Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT

Chee, Choong Guen; Yoon, Min Ho; Kim, Kyung Won; Ko, Yusun; Ham, Su Jung; Cho, Young Chul; Park, Bumwoo; Chung, Hye Won

doi:10.1007/s00330-021-07832-x

Cited by 35 publications

(29 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, as all the patients enrolled in this study were from tertiary referral centers, the prevalence of malignant fractures was high. Second, although a previous study showed that the diagnostic performance of CT-based radiomics model for predicting fracture malignancy improved by integrating clinical parameters such as patient age and history of malignancy with radiomics features 6 , we developed the model using only the radiomics features, as the purpose of this study was to evaluate the applicability of the automated segmentation algorithm for use in radiomics. We believe that our radiomics model’s diagnostic accuracy measures can be improved by incorporating clinical parameters with radiomics features in the prediction model.…”

Section: Discussionmentioning

confidence: 99%

“…Image segmentation in radiomics can be performed manually, semi-automatically using methods such as region-growing or thresholding, or fully automatically using deep learning algorithms 1 . Although manual segmentation methods have been commonly used for the radiomics analysis of vertebrae 6 – 9 , manual delineation of the VOI is labor-intensive and time-consuming, especially for thin-slice CT of the spine yielding a large number of reconstructed images, making it prone to intra- and/or inter-observer variability 10 . Several automated approaches, including statistical shape models 11 , atlas-based methods 12 , active contours 13 , and intensity-based level-sets 14 , have been used for vertebral segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…The widespread availability, speed and affordability of CT have led to its frequent use in the evaluation of vertebral fractures. In several recent studies, CT radiomics has shown promising results in the evaluation of vertebral fractures 6 , 9 , including the ability to successfully differentiate malignant from acute benign compression fractures 6 . These findings suggest that CT radiomics may provide an alternative diagnostic approach to determine the etiology of vertebral fractures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Park

Yoon

Cho

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Although CT radiomics has shown promising results in the evaluation of vertebral fractures, the need for manual segmentation of fractured vertebrae limited the routine clinical implementation of radiomics. Therefore, automated segmentation of fractured vertebrae is needed for successful clinical use of radiomics. In this study, we aimed to develop and validate an automated algorithm for segmentation of fractured vertebral bodies on CT, and to evaluate the applicability of the algorithm in a radiomics prediction model to differentiate benign and malignant fractures. A convolutional neural network was trained to perform automated segmentation of fractured vertebral bodies using 341 vertebrae with benign or malignant fractures from 158 patients, and was validated on independent test sets (internal test, 86 vertebrae [59 patients]; external test, 102 vertebrae [59 patients]). Then, a radiomics model predicting fracture malignancy on CT was constructed, and the prediction performance was compared between automated and human expert segmentations. The algorithm achieved good agreement with human expert segmentation at testing (Dice similarity coefficient, 0.93–0.94; cross-sectional area error, 2.66–2.97%; average surface distance, 0.40–0.54 mm). The radiomics model demonstrated good performance in the training set (AUC, 0.93). In the test sets, automated and human expert segmentations showed comparable prediction performances (AUC, internal test, 0.80 vs 0.87, p = 0.044; external test, 0.83 vs 0.80, p = 0.37). In summary, we developed and validated an automated segmentation algorithm that showed comparable performance to human expert segmentation in a CT radiomics model to predict fracture malignancy, which may enable more practical clinical utilization of radiomics.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Park

Yoon

Cho

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although the RECIST 1.1 criteria are controversial in the evaluation of neoadjuvant therapy for STS, some STSs that respond biologically to radiotherapy may not shrink due to tumour enlargement due to necrosis, intratumoural haemorrhage, and cystic degeneration [18], but this study is a study of lung metastases, and the above situation does not apply. In previous studies, in the radiomics study of multiple lesions, a single lesion was usually selected for study in a single patient [19]. However, the delineation of ROIs in this study was different because there may be a single lung metastasis or multiple lung metastases in patients with STS.…”

Section: Discussionmentioning

confidence: 99%

Prediction of the therapeutic efficacy of epirubicin combined with ifosfamide in patients with lung metastases from soft tissue sarcoma based on chest enhanced CT radiomics features: a pilot study

