Abstract
ObjectiveTo determine whether machine learning based on conventional magnetic resonance imaging (MRI) sequences have the potential for the differential diagnosis of multiple myeloma (MM), and different tumor metastasis lesions of the lumbar vertebra.MethodsWe retrospectively enrolled 107 patients newly diagnosed with MM and different metastasis of the lumbar vertebra. In total 60 MM lesions and 118 metastasis lesions were selected for training classifiers (70%) and subsequent validation (30%). Following segmentation, 282 texture features were extracted from both T1WI and T2WI images. Following regression analysis using the least absolute shrinkage and selection operator (LASSO) algorithm, the following machine learning models were selected: Support‐Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Artificial Neural Networks (ANN), and Naïve Bayes (NB) using 10-fold cross validation, and the performances were evaluated using a confusion matrix. Matthews correlation coefficient (MCC), sensitivity, specificity, and accuracy of the models were also calculated.ResultsTo differentiate MM and metastasis, 13 features in the T1WI images and 9 features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.605) with accuracy, sensitivity, and specificity of 0.815, 0.879, and 0.790, respectively, in the validation cohort. To differentiate MM and metastasis subtypes, eight features in the T1WI images and seven features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.560, 0.412, 0.449), respectively, with accuracy = 0.648; sensitivity 0.714, 0.821, 0.897 and specificity 0.775, 0.600, 0.640 for the MM, lung, and other metastases, respectively, in the validation cohort.ConclusionsMachine learning–based classifiers showed a satisfactory performance in differentiating MM lesions from those of tumor metastasis. While their value for distinguishing myeloma from different metastasis subtypes was moderate.
Highlights
Bone metastasis and multiple myeloma (MM) are two different diseases, both frequently involve bone marrow evaluation during clinical workup [1], which may result in bone pain and fractures for patients [2]
Inclusion criteria: [1] patients diagnosed with MM according to the International Myeloma Working Group Diagnostic Criteria [19] or metastatic tumors on lumbar vertebra confirmed by core needle or excisional biopsy; [2] patients with no magnetic resonance imaging (MRI) examination contradiction; [3] patients with intact and high quality MRI images before treatment, including sagittal T1WI and sagittal and transverse T2WI sequences; [4] at least one lesion having a diameter >1 cm; and [5] availability of complete clinical information
All patients in the study had no prior history of malignant tumor diagnosis, and all metastasis patients had been subjected to pathological analyses for primary cancer
Summary
Bone metastasis and multiple myeloma (MM) are two different diseases, both frequently involve bone marrow evaluation during clinical workup [1], which may result in bone pain and fractures for patients [2]. Metastases from lung cancer are the most prevalent type of metastases [4] If these lesions were accurately predicted by conventional magnetic resonance imaging (MRI), it would narrow the examination range to using chest CT, which is accessible and much cheaper. The identification of cheaper imaging examinations to detect primary cancer will provide a beneficial cost-effective approach for the management of patients. With regard to metastatic cancer, further follow-up for detecting the primary cancer may be needed before choosing the optimal treatment strategy, which may include surgery, radiation, and/or chemotherapy. While MRI can provide detailed morphological information about lesions and is the most sensitive imaging modality for tumor infiltration in bone marrow, MM and metastasis appear similar and are often indistinguishable [9], for multiple vertebra focal osteolytic lesions [10]. Previous studies have reported that vascular parameters measured by dynamiccontrast-enhanced (DCE) MRI can help identify primary spinal cancers [11, 12] and metastatic cancers of different primary tumors [13, 14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
