RESUMEN
PURPOSE: The current study explores the application of 3D U-Net architectures combined with Inception and ResNet modules for precise lung nodule detection through deep learning-based segmentation technique. This investigation is motivated by the objective of developing a Computer-Aided Diagnosis (CAD) system for effective diagnosis and prognostication of lung nodules in clinical settings. METHODS: The proposed method trained four different 3D U-Net models on the retrospective dataset obtained from AIIMS Delhi. To augment the training dataset, affine transformations and intensity transforms were utilized. Preprocessing steps included CT scan voxel resampling, intensity normalization, and lung parenchyma segmentation. Model optimization utilized a hybrid loss function that combined Dice Loss and Focal Loss. The model performance of all four 3D U-Nets was evaluated patient-wise using dice coefficient and Jaccard coefficient, then averaged to obtain the average volumetric dice coefficient (DSCavg) and average Jaccard coefficient (IoUavg) on a test dataset comprising 53 CT scans. Additionally, an ensemble approach (Model-V) was utilized featuring 3D U-Net (Model-I), ResNet (Model-II), and Inception (Model-III) 3D U-Net architectures, combined with two distinct patch sizes for further investigation. RESULTS: The ensemble of models obtained the highest DSCavg of 0.84 ± 0.05 and IoUavg of 0.74 ± 0.06 on the test dataset, compared against individual models. It mitigated false positives, overestimations, and underestimations observed in individual U-Net models. Moreover, the ensemble of models reduced average false positives per scan in the test dataset (1.57 nodules/scan) compared to individual models (2.69-3.39 nodules/scan). CONCLUSIONS: The suggested ensemble approach presents a strong and effective strategy for automatically detecting and delineating lung nodules, potentially aiding CAD systems in clinical settings. This approach could assist radiologists in laborious and meticulous lung nodule detection tasks in CT scans, improving lung cancer diagnosis and treatment planning.
RESUMEN
OBJECTIVES: To translate the Pediatric Nausea Assessment Tool (PeNAT) into Hindi and validate it in Indian pediatric cancer patients and survivors. METHODS: The PeNAT-Hindi was finalized by forward and backward translations, and pilot testing. The PeNAT-Hindi was administered to 200 Hindi-speaking pediatric (4-18 y) cancer patients/survivors, in three groups. These included pediatric cancer patients who had recently received chemotherapy (n = 150); who received no chemotherapy within 5 d (n = 25) and survivors (n = 25). Construct validity was tested by comparing scores among the three groups. Test-retest reliability and criterion validity were estimated by the correlation of the first PeNAT score with the second (taken 1 h later) PeNAT score and the number of vomiting/retching episodes, respectively. Convergent validity and discriminant validity were estimated by correlating PeNAT scores with parent-assessed nausea severity, and pain, respectively. The responsiveness was tested by comparing second PeNAT scores with subsequent divergent PeNAT scores among patients reporting subjective change (improvement and worsening, respectively) in nausea severity. RESULTS: Test-retest reliability of PeNAT-Hindi was good (intraclass correlation = 0.791). The initial PeNAT score had moderate correlation with the number of vomiting/retching episodes (Spearman ρ = 0.401). Median PeNAT scores in group 1 versus groups 2 and 3 were significantly different (p < 0.001). Initial PeNAT scores showed a moderate correlation with parent-assessed nausea (Spearman ρ = 0.657) and a weak correlation with parent-assessed pain (Spearman ρ = 0.319). The responsiveness (standardized response mean) of PeNAT-Hindi to the change in nausea severity was -1.79 (improvement) and 2.19 (worsening), respectively. CONCLUSION: PeNAT-Hindi showed good reliability and acceptable validity. It may be used among Hindi-speaking children for measuring nausea. The responsiveness of PeNAT-Hindi needs further evaluation.
Asunto(s)
Neoplasias , Calidad de Vida , Humanos , Niño , Psicometría , Reproducibilidad de los Resultados , Encuestas y Cuestionarios , Traducciones , Náusea/diagnóstico , Lenguaje , Neoplasias/complicaciones , Neoplasias/diagnóstico , Neoplasias/tratamiento farmacológico , Vómitos/diagnóstico , DolorRESUMEN
PURPOSE: The proposed work aims to develop an algorithm to precisely segment the lung parenchyma in thoracic CT scans. To achieve this goal, the proposed technique utilized a combination of deep learning and traditional image processing algorithms. The initial step utilized a trained convolutional neural network (CNN) to generate preliminary lung masks, followed by the proposed post-processing algorithm for lung boundary correction. METHODS: First, the proposed method trained an improved 2D U-Net CNN model with Inception-ResNet-v2 as its backbone. The model was trained on 32 CT scans from two different sources: one from the VESSEL12 grand challenge and the other from AIIMS Delhi. Further, the model's performance was evaluated on a test dataset of 16 CT scans with juxta-pleural nodules obtained from AIIMS Delhi and the LUNA16 challenge. The model's performance was assessed using evaluation metrics such as average volumetric dice coefficient (DSCavg), average IoU score (IoUavg), and average F1 score (F1avg). Finally, the proposed post-processing algorithm was implemented to eliminate false positives from the model's prediction and to include juxta-pleural nodules in the final lung masks. RESULTS: The trained model reported a DSCavg of 0.9791 ± 0.008, IoUavg of 0.9624 ± 0.007, and F1avg of 0.9792 ± 0.004 on the test dataset. Applying the post-processing algorithm to the predicted lung masks obtained a DSCavg of 0.9713 ± 0.007, IoUavg of 0.9486 ± 0.007, and F1avg of 0.9701 ± 0.008. The post-processing algorithm successfully included juxta-pleural nodules in the final lung mask. CONCLUSIONS: Using a CNN model, the proposed method for lung parenchyma segmentation produced precise segmentation results. Furthermore, the post-processing algorithm addressed false positives and negatives in the model's predictions. Overall, the proposed approach demonstrated promising results for lung parenchyma segmentation. The method has the potential to be valuable in the advancement of computer-aided diagnosis (CAD) systems for automatic nodule detection.
