Search

Background: Distinguishing between the spinal cord and cerebrospinal fluid (CSF) non-invasively on CT is challenging due to their similar mass densities. We hypothesize that patch-based machine learning applied to dual-energy CT can accurately distinguish CSF from neural or other tissues based on the center voxel and neighboring voxels. Methods: 88 regions of interest (ROIs) from 12 patients’ dual-energy (100 and 140 kVp) lumbar spine CT exams were manually labeled by a neuroradiologist as one of 4 major tissue types (water, fat, bone, and nonspecific soft tissue). Four-class classifier convolutional neural networks were trained, validated, and tested on thousands of nonoverlapping patches extracted from 82 ROIs among 11 CT exams, with each patch representing pixel values (at low and high energies) of small, rectangular, 3D CT volumes. Different patch sizes were evaluated, ranging from 3 × 3 × 3 × 2 to 7 × 7 × 7 × 2. A final ensemble model incorporating all patch sizes was tested on patches extracted from six ROIs in a holdout patient. Results: Individual models showed overall test accuracies ranging from 99.8% for 3 × 3 × 3 × 2 patches (N = 19,423) to 98.1% for 7 × 7 × 7 × 2 patches (N = 1298). The final ensemble model showed 99.4% test classification accuracy, with sensitivities and specificities of 90% and 99.6%, respectively, for the water class and 98.6% and 100% for the soft tissue class. Conclusions: Convolutional neural networks utilizing local low-level features on dual-energy spine CT can yield accurate tissue classification and enhance the visualization of intraspinal neural tissue.

The emergence of the COVID-19 pandemic over a relatively brief interval illustrates the need for rapid data-driven approaches to facilitate clinical decision making. We examined a machine learning process to predict inpatient mortality among COVID-19 patients using clinical and chest radiographic data. Modeling was performed with a de-identified dataset of encounters prior to widespread vaccine availability. Non-imaging predictors included demographics, pre-admission clinical history, and past medical history variables. Imaging features were extracted from chest radiographs by applying a deep convolutional neural network with transfer learning. A multi-layer perceptron combining 64 deep learning features from chest radiographs with 98 patient clinical features was trained to predict mortality. The Local Interpretable Model-Agnostic Explanations (LIME) method was used to explain model predictions. Non-imaging data alone predicted mortality with an ROC-AUC of 0.87 ± 0.03 (mean ± SD), while the addition of imaging data improved prediction slightly (ROC-AUC: 0.91 ± 0.02). The application of LIME to the combined imaging and clinical model found HbA1c values to contribute the most to model prediction (17.1 ± 1.7%), while imaging contributed 8.8 ± 2.8%. Age, gender, and BMI contributed 8.7%, 8.2%, and 7.1%, respectively. Our findings demonstrate a viable explainable AI approach to quantify the contributions of imaging and clinical data to COVID mortality predictions.

The presence of a single nodal metastasis has significant prognostic and treatment implications for patients with head and neck cancer. This study aims to investigate whether dual-energy computed tomography (DECT)-derived iodine content and spectral attenuation curve analysis can improve detection of nodal metastasis in oropharyngeal carcinoma. Eight patients with newly diagnosed oropharyngeal squamous cell carcinoma and pathologically proven nodal metastatic disease (n = 13 metastatic nodes, n = 16 nonmetastatic nodes) who underwent contrast-enhanced DECT of the neck were retrospectively evaluated. DECT-derived iodine content (mg/mL) and monoenergetic attenuation values at 40 keV and 100 keV were obtained via circular regions of interest within metastatic and nonmetastatic cervical lymph nodes. Iodine content was significantly lower in metastatic nodes (0.96 ± 0.28 mg/mL) than in nonmetastatic nodes (1.65 ± 0.38 mg/mL, P = .002). Iodine spectral attenuation slope was significantly lower in metastatic nodes (1.33 ± 0.49 mg/mL) than in nonmetastatic nodes (1.91 ± 0.64 mg/mL, P = .015). A nodal iodine threshold of ≤1.3 mg/mL showed a sensitivity of 84.6% and a specificity of 75.0%, with an area under the curve of 0.839, P &lt, 0001. At a threshold value of ≤1.95 for nodal spectral attenuation slope, an optimized specificity of 92.3% and specificity of 50.0% was achieved, with an area under the curve of 0.68 (P = .049). DECT-derived quantitative iodine data and spectral attenuation curves may improve the diagnostic accuracy of computed tomography for nodal metastasis in patients with squamous cell carcinoma of the oropharynx.