Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis
Artificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automat...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/6/690 |
| _version_ | 1797596015847538688 |
|---|---|
| author | Bryce Dunn Mariaelena Pierobon Qi Wei |
| author_facet | Bryce Dunn Mariaelena Pierobon Qi Wei |
| author_sort | Bryce Dunn |
| collection | DOAJ |
| description | Artificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automated diagnostic tools is a key goal of radiomics, a fast-growing research field which combines medical imaging with personalized medicine. Radiomic studies have demonstrated potential for accurate lung cancer diagnoses and prognostications. The practice of delineating the tumor region of interest, known as segmentation, is a key bottleneck in the development of generalized classification models. In this study, the incremental multiple resolution residual network (iMRRN), a publicly available and trained deep learning segmentation model, was applied to automatically segment CT images collected from 355 lung cancer patients included in the dataset “Lung-PET-CT-Dx”, obtained from The Cancer Imaging Archive (TCIA), an open-access source for radiological images. We report a failure rate of 4.35% when using the iMRRN to segment tumor lesions within plain CT images in the lung cancer CT dataset. Seven classification algorithms were trained on the extracted radiomic features and tested for their ability to classify different lung cancer subtypes. Over-sampling was used to handle unbalanced data. Chi-square tests revealed the higher order texture features to be the most predictive when classifying lung cancers by subtype. The support vector machine showed the highest accuracy, 92.7% (0.97 AUC), when classifying three histological subtypes of lung cancer: adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. The results demonstrate the potential of AI-based computer-aided diagnostic tools to automatically diagnose subtypes of lung cancer by coupling deep learning image segmentation with supervised classification. Our study demonstrated the integrated application of existing AI techniques in the non-invasive and effective diagnosis of lung cancer subtypes, and also shed light on several practical issues concerning the application of AI in biomedicine. |
| first_indexed | 2024-03-11T02:45:34Z |
| format | Article |
| id | doaj.art-3de7698cbf8b4e9db20f0c60fe430c40 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-11T02:45:34Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-3de7698cbf8b4e9db20f0c60fe430c402023-11-18T09:21:25ZengMDPI AGBioengineering2306-53542023-06-0110669010.3390/bioengineering10060690Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic AnalysisBryce Dunn0Mariaelena Pierobon1Qi Wei2Department of Bioengineering, George Mason University, Fairfax, VA 22030, USASchool of Systems Biology, Center for Applied Proteomics and Molecular Medicine, George Mason University, Fairfax, VA 22030, USADepartment of Bioengineering, George Mason University, Fairfax, VA 22030, USAArtificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automated diagnostic tools is a key goal of radiomics, a fast-growing research field which combines medical imaging with personalized medicine. Radiomic studies have demonstrated potential for accurate lung cancer diagnoses and prognostications. The practice of delineating the tumor region of interest, known as segmentation, is a key bottleneck in the development of generalized classification models. In this study, the incremental multiple resolution residual network (iMRRN), a publicly available and trained deep learning segmentation model, was applied to automatically segment CT images collected from 355 lung cancer patients included in the dataset “Lung-PET-CT-Dx”, obtained from The Cancer Imaging Archive (TCIA), an open-access source for radiological images. We report a failure rate of 4.35% when using the iMRRN to segment tumor lesions within plain CT images in the lung cancer CT dataset. Seven classification algorithms were trained on the extracted radiomic features and tested for their ability to classify different lung cancer subtypes. Over-sampling was used to handle unbalanced data. Chi-square tests revealed the higher order texture features to be the most predictive when classifying lung cancers by subtype. The support vector machine showed the highest accuracy, 92.7% (0.97 AUC), when classifying three histological subtypes of lung cancer: adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. The results demonstrate the potential of AI-based computer-aided diagnostic tools to automatically diagnose subtypes of lung cancer by coupling deep learning image segmentation with supervised classification. Our study demonstrated the integrated application of existing AI techniques in the non-invasive and effective diagnosis of lung cancer subtypes, and also shed light on several practical issues concerning the application of AI in biomedicine.https://www.mdpi.com/2306-5354/10/6/690deep learningradiomicsCT tumor segmentationlung cancerclassification |
| spellingShingle | Bryce Dunn Mariaelena Pierobon Qi Wei Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis Bioengineering deep learning radiomics CT tumor segmentation lung cancer classification |
| title | Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis |
| title_full | Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis |
| title_fullStr | Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis |
| title_full_unstemmed | Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis |
| title_short | Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis |
| title_sort | automated classification of lung cancer subtypes using deep learning and ct scan based radiomic analysis |
| topic | deep learning radiomics CT tumor segmentation lung cancer classification |
| url | https://www.mdpi.com/2306-5354/10/6/690 |
| work_keys_str_mv | AT brycedunn automatedclassificationoflungcancersubtypesusingdeeplearningandctscanbasedradiomicanalysis AT mariaelenapierobon automatedclassificationoflungcancersubtypesusingdeeplearningandctscanbasedradiomicanalysis AT qiwei automatedclassificationoflungcancersubtypesusingdeeplearningandctscanbasedradiomicanalysis |