Limitations of using artificial intelligence services to analyze chest x-ray imaging

Cover Image

Cite item

Full Text

Abstract

BACKGROUND: Chest X-ray examination is one of the first radiology areas that started applying artificial intelligence, and it is still used to the present. However, when interpreting X-ray scans using artificial intelligence, radiologists still experience several routine restrictions that should be considered in issuing a medical report and require the attention of artificial intelligence developers to further improve the algorithms and increase their efficiency.

AIM: To identify restrictions of artificial intelligence services for analyzing chest X-ray images and assesses the clinical significance of these restrictions.

MATERIALS AND METHODS: A retrospective analysis was performed for 155 cases of discrepancies between the conclusions of artificial intelligence services and medical reports when analyzing chest X-ray images. All cases included in the study were obtained from the Unified Radiological Information Service of the Unified Medical Information and Analytical System of Moscow.

RESULTS: Of the 155 analyzed difference cases, 48 (31.0%) were false-positive and 78 (50.3%) were false-negative cases. The remaining 29 (18.7%) cases were removed from further studies because they were true positive (27) or true negative (2) in the expert review. Most (93.8%) of the 48 false-positive cases were due to the artificial intelligence service mistaking normal chest anatomy (97.8% of cases) or catheter shadow (2.2% of cases) for pneumothorax signs. Overlooked clinically significant pathologies accounted for 22.0% of false-negative scans. Nearly half of these cases (44.4%) were overlooked lung nodules. Lung calcifications (60.9%) were the most common clinically insignificant pathology.

CONCLUSIONS: Artificial intelligence services demonstrate a tendency toward over diagnosis. All false-positive cases were associated with erroneous detection of clinically significant pathology: pneumothorax, lung nodules, and pulmonary consolidation. Among false-negative cases, the rate of overlooked clinically significant pathology was low, which accounted for less than one-fourth.

About the authors

Yuriy A. Vasilev

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: npcmr@zdrav.mos.ru
ORCID iD: 0000-0002-5283-5961
SPIN-code: 4458-5608

MD, Cand. Sci. (Medicine)

Russian Federation, Moscow

Anton V. Vladzymyrskyy

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: a.vladzimirsky@npcmr.ru
ORCID iD: 0000-0002-2990-7736
SPIN-code: 3602-7120

MD, Dr. Sci. (Medicine), Professor

Russian Federation, Moscow

Kirill M. Arzamasov

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: ArzamasovKM@zdrav.mos.ru
ORCID iD: 0000-0001-7786-0349
SPIN-code: 3160-8062

MD, Cand. Sci. (Medicine)

Russian Federation, Moscow

Igor M. Shulkin

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: i.shulkin@npcmr.ru
ORCID iD: 0000-0002-7613-5273
SPIN-code: 5266-0618
Russian Federation, Moscow

Elena V. Astapenko

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Author for correspondence.
Email: AstapenkoEV1@zdrav.mos.ru
ORCID iD: 0009-0006-6284-2088
SPIN-code: 7362-8553
Russian Federation, Moscow

Lev D. Pestrenin

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: PestreninLD@zdrav.mos.ru
ORCID iD: 0000-0002-1786-4329
SPIN-code: 7193-7706
Russian Federation, Moscow

