Clinical evaluation of AI software for rib fracture detection and its impact on junior radiologist performance

2021 ◽  
pp. 028418512110438
Author(s):  
Xiang Liu ◽  
Dijia Wu ◽  
Huihui Xie ◽  
Yufeng Xu ◽  
Lin Liu ◽  
...  
Keyword(s):  
Detection System ◽  
Ct Images ◽  
Diagnostic Efficiency ◽  
Fracture Detection ◽  
Patient Level ◽  
Primary Endpoints ◽  
Significant Difference ◽  
Secondary Endpoints ◽  
Lesion Level ◽  
Missed Diagnosis

Background The detection of rib fractures (RFs) on computed tomography (CT) images is time-consuming and susceptible to missed diagnosis. An automated artificial intelligence (AI) detection system may be helpful to improve the diagnostic efficiency for junior radiologists. Purpose To compare the diagnostic performance of junior radiologists with and without AI software for RF detection on chest CT images. Materials and methods Six junior radiologists from three institutions interpreted 393 CT images of patients with acute chest trauma, with and without AI software. The CT images were randomly split into two sets at each institution, with each set assigned to a different radiologist First, the detection of all fractures (AFs), including displaced fractures (DFs), non-displaced fractures and buckle fractures, was analyzed. Next, the DFs were selected for analysis. The sensitivity and specificity of the radiologist-only and radiologist-AI groups at the patient level were set as primary endpoints, and secondary endpoints were at the rib and lesion level. Results Regarding AFs, the sensitivity difference between the radiologist-AI group and the radiologist-only group were significant at different levels (patient-level: 26.20%; rib-level: 22.18%; lesion-level: 23.74%; P < 0.001). Regarding DFs, the sensitivity difference was 16.67%, 14.19%, and 16.16% at the patient, rib, and lesion levels, respectively ( P < 0.001). No significant difference was found in the specificity between the two groups for AFs and DFs at the patient and rib levels ( P > 0.05). Conclusion AI software improved the sensitivity of RF detection on CT images for junior radiologists and reduced the reading time by approximately 1 min per patient without decreasing the specificity.

scholarly journals Rib fracture detection system based on deep learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Liding Yao ◽  
Xiaojun Guan ◽  
Xiaowei Song ◽  
Yanbin Tan ◽  
Chun Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Detection System ◽  
Rib Fracture ◽  
Diagnostic Efficiency ◽  
Fracture Detection ◽  
Deep Learning Algorithm ◽  
Experienced Radiologist ◽  
Comparable Performance ◽  
Detection And Diagnosis

AbstractRib fracture detection is time-consuming and demanding work for radiologists. This study aimed to introduce a novel rib fracture detection system based on deep learning which can help radiologists to diagnose rib fractures in chest computer tomography (CT) images conveniently and accurately. A total of 1707 patients were included in this study from a single center. We developed a novel rib fracture detection system on chest CT using a three-step algorithm. According to the examination time, 1507, 100 and 100 patients were allocated to the training set, the validation set and the testing set, respectively. Free Response ROC analysis was performed to evaluate the sensitivity and false positivity of the deep learning algorithm. Precision, recall, F1-score, negative predictive value (NPV) and detection and diagnosis were selected as evaluation metrics to compare the diagnostic efficiency of this system with radiologists. The radiologist-only study was used as a benchmark and the radiologist-model collaboration study was evaluated to assess the model’s clinical applicability. A total of 50,170,399 blocks (fracture blocks, 91,574; normal blocks, 50,078,825) were labelled for training. The F1-score of the Rib Fracture Detection System was 0.890 and the precision, recall and NPV values were 0.869, 0.913 and 0.969, respectively. By interacting with this detection system, the F1-score of the junior and the experienced radiologists had improved from 0.796 to 0.925 and 0.889 to 0.970, respectively; the recall scores had increased from 0.693 to 0.920 and 0.853 to 0.972, respectively. On average, the diagnosis time of radiologist assisted with this detection system was reduced by 65.3 s. The constructed Rib Fracture Detection System has a comparable performance with the experienced radiologist and is readily available to automatically detect rib fracture in the clinical setting with high efficacy, which could reduce diagnosis time and radiologists’ workload in the clinical practice.

