Single-Photon Emission Computed Tomography/Computed Tomography Image-Based Radiomics for Discriminating Vertebral Bone Metastases From Benign Bone Lesions in Patients With Tumors

Abstract

Purpose: The purpose of this study was to investigate the feasibility of Single-Photon Emission Computed Tomography/Computed Tomography (SPECT/CT) image-based radiomics in differentiating bone metastases from benign bone lesions in patients with tumors.Methods: A total of 192 lesions from 132 patients (134 in the training group, 58 in the validation group) diagnosed with vertebral bone metastases or benign bone lesions were enrolled. All images were evaluated and diagnosed independently by two physicians with more than 20 years of diagnostic experience for qualitative classification, the images were imported into MaZda software in Bitmap (BMP) format for feature extraction. All radiomics features were selected by least absolute shrinkage and selection operator (LASSO) regression and 10-fold cross-validation algorithms after the process of normalization and correlation analysis. Based on these selected features, two models were established: The CT model and SPECT model (radiomics features were derived from CT and SPECT images, respectively). In addition, a combination model (ComModel) combined CT and SPECT features was developed in order to better evaluate the predictive performance of radiomics models. Subsequently, the diagnostic performance between each model was separately evaluated by a confusion matrix.Results: There were 12, 13, and 18 features contained within the CT, SPECT, and ComModel, respectively. The constructed radiomics models based on SPECT/CT images to discriminate between bone metastases and benign bone lesions not only had high diagnostic efficacy in the training group (AUC of 0.894, 0.914, 0.951 for CT model, SPECT model, and ComModel, respectively), but also performed well in the validation group (AUC; 0.844, 0.871, 0.926). The AUC value of the human experts was 0.849 and 0.839 in the training and validation groups, respectively. Furthermore, both SPECT model and ComModel show higher classification performance than human experts in the training group (P = 0.021 and P = 0.001, respectively) and the validation group (P = 0.037 and P = 0.007, respectively). All models showed better diagnostic accuracy than human experts in the training group and the validation group.Conclusion: Radiomics derived from SPECT/CT images could effectively discriminate between bone metastases and benign bone lesions. This technique may be a new non-invasive way to help prevent unnecessary delays in diagnosis and a potential contribution in disease staging and treatment planning.

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

“…Also, there are a few studies based on SPECT/ CT-based radiomics in relation to bone diseases. Jin [14] discovered that radiomics derived from SPECT/CT images are capable of efficiently differentiating between benign bone lesions and bone metastases. This technique could be a new noninvasive alternative to assist in avoiding needless diagnostic delays.…”

“…As for adults, Corino et al [39] found comparable findings. Yin et al [6] 2019 Retrospective Chordoma & Giant cell tumor CT 95 AUC = 0.79 Tagliafico et al [7] 2021 Retrospective Multiple myeloma CT 70 AUC = 0.79 Nie et al [8] 2023 Retrospective Chordoma & Giant cell tumor CT 111 AUC = 0.980 Li et al [10] 2019 Retrospective Chordoma & Chondrosarcoma MR 210 AUC = 0.87 Dai et al [11] 2020 Retrospective Osteosarcoma & Ewing sarcoma MR 66 AUC = 0.77-0.88 Mannam et al [12] 2023 Retrospective Skeletal metastases & Multiple myeloma PET/CT 40 AUC = 0.945 AUC = 0.9538 Jin et al [13] 2022 Retrospective Spine multiple myeloma & Bone metastasis PET/CT 131 AUC = 0.973 Jin et al [14] 2021 Retrospective Bone metastases & Benign bone lesions SPECT/CT 132 AUC = 0.951…”

Research in Musculoskeletal Radiology: Setting Goals and Strategic Directions

“…AI has also enabled the construction of predictive radiomics models for a multitude of MSK applications. Differentiation between benign and malignant osseous [19][20][21] and soft tissue lesions 21 has been performed with the use of radiomics data based on computed tomography (CT), MRI, and nuclear imaging, 22 used to build high accuracy machine learning models. Such models (with or without the addition of radiomics) have also been used to diagnose osteoarthritis [23][24][25][26] and osteoporosis 27 and to identify factors responsible for the development of early-onset osteoarthritis.…”

Establishment and validation of novel predictive models to predict bone metastasis in newly diagnosed prostate adenocarcinoma based on single-photon emission computed tomography radiomics

“…Radiomics models derived from SPECT/CT images can effectively discriminate between vertebral bone metastases and benign bone disease [15] . Unfortunately, only a few studies have used SPECT/CT radiomics to study bone metastases associated with PCa.…”