References

  1. Çallı E, Sogancioglu E, van Ginneken B, et al. Deep learning for chest X-ray analysis: A survey. Medical Image Analysis. 2021;72:102125. doi: 10.1016/j.media.2021.102125
  2. Vasilev YuA, Tyrov IA, Vladzymyrskyy AV, et al. A New Model of Organizing Mass Screening Based on Stand-Alone Artificial Intelligence Used for Fluorography Image Triage. Zdorov’e Naseleniya i Sreda Obitaniya. 2023;31(11):23–32. (In Russ.) doi: 10.35627/2219-5238/2023-31-11-23-32
  3. Akhter Y, Singh R, Vatsa M. AI-based radiodiagnosis using chest X-rays: A review. Frontiers in Big Data. 2023;6:1120989. doi: 10.3389/fdata.2023.1120989
  4. Fanni SC, Marcucci A, Volpi F, et al. Artificial Intelligence-Based Software with CE Mark for Chest X-ray Interpretation: Opportunities and Challenges. Diagnostics (Basel). 2023;13(12):2020. doi: 10.3390/diagnostics13122020
  5. Gusev AV, Vladzymyrskyy AV, Sharova DE, et al. Evolution of research and development in the field of artificial intelligence technologies for healthcare in the Russian Federation: results of 2021. Digital Diagnostics. 2022;3(3):178–194. doi: 10.17816/DD107367
  6. Kim J, Kim KH. Role of chest radiographs in early lung cancer detection. Translational Lung Cancer Research. 2020;9(3):522–531. doi: 10.21037/tlcr.2020.04.02
  7. Golubev NA, Ogryzko EV, Tyurina EM, et al. Features of the development of the radiology diagnostic service in the Russian Federation for 2014-2019. Current problems of health care and medical statistics. 2021;(2):356–376. doi: 10.24412/2312-2935-2021-2-356-376
  8. Wu JT, Wong KCL, Gur Y, et al. Comparison of Chest Radiograph Interpretations by Artificial Intelligence Algorithm vs Radiology Residents. JAMA Network Open. 2020;3(10):e2022779. doi: 10.1001/jamanetworkopen.2020.22779
  9. Miró Catalina Q, Fuster-Casanovas A, Solé-Casals J, Vidal-Alaball J. Developing an Artificial Intelligence Model for Reading Chest X-rays: Protocol for a Prospective Validation Study. JMIR Research Protocols. 2022;11(11):e39536. doi: 10.2196/39536
  10. Plesner LL, Müller FC, Nybing JD, et al. Autonomous Chest Radiograph Reporting Using AI: Estimation of Clinical Impact. Radiology. 2023;307(3):e222268. doi: 10.1148/radiol.222268
  11. Vasilev Yu, Vladzymyrskyy A, Omelyanskaya O, et al. AI-Based CXR First Reading: Current Limitations to Ensure Practical Value. Diagnostics (Basel). 2023;13(8):1430. doi: 10.3390/diagnostics13081430
  12. Driver CN, Bowles BS, Bartholmai BJ, Greenberg-Worisek AJ. Artificial Intelligence in Radiology: A Call for Thoughtful Application. Clinical and Translational Science. 2020;13(2):216–218. doi: 10.1111/cts.12704
  13. Yoo H, Kim EY, Kim H, et al. Artificial intelligence-based identification of normal chest radiographs: a simulation study in a multicenter health screening cohort. Korean Journal of Radiology. 2022;23(10):1009–1018. doi: 10.3348/kjr.2022.0189
  14. Suganuma N, Yoshida S, Takeuchi Y, et al. Artificial intelligence in quantitative chest imaging analysis for occupational lung disease. Seminars in Respiratory and Critical Care Medicine. 2023;44(3):362–369. doi: 10.1055/s-0043-1767760
  15. Brown C, Nazeer R, Gibbs A, et al. Breaking Bias: The role of artificial intelligence in improving clinical decision-making. Cureus. 2023;15(3):e36415. doi: 10.7759/cureus.36415
  16. Kaviani P, Kalra MK, Digumarthy SR, et al. Frequency of missed findings on chest radiographs (CXRs) in an international, multicenter study: application of AI to reduce missed findings. Diagnostics (Basel). 2022;12(10):2382. doi: 10.3390/diagnostics12102382
  17. de Groot PM, Carter BW, Abbott GF, Wu CC. Pitfalls in chest radiographic interpretation: blind spots. Seminars in Roentgenology. 2015;50(3):197–209. doi: 10.1053/j.ro.2015.01.008
  18. Gefter WB, Post BA, Hatabu H. Commonly missed findings on chest radiographs: causes and consequences. Chest. 2023;163(3):650–661. doi: 10.1016/j.chest.2022.10.039
