Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks

Adolfo Jara Gavilanes; Remigio Hurtado Ortiz; Stefania Guzman Ortiz

doi:10.1109/CLEI60451.2023.10346202

Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks

Adolfo Jara Gavilanes
, Remigio Hurtado Ortiz
, Stefania Guzman Ortiz

Research Group on Artificial Intelligence and Assistive Technologies (GI-IATA)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

Lung cancer ranks third in cancer detection, following breast and prostate cancer, but it causes more deaths compared to other cancer types. It is divided into Non-Small Cell Lung Cancer (NSCLC), comprising three sub-types, and Small Cell Lung Cancer (SCLC). Distinguishing between these two types is challenging for doctors, necessitating the development of new technological tools. This work introduces a two-phase method with a total of eight steps to identify the sub-types of NSCLS (adenocarcinoma and squamous cell carcinoma) and SCLC. The process involves gathering and loading data, selecting PET scans, transforming them into RGB images, creating patient videos, and applying data augmentation before splitting the data into training and testing sets. Three models are built using Convolutional Neural Networks with hyperparameter tuning, VGG16, and ResNet50, each assembled with a Gated Recurrent Unit (GRU). The models are trained and tested, and the results are presented. The method utilizes a public dataset from The Cancer Imaging Archive, specifically the Lung-PET-CT-Dx dataset. Moreover, this approach can potentially be extended to detect and predict other types of cancers and diseases based on PET scans.

Original language	English
Title of host publication	Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350318876
DOIs	https://doi.org/10.1109/CLEI60451.2023.10346202
State	Published - 2023
Event	49th Latin American Computing Conference, CLEI 2023 - La Paz, Bolivia, Plurinational State of Duration: 16 Oct 2023 → 20 Oct 2023

Publication series

Name	Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023

Conference

Conference	49th Latin American Computing Conference, CLEI 2023
Country/Territory	Bolivia, Plurinational State of
City	La Paz
Period	16/10/23 → 20/10/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Convolutional Neural Networks
Data Science
Deep Learning
Image Preprocessing
Lung Cancer
Positron Emission Tomography
Recurrent Neural Networks
Transfer Learning

CACES Knowledge Areas

245A Statistics
116A Computer Science

Access to Document

10.1109/CLEI60451.2023.10346202

Cite this

Jara Gavilanes, A., Hurtado Ortiz, R., & Guzman Ortiz, S. (2023). Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks. In Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023 (Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CLEI60451.2023.10346202

Jara Gavilanes, Adolfo ; Hurtado Ortiz, Remigio ; Guzman Ortiz, Stefania. / Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks. Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023).

@inproceedings{f5e780e2ad874213a65474b73ab3a117,

title = "Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks",

abstract = "Lung cancer ranks third in cancer detection, following breast and prostate cancer, but it causes more deaths compared to other cancer types. It is divided into Non-Small Cell Lung Cancer (NSCLC), comprising three sub-types, and Small Cell Lung Cancer (SCLC). Distinguishing between these two types is challenging for doctors, necessitating the development of new technological tools. This work introduces a two-phase method with a total of eight steps to identify the sub-types of NSCLS (adenocarcinoma and squamous cell carcinoma) and SCLC. The process involves gathering and loading data, selecting PET scans, transforming them into RGB images, creating patient videos, and applying data augmentation before splitting the data into training and testing sets. Three models are built using Convolutional Neural Networks with hyperparameter tuning, VGG16, and ResNet50, each assembled with a Gated Recurrent Unit (GRU). The models are trained and tested, and the results are presented. The method utilizes a public dataset from The Cancer Imaging Archive, specifically the Lung-PET-CT-Dx dataset. Moreover, this approach can potentially be extended to detect and predict other types of cancers and diseases based on PET scans.",

keywords = "Convolutional Neural Networks, Data Science, Deep Learning, Image Preprocessing, Lung Cancer, Positron Emission Tomography, Recurrent Neural Networks, Transfer Learning",

author = "\{Jara Gavilanes\}, Adolfo and \{Hurtado Ortiz\}, Remigio and \{Guzman Ortiz\}, Stefania",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 49th Latin American Computing Conference, CLEI 2023 ; Conference date: 16-10-2023 Through 20-10-2023",

year = "2023",

doi = "10.1109/CLEI60451.2023.10346202",

language = "English",

series = "Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023",

address = "United States",

}

Jara Gavilanes, A, Hurtado Ortiz, R & Guzman Ortiz, S 2023, Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks. in Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023. Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023, Institute of Electrical and Electronics Engineers Inc., 49th Latin American Computing Conference, CLEI 2023, La Paz, Bolivia, Plurinational State of, 16/10/23. https://doi.org/10.1109/CLEI60451.2023.10346202

Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks. / Jara Gavilanes, Adolfo; Hurtado Ortiz, Remigio; Guzman Ortiz, Stefania.
Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks

AU - Jara Gavilanes, Adolfo

AU - Hurtado Ortiz, Remigio

AU - Guzman Ortiz, Stefania

PY - 2023

Y1 - 2023

N2 - Lung cancer ranks third in cancer detection, following breast and prostate cancer, but it causes more deaths compared to other cancer types. It is divided into Non-Small Cell Lung Cancer (NSCLC), comprising three sub-types, and Small Cell Lung Cancer (SCLC). Distinguishing between these two types is challenging for doctors, necessitating the development of new technological tools. This work introduces a two-phase method with a total of eight steps to identify the sub-types of NSCLS (adenocarcinoma and squamous cell carcinoma) and SCLC. The process involves gathering and loading data, selecting PET scans, transforming them into RGB images, creating patient videos, and applying data augmentation before splitting the data into training and testing sets. Three models are built using Convolutional Neural Networks with hyperparameter tuning, VGG16, and ResNet50, each assembled with a Gated Recurrent Unit (GRU). The models are trained and tested, and the results are presented. The method utilizes a public dataset from The Cancer Imaging Archive, specifically the Lung-PET-CT-Dx dataset. Moreover, this approach can potentially be extended to detect and predict other types of cancers and diseases based on PET scans.

AB - Lung cancer ranks third in cancer detection, following breast and prostate cancer, but it causes more deaths compared to other cancer types. It is divided into Non-Small Cell Lung Cancer (NSCLC), comprising three sub-types, and Small Cell Lung Cancer (SCLC). Distinguishing between these two types is challenging for doctors, necessitating the development of new technological tools. This work introduces a two-phase method with a total of eight steps to identify the sub-types of NSCLS (adenocarcinoma and squamous cell carcinoma) and SCLC. The process involves gathering and loading data, selecting PET scans, transforming them into RGB images, creating patient videos, and applying data augmentation before splitting the data into training and testing sets. Three models are built using Convolutional Neural Networks with hyperparameter tuning, VGG16, and ResNet50, each assembled with a Gated Recurrent Unit (GRU). The models are trained and tested, and the results are presented. The method utilizes a public dataset from The Cancer Imaging Archive, specifically the Lung-PET-CT-Dx dataset. Moreover, this approach can potentially be extended to detect and predict other types of cancers and diseases based on PET scans.

KW - Convolutional Neural Networks

KW - Data Science

KW - Deep Learning

KW - Image Preprocessing

KW - Lung Cancer

KW - Positron Emission Tomography

KW - Recurrent Neural Networks

KW - Transfer Learning

UR - https://www.scopus.com/pages/publications/85182280944

U2 - 10.1109/CLEI60451.2023.10346202

DO - 10.1109/CLEI60451.2023.10346202

M3 - Conference contribution

AN - SCOPUS:85182280944

T3 - Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023

BT - Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 49th Latin American Computing Conference, CLEI 2023

Y2 - 16 October 2023 through 20 October 2023

ER -

Jara Gavilanes A, Hurtado Ortiz R, Guzman Ortiz S. Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks. In Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (Proceedings - 2023 49th Latin American Computing Conference, CLEI 2023). doi: 10.1109/CLEI60451.2023.10346202

Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

CACES Knowledge Areas

Access to Document

Other files and links

Fingerprint

Development of Models and Software with Artificial Intelligence and Machine Learning for Decision Support in Cancer Diagnosis and Treatment

Cite this

Lung Cancer Detection Using Positron Emission Tomography Images Through Convolutional and Recurrent Neural Networks

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

CACES Knowledge Areas

Access to Document

Other files and links

Fingerprint

Projects

Development of Models and Software with Artificial Intelligence and Machine Learning for Decision Support in Cancer Diagnosis and Treatment

Cite this