scholarly journals Magnetic Resonance Imaging Images under Deep Learning in the Identification of Tuberculosis and Pneumonia

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Yabin Liu ◽  
Yimin Wang ◽  
Ya Shu ◽  
Jing Zhu
Keyword(s):  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Pulmonary Tuberculosis ◽  
Learning Algorithm ◽  
B Value ◽  
Resonance Imaging ◽  
Specific Sequence ◽  
Adc Value ◽  
Noise Ratio

This work aimed to explore the application value of deep learning-based magnetic resonance imaging (MRI) images in the identification of tuberculosis and pneumonia, in order to provide a certain reference basis for clinical identification. In this study, 30 pulmonary tuberculosis patients and 27 pneumonia patients who were hospitalized were selected as the research objects, and they were divided into a pulmonary tuberculosis group and a pneumonia group. MRI examination based on noise reduction algorithms was used to observe and compare the signal-to-noise ratio (SNR) and carrier-to-noise ratio (CNR) of the images. In addition, the apparent diffusion coefficient (ADC) value for the diagnosis efficiency of lung parenchymal lesions was analyzed, and the best b value was selected. The results showed that the MRI image after denoising by the deep convolutional neural network (DCNN) algorithm was clearer, the edges of the lung tissue were regular, the inflammation signal was higher, and the SNR and CNR were better than before, which were 119.79 versus 83.43 and 12.59 versus 7.21, respectively. The accuracy of MRI based on a deep learning algorithm in the diagnosis of pulmonary tuberculosis and pneumonia was significantly improved (96.67% vs. 70%, 100% vs. 62.96%) ( P < 0.05 ). With the increase in b value, the CNR and SNR of MRI images all showed a downward trend ( P < 0.05 ). Therefore, it was found that the shadow of tuberculosis lesions under a specific sequence was higher than that of pneumonia in the process of identifying tuberculosis and pneumonia, which reflected the importance of deep learning MRI images in the differential diagnosis of tuberculosis and pneumonia, thereby providing reference basis for clinical follow-up diagnosis and treatment.

scholarly journals Multiple b values of diffusion-weighted magnetic resonance imaging in evaluation of solid head and neck masses

2019 ◽  
Vol 50 (1) ◽  
Author(s):  
Rania Sobhy Abou khadrah ◽  
Haytham Haroon Imam
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Head And Neck ◽  
Resonance Imaging ◽  
Adc Value ◽  
Neck Masses ◽  
Adc Values ◽  
Weighted Magnetic Resonance Imaging ◽  
The Mean ◽  
Head And Neck Masses

Abstract Background Differentiation between malignant and benign masses is essential for treatment planning and helps in improving the prognosis of malignant tumors; the aim of this work is to determine the role of diffusion-weighted magnetic resonance imaging (DW-MRI) and the apparent diffusion coefficient (ADC) in the differentiation between benign and malignant solid head and neck masses by comparing diagnostic performance of low b values (0.50 and 400 s/mm2) versus high b values (800 and 1000 s/mm2) and comparing the result with histopathological finding. Results The study included 60 patients (34 male and 26 female) with solid head and neck masses > 1 cm who referred to radiodiagnosis department for MRI evaluation. Multiple b values were used 50, 400, 800, and 1000 s/mm2 (at least 2 b values). DWI and ADC value of all 60 patients were acquired. Mean ADC values of both malignant and benign masses were statistically measured and compared, and cut off value was determined. Solid head and neck masses in our study DWI with the use of high b value 800 and 1000 s/mm2 were of higher significance (P value 0.001*). There was a significant difference in the mean ADC value between benign and malignant masses (P < 0.01); solid masses were divided into 2 categories: (a) malignant lesions 46.7% (n = 28) with mean ADC value (0.82 ± 0.19) × 10−3 s/mm2 and (b) benign lesions 53.3% (n = 32) with mean ADC value (2.05 ± 0.46) × 10−3 s/mm2) with ADC cutoff value of 1.0 × 10−3 s/mm2 and 94% sensitivity, 93% specificity, negative predictive value (NPV) = 94%, positive predictive value (PPV) 93%, and an accuracy of 93.5%. Conclusion The DWI with ADC mapping were valuable as non-invasive tools in differentiating between benign and malignant solid head and neck masses. The use of high b value 800 and 1000 s/mm2 was of higher significance (P value 0.001*) in differentiation between benign and malignant lesion than that with low b values 0, 50, and 400 s/mm2 (0.01). The mean ADC values were significantly lower in malignant solid masses. Attention had to be paid to the choice of b values in MRI-DWI in the head and neck region.

Sign in / Sign up

Export Citation Format

Share Document