Simultaneous MR knee image segmentation and bias field correction using deep learning and partial convolution

Wan, Fengkai; Smedby, Örjan

doi:10.1117/12.2512950

Cited by 10 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [32] proposed an iterative process where a U-net is applied to provide a preliminary segmentation followed by a convolution layer to estimate the bias field in magnetic resonance (MR) images. Next, the bias field corrected image is again sent to the U-net for the next iteration, improving the segmentation.…”

Section: Deep Methods Addressing Inhomogeneous Illuminationmentioning

confidence: 99%

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

Memariani

Nikou

Endres

et al. 2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Clostridioides difficile infection (C. diff) is the most common cause of death due to secondary infection in hospital patients in the United States. Detection of C. diff cells in scanning electron microscopy (SEM) images is an important task to quantify the efficacy of the under-development treatments. However, detecting C. diff cells in SEM images is a challenging problem due to the presence of inhomogeneous illumination and occlusion. An Illumination normalization pre-processing step destroys the texture and adds noise to the image. Furthermore, cells are often clustered together resulting in touching cells and occlusion. In this paper, DETCID, a deep cell detection method using adversarial training, specifically robust to inhomogeneous illumination and occlusion, is proposed. An adversarial network is developed to provide region proposals and pass the proposals to a feature extraction network. Furthermore, a modified IoU metric is developed to allow the detection of touching cells in various orientations. The results indicate that DETCID outperforms the state-of-the-art in detection of touching cells in SEM images by at least 20 percent improvement of mean average precision.

show abstract

Section: Deep Methods Addressing Inhomogeneous Illuminationmentioning

confidence: 99%

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

Memariani

Nikou

Endres

et al. 2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

show abstract

“…The following works all used a deep learning approach for bias field corrections but used different strategies to create a dataset for training. Venkatesh et al 17 used a set of basis functions to generate a bias field for brain images from BrainWeb; the work of Dai et al, 18 Chuang et al, 19 and Gaillochet et al 20 used the results from the N4 algorithm as substitute for a ground truth image to train a neural network; in the work of Wan et al, 21 a neural network was trained to remove the bias field in conjunction with a segmentation task to avoid the need for a homogeneous ground truth image; in the work of Goldfryd et al, 22 the bias field was generated by third order polynomials; Simk o et al 23 used a Gaussian covariance model to generate a bias field; Nelamangala et al 24 used a bias field obtained from the Human Connectome Project, which used the T 1 weighted (T1w) and T 2 weighted (T2w) brain images to approximate a bias field. 25 In this work we created a synthetic 7 T dataset of T2w prostate images, which was based on simulated B 1 distributions of the eight-element coil array shown in the work of Raaijmakers et al, 26 and T2w prostate images obtained at 1.5 T. Note that this paper focuses only on T2w spin echo sequences as they are the workhorse for diagnosis and treatment planning of prostate cancer.…”

Section: Introductionmentioning

confidence: 99%

Deep learning based correction of RF field induced inhomogeneities for T2w prostate imaging at 7 T

