scholarly journals Deep Learning-Based CT Imaging in Diagnosing Myeloma and Its Prognosis Evaluation

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Jinzhou Wang ◽  
Xiangjun Shi ◽  
Xingchen Yao ◽  
Jie Ren ◽  
Xinru Du
Keyword(s):  
Deep Learning ◽  
Plasma Cells ◽  
Ct Images ◽  
Erector Spinae ◽  
Detection Accuracy ◽  
Research Subjects ◽  
Before And After ◽  
Group 2 ◽  
Psoas Major ◽  
Group 1

Imaging examination plays an important role in the early diagnosis of myeloma. The study focused on the segmentation effects of deep learning-based models on CT images for myeloma, and the influence of different chemotherapy treatments on the prognosis of patients. Specifically, 186 patients with suspected myeloma were the research subjects. The U-Net model was adjusted to segment the CT images, and then, the Faster region convolutional neural network (RCNN) model was used to label the lesions. Patients were divided into bortezomib group (group 1, n = 128) and non-bortezomib group (group 2, n = 58). The biochemical indexes, blood routine indexes, and skeletal muscle of the two groups were compared before and after chemotherapy. The results showed that the improved U-Net model demonstrated good segmentation results, the Faster RCNN model can realize the labeling of the lesion area in the CT image, and the classification accuracy rate was as high as 99%. Compared with group 1, group 2 showed enlarged psoas major and erector spinae muscle after treatment and decreased bone marrow plasma cells content, blood M protein, urine 24 h light chain, pBNP, ß-2 microglobulin (β2MG), ALP, and white blood cell (WBC) levels ( P < 0.05 ). In conclusion, deep learning is suggested in the segmentation and classification of CT images for myeloma, which can lift the detection accuracy. Two different chemotherapy regimens both improve the prognosis of patients, but the effects of non-bortezomib chemotherapy are better.

Comparison of 24-Hour Electrocardiogram Parameters in Patients with Graves Disease Before and After Anti-Thyroid Therapy

2020 ◽  
Vol 20 ◽  
Author(s):  
Gamze Akkuş ◽  
Yeliz Sökmen ◽  
Mehmet Yılmaz ◽  
Özkan Bekler ◽  
Oğuz Akkuş
Keyword(s):  
Treatment Group ◽  
Medical Treatment ◽  
Surgical Therapy ◽  
Graves Disease ◽  
Before And After ◽  
Euthyroid Status ◽  
Ectopic Beats ◽  
Group 2 ◽  
Electrocardiographic Parameters ◽  
Group 1

Background: We aimed prospectively investigate the laboratory and electrocardiographic parameters (hearth rate, QRS, QT, QTc, Tpe, Tpe/QTc, arrhythmia prevalance) in patients with graves disease before and after antithyroid therapy. Methods: 71 patients (48 female, 23 male), age between 18-50 (mean±SD: 36.48±12.20 ) with GD were included into the study. Patients treated with antithyroid therapy (thionamids and/or surgical therapy) to maintain euthyroid status. Patients were examined in terms of electrocardiographic parameters before and after the treatment. Results: Mean TSH, free thyroxin (fT4) and tri-iodothyrionine (fT3) levels of all patients were 0.005±0.21, 3.27± 1.81, 11.42±7.44, respectively. While 9 patients (group 2) underwent surgical therapy, had suspicious of malignant nodule or large goiter and unresponsiveness to medical treatment; the other patients (n=62, group 1) were treated with medical therapy. Patients with surgical therapy had more increased serum fT4 (p=0.045), anti-thyroglobulin value (p=0.018) and more severe graves orbitopathy (n=0.051) before treatment when compared to medical therapy group. Baseline Tpe duration and baseline Tpe/QTc ratio and frequency of supraventricular ectopic beats were found to be significantly higher in group 2 when compared to group 1 (p=0.00, p=0.005). Otherwise baseline mean heart rate, QRS duration, QTc values of both groups were similar. Although the patients became their euthyroid status, group 2 patients had still suffered from more sustained supraventricular ectopics beats than group 1. Conclusion: Distinct from medical treatment group, surgical treatment group with euthyroidism at least 3 months had still suffered from an arrhythmia (Tpe, Tpe/QTc, supraventricular and ventricular ectopic beats).

COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image (Preprint)

2020 ◽  
Author(s):  
Jinseok Lee
Keyword(s):  
Deep Learning ◽  
Diagnostic Performance ◽  
Ct Images ◽  
Chest Ct ◽  
University Hospital ◽  
Detection Accuracy ◽  
Ct Image ◽  
Test Dataset ◽  
Learning Framework ◽  
Testing Dataset

BACKGROUND The coronavirus disease (COVID-19) has explosively spread worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) can be used as a relevant screening tool owing to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely busy fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. OBJECTIVE We aimed to quickly develop an AI technique to diagnose COVID-19 pneumonia and differentiate it from non-COVID pneumonia and non-pneumonia diseases on CT. METHODS A simple 2D deep learning framework, named fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning, using one of the four state-of-art pre-trained deep learning models (VGG16, ResNet50, InceptionV3, or Xception) as a backbone. For training and testing of FCONet, we collected 3,993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and non-pneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training and a testing set at a ratio of 8:2. For the test dataset, the diagnostic performance to diagnose COVID-19 pneumonia was compared among the four pre-trained FCONet models. In addition, we tested the FCONet models on an additional external testing dataset extracted from the embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. RESULTS Of the four pre-trained models of FCONet, the ResNet50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100%, and accuracy 99.87%) and outperformed the other three pre-trained models in testing dataset. In additional external test dataset using low-quality CT images, the detection accuracy of the ResNet50 model was the highest (96.97%), followed by Xception, InceptionV3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). CONCLUSIONS The FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing dataset, the ResNet50-based FCONet might be the best model, as it outperformed other FCONet models based on VGG16, Xception, and InceptionV3.

A Neutralizing Antibody Selected from Plasma Cells That Binds to Group 1 and Group 2 Influenza A Hemagglutinins

Science ◽  
2011 ◽  
Vol 333 (6044) ◽  
pp. 850-856 ◽  
Author(s):  
D. Corti ◽  
J. Voss ◽  
S. J. Gamblin ◽  
G. Codoni ◽  
A. Macagno ◽  
...  
Keyword(s):  
Influenza A ◽  
Plasma Cells ◽  
Neutralizing Antibody ◽  
Group 2 ◽  
Group 1

scholarly journals Adaptive functional change of the contralateral kidney after partial nephrectomy

2017 ◽  
Vol 313 (2) ◽  
pp. F192-F198 ◽  
Author(s):  
Se Young Choi ◽  
Sangjun Yoo ◽  
Dalsan You ◽  
In Gab Jeong ◽  
Cheryn Song ◽  
...  
Keyword(s):  
Renal Function ◽  
Partial Nephrectomy ◽  
Functional Change ◽  
Functional Changes ◽  
Contralateral Kidney ◽  
Before And After ◽  
Group 2 ◽  
American Society ◽  
American Society Of Anesthesiologists ◽  
Group 1

