Automatic measurement algorithm of scoliosis Cobb angle based on deep learning
01 Apr 2019-Vol. 1187, Iss: 4, pp 042100
TL;DR: A deep learning based scoliosis Cobb angle measurement algorithm which can automatically calculate Cobb angle without the physician's manual definition is proposed and a DU-Net detection and segmentation network is proposed to remove the unrelated regions and to segment the spine contour in the spine X-ray image.
Abstract: Aiming at the subjective experience of the physician, the high measurement error in the Cobb angle measurement of scoliosis X-ray images and the X-ray image of spine is difficult to segment. A deep learning based scoliosis Cobb angle measurement algorithm which can automatically calculate Cobb angle without the physician's manual definition is proposed. A DU-Net detection and segmentation network is proposed in this paper to remove the unrelated regions and to segment the spine contour in the spine X-ray image. The aggregated channel features in pedestrian detection algorithm is introduced to scoliosis image to realize the spine region detection. And the DU-Net network is training to segment spine contour. Therefore, the spine curve can be fitted by the spine contour and the Cobb angle can be automatically measured by the tangent line of spine curve. As a result, the Cobb angle measure methods yields an average error of 2.9° to reference Cobb angle which are measured manually by special orthopaedist. The detection algorithm in this paper yields an average precision of 98.5% and a recall of 99.5%. Moreover, the DU-Net reach an average Dice coefficient to reference segmentation of 90.28%, an IOU of 82.29% and a precision of 86.30%.
Citations
More filters
06 Jun 2022
TL;DR: This study proposed an end-to-end pipeline for automatic Cobb angle measurement to pinpoint scoliosis severity using convolutional neural networks, showing that the Residual U-Net architecture provides vertebrae average segmentation accuracy based on Dice and Jaccard similarity coefficients.
Abstract: Efficient and reliable medical image analysis is indispensable in modern healthcare settings. The conventional approaches in diagnostics and evaluations from a mere picture are complex. It often leads to subjectivity due to experts' various experiences and expertise. Using convolutional neural networks, we proposed an end-to-end pipeline for automatic Cobb angle measurement to pinpoint scoliosis severity. Our results show that the Residual U-Net architecture provides vertebrae average segmentation accuracy of 92.95% based on Dice and Jaccard similarity coefficients. Furthermore, a comparative benchmark between physician's measurement and our machine-driven approach produces an acceptable mean deviation of 1.57 degrees and a T-test p-value of 0.9028, indicating no significant difference. This study has the potential to help doctors in prompt scoliosis magnitude assessments.
24 citations
09 Nov 2011
TL;DR: The widespread availability of inclinometer-equipped mobile phones and the ability to store measurements in later versions of the angle measurement software may make these new technologies attractive for clinical measurement applications.
Abstract: Purpose:
The Cobb technique is the universally accepted method for measuring the severity of spinal deformities. Traditionally, Cobb angles have been measured using protractor and pencil on hardcopy radiographic films. The new generation of mobile phones make accurate angle measurement possible using an integrated accelerometer, providing a potentially useful clinical tool for assessing Cobb angles. The purpose of this study was to compare Cobb angle measurements performed using an Apple iPhone and traditional protractor in a series of twenty Adolescent Idiopathic Scoliosis patients.
Methods:
Seven observers measured major Cobb angles on twenty pre-operative postero-anterior radiographs of Adolescent Idiopathic Scoliosis patients with both a standard protractor and using an Apple iPhone. Five of the observers repeated the measurements at least a week after the original measurements.
Results:
The mean absolute difference between pairs of iPhone/protractor measurements was 2.1°, with a small (1°) bias toward lower Cobb angles with the iPhone. 95% confidence intervals for intra-observer variability were ±3.3° for the protractor and ±3.9° for the iPhone. 95% confidence intervals for inter-observer variability were ±8.3° for the iPhone and ±7.1° for the protractor. Both of these confidence intervals were within the range of previously published Cobb measurement studies.
Conclusions:
We conclude that the iPhone is an equivalent Cobb measurement tool to the manual protractor, and measurement times are about 15% less. The widespread availability of inclinometer-equipped mobile phones and the ability to store measurements in later versions of the angle measurement software may make these new technologies attractive for clinical measurement applications.
19 citations
TL;DR: Deep transfer learning models were developed to perform three-class classification as well as pair-wise binary classifications among the three classes, and high accuracy values were achieved for most of the models, reflecting a robust ability to diagnose the subjects’ vertebral column disorders from standard X-ray images.
Abstract: Recent years have witnessed wider prevalence of vertebral column pathologies due to lifestyle changes, sedentary behaviors, or injuries. Spondylolisthesis and scoliosis are two of the most common ailments with an incidence of 5% and 3% in the United States population, respectively. Both of these abnormalities can affect children at a young age and, if left untreated, can progress into severe pain. Moreover, severe scoliosis can even lead to lung and heart problems. Thus, early diagnosis can make it easier to apply remedies/interventions and prevent further disease progression. Current diagnosis methods are based on visual inspection by physicians of radiographs and/or calculation of certain angles (e.g., Cobb angle). Traditional artificial intelligence-based diagnosis systems utilized these parameters to perform automated classification, which enabled fast and easy diagnosis supporting tools. However, they still require the specialists to perform error-prone tedious measurements. To this end, automated measurement tools were proposed based on processing techniques of X-ray images. In this paper, we utilize advances in deep transfer learning to diagnose spondylolisthesis and scoliosis from X-ray images without the need for any measurements. We collected raw data from real X-ray images of 338 subjects (i.e., 188 scoliosis, 79 spondylolisthesis, and 71 healthy). Deep transfer learning models were developed to perform three-class classification as well as pair-wise binary classifications among the three classes. The highest mean accuracy and maximum accuracy for three-class classification was 96.73% and 98.02%, respectively. Regarding pair-wise binary classification, high accuracy values were achieved for most of the models (i.e., > 98%). These results and other performance metrics reflect a robust ability to diagnose the subjects’ vertebral column disorders from standard X-ray images. The current study provides a supporting tool that can reasonably help the physicians make the correct early diagnosis with less effort and errors, and reduce the need for surgical interventions.
