ABSTRACT
AIM: To develop a high-accuracy low-dose computed tomography (LDCT) lung nodule diagnosis system by combining artificial intelligence (AI) technology with the Lung CT Screening Reporting and Data System (Lung-RADS), which can be used in the future AI-aided diagnosis of pulmonary nodules. MATERIALS AND METHODS: The study comprised the following steps: (1) the best deep-learning segmentation method for pulmonary nodules was compared and selected objectively; (2) the Image Biomarker Standardization Initiative (IBSI) was used for feature extraction and to determine the best feature reduction method; and (3) a principal component analysis (PCA) and three machine learning methods were used to analyse the extracted features, and the best method was determined. The Lung Nodule Analysis 16 dataset was applied to train and test the established system in this study. RESULTS: The competition performance metric (CPM) score of the nodule segmentation reached 0.83, the accuracy of nodule classification was 92%, the kappa coefficient with the ground truth was 0.68, and the overall diagnostic accuracy (calculated by the nodules) was 0.75. CONCLUSION: This paper summarises a more efficient AI-assisted diagnosis process of pulmonary nodules, and has better performance compared with the previous literature. In addition, this method will be validated in a future external clinical study.
Subject(s)
Lung Neoplasms , Multiple Pulmonary Nodules , Solitary Pulmonary Nodule , Humans , Artificial Intelligence , Lung Neoplasms/diagnostic imaging , Tomography, X-Ray Computed/methods , Multiple Pulmonary Nodules/diagnostic imaging , Diagnosis, Computer-Assisted/methods , Solitary Pulmonary Nodule/diagnostic imaging , Radiographic Image Interpretation, Computer-AssistedABSTRACT
Little is known of how the genetic background effects the phenomenon of genomic imprinting. The H19 gene belongs to a cluster of imprinted genes on human chromosome 11. Here we show that the alternative splicing of a human H19 transcript is genotype-specific. Moreover, this variant transcript, which lacks exon 4, is either not found at all, is widely expressed or is confined to extra-villous cytotrophoblasts in first trimester placenta, depending on a combination of the genotype and the sex of the transmitting parent.
Subject(s)
Genes, Tumor Suppressor , Genomic Imprinting , Muscle Proteins/genetics , RNA, Untranslated , Alleles , Alternative Splicing , Base Sequence , DNA/genetics , Female , Gene Expression Regulation, Developmental , Genotype , Humans , In Situ Hybridization , Male , Oligonucleotide Probes/genetics , Pregnancy , RNA/genetics , RNA/metabolism , RNA, Long Noncoding , Trophoblasts/metabolismABSTRACT
Combined paresis of all three ocular motor nerves is a rare ocular manifestation in diabetic patients. We present a case of a 73-year-old female with complete ophthalmoplegia. There was no evidence of peripheral neuropathy. Diagnostic angiography showed atherosclerotic stenosis in the cavernous segment of left internal carotid artery. The ophthalmoplegia had a self-limited course despite the severe vascular lesions.