Asunto(s)
Aprendizaje Profundo , Humanos , Pulmón/diagnóstico por imagen , Tórax , Redes Neurales de la Computación , Procesamiento de Imagen Asistido por Computador/métodos , Tomografía Computarizada por Rayos XRESUMEN
The presence of lung metastases in patients with primary malignancies is an important criterion for treatment management and prognostication. Computed tomography (CT) of the chest is the preferred method to detect lung metastasis. However, CT has limited efficacy in differentiating metastatic nodules from benign nodules (e.g., granulomas due to tuberculosis) especially at early stages (<5 mm). There is also a significant subjectivity associated in making this distinction, leading to frequent CT follow-ups and additional radiation exposure along with financial and emotional burden to the patients and family. Even 18F-fluoro-deoxyglucose positron emission technology-computed tomography (18F-FDG PET-CT) is not always confirmatory for this clinical problem. While pathological biopsy is the gold standard to demonstrate malignancy, invasive sampling of small lung nodules is often not clinically feasible. Currently, there is no non-invasive imaging technique that can reliably characterize lung metastases. The lung is one of the favored sites of metastasis in sarcomas. Hence, patients with sarcomas, especially from tuberculosis prevalent developing countries, can provide an ideal platform to develop a model to differentiate lung metastases from benign nodules. To overcome the lack of optimal specificity of CT scan in detecting pulmonary metastasis, a novel artificial intelligence (AI)-based protocol is proposed utilizing a combination of radiological and clinical biomarkers to identify lung nodules and characterize it as benign or metastasis. This protocol includes a retrospective cohort of nearly 2,000-2,250 sample nodules (from at least 450 patients) for training and testing and an ambispective cohort of nearly 500 nodules (from 100 patients; 50 patients each from the retrospective and prospective cohort) for validation. Ground-truth annotation of lung nodules will be performed using an in-house-built segmentation tool. Ground-truth labeling of lung nodules (metastatic/benign) will be performed based on histopathological results or baseline and/or follow-up radiological findings along with clinical outcome of the patient. Optimal methods for data handling and statistical analysis are included to develop a robust protocol for early detection and classification of pulmonary metastasis at baseline and at follow-up and identification of associated potential clinical and radiological markers.
RESUMEN
Importance: A surge of COVID-19 occurred from March to June 2021, in New Delhi, India, linked to the B.1.617.2 (Delta) variant of SARS-CoV-2. COVID-19 vaccines were rolled out for health care workers (HCWs) starting in January 2021. Objective: To assess the incidence density of reinfection among a cohort of HCWs and estimate the effectiveness of the inactivated whole virion vaccine BBV152 against reinfection. Design, Setting, and Participants: This was a retrospective cohort study among HCWs working at a tertiary care center in New Delhi, India. Exposures: Vaccination with 0, 1, or 2 doses of BBV152. Main Outcomes and Measures: The HCWs were categorized as fully vaccinated (with 2 doses and ≥15 days after the second dose), partially vaccinated (with 1 dose or 2 doses with <15 days after the second dose), or unvaccinated. The incidence density of COVID-19 reinfection per 100 person-years was computed, and events from March 3, 2020, to June 18, 2021, were included for analysis. Unadjusted and adjusted hazard ratios (HRs) were estimated using a Cox proportional hazards model. Estimated vaccine effectiveness (1 - adjusted HR) was reported. Results: Among 15â¯244 HCWs who participated in the study, 4978 (32.7%) were diagnosed with COVID-19. The mean (SD) age was 36.6 (10.3) years, and 55.0% were male. The reinfection incidence density was 7.26 (95% CI: 6.09-8.66) per 100 person-years (124 HCWs [2.5%], total person follow-up period of 1696 person-years as time at risk). Fully vaccinated HCWs had lower risk of reinfection (HR, 0.14 [95% CI, 0.08-0.23]), symptomatic reinfection (HR, 0.13 [95% CI, 0.07-0.24]), and asymptomatic reinfection (HR, 0.16 [95% CI, 0.05-0.53]) compared with unvaccinated HCWs. Accordingly, among the 3 vaccine categories, reinfection was observed in 60 of 472 (12.7%) of unvaccinated (incidence density, 18.05 per 100 person-years; 95% CI, 14.02-23.25), 39 of 356 (11.0%) of partially vaccinated (incidence density 15.62 per 100 person-years; 95% CI, 11.42-21.38), and 17 of 1089 (1.6%) fully vaccinated (incidence density 2.18 per 100 person-years; 95% CI, 1.35-3.51) HCWs. The estimated effectiveness of BBV152 against reinfection was 86% (95% CI, 77%-92%); symptomatic reinfection, 87% (95% CI, 76%-93%); and asymptomatic reinfection, 84% (95% CI, 47%-95%) among fully vaccinated HCWs. Partial vaccination was not associated with reduced risk of reinfection. Conclusions and Relevance: These findings suggest that BBV152 was associated with protection against both symptomatic and asymptomatic reinfection in HCWs after a complete vaccination schedule, when the predominant circulating variant was B.1.617.2.