Search

PurposeMultiple 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.MethodsWe 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).ResultsAblation 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.ConclusionsThe 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.

Zezheng Liu,1,* Wenquan Liang,1,* Dawei Kang,1 Qingjing Chen,1 Zhicong Ouyang,1 Huibo Yan,1 Bin Huang,1 Dadi Jin,1 Yinkui Chen,2 Qingchu Li1 1Academy of Orthopedics, Guangdong Province, Department of Spine Surgery, The Third Affiliated Hospital of Southern Medical University, Guangzhou, People’s Republic of China; 2Department of Oncology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, People’s Republic of China*These authors contributed equally to this workCorrespondence: Qingchu LiDepartment of Spine Surgery, The Third Affiliated Hospital of Southern Medical University, Guangzhou, People’s Republic of ChinaEmail lqc16@263.netYinkui ChenDepartment of Oncology, The Third Affiliated Hospital of Southern Medical University, Guangzhou, People’s Republic of ChinaEmail clytze2@126.comIntroduction: Estrogen deficiency leads to bone loss in postmenopausal osteoporosis, because bone formation, albeit enhanced, fails to keep pace with the stimulated osteoclastic bone resorption. The mechanism driving this uncoupling is central to the pathogenesis of postmenopausal osteoporosis, which, however, remains poorly understood. We previously found that Cxcl9 secreted by osteoblasts inhibited osteogenesis in bone, while the roles of Cxcl9 on osteoclastic bone resorption and osteoporosis are unclear.Materials and Methods: Postmenopausal osteoporosis mouse model was established by bilateral surgical ovariectomy (OVX). In situ hybridization was performed to detect Cxcl9 mRNA expression in bone. ELISA assay was conducted to assess Cxcl9 concentrations in bone and serum. Cxcl9 activity was blocked by its neutralizing antibody. Micro-CT was performed to determine the effects of Cxcl9 neutralization on bone structure. Cell Migration and adhesion assay were conducted to evaluate the effects of Cxcl9 on osteoclast activity. TRAP staining and Western blot were performed to assess osteoclast differentiation. CXCR3 antagonist NBI-74,330 or ERK antagonist SCH772984 was administered to osteoclast to study the effects of Cxcl9 on CXCR3/ERK signaling.Results: Cxcl9 was expressed and secreted increasingly in OVX mice bone. Neutralizing Cxcl9 in bone marrow prevented bone loss in the mice by facilitating bone formation as well as inhibiting bone resorption. In vitro, Cxcl9 secreted from osteoblasts facilitated osteoclast precursors adhesion, migration and their differentiation into mature osteoclasts. The positive role of osteoblastic Cxcl9 on osteoclasts was eliminated by blocking CXCR3/ERK signaling in osteoclasts. Estrogen negatively regulated Cxcl9 expression and secretion in osteoblasts, explaining the increased Cxcl9 concentration in OVX mice bone.Conclusion: Our study illustrates the roles of Cxcl9 in inhibiting bone formation and stimulating bone resorption in osteoporotic bone, therefore providing a possible therapeutic target to the treatment of postmenopausal osteoporosis.Keywords: postmenopausal osteoporosis, bone resorption, osteoclast, Cxcl9