Prediction of the early recurrence in spinal giant cell tumor of bone using radiomics of preoperative CT: Long-term outcome of 62 consecutive patients

A CT-based radiomics nomogram for predicting histologic grade and outcome in chondrosarcoma

OBJECTIVE

The preoperative identification of tumor grade in chondrosarcoma (CS) is crucial for devising effective treatment strategies and predicting outcomes. The study aims to build and validate a CT-based radiomics nomogram (RN) for the preoperative identification of tumor grade in CS, and to evaluate the correlation between the RN-predicted tumor grade and postoperative outcome.

METHODS

A total of 196 patients (139 in the training cohort and 57 in the external validation cohort) were derived from three different centers. A clinical model, radiomics signature (RS) and RN (which combines significant clinical factors and RS) were developed and validated to assess their ability to distinguish low-grade from high-grade CS with area under the curve (AUC). Additionally, Kaplan-Meier survival analysis was applied to examine the association between RN-predicted tumor grade and recurrence-free survival (RFS) of CS. The predictive accuracy of the RN was evaluated using Harrell's concordance index (C-index), hazard ratio (HR) and AUC.

RESULTS

Size, endosteal scalloping and active periostitis were selected to build the clinical model. Three radiomics features, based on CT images, were selected to construct the RS. Both the RN (AUC, 0.842) and RS (AUC, 0.835) were superior to the clinical model (AUC, 0.776) in the validation set (P = 0.003, 0.040, respectively). A correlation between Nomogram score (Nomo-score, derived from RN) and RFS was observed through Kaplan-Meier survival analysis in the training and test cohorts (log-rank P < 0.050). Patients with high Nomo-score tumors were 2.669 times more likely to suffer recurrence than those with low Nomo-score tumors (HR, 2.669, P < 0.001).

CONCLUSIONS

The CT-based RN performed well in predicting both the histologic grade and outcome of CS.

Research status and progress of radiomics in bone and soft tissue tumors: A review

Bone and soft tissue tumors are diverse, accompanying by complex histological components and significantly divergent biological behaviors. It is a challenge to address the demand for qualitative imaging as traditional imaging is restricted to the detection of anatomical structures and aberrant signals. With the improvement of digitalization in hospitals and medical centers, the introduction of electronic medical records and easier access to large amounts of information coupled with the improved computational power, traditional medicine has evolved into the combination of human brain, minimal data, and artificial intelligence. Scholars are committed to mining deeper levels of imaging data, and radiomics is worthy of promotion. Radiomics extracts subvisual quantitative features, analyzes them based on medical images, and quantifies tumor heterogeneity by outlining the region of interest and modeling. Two observers separately examined PubMed, Web of Science and CNKI to find existing studies, case reports, and clinical guidelines about research status and progress of radiomics in bone and soft tissue tumors from January 2010 to February 2023. When evaluating the literature, factors such as patient age, medical history, and severity of the condition will be considered. This narrative review summarizes the application and progress of radiomics in bone and soft tissue tumors.

A diagnostic approach integrated multimodal radiomics with machine learning models based on lumbar spine CT and X-ray for osteoporosis

INTRODUCTION

The aim of this analysis is to construct a combined model that integrates radiomics, clinical risk factors, and machine learning algorithms to diagnose osteoporosis in patients and explore its potential in clinical applications.

MATERIALS AND METHODS

A retrospective analysis was conducted on 616 lumbar spine. Radiomics features were extracted from the computed tomography (CT) scans and anteroposterior and lateral X-ray images of the lumbar spine. Logistic regression (LR), support vector machine (SVM), and random forest (RF) algorithms were used to construct radiomics models. The receiver operating characteristic curve (ROC) was employed to select the best-performing model. Clinical risk factors were identified through univariate logistic regression analysis (ULRA) and multivariate logistic regression analysis (MLRA) and utilized to develop a clinical model. A combined model was then created by merging radiomics and clinical risk factors. The performance of the models was evaluated using ROC curve analysis, and the clinical value of the models was assessed using decision curve analysis (DCA).

RESULTS

A total of 4858 radiomics features were extracted. Among the radiomics models, the SVM model demonstrated the optimal diagnostic capabilities and accuracy, with an area under the curve (AUC) of 0.958 (0.9405-0.9762) in the training cohort and 0.907 (0.8648-0.9492) in the test cohort. Furthermore, the combined model exhibited an AUC of 0.959 (0.9412-0.9763) in the training cohort and 0.910 (0.8690-0.9506) in the test cohort.

