Traffic Noise Assessment in Urban Puducherry, South India.

Background Noise pollution is an emerging global problem that can affect people's well-being and mental and physical health. In India, six percent of people suffer hearing loss, and prolonged exposure leads to irreversible noise-induced hearing loss. Objective To assess the noise levels at selected residential, commercial, industrial, silence zones, traffic junctions, and related noise indices in urban Puducherry and compare them with Central Pollution Control Board (CPCB) standards. Methods The study was conducted using a cross-sectional noise survey based on the 2015 study sites in urban Puducherry using a sound level meter, analyzed the results with limits set by the CPCB standards, and calculated the various noise indices. Results In urban Puducherry, the noise level showing silence zones is more hazardous than industrial, residential, commercial, and traffic junctions. Out of the 36 sites surveyed, 33 locations are above the prescribed daytime limit by CPCB. Conclusions The noise assessment at selected sites in urban Puducherry shows that around 92% of study sites are well above the daytime standards of CPCB, highlighting an urgent need to curb noise levels. The findings revealed that increased noise at study sites could be due to the increased number of vehicles and transportation systems.

Observer Performance Evaluation of a Deep Learning Model for Multilabel Classification of Active Tuberculosis Lung Zone-Wise Manifestations.

Background Chest X-rays (CXRs) are widely used for cost-effective screening of active pulmonary tuberculosis despite their limitations in sensitivity and specificity when interpreted by clinicians or radiologists. To address this issue, computer-aided detection (CAD) algorithms, particularly deep learning architectures based on convolution, have been developed to automate the analysis of radiography imaging. Deep learning algorithms have shown promise in accurately classifying lung abnormalities using chest X-ray images. In this study, we utilized the EfficientNet B4 model, which was pre-trained on ImageNet with 380x380 input dimensions, using its weights for transfer learning, and was modified with a series of components including global average pooling, batch normalization, dropout, and a classifier with 12 image-wise and 44 segment-wise lung zone evaluation classes using sigmoid activation. Objectives Assess the clinical usefulness of our previously created EfficientNet B4 model in identifying lung zone-specific abnormalities related to active tuberculosis through an observer performance test involving a skilled clinician operating in tuberculosis-specific environments. Methods The ground truth was established by a radiologist who examined all sample CXRs to identify lung zone-wise abnormalities. An expert clinician working in tuberculosis-specific settings independently reviewed the same CXR with blinded access to the ground truth. Simultaneously, the CXRs were classified using the EfficientNet B4 model. The clinician's assessments were then compared with the model's predictions, and the agreement between the two was measured using the kappa coefficient, evaluating the model's performance in classifying active tuberculosis manifestations across lung zones. Results The results show a strong agreement (Kappa ≥0.81) seen for lung zone-wise abnormalities of pneumothorax, mediastinal shift, emphysema, fibrosis, calcifications, pleural effusion, and cavity. Substantial agreement (Kappa = 0.61-0.80) for cavity, mediastinal shift, volume loss, and collapsed lungs. The Kappa score for lung zone-wise abnormalities is moderate (0.41-0.60) for 39% of cases. In image-wise agreement, the EfficientNet B4 model's performance ranges from moderate to almost perfect across categories, while in lung zone-wise agreement, it varies from fair to almost perfect. The results show strong agreement between the EfficientNet B4 model and the human reader in detecting lung zone-wise and image-wise manifestations. Conclusion The clinical utility of the EfficientNet B4 models to detect the abnormalities can aid clinicians in primary care settings for screening and triaging tuberculosis where resources are constrained or overburdened.

Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: a multi label approach.

Chest X-rays are the most economically viable diagnostic imaging test for active pulmonary tuberculosis screening despite the high sensitivity and low specificity when interpreted by clinicians or radiologists. Computer aided detection (CAD) algorithms, especially convolution based deep learning architecture, have been proposed to facilitate the automation of radiography imaging modalities. Deep learning algorithms have found success in classifying various abnormalities in lung using chest X-ray. We fine-tuned, validated and tested EfficientNetB4 architecture and utilized the transfer learning methodology for multilabel approach to detect lung zone wise and image wise manifestations of active pulmonary tuberculosis using chest X-ray. We used Area Under Receiver Operating Characteristic (AUC), sensitivity and specificity along with 95% confidence interval as model evaluation metrics. We also utilized the visualisation capabilities of convolutional neural networks (CNN), Gradient-weighted Class Activation Mapping (Grad-CAM) as post-hoc attention method to investigate the model and visualisation of Tuberculosis abnormalities and discuss them from radiological perspectives. EfficientNetB4 trained network achieved remarkable AUC, sensitivity and specificity of various pulmonary tuberculosis manifestations in intramural test set and external test set from different geographical region. The grad-CAM visualisations and their ability to localize the abnormalities can aid the clinicians at primary care settings for screening and triaging of tuberculosis where resources are constrained or overburdened.

Geographical Information System-Aided Noise Pollution Mapping of Urban Puducherry, South India.

Context: Noise pollution and its influence on environmental and quality of human life are a major concern and hot topic of scientific research in the twenty-first century. Aims: Spatial analysis of noise pollution in urban Puducherry, South India. Settings and Design: Cross-sectional study conducted in 36 locations of urban Puducherry. Methods and Material: Noise measurements were taken using a calibrated NOR 132 digital sound level meter using the prescribed parameters set by the Central Pollution Control Board. Geo coordinates were taken using Garmin Oregon 550 GPS. Noise measurements were classified according to the Bureau of Indian Standards for town planning into five zones. Statistical Analysis Used: Noise pollution map of urban Puducherry for three time points of the day was generated using ArcGIS Desktop v10.3 with Geo-statistical module and Inverse Distance method. Results: Seventeen percent of the sites are high noise sources (80-90 dB), two thirds (65%) of the study sites fall into concentrated average noise zones (70-80 dB), and less than one fifth (18%) of the study sites are in relatively quiet zones across different measurement time slots. Conclusions: Long-term strategy for noise control should be incorporated in the development of new townships and other infrastructures in accordance with the noise control norms. Implications for future research include monitoring noise pollution levels in rural areas and health effects of noise pollution in bystanders and drivers.