Quantitative error prediction of medical image registration using regression forests

Sokooti, Hessam; Saygılı, Görkem; Glocker, Ben; Lelieveldt, Boudewijn P. F.; Staring, Marius

doi:10.1016/j.media.2019.05.005

Cited by 34 publications

(24 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ROI Dimension Modality End point [112] HN 3D CT TRE prediction [34] Lung 3D CT Registration error [31] Brain 3D MRI DSC score [47] Lung 3D CT Landmark Pairs [49] Lung 3D CT Registration error [138] Lung 3D CT Registration error…”

Section: Referencesmentioning

confidence: 99%

Deep learning in medical image registration: a review

et al. 2020

View full text Add to dashboard Cite

This paper presents a review of deep learning (DL) based medical image registration methods. We summarized the latest developments and applications of DL-based registration methods in the medical field. These methods were classified into seven categories according to their methods, functions and popularity. A detailed review of each category was presented, highlighting important contributions and identifying specific challenges. A short assessment was presented following the detailed review of each category to summarize its achievements and future potentials. We provided a comprehensive comparison among DL-based methods for lung and brain registration using benchmark datasets. Lastly, we analyzed the statistics of all the cited works from various aspects, revealing the popularity and future trend of DL-based medical image registration. 1 arXiv:1912.12318v1 [eess.IV] 27 Dec 2019 1. Summarize the latest developments in DL-based medical image registration. 2. Highlight contributions, identify challenges and outline future trends. 3. Provide detailed statistics on recent publications from different perspectives. 2 Deep Learning 2 Convolutional Neural NetworkConvolutional neural network (CNN) is a class of deep neural networks with regularized multilayer perceptron. CNN uses convolution operation in place of general matrix multiplication in simple neural networks. The convolutional filters and operations in CNN make it suitable for visual imagery signal processing. Because of its excellent feature extraction ability, CNN is one of the most successful models for image analysis. Since the breakthrough of AlexNet [79], many variants of CNN have been proposed and have achieved the-state-of-art performances in various image processing tasks. A typical CNN usually consists of multiple convolutional layers, max pooling layers, batch normalization layers, dropout layers, a sigmoid or softmax layer. In each convolutional layer, multiple channels of feature maps were extracted by sliding trainable convolutional kernels across the input feature maps. Hierarchical features with high-level abstraction are extracted using multiple convolutional layers. These feature maps usually go through multiple fully connected layer before reaching the final decision layer. Max pooling layers are often used to reduce the image sizes and to promote spatial invariance of the network. Batch normalization is used to reduce internal covariate shift among the training samples. Weight regularization and dropout layers are used to alleviate data overfitting. The loss function is defined as the difference between the predicted and the target output. CNN is usually trained by minimizing the loss via gradient back propagation using optimization methods. Many different types of network architectures have been proposed to improve the performance of CNN [93]. U-Net proposed by Ronneberger et al. is among one of the most used network architectures [120]. U-Net was originally used to perform neuronal structures segmentation. U-Net adopts symmetrical contractiv...

show abstract

Section: Referencesmentioning

confidence: 99%

Deep learning in medical image registration: a review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…After the feature extraction, feature pooling is applied akin to [23,25,26]. Feature pooling enlarges feature space by extracting new features from the existing ones using the mean filter.…”

Section: Methodsmentioning

confidence: 99%

“…Furthermore, RF is robust against overfitting and requires a fewer number of hyperparameters to be set. It is also the preferred classifier in [23,25,26].…”

Section: Methodsmentioning

confidence: 99%

“…In this work, we aim to detect such errors in an embedding to inform the observer. Recently, detecting errors in medical image registration has been the aim of several studies [23][24][25][26]. Two of those studies use matching to extract features from two scans [24,25] and use this information in a random forest (RF) regressor to predict the errors [25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A supervised learning approach for detecting erroneous samples in embeddings

Saygılı¹

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Visualizing multidimensional data has been a crucial task in recent years regarding the growing amount of data from various sources. To achieve this, dimensionality reduction algorithms have been used to reduce the number of dimensions for visualization of the data on a screen. However, these algorithms may fail to faithfully represent high dimensional data in lower dimensions and eventually lead to erroneous visualizations. In this work, we propose an error detection algorithm for dimensionality reduction algorithms based on recently developed error prediction algorithms for medical image registration. The proposed algorithm matches the neighborhoods of high and low dimensional data with different similarity measures and predicts the errors using a random forest classifier. The results on three datasets show that the proposed algorithm can successfully detect errors with an accuracy up to 86% and area under the curve score of 0.81 .

show abstract

“…Colon histopathology image analysis is the basis of the primary detection of colon lesions [10]. e gland structure is shown in Figure 1(a).…”

Section: Introductionmentioning

confidence: 99%

Multiple Morphological Constraints-Based Complex Gland Segmentation in Colorectal Cancer Pathology Image Analysis

Zhang

Hua

et al. 2020

Complexity

View full text Add to dashboard Cite

Histological assessment of glands is one of the major concerns in colon cancer grading. Considering that poorly differentiated colorectal glands cannot be accurately segmented, we propose an approach for segmentation of glands in colon cancer images, based on the characteristics of lumens and rough gland boundaries. First, we use a U-net for stain separation to obtain H-stain, E-stain, and background stain intensity maps. Subsequently, epithelial nucleus is identified on the histopathology images, and the lumen segmentation is performed on the background intensity map. Then, we use the axis of least inertia-based similar triangles as the spatial characteristics of lumens and epithelial nucleus, and a triangle membership is used to select glandular contour candidates from epithelial nucleus. By connecting lumens and epithelial nucleus, more accurate gland segmentation is performed based on the rough gland boundary. The proposed stain separation approach is unsupervised, and the stain separation makes the category information contained in the H&E image easy to identify and deal with the uneven stain intensity and the inconspicuous stain difference. In this project, we use deep learning to achieve stain separation by predicting the stain coefficient. Under the deep learning framework, we design a stain coefficient interval model to improve the stain generalization performance. Another innovation is that we propose the combination of the internal lumen contour of adenoma and the outer contour of epithelial cells to obtain a precise gland contour. We compare the performance of the proposed algorithm against that of several state-of-the-art technologies on publicly available datasets. The results show that the segmentation approach combining the characteristics of lumens and rough gland boundary has better segmentation accuracy.

show abstract

Quantitative error prediction of medical image registration using regression forests

Cited by 34 publications

References 44 publications

Deep learning in medical image registration: a review

Deep learning in medical image registration: a review

A supervised learning approach for detecting erroneous samples in embeddings

Multiple Morphological Constraints-Based Complex Gland Segmentation in Colorectal Cancer Pathology Image Analysis

Contact Info

Product

Resources

About