CONCLUSION

The combined model displayed outstanding ability in diagnosing osteoporosis, providing a safe and efficient method for clinical decision-making.

Machine learning-based radiomics analysis for predicting local recurrence of primary dermatofibrosarcoma protuberans after surgical treatment

BACKGROUND AND PURPOSE

Dermatofibrosarcoma protuberans (DFSP) is characterized by locally invasive growth patterns and high local recurrence rates. Accurately identifying patients with high local recurrence risk may benefit patients during follow-up and has potential value for making treatment decisions. This study aimed to investigate whether machine learning-based radiomics models could accurately predict the local recurrence of primary DFSP after surgical treatment.

MATERIALS AND METHODS

This retrospective study included a total of 146 patients with DFSP who underwent MRI scans between 2010 and 2016 from two different institutions: institution 1 (n = 104) for the training set and institution 2 (n = 42) for the external test set. Three radiomics random survival forest (RSF) models were developed using MRI images. Additionally, the performance of the Ki67 index was compared with the three RSF models in the external validation set.

RESULTS

The average concordance index (C-index) scores of the RSF models based on fat-saturation T2W (FS-T2W) images, fat-saturation T1W with gadolinium contrast (FS-T1W + C) images, and both FS-T2W and FS-T1W + C images from 10-fold cross-validation in the training set were 0.855 (95% CI: 0.629, 1.00), 0.873 (95% CI: 0.711, 1.00), and 0.875 (95% CI: 0.688, 1.00), respectively. In the external validation set, the C-indexes of the three trained RSF models were higher than that of the Ki67 index (0.838, 0.754, and 0.866 vs. 0.601, respectively).

CONCLUSION

Random survival forest models developed using radiomics features derived from MRI images were proven helpful for accurate prediction of local recurrence of primary DFSP after surgical treatment and showed better predicting performance than the Ki67 index.

A systematic review of radiomics in giant cell tumor of bone (GCTB): the potential of analysis on individual radiomics feature for identifying genuine promising imaging biomarkers

PURPOSE

To systematically assess the quality of radiomics research in giant cell tumor of bone (GCTB) and to test the feasibility of analysis at the level of radiomics feature.

METHODS

We searched PubMed, Embase, Web of Science, China National Knowledge Infrastructure, and Wanfang Data to identify articles of GCTB radiomics until 31 July 2022. The studies were assessed by radiomics quality score (RQS), transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) statement, checklist for artificial intelligence in medical imaging (CLAIM), and modified quality assessment of diagnostic accuracy studies (QUADAS-2) tool. The radiomic features selected for model development were documented.

RESULTS

Nine articles were included. The average of the ideal percentage of RQS, the TRIPOD adherence rate and the CLAIM adherence rate were 26%, 56%, and 57%, respectively. The risk of bias and applicability concerns were mainly related to the index test. The shortness in external validation and open science were repeatedly emphasized. In GCTB radiomics models, the gray level co-occurrence matrix features (40%), first order features (28%), and gray-level run-length matrix features (18%) were most selected features out of all reported features. However, none of the individual feature has appeared repeatably in multiple studies. It is not possible to meta-analyze radiomics features at present.

CONCLUSION

The quality of GCTB radiomics studies is suboptimal. The reporting of individual radiomics feature data is encouraged. The analysis at the level of radiomics feature has potential to generate more practicable evidence for translating radiomics into clinical application.

Machine learning-based CT radiomics model to discriminate the primary and secondary intracranial hemorrhage

It is challenging to distinguish between primary and secondary intracranial hemorrhage (ICH) purely by imaging data, and the two forms of ICHs are treated differently. This study aims to evaluate the potential of CT-based machine learning to identify the etiology of ICHs and compare the effectiveness of two regions of interest (ROI) sketching methods. A total of 1702 radiomic features were extracted from the CT brain images of 238 patients with acute ICH. We used the Select K Best method, least absolute shrinkage, and selection operator logistic regression to select the most discriminable features with a support vector machine to build a classifier model. Then, a ten-fold cross-validation strategy was employed to evaluate the performance of the classifier. From all quantitative CT-based imaging features obtained by two sketch methods, eighteen features were selected respectively. The radiomics model outperformed radiologists in distinguishing between primary and secondary ICH in both the volume of interest and the three-layer ROI sketches. As a result, a machine learning-based CT radiomics model can improve the accuracy of identifying primary and secondary ICH. A three-layer ROI sketch can identify primary versus secondary ICH based on the CT radiomics method.

