Scholarlink

This paper presents a thorough scheme that combines a ConvNetCNN (ConvNet) and Long Short-Term Memory (LSTMLong Short-Term Memory (LSTM)) model to predict lung cancerCancer using CT scansCT scans. This integrated model accepts preprocessed CT scanCT scans images and classifies them into three groups: benign, malignant, and normal cases. This work aims to contribute improved lung cancerCancer diagnosis and patient care by enabling early identification of malignant cases and improving the model’s capacity to evaluate both temporal and spatial data for precise predictionsPrediction. The CNNCNN (ConvNet) extracts spatial features, capturing local patterns and visual cues related to lung cancerCancer, whereas the LSTMLong Short-Term Memory (LSTM) captures temporal dependencies, enabling the method to study from sequential CT scanCT scans data. The proposed work aims to develop a robust predictionPrediction model, optimize its performance through suitable preprocessingPreprocessing techniques and architecture fine-tuning, and compare the effectiveness with existing approaches.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Lung Cancer Prediction Using Integrated Deep Learning Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • M. V. Sudhamani,
  • Anil Kumar

摘要

This paper presents a thorough scheme that combines a ConvNetCNN (ConvNet) and Long Short-Term Memory (LSTMLong Short-Term Memory (LSTM)) model to predict lung cancerCancer using CT scansCT scans. This integrated model accepts preprocessed CT scanCT scans images and classifies them into three groups: benign, malignant, and normal cases. This work aims to contribute improved lung cancerCancer diagnosis and patient care by enabling early identification of malignant cases and improving the model’s capacity to evaluate both temporal and spatial data for precise predictionsPrediction. The CNNCNN (ConvNet) extracts spatial features, capturing local patterns and visual cues related to lung cancerCancer, whereas the LSTMLong Short-Term Memory (LSTM) captures temporal dependencies, enabling the method to study from sequential CT scanCT scans data. The proposed work aims to develop a robust predictionPrediction model, optimize its performance through suitable preprocessingPreprocessing techniques and architecture fine-tuning, and compare the effectiveness with existing approaches.