Partial nephrectomy aims to maintain renal function by nephron sparing; however, functional changes in the contralateral kidney remain unknown. We evaluate the functional change in the contralateral kidney using a diethylene triamine penta-acetic acid (DTPA) renal scan and determine factors predicting contralateral kidney function after partial nephrectomy. A total of 699 patients underwent partial nephrectomy, with a DTPA scan before and after surgery to assess the separate function of each kidney. Patients were divided into three groups according to initial contralateral glomerular filtration rate (GFR; group 1: <30 ml·min−1·1.73 m−2, group 2: 30–45 ml·min−1·1.73 m−2, and group 3: ≥45 ml·min−1·1.73 m−2). Multiple-regression analysis was used to identify the factors associated with increased GFR of the contralateral kidney over a 4-yr postoperative period. Patients in group 1 had a higher mean age and hypertension history, worse American Society of Anesthesiologists score, and larger tumor size than in the other two groups. The ipsilateral GFR changes at 4 yr after partial nephrectomy were −18.9, −3.6, and 3.9% in groups 1, 2, and 3, respectively, whereas the contralateral GFR changes were 10.8, 25.7, and 38.8%. Age [β: −0.105, 95% confidence interval (CI): −0.213; −0.011, P < 0.05] and preoperative contralateral GFR (β: −0.256, 95% CI: −0.332; −0.050, P < 0.01) were significant predictive factors for increased GFR of the contralateral kidney after 4 yr. The contralateral kidney compensated for the functional loss of the ipsilateral kidney. The increase of GFR in contralateral kidney is more prominent in younger patients with decreased contralateral renal function.

A deep Residual U-Net algorithm for automatic detection and quantification of ascites on the abdominopelvic computed tomography acquired in the emergency department (Preprint)

2021 ◽  
Author(s):  
Hoon Ko ◽  
Jimi Huh ◽  
Kyung Won Kim ◽  
Heewon Chung ◽  
Yousun Ko ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Automatic Detection ◽  
High Specificity ◽  
Ct Images ◽  
Free Fluid ◽  
Detection Accuracy ◽  
Abdominopelvic Ct ◽  
Segmentation Accuracy ◽  
Detection And Quantification

BACKGROUND Detection and quantification of intraabdominal free fluid (i.e., ascites) on computed tomography (CT) are essential processes to find emergent or urgent conditions in patients. In an emergent department, automatic detection and quantification of ascites will be beneficial. OBJECTIVE We aimed to develop an artificial intelligence (AI) algorithm for the automatic detection and quantification of ascites simultaneously using a single deep learning model (DLM). METHODS 2D deep learning models (DLMs) based on a deep residual U-Net, U-Net, bi-directional U-Net, and recurrent residual U-net were developed to segment areas of ascites on an abdominopelvic CT. Based on segmentation results, the DLMs detected ascites by classifying CT images into ascites images and non-ascites images. The AI algorithms were trained using 6,337 CT images from 160 subjects (80 with ascites and 80 without ascites) and tested using 1,635 CT images from 40 subjects (20 with ascites and 20 without ascites). The performance of AI algorithms was evaluated for diagnostic accuracy of ascites detection and for segmentation accuracy of ascites areas. Of these DLMs, we proposed an AI algorithm with the best performance. RESULTS The segmentation accuracy was the highest in the deep residual U-Net with a mean intersection over union (mIoU) value of 0.87, followed by U-Net, bi-directional U-Net, and recurrent residual U-net (mIoU values 0.80, 0.77, and 0.67, respectively). The detection accuracy was the highest in the deep residual U-net (0.96), followed by U-Net, bi-directional U-net, and recurrent residual U-net (0.90, 0.88, and 0.82, respectively). The deep residual U-net also achieved high sensitivity (0.96) and high specificity (0.96). CONCLUSIONS We propose the deep residual U-net-based AI algorithm for automatic detection and quantification of ascites on abdominopelvic CT scans, which provides excellent performance.

A cross-sectional research conducted in Malatya province, Turkey: Knowledge levels and awareness about rational antibiotic use and antimicrobial resistance before and after graduation

2019 ◽  
Author(s):  
ADEM KOSE
Keyword(s):  
Antimicrobial Resistance ◽  
Family Physicians ◽  
Antibiotic Use ◽  
Theoretical Knowledge ◽  
Cross Sectional ◽  
Before And After ◽  
Group 2 ◽  
Senior Students ◽  
Rational Antibiotic Use ◽  
Group 1