Radiomics in clinical trials: perspectives on standardization

The term biomarker is used to describe a biological measure of the disease behavior. The existing imaging biomarkers are associated with the known tissue biological characteristics and follow a well-established roadmap to be implemented in routine clinical practice. Recently, a new quantitative imaging analysis approach named radiomics has emerged. It refers to the extraction of a large number of advanced imaging features with high-throughput computing. Extensive research has demonstrated its value in predicting disease behavior, progression, and response to therapeutic options. However, there are numerous challenges to establishing it as a clinically viable solution, including lack of reproducibility and transparency. The data-driven nature also does not offer insights into the underpinning biology of the observed relationships. As such, additional effort is needed to establish it as a qualified biomarker to inform clinical decisions. Here we review the technical difficulties encountered in the clinical applications of radiomics and current effort in addressing some of these challenges in clinical trial designs. By addressing these challenges, the true potential of radiomics can be unleashed.

Prognostic Value and Quantitative CT Analysis in RANKL Expression of Spinal GCTB in the Denosumab Era: A Machine Learning Approach

The receptor activator of the nuclear factor kappa B ligand (RANKL) is the therapeutic target of denosumab. In this study, we evaluated whether radiomics signature and machine learning analysis can predict RANKL status in spinal giant cell tumors of bone (GCTB). This retrospective study consisted of 107 patients, including a training set (n = 82) and a validation set (n = 25). Kaplan-Meier survival analysis was used to validate the prognostic value of RANKL status. Radiomic feature extraction of three heterogeneous regions (VOIentire, VOIedge, and VOIcore) from pretreatment CT were performed. Followed by feature selection using Selected K Best and least absolute shrinkage and selection operator (LASSO) analysis, three classifiers (random forest (RF), support vector machine, and logistic regression) were used to build models. The area under the curve (AUC), accuracy, F1 score, recall, precision, sensitivity, and specificity were used to evaluate the models' performance. Classification of 75 patients with eligible follow-up based on RANKL status resulted in a significant difference in progression-free survival (p = 0.035). VOIcore-based RF classifier performs best. Using this model, the AUCs for the training and validation cohorts were 0.880 and 0.766, respectively. In conclusion, a machine learning approach based on CT radiomic features could discriminate prognostically significant RANKL status in spinal GCTB, which may ultimately aid clinical decision-making.

Differentiation between spinal multiple myeloma and metastases originated from lung using multi-view attention-guided network

Purpose

Multiple myeloma (MM) and metastasis originated are the two common malignancy diseases in the spine. They usually show similar imaging patterns and are highly demanded to differentiate for precision diagnosis and treatment planning. The objective of this study is therefore to construct a novel deep-learning-based method for effective differentiation of two diseases, with the comparative study of traditional radiomics analysis.

Methods

We retrospectively enrolled a total of 217 patients with 269 lesions, who were diagnosed with spinal MM (79 cases, 81 lesions) or spinal metastases originated from lung cancer (138 cases, 188 lesions) confirmed by postoperative pathology. Magnetic resonance imaging (MRI) sequences of all patients were collected and reviewed. A novel deep learning model of the Multi-view Attention-Guided Network (MAGN) was constructed based on contrast-enhanced T1WI (CET1) sequences. The constructed model extracts features from three views (sagittal, coronal and axial) and fused them for a more comprehensive differentiation analysis, and the attention guidance strategy is adopted for improving the classification performance, and increasing the interpretability of the method. The diagnostic efficiency among MAGN, radiomics model and the radiologist assessment were compared by the area under the receiver operating characteristic curve (AUC).

Results

Ablation studies were conducted to demonstrate the validity of multi-view fusion and attention guidance strategies: It has shown that the diagnostic model using multi-view fusion achieved higher diagnostic performance [ACC (0.79), AUC (0.77) and F1-score (0.67)] than those using single-view (sagittal, axial and coronal) images. Besides, MAGN incorporating attention guidance strategy further boosted performance as the ACC, AUC and F1-scores reached 0.81, 0.78 and 0.71, respectively. In addition, the MAGN outperforms the radiomics methods and radiologist assessment. The highest ACC, AUC and F1-score for the latter two methods were 0.71, 0.76 & 0.54, and 0.69, 0.71, & 0.65, respectively.