Exploratory randomized trial to evaluate the effect of indisetron tablets for preventing chemotherapy-induced nausea and vomiting (CINV)/acute-onset diarrhea induced by IRIS/FOLFIRI: HGCSG0704.

2014 ◽  
Vol 32 (3_suppl) ◽  
pp. 624-624
Author(s):  
Sosuke Kato ◽  
Hiraku Fukushima ◽  
Kanji Kato ◽  
Satoshi Yuki ◽  
Kazuaki Harada ◽  
...  
Keyword(s):  
Receptor Antagonist ◽  
Rescue Medication ◽  
Complete Response ◽  
Acute Onset ◽  
Complete Protection ◽  
Primary Endpoints ◽  
Significant Difference ◽  
Secondary Endpoints ◽  
Colorectal Cancer Patients ◽  
Ecog Ps

624 Background: Indisetron is a 5-HT3 receptor antagonist that also antagonizes 5-HT4receptors. Indisetron tablets showed the non-inferiority to ondansetron tablets in terms of efficacy for preventing CINV. Moreover, preclinical data administered with irinotecan showed indisetron significantly reduced stool frequency in mice and inhibited the colonic peristalsis in dogs. We designed a pilot study compared with granisetron in the efficacy and tolerability of indisetron for irinotecan-induced nausea, vomiting and especially in diarrhea. Methods: Advanced colorectal cancer patients treated with FOLFIRI or IRIS (Irinotecan + S-1) with or without bevacizumab were enrolled in this study. Treatment: Arm A: indisetron tablets 8mg po day1. Arm B: granisetron 3mg iv day 1. The primary endpoints were the incidence of acute-onset diarrhea and complete protection from vomiting. Secondary endpoints were tolerability, complete protection from nausea and rate of no rescue medication. Results: Between May 2008 and July 2012, 33 patients (pts) were randomized. The study was closed prematurely due to poor accrual. Arm A: 16 pts, arm B 17 pts. Median age A: 68 y.o., B: 66 y.o.: ECOG PS 0/1: A: 12/4, B: 14/3pts. There was no significant difference of the incidence of acute-onset diarrhea between both groups (18.8% in A vs. 35.3% in B, p = 0.438). The proportion of complete protection from vomiting was 87.5% in A and 88.2% in B (p = 1.000). Similarly, complete protection from nausea, rate of no rescue medication, proportion of patients with a complete response (defined as no emetic episodes and no rescue medication) did not have a significant difference. Severity of nausea/vomiting and AE induced by 5-HT3 receptor antagonist were also similar between two groups. Conclusions: Compared with granisetron, indisetron showed effective and feasible results for preventing CINV induced by FOLFIRI or IRIS. Indisetron had also not improved the incidence of acute-onset diarrhea induced by irinotecan. Clinical trial information: UMIN000010162.

Comparison of Tobramycin Pharmacokinetics After Administration by Cris and a Traditional Intravenous Piggyback Infusion

1995 ◽  
Vol 29 (5) ◽  
pp. 465-469
Author(s):  
Vincent F Mauro ◽  
Lori R Jacobs ◽  
Laurie S Mauro ◽  
Rodger D MacArthur ◽  
Donald B White
Keyword(s):  
Maximum Concentration ◽  
Elimination Rate ◽  
Random Order ◽  
Open Label ◽  
Medical College ◽  
Primary Endpoints ◽  
Significant Difference ◽  
Secondary Endpoints ◽  
Open Label Trial ◽  
Infusion System

