A Novel Medical Decision-Making System Based on Multi-Scale Feature Enhancement for Small Samples

• Published in: Mathematics (Basel) Vol. 11; no. 9; p. 2116
• Main Authors: He, Keke, Qin, Yue, Gou, Fangfang, Wu, Jia
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.04.2023
• Subjects: Accuracy; Automation; Bone cancer; Brain cancer; Decision making; decision-making system; Deep learning; Developing countries; Diagnosis; Disease; few-shot; Image segmentation; imaging segmentation; LDCs; Magnetic resonance imaging; Mathematics; Medical diagnosis; Medical imaging; Medical imaging equipment; Medical prognosis; Medical research; Methods; multi-scale feature enhancement; Patients; Physicians; Tumors; Workloads; China
• ISSN: 2227-7390; 2227-7390
• DOI: 10.3390/math11092116

The medical decision-making system is an advanced system for patients that can assist doctors in their medical work. Osteosarcoma is a primary malignant tumor of the bone, due to its specificity, such as its blurred borders, diverse tumor morphology, and inconsistent scales. Diagnosis is quite difficult, especially for developing countries, where medical resources are inadequate per capita and there is a lack of professionals, and the time spent in the diagnosis process may lead to a gradual deterioration of the disease. To address these, we discuss an osteosarcoma-assisted diagnosis system (OSADS) based on small samples with multi-scale feature enhancement that can assist doctors in performing preliminary automatic segmentation of osteosarcoma and reduce the workload. We proposed a multi-scale feature enhancement network (MFENet) based on few-shot learning in OSADS. Global and local feature information is extracted to effectively segment the boundaries of osteosarcoma by feeding the images into MFENet. Simultaneously, a prior mask is introduced into the network to help it maintain a certain accuracy range when segmenting different shapes and sizes, saving computational costs. In the experiments, we used 5000 osteosarcoma MRI images provided by Monash University for testing. The experiments show that our proposed method achieves 93.1% accuracy and has the highest comprehensive evaluation index compared with other methods.