15 citations
TL;DR: This work proposes an automated architecture that uses combined segmentation with landmark information to estimate 68 landmarks of 17 vertebrae and considers spinal curvature described by 68 landmarks as a constraint to estimate the Cobb angle.
Abstract: Scoliosis is a medical condition where a person’s spine has a sideways curve. The Cobb angle quantifying the degree of spinal curvature is the gold standard for a scoliosis assessment. Recently, the deep learning methods based on segmentation and landmark estimation both achieve high performance for automated Cobb angle measurement on X-rays. However, we notice that these methods utilize segmentation and landmark information separately. In this light, we propose an automated architecture that uses combined segmentation with landmark information to estimate 68 landmarks of 17 vertebrae. In addition, we consider spinal curvature described by 68 landmarks as a constraint to estimate the Cobb angle. Extensive experiment results which test on 240 X-rays demonstrate that our method improves the landmark estimation performance effectively and reduces the Cobb angle error.
12 citations
TL;DR: The research progress of Cobb angle measurement in recent years is reviewed from the perspectives of computer vision and deep learning by comparing the measurement effects of typical methods and their advantages and disadvantages.
Abstract: Scoliosis is a common disease of the spine and requires regular monitoring due to its progressive properties. A preferred indicator to assess scoliosis is by the Cobb angle, which is currently measured either manually by the relevant medical staff or semi-automatically, aided by a computer. These methods are not only labor-intensive but also vary in precision by the inter-observer and intra-observer. Therefore, a reliable and convenient method is urgently needed. With the development of computer vision and deep learning, it is possible to automatically calculate the Cobb angles by processing X-ray or CT/MR/US images. In this paper, the research progress of Cobb angle measurement in recent years is reviewed from the perspectives of computer vision and deep learning. By comparing the measurement effects of typical methods, their advantages and disadvantages are analyzed. Finally, the key issues and their development trends are also discussed.
6 citations
References
More filters
07 Jun 2015
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet [20], the VGG net [31], and GoogLeNet [32]) into fully convolutional networks and transfer their learned representations by fine-tuning [3] to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes less than one fifth of a second for a typical image.
28,225 citations
Posted Content•
TL;DR: It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Abstract: There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at this http URL .
19,534 citations
TL;DR: Fully convolutional networks (FCN) as mentioned in this paper were proposed to combine semantic information from a deep, coarse layer with appearance information from shallow, fine layer to produce accurate and detailed segmentations.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Our key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional networks achieve improved segmentation of PASCAL VOC (30% relative improvement to 67.2% mean IU on 2012), NYUDv2, SIFT Flow, and PASCAL-Context, while inference takes one tenth of a second for a typical image.
4,960 citations
24 Jul 1998
TL;DR: Several improvements to Freund and Schapire’s AdaBoost boosting algorithm are described, particularly in a setting in which hypotheses may assign confidences to each of their predictions.
Abstract: We describe several improvements to Freund and Schapire‘s AdaBoost boosting algorithm, particularly in a setting in which hypotheses may assign confidences to each of their predictions. We give a simplified analysis of AdaBoost in this setting, and we show how this analysis can be used to find improved parameter settings as well as a refined criterion for training weak hypotheses. We give a specific method for assigning confidences to the predictions of decision trees, a method closely related to one used by Quinlan. This method also suggests a technique for growing decision trees which turns out to be identical to one proposed by Kearns and Mansour. We focus next on how to apply the new boosting algorithms to multiclass classification problems, particularly to the multi-label case in which each example may belong to more than one class. We give two boosting methods for this problem, plus a third method based on output coding. One of these leads to a new method for handling the single-label case which is simpler but as effective as techniques suggested by Freund and Schapire. Finally, we give some experimental results comparing a few of the algorithms discussed in this paper.
2,900 citations
21 Jul 2017
TL;DR: The ChestX-ray dataset as discussed by the authors contains 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels from the associated radiological reports using natural language processing.
Abstract: The chest X-ray is one of the most commonly accessible radiological examinations for screening and diagnosis of many lung diseases. A tremendous number of X-ray imaging studies accompanied by radiological reports are accumulated and stored in many modern hospitals Picture Archiving and Communication Systems (PACS). On the other side, it is still an open question how this type of hospital-size knowledge database containing invaluable imaging informatics (i.e., loosely labeled) can be used to facilitate the data-hungry deep learning paradigms in building truly large-scale high precision computer-aided diagnosis (CAD) systems. In this paper, we present a new chest X-ray database, namely ChestX-ray8, which comprises 108,948 frontal-view X-ray images of 32,717 unique patients with the text-mined eight disease image labels (where each image can have multi-labels), from the associated radiological reports using natural language processing. Importantly, we demonstrate that these commonly occurring thoracic diseases can be detected and even spatially-located via a unified weakly-supervised multi-label image classification and disease localization framework, which is validated using our proposed dataset. Although the initial quantitative results are promising as reported, deep convolutional neural network based reading chest X-rays (i.e., recognizing and locating the common disease patterns trained with only image-level labels) remains a strenuous task for fully-automated high precision CAD systems.
2,100 citations