AI based diagnostics product design for osteosarcoma cells microscopy imaging of bone cancer patients using CA-MobileNet V3
Qian Liu, Xing She, Xia Qian
Abstract
• A modified CA-MobileNet V3 model that can automatically distinguish osteosarcoma cells from other cells on pathological images was explored. • The robustness and versatility of the model were ensured by using a public dataset, and the improved model had a recognition accuracy of up to 98.69%. • The method showed excellent performance in image recognition and can provide medical professionals with an efficient solution for diagnosing osteosarcoma in bone cancer patients. • An AI microscope integrating CA-MobileNet V3 was developed, and preliminary tests showed that the device has great application prospects in osteosarcoma diagnosis. The incidence of osteosarcoma (OS) is low, but primary malignant bone tumors rank third among the causes of death in cancer patients under the age of 20. Currently, analysis of cellular structure and tumor morphology through microscopic images remains one of the main diagnostic methods for osteosarcoma. However, this completely manual approach is tedious, time-consuming, and difficult to diagnose accurately due to the similarities in certain characteristics of malignant and benign tumors. Leveraging the potential of artificial intelligence (AI) in assessing and classifying images, this study explored a modified CA-MobileNet V3 model that was embedded into innovative microscope products to enhance the microscope’s feature extraction capabilities and help reduce misclassification during diagnosis. The intelligent recognition model method introduced in this paper has significant advantages in retrieval and classification of osteosarcoma cells and other cell types. Compared with models such as ShuffleNet V2, EfficientNet V2, Mobilenet V3 (without transfer learning), TL-MobileNet V3 (with transfer learning), etc., the model size is only 5.33 MB, is a lightweight model, and the accuracy of the improved model reached 98.69 %. In addition, the artificial intelligence microscope (AIM) with integrated design based on this model can also help improve diagnostic efficiency. The innovative method of the CA-MobileNet V3 automatic classification model based on deep learning provides an efficient and reliable solution for the pathological diagnosis of osteosarcoma. This study contributes to medical image analysis and provides doctors with an accurate and valuable tool for microscopic diagnosis. It also promotes the advancement of artificial intelligence in medical imaging technology.