Harrevelt,

Meliado,

van Lier

et al. 2023

NMR in Biomedicine

View full text Add to dashboard Cite

At ultrahigh field strengths images of the body are hampered by B1‐field inhomogeneities. These present themselves as inhomogeneous signal intensity and contrast, which is regarded as a “bias field” to the ideal image. Current bias field correction methods, such as the N4 algorithm, assume a low frequency bias field, which is not sufficiently valid for T2w images at 7 T. In this work we propose a deep learning based bias field correction method to address this issue for T2w prostate images at 7 T. By combining simulated B1‐field distributions of a multi‐transmit setup at 7 T with T2w prostate images at 1.5 T, we generated artificial 7 T images for which the homogeneous counterpart was available. Using these paired data, we trained a neural network to correct the bias field. We predicted either a homogeneous image (t‐Image neural network) or the bias field (t‐Biasf neural network). In addition, we experimented with the single‐channel images of the receive array and the corresponding sum of magnitudes of this array as the input image. Testing was carried out on four datasets: the test split of the synthetic training dataset, volunteer and patient images at 7 T, and patient images at 3 T. For the test split, the performance was evaluated using the structural similarity index measure, Wasserstein distance, and root mean squared error. For all other test data, the features Homogeneity and Energy derived from the gray level co‐occurrence matrix (GLCM) were used to quantify the improvement. For each test dataset, the proposed method was compared with the current gold standard: the N4 algorithm. Additionally, a questionnaire was filled out by two clinical experts to assess the homogeneity and contrast preservation of the 7 T datasets. All four proposed neural networks were able to substantially reduce the B1‐field induced inhomogeneities in T2w 7 T prostate images. By visual inspection, the images clearly look more homogeneous, which is confirmed by the increase in Homogeneity and Energy in the GLCM, and the questionnaire scores from two clinical experts. Occasionally, changes in contrast within the prostate were observed, although much less for the t‐Biasf network than for the t‐Image network. Further, results on the 3 T dataset demonstrate that the proposed learning based approach is on par with the N4 algorithm. The results demonstrate that the trained networks were capable of reducing the B1‐field induced inhomogeneities for prostate imaging at 7 T. The quantitative evaluation showed that all proposed learning based correction techniques outperformed the N4 algorithm. Of the investigated methods, the single‐channel t‐Biasf neural network proves most reliable for bias field correction.

show abstract

“…N4ITK [10] is the one of the most popular tools for the bias field removal, and the quality of the bias-free image generated is largely determined by the convergence setting, i.e., number of iterations, which may be computationally expensive for image with high spatial resolution. Several DL based methods have been developed to accelerate the bias field correction [11][12][13]. Particularly, an iterative bias field correction and image segmentation framework is proposed in [13], where a preliminary image segmentation is first generated and subsequently used to estimate the bias field at each iteration step.…”

Section: Introductionmentioning

confidence: 99%

“…Several DL based methods have been developed to accelerate the bias field correction [11][12][13]. Particularly, an iterative bias field correction and image segmentation framework is proposed in [13], where a preliminary image segmentation is first generated and subsequently used to estimate the bias field at each iteration step. An end-to-end learning framework is proposed to generate bias-free image and bias field by integrating segmentation loss, adversarial loss, and reconstruction loss to optimize the DL model [11].…”

Section: Introductionmentioning

confidence: 99%

Cascaded convolutional networks for unsupervised brain tissue segmentation and bias field estimation

Li,

Fan

2023

Emerging Topics in Artificial Intelligence (ETAI) 2023

View full text Add to dashboard Cite

Brain tissue segmentation from MR images is a critical step for quantifying the brain morphology in neuroimaging studies. While deep learning (DL) based brain tissue segmentation methods have achieved promising performance, most of them are built upon supervised learning and therefore their performance is bounded by the training data used and limited by the small size of datasets with manual segmentation labels. To leverage the large amount of unlabeled brain imaging data, we develop an unsupervised DL model for joint brain tissue segmentation and bias field estimation using cascaded convolutional networks. The proposed DL model consists of multiple cascaded bias field estimation modules and one segmentation module. The bias field estimation modules are applied to the input image for estimating the bias field and generating a bias-free image recursively, and the bias field corrected image is then fed into the segmentation module to obtain the brain tissue segmentation result. A Gaussian mixture model is adopted to characterize the bias-free image with tissue-specific intensity statistics and the model fitting error is adopted as the loss function to guide the optimization of the model parameters progressively in an unsupervised setting. We have evaluated the proposed method on the HCP-Aging and HCP-Development datasets. Quantitative results have demonstrated that our unsupervised DL model could obtain competitive bias field correction and segmentation performance, compared with state-of-the-art bias field correction methods and unsupervised segmentation methods.

show abstract

Simultaneous MR knee image segmentation and bias field correction using deep learning and partial convolution

Cited by 10 publications

References 11 publications

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

DETCIC: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Stack of Conditional Random Fields

Deep learning based correction of RF field induced inhomogeneities for T2w prostate imaging at 7 T

Cascaded convolutional networks for unsupervised brain tissue segmentation and bias field estimation

Contact Info

Product

Resources

About