Dwarfism computer-aided diagnosis algorithm based on multimodal pyradiomics

• Published in: Information fusion Vol. 80; pp. 137 - 145
• Main Authors: Qiu, Shi, Jin, Yi, Feng, Songhe, Zhou, Tao, Li, Yidong
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.04.2022
• Subjects: Brain-computer interface; Children; Computer-aided diagnosis; Dwarfism; Multimodal; Pyradiomics; Brain-computer interface; Dwarfism; Pyradiomics; Children; Multimodal; Computer-aided diagnosis
• ISSN: 1566-2535; 1872-6305; 1872-6305
• DOI: 10.1016/j.inffus.2021.11.012

•The tensor multi-level structure is established to segment the pituitary.•A multi-dimensional fusion model is established to enhance image features.•The imaging features and clinical manifestations are integrated to enhance the accuracy of detection. Dwarfism refers to the phenomenon that children with same gender and age are lower than two standard deviations of normal height in the same living environment. It is of great significance for early diagnosis and early treatment of dwarfism. Dwarfism can be divided into growth hormone deficiency (GHD) and idiopathic short stature (ISS). GHD can be distinguished by growth hormone, while ISS is difficult to distinguish because its hormone features are not obvious. Thus, a computer-aided diagnosis model based on brain image data and clinical features is established for the first time and a dwarfism prediction algorithm is proposed based on multimodal pyradiomics. Firstly, we establish the extraction of pituitary gland based on tensor and binary wavelet model, as the pituitary gland is an important organ that affects the growth hormone. Then, the multi-dimensional fusion model is established to distinguish dwarfism. In the process of distinguishment, the pyradiomics features and clinical features are extracted to distinguish together. Finally, dwarfism computer-aided diagnosis algorithm based on multimodal pyradiomics is realized.