Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images
Chest radiography is an indispensable diagnostic method for detecting a variety of medical conditions, such as infections, tumors, injuries, etc. Millions of chest X-ray examinations are conducted annually, providing crucial information about the functioning of the respiratory and circulatory system...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818426/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592936804548608 |
|---|---|
| author | Alexey Kornaev Dmitry Lvov Ilya Pershin Semen Kiselev Danil Afonchikov Iskander Bariev Bulat Ibragimov |
| author_facet | Alexey Kornaev Dmitry Lvov Ilya Pershin Semen Kiselev Danil Afonchikov Iskander Bariev Bulat Ibragimov |
| author_sort | Alexey Kornaev |
| collection | DOAJ |
| description | Chest radiography is an indispensable diagnostic method for detecting a variety of medical conditions, such as infections, tumors, injuries, etc. Millions of chest X-ray examinations are conducted annually, providing crucial information about the functioning of the respiratory and circulatory systems. The conventional approach to quantifying cardiothoracic indices, such as the Lupi and Moore indices and the Cardiothoracic Index (CTI), requires considerable time and effort from radiologists. Consequently, it calls for the exploration of computational methods for improvement through deep learning. In this study, we addressed the challenge of automating the calculation of these cardiometric indices. We engaged four experienced radiologists to manually label 800 chest X-ray images each. Using these labeled images, we trained a deep learning model that achieved the level of performance comparable to that of a professional radiologist. Additionally, we have replaced the central points of the indices with landmarks based on the vertebrae, improving the accuracy. The use of AI led to improved accuracy of correct predictions, increasing it from 85.94% to 87.34% for the MOORE coefficient and from 87.55% to 90.67% for the LUPI coefficient. |
| format | Article |
| id | doaj-art-8604c90742be48be8c17e7b3791aa30c |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8604c90742be48be8c17e7b3791aa30c2025-01-21T00:01:18ZengIEEEIEEE Access2169-35362025-01-0113107021071210.1109/ACCESS.2024.352411610818426Automatic Calculation of Cardiometric Coefficients on Chest X-Ray ImagesAlexey Kornaev0Dmitry Lvov1https://orcid.org/0009-0008-3211-5853Ilya Pershin2https://orcid.org/0000-0001-7052-2355Semen Kiselev3https://orcid.org/0009-0000-9153-1429Danil Afonchikov4https://orcid.org/0009-0003-0089-6273Iskander Bariev5https://orcid.org/0000-0001-5121-6045Bulat Ibragimov6https://orcid.org/0000-0001-7739-7788Research Center for Artificial Intelligence in Healthcare, National Medical Research Center of Oncology named after N.N. Blokhin, Moscow, RussiaResearch Center for Artificial Intelligence, Innopolis University, Innopolis, RussiaResearch Center for Artificial Intelligence, Innopolis University, Innopolis, RussiaResearch Center for Artificial Intelligence, Innopolis University, Innopolis, RussiaResearch Center for Artificial Intelligence, Innopolis University, Innopolis, RussiaResearch Center for Artificial Intelligence, Innopolis University, Innopolis, RussiaDepartment of Computer Science, University of Copenhagen, Copenhagen, DenmarkChest radiography is an indispensable diagnostic method for detecting a variety of medical conditions, such as infections, tumors, injuries, etc. Millions of chest X-ray examinations are conducted annually, providing crucial information about the functioning of the respiratory and circulatory systems. The conventional approach to quantifying cardiothoracic indices, such as the Lupi and Moore indices and the Cardiothoracic Index (CTI), requires considerable time and effort from radiologists. Consequently, it calls for the exploration of computational methods for improvement through deep learning. In this study, we addressed the challenge of automating the calculation of these cardiometric indices. We engaged four experienced radiologists to manually label 800 chest X-ray images each. Using these labeled images, we trained a deep learning model that achieved the level of performance comparable to that of a professional radiologist. Additionally, we have replaced the central points of the indices with landmarks based on the vertebrae, improving the accuracy. The use of AI led to improved accuracy of correct predictions, increasing it from 85.94% to 87.34% for the MOORE coefficient and from 87.55% to 90.67% for the LUPI coefficient.https://ieeexplore.ieee.org/document/10818426/Artificial intelligencecardiometrychest X-raysdeep learningspine |
| spellingShingle | Alexey Kornaev Dmitry Lvov Ilya Pershin Semen Kiselev Danil Afonchikov Iskander Bariev Bulat Ibragimov Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images IEEE Access Artificial intelligence cardiometry chest X-rays deep learning spine |
| title | Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images |
| title_full | Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images |
| title_fullStr | Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images |
| title_full_unstemmed | Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images |
| title_short | Automatic Calculation of Cardiometric Coefficients on Chest X-Ray Images |
| title_sort | automatic calculation of cardiometric coefficients on chest x ray images |
| topic | Artificial intelligence cardiometry chest X-rays deep learning spine |
| url | https://ieeexplore.ieee.org/document/10818426/ |
| work_keys_str_mv | AT alexeykornaev automaticcalculationofcardiometriccoefficientsonchestxrayimages AT dmitrylvov automaticcalculationofcardiometriccoefficientsonchestxrayimages AT ilyapershin automaticcalculationofcardiometriccoefficientsonchestxrayimages AT semenkiselev automaticcalculationofcardiometriccoefficientsonchestxrayimages AT danilafonchikov automaticcalculationofcardiometriccoefficientsonchestxrayimages AT iskanderbariev automaticcalculationofcardiometriccoefficientsonchestxrayimages AT bulatibragimov automaticcalculationofcardiometriccoefficientsonchestxrayimages |