Abstract Background Irrational antibiotic use can adversely affect treatment outcomes or even lead to increased antimicrobial resistance. We aimed to determine antimicrobial prescribing habits and to evaluate the level of theoretical knowledge of rational antibiotic use and awareness about antimicrobial resistance among the senior students of medical faculty and the family physicians in Malatya province in Turkey. Methods This study was cross-sectional research and was carried out between dates of 01 February-30 April 2019, in Malatya province. Power analysis was calculated as minimum 240 participants when considering a proportion difference of 0.18 between the groups, a type I error of 0.05 and a type II error of 0.20. A total 225 senior students in Inonu University Medical Faculty (Group 1) and 230 actively-working family physicians in Malatya primary healthcare services who were found eligible (Group 2) were included in to this study. A questionnaire form was prepared including seven sections and thirty questions. All of the participants were interviewed face to face. Before the questions, the purpose of the study and the contents of the questions were explained to participants. Qualitative data were analyzed by Pearson chi-square test. A p<0.05 value was considered to be statistically significant. Results The group 1 had a tendency to apply to specialist physician when starting to themselves antibiotic treatment, they were more cautious when making antibiotic decision, and their theoretical knowledge level was better. They argued that penal sanctions could be more effective by developing strict use policies to raise awareness of resistance to antibiotics. The group 2 had higher self-confidence and it was also concluded that forgot their theoretical antibiotic knowledge over time and could not follow the novel information because of the intensity of working life. Both groups stated that post-graduation trainings could be used effectively for reducing the antibiotic resistance. Conclusion This study highlighted the need for immediate action of training and corrective actions and might create awareness to determine the difference in theoretical knowledge levels and behavior models of physicians before and after graduation and to reduce higher use rates to lower levels. Key words: Antimicrobial resistance, antibiotic, awareness, rational use

Attitude of the Canine in Secondary Bone-Grafted and Nongrafted Patients with Cleft Lip and Palate

2005 ◽  
Vol 42 (6) ◽  
pp. 679-686 ◽  
Author(s):  
Enkhtuvshin Gereltzul ◽  
Yoshiyuki Baba ◽  
Kimie Ohyama
Keyword(s):  
Cleft Lip ◽  
Cleft Lip And Palate ◽  
Panoramic Radiography ◽  
Control Groups ◽  
Significant Difference ◽  
Before And After ◽  
Group 2 ◽  
Two Stages ◽  
And Control ◽  
Group 1

Objective To investigate the eruption pattern of the cleft-side canine regarding its pre-eruption position relative to the cleft in bone-grafted (BG) and nongrafted (NonBG) patients with cleft lip and palate. Methods Fifty-three patients with cleft lip and palate (21 BG, 32 NonBG) were examined by panoramic radiography and posteroanterior cephalography taken before and after canine eruption. Subjects were categorized into BG, NonBG, and control groups. Canines at the pre-eruption stage were categorized as close to (group 1) or distant from (group 2) the cleft area. The canine angle and its change between the two stages were evaluated. Results No significant differences were noted between the initial canine angle of the BG and NonBG groups. Although canines in the BG group erupted without a significant change in angle, the canine angle increased significantly (p < .0001) in the NonBG and control groups. In group 1, a greater change in canine angle was noted in the NonBG (p < .05) and control (p < .01) groups than in the BG group. In group 2, no significant difference was noted among the three groups. Conclusions In BG patients, a canine located near the cleft appears to erupt at the same angle as it had before grafting. However, in NonBG patients, it erupts more vertically, guided by cortical bone. For canines distant from the cleft area, there is no significant difference in the change in angulation between NonBG and BG patients.

scholarly journals The effect of capped biparametric magnetic resonance imaging slots on weekly prostate cancer imaging workload

2020 ◽  
Vol 93 (1108) ◽  
pp. 20190929 ◽  
Author(s):  
Nikita Sushentsev ◽  
Iztok Caglic ◽  
Evis Sala ◽  
Nadeem Shaida ◽  
Rhys A Slough ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Mean Absolute Deviation ◽  
Resonance Imaging ◽  
Absolute Deviation ◽  
Intergroup Comparison ◽  
Before And After ◽  
Group 2 ◽  
Group 1