Conclusions

The proposed MAGN can achieve satisfactory performance in differentiating spinal MM between metastases originating from lung cancer, which also outperforms the radiomics method and radiologist assessment.

Incremental Value of Radiomics in 5-Year Overall Survival Prediction for Stage II-III Rectal Cancer

Although rectal cancer comprises up to one-third of colorectal cancer cases and several prognosis nomograms have been established for colon cancer, statistical tools for predicting long-term survival in rectal cancer are lacking. In addition, previous prognostic studies did not include much imaging findings, qualitatively or quantitatively. Therefore, we include multiparametric MRI information from both radiologists' readings and quantitative radiomics signatures to construct a prognostic model that allows 5-year overall survival (OS) prediction for advance-staged rectal cancer patients. The result suggested that the model combined with quantitative imaging findings might outperform that of conventional TNM staging or other clinical prognostic factors. It was noteworthy that the identified radiomics signature consisted of three from dynamic contrast-enhanced (DCE)-MRI, four from anatomical MRI, and one from functional diffusion-weighted imaging (DWI). This highlighted the importance of multiparametric MRI to address the issue of long-term survival estimation in rectal cancer. Additionally, the constructed radiomics signature demonstrated value to the conventional prognostic factors in predicting 5-year OS for stage II-III rectal cancer. The presented nomogram also provides a practical example of individualized prognosis estimation and may potentially impact treatment strategies.

Clinical parameters combined with radiomics features of PET/CT can predict recurrence in patients with high-risk pediatric neuroblastoma

Background

This retrospective study aimed to develop and validate a combined model based [¹⁸F]FDG PET/CT radiomics and clinical parameters for predicting recurrence in high-risk pediatric neuroblastoma patients.

Methods

Eighty-four high-risk neuroblastoma patients were retrospectively enrolled and divided into training and test sets according to the ratio of 3:2. [¹⁸F]FDG PET/CT images of the tumor were segmented by 3D Slicer software and the radiomics features were extracted. The effective features were selected by the least absolute shrinkage and selection operator to construct the radiomics score (Rad_score). And the radiomics model (R_model) was constructed based on Rad_score for prediction of recurrence. Then, univariate and multivariate analyses were used to screen out the independent clinical risk parameters and construct the clinical model (C_model). A combined model (RC_model) was developed based on the Rad_score and independent clinical risk parameters and presented as radiomics nomogram. The performance of the above three models was assessed by the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).

Results

Seven radiomics features were selected for building the R_model. The AUCs of the C_model in training and test sets were 0.744 (95% confidence interval [CI], 0.595–0.874) and 0.750 (95% CI, 0.577–0.904), respectively. The R_model yielded AUCs of 0.813 (95% CI, 0.685–0.916) and 0.869 (95% CI, 0.715–0.985) in the training and test sets, respectively. The RC_model demonstrated the largest AUCs of 0.889 (95% CI, 0.794–0.963) and 0.892 (95% CI, 0.758–0.992) in the training and test sets, respectively. DCA demonstrated that RC_model added more net benefits than either the C_model or the R_model for predicting recurrence in high-risk pediatric neuroblastoma.

Conclusions

The combined model performed well for predicting recurrence in high-risk pediatric neuroblastoma, which can facilitate disease follow-up and management in clinical practice.

State of the Art and New Concepts in Giant Cell Tumor of Bone: Imaging Features and Tumor Characteristics

Simple Summary

The 2020 World Health Organization classification of soft tissue and bone tumors classified the giant cell tumor of bone (GCTB) as an intermediate malignant tumor, with locally aggressive behavior and high recurrence rate. Imaging plays a pivotal role in the assessment of GCTB, and this review tries to summarize the main concepts about GCTB histopathogenesis and new biomarkers, describing those GCTB imaging findings which could possibly be explained by tumor molecular alterations. We have illustrated pre-operative imaging features related to prognosis and radiological findings for response evaluation after surgical treatment and denosumab administration. We have also reported the results described in literature regarding the role of radiomics in aiding GCTB diagnosis, predicting possible post-treatment recurrence and providing a quantitative assessment of the response to denosumab treatment.

