arXiv subjects

Aashish Ghimire

Publications and source records attributed to Aashish Ghimire.

7 recordsLinked to original sources

arXiv2026

A Comparative Study of GAN-Based Deep Learning Models for Pneumonia Detection in Chest X-Rays

This study evaluates pneumonia classification in chest X-rays using VGG19, MobileNetV2, ResNet50, and a custom CNN, and explores Generative Adversarial Network (GAN)-based synthetic data augmentation. MobileNetV2 achieved the highest reported accuracy of 88% with balanced class-wise performance. The custom CNN achieved pneumonia recall of 92.67% and precision of 79.43%, highlighting a precision-recall trade-off. Accuracy, F1-score, precision, recall, confusion matrices, and training curves were used to assess performance. Synthetic pneumonia images were combined with real images to investigate whether augmentation could improve classification performance. In the reported VGG19 comparison, augmented-data training accuracy reached approximately 100%, while validation accuracy remained near 50%, below the real-data validation accuracy. This experiment therefore did not demonstrate a validation-performance benefit from GAN augmentation. The classifier comparison highlights differences in accuracy and pneumonia recall, while the augmentation experiment indicates the need for further evaluation of synthetic-image quality and training settings.

cs.CV↗

arXiv2026

DentiAsk: A VQA Benchmark for Multimodal Reasoning in Panoramic Dental Radiographs

Accurate interpretation of panoramic dental radiographs requires the integration of multiple reasoning capabilities: detection, spatial localization, and quantitative assessment. Despite recent advances in multimodal learning, existing medical visual question answering (VQA) benchmarks do not fully capture this complexity, often reducing the task to simplified classification or templated queries. As a result, they provide limited coverage of the diverse reasoning processes required for clinically meaningful interpretation. We introduce DentiAsk, a large-scale dental VQA benchmark that pairs high-resolution panoramic dental radiographs with clinician-validated question-answer pairs spanning three reasoning tiers: descriptive recognition, spatial localization, and numerical quantification across three high-prevalence pathologies: periapical radiolucency (PARL), impacted teeth, and dental caries. DentiAsk comprises 1,000 high-resolution radiographs annotated with 10,000 expert-curated QA pairs. To our knowledge, it is the first dental VQA benchmark to unify categorical, spatial, and quantitative reasoning as separately scored tasks within a single evaluation framework. We benchmark 10 state-of-the-art vision-language models, including LLaVA-v1.5, LLaVA-v1.6, Qwen-VL, InternVL2, and LLaVA-Med, and find that models achieve stronger performance on descriptive queries, whereas they degrade sharply on spatial localization and counting, exposing limitations in compositional, multi-step reasoning. These findings reveal a gap between visual recognition and clinically meaningful reasoning, establishing DentiAsk as a challenging benchmark for advancing multimodal reasoning in medical imaging.

q-bio.QM↗

arXiv2026

Low-Cost IoT-Enabled Tele-ECG Monitoring for Resource-Constrained Settings: System Design and Prototype

With the availability of automation machinery and its superiority, are being slothful and inviting many diseases to invade them. The world still has so many places where people lack basic health facilities. Due to early detection and intervention, CDV can be cured to an extreme extent. It heavily reduces travel and associated costs. A remote ECG monitoring system enables community health workers to support and empower patients through telemedicine. However, there remains some financial and logistical burden. Heart disease cannot be taken lightly. These patients require regular health check-ups and the attention of health personnel in a short period if their health deteriorates suddenly and rapidly. Chronic diseases are extremely variable in their symptoms and evolution of treatment. Some, if not treated early, will end the patient's life. The trend of the INTERNET OF THINGS, IoT, is spreading massively. This paper focuses on the three main: the operator, the doctor, and the server over which the data is being sent.

cs.AR↗

arXiv2025

When CNNs Outperform Transformers and Mambas: Revisiting Deep Architectures for Dental Caries Segmentation

