Current Issue : October - December Volume : 2020 Issue Number : 4 Articles : 5 Articles
Increasing evidence suggests the utility of magnetic resonance imaging (MRI) as an\nimportant technique for the diagnosis of Alzheimerâ??s disease (AD) and for predicting the onset of this\nneurodegenerative disorder. In this study, we present a sophisticated machine learning (ML) model\nof great accuracy to diagnose the early stages of AD. A total of 373 MRI tests belonging to 150 subjects.............
Background: Coronary heart disease is one of the diseases with the highest mortality rate. Due to the important\nposition of cardiovascular disease prevention and diagnosis in the medical field, the segmentation of cardiovascular\nimages has gradually become a research hotspot. How to segment accurate blood vessels from coronary\nangiography videos to assist doctors in making accurate analysis has become the goal of our research.\nMethod: Based on the U-net architecture, we use a context-based convolutional network for capturing more\ninformation of the vessel in the video. The proposed method includes three modules: the sequence encoder module,\nthe sequence decoder module, and the sequence filter module. The high-level information of the feature is extracted\nin the encoder module. Multi-kernel pooling layers suitable for the extraction of blood vessels are added before the\ndecoder module. In the filter block, we add a simple temporal filter to reducing inter-frame flickers.\nResults: The performance comparison with other method shows that our work can achieve 0.8739 in Sen, 0.9895 in\nAcc. From the performance of the results, the accuracy of our method is significantly improved. The performance\nbenefit from the algorithm architecture and our enlarged dataset.\nConclusion: Compared with previous methods that only focus on single image analysis, our method can obtain\nmore coronary information through image sequences. In future work, we will extend the network to 3D networks...
Percutaneous transluminal angioplasty (PTA) is increasingly requested in the therapy of peripheral\narterial occlusive disease. The evaluation of the technical result after balloon angioplasty with regard to bailout\nstenting is highly dependent on the operators´ subjective assessment and mainly based on the monochromatic\ndigital subtraction angiography (DSA) images. The aim of this study was to compare color-coded single image as a\nnovel diagnostic tool with monochromatic DSA for the analysis of flow limitation and need for stent implantation\nafter PTA of superficial femoral artery (SFA) stenoses.\nMethods: During a period of 18 months, 213 SFA lesions were treated by PTA with a standard balloon in 170\npatients, resulting in a total of 193 endovascular procedures. The median age of the patients was 77 years (range,\n35-96 years). Median length of the treated lesions was 10.5 cm (range, 1.0-50 cm). Three interventional radiologists\nretrospectively evaluated the results of balloon angioplasty with monochromatic as well as post-processed colorcoded\nDSA images for flow limitations to decide if subsequent stent implantation was necessary. Consensus\nreading of two experienced interventional radiologists 2 months after the initial review served as reference standard\nto perform a receiver operating characteristics (ROC) analysis.\nResults: ROC analysis for readers A, B and C showed area under the curve (AUC) values of 0.797, 0.865 and 0.804\nfor color-coded DSA and AUC values of 0.792, 0.843 and 0.872 for monochromatic DSA: a significant advantage of\ncolor-coded over conventional monochromatic DSA was not found for.................
In December 2019, an outbreak of a novel coronavirus pneumonia, now called COVID-19, occurred in\nWuhan, Hubei Province, China. COVID-19, which is caused by the severe acute respiratory syndrome coronavirus 2\n(SARS-CoV-2), has spread quickly across China and the rest of the world. This study aims to evaluate initial chest\nthin-section CT findings of COVID-19 patients after their admission at our hospital.\nMethods: Retrospective study in a tertiary referral hospital in Anhui, China. From January 22, 2020 to February 16,\n2020, 110 suspected or confirmed COVID-19 patients were examined using chest thin-section CT. Patients in group\n1 (n = 51) presented with symptoms of COVID-19 according to the diagnostic criteria. Group 2 (n = 29) patients\nwere identified as a high degree of clinical suspicion. Patients in group 3 (n = 30) presented with mild symptoms\nand normal chest radiographs. The characteristics, positions, and distribution of intrapulmonary lesions were\nanalyzed. Moreover, interstitial lesions, pleural thickening and effusion, lymph node enlargement, and other CT\nabnormalities were reviewed.\nResults: CT abnormalities were found only in groups 1 and 2. The segments involved were mainly distributed in\nthe lower lobes (58.3%) and the peripheral zone (73.8%). The peripheral lesions, adjacent subpleural lesions,\naccounted for 51.8%. Commonly observed CT patterns were ground-glass opacification (GGO) (with or without\nconsolidation), interlobular septal thickening, and intralobular interstitial thickening. Compared with group 1,\npatients in group 2 presented with smaller lesions, and all lesions were distributed in fewer lung segments.\nLocalized pleural thickening was observed in 51.0% of group 1 patients and 48.2% of group 2 patients. The\nprevalence of lymph node enlargement in groups 1 and 2 combined was extremely low (1 of 80 patients), and no\nsignificant pleural effusion or pneumothorax was observed (0 of 80 patients).\nConclusion: The common features of chest thin-section CT of COVID-19 are multiple areas of GGO, sometimes\naccompanied by consolidation. The lesions are mainly distributed in the lower lobes and peripheral zone, and a\nlarge proportion of peripheral lesions are accompanied by localized pleural thickening adjacent to the subpleural\nregion....
Background: Image segmentation is an important part of computer-aided diagnosis\n(CAD), the segmentation of small ground glass opacity (GGO) pulmonary nodules is\nbeneficial for the early detection of lung cancer. For the segmentation of small GGO\npulmonary nodules, an integrated active contour model based on Markov random\nfield energy and Bayesian probability difference (IACM-MRFEBPD) is proposed in this\npaper.\nMethods: First, the Markov random field (MRF) is constructed on the computed\ntomography (CT) images, then the MRF energy is calculated. The MRF energy is used\nto construct the region term. It can not only enhance the contrast between pulmonary\nnodule and the background region, but also solve the problem of intensity inhomogeneity\nusing local spatial correlation information between neighboring pixels in the\nimage. Second, the Gaussian mixture model is used to establish the probability model\nof the image, and the model parameters are estimated by the expectation maximization\n(EM) algorithm. So the Bayesian posterior probability difference of each pixel can\nbe calculated. The probability difference is used to construct the boundary detection\nterm, which is 0 at the boundary. Therefore, the blurred boundary problem can be\nsolved. Finally, under the framework of the level set, the integrated active contour\nmodel is constructed.\nResults: To verify the effectiveness of the proposed method, the public data of the\nlung image database consortium and image database resource initiative (LIDC-IDRI)\nand the clinical data of the Affiliated Jiangmen Hospital of Sun Yat-sen University are\nused to perform experiments, and the intersection over union (IOU) score is used to\nevaluate the segmentation methods. Compared with other methods, the proposed\nmethod achieves the best results with the highest average IOU of 0.7444, 0.7503, and\n0.7450 for LIDC-IDRI test set, clinical test set, and all test sets, respectively.\nConclusions: The experiment results show that the proposed method can segment\nvarious small GGO pulmonary nodules more accurately and robustly, which is helpful\nfor the accurate evaluation of medical imaging....
Loading....