scholarly journals Automated Computed Tomography Lung Densitometry in Bronchiectasis Patients

Author(s):  
Marcio Valente Yamada Sawamura ◽  
Rodrigo Abensur Athanazio ◽  
Maria Cecilia Nieves Teixeira Maiorano de Nucci ◽  
Samia Zahi Rached ◽  
Alberto Cukier ◽  
...  

Abstract Rationale: Bronchiectasis is a complex and heterogeneous disease. Visual computed tomography (CT) scoring systems are used to assess disease severity, disease progression and predict outcomes in bronchiectasis although they have some limitations such as subjectivity, requirement of previous training and are time-consuming. Objective: To correlate quantitative CT lung densitometry measurements with pulmonary function test (PFT) and multidimensional prognostic scores in patients with bronchiectasis.Materials and methods: From 2014 to 2017, 100 consecutive adult patients with non-cystic fibrosis bronchiectasis underwent inspiratory and expiratory volumetric chest CT and PFT (spirometry, plethysmograph, diffusing capacity of carbon monoxide measurement [DLCO]). Visual CT score (CF-CT score), CT lung densitometry parameters (kurtosis, skewness and expiratory/inspiratory mean lung density [E/I MLD]) and multidimensional prognostic scores (BSI and FACED) were calculated in all patients and correlated to PFT.Results: CT lung densitometry parameters (kurtosis and skewness), correlated with forced expiratory volume in 1 second (FEV1) (R=0.32; p=0.001 and R=0.34; p<0.001) and DLCO (R=0.41 and R=0.43; p<0.001). Automated CT air trapping quantification (E/I MLD) showed correlation with residual volume (RV), multidimensional score FACED (R=0.63 and R=0.53; p<0.001) and performed better than the CF-CT score in the diagnosis of high-risk patients and severe air trapping. Conclusion: CT lung densitometry parameters showed correlations with PFT in non-cystic fibrosis bronchiectasis patients. Automated CT air trapping quantification performed better than visual CT score in the identification of high-risk patients and severe air trapping, suggesting it could be a useful tool in the evaluation of these patients, although further studies are needed to confirm these findings.

Blood ◽  
2015 ◽  
Vol 126 (23) ◽  
pp. 5150-5150 ◽  
Author(s):  
Mikhail Fominykh ◽  
Vasily Shuvaev ◽  
Irina Martynkevich ◽  
Grigory Tsaur ◽  
Natalya Bederak ◽  
...  

