A Novel Two-step Classification Approach for Differentiating Bone Metastases From Benign Bone Lesions in SPECT/CT Imaging.
Authors
Affiliations (5)
Affiliations (5)
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning 110167, China (W.X., L.M., X.P., Y.Z., Z.Y.); Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning 110016, China (W.X., X.W., M.L., L.M., X.P., Y.Z., J.Z., X.W., Y.D., Y.P., G.Z., Z.Y., Z.W.).
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning 110016, China (W.X., X.W., M.L., L.M., X.P., Y.Z., J.Z., X.W., Y.D., Y.P., G.Z., Z.Y., Z.W.).
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning 110016, China (W.X., X.W., M.L., L.M., X.P., Y.Z., J.Z., X.W., Y.D., Y.P., G.Z., Z.Y., Z.W.); Department of Nuclear Medicine, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi 710000, China (M.L.).
- School of Computer Science and Engineering, Northeastern University, Shenyang, Liaoning 110167, China (H.S.).
- Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning 110016, China (W.X., X.W., M.L., L.M., X.P., Y.Z., J.Z., X.W., Y.D., Y.P., G.Z., Z.Y., Z.W.). Electronic address: [email protected].
Abstract
This study aims to develop and validate a novel two-step deep learning framework for the automated detection, segmentation, and classification of bone metastases in SPECT/CT imaging, accurately distinguishing malignant from benign lesions to improve early diagnosis and facilitate personalized treatment planning. A segmentation model, BL-Seg, was developed to automatically segment lesion regions in SPECT/CT images, utilizing a multi-scale attention fusion module and a triple attention mechanism to capture metabolic variations and refine lesion boundaries. A radiomics-based ensemble learning classifier was subsequently applied to integrate metabolic and texture features for benign-malignant differentiation. The framework was trained and evaluated using a proprietary dataset of SPECT/CT images collected from our institution. Performance metrics, including Dice coefficient, sensitivity, specificity, and AUC, were compared against conventional methods. The study utilized a dataset of SPECT/CT cases from our institution, divided into training and test sets acquired on Siemens SPECT/CT scanners with minor protocol differences. BL-Seg achieved a Dice coefficient of 0.8797, surpassing existing segmentation models. The classification model yielded an AUC of 0.8502, with improved sensitivity and specificity compared to traditional approaches. The proposed framework, with BL-Seg's automated lesion segmentation, demonstrates superior accuracy in detecting, segmenting, and classifying bone metastases, offering a robust tool for early diagnosis and personalized treatment planning in metastatic bone disease.