scholarly journals Novel Autosegmentation Spatial Similarity Metrics Capture the Time Required to Correct Segmentations Better than Traditional Metrics in a Thoracic Cavity Segmentation Workflow

2020 ◽  
Author(s):  
Kendall Kiser ◽  
Arko Barman ◽  
Sonja Stieb ◽  
Clifton D Fuller ◽  
Luca Giancardo
Keyword(s):  
Path Length ◽  
Rank Correlation ◽  
Correlation Coefficients ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Similarity Metrics ◽  
Automated Segmentation ◽  
Thoracic Cavity ◽  
Clinical Variables ◽  
Spatial Similarity

Introduction Automated segmentation templates can save clinicians time compared to de novo segmentation but may still take substantial time to review and correct. It has not been thoroughly investigated which automated segmentation-corrected segmentation similarity metrics best predict clinician correction time. Materials and Methods Bilateral thoracic cavity volumes in 329 CT scans were segmented by a UNet-inspired deep learning segmentation tool and subsequently corrected by a fourth-year medical student. Eight spatial similarity metrics were calculated between the automated and corrected segmentations and associated with correction times using Spearman′s rank correlation coefficients. Nine clinical variables were also associated with metrics and correction times using Spearman′s rank correlation coefficients or Mann-Whitney U tests. Results The added path length, false negative path length, and surface Dice similarity coefficient correlated better with correction time than traditional metrics, including the popular volumetric Dice similarity coefficient (respectively ρ = 0.69, ρ = 0.65, ρ = −0.48 versus ρ = −0.25; correlation p values < 0.001). Clinical variables poorly represented in the autosegmentation tool′s training data were often associated with decreased accuracy but not necessarily with prolonged correction time. Discussion Metrics used to develop and evaluate autosegmentation tools should correlate with clinical time saved. To our knowledge, this is only the second investigation of which metrics correlate with time saved. Validation of our findings is indicated in other anatomic sites and clinical workflows. Conclusion Novel spatial similarity metrics may be preferable to traditional metrics for developing and evaluating autosegmentation tools that are intended to save clinicians time.

scholarly journals Novel Autosegmentation Spatial Similarity Metrics Capture the Time Required to Correct Segmentations Better Than Traditional Metrics in a Thoracic Cavity Segmentation Workflow

2021 ◽  
Author(s):  
Kendall J. Kiser ◽  
Arko Barman ◽  
Sonja Stieb ◽  
Clifton D. Fuller ◽  
Luca Giancardo
Keyword(s):  
Path Length ◽  
Rank Correlation ◽  
Correlation Coefficients ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Similarity Metrics ◽  
Automated Segmentation ◽  
Thoracic Cavity ◽  
Spatial Similarity ◽  
Spearman’S Rank Correlation

AbstractAutomated segmentation templates can save clinicians time compared to de novo segmentation but may still take substantial time to review and correct. It has not been thoroughly investigated which automated segmentation-corrected segmentation similarity metrics best predict clinician correction time. Bilateral thoracic cavity volumes in 329 CT scans were segmented by a UNet-inspired deep learning segmentation tool and subsequently corrected by a fourth-year medical student. Eight spatial similarity metrics were calculated between the automated and corrected segmentations and associated with correction times using Spearman’s rank correlation coefficients. Nine clinical variables were also associated with metrics and correction times using Spearman’s rank correlation coefficients or Mann–Whitney U tests. The added path length, false negative path length, and surface Dice similarity coefficient correlated better with correction time than traditional metrics, including the popular volumetric Dice similarity coefficient (respectively ρ = 0.69, ρ = 0.65, ρ =  − 0.48 versus ρ =  − 0.25; correlation p values < 0.001). Clinical variables poorly represented in the autosegmentation tool’s training data were often associated with decreased accuracy but not necessarily with prolonged correction time. Metrics used to develop and evaluate autosegmentation tools should correlate with clinical time saved. To our knowledge, this is only the second investigation of which metrics correlate with time saved. Validation of our findings is indicated in other anatomic sites and clinical workflows. Novel spatial similarity metrics may be preferable to traditional metrics for developing and evaluating autosegmentation tools that are intended to save clinicians time.

scholarly journals Multiple U-Net-Based Automatic Segmentations and Radiomics Feature Stability on Ultrasound Images for Patients With Ovarian Cancer

2021 ◽  
Vol 10 ◽  
Author(s):  
Juebin Jin ◽  
Haiyan Zhu ◽  
Jindi Zhang ◽  
Yao Ai ◽  
Ji Zhang ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Pearson Correlation ◽  
Automatic Segmentation ◽  
Intraclass Correlation ◽  
Correlation Coefficients ◽  
Ground Truth ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Ultrasound Images ◽  
Target Volumes

