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

Abstract

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.

Computational Description of a Spinal Compression Mechanism based on Stress-Shielding in an Anteroposteriorly Osteolytic Lumbar Vertebra

“…Of course, this influence seems different for different levels of the vertebral column. Figure 1 shows larger deformation of an anteroposteriorly damaged thoracic vertebral body [9], in comparison to a lumbar vertebra, examined by the present study. In spite of larger deformation and failure of the thoracic vertebral body in this figure, instability of the posterior elements of the lumbar vertebra has exposed the spinal canal to larger compression.…”

Accurate Differentiation of Spinal Tuberculosis and Spinal Metastases Using MR-Based Deep Learning Algorithms

“…Li et al 25 extracted deep learning features from MRI images using ResNet18 and showed that the model can predict the molecular subtypes of gliomas. Furthermore, Chen et al 26 demonstrated that DL models based on attention mechanisms can accurately distinguish between multiple myeloma and spinal metastases. Our recent study showed that deep learning models are capable of identifying the primary tumor source of spinal metastases.…”

Radiomics Analysis for Multiple Myeloma: A Systematic Review with Radiomics Quality Scoring

“…In total, 8 out of 23 studies (34.8%) were published in radiology journals, 4/23 (17.4%) were published in oncological journals, 3/23 (13%) were published in nuclear medicine journals. More Chen [12] Frontiers in Oncology Oncology Q1 5.738 2022 China Ekert [13] Cancers Oncology Q1 6.575 2020 Germany Hwang [14] Scientific The methodological details of individual studies are presented in Table 2. A total of 2682 patients were examined in the 23 included studies.…”