Objective: To compare the administration pharmacokinetics of a 30-minute intravenous piggyback (ivpb) infusion of tobramycin with those of controlled-release infusion system (CRIS) using a 20-mL vial at rates of 60 and 120 mL/h. Design: Randomized, controlled, crossover, prospective, open-label trial. Setting: Medical college-affiliated hospital. Participants: Eight healthy volunteer men between the ages of 22 and 24 years weighing between 60 and 90 kg. Interventions: Volunteers received, in random order, tobramycin sulfate 2 mg/kg iv on 3 occasions separated by 1 week. The drug was administered using a 50-mL ivpb infusion at 100 mL/h for 30 minutes, and with the CRIS using a 20-mL vial with flow rates of 60 mL/h for 1 hour (slow) and 120 mL/h for 1 hour (fast). Main Outcome Measures: Primary endpoints were area under the time–concentration curve (AUC), time to reach maximum concentration (tmax), and maximum concentration (Cmax). Secondary endpoints were elimination rate constant (ke), clearance (Cl), and half-life (t1/2). Results: Six volunteers successfully completed the trial. The tmax values observed following fast CRIS and ivpb were 28 ± 8 and 32 ± 4 minutes, respectively, and not significantly different from each other. Both occurred significantly earlier than the tmax associated with slow CRIS (44 ± 7 min). The Cmax values observed following ivpb (11.2 ± 1.5 mg/L) and slow CRIS (10.9 ± 0.9 mg/L) administration were not significantly different from each other, but both were significantly lower than that of fast CRIS (13.4 ± 1.5 mg/L). The AUCs of slow and fast CRIS were 29.8 ± 4.8 and 31.2 ± 3.8 mg/L•h, respectively, and were not significantly different from each other. The AUC of fast CRIS was significantly greater than that observed with ivpb (27.4 ± 4.3 mg/L•h). No significant difference in ke (fast CRIS 0.32 ± 0.03 h-1; slow CRIS 0.33 ± 0.04 h-1; ivpb 0.34 ± 0.0 h-1) was observed among any of the methods. Conclusions: CRIS administration of tobramycin resulted in higher AUCs than did ivpb administration. Compared with ivpb, fast CRIS resulted in a higher Cmax, but the tmax values of fast CRIS and ivpb administration were not statistically different. Compared with ivpb, slow CRIS resulted in a more delayed tmax, but the Cmax values of slow CRIS and ivpb were not statistically different.

scholarly journals Post-streptokinase PCI in STEMI patients exceeding the 24-h guidelines

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
El-Zahraa M. Esmat Sultan ◽  
Khaled R. Abdel Meguid ◽  
Hesham B. Mahmoud
Keyword(s):  
End Point ◽  
Timi Flow ◽  
Primary Endpoints ◽  
Significant Difference ◽  
Close Observation ◽  
Secondary Endpoints ◽  
Group 2 ◽  
Group 1 ◽  
The Ideal

Abstract Background Due to delay in obtaining approval from insurance institution, performing PCI after successful reperfusion using streptokinase was postponed for ˃24 h-1 week. The study was conducted to investigate safety and efficacy of such delay in comparison to the ideal guidelines of PCI (≤ 24 h) in 129 STEMI patients received streptokinase followed by PCI. Patients were divided into two groups: (group 1 = 57; early PCI ≤ 24 h.) and (group 2 = 72; late PCI > 24 h.). Results Primary end point was death, congestive heart failure and reinfarction up to 30 days. Secondary end point was TIMI flow < G3, ischemic stroke, intracranial hemorrhage and non-intracranial bleeding. No statistical significant difference was found between both groups regarding LVEF, dimensions and myocardium wall preservation and incidence of complications and TIMI flow. No primary endpoints were detected. Five patients had secondary endpoints in early PCI and four in the late PCI. Suction device and IV Eptifibatide were used more in early PCI (p = 0.003). Conclusions The study suggests that relatively late PCI (> 24 h–1wk) after successful reperfusion using streptokinase in STEMI patients seems to be safe and effective in 30-day follow-up, provided that patients received DAPT and were subjected to close observation. The results seem safely applicable when we are forced to this choice; however lack of more investigations to this hypothesis is considered a limitation.