Abstract Background. About 70% of chronic myeloid leukemia (CML) patients achieve early molecular response (BCR-ABLIS2 10% at 3-months) that lead to 5-years overall survival close to 95%. However, CML patients remain heterogeneous group and several studies in recent years were aimed to personalize treatment based on individual patients' characteristics. Our group previously put forward a hypothesis about the prognostic value of individual BCR-ABL declinerate in the first three months of CML therapy1,2. The ratio BCR-ABL at 3 months to baseline had chosen as 0.1 as best cut-off value to predict MMR at 12 months. The aims of this study were to validate our prognostic method in larger group of patients and compare these results according to CML prognostic scores. Patients and methods. Fifty-five patients (median age, 52 years; range 19-84; 24 male and 31 female) with chronic phase CML were included in the study. Patients' distribution for Sokal risk groups were as follows: low-30 / intermediate-15 / high-10. Six patients had EUTOS high-risk. Forty-two patients started treatment with Imatinib 400 mg/day, 12 patients started with Nilotinib 600 mg/day and 1 patient started with Dasatinib 100 mg/day. Median BCR-ABL transcript levels was 41.38% at diagnosis, range 3.39-3185.36% (IS). The ratio of BCR-ABL levels at 3 months to baseline for each patient was calculated. In addition, we calculated ratio of BCR-ABL levels at 3 months to BCR-ABL levels at 1 month for 13 patients. Comparison was made of the predictive sensitivity to achieve early molecular response at 3 months (10% by IS) and according to prognostic CML scores (Sokal and EUTOS). We also assessed positive likelihood ratio (LR) value for the probability of achieving MMR between patients' stratification methods. Statistical analysis was conducted with Fisher exact test and sensitivity-specificity analyses. Results. Twenty-six out of 34 patients (76.5%) with ratio of BCR-ABL levels at 3 months to baseline below than 0.1 achieved MMR at 12 months, while only 9 of 21 patients (42.9%) with ratio more than 0.1 had optimal response (LR = 1.86 (1.05 - 3.29); p=0.003). Ratio of BCR-ABL levels at 3 months to 1 month showed much better results with the same (0.1) cut-off value - 5 out of 6 patients (83.3%) with ratio BCR-ABL at 3 months to 1 month below than 0.1, while only 1 patient (14.3%) with ratio more than 0.1 achieved optimal response (LR = 5.83 (0.92 - 37.08); p=0.05), respectively. Application of early molecular response at 3 months (10% by IS) yielded worse discrimination results: 34 of 47 (72.3%) patients with BCR-ABL level ²10% at 3 months, whereas 2 of 8 (25%) patients with BCR-ABL >10% had MMR at 1 year (LR = 1.38 (1.01 - 1.89); p=0.78), respectively. CML prognostic scores results had the following sensitivity-specificity results: for Sokal - low-risk 23 of 30 (76.7%), intermediate-risk 9 of 15 (60%) and 3 of 10 (30%) high-risk patients achieved MMR at 1 year (LR (low+intermediate)/high = 1.41 (1.00 - 1.97); p=0.03); for EUTOS-score - low-risk 34 of 49 (69.4%) and only 1 of 6 (16.7%) high-risk patients had achieved MMR at 12 months (LR = 1.30 (1.00 - 1.68); p=0.02). Furthermore, application of our ratio cut-off value among patients with BCR-ABL level ²10% at 3 months allowed us to revealed additional 6 high-risk patients have not reached MMR at 1 year of therapy (Table 1). Conclusion. Our study showed that individual rates of BCR-ABL decline from baseline to 3 months and to 1 month had better LR than CML prognostic scores (Sokal, EUTOS) or early molecular response achievement (BCR-ABL levels ²10% at 3 months) and might be useful as an optimized predictors of outcome for CML patients (MMR at 1 year of treatment). 1 Fominykh M., ShuvaevV., Martynkevich I. et al. ELN Frontiers Meeting ÇWhere science meets clinical practiceÈ 16-19 October, 2014, Berlin, Germany. Abstract book: 11. 2 Shuvaev V., Fominykh M., Martynkevich I. et al. Blood (56th ASH Annual Meeting Abstracts), 2014; 124 (21): 5529. Figure 1. The patient numbers of achieving MMR at 12 months of therapy in various stratification groups with sensitivity-specificity characteristics Figure 1. The patient numbers of achieving MMR at 12 months of therapy in various stratification groups with sensitivity-specificity characteristics Disclosures Chelysheva: Novartis Pharma: Consultancy, Honoraria; Bristol Myers Squibb: Honoraria. Turkina:Bristol Myers Squibb: Consultancy; Pfizer: Consultancy; Novartis Pharma: Consultancy.


Heart ◽  
2018 ◽  
Vol 104 (7) ◽  
pp. 625-625 ◽  
Author(s):  
Vincenzo Vizzi ◽  
Maurizio Di Biasi ◽  
Giuseppe Alessandrino ◽  
Alessandro Colombo ◽  
Paolo Danna ◽  
...  

Author(s):  
Shuo Wang ◽  
Yunfei Zha ◽  
Weimin Li ◽  
Qingxia Wu ◽  
Xiaohu Li ◽  
...  

AbstractCoronavirus disease 2019 (COVID-19) has spread globally, and medical resources become insufficient in many regions. Fast diagnosis of COVID-19, and finding high-risk patients with worse prognosis for early prevention and medical resources optimization is important. Here, we proposed a fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis by routinely used computed tomography.We retrospectively collected 5372 patients with computed tomography images from 7 cities or provinces. Firstly, 4106 patients with computed tomography images and gene information were used to pre-train the DL system, making it learn lung features. Afterwards, 1266 patients (924 with COVID-19, and 471 had follow-up for 5+ days; 342 with other pneumonia) from 6 cities or provinces were enrolled to train and externally validate the performance of the deep learning system.In the 4 external validation sets, the deep learning system achieved good performance in identifying COVID-19 from other pneumonia (AUC=0.87 and 0.88) and viral pneumonia (AUC=0.86). Moreover, the deep learning system succeeded to stratify patients into high-risk and low-risk groups whose hospital-stay time have significant difference (p=0.013 and 0.014). Without human-assistance, the deep learning system automatically focused on abnormal areas that showed consistent characteristics with reported radiological findings.Deep learning provides a convenient tool for fast screening COVID-19 and finding potential high-risk patients, which may be helpful for medical resource optimization and early prevention before patients show severe symptoms.Take-home messageFully automatic deep learning system provides a convenient method for COVID-19 diagnostic and prognostic analysis, which can help COVID-19 screening and finding potential high-risk patients with worse prognosis.


Respiration ◽  
2012 ◽  
Vol 84 (6) ◽  
pp. 501-508 ◽  
Author(s):  
T. Schneider ◽  
M. Puderbach ◽  
J. Kunz ◽  
A. Bischof ◽  
F.L. Giesel ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document