Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis

Aim: Lung cancer is a leading cause of cancer-related deaths globally, where early and accurate diagnosis significantly improves survival rates. This study proposes an AI-based diagnostic framework integrating U-Net for lung nodule segmentation and a custom convolutional neural network (CNN) for bin...

Full description

Saved in:
Bibliographic Details
Main Authors: Ashwin Kumar Azhagarasan, Prashanthi Bhaskaran, Arunkumar Ramachandran, Kalpana Sivalingam
Format: Article
Language:English
Published: Open Exploration Publishing Inc. 2025-07-01
Series:Exploration of Medicine
Subjects:
Online Access:https://www.explorationpub.com/uploads/Article/A1001341/1001341.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087366765576192
author Ashwin Kumar Azhagarasan
Prashanthi Bhaskaran
Arunkumar Ramachandran
Kalpana Sivalingam
author_facet Ashwin Kumar Azhagarasan
Prashanthi Bhaskaran
Arunkumar Ramachandran
Kalpana Sivalingam
author_sort Ashwin Kumar Azhagarasan
collection DOAJ
description Aim: Lung cancer is a leading cause of cancer-related deaths globally, where early and accurate diagnosis significantly improves survival rates. This study proposes an AI-based diagnostic framework integrating U-Net for lung nodule segmentation and a custom convolutional neural network (CNN) for binary classification of nodules as benign or malignant. Methods: The model was developed using the Barnard Institute of Radiology (BIR) Lung CT dataset. U-Net was used for segmentation, and a custom CNN, compared with EfficientNet B0, VGG-16, and Inception v3, was implemented for classification. Due to limited subtype labels and diagnostically ambiguous “suspicious” cases, classification was restricted to a binary task. These uncertain cases were reserved for validation. Overfitting was addressed through stratified 5-fold cross-validation, dropout, early stopping, L2 regularization, and data augmentation. Results: EfficientNet B0 achieved ~99.3% training and ~97% validation accuracy. Cross-validation yielded consistent metrics (accuracy: 0.983 ± 0.014; F1-score: 0.983 ± 0.006; AUC = 0.990), confirming robustness. External validation on the LIDC-IDRI dataset demonstrated generalizability across diverse populations. Conclusions: The proposed AI model shows strong potential for clinical deployment in lung cancer diagnosis. Future work will address demographic bias, expand multi-center data inclusion, and explore regulatory pathways for real-world integration.
format Article
id doaj-art-fd122e88c3c84e9e9ff8a1373561110a
institution DOAJ
issn 2692-3106
language English
publishDate 2025-07-01
publisher Open Exploration Publishing Inc.
record_format Article
series Exploration of Medicine
spelling doaj-art-fd122e88c3c84e9e9ff8a1373561110a2025-08-20T02:43:13ZengOpen Exploration Publishing Inc.Exploration of Medicine2692-31062025-07-016100134110.37349/emed.2025.1001341Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosisAshwin Kumar Azhagarasan0https://orcid.org/0000-0001-5640-2656Prashanthi Bhaskaran1https://orcid.org/0009-0006-5827-1649Arunkumar Ramachandran2https://orcid.org/0000-0002-6665-5312Kalpana Sivalingam3https://orcid.org/0000-0003-3825-3145Current address: Radiodiagnosis, Sree Balaji Medical College and Hospital, Chennai 600003, Tamil Nadu, India; Radiodiagnosis, Bernad Institute of Radiodiagnosis, Madras Medical College, Chennai 600003, Tamil Nadu, IndiaDepartment of Computer Science, St. Peter’s Institute of Higher Education and Research (Deemed to be University), Chennai 600054, Tamil Nadu, IndiaMultidisciplinary Research Unit (MRU), Department of Health Research, Madras Medical College, Chennai 600003, Tamil Nadu, IndiaBarnard Institute of Radiology, Madras Medical College, Chennai 600003, Tamil Nadu, IndiaAim: Lung cancer is a leading cause of cancer-related deaths globally, where early and accurate diagnosis significantly improves survival rates. This study proposes an AI-based diagnostic framework integrating U-Net for lung nodule segmentation and a custom convolutional neural network (CNN) for binary classification of nodules as benign or malignant. Methods: The model was developed using the Barnard Institute of Radiology (BIR) Lung CT dataset. U-Net was used for segmentation, and a custom CNN, compared with EfficientNet B0, VGG-16, and Inception v3, was implemented for classification. Due to limited subtype labels and diagnostically ambiguous “suspicious” cases, classification was restricted to a binary task. These uncertain cases were reserved for validation. Overfitting was addressed through stratified 5-fold cross-validation, dropout, early stopping, L2 regularization, and data augmentation. Results: EfficientNet B0 achieved ~99.3% training and ~97% validation accuracy. Cross-validation yielded consistent metrics (accuracy: 0.983 ± 0.014; F1-score: 0.983 ± 0.006; AUC = 0.990), confirming robustness. External validation on the LIDC-IDRI dataset demonstrated generalizability across diverse populations. Conclusions: The proposed AI model shows strong potential for clinical deployment in lung cancer diagnosis. Future work will address demographic bias, expand multi-center data inclusion, and explore regulatory pathways for real-world integration.https://www.explorationpub.com/uploads/Article/A1001341/1001341.pdfai in healthcarenodule segmentationdiagnostic precisionlung cancer classificationconvolutional neural network
spellingShingle Ashwin Kumar Azhagarasan
Prashanthi Bhaskaran
Arunkumar Ramachandran
Kalpana Sivalingam
Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
Exploration of Medicine
ai in healthcare
nodule segmentation
diagnostic precision
lung cancer classification
convolutional neural network
title Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
title_full Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
title_fullStr Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
title_full_unstemmed Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
title_short Artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network—from imaging to diagnosis
title_sort artificial intelligence framework for lung cancer nodule segmentation and classification using convolutional neural network from imaging to diagnosis
topic ai in healthcare
nodule segmentation
diagnostic precision
lung cancer classification
convolutional neural network
url https://www.explorationpub.com/uploads/Article/A1001341/1001341.pdf
work_keys_str_mv AT ashwinkumarazhagarasan artificialintelligenceframeworkforlungcancernodulesegmentationandclassificationusingconvolutionalneuralnetworkfromimagingtodiagnosis
AT prashanthibhaskaran artificialintelligenceframeworkforlungcancernodulesegmentationandclassificationusingconvolutionalneuralnetworkfromimagingtodiagnosis
AT arunkumarramachandran artificialintelligenceframeworkforlungcancernodulesegmentationandclassificationusingconvolutionalneuralnetworkfromimagingtodiagnosis
AT kalpanasivalingam artificialintelligenceframeworkforlungcancernodulesegmentationandclassificationusingconvolutionalneuralnetworkfromimagingtodiagnosis