Current Issue : April-June Volume : 2022 Issue Number : 2 Articles : 5 Articles
Aim: This study is to compare the lung image quality between shelter hospital CT (CT Ark) and ordinary CT scans (Brilliance 64) scans. Methods: The patients who received scans with CT Ark or Brilliance 64 CT were enrolled. Their lung images were divided into two groups according to the scanner. The objective evaluation methods of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were used. The subjective evaluation methods including the evaluation of the fine structure under the lung window and the evaluation of the general structure under the mediastinum window were compared. Kappa method was used to assess the reliability of the subjective evaluation. The subjective evaluation results were analyzed using the Wilcoxon rank sum test. SNR and CNR were tested using independent sample t tests. Results: There was no statistical difference in somatotype of enrolled subjects. The Kappa value between the two observers was between 0.68 and 0.81, indicating good consistency. For subjective evaluation results, the rank sum test P value of fine structure evaluation and general structure evaluation by the two observers was ≥ 0.05. For objective evaluation results, SNR and CNR between the two CT scanners were significantly different (P<0.05). Notably, the absolute values of SNR and CNR of the CT Ark were larger than Brilliance 64 CT scanner. Conclusion: CT Ark is fully capable of scanning the lungs of the COVID-19 patients during the epidemic in the shelter hospital....
Background: Segmentation of important structures in temporal bone CT is the basis of image-guided otologic surgery. Manual segmentation of temporal bone CT is time- consuming and laborious. We assessed the feasibility and generalization ability of a proposed deep learning model for automated segmentation of critical structures in temporal bone CT scans. Methods: Thirty-nine temporal bone CT volumes including 58 ears were divided into normal (n = 20) and abnormal groups (n = 38). Ossicular chain disruption (n = 10), facial nerve covering vestibular window (n = 10), and Mondini dysplasia (n = 18) were included in abnormal group. All facial nerves, auditory ossicles, and labyrinths of the normal group were manually segmented. For the abnormal group, aberrant structures were manually segmented. Temporal bone CT data were imported into the network in unmarked form. The Dice coefficient (DC) and average symmetric surface distance (ASSD) were used to evaluate the accuracy of automatic segmentation. Results: In the normal group, the mean values of DC and ASSD were respectively 0.703, and 0.250 mm for the facial nerve; 0.910, and 0.081 mm for the labyrinth; and 0.855, and 0.107 mm for the ossicles. In the abnormal group, the mean values of DC and ASSD were respectively 0.506, and 1.049 mm for the malformed facial nerve; 0.775, and 0.298 mm for the deformed labyrinth; and 0.698, and 1.385 mm for the aberrant ossicles. Conclusions: The proposed model has good generalization ability, which highlights the promise of this approach for otologist education, disease diagnosis, and preoperative planning for image-guided otology surgery....
/is study aimed to explore the therapeutic effects of neoadjuvant chemoradiotherapy (NCRT) on rectal cancer patients using the MRI based on low-rank matrix denoising algorithm, which was then compared with the postoperative pathological examination to evaluate its application value in tumor staging after NCRTtreatment. 15 patients with rectal cancer who met the requirements of radiotherapy and chemotherapy after conventional MRI were selected as the research subjects. /e conventional MRI images before and after NCRTtreatment were divided in two groups. One group was not processed and set as the conventional group; the other group was processed with low-rank matrix denoising algorithm and set as the optimized group. /e two groups of images were observed for the changes in the ADC value and length and thickness of the tumor before and after NCRTtreatment. /e two groups were compared with the pathological examination for the complete remission of pathology (pCR) after the NCRT treatment and the tumor stage results. /e results showed that Root Mean Square Error (RMSE) and Peak Signal to Noise Ratio (PSNR) (18.9121 and 74.9911 dB) after introducing the low-rank matrix denoising algorithm were significantly better than those before (20.1234 and 70.1234 dB) (P < 0.05); there were notable differences in the tumor index data within the two groups before and after NCRT treatment (P < 0.05), indicating that the NCRT treatment was effective. /e pathological examination results of pCR data of the two groups were not much different (P > 0.05); the examination results between the two groups were different, but no notable difference was noted (P < 0.05); in the optimized group, there was no notable difference between the MRI results and the pathological examination results (P < 0.05), while in the conventional group, there were notable differences in the MRI results and pathological examination results (P < 0.05). In conclusion, MRI images based on low-rank matrix denoising algorithm are clearer, which can improve the diagnosis rate of patients and better display the changes of the microenvironment after NCRT treatment. It also indicates that NCRT treatment has significant clinical effects in the treatment of rectal cancer patients, which is worth promoting....
