MR Image Analytics to Characterize the Upper Airway Structure in Obese Children with Obstructive Sleep Apnea Syndrome

Tong, Yubing; Udupa, Jayaram K.; Sin, Sanghun; Liu, Zhengbing; Wileyto, E. Paul; Torigian, Drew A.; Arens, Raanan

doi:10.1371/journal.pone.0159327

Cited by 19 publications

(14 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The size of the selected optimal feature set can be varied by changing the amount of residual correlation allowed and the percent of top highly uncorrelated features we desire to select for this residual correlation. 41 The optimal biomarker feature sets from a minimum of 9 features to a maximum of 18 features were selected in this manner and analyzed. Table 1 shows the optimal biomarker feature set with 9, 14, and 18 features and the corresponding performance measures of sensitivity, specificity, prediction accuracy, and area under the ROC curve at both the patient and sector levels.…”

Section: Resultsmentioning

confidence: 99%

“…After the intensity and texture feature sets were extracted for the 3 shells at the patient and sector levels, a recently developed optimal biomarker approach was used to extract a small optimal feature set. 41 The idea behind this approach was to find a small set of discriminating features from the set of all features in several steps as follows: 1) Extract a subset of features that have a low level of correlation among all features. A heat map visualization technique that allows for the grouping of parameters on the basis of correlations among them was used for this purpose; 2) independently of step 1, extract a subset of features from the entire set that is capable of separating the 2 patient groups of interest.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Radiomics-guided therapy for bladder cancer: Using an optimal biomarker approach to determine extent of bladder cancer invasion from t2-weighted magnetic resonance images

Tong

Udupa

Wang

et al. 2018

Advances in Radiation Oncology

Self Cite

View full text Add to dashboard Cite

BackgroundCurrent clinical staging methods are unable to accurately define the extent of invasion of localized bladder cancer, which affects the proper use of systemic therapy, surgery, and radiation. Our purpose was to test a novel radiomics approach to identify optimal imaging biomarkers from T2-weighted magnetic resonance imaging (MRI) scans that accurately classify localized bladder cancer into 2 tumor stage groups (≤T2 vs >T2) at both the patient level and within bladder subsectors.Method and MaterialsPreoperative T2-weighted MRI scans of 65 consecutive patients followed by radical cystectomy were identified. A 3-layer, shell-like volume of interest (VOI) was defined on each MRI slice: Inner (lumen), middle (bladder wall), and outer (perivesical tissue). An optimal biomarker method was used to identify features from 15,834 intensity and texture properties that maximized the classification of patients into ≤T2 versus >T2 groups. A leave-one-out strategy was used to cross-validate the performance of the identified biomarker feature set at the patient level. The performance of the feature set was then evaluated at the subsector level of the bladder by dividing the VOIs into 8 radial sectors.ResultsA total of 9 optimal biomarker features were derived and demonstrated a sensitivity, specificity, accuracy of prediction, and area under a receiver operating characteristic curve of 0.742, 0.824, 0.785, and 0.806, respectively, at the patient level and 0.681, 0.788, 0.763, and 0.813, respectively, at the radial sector level. All 9 selected features were extracted from the middle shell of the VOI and based on texture properties.ConclusionsAn approach to select a small, highly independent feature set that is derived from T2-weighted MRI scans that separate patients with bladder cancer into ≤T2 versus >T2 groups at both the patient level and within subsectors of the bladder has been developed and tested. With external validation, this radiomics approach could improve the clinical staging of bladder cancer and optimize therapeutic management.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Radiomics-guided therapy for bladder cancer: Using an optimal biomarker approach to determine extent of bladder cancer invasion from t2-weighted magnetic resonance images