Few studies have reported the reproducibility and stability of ultrasound (US) images based radiomics features obtained from automatic segmentation in oncology. The purpose of this study is to study the accuracy of automatic segmentation algorithms based on multiple U-net models and their effects on radiomics features from US images for patients with ovarian cancer. A total of 469 US images from 127 patients were collected and randomly divided into three groups: training sets (353 images), validation sets (23 images), and test sets (93 images) for automatic segmentation models building. Manual segmentation of target volumes was delineated as ground truth. Automatic segmentations were conducted with U-net, U-net++, U-net with Resnet as the backbone (U-net with Resnet), and CE-Net. A python 3.7.0 and package Pyradiomics 2.2.0 were used to extract radiomic features from the segmented target volumes. The accuracy of automatic segmentations was evaluated by Jaccard similarity coefficient (JSC), dice similarity coefficient (DSC), and average surface distance (ASD). The reliability of radiomics features were evaluated by Pearson correlation and intraclass correlation coefficients (ICC). CE-Net and U-net with Resnet outperformed U-net and U-net++ in accuracy performance by achieving a DSC, JSC, and ASD of 0.87, 0.79, 8.54, and 0.86, 0.78, 10.00, respectively. A total of 97 features were extracted from the delineated target volumes. The average Pearson correlation was 0.86 (95% CI, 0.83–0.89), 0.87 (95% CI, 0.84–0.90), 0.88 (95% CI, 0.86–0.91), and 0.90 (95% CI, 0.88–0.92) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. The average ICC was 0.84 (95% CI, 0.81–0.87), 0.85 (95% CI, 0.82–0.88), 0.88 (95% CI, 0.85–0.90), and 0.89 (95% CI, 0.86–0.91) for U-net++, U-net, U-net with Resnet, and CE-Net, respectively. CE-Net based segmentation achieved the best radiomics reliability. In conclusion, U-net based automatic segmentation was accurate enough to delineate the target volumes on US images for patients with ovarian cancer. Radiomics features extracted from automatic segmented targets showed good reproducibility and for reliability further radiomics investigations.

scholarly journals A Preliminary Study on Dependence of Mercury Distribution on the Degree of Coalification in Ningwu Coalfield, Shanxi, China

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3119
Author(s):  
Yinjiao Su ◽  
Xuan Liu ◽  
Yang Teng ◽  
Kai Zhang
Keyword(s):  
Linear Correlation ◽  
Bituminous Coal ◽  
Rank Correlation ◽  
Correlation Coefficients ◽  
Chemical Extraction ◽  
Mercury Distribution ◽  
Sequential Chemical Extraction ◽  
Average Proportion ◽  
Total Proportion ◽  
The Relationship

Mercury (Hg) is a toxic trace element emitted from coal conversion and utilization. Samples with different coal ranks and gangue from Ningwu Coalfield are selected and investigated in this study. For understanding dependence of mercury distribution characteristics on coalification degree, Pearson regression analysis coupled with Spearman rank correlation is employed to explore the relationship between mercury and sulfur, mercury and ash in coal, and sequential chemical extraction method is adopted to recognize the Hg speciation in the samples of coal and gangue. The measured results show that Hg is positively related to total sulfur content in coal and the affinity of Hg to different sulfur forms varies with the coalification degree. Organic sulfur has the biggest impact on Hg in peat, which becomes weak with increasing the coalification degree from lignite to bituminous coal. Sulfate sulfur is only related to Hg in peat or lignite as little content in coal. However, the Pearson linear correlation coefficients of Hg and pyritic sulfur are relatively high with 0.479 for lignite, 0.709 for sub-bituminous coal and 0.887 for bituminous coal. Hg is also related to ash content in coal, whose Pearson linear correlation coefficients are 0.504, 0.774 and 0.827 respectively, in lignite, sub-bituminous coal and bituminous coal. Furthermore, Hg distribution is directly depended on own speciation in coal. The total proportion of F2 + F3 + F4 is increased from 41.5% in peat to 87.4% in bituminous coal, but the average proportion of F5 is decreased from 56.8% in peat to 12.4% in bituminous coal. The above findings imply that both Hg and sulfur enrich in coal largely due to the migration from organic state to inorganic state with the increase of coalification degree in Ningwu Coalfield.

scholarly journals Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 1952
Author(s):  
May Phu Paing ◽  
Supan Tungjitkusolmun ◽  
Toan Huy Bui ◽  
Sarinporn Visitsattapongse ◽  
Chuchart Pintavirooj
Keyword(s):  
Deep Learning ◽  
Brain Infarction ◽  
Three Dimensional ◽  
Dice Similarity Coefficient ◽  
Automated Segmentation ◽  
Variational Mode Decomposition ◽  
Brain Scans ◽  
Automated Method ◽  
Mode Decomposition ◽  
Segmentation Task

Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.

scholarly journals Detection and Severity Classification of COVID-19 in CT Images Using Deep Learning

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 893
Author(s):  
Yazan Qiblawey ◽  
Anas Tahir ◽  
Muhammad E. H. Chowdhury ◽  
Amith Khandakar ◽  
Serkan Kiranyaz ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Early Stage ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Lung Region ◽  
Computed Tomography Images ◽  
Feature Pyramid ◽  
Severity Levels

Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder–Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.