Objective: To introduce capped biparametric (bp) MRI slots for follow-up imaging of prostate cancer patients enrolled in active surveillance (AS) and evaluate the effect on weekly variation in the number of AS cases and total MRI workload. Methods: Three 20 min bpMRI AS slots on two separate days were introduced at Addenbrooke’s Hospital, Cambridge. The weekly numbers of total prostate MRIs and AS cases recorded 15 months before and after the change (Groups 1 and 2, respectively). An intergroup variation in the weekly scan numbers was assessed using the coefficient of variance (CV) and mean absolute deviation; the Mann–Whitney U test was used for an intergroup comparison of the latter. Results: In AS patients, a shift from considerable to moderate variation in weekly scan numbers was observed between the two groups (CV, 51.7 and 26.8%, respectively); mean absolute deviation of AS scans also demonstrated a significant decrease in Group 2 (1.28 vs 2.58 in Group 1; p < 0.001). No significant changes in the variation in total prostate MRIs were observed, despite a 10% increased workload in Group 2. Conclusion: A significant reduction in weekly variation of AS cases was demonstrated following the introduction of capped bpMRI slots, which can be used for more accurate long-term planning of MRI workload. Advances in knowledge: The paper illustrates the potential of introducing capped AS MRI slots using a bp protocol to reduce weekly variation in demand and allow for optimising workflow, which will be increasingly important as the demands on radiology departments increase worldwide.

scholarly journals Endothelium-derived hyperpolarizing factor in preeclampsia: heterogeneous contribution, mechanisms, and morphological prerequisites

2008 ◽  
Vol 294 (2) ◽  
pp. R510-R519 ◽  
Author(s):  
Leanid Luksha ◽  
Henry Nisell ◽  
Natallia Luksha ◽  
Marius Kublickas ◽  
Kjell Hultenby ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Transmission Electron Microscopy ◽  
Subcutaneous Fat ◽  
Normal Pregnancy ◽  
Transmission Electron ◽  
Main Pathway ◽  
Before And After ◽  
Group 2 ◽  
Cytochrome P 450 ◽  
Group 1

We hypothesized that in preeclampsia (PE), contribution of endothelium-derived hyperpolarizing factor (EDHF) and the mechanism/s of its action differ from that in normal pregnancy (NP). We aimed to assess endothelial function and morphology in arteries from NP and PE with particular focus on EDHF. Arteries (≈200 μm) were dissected from subcutaneous fat biopsies obtained from women undergoing cesarean section. With the use of wire myography, responses to the endothelium-dependent agonist bradykinin (BK) were determined before and after inhibition of pathways relevant to EDHF activity. The overall responses to BK in arteries from PE ( n = 13) and NP ( n = 17) were similar. However, in PE, EDHF-mediated relaxation was reduced ( P < 0.05). All women within the PE group were divided into two subgroups: with more ( group 1) or less ( group 2) than 50% reduction of EDHF-typed responses after 18-α-glycyrrhetinic acid (an inhibitor of myoendothelial gap junctions, MEGJs). The division showed that 1) MEGJs are principally involved when the EDHF contribution is reduced; and 2) when the EDHF contribution is similar to that in NP, the H2O2 and/or cytochrome P-450 epoxygenase products of arachidonic acid (AA), along with MEGJs, confer EDHF-mediated relaxation. In contrast, MEGJs were the main pathway for EDHF in NP. The abundant presence of MEGJs in arteries from NP but deficiency of them in PE was observed using transmission electron microscopy. We conclude that PE is associated with heterogeneous contribution of EDHF, and the mechanism behind EDHF-typed responses is mediated either by MEGJs alone or in combination with H2O2 or cytochrome P-450 epoxygenase metabolites of AA.

Sign in / Sign up

Export Citation Format

Share Document