Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Dec;11(12):4753-4766.
doi: 10.21037/qims-20-1114.

MRI classification using semantic random forest with auto-context model

Yang Lei  1 , Tonghe Wang  1 , Xue Dong  1 , Sibo Tian  1 , Yingzi Liu  1 , Hui Mao  2 , Walter J Curran  1 , Hui-Kuo Shu  1 , Tian Liu  1 , Xiaofeng Yang  1
Affiliations

MRI classification using semantic random forest with auto-context model

Yang Lei et al. Quant Imaging Med Surg. 2021 Dec.

Abstract

Background: It is challenging to differentiate air and bone on MR images of conventional sequences due to their low contrast. We propose to combine semantic feature extraction under auto-context manner into random forest to improve reasonability of the MRI segmentation for MRI-based radiotherapy treatment planning or PET attention correction.

Methods: We applied a semantic classification random forest (SCRF) method which consists of a training stage and a segmentation stage. In the training stage, patch-based MRI features were extracted from registered MRI-CT training images, and the most informative elements were selected via feature selection to train an initial random forest. The rest sequence of random forests was trained by a combination of MRI feature and semantic feature under an auto-context manner. During segmentation, the MRI patches were first fed into these random forests to derive patch-based segmentation. By using patch fusion, the final end-to-end segmentation was obtained.

Results: The Dice similarity coefficient (DSC) for air, bone and soft tissue classes obtained via proposed method were 0.976±0.007, 0.819±0.050 and 0.932±0.031, compared to 0.916±0.099, 0.673±0.151 and 0.830±0.083 with random forest (RF), and 0.942±0.086, 0.791±0.046 and 0.917±0.033 with U-Net. SCRF also outperformed the competing methods in sensitivity and specificity for all three structure types.

Conclusions: The proposed method accurately segmented bone, air and soft tissue. It is promising in facilitating advanced MR application in diagnosis and therapy.

Keywords: MRI segmentation; auto-context; semantic classification random forest (SCRF).

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at http://dx.doi.org/10.21037/qims-20-1114). The special issue “Artificial Intelligence for Image-guided Radiation Therapy” was commissioned by the editorial office without any funding or sponsorship. All authors report this research was supported in part by the National Cancer Institute of the National Institutes of Health Award Number R01CA215718. The authors have no other conflicts of interest to declare.

Figures

Figure 1
Figure 1
The workflow of the proposed brain MRI SCRF method. The training stage is shown on the left, and the segmentation stage is shown on the right. MRI, magnetic resonance image; SCRF, semantic classification random forest.
Figure 2
Figure 2
An example illustrating the blocks within a window for semantic feature extraction. The axial view of probability map of air, soft tissue and bone classes are shown by (A), (B) and (C), respectively. The semantic features are extracted within an extracting window, which is shown as yellow dashed rectangles. For each semantic feature, it is calculated by the mean value of a white rectangle located within extracting window. The yellow arrow indicates a window position.
Figure 3
Figure 3
An example of probability maps generation during auto-context procedure. (B1) shows the MRI in axial view. (A1), (C1) and (D1) show the ground truth probability map of tissue classes, which is a binary mask of ground truth contour. (A2), (C2) and (D2) show the estimated probability maps via first random forest. (A3), (C3) and (D3) show the estimated probability maps via second random forest. (B2,B3) show the zoomed-in regions close to the nasopharynx. The context locations are shown in black dashed rectangles. By calculating mean value, each context location generates a semantic feature. MRI, magnetic resonance image.
Figure 4
Figure 4
An example illustrating the significance of feature selection. (A) and (B) show axial viewed MRI and CT image, where the sample voxels corresponding to air tissue are represented by green circles, and the sample voxels of bone tissue are highlighted by red asterisks. (C) Shows the scatter plots of first three principle components of MRI features of these samples. The principle components are obtained via principle component analysis. (D) Shows the scatter plots of first three principle components of MRI features that are derived after feature selection. MRI, magnetic resonance image.
Figure 5
Figure 5
Qualitative comparison between RF and SCRF methods. (A1) and (A4) shows MRI in axial view and sagittal view, respectively. (A2), (A5) and (A3), (A6) are corresponding CT images and CT labels (black for air, gray for soft-tissue, and white for bone) respectively. Row (B) and (C) are results generated with RF and SCRF respectively. The yellow arrows indicate bone region that is challenging during classification. The red arrows indicate soft tissue and air regions that are challenging during classification. MRI, magnetic resonance image; SCRF, semantic classification random forest.
Figure 6
Figure 6
Quantitative comparison of RF and SCRF methods for DSC (left), sensitivity (middle), and specificity (right). Error bars show standard deviation. SCRF, semantic classification random forest; DSC, Dice similarity coefficient.
Figure 7
Figure 7
Qualitative comparison between U-Net and SCRF methods. (A1) and (A4) shows MRI in axial view and sagittal view, respectively. (A2), (A5) and (A3), (A6) are corresponding CT images and CT labels (black for air, gray for soft-tissue, white for bone) respectively. Row (B) and (C) are results generated with RF and SCRF respectively. The red arrows indicate soft tissue and bone regions that are challenging during classification. MRI, magnetic resonance image; SCRF, semantic classification random forest.
Figure 8
Figure 8
Quantitative comparison of U-Net and SCRF methods on DSC (left), sensitivity (middle) and specificity (right). Error bars show standard deviation. SCRF, semantic classification random forest; DSC, Dice similarity coefficient.
See this image and copyright information in PMC

References

    1. Wang T, Manohar N, Lei Y, Dhabaan A, Shu HK, Liu T, Curran WJ, Yang X. MRI-based treatment planning for brain stereotactic radiosurgery: Dosimetric validation of a learning-based pseudo-CT generation method. Med Dosim 2019;44:199-204. 10.1016/j.meddos.2018.06.008 - DOI - PMC - PubMed
    1. Yang X, Wang T, Lei Y, Higgins K, Liu T, Shim H, Curran WJ, Mao H, Nye JA. MRI-based attenuation correction for brain PET/MRI based on anatomic signature and machine learning. Phys Med Biol 2019;64:025001. 10.1088/1361-6560/aaf5e0 - DOI - PMC - PubMed
    1. Schlesinger D, Benedict S, Diederich C, Gedroyc W, Klibanov A, Larner J. MR-guided focused ultrasound surgery, present and future. Med Phys 2013;40:080901. 10.1118/1.4811136 - DOI - PMC - PubMed
    1. Wang T, Hedrick S, Lei Y, Liu T, Jiang X, Dhabaan A, Tang X, Curran W, McDonald M, Yang X. Dosimetric Study of Cone-Beam CT in Adaptive Proton Therapy for Brain Cancer. Med Phys 2018;45:E259.
    1. Yang X, Lei Y, Wang T, Patel P, Dhabaan A, Jiang X, Shim H, Mao H, Curran W, Jani A. Patient-Specific Synthetic CT Generation for MRI-Only Prostate Radiotherapy Treatment Planning. Med Phys 2018;45:E701-E702.

LinkOut - more resources