Differential Diagnosis of Multiple Myeloma and Systemic Light Chain Amyloidosis Using Plasma Cell Morphology Based on Deep Learning

Multiple myeloma (MM) is a common hematological malignancy. There are approximately 588,161 people diagnosed with MM worldwide each year. At present, MM cannot be cured. But appropriate treatment can prolong the survival of patients. So, timely diagnosis of MM is very important. Systemic light chain amyloidosis（AL) is another kind of plasma cell-derived malignancy. There are several similarities and overlapping clinical manifestations of MM and AL. They both damage normal tissues and organs, leading to bone pain, osteoporosis, anemia, bleeding, etc. So they need to be identified. The different biological characteristics of neoplastic plasma cells are the important pathological basis of the different manifestations of the two diseases and structure is the basis of function. So we speculated that there may be differences in the morphology of plasma cells between the two diseases, leading to differences in the function of plasma cells.Bone marrow smears are a routine test for the diagnosis of MM and AL and can provide important clues for differentiation. The main method of bone marrow smear detection is manual detection, which requires considerable manpower and a long time, and the results are easily affected by the subjective factors of the tester. Artificial intelligence can improve the speed and accuracy of this process. At present, there are few reports of MM and AL identification via artificial intelligence recognition of plasma cell morphology. Therefore, we hypothesized that there are morphological differences between plasma cells in bone marrow smears from MM patients and AL patients. These differences could enable differential diagnosis between MM patients and AL patients. In addition, we established deep learning models for plasma cell recognition to identify MM patients and AL patients.

Bone marrow smears obtained from patients diagnosed with MM and AL in hospitals were retrospectively analyzed. The bone marrow cell images under Olympus BX51 with oil lens resolution (1000X) were obtained via the Windows camera and the Imagetion Toolbox acquisition kit of MATLAB. Single plasma cells were extracted via ImageJ/MATLAB to construct the dataset. Using the plasma cell dataset, the deep learning models used to identify MM and AL was trained on the ImageNet pretraining network models shufflenet, ResNet50, ResNet101, SqueezeNet, Inceptionv3, and MobileNetv2. The ratio of the training set ,the validation set and the test set is set to 7:2:1. The confusion matrix, receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) were used to evaluate the deep learning models.

We built a single plasma cell dataset of 10000+ which contains data from MM and AL. And we generated deep learning models on the basis of the pretrained network models of shufflenet, ResNet50, ResNet101, SqueezeNet, Inceptionv3, and MobileNetv2. By testing deep learning models, we obtained the confusion matrix of each model and calculated the accuracy, AUC, precision and recall. We found that the confusion matrix shows that most deep learning models misjudge only a small number of AL plasma cells as MM plasma cells. The accuracy of the deep learning models in identifying AL and MM plasma cells are above 0.97. The accuracy rates of shufflenet, ResNet50, ResNet101, SqueezeNet, Inceptionv3 and MobileNetv2 were 0.99, 0.99, 1.00, 0.99, 0.97 and 0.99, respectively. The AUC values were all above 0.95, and the AUC values of the six pretrained models were 0.9949, 0.9936, 0.9962, 0.9949, 0.9720 and 0.99. The accuracies of the six pretraining models are 0.99, 0.99, 0.99, 0.99, 0.95, and 0.9907. The recall rates of the six pretrained models are 1.00, 1.00, 1.00, 1.00, and 0.99. Among them, the accuracy, accuracy and recall rate of ResNet101 are the highest, are 1.00, 0.99 and 1.00, respectively. It has the best performance. Therefore, we concluded that The deep learning models based on plasma cell morphology could identify MM and AL plasma cells accurately.