Final results of study 20050181: A randomized phase III study of FOLFIRI with our without panitumumab (pmab) for the second‑line treatment (tx) of metastatic colorectal cancer (mCRC).

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 3535-3535 ◽  
Author(s):  
Alberto F. Sobrero ◽  
Marc Peeters ◽  
Timothy Jay Price ◽  
Yevhen Hotko ◽  
Andres Cervantes-Ruiperez ◽  
...  
Keyword(s):  
Descriptive Analysis ◽  
Objective Response ◽  
Progression Free Survival ◽  
Phase Iii ◽  
Second Line ◽  
Primary Analysis ◽  
Primary Endpoints ◽  
Significant Difference ◽  
Secondary Endpoints ◽  
Event Rates

3535 Background: The primary analysis of study 20050181 showed that in patients (pts) with wild-type (WT) KRAS mCRC, pmab plus FOLFIRI given as second-line therapy significantly improved progression-free survival (PFS) vs FOLFIRI alone. Here, we report on a prespecified descriptive analysis planned for 30 months (mos) after the last pt was enrolled. Methods: Pts with mCRC, ECOG 0-2, who had one prior fluoropyrimidine-based chemotherapy regimen were randomized 1:1 to pmab 6.0 mg/kg Q2W+FOLFIRI (Arm 1) vs FOLFIRI (Arm 2). Co-primary endpoints were OS and PFS (central assessment). Secondary endpoints included objective response rate (ORR) and safety. Tumor KRAS status was determined by a blinded central lab. Results: 1186 pts were randomised and received tx: 591 in Arm 1, 595 In Arm 2. 1083 pts (91%) had KRAS results. Adverse event rates were consistent with the primary analysis. Results are shown below. Conclusions: In pts with WT KRAS mCRC receiving pmab+FOLFIRI vs FOLFIRI, PFS and ORR were significantly improved, and there was a trend toward improved OS. Post-progression anti-EGFR tx may have attenuated any significant difference in OS between tx arms. In pts with MT KRAS mCRC, no difference in efficacy was observed between tx arms. KRAS testing is critical to select appropriate pts for tx with pmab. [Table: see text]

scholarly journals The role of 99mTc-MIBI SPECT/CT in patients with secondary hyperparathyroidism: comparison with 99mTc-MIBI planar scintigraphy and ultrasonography

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Shu-Qin Jiang ◽  
Ting Yang ◽  
Qiong Zou ◽  
Lei Xu ◽  
Ting Ye ◽  
...  
Keyword(s):  
Secondary Hyperparathyroidism ◽  
Hounsfield Unit ◽  
Ct Images ◽  
Maximum Diameter ◽  
Planar Scintigraphy ◽  
Diagnosis Group ◽  
Significant Difference ◽  
Missed Diagnosis ◽  
99Mtc Mibi ◽  
Mibi Spect

Abstract Background This study aimed to compare the sensitivity of 99mTc-MIBI SPECT/CT, 99mTc-MIBI planar scintigraphy and ultrasonography (US) in patients with secondary hyperparathyroidism (SHPT), and to explore the factors that affect the sensitivity of 99mTc-MIBI SPECT/CT. Methods In this retrospective study, forty-six patients with SHPT who underwent 99mTc-MIBI planar scintigraphy, 99mTc-MIBI SPECT/CT and US were enrolled. They underwent surgery within 1 month. We compared the sensitivity of the different imaging methods based on the lesions according to the pathological results. The parathyroid lesions on 99mTc-MIBI SPECT/CT images were divided into missed diagnosis group (MDG) and non-missed diagnosis group (NMDG). We compared the lesion to background ratio (LBR), maximum diameter, volume, the mean CT Hounsfield unit values (CTmean) and location of lesions between MDG and NMDG. Results The sensitivity of 99mTc-MIBI SPECT/CT, 99mTc-MIBI planar scintigraphy and US were 70.30% versus 48.48% versus 61.82%, respectively. The sensitivity of 99mTc-MIBI SPECT/CT combined US was 79.39%, which was higher than 99mTc-MIBI SPECT/CT with significant difference (P = 0.000). On 99mTc-MIBI SPECT/CT images, the LBR, maximum diameter and volume of lesions in MDG was smaller than those in NMDG with significant difference (P < 0.001). The average LBR, maximum diameter and volume of lesions in MDG and NMDG were 3.42 ± 1.28, 9.32 ± 2.69 mm, 208.51 ± 163.22 mm3 versus 6.75 ± 5.08, 15.03 ± 4.94 mm and 863.85 ± 1216.0 mm3, respectively. Conclusions 99mTc-MIBI SPECT/CT exhibited the highest sensitivity among the three methods. When 99mTc-MIBI SPECT/CT combined with US, the sensitivity can be further improved. Lesions with lower MIBI uptake and smaller lesions on 99mTc-MIBI SPECT/CT images were easily missed.