Purpose: The objective of this study is to construct a computer aided diagnosis system for normal people and pneumoconiosis using X-raysand deep learning algorithms. Materials and methods: 1760 anonymous digital X-ray images of real patients between January 2017 and June 2020 were collected for this experiment. In order to concentrate the feature extraction ability of the model more on the lung region and restrain the influence of external background factors, a two-stage pipeline from coarse to fine was established. First, the U-Net model was used to extract the lung regions on each sides of the collection images. Second, the ResNet-34 model with transfer learning strategy was implemented to learn the image features extracted in the lung region to achieve accurate classification of pneumoconiosis patients and normal people. Results: Among the 1760 cases collected, the accuracy and the area under curve of the classification model were 92.46% and 89% respectively. Conclusion: The successful application of deep learning in the diagnosis of pneumoconiosis further demonstrates the potential of medical artificial intelligence and proves the effectiveness of our proposed algorithm. However, when we further classified pneumoconiosis patients and normal subjects into four categories, we found that the overall accuracy decreased to 70.1%. We will use the CT modality in future studies to provide more details of lung regions....
Background: Avascular necrosis is a delayed complication of proximal humerus fractures that increases the likelihood of poor clinical outcomes. CT scans are routinely performed to guide proximal humerus fracture management. We hypothesized iodine concentration on post-contrast dual energy CT scans identifies subjects who develop avascular necrosis and ischemia due to compromised blood flow. Materials and methods: 55 patients with proximal humerus fractures enrolled between 2014 and 2017 underwent clinical, radiographic and contrast enhanced dual energy CT assessment. Iodine densities of the humeral head and the glenoid (control) were measured on CT. Subjects managed with open reduction internal fixation or conservatively (non-surgical) were followed for up to two years for radiographic evidence of avascular necrosis. Arthroplasty subjects underwent histopathologic evaluation for ischemia of the resected humeral head. Results: 17 of 55 subjects (30.9%) were treated conservatively, 21 (38.2%) underwent open reduction internal fixation and 17 of 55 (30.9%) underwent arthroplasty. Of the 38 subjects treated conservatively or with ORIF, 20 (52.6%) completed 12 months of follow up and 14 (36.8%) 24 months of follow up. At 12 months follow up, two of 20 subjects (10%) and at 24 months 3 of 14 subjects (21.4%) developed avascular necrosis. At 12 months, the mean humerus/ glenoid iodine ratio was 1.05 (standard deviation 0.24) in subjects with AVN compared to 0.91 (0.24) in those who did not. At 24 months, subjects with avascular necrosis had a mean humerus/glenoid iodine concentration ratio of 1.06 (0.17) compared to 0.924 (0.21) in those who did not. Of 17 arthroplasty subjects, 2 had severe ischemia and an iodine ratio of 1.08 (0.30); 5 had focal ischemia and a ratio of 1.00 (0.36); and 8 no ischemia and a ratio of 0.83 (0.08). Conclusions: Quantifying iodine using dual energy CT in subjects with proximal humerus fractures is technically feasible. Preliminary data suggest higher humeral head iodine concentration may increase risk of avascular necrosis; however, future studies must enroll and follow enough subjects managed with open reduction internal fixation or conservatively for two or more years to provide statistically significant results. Trial Registrations NCT02170545 registered June 23, 2014, ClinicalTrials.gov....
Loading....