Radiological images and machine learning: Trends, perspectives, and prospects

Zhang, Zhen-wei; Sejdić, Ervin

doi:10.1016/j.compbiomed.2019.02.017

Cited by 156 publications

(96 citation statements)

References 192 publications

(200 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Segmentation is the process by which the computer goes through each pixel in an image and classifies it as belonging to either the region of interest, in this case the second metacarpal, or the background. 7 This requires x-rays to be standardized to train the model effectively with available data. Before segmentation, the raw images were standardized to have the appearance of a vertically oriented right hand.…”

Section: Methodsmentioning

confidence: 99%

“…6 Computer learning is a fundamental concept of artificial intelligence research and is the study of computer algorithms that improve automatically through experience. 7 An important subset of computer learning is called supervised learning, in which the machine learns how to perform a task based on labeled examples. 7 Classification is a specific type of supervised learning that can be used to determine in which category something belongs after seeing a number of examples from several categories.…”

mentioning

confidence: 99%

“…7 An important subset of computer learning is called supervised learning, in which the machine learns how to perform a task based on labeled examples. 7 Classification is a specific type of supervised learning that can be used to determine in which category something belongs after seeing a number of examples from several categories. 7 We hypothesized that the use of such a computer learning model would predict osteoporosis on plain hand or wrist films based on the 2MCP.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening

Tecle

Teitel

Morris

et al. 2020

The Journal of Hand Surgery

View full text Add to dashboard Cite

Purpose Osteoporosis and osteopenia are extremely common and can lead to fragility fractures. The purpose of this study was to determine whether a computer learning system could classify whether a hand radiograph demonstrated osteoporosis based on the second metacarpal cortical percentage. Methods We used the second metacarpal cortical percentage as the osteoporosis predictor. A total of 4,000 posteroanterior (PA) radiographs of the hand were standardized through laterality correction, vertical alignment correction, segmentation, proxy osteoporosis predictor, and full pipeline. Laterality was classified using a LeNet convolutional neural network (CNN). Vertical alignment classification used 2,000 PA x-rays to determine vertical alignment of the second metacarpal. We employed segmentation to determine which pixels belong to the second metacarpal from 1,000 PA x-rays using the FSN-8 CNN. The full pipeline was tested on 265 previously unseen PA x-rays. Results Laterality classification accuracy was 99.62%, with a specificity of 100% and sensitivity of 99.3%. Rotation of the hand within 10 of vertical was accurate in 93.2% of films. Segmentation was 94.8% accurate. Proxy osteoporosis predictor was 88.4% accurate. Full pipeline accuracy was 93.9%. In the testing data set, the CNN had a sensitivity of 82.4% and specificity of 95.7%. In the balanced data set, 6 of 39 osteoporotic films were classified as nonosteoporotic; sensitivity was 82.4% and specificity, 94.3%. Conclusions We have created a series of CNN that can accurately identify osteoporosis from non-osteoporosis. Furthermore, our CNN is able to make adjustments to images based on laterality and vertical alignment. Clinical relevance Convolutional neural network and computer learning can be used as an adjunct to dual-energy x-ray absorptiometry scans or to screen and make appropriate referrals for further workup in patients with suspected osteoporosis.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening

Tecle

Teitel

Morris

et al. 2020

The Journal of Hand Surgery

View full text Add to dashboard Cite

show abstract

“…However, deep learning in medical image registration has not been extensively studied until the past three to four years. Though several review papers on deep learning in medical image analysis have been published [73,93,96,105,106,121,132,182], there are very few review papers that are specific to deep learning in medical image registration [60]. The goal of this paper is to summarize the latest developments, challenges and trends in DL-based medical image registration methods.…”

Section: Introductionmentioning

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

“…Machine Learning (ML) approaches have been proved useful in many health-related classification tasks. One of the strongest example is its employment on the analysis of radiological images to detect diseases (Zhang & Sejdić, 2019). With respect to ASD, ML classification has been applied in several studies to predict diagnosis, however with sparse prediction results.…”

Section: Introductionmentioning

confidence: 99%

Dopaminergic Gene Dosage in Autism versus Developmental Delay: From Complex Networks to Machine Learning approaches

Santos

Caramelo

Melo

2020

Preprint

View full text Add to dashboard Cite

we studied genetic alterations related to dopamine processes that could impact brain development and function of 2636 participants. On average, from a genetic sample we were able to correctly separate autism from developmental delay with an accuracy of 85%. AbstractThe neural basis of behavioural changes in Autism Spectrum Disorders (ASD) remains a controversial issue. One factor contributing to this challenge is the phenotypic heterogeneity observed in ASD, which suggests that several different system disruptions may contribute to diverse patterns of impairment between and within study samples. Here, we took a retrospective approach, using SFARI data to study ASD by focusing on participants with genetic imbalances targeting the dopaminergic system. Using complex network analysis, we investigated the relations between participants, Gene Ontology (GO) and gene dosage related to dopaminergic neurotransmission from a polygenic point of view. We converted network analysis into a machine learning binary classification problem to differentiate ASD diagnosed participants from DD (developmental delay) diagnosed participants. Using 1846 participants to train a Random Forest algorithm, our best classifier achieved on average a diagnosis predicting accuracy of 85.18% (sd 1.11%) on a test sample of 790 participants using gene dosage features. In addition, we observed that if the classifier uses GO features it was also able to infer a correct response based on the previous examples because it is tied to a set of biological process, molecular functions and cellular components relevant to the problem. This yields a less variable and more compact set of features when comparing with gene dosage classifiers. Other facets of knowledge-based systems approaches addressing ASD through network analysis and machine learning, providing an interesting avenue of research for the future, are presented through the study.

show abstract

Radiological images and machine learning: Trends, perspectives, and prospects

Cited by 156 publications

References 192 publications

Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening

Convolutional Neural Network for Second Metacarpal Radiographic Osteoporosis Screening

Deep learning in medical image registration: a review

Dopaminergic Gene Dosage in Autism versus Developmental Delay: From Complex Networks to Machine Learning approaches

Contact Info

Product

Resources

About