A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance

2021 ◽  
Author(s):  
Xiang Hong Meng ◽  
Di Jia Wu ◽  
Zhi Wang ◽  
Xin Long Ma ◽  
Xiao Man Dong ◽  
...  
Keyword(s):  
Detection System ◽  
Ct Images ◽  
Chest Ct ◽  
Rib Fracture ◽  
Fracture Detection

scholarly journals The prevalence of paramagnetic rim lesions in multiple sclerosis: A systematic review and meta-analysis

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0256845
Author(s):  
Koy Chong Ng Kee Kwong ◽  
Daisy Mollison ◽  
Rozanna Meijboom ◽  
Elizabeth N. York ◽  
Agniete Kampaite ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Systematic Review ◽  
Subgroup Analysis ◽  
Meta Analysis ◽  
Patient Level ◽  
Pooled Prevalence ◽  
Significant Difference ◽  
Disability Status ◽  
Lesion Level ◽  
Meta Regression

Background Recent findings from several studies have shown that paramagnetic rim lesions identified using susceptibility-based MRI could represent potential diagnostic and prognostic biomarkers in multiple sclerosis (MS). Here, we perform a systematic review and meta-analysis of the existing literature to assess their pooled prevalence at lesion-level and patient-level. Methods Both database searching (PubMed and Embase) and handsearching were conducted to identify studies allowing the lesion-level and/or patient-level prevalence of rim lesions or chronic active lesions to be calculated. Pooled prevalence was estimated using the DerSimonian-Laird random-effects model. Subgroup analysis and meta-regression were performed to explore possible sources of heterogeneity. PROSPERO registration: CRD42020192282. Results 29 studies comprising 1230 patients were eligible for analysis. Meta-analysis estimated pooled prevalences of 9.8% (95% CI: 6.6–14.2) and 40.6% (95% CI: 26.2–56.8) for rim lesions at lesion-level and patient-level, respectively. Pooled lesion-level and patient-level prevalences for chronic active lesions were 12.0% (95% CI: 9.0–15.8) and 64.8% (95% CI: 54.3–74.0), respectively. Considerable heterogeneity was observed across studies (I2>75%). Subgroup analysis revealed a significant difference in patient-level prevalence between studies conducted at 3T and 7T (p = 0.0312). Meta-regression analyses also showed significant differences in lesion-level prevalence with respect to age (p = 0.0018, R2 = 0.20) and disease duration (p = 0.0018, R2 = 0.48). Other moderator analyses demonstrated no significant differences according to MRI sequence, gender and expanded disability status scale (EDSS). Conclusion In this study, we show that paramagnetic rim lesions may be present in an important proportion of MS patients, notwithstanding significant variation in their assessment across studies. In view of their possible clinical relevance, we believe that clear guidelines should be introduced to standardise their assessment across research centres to in turn facilitate future analyses.

LABORATORY TESTS OF THYROID FUNCTION IN HYPERTHYROIDISM II.