Tong

Udupa

Wang

et al. 2018

Advances in Radiation Oncology

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, by modeling object geographic relationship information with respect to the body region, objects can be quickly placed in an image based purely on prior knowledge. (b) Body composition analysis: Quantification of bodily tissues, 4,11 especially subcutaneous and visceral adipose components, has been shown to be useful as biomarkers in the study of various disease and treatment processes such as obstructive sleep apnea, 12 lung transplant surgery, 13 acute kidney injury in trauma, 14 etc. Without a precise definition of the body regions, standardized assessment of these tissues by body region becomes meaningless.…”

Section: B Related Workmentioning

confidence: 99%

BRR‐Net: A tandem architectural CNN–RNN for automatic body region localization in CT images

et al. 2020

Self Cite

View full text Add to dashboard Cite

Purpose: Automatic identification of consistently defined body regions in medical images is vital in many applications. In this paper, we describe a method to automatically demarcate the superior and inferior boundaries for neck, thorax, abdomen, and pelvis body regions in computed tomography (CT) images. Methods: For any three-dimensional (3D) CT image I, following precise anatomic definitions, we denote the superior and inferior axial boundary slices of the neck, thorax, abdomen, and pelvis body regions by NS(I), NI(I), TS(I), TI(I), AS(I), AI(I), PS(I), and PI(I), respectively. Of these, by definition, AI (I) = PS(I), and so the problem reduces to demarcating seven body region boundaries. Our method consists of a two-step approach. In the first step, a convolutional neural network (CNN) is trained to classify each axial slice in I into one of nine categories: the seven body region boundaries, plus legs (defined as all axial slices inferior to PI(I)), and the none-of-the-above category. This CNN uses a multichannel approach to exploit the interslice contrast, providing the neural network with additional visual context at the body region boundaries. In the second step, to improve the predictions for body region boundaries that are very subtle and that exhibit low contrast, a recurrent neural network (RNN) is trained on features extracted by CNN, limited to a flexible window about the predictions from the CNN. Results: The method is evaluated on low-dose CT images from 442 patient scans, divided into training and testing sets with a ratio of 70:30. Using only the CNN, overall absolute localization error for NS(I), NI(I), TS(I), TI(I), AS(I), AI(I), and PI(I) expressed in terms of number of slices (nS) is (mean AE SD): 0.61 AE 0.58, 1.05 AE 1.13, 0.31 AE 0.46, 1.85 AE 1.96, 0.57 AE 2.44, 3.42 AE 3.16, and 0.50 AE 0.50, respectively. Using the RNN to refine the CNN's predictions for select classes improved the accuracy of TI(I) and AI(I) to: 1.35 AE 1.71 and 2.83 AE 2.75, respectively. This model outperforms the results achieved in our previous work by 2.4, 1.7, 3.1, 1.1, and 2 slices, respectively for TS(I), TI(I), AS(I), AI(I) = PS(I), and PI(I) classes with statistical significance. The model trained on low-dose CT images was also tested on diagnostic CT images for NS(I), NI(I), and TS(I) classes; the resulting errors were: 1.48 AE 1.33, 2.56 AE 2.05, and 0.58 AE 0.71, respectively. Conclusions: Standardized body region definitions are a prerequisite for effective implementation of quantitative radiology, but the literature is severely lacking in the precise identification of body regions. The method presented in this paper significantly outperforms earlier works by a large margin, and the deviations of our results from ground truth are comparable to variations observed in manual labeling by experts. The solution presented in this work is critical to the adoption and employment of the idea of standardized body regions, and clears the path for development of applications requiring accurate demarcations of body re...

show abstract

“…[1][2][3] Standardized object definitions can also facilitate enriching and sharpening prior knowledge that is encoded into and utilized in methods for localizing objects body-wide 4,5 and distinguishing different patient groups. 6,7 In this spirit, body region definition becomes just as important as or even more important than objects contained in the body region. Some objects that cross body regions depend directly on precise body region definition for their accurate specification.…”

