AI-Assisted Diagnosis and Decision-Making Method in Developing Countries for Osteosarcoma

Abstract

Osteosarcoma is a malignant tumor derived from primitive osteogenic mesenchymal cells, which is extremely harmful to the human body and has a high mortality rate. Early diagnosis and treatment of this disease is necessary to improve the survival rate of patients, and MRI is an effective tool for detecting osteosarcoma. However, due to the complex structure and variable location of osteosarcoma, cancer cells are highly heterogeneous and prone to aggregation and overlap, making it easy for doctors to inaccurately predict the area of the lesion. In addition, in developing countries lacking professional medical systems, doctors need to examine mass of osteosarcoma MRI images of patients, which is time-consuming and inefficient, and may result in misjudgment and omission. For the sake of reducing labor cost and improve detection efficiency, this paper proposes an Attention Condenser-based MRI image segmentation system for osteosarcoma (OMSAS), which can help physicians quickly locate the lesion area and achieve accurate segmentation of the osteosarcoma tumor region. Using the idea of AttendSeg, we constructed an Attention Condenser-based residual structure network (ACRNet), which greatly reduces the complexity of the structure and enables smaller hardware requirements while ensuring the accuracy of image segmentation. The model was tested on more than 4000 samples from two hospitals in China. The experimental results demonstrate that our model has higher efficiency, higher accuracy and lighter structure for osteosarcoma MRI image segmentation compared to other existing models.

Image segmentation technology based on transformer in medical decision‐making system

“…Furthermore, during our experiments, we performed a comparative analysis of our model with several typical networks. We used six classical networks, FCN (2018) [63], PSPNet (2017) [64], MSFCN (2017) [65], MSRN (2018) [66] U-Net (2015) [35] FIGURE 9 Comparison of segmentation results of various algorithms for images containing tiny tumours.…”

“…The equipment needed to diagnose osteosarcoma is energy intensive and expensive. General hospitals can hardly bear it, resulting in high resistance to disease detection [9]. In addition, the regional disproportionate allocation of medical facilities in those countries.…”

Two‐stage coarse‐to‐fine method for pathological images in medical decision‐making systems

“…Relying on physicians alone to screen and diagnose pathologic images is inefficient and significantly more costly in terms of labor. This makes the diagnosis of diseases particularly difficult for developing countries with low levels of medical care and inadequate medical resources [42][43][44][45]. In this paper, we take osteosarcoma as our research object, a high-accuracy and low-cost osteosarcoma pathological image segmentation system-CRMIsPI is designed.…”

An effective data communication community establishment scheme in opportunistic networks

“…The three major business scenarios of 5G are: eMBB mobile broadband enhancement, mMTC large-scale IoT, and uRLLC ultra-reliable and ultra-low latency, of which mMTC large-scale IoT is the research content of this paper [32,33]. In the context of large-scale IoT [34,35], each device can be regarded as a data node with data collection, storage, and transmission functions, and due to the devices within a certain area, their communication preferences are partially similar [36][37][38][39], we can define these nodes and the network they are in as a community, as shown in Figure 1. Various devices in a city communicate with each other through the Internet.…”