Accurate identification and segmentation of dental caries in panoramic radiographs are critical for early diagnosis and effective treatment planning. Automated segmentation remains challenging due to low lesion contrast, morphological variability, and limited annotated data. In this study, we present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset. Twelve state-of-the-art architectures, including VMUnet, MambaUNet, VMUNetv2, RMAMamba-S, TransNetR, PVTFormer, DoubleU-Net, and ResUNet++, were trained under identical configurations. Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants. In the study, the top 3 results across all performance metrics were achieved by CNN-based architectures. Here, Mamba and transformer-based methods, despite their theoretical advantage in global context modeling, underperformed due to limited data and weaker spatial priors. These findings underscore the importance of architecture-task alignment in domain-specific medical image segmentation more than model complexity. Our code is available at: https://github.com/JunZengz/dental-caries-segmentation.

cs.CV↗

arXiv2024

Generative AI Adoption in Classroom in Context of Technology Acceptance Model (TAM) and the Innovation Diffusion Theory (IDT)

The burgeoning development of generative artificial intelligence (GenAI) and the widespread adoption of large language models (LLMs) in educational settings have sparked considerable debate regarding their efficacy and acceptability.Despite the potential benefits, the assimilation of these cutting-edge technologies among educators exhibits a broad spectrum of attitudes, from enthusiastic advocacy to profound skepticism.This study aims to dissect the underlying factors influencing educators' perceptions and acceptance of GenAI and LLMs.We conducted a survey among educators and analyzed the data through the frameworks of the Technology Acceptance Model (TAM) and Innovation Diffusion Theory (IDT). Our investigation reveals a strong positive correlation between the perceived usefulness of GenAI tools and their acceptance, underscoring the importance of demonstrating tangible benefits to educators. Additionally, the perceived ease of use emerged as a significant factor, though to a lesser extent, influencing acceptance. Our findings also show that the knowledge and acceptance of these tools is not uniform, suggesting that targeted strategies are required to address the specific needs and concerns of each adopter category to facilitate broader integration of AI tools.in education.

cs.CY↗

arXiv2024

Generative AI in Education: A Study of Educators' Awareness, Sentiments, and Influencing Factors

The rapid advancement of artificial intelligence (AI) and the expanding integration of large language models (LLMs) have ignited a debate about their application in education. This study delves into university instructors' experiences and attitudes toward AI language models, filling a gap in the literature by analyzing educators' perspectives on AI's role in the classroom and its potential impacts on teaching and learning. The objective of this research is to investigate the level of awareness, overall sentiment towardsadoption, and the factors influencing these attitudes for LLMs and generative AI-based tools in higher education. Data was collected through a survey using a Likert scale, which was complemented by follow-up interviews to gain a more nuanced understanding of the instructors' viewpoints. The collected data was processed using statistical and thematic analysis techniques. Our findings reveal that educators are increasingly aware of and generally positive towards these tools. We find no correlation between teaching style and attitude toward generative AI. Finally, while CS educators show far more confidence in their technical understanding of generative AI tools and more positivity towards them than educators in other fields, they show no more confidence in their ability to detect AI-generated work.

cs.AI↗

arXiv2024

From Guidelines to Governance: A Study of AI Policies in Education

Emerging technologies like generative AI tools, including ChatGPT, are increasingly utilized in educational settings, offering innovative approaches to learning while simultaneously posing new challenges. This study employs a survey methodology to examine the policy landscape concerning these technologies, drawing insights from 102 high school principals and higher education provosts. Our results reveal a prominent policy gap: the majority of institutions lack specialized guide-lines for the ethical deployment of AI tools such as ChatGPT. Moreover,we observed that high schools are less inclined to work on policies than higher educational institutions. Where such policies do exist, they often overlook crucial issues, including student privacy and algorithmic transparency. Administrators overwhelmingly recognize the necessity of these policies, primarily to safeguard student safety and mitigate plagiarism risks. Our findings underscore the urgent need for flexible and iterative policy frameworks in educational contexts.

cs.CY↗