scholarly journals Multi-Level Seg-Unet Model with Global and Patch-Based X-ray Images for Knee Bone Tumor Detection

Diagnostics ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 691
Author(s):  
Nhu-Tai Do ◽  
Sung-Taek Jung ◽  
Hyung-Jeong Yang ◽  
Soo-Hyung Kim
Keyword(s):  
Malignant Tumor ◽  
Bone Tumor ◽  
Tumor Detection ◽  
University Hospital ◽  
Tumor Segmentation ◽  
Bone Lesions ◽  
Global Context ◽  
Liver Cancers ◽  
National University ◽  
Radiographic Interpretation

Tumor classification and segmentation problems have attracted interest in recent years. In contrast to the abundance of studies examining brain, lung, and liver cancers, there has been a lack of studies using deep learning to classify and segment knee bone tumors. In this study, our objective is to assist physicians in radiographic interpretation to detect and classify knee bone regions in terms of whether they are normal, begin-tumor, or malignant-tumor regions. We proposed the Seg-Unet model with global and patched-based approaches to deal with challenges involving the small size, appearance variety, and uncommon nature of bone lesions. Our model contains classification, tumor segmentation, and high-risk region segmentation branches to learn mutual benefits among the global context on the whole image and the local texture at every pixel. The patch-based model improves our performance in malignant-tumor detection. We built the knee bone tumor dataset supported by the physicians of Chonnam National University Hospital (CNUH). Experiments on the dataset demonstrate that our method achieves better performance than other methods with an accuracy of 99.05% for the classification and an average Mean IoU of 84.84% for segmentation. Our results showed a significant contribution to help the physicians in knee bone tumor detection.

scholarly journals Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics

2020 ◽  
Author(s):  
Yoon Seong Choi ◽  
Sohi Bae ◽  
Jong Hee Chang ◽  
Seok-Gu Kang ◽  
Se Hoon Kim ◽  
...  
Keyword(s):  
Hybrid Model ◽  
Hybrid Approach ◽  
University Hospital ◽  
Tumor Segmentation ◽  
Idh Mutation ◽  
Mr Images ◽  
Mutation Status ◽  
Severance Hospital ◽  
National University ◽  
Fluid Attenuated Inversion Recovery

Abstract Background Glioma prognosis depends on isocitrate dehydrogenase (IDH) mutation status. We aimed to predict the IDH status of gliomas from preoperative MR images using a fully automated hybrid approach with convolutional neural networks (CNNs) and radiomics. Methods We reviewed 1166 preoperative MR images of gliomas (grades II–IV) from Severance Hospital (n = 856), Seoul National University Hospital (SNUH; n = 107), and The Cancer Imaging Archive (TCIA; n = 203). The Severance set was subdivided into the development (n = 727) and internal test (n = 129) sets. Based on T1 postcontrast, T2, and fluid-attenuated inversion recovery images, a fully automated model was developed that comprised a CNN for tumor segmentation (Model 1) and CNN-based classifier for IDH status prediction (Model 2) that uses a hybrid approach based on 2D tumor images and radiomic features from 3D tumor shape and loci guided by Model 1. The trained model was tested on internal (a subset of the Severance set) and external (SNUH and TCIA) test sets. Results The CNN for tumor segmentation (Model 1) achieved a dice coefficient of 0.86–0.92 across datasets. Our hybrid model achieved accuracies of 93.8%, 87.9%, and 78.8%, with areas under the receiver operating characteristic curves of 0.96, 0.94, and 0.86 and areas under the precision-recall curves of 0.88, 0.82, and 0.81 in the internal test, SNUH, and TCIA sets, respectively. Conclusions Our fully automated hybrid model demonstrated the potential to be a highly reproducible and generalizable tool across different datasets for the noninvasive prediction of the IDH status of gliomas.

Integrated Approach For Bone Tumor Detection From Mri Scan Imagery

2019 ◽  
Vol 7 (4) ◽  
pp. 324-325
Author(s):  
Mrs. V.P. Krishnammal ◽  
Firosha S Fathima ◽  
Jills P Mathew ◽  
Preethi kalyani M. ◽  
V Shiva Shankari
Keyword(s):  
Bone Tumor ◽  
Integrated Approach ◽  
Tumor Detection ◽  
Mri Scan

Intestinal parasite survey of Kyungpook National University Hospital patients

1971 ◽  
Vol 9 (2) ◽  
pp. 47 ◽  
Author(s):  
Dong Wik Choi ◽  
Sung Deok Park ◽  
Jae Woun Kim ◽  
Doo Hong Ahn ◽  
Young Myung Kim
Keyword(s):  
Intestinal Parasite ◽  
University Hospital ◽  
Hospital Patients ◽  
National University

scholarly journals Circulating regulatory T cells predict efficacy and atypical responses in lung cancer patients treated with PD-1/PD-L1 inhibitors

2021 ◽  
Author(s):  
Da Hyun Kang ◽  
Chaeuk Chung ◽  
Pureum Sun ◽  
Da Hye Lee ◽  
Song-I Lee ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Cancer Patients ◽  
Advanced Nsclc ◽  
Checkpoint Inhibitors ◽  
Standard Of Care ◽  
Treg Cells ◽  
University Hospital ◽  
X Rays ◽  
Lung Cancer Patients ◽  
National University

