Artificial Intelligence has changed the way medical images are looked at in radiology. Doctors need to diagnose people accurately. Old Artificial Intelligence systems for medicine usually need the internet to work. They use cloud computing. Need to be online all the time to look at medical data. This is a problem because it can be slow, expensive and not good for keeping patient information private. It also does not work well in places with internet. This makes it hard to use diagnostic systems in rural areas, emergency rooms and other places where resources are limited. So, this project is trying to make a system that can detect lung disease from chest X-ray images without needing the internet. The system uses learning to find many kinds of lung diseases like pneumonia, tuberculosis and COVID-19. It can do this on devices like NVIDIA Jetson Nano, Google Coral Edge TPU and Raspberry Pi 5 and even on smartphones. This research proposes an enhanced Artificial Intelligence (AI)-based lung disease diagnosis system that integrates real-time edge detection techniques with a voice-based explanation module. The system utilizes deep learning algorithms, particularly Convolutional Neural Networks (CNNs), to analyze chest X-ray or CT scan images. Real-time edge detection is applied as a preprocessing step to enhance lung boundaries, highlight abnormal regions, and improve feature extraction accuracy. The integration of real-time processing and voice assistance makes the system suitable for smart healthcare environments and telemedicine applications. This approach contributes to early disease detection, improved patient communication, and accessible AI-driven medical diagnostics. Because the system works on the device itself it is faster does not need the cloud and keeps information private. It can give answers in one to two seconds, which's good for medical emergencies. Another important thing about this system is that it is transparent. In healthcare it is not enough for a model to be right it also needs to explain why it made a decision. So, the system uses techniques like Gradient-weighted Class Activation Mapping and Local Interpretable Model- Explanations. These help doctors see which parts of the X-ray image the system used to make its decision. The system also has a voice feature that tells doctors what it found in language. This is helpful for healthcare workers who may not be able to look at the images. It makes the system easier to use in medical settings. The system is portable uses energy keeps information private and can be used offline. It combines edge computing, deep learning, Artificial Intelligence and voice features to help doctors detect lung disease early. This can help doctors diagnose faster have work to do and make healthcare better especially in places where internet and medical resources are limited. Artificial Intelligence and lung disease detection are important for saving lives. Lung disease detection systems, like this one can really make a difference. The proposed model performs automated classification of lung conditions and provides rapid diagnostic predictions with high accuracy. To improve usability and accessibility, especially in rural or resource-limited healthcare settings, the system incorporates a voice-based explanation feature. This module converts diagnostic results into clear, understandable audio feedback for patients and medical practitioners, thereby enhancing transparency and interpretability of AI decisions. This paper presents an enhanced Artificial Intelligence (AI)-based lung disease diagnosis system that combines real-time edge detection with a voice-based explanation framework to improve diagnostic precision, interpretability, and accessibility.
Chest X-ray, Deep Learning, Edge AI, Explainable AI (XAI), MobileNetV3, Lung Segmentation, Offline Diagnostics, Multimodal Interface, Grad-CAM, Medical Imaging, Rural Healthcare, Computer-Aided Diagnosis (CADx), Squeeze-and-Excitation Networks, Model Quantization, Semantic Segmentation, Clinical Decision Support System (CDSS), Human-Centric AI.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.