RESUMO
Colonoscopy is a reliable diagnostic method to detect colorectal polyps early on and prevent colorectal cancer. The current examination techniques face a significant challenge of high missed rates, resulting in numerous undetected polyps and irregularities. Automated and real-time segmentation methods can help endoscopists to segment the shape and location of polyps from colonoscopy images in order to facilitate clinician's timely diagnosis and interventions. Different parameters like shapes, small sizes of polyps, and their close resemblance to surrounding tissues make this task challenging. Furthermore, high-definition image quality and reliance on the operator make real-time and accurate endoscopic image segmentation more challenging. Deep learning models utilized for segmenting polyps, designed to capture diverse patterns, are becoming progressively complex. This complexity poses challenges for real-time medical operations. In clinical settings, utilizing automated methods requires the development of accurate, lightweight models with minimal latency, ensuring seamless integration with endoscopic hardware devices. To address these challenges, in this study a novel lightweight and more generalized Enhanced Nanonet model, an improved version of Nanonet using NanonetB for real-time and precise colonoscopy image segmentation, is proposed. The proposed model enhances the performance of Nanonet using Nanonet B on the overall prediction scheme by applying data augmentation, Conditional Random Field (CRF), and Test-Time Augmentation (TTA). Six publicly available datasets are utilized to perform thorough evaluations, assess generalizability, and validate the improvements: Kvasir-SEG, Endotect Challenge 2020, Kvasir-instrument, CVC-ClinicDB, CVC-ColonDB, and CVC-300. Through extensive experimentation, using the Kvasir-SEG dataset, our model achieves a mIoU score of 0.8188 and a Dice coefficient of 0.8060 with only 132,049 parameters and employing minimal computational resources. A thorough cross-dataset evaluation was performed to assess the generalization capability of the proposed Enhanced Nanonet model across various publicly available polyp datasets for potential real-world applications. The result of this study shows that using CRF (Conditional Random Fields) and TTA (Test-Time Augmentation) enhances performance within the same dataset and also across diverse datasets with a model size of just 132,049 parameters. Also, the proposed method indicates improved results in detecting smaller and sessile polyps (flats) that are significant contributors to the high miss rates.
RESUMO
The vitality contribution is a vital cause for defensible monetary improvement and collective success by eradicating poverty. Adopting the solar home lighting system (SHLS) is advantageous not only in social lifestyles but also improves the health of family members and increases home-based small businesses activities due to the inexpensive and continuous supply of energy. The main aims of the study are to scrutinize the most substantial barriers to adopting SHLS in Pakistan. A comprehensive, structured questionnaire appraisal was conducted for sample size with the help of non-probability sampling (purposive sampling), and primary data was collected. The designated hypotheses were evaluated using partial least square structural equation modeling (PLS-SEM). In the present study, we validate the model using a sample of 271 adopters of SHLS contributed as respondents. The results disclose that entire autonomous variables expressively and positively correlated with adopting SHLS dipping energy disasters and improving home-based small business activities. Correspondingly, social media-based awareness of SHLS significantly moderates and positively affects the selected factors in this study. Empirical results indicate that prudently eradicating maintenance barriers with experienced professionals, subsidy in prices from the government, quality base satisfaction of owners, and social media-based awareness are the primary tools to adopt SHLS. Additionally, the outcomes offer valuable suggestions to the competent authorities that introduce encouragement and maintenance policy for adopting SHLS.