scholarly journals Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning

2021 ◽  
pp. 002203452110053
Author(s):  
H. Wang ◽  
J. Minnema ◽  
K.J. Batenburg ◽  
T. Forouzanfar ◽  
F.J. Hu ◽  
...  
Keyword(s):  
Gold Standard ◽  
Orthodontic Treatment ◽  
3D Models ◽  
Similarity Coefficient ◽  
Patient Specific ◽  
Dice Similarity Coefficient ◽  
Surface Deviations ◽  
Surface Deviation ◽  
Binary Segmentation ◽  
Time Required

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network–based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

Quantitative Comparisons of Deep-learning-based and Atlas-based Auto-segmentation of the Intermediate Risk Clinical Target Volume for Nasopharyngeal Carcinoma

2021 ◽  
Vol 17 ◽  
Author(s):  
Yisong He ◽  
Shengyuan Zhang ◽  
Yong Luo ◽  
Hang Yu ◽  
Yuchuan Fu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Target Volume ◽  
Target Volume ◽  
Similarity Coefficient ◽  
Relative Volume ◽  
Dice Similarity Coefficient ◽  
Intermediate Risk ◽  
Segmentation Methods ◽  
Accuracy And Stability ◽  
Volume Difference

Background: Manual segment target volumes were time-consuming and inter-observer variability couldn’t be avoided. With the development of computer science, auto-segmentation had the potential to solve this problem. Objective: To evaluate the accuracy and stability of Atlas-based and deep-learning-based auto-segmentation of the intermediate risk clinical target volume, composed of CTV2 and CTVnd, for nasopharyngeal carcinoma quantitatively. Methods and Materials: A cascade-deep-residual neural network was constructed to automatically segment CTV2 and CTVnd by deep learning method. Meanwhile, a commercially available software was used to automatically segment the same regions by Atlas-based method. The datasets included contrast computed tomography scans from 102 patients. For each patient, the two regions were manually delineated by one experienced physician. The similarity between the two auto-segmentation methods was quantitatively evaluated by Dice similarity coefficient, the 95th Hausdorff distance, volume overlap error and relative volume difference, respectively. Statistical analyses were performed using the ranked Wilcoxon test. Results: The average Dice similarity coefficient (±standard deviation) given by the deep-learning-based and Atlas-based auto-segmentation were 0.84(±0.03) and 0.74(±0.04) for CTV2, 0.79(±0.02) and 0.68(±0.03) for CTVnd, respectively. For the 95th Hausdorff distance, the corresponding values were 6.30±3.55mm and 9.34±3.39mm for CTV2, 7.09±2.27mm and 14.33±3.98mm for CTVnd. Besides, volume overlap error and relative volume difference could also predict the same situations. Statistical analyses showed significant difference between the two auto-segmentation methods (p<0.01). Conclusions: Compared with the Atlas-based segmentation approach, the deep-learning-based segmentation method performed better both in accuracy and stability for meaningful anatomical areas other than organs at risk.

scholarly journals Comparison of a picture-sort food-frequency questionnaire with 24-hour dietary recalls in an elderly Utah population

2001 ◽  
Vol 4 (5) ◽  
pp. 961-970 ◽  
Author(s):  
Heidi J Wengreen ◽  
Ronald G Munger ◽  
Siew Sun Wong ◽  
Nancy A West ◽  
Richard Cutler
Keyword(s):  
Food Frequency Questionnaire ◽  
Dietary Assessment ◽  
Rank Correlation ◽  
Correlation Coefficients ◽  
Assessment Method ◽  
Impaired Hearing ◽  
Low Literacy ◽  
Food Frequency ◽  
Dietary Recall ◽  
Memory Skill

AbstractObjective:To evaluate the 137-item Utah Picture-sort Food-frequency Questionnaire (FFQ) in the measurement of usual dietary intake in older adults.Design:The picture-sort FFQ was administered at baseline and again one year later. Three seasonal 24-hour dietary recall interviews were collected during the year between the two FFQs. Mean nutrient intakes were compared between methods and between administrations of the FFQ.Setting:The FFQ interviews were administered in respondents' homes or care-centres. The 24-hour diet recalls were conducted by telephone interview on random days of the week.Subjects:Two-hundred-and-eight men and women aged 55–84 years were recruited by random sample of controls from a case–control study of nutrition and bone health in Utah.Results:After adjustment for total energy intake, median Spearman rank correlation coefficients between the two picture-sort FFQs were 0.69 for men aged ≤69 years, 0.66 for men aged >69 years; and 0.68 for women aged ≤69 years, 0.67 for women aged >69 years. Median correlation coefficients between methods were 0.50 for men ≤69 years old, 0.52 for men >69 years old; 0.55 for women ≤69 years old, 0.46 for women >69 years old.Conclusions:We report intake correlations between methods and administrations comparable to those reported in the literature for traditional paper-and-pencil FFQs and one other picture-sort method of FFQ. This dietary assessment method may improve ease and accuracy of response in this and other populations with low literacy levels, poor memory skill, impaired hearing, or poor vision.

Sign in / Sign up

Export Citation Format

Share Document