Miao

Jiang

et al. 2022

Preprint

View full text Add to dashboard Cite

Objective To investigate the value of enhanced chest CT radiomics features in predicting the efficacy of epirubicin combined with ifosfamide in patients with pulmonary metastases from soft tissue sarcoma Methods In a retrospective analysis of 51 patients with pulmonary metastases from soft tissue sarcoma, all received the chemotherapy regimen of epirubicin combined with ifosfamide, and the efficacy was evaluated by the RECIST(1.1). Each patient selected 1 or 2 chemotherapy regimens. Lung metastases were used as target lesions (86 target lesions total), and the patients were divided into a progression group (n = 29) and a nonprogressive group (n = 57). The nonprogressive group included a stable group (n = 34) and a partial response group (n = 23). Information of lung metastases was extracted from enhanced CT images before chemotherapy, and all lesions were delineated by ITK-SNAP software manually or semiautomatically. The decision tree classifier had a better effect in all radiomics models. The receiver operating characteristic (ROC) curve was plotted to evaluate the predictive performance of the model for progression vs. nonprogression. Results In total, 851 enhanced CT radiomics features were extracted for each target lesion and finally reduced to 2 radiomics features, which were used to construct a radiomics model. The areas under the curve (AUCs) of the model for predicting the progression of lesions were 0.917 and 0.856 in the training and test groups. Conclusion The model established based on the radiomic features of chest enhanced CT before treatment has certain predictive value for the chemotherapy efficacy of patients with soft tissue sarcoma lung metastases.

show abstract

“… 40 Texture analysis based on CT images can provide numerous pixel-level texture parameters and more objectively depict lesions via mathematical algorithms, which reflect more stable patient information. 19 , 41 Accuracy, sensitivity, specificity, PPV, and NPV were measured to comprehensively evaluate the performance of the model, and were all good in our selected model. This indicated that a radiomic-based approach for CT scan femoral neck images with machine-learning algorithms can help mine valuable texture features related to femoral neck fracture, suggesting the potential utility and extensibility of a radiomic-based approach for predicting the prognosis of femoral neck–fracture patients receiving THA.…”

Section: Discussionmentioning

confidence: 99%

Prediction Models for Prognosis of Femoral Neck–Fracture Patients 6 Months after Total Hip Arthroplasty

Zheng¹,

Xiao²,

Xie³

et al. 2022

IJGM

View full text Add to dashboard Cite

Purpose To establish prediction models for 6-month prognosis in femoral neck–fracture patients receiving total hip arthroplasty (THA). Patients and Methods In total, 182 computed tomography image pairs from 85 patients were collected and divided into a training set (n=127) and testing set (n=55). Least absolute shrinkage–selection operator regression was used for selecting optimal predictors. A random-forest algorithm was used to establish the prediction models, which were evaluated for accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the curve (AUC). Results The best model in this study was constructed based on demographic data, preoperative laboratory indicators, and three preoperative radiomic features. In the random-forest model, activated partial thromboplastin time, a preoperative radiomic feature (maximum diameter), and fibrinogen were important variables correlating with patient outcomes. The AUC, sensitivity, specificity, PPV, NPV, and accuracy in the training set were 0.986 (95% CI 0.971–1), 0.925 (95% CI 0.862–0.988), 0.983 (95% CI 0.951–1.016), 0.984 (95% CI 0.953–1.014), 0.922 (95% CI 0.856–0.988), and 0.953 (95% CI 0.916–0.990), respectively. The AUC, sensitivity, specificity, PPV, NPV, and accuracy in the testing set were 0.949 (95% CI 0.885–1), 0.767 (95% CI 0.615–0.918), 1 (95% CI 1–1), 1 (95% CI 1–1), 0.781 (95% CI 0.638–0.924), and 0.873 (95% CI 0.785–0.961), respectively. Conclusion The model based on demographic, preoperative clinical, and preoperative radiomic data showed the best predictive ability for 6-month prognosis in the femoral neck–fracture patients receiving THA.

show abstract

Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT

Cited by 35 publications

References 43 publications

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Prediction of the therapeutic efficacy of epirubicin combined with ifosfamide in patients with lung metastases from soft tissue sarcoma based on chest enhanced CT radiomics features: a pilot study

Prediction Models for Prognosis of Femoral Neck–Fracture Patients 6 Months after Total Hip Arthroplasty

Contact Info

Product

Resources

About