Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images
Early detection increases overall survival among patients with lung cancer. This study formulated a machine learning method that processes chest X-rays (CXRs) to detect lung cancer early. After we preprocessed our dataset using monochrome and brightness correction, we used different kinds of preproc...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Biomedicines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9059/10/11/2839 |
| _version_ | 1797468976577511424 |
|---|---|
| author | Hwa-Yen Chiu Rita Huan-Ting Peng Yi-Chian Lin Ting-Wei Wang Ya-Xuan Yang Ying-Ying Chen Mei-Han Wu Tsu-Hui Shiao Heng-Sheng Chao Yuh-Min Chen Yu-Te Wu |
| author_facet | Hwa-Yen Chiu Rita Huan-Ting Peng Yi-Chian Lin Ting-Wei Wang Ya-Xuan Yang Ying-Ying Chen Mei-Han Wu Tsu-Hui Shiao Heng-Sheng Chao Yuh-Min Chen Yu-Te Wu |
| author_sort | Hwa-Yen Chiu |
| collection | DOAJ |
| description | Early detection increases overall survival among patients with lung cancer. This study formulated a machine learning method that processes chest X-rays (CXRs) to detect lung cancer early. After we preprocessed our dataset using monochrome and brightness correction, we used different kinds of preprocessing methods to enhance image contrast and then used U-net to perform lung segmentation. We used 559 CXRs with a single lung nodule labeled by experts to train a You Only Look Once version 4 (YOLOv4) deep-learning architecture to detect lung nodules. In a testing dataset of 100 CXRs from patients at Taipei Veterans General Hospital and 154 CXRs from the Japanese Society of Radiological Technology dataset, the sensitivity of the AI model using a combination of different preprocessing methods performed the best at 79%, with 3.04 false positives per image. We then tested the AI by using 383 sets of CXRs obtained in the past 5 years prior to lung cancer diagnoses. The median time from detection to diagnosis for radiologists assisted with AI was 46 (3–523) days, longer than that for radiologists (8 (0–263) days). The AI model can assist radiologists in the early detection of lung nodules. |
| first_indexed | 2024-03-09T19:14:57Z |
| format | Article |
| id | doaj.art-2ff2ebf46fff41e0adaf65cd06799aa4 |
| institution | Directory Open Access Journal |
| issn | 2227-9059 |
| language | English |
| last_indexed | 2024-03-09T19:14:57Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomedicines |
| spelling | doaj.art-2ff2ebf46fff41e0adaf65cd06799aa42023-11-24T03:51:35ZengMDPI AGBiomedicines2227-90592022-11-011011283910.3390/biomedicines10112839Artificial Intelligence for Early Detection of Chest Nodules in X-ray ImagesHwa-Yen Chiu0Rita Huan-Ting Peng1Yi-Chian Lin2Ting-Wei Wang3Ya-Xuan Yang4Ying-Ying Chen5Mei-Han Wu6Tsu-Hui Shiao7Heng-Sheng Chao8Yuh-Min Chen9Yu-Te Wu10Department of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, TaiwanInstitute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, TaiwanInstitute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, TaiwanInstitute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, TaiwanInstitute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, TaiwanDepartment of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, TaiwanSchool of Medicine, National Yang Ming Chiao Tung University, Taipei 112, TaiwanDepartment of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, TaiwanDepartment of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, TaiwanDepartment of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, TaiwanInstitute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, TaiwanEarly detection increases overall survival among patients with lung cancer. This study formulated a machine learning method that processes chest X-rays (CXRs) to detect lung cancer early. After we preprocessed our dataset using monochrome and brightness correction, we used different kinds of preprocessing methods to enhance image contrast and then used U-net to perform lung segmentation. We used 559 CXRs with a single lung nodule labeled by experts to train a You Only Look Once version 4 (YOLOv4) deep-learning architecture to detect lung nodules. In a testing dataset of 100 CXRs from patients at Taipei Veterans General Hospital and 154 CXRs from the Japanese Society of Radiological Technology dataset, the sensitivity of the AI model using a combination of different preprocessing methods performed the best at 79%, with 3.04 false positives per image. We then tested the AI by using 383 sets of CXRs obtained in the past 5 years prior to lung cancer diagnoses. The median time from detection to diagnosis for radiologists assisted with AI was 46 (3–523) days, longer than that for radiologists (8 (0–263) days). The AI model can assist radiologists in the early detection of lung nodules.https://www.mdpi.com/2227-9059/10/11/2839artificial intelligenceAIdetectionlung cancermachine learning |
| spellingShingle | Hwa-Yen Chiu Rita Huan-Ting Peng Yi-Chian Lin Ting-Wei Wang Ya-Xuan Yang Ying-Ying Chen Mei-Han Wu Tsu-Hui Shiao Heng-Sheng Chao Yuh-Min Chen Yu-Te Wu Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images Biomedicines artificial intelligence AI detection lung cancer machine learning |
| title | Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images |
| title_full | Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images |
| title_fullStr | Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images |
| title_full_unstemmed | Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images |
| title_short | Artificial Intelligence for Early Detection of Chest Nodules in X-ray Images |
| title_sort | artificial intelligence for early detection of chest nodules in x ray images |
| topic | artificial intelligence AI detection lung cancer machine learning |
| url | https://www.mdpi.com/2227-9059/10/11/2839 |
| work_keys_str_mv | AT hwayenchiu artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT ritahuantingpeng artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT yichianlin artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT tingweiwang artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT yaxuanyang artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT yingyingchen artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT meihanwu artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT tsuhuishiao artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT hengshengchao artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT yuhminchen artificialintelligenceforearlydetectionofchestnodulesinxrayimages AT yutewu artificialintelligenceforearlydetectionofchestnodulesinxrayimages |