Electrical and Computer Engineering (C. Chang, B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
| | - D J Englot
- From the Department of Biomedical Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang., V.L.M., C. Constantinidis, D.J.E.), Vanderbilt University, Nashville, Tennessee
- Institute of Imaging Science (D.J.D., G.W.J., S.N., J.S.S., J.W.J., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Vanderbilt Institute for Surgery and Engineering (D.J.D., G.W.J., S.N., H.F.J.G., C. Chang, V.L.M., B.M.D., D.J.E.), Nashville, Tennessee
- Department of Neurological Surgery (S.N., J.S.S., J.W.J., D.L.P., V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
- Department of Electrical and Computer Engineering (C. Chang, B.M.D., D.J.E.), Vanderbilt University, Nashville, Tennessee
- Department of Radiological Sciences (V.L.M., D.J.E.), Vanderbilt University Medical Center, Nashville, Tennessee
| |
Collapse
|