Section: A Backgroundmentioning

confidence: 99%

“…For example, without a precise definition of the boundaries of the thoracic body region and intrathoracic adipose tissue region, standardized quantification of intrathoracic fat becomes impossible . Standardized object definitions can also facilitate enriching and sharpening prior knowledge that is encoded into and utilized in methods for localizing objects body‐wide and distinguishing different patient groups . In this spirit, body region definition becomes just as important as or even more important than objects contained in the body region.…”

Section: Introductionmentioning

confidence: 99%

Body region localization in whole‐body low‐dose CT images of PET/CT scans using virtual landmarks

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose Radiological imaging and image interpretation for clinical decision making are mostly specific to each body region such as head and neck, thorax, abdomen, pelvis, and extremities. In this study, we present a new solution to trim automatically the given axial image stack into image volumes satisfying the given body region definition. Methods The proposed approach consists of the following steps. First, a set of reference objects is selected and roughly segmented. Virtual landmarks (VLs) for the objects are then identified by using principal component analysis and recursive subdivision of the object via the principal axes system. The VLs can be defined based on just the binary objects or objects with gray values also considered. The VLs may lie anywhere with respect to the object, inside or outside, and rarely on the object surface, and are tethered to the object. Second, a classic neural network regressor is configured to learn the geometric mapping relationship between the VLs and the boundary locations of each body region. The trained network is then used to predict the locations of the body region boundaries. In this study, we focus on three body regions — thorax, abdomen, and pelvis, and predict their superior and inferior axial locations denoted by TS(I), TI(I), AS(I), AI(I), PS(I), and PI(I), respectively, for any given volume image I. Two kinds of reference objects — the skeleton and the lungs and airways, are employed to test the localization performance of the proposed approach. Results Our method is tested by using low‐dose unenhanced computed tomography (CT) images of 180 near whole‐body 18F‐fluorodeoxyglucose‐positron emission tomography/computed tomography (FDG‐PET/CT) scans (including 34 whole‐body scans) which are randomly divided into training and testing sets with a ratio of 85%:15%. The procedure is repeated six times and three times for the case of lungs and skeleton, respectively, with different divisions of the entire data set at this proportion. For the case of using skeleton as a reference object, the overall mean localization error for the six locations expressed as number of slices (nS) and distance (dS) in mm, is found to be nS: 3.4, 4.7, 4.1, 5.2, 5.2, and 3.9; dS: 13.4, 18.9, 16.5, 20.8, 20.8, and 15.5 mm for binary objects; nS: 4.1, 5.7, 4.3, 5.9, 5.9, and 4.0; dS: 16.2, 22.7, 17.2, 23.7, 23.7, and 16.1 mm for gray objects, respectively. For the case of using lungs and airways as a reference object, the corresponding results are, nS: 4.0, 5.3, 4.1, 6.9, 6.9, and 7.4; dS: 15.0, 19.7, 15.3, 26.2, 26.2, and 27.9 mm for binary objects; nS: 3.9, 5.4, 3.6, 7.2, 7.2, and 7.6; dS: 14.6, 20.1, 13.7, 27.3, 27.3, and 28.6 mm for gray objects, respectively. Conclusions Precise body region identification automatically in whole‐body or body region tomographic images is vital for numerous medical image analysis and analytics applications. Despite its importance, this issue has received very little attention in the literature. We present a solution to this problem in this study using the conce...

show abstract

MR Image Analytics to Characterize the Upper Airway Structure in Obese Children with Obstructive Sleep Apnea Syndrome

Cited by 19 publications

References 34 publications

Radiomics-guided therapy for bladder cancer: Using an optimal biomarker approach to determine extent of bladder cancer invasion from t2-weighted magnetic resonance images

Radiomics-guided therapy for bladder cancer: Using an optimal biomarker approach to determine extent of bladder cancer invasion from t2-weighted magnetic resonance images

BRR‐Net: A tandem architectural CNN–RNN for automatic body region localization in CT images

Body region localization in whole‐body low‐dose CT images of PET/CT scans using virtual landmarks

Contact Info

Product

Resources

About