Abstract

Giant cell tumor of bone (GCTB) is classified as an intermediate malignant tumor due to its locally aggressive behavior, burdened by high local recurrence rate. GCTB accounts for about 4–5% of all primary bone tumors and typically arises in the metaphysis and epiphyses of the long tubular bones. Mutation of gene H3F3A is at the basis of GCTB etiopathogenesis, and its immunohistochemical expression is a valuable method for practical diagnosis, even if new biomarkers have been identified for early diagnosis and for potential tumor recurrence prediction. In the era of computer-aided diagnosis, imaging plays a key role in the assessment of GCTB for surgical planning, patients’ prognosis prediction and post treatment evaluation. Cystic changes, penetrating irregular margins and adjacent soft tissue invasion on preoperative Magnetic Resonance Imaging (MRI) have been associated with a higher rate of local recurrence. Distance from the tumor edge to the articular surface and thickness of unaffected cortical bone around the tumor should be evaluated on Computed Tomography (CT) as related to local recurrence. Main features associated with local recurrence after curettage are bone resorption around the graft or cement, soft tissue mass formation and expansile destruction of bone. A denosumab positive response is represented by a peripherical well-defined osteosclerosis around the lesion and intralesional ossification. Radiomics has proved to offer a valuable contribution in aiding GCTB pre-operative diagnosis through clinical-radiomics models based on CT scans and multiparametric MR imaging, possibly guiding the choice of a patient-tailored treatment. Moreover, radiomics models based on texture analysis demonstrated to be a promising alternative solution for the assessment of GCTB response to denosumab both on conventional radiography and CT since the quantitative variation of some radiomics features after therapy has been correlated with tumor response, suggesting they might facilitate disease monitoring during post-denosumab surveillance.

Measuring the bias of incorrect application of feature selection when using cross-validation in radiomics

BACKGROUND

Many studies in radiomics are using feature selection methods to identify the most predictive features. At the same time, they employ cross-validation to estimate the performance of the developed models. However, if the feature selection is performed before the cross-validation, data leakage can occur, and the results can be biased. To measure the extent of this bias, we collected ten publicly available radiomics datasets and conducted two experiments. First, the models were developed by incorrectly applying the feature selection prior to cross-validation. Then, the same experiment was conducted by applying feature selection correctly within cross-validation to each fold. The resulting models were then evaluated against each other in terms of AUC-ROC, AUC-F1, and Accuracy.

RESULTS

Applying the feature selection incorrectly prior to the cross-validation showed a bias of up to 0.15 in AUC-ROC, 0.29 in AUC-F1, and 0.17 in Accuracy.

CONCLUSIONS

Incorrect application of feature selection and cross-validation can lead to highly biased results for radiomic datasets.

Computerised tomography features of giant cell tumour of the knee are associated with local recurrence after extended curettage

Background

Extended curettage has increasingly become the preferred treatment for giant cell tumour of bone (GCTB), but the high recurrence rate after curettage poses a major challenge for orthopaedic surgeons. Computed tomography (CT) is valuable in the evaluation of GCTB. Our aim was to identify specific features of GCTB around the knee in pre-operative CT images that might have prognostic value for local recurrence.

Methods

We retrospectively analyzed data from 124 patients with primary GCTB around the knee who underwent extended curettage from 2010 through 2019. We collected demographic, clinical, and therapeutic data along with several CT-derived tumour characteristics. CT-derived tumor characteristics included tumour size, the distance between the tumour edge and articular surface (DTA), and destruction of posterior cortical bone (DPC). Akaike information criterion (AIC) was used to select which variables to enter into multivariate logistic regression models and to determine significant factors affecting recurrence.

Results

The total recurrence rate was 21.0% (26/124), and the average follow-up time was 69.5 ± 31.2 months (24–127 months). Age, DTA (< 2 mm), and DPC were significantly related to recurrence, as determined by multivariate logistic regression. The C-index of the final model was 0.79 (95% CI: 0.71 to 0.88), representing a good model for predicting recurrence.

Conclusion

Identifying certain features of GCTB around the knee on CT has prognostic value for patients treated with extended curettage. A three-factor model predicts tumour recurrence well after extended curettage.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00264-021-05260-6.