IM- LTS: An Integrated Model for Lung Tumor Segmentation using Neural Networks and IoMT.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computer Science

Background:

• Early lung tumor diagnosis is critical for patient outcomes.
• Internet of Medical Things (IoMT) and Deep Learning (DL) are increasingly vital in medical data processing.
• Existing models require improved precision for lung tumor segmentation and classification.

Purpose of the Study:

• To develop an Integrated Model for Lung Tumor Segmentation (IM-LTS) utilizing IoMT and Neural Networks (NN).
• To enhance the precision of early lung cancer diagnosis through advanced segmentation and classification techniques.
• To integrate MobileNetV2 and U-NET architectures for classifying lung CT images.

Main Methods:

• Pre-processing of CT lung images using Z-score Normalization.
• Extraction of semantic features (texture, intensity, shape) for network training.
• Implementation of transfer learning with a pre-trained NN as a U-NET encoder.
• Classification of lung data as benign or malignant using Support Vector Machine (SVM).

Main Results:

• The proposed IM-LTS model demonstrated superior performance in lung tumor segmentation and classification.
• Evaluation metrics included specificity, sensitivity, precision, accuracy, and F-Score on benchmark datasets.
• The model achieved better results compared to existing lung tumor segmentation and classification methods.

Conclusions:

• The developed IM-LTS model offers improved accuracy for early lung tumor detection.
• Integration of IoMT and DL techniques provides a robust framework for medical decision-making.
• This approach supports earlier and more precise diagnosis of lung cancer.