30 January 2024 in Frontiers in Neuroscience
Background and purpose: The differential diagnosis between solid glioma and brain inflammation is necessary but sometimes difficult. We assessed the effectiveness of multiple diffusion metrics of diffusion-weighted imaging (DWI) in differentiating solid glioma from brain inflammation and compared the diagnostic performance of different DWI models.Materials and methods: Participants diagnosed with either glioma or brain inflammation with a solid lesion on MRI were enrolled in this prospective study from May 2016 to April 2023. Diffusion-weighted imaging was performed using a spin-echo echo-planar imaging sequence with five b values (500, 1,000, 1,500, 2000, and 2,500 s/mm2) in 30 directions for each b value, and one b value of 0 was included. The mean values of multiple diffusion metrics based on diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), mean apparent propagator (MAP), and neurite orientation dispersion and density imaging (NODDI) in the abnormal signal area were calculated. Comparisons between glioma and inflammation were performed. The area under the curve (AUC) of the receiver operating characteristic curve (ROC) of diffusion metrics were calculated.Results: 57 patients (39 patients with glioma and 18 patients with inflammation) were finally included. MAP model, with its metric non-Gaussianity (NG), shows the greatest diagnostic performance (AUC = 0.879) for differentiation of inflammation and glioma with atypical MRI manifestation. The AUC of DKI model, with its metric mean kurtosis (MK) are comparable to NG (AUC = 0.855), followed by NODDI model with intracellular volume fraction (ICVF) (AUC = 0.825). The lowest value was obtained in DTI with mean diffusivity (MD) (AUC = 0.758).Conclusion: Multiple diffusion metrics can be used in differentiation of inflammation and solid glioma. Non-Gaussianity (NG) from mean apparent propagator (MAP) model shows the greatest diagnostic performance for differentiation of inflammation and glioma.
18 August 2021 in IEEE Transactions on Industrial Informatics
In this article, glioma segmentation in the glioma grading computer-aided diagnosis (CAD) system requires manual delineation from radiologists, adding substantially to their workload. Although automatic segmentation is powerful, it cannot fully delegate power to artificial intelligence. We propose an AI-powered radiomics algorithm based on slice pooling (AI-RASP). AI-RASP generated compress images by compressing the gray value of each magnetic resonance imaging slice for radiologists to segment manually. In addition, AI-RASP integrated radiomics models to verify the glioma grading effect and the availability of compressed images. AI-RASP significantly reduce the time of manual segmentation. Results reported on multicenter datasets reveal that our architecture is better than the traditional manual segmentation while being over five times faster. The radiomics model with slice pooling mechanism achieves an area under the curve values of 0.86, 086, and 0.83 in the validation cohorts. Radiologists and patients can benefit from a CAD system integrated with AI-RASP.
31 August 2020 in IEEE Access
The access to and sharing of medical image data is essential to accelerate the research progress of complex diseases and sudden disease outbreaks. Multicenter image data is collected from different medical institutions, and the contrast and brightness of the images are significantly different, making it difficult to use the images directly. Herein, we introduce a standardized method based on magnetic resonance imaging, referred to as Histogram specification–grid search (HS–GS), which is mainly used to eliminate differences in image contrast and brightness. A Gaussian probability density function with adjustable parameters is used to generate the cumulative distribution function, and the transfer function required for the HS mapping is constructed to obtain standardized image sets based on the controllable parameters. The image sets are used to perform the GS task of radiomics classification to find the optimal controllable parameter combination and classification results, and then obtain the optimal standardized image sets. We used HS–GS to test and verify the predictive ability of the standardized mixed image sets for glioma grading, and compared it with existing methods. The experiments indicate that the standardized image sets generated by the HS–GS algorithm retain excellent stability after mixing and also show excellent classification performance. This novel image set standardization technique has proven to be a promising solution for integration into medical expert systems.
1 July 2023 in Current Medical Imaging
Introduction: Scrotal leiomyoma is a rare benign mesenchymal neoplasm that originates from smooth muscles. Up to now, the exact tumor properties remain unclear. Case Presentation: A 53-year-old male presented with intermittent mild pain and constant heaviness in the right scrotum for 1 year. The physical examination revealed a 6.5 cm by 5.5 cm by 5.5 cm sized, firm, mobile and non-tender lump within the inferior right scrotum. The ultrasound examination revealed a well-circumscribed and heterogenous hypoechoic tumor. MR imaging showed isointense on T1-weighted images, hypointense on T2-weighted images, and mild enhancement on post-contrast sequences. Then, he received simple tumor excision and further pathological examination demonstrated the diagnosis of typical leiomyoma. Conclusion: A full understanding of these rare tumor properties is the key to administering optimal treatment.