Abstract Background Immune checkpoint inhibitors (ICIs) have become the standard of care for a variety of cancers, including non-small cell lung cancer (NSCLC). In this study, we investigated the frequency of pseudoprogression and hyperprogression in lung cancer patients treated with ICIs in the real world and aimed to discover a novel candidate marker to distinguish pseudoprogression from hyperprogression soon after ICI treatment. Methods This study included 74 patients with advanced NSCLC who were treated with PD-1/PD-L1 inhibitors at Chungnam National University Hospital (CNUH) between January 2018 and August 2020. Chest X-rays were examined on day 7 after the first ICI dose to identify changes in the primary mass, and the response was assessed by computed tomography (CT). We evaluated circulating regulatory T (Treg) cells using flow cytometry and correlated the findings with clinical outcomes. Results The incidence of pseudoprogression was 13.5%, and that of hyperprogression was 8.1%. On day 7 after initiation of treatment, the frequency of CD4+CD25+CD127loFoxP3+ Treg cells was significantly decreased compared with baseline (P = 0.038) in patients who experienced pseudoprogression and significantly increased compared with baseline (P = 0.024) in patients who experienced hyperprogression. In the responder group, the frequencies of CD4+CD25+CD127loFoxP3+ Treg cells and PD-1+CD4+CD25+CD127loFoxP3+ Treg cells were significantly decreased 7 days after commencement of treatment compared with baseline (P = 0.034 and P < 0.001, respectively). Conclusion Circulating Treg cells represent a promising potential dynamic biomarker to predict efficacy and differentiate atypical responses, including pseudoprogression and hyperprogression, after immunotherapy in patients with NSCLC.

scholarly journals Association of Carotid Artery Endothelial Signal Intensity Gradient with Unilateral Large Artery Ischemic Stroke

2021 ◽  
Vol 50 (3) ◽  
pp. 270-278
Author(s):  
Chan-Hyuk Lee ◽  
Sang Hyuk Lee ◽  
Young I. Cho ◽  
Seul-Ki Jeong
Keyword(s):  
Ischemic Stroke ◽  
Carotid Artery ◽  
Signal Intensity ◽  
Internal Carotid ◽  
University Hospital ◽  
Large Artery ◽  
Intensity Gradient ◽  
National University ◽  
Endothelial Shear Stress ◽  
Stroke Center

<b><i>Background:</i></b> Common carotid artery (CCA) and internal carotid artery (ICA) are aligned linearly, but their hemodynamic role in ischemic stroke has not been studied in depth. <b><i>Objectives:</i></b> We aimed to investigate whether CCA and ICA endothelial shear stress (ESS) could be associated with the ischemic stroke of large artery atherosclerosis (LAA). <b><i>Methods:</i></b> We enrolled consecutive patients with unilateral ischemic stroke of LAA and healthy controls aged &#x3e;60 years in the stroke center of Jeonbuk National University Hospital. All patients and controls were examined with carotid artery time-of-flight magnetic resonance angiography, and their endothelial signal intensity gradients (SIGs) were determined, as a measure of ESS. The effect of right or left unilateral stroke on the association between carotid artery endothelial SIG and ischemic stroke of LAA was assessed. <b><i>Results:</i></b> In total, the results from 132 patients with ischemic stroke of LAA and 121 controls were analyzed. ICA endothelial SIG showed significant and independent associations with the same-sided unilateral ischemic stroke of LAA, even after adjusting for the potential confounders including carotid stenosis, whereas CCA endothelial SIG showed a significant association with the presence of the ischemic stroke of LAA. <b><i>Conclusion:</i></b> Although CCA and ICA are located with continuity, the hemodynamics and their roles in large artery ischemic stroke should be considered separately. Further studies are needed to delineate the pathophysiologic roles of ESS in CCA and ICA for large artery ischemic stroke.

scholarly journals Surgical Outcomes of Phacoemulsification Surgery in a Restructured Asian Training Hospital

1970 ◽  
Vol 12 (4) ◽  
pp. 201-207
Author(s):  
David Zhiwei Law ◽  
Seng Chee Loon ◽  
Wan Ling Wong ◽  
Marilou Sevilla Ebreo ◽  
Xiang Li ◽  
...  
Keyword(s):  
Visual Acuity ◽  
Surgical Outcomes ◽  
Perioperative Complications ◽  
University Hospital ◽  
Complication Rates ◽  
Corrected Visual Acuity ◽  
Duration Of Surgery ◽  
National University ◽  
Chi Squared ◽  
Best Corrected Visual Acuity

Aim: To evaluate the surgical outcomes of phacoemulsification performed at National University Hospital, Singapore, with emphasis on the results achieved by residents.Methods: This was a retrospective analysis of surgical outcomes of patients who underwent phacoemulsification in a restructured hospital in 2008. The study included 318 eyes of patients of predominantly Asian descent. Pre- and postoperative best-corrected visual acuity, perioperative complications and associations of patient, surgical and surgeon factors were studied. One-way analysis of variance for means, chi-squared test for proportions, and multivariate analyses were performed to determine factors associated with postoperative best-corrected visual acuity outcomes. Main outcome measures included postoperative best-corrected visual acuity, degree of improvement in best-corrected visual acuity, and achievement of specific best-corrected visual acuity targets of 6/9 and 6/12 at postoperative months 1 and 3.Results: Duration of surgery of less than 20 minutes was found to be significantly associated with better postoperative best-corrected visual acuity. Level of surgical experience was also associated with betterpostoperative best-corrected visual acuity at postoperative months 1 (p < 0.001) and 3 (p = 0.004). While senior consultants produced the best postoperative best-corrected visual acuity outcomes, the results achieved by residents were comparable to those reported in prior resident-only studies. For surgeries performed by residents, the overall rate of posterior capsule rupture was 3.1% with a 0.0% rate of vitreous loss.Conclusions: The continued close guidance and training of ophthalmology residents in a restructured Asian training hospital will ensure that complication rates remain low while maintaining postoperative outcomes at safe levels.

Sign in / Sign up

Export Citation Format

Share Document