A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models

Background: Lung cancer remains a significant health concern, and the effectiveness of early detection significantly enhances patient survival rates. Identifying lung tumors with high precision is a challenge due to the complex nature of tumor structures and the surrounding lung tissues. Methods: To...

Full description

Saved in:
Bibliographic Details
Main Authors: Hamidreza Najafi, Kimia Savoji, Marzieh Mirzaeibonehkhater, Seyed Vahid Moravvej, Roohallah Alizadehsani, Siamak Pedrammehr
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/22/2604
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153814085730304
author Hamidreza Najafi
Kimia Savoji
Marzieh Mirzaeibonehkhater
Seyed Vahid Moravvej
Roohallah Alizadehsani
Siamak Pedrammehr
author_facet Hamidreza Najafi
Kimia Savoji
Marzieh Mirzaeibonehkhater
Seyed Vahid Moravvej
Roohallah Alizadehsani
Siamak Pedrammehr
author_sort Hamidreza Najafi
collection DOAJ
description Background: Lung cancer remains a significant health concern, and the effectiveness of early detection significantly enhances patient survival rates. Identifying lung tumors with high precision is a challenge due to the complex nature of tumor structures and the surrounding lung tissues. Methods: To address these hurdles, this paper presents an innovative three-step approach that leverages Generative Adversarial Networks (GAN), Long Short-Term Memory (LSTM), and VGG16 algorithms for the accurate reconstruction of three-dimensional (3D) lung tumor images. The first challenge we address is the accurate segmentation of lung tissues from CT images, a task complicated by the overwhelming presence of non-lung pixels, which can lead to classifier imbalance. Our solution employs a GAN model trained with a reinforcement learning (RL)-based algorithm to mitigate this imbalance and enhance segmentation accuracy. The second challenge involves precisely detecting tumors within the segmented lung regions. We introduce a second GAN model with a novel loss function that significantly improves tumor detection accuracy. Following successful segmentation and tumor detection, the VGG16 algorithm is utilized for feature extraction, preparing the data for the final 3D reconstruction. These features are then processed through an LSTM network and converted into a format suitable for the reconstructive GAN. This GAN, equipped with dilated convolution layers in its discriminator, captures extensive contextual information, enabling the accurate reconstruction of the tumor’s 3D structure. Results: The effectiveness of our method is demonstrated through rigorous evaluation against established techniques using the LIDC-IDRI dataset and standard performance metrics, showcasing its superior performance and potential for enhancing early lung cancer detection. Conclusions:This study highlights the benefits of combining GANs, LSTM, and VGG16 into a unified framework. This approach significantly improves the accuracy of detecting and reconstructing lung tumors, promising to enhance diagnostic methods and patient results in lung cancer treatment.
format Article
id doaj-art-e579bc8efb9f49cc8c10f96173c20f18
institution Kabale University
issn 2075-4418
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-e579bc8efb9f49cc8c10f96173c20f182024-11-26T18:00:05ZengMDPI AGDiagnostics2075-44182024-11-011422260410.3390/diagnostics14222604A Novel Method for 3D Lung Tumor Reconstruction Using Generative ModelsHamidreza Najafi0Kimia Savoji1Marzieh Mirzaeibonehkhater2Seyed Vahid Moravvej3Roohallah Alizadehsani4Siamak Pedrammehr5Biomedical Engineering Department, School of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13114, IranBiomedical Data Science and Informatics, School of Computing, Clemson University, Clemson, SC 29634, USADepartment of Electrical and Computer Engineering, Indiana University-Purdue University, Indianapolis, IN 46202, USADepartment of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan 84156-83111, IranInstitute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, VIC 3216, AustraliaFaculty of Design, Tabriz Islamic Art University, Tabriz 51647-36931, IranBackground: Lung cancer remains a significant health concern, and the effectiveness of early detection significantly enhances patient survival rates. Identifying lung tumors with high precision is a challenge due to the complex nature of tumor structures and the surrounding lung tissues. Methods: To address these hurdles, this paper presents an innovative three-step approach that leverages Generative Adversarial Networks (GAN), Long Short-Term Memory (LSTM), and VGG16 algorithms for the accurate reconstruction of three-dimensional (3D) lung tumor images. The first challenge we address is the accurate segmentation of lung tissues from CT images, a task complicated by the overwhelming presence of non-lung pixels, which can lead to classifier imbalance. Our solution employs a GAN model trained with a reinforcement learning (RL)-based algorithm to mitigate this imbalance and enhance segmentation accuracy. The second challenge involves precisely detecting tumors within the segmented lung regions. We introduce a second GAN model with a novel loss function that significantly improves tumor detection accuracy. Following successful segmentation and tumor detection, the VGG16 algorithm is utilized for feature extraction, preparing the data for the final 3D reconstruction. These features are then processed through an LSTM network and converted into a format suitable for the reconstructive GAN. This GAN, equipped with dilated convolution layers in its discriminator, captures extensive contextual information, enabling the accurate reconstruction of the tumor’s 3D structure. Results: The effectiveness of our method is demonstrated through rigorous evaluation against established techniques using the LIDC-IDRI dataset and standard performance metrics, showcasing its superior performance and potential for enhancing early lung cancer detection. Conclusions:This study highlights the benefits of combining GANs, LSTM, and VGG16 into a unified framework. This approach significantly improves the accuracy of detecting and reconstructing lung tumors, promising to enhance diagnostic methods and patient results in lung cancer treatment.https://www.mdpi.com/2075-4418/14/22/2604lung cancerlung segmentationtumor detection3D tumor reconstructiongenerative adversarial networkimbalanced data
spellingShingle Hamidreza Najafi
Kimia Savoji
Marzieh Mirzaeibonehkhater
Seyed Vahid Moravvej
Roohallah Alizadehsani
Siamak Pedrammehr
A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
Diagnostics
lung cancer
lung segmentation
tumor detection
3D tumor reconstruction
generative adversarial network
imbalanced data
title A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
title_full A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
title_fullStr A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
title_full_unstemmed A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
title_short A Novel Method for 3D Lung Tumor Reconstruction Using Generative Models
title_sort novel method for 3d lung tumor reconstruction using generative models
topic lung cancer
lung segmentation
tumor detection
3D tumor reconstruction
generative adversarial network
imbalanced data
url https://www.mdpi.com/2075-4418/14/22/2604
work_keys_str_mv AT hamidrezanajafi anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT kimiasavoji anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT marziehmirzaeibonehkhater anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT seyedvahidmoravvej anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT roohallahalizadehsani anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT siamakpedrammehr anovelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT hamidrezanajafi novelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT kimiasavoji novelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT marziehmirzaeibonehkhater novelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT seyedvahidmoravvej novelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT roohallahalizadehsani novelmethodfor3dlungtumorreconstructionusinggenerativemodels
AT siamakpedrammehr novelmethodfor3dlungtumorreconstructionusinggenerativemodels