1969 ◽  
Vol 62 (4_Suppla) ◽  
pp. S23-S35
Author(s):  
B.-A. Lamberg ◽  
O. P. Heinonen ◽  
K. Liewendahl ◽  
G. Kvist ◽  
M. Viherkoski ◽  
...  
Keyword(s):  
Thyroid Function ◽  
Laboratory Tests ◽  
Goodness Of Fit ◽  
Point Of View ◽  
Accurate Estimation ◽  
Diagnostic Efficiency ◽  
Normal Limits ◽  
Significant Difference ◽  
Crossing Point ◽  
Hyperthyroid Patients

ABSTRACT The distributions of 13 variables based on 10 laboratory tests measuring thyroid function were studied in euthyroid controls and in patients with toxic diffuse or toxic multinodular goitre. Density functions were fitted to the empirical data and the goodness of fit was evaluated by the use of the χ2-test. In a few instances there was a significant difference but the material available was in some respects too small to allow a very accurate estimation. The normal limits for each variable was defined by the 2.5 and 97.5 percentiles. It appears that in some instances these limits are too rigorous from the practical point of view. It is emphasized that the crossing point of the functions for euthyroid controls and hyperthyroid patients may be a better limit to use. In a preliminary analysis of the diagnostic efficiency the variables of total or free hormone concentration in the blood proved clearily superior to all other variables.

scholarly journals Randomised, controlled trial of erenumab for the prevention of episodic migraine in patients from Asia, the Middle East, and Latin America: The EMPOwER study

Cephalalgia ◽  
2021 ◽  
pp. 033310242110241
Author(s):  
Shuu-Jiun Wang ◽  
Artemio A Roxas ◽  
Bibiana Saravia ◽  
Byung-Kun Kim ◽  
Debashish Chowdhury ◽  
...  
Keyword(s):  
Latin America ◽  
Middle East ◽  
Primary Endpoint ◽  
Episodic Migraine ◽  
Acute Migraine ◽  
Efficacy And Safety ◽  
Medication Treatment ◽  
Significant Difference ◽  
Specific Medication ◽  
Secondary Endpoints

Objective EMPOwER, a double-blind, randomised, phase 3 study, evaluated the efficacy and safety of erenumab in adults with episodic migraine from Asia, the Middle East, and Latin America. Methods Randomised patients (N = 900) received monthly subcutaneous injections of placebo, erenumab 70 mg, or 140 mg (3:3:2) for 3 months. Primary endpoint was change from baseline in monthly migraine days at Month 3. Other endpoints included achievement of ≥50%, ≥75%, and 100% reduction in monthly migraine days, change in monthly acute migraine-specific medication treatment days, patient-reported outcomes, and safety assessment. Results At baseline, mean (standard deviation) age was 37.5 (9.9) years, 81.9% were women, and monthly migraine days was 8.2 (2.8). At Month 3, change from baseline in monthly migraine days (primary endpoint) was −3.1, −4.2, and −4.8 days for placebo, erenumab 70 mg, and erenumab 140 mg, respectively, with a statistically significant difference for erenumab versus placebo (P = 0.002 [70 mg], P < 0.001 [140 mg]). Both erenumab doses were also significantly superior to placebo on all secondary endpoints, including the proportion of patients achieving ≥50% reduction from baseline in monthly migraine days, change from baseline in monthly acute migraine-specific medication treatment days and change from baseline in the Headache Impact Test-6™ scores. The safety profile of erenumab was comparable with placebo; no new safety signals were observed. Conclusions This study of erenumab in patients with episodic migraine from Asia, the Middle East, and Latin America met all primary and secondary endpoints. A consistent numerical benefit was observed with erenumab 140 mg versus erenumab 70 mg across all efficacy endpoints. These findings extend evidence of erenumab’s efficacy and safety to patients under-represented in previous trials. ClinicalTrials.gov identifier: NCT03333109

Sign in / Sign up

Export Citation Format

Share Document