End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones from Bi-planar X-Ray Images

Kasten, Yoni; Doktofsky, Daniel; Kovler, Ilya

doi:10.1007/978-3-030-61598-7_12

Cited by 63 publications

(55 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lot of prior studies involving radiographic image segmentation of the human knee have only focused on knee osteoarthritis assessment [ 25 , 26 ] or knee bone detection [ 27 , 28 ]. However, there is very little research applying radiographic images to segment knee bone tumors: George et al [ 29 ] used various texture features of radiography to recognize bone patterns in the tumor region.…”

Section: Appendix A1 Tumor Detectionmentioning

confidence: 99%

Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection

Jung

Yang

et al. 2021

Diagnostics

View full text Add to dashboard Cite

Tumor classification and segmentation problems have attracted interest in recent years. In contrast to the abundance of studies examining brain, lung, and liver cancers, there has been a lack of studies using deep learning to classify and segment knee bone tumors. In this study, our objective is to assist physicians in radiographic interpretation to detect and classify knee bone regions in terms of whether they are normal, begin-tumor, or malignant-tumor regions. We proposed the Seg-Unet model with global and patched-based approaches to deal with challenges involving the small size, appearance variety, and uncommon nature of bone lesions. Our model contains classification, tumor segmentation, and high-risk region segmentation branches to learn mutual benefits among the global context on the whole image and the local texture at every pixel. The patch-based model improves our performance in malignant-tumor detection. We built the knee bone tumor dataset supported by the physicians of Chonnam National University Hospital (CNUH). Experiments on the dataset demonstrate that our method achieves better performance than other methods with an accuracy of 99.05% for the classification and an average Mean IoU of 84.84% for segmentation. Our results showed a significant contribution to help the physicians in knee bone tumor detection.

show abstract

Section: Appendix A1 Tumor Detectionmentioning

confidence: 99%

Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection

Jung

Yang

et al. 2021

Diagnostics

View full text Add to dashboard Cite

show abstract

“…The system is highly modular and geometry misalignment occurs in every new acquisition setup. The 3D 2 YMOX system is discussed further in Section 2.1. To obtain a high quality tomographic reconstruction and to exploit the benefits of a stereo X-ray CT setup, the system needs to be calibrated by estimating the geometric relationship between the X-ray source and the detector pairs with respect to the rotation axis prior to image reconstruction.…”

Section: Introductionmentioning

confidence: 99%

“…A genetic optimization algorithm was used to fine-tune the position of the source as well as the detector orientation. However, the method required the rotation stage to be manipulated with under 1 mm accuracy and the nominal system geometry to be well-measured, these requirements are not fulfilled in the 3D 2 YMOX system. In another study, Allab et al [17] reported a phantom-based calibration method as an alternative to the box calibration cage, which is usually used in radio stereometric analysis applications as a reference frame to locate the positions of implants or bones in the patients.…”

Section: Introductionmentioning

confidence: 99%

“…The geometry parameters and the marker coordinates were estimated by iteratively matching the reconstructed 3D point-cloud of the phantom with its reference model. A default calibration is required to generate the initial reference model for calibration, and yet this is not the case for the 3D 2 YMOX system as no pre-calibrated information available.…”

Section: Introductionmentioning

confidence: 99%

“…The positions of the markers in the phantom can be calculated from the dimensions of LEGO bricks at a reliable accuracy as LEGO bricks are molded with dimensional tolerance of 5 µm [20]. Furthermore, our proposed calibration method requires no pre-calibrated geometry information and is capable of calibrating a modular stereo cone-beam X-ray CT system such as the 3D 2 YMOX system. The paper is structured as follows.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Geometry Calibration of a Modular Stereo Cone-Beam X-ray CT System

et al. 2021

View full text Add to dashboard Cite

Compared to single source systems, stereo X-ray CT systems allow acquiring projection data within a reduced amount of time, for an extended field-of-view, or for dual X-ray energies. To exploit the benefit of a dual X-ray system, its acquisition geometry needs to be calibrated. Unfortunately, in modular stereo X-ray CT setups , geometry misalignment occurs each time the setup is changed, which calls for an efficient calibration procedure. Although many studies have been dealing with geometry calibration of an X-ray CT system, little research targets the calibration of a dual cone-beam X-ray CT system. In this work, we present a phantom-based calibration procedure to accurately estimate the geometry of a stereo cone-beam X-ray CT system. With simulated as well as real experiments, it is shown that the calibration procedure can be used to accurately estimate the geometry of a modular stereo X-ray CT system thereby reducing the misalignment artifacts in the reconstruction volumes.

show abstract

Deep learning‐based fast volumetric imaging using kV and MV projection images for lung cancer radiotherapy: A feasibility study

et al. 2023

View full text Add to dashboard Cite

PurposeThe long acquisition time of CBCT discourages repeat verification imaging, therefore increasing treatment uncertainty. In this study, we present a fast volumetric imaging method for lung cancer radiation therapy using an orthogonal 2D kV/MV image pair.MethodsThe proposed model is a combination of 2D and 3D networks. The proposed model consists of five major parts: (1) kV and MV feature extractors are used to extract deep features from the perpendicular kV and MV projections. (2) The feature‐matching step is used to re‐align the feature maps to their projection angle in a Cartesian coordinate system. By using a residual module, the feature map can focus more on the difference between the estimated and ground truth images. (3) In addition, the feature map is downsized to include more global semantic information for the 3D estimation, which is useful to reduce inhomogeneity. By using convolution‐based reweighting, the model is able to further increase the uniformity of image. (4) To reduce the blurry noise of generated 3D volume, the Laplacian latent space loss calculated via the feature map that is extracted via specifically‐learned Gaussian kernel is used to supervise the network. (5) Finally, the 3D volume is derived from the trained model. We conducted a proof‐of‐concept study using 50 patients with lung cancer. An orthogonal kV/MV pair was generated by ray tracing through CT of each phase in a 4D CT scan. Orthogonal kV/MV pairs from nine respiratory phases were used to train this patient‐specific model while the kV/MV pair of the remaining phase was held for model testing.ResultsThe results are based on simulation data and phantom results from a real Linac system. The mean absolute error (MAE) values achieved by our method were 57.5 HU and 77.4 HU within body and tumor region‐of‐interest (ROI), respectively. The mean achieved peak‐signal‐to‐noise ratios (PSNR) were 27.6 dB and 19.2 dB within the body and tumor ROI, respectively. The achieved mean normalized cross correlation (NCC) values were 0.97 and 0.94 within the body and tumor ROI, respectively. A phantom study demonstrated that the proposed method can accurately re‐position the phantom after shift. It is also shown that the proposed method using both kV and MV is superior to current method using kV or MV only in image quality.ConclusionThese results demonstrate the feasibility and accuracy of our proposed fast volumetric imaging method from an orthogonal kV/MV pair, which provides a potential solution for daily treatment setup and verification of patients receiving radiation therapy for lung cancer.

show abstract

End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones from Bi-planar X-Ray Images

Cited by 63 publications

References 24 publications

Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection

Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection

Geometry Calibration of a Modular Stereo Cone-Beam X-ray CT System

Deep learning‐based fast volumetric imaging using kV and MV projection images for lung cancer radiotherapy: A feasibility study

Contact Info

Product

Resources

About