Differentiation of benign and malignant spinal schwannoma using guided attention inference networks on multi-source MRI: comparison with radiomics method and radiologist-based clinical assessment.

BACKGROUND: Differentiating diagnosis between the benign schwannoma and the malignant counterparts merely by neuroimaging is not always clear and remains still confounding in many cases because of atypical imaging presentation encountered in clinic and the lack of specific diagnostic markers. PURPOSE: To construct and validate a novel deep learning model based on multi-source magnetic resonance imaging (MRI) in automatically differentiating malignant spinal schwannoma from benign. MATERIAL AND METHODS: We retrospectively reviewed MRI imaging data from 119 patients with the initial diagnosis of benign or malignant spinal schwannoma confirmed by postoperative pathology. A novel convolutional neural network (CNN)-based deep learning model named GAIN-CP (Guided Attention Inference Network with Clinical Priors) was constructed. An ablation study for the fivefold cross-validation and cross-source experiments were conducted to validate the novel model. The diagnosis performance among our GAIN-CP model, the conventional radiomics model, and the radiologist-based clinical assessment were compared using the area under the receiver operating characteristic curve (AUC) and balanced accuracy (BAC). RESULTS: The AUC score of the proposed GAIN method is 0.83, which outperforms the radiomics method (0.65) and the evaluations from the radiologists (0.67). By incorporating both the image data and the clinical prior features, our GAIN-CP achieves an AUC score of 0.95. The GAIN-CP also achieves the best performance on fivefold cross-validation and cross-source experiments. CONCLUSION: The novel GAIN-CP method can successfully classify malignant spinal schwannoma from benign cases using the provided multi-source MR images exhibiting good prospect in clinical diagnosis.

Enhanced brain parcellation via abnormality inpainting for neuroimage-based consciousness evaluation of hydrocephalus patients by lumbar drainage.

Brain network analysis based on structural and functional magnetic resonance imaging (MRI) is considered as an effective method for consciousness evaluation of hydrocephalus patients, which can also be applied to facilitate the ameliorative effect of lumbar cerebrospinal fluid drainage (LCFD). Automatic brain parcellation is a prerequisite for brain network construction. However, hydrocephalus images usually have large deformations and lesion erosions, which becomes challenging for ensuring effective brain parcellation works. In this paper, we develop a novel and robust method for segmenting brain regions of hydrocephalus images. Our main contribution is to design an innovative inpainting method that can amend the large deformations and lesion erosions in hydrocephalus images, and synthesize the normal brain version without injury. The synthesized images can effectively support brain parcellation tasks and lay the foundation for the subsequent brain network construction work. Specifically, the novelty of the inpainting method is that it can utilize the symmetric properties of the brain structure to ensure the quality of the synthesized results. Experiments show that the proposed brain abnormality inpainting method can effectively aid the brain network construction, and improve the CRS-R score estimation which represents the patient's consciousness states. Furthermore, the brain network analysis based on our enhanced brain parcellation method has demonstrated potential imaging biomarkers for better interpreting and understanding the recovery of consciousness in patients with secondary hydrocephalus.