Automated diagnosis of tuberculosis (TB) from chest X-Rays (CXR) has been tackled with either hand-crafted algorithms or machine learning approaches such as support vector machines (SVMs) and convolutional neural networks (CNNs). Most deep neural network applied to the task of tuberculosis diagnosis have been adapted from natural image classification. These models have a large number of parameters as well as high hardware requirements, which makes them prone to overfitting and harder to deploy in mobile settings. We propose a simple convolutional neural network optimized for the problem which is faster and more efficient than previous models but preserves their accuracy. Moreover, the visualization capabilities of CNNs have not been fully investigated. We test saliency maps and grad-CAMs as tuberculosis visualization methods, and discuss them from a radiological perspective.
a b s t r a c tBackground: Treatment decisions for multimodal therapy in soft tissue sarcoma (STS) patients greatly depend on the differentiation between low-grade and high-grade tumors. We developed MRI-based radiomics grading models for the differentiation between low-grade (G1) and high-grade (G2/G3) STS. Methods: The study was registered at ClinicalTrials.gov (number NCT03798795). Contrast-enhanced T1-weighted fat saturated (T1FSGd), fat-saturated T2-weighted (T2FS) MRI sequences, and tumor grading following the French Federation of Cancer Centers Sarcoma Group obtained from pre-therapeutic biopsies were gathered from two independent retrospective patient cohorts. Volumes of interest were manually segmented. After preprocessing, 1394 radiomics features were extracted from each sequence. Features unstable in 21 independent multiple-segmentations were excluded. Least absolute shrinkage and selection operator models were developed using nested cross-validation on a training patient cohort (122 patients). The influence of ComBatHarmonization was assessed for correction of batch effects. Findings: Three radiomic models based on T2FS, T1FSGd and a combined model achieved predictive performances with an area under the receiver operator characteristic curve (AUC) of 0.78, 0.69, and 0.76 on the independent validation set (103 patients), respectively. The T2FS-based model showed the best reproducibility. The radiomics model involving T1FSGd-based features achieved significant patient stratification. Combining the T2FS radiomic model into a nomogram with clinical staging improved prognostic performance and the clinical net benefit above clinical staging alone. Interpretation: MRI-based radiomics tumor grading models effectively classify low-grade and high-grade soft tissue sarcomas.
Background Although advanced medical imaging technologies give detailed diagnostic information, a low-dose, fast, and inexpensive option for early detection of respiratory diseases and follow-ups is still lacking. The novel method of x-ray dark-field chest imaging might fill this gap but has not yet been studied in living humans. Enabling the assessment of microstructural changes in lung parenchyma, this technique presents a more sensitive alternative to conventional chest x-rays, and yet requires only a fraction of the dose applied in CT. We studied the application of this technique to assess pulmonary emphysema in patients with chronic obstructive pulmonary disease (COPD). MethodsIn this diagnostic accuracy study, we designed and built a novel dark-field chest x-ray system (Technical University of Munich, Munich, Germany)-which is also capable of simultaneously acquiring a conventional thorax radiograph ( 7s, 0•035 mSv effective dose). Patients who had undergone a medically indicated chest CT were recruited from the department of Radiology and Pneumology of our site (Klinikum rechts der Isar, Technical University of Munich, Munich, Germany). Patients with pulmonary pathologies, or conditions other than COPD, that might influence lung parenchyma were excluded. For patients with different disease stages of pulmonary emphysema, x-ray dark-field images and CT images were acquired and visually assessed by five readers. Pulmonary function tests (spirometry and body plethysmography) were performed for every patient and for a subgroup of patients the measurement of diffusion capacity was performed. Individual patient datasets were statistically evaluated using correlation testing, rank-based analysis of variance, and pair-wise post-hoc comparison. Findings Between October, 2018 and December, 2019 we enrolled 77 patients. Compared with CT-based parameters (quantitative emphysema ρ=-0•27, p=0•089 and visual emphysema ρ=-0•45, p=0•0028), the dark-field signal (ρ=0•62, p<0•0001) yields a stronger correlation with lung diffusion capacity in the evaluated cohort. Emphysema assessment based on dark-field chest x-ray features yields consistent conclusions with findings from visual CT image interpretation and shows improved diagnostic performance than conventional clinical tests characterising emphysema. Pair-wise comparison of corresponding test parameters between adjacent visual emphysema severity groups (CT-based, reference standard) showed higher effect sizes. The mean effect size over the group comparisons (absent-trace, trace-mild, mild-moderate, and moderate-confluent or advanced destructive visual emphysema grades) for the COPD assessment test score is 0•21, for forced expiratory volume in 1 s (FEV 1 )/functional vital capacity is 0•25, for FEV 1 % of predicted is 0•23, for residual volume % of predicted is 0•24, for CT emphysema index is 0•35, for dark-field signal homogeneity within lungs is 0•38, for dark-field signal texture within lungs is 0•38, and for darkfield-based emphysema severity is 0•42. Interpretation X-r...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.