Abstract
Objective: the purpose of this study was to assess residual neck nodes after Chemo- Radiotherapy (CRT) using diffusion and T2 weighted imaging.
Methods: Apparent Diffusion Coefficient (ADC) and T2 signal intensity were retrospectively analyzed in 45 residual nodes 8 weeks after the end of CRT. Sensitivity, specificity, Positive and Negative Predictive Values (PPV, NPV) and accuracy of diffusion and T2 weighted sequences were calculated. In a subgroup of 25 patients ADC and T2 signal intensity were compared to Positron Emission Tomography - Computed Tomography (PET-CT) results. Histopathology and a 24 months follow- up after CRT were used as reference standard.
Results: T2 signal intensity showed an accuracy of 63%, a sensitivity of 73.3%, a specificity of 55.6%, a PPV of 53.8% and a NPV of 75%. ADC showed an accuracy of 71.1%, using a threshold of 1.25 10-3 mm2/s, a sensitivity of 52.6%, a specificity of 84.6%, a PPV of 71.4% and a NPV of 71%. The combination of T2 signal intensity and ADC showed an accuracy of 73.3%, a sensitivity of 50%, a specificity of 84.6%, a PPV of 60% and a NPV of 78.7%. In the subset of 25 patients we correlated ADC and T2 data with PET-CT data: the latter showed higher accuracy, sensitivity and NPV and lower specificity; the PPV was similar between the two methods.
Conclusion: Our results demonstrated that MRI, using diffusion and T2 weighted imaging, has high specificity in detecting post-CRT residual neck nodes but it has a lower accuracy, sensitivity and NPV than PET-CT.
Keywords: Lymph nodes, diffusion weighted imaging, T2 weighted imaging, magnetic resonance imaging, treatment response, head and neck squamous cell carcinoma, residual tumour.
Graphical Abstract
Call for Papers in Thematic Issues
Intelligent Information Retrieval for Multispectral and Hyperspectral Imaging
Multispectral and hyperspectral imaging is an interdisciplinary research area, widely focuses on spectral, spatial, and temporal data. It offers a plethora of opportunities to efficiently analyze the vast area of the earth's surface. However, there are numerous factors such as dimensionality and size of the hyperspectral data, lesser training samples, ...read more
Machine and Deep Learning in Medical Image Diagnosis
Medical Image Processing regards a set of methodologies that have been developed over recent years with the purpose of improving medical image quality, improving medical data visualization, understanding, and assisting medical diagnosis, and so on. The application of machine and deep learning methods in sensing and imaging can potentially have ...read more
Quantum Machine Learning for Medical Data and Imaging
Quantum computing has promised a significant speedup in certain computationally intensive tasks that are intractable on classical computers. Researchers in quantum machine learning, such as those working in computer vision, image processing, biomedical analysis, and related topics, may play an important role in comprehending and working on complicated medical data, ...read more
11
4
1
1