Cargando…

Gastrointestinal stromal tumors diagnosis on multi-center endoscopic ultrasound images using multi-scale image normalization and transfer learning

BACKGROUND: Automated diagnosis of gastrointestinal stromal tumors’ (GISTs) cancerization is an effective way to improve the clinical diagnostic accuracy and reduce possible risks of biopsy. Although deep convolutional neural networks (DCNNs) have proven to be very effective in many image classifica...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Chengcheng, Guo, Yi, Jiang, Fei, Xu, Leiming, Shen, Feng, Jin, Zhendong, Wang, Yuanyuan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: IOS Press 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9028612/
https://www.ncbi.nlm.nih.gov/pubmed/35124583
http://dx.doi.org/10.3233/THC-228005
Descripción
Sumario:BACKGROUND: Automated diagnosis of gastrointestinal stromal tumors’ (GISTs) cancerization is an effective way to improve the clinical diagnostic accuracy and reduce possible risks of biopsy. Although deep convolutional neural networks (DCNNs) have proven to be very effective in many image classification problems, there is still a lack of studies on endoscopic ultrasound (EUS) images of GISTs. It remains a substantial challenge mainly due to the data distribution bias of multi-center images, the significant inter-class similarity and intra-class variation, and the insufficiency of training data. OBJECTIVE: The study aims to classify GISTs into higher-risk and lower-risk categories. METHODS: Firstly, a novel multi-scale image normalization block is designed to perform same-size and same-resolution resizing on the input data in a parallel manner. A dilated mask is used to obtain a more accurate interested region. Then, we construct a multi-way feature extraction and fusion block to extract distinguishable features. A ResNet-50 model built based on transfer learning is utilized as a powerful feature extractor for tumors’ textural features. The tumor size features and the patient demographic features are also extracted respectively. Finally, a robust XGBoost classifier is trained on all features. RESULTS: Experimental results show that our proposed method achieves the AUC score of 0.844, which is superior to the clinical diagnosis performance. CONCLUSIONS: Therefore, the results have provided a solid baseline to encourage further researches in this field.