Transfer Learning in Lung Cancer Detection: Leveraging Pre-Trained Models for Improved Performance

EasyChair Preprint 12792

Abstract

Transfer learning techniques have gained prominence in the field of lung cancer detection as a means to enhance the performance of models, particularly in scenarios where labeled data is limited. This topic delves into the application of transfer learning in the context of lung cancer detection, with a focus on leveraging pre-trained models or knowledge from related domains to improve the accuracy and efficacy of detection models.Transfer learning involves utilizing knowledge gained from pre-existing models that have been trained on large-scale datasets in related fields. By leveraging the learned representations and features from these pre-trained models, the performance of lung cancer detection models can be enhanced, even when the availability of labeled data is restricted. This approach is particularly valuable in the medical domain, where obtaining labeled medical imaging data for training purposes can be challenging and resource-intensive.The application of transfer learning in lung cancer detection involves fine-tuning pre-trained models, such as convolutional neural networks (CNN), that were initially trained on general image recognition tasks. By adapting these pre-trained models to the specific characteristics of lung cancer detection, the models can effectively learn discriminative features related to lung abnormalities and improve their diagnostic accuracy.

Keyphrases: Cancer extraction, Lung Cancer Detection, Lung Cancer Treatment

@booklet{EasyChair:12792,
  author    = {Emmanuel Idowu and Lucas Doris},
  title     = {Transfer Learning in Lung Cancer Detection: Leveraging Pre-Trained Models for Improved Performance},
  howpublished = {EasyChair Preprint 12792},
  year      = {EasyChair, 2024}}