  19. Vasilev YuA, Vladzimirsky AV, editors. Komp’yuternoe zrenie v luchevoj diagnostike: pervyj etap Moskovskogo eksperimenta. Moscow: Izdatelskie resheniya; 2022. (In Russ.)
  20. Morozov SP, Burenchev DV, Vladzimirsky AV, et al. Principy i pravila opisanij rezul’tatov luchevyh issledovanij. The series “Best practices of radiation and instrumental diagnostics”. Issue 97. Moscow: State Budget-Funded Health Care Institution of the City of Moscow “Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Health Care Department”; 2021. (In Russ.)
  21. Choi YR, Yoon SH, Kim J, et al. Chest Radiography of Tuberculosis: Determination of Activity Using Deep Learning Algorithm. Tuberculosis and Respiratory Diseases. 2023;86(3):226–233. doi: 10.4046/trd.2023.0020
  22. Sun Z, Zhou J, Zhao L. Application status and problems summary of artificial intelligence in chest imaging. Asian Journal of Surgery. 2023;46(10):4437–4438. doi: 10.1016/j.asjsur.2023.04.100
  23. Bernstein MH, Atalay MK, Dibble EH, et al. Can incorrect artificial intelligence (AI) results impact radiologists, and if so, what can we do about it? A multi-reader pilot study of lung cancer detection with chest radiography. European Radiology. 2023;33(11):8263–8269. doi: 10.1007/s00330-023-09747-1
  24. Becker J, Decker JA, Römmele C, et al. Artificial Intelligence-based detection of pneumonia in chest radiographs. Diagnostics (Basel). 2022;12(6):1465. doi: 10.3390/diagnostics12061465
  25. Dasegowda G, Bizzo BC, Gupta RV, et al. Radiologist-trained AI model for identifying suboptimal chest-radiographs. Academic Radiology. 2023;30(12):2921–2930. doi: 10.1016/j.acra.2023.03.006
  26. Fanni SC, Greco G, Rossi S, et al. Role of artificial intelligence in oncologic emergencies: a narrative review. Exploration of Targeted Anti-tumor Therapy. 2023;4(2):344–354. doi: 10.37349/etat.2023.00138
  27. Hwang EJ, Goo JM, Nam JG, et al. Conventional versus artificial intelligence-assisted interpretation of chest radiographs in patients with acute respiratory symptoms in emergency department: a pragmatic randomized clinical trial. Korean Journal of Radiology. 2023;24(3):259–270. doi: 10.3348/kjr.2022.0651
  28. Tan H, Xu H, Yu N, et al. The value of deep learning-based computer aided diagnostic system in improving diagnostic performance of rib fractures in acute blunt trauma. BMC Medical Imaging. 2023;23(1):55. doi: 10.1186/s12880-023-01012-7
  29. Wu J, Liu N, Li X, et al. Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study. BMC Medical Imaging. 2023;23(1):18. doi: 10.1186/s12880-023-00975-x
  30. Lee HW, Jin KN, Oh S, et al. Artificial intelligence solution for chest radiographs in respiratory outpatient clinics: multicenter prospective randomized clinical trial. Annals of the American Thoracic Society. 2023;20(5):660–667. doi: 10.1513/AnnalsATS.202206-481OC
  31. Hillis JM, Bizzo BC, Mercaldo S, et al. Evaluation of an artificial intelligence model for detection of pneumothorax and tension pneumothorax in chest radiographs. JAMA Network Open. 2022;5(12):e2247172. doi: 10.1001/jamanetworkopen.2022.47172

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. Frequency of recognition by artificial intelligence services of anatomical structures (green) and foreign objects (blue) as the edge of a lung compressed by air (pneumothorax).

Download (121KB)
Indexing metadata
3. Fig. 2. Structure of omissions of clinically significant pathology. OOP — esophageal opening of the diaphragm.

Download (102KB)
Indexing metadata
4. Fig. 3. Structure of omissions of clinically insignificant pathology. CVC — central venous catheter.

Download (192KB)
Indexing metadata
5. Fig. 4. Post-inflammatory changes, fibrosis, pleuro-parenchymatous cords, adhesions.

Download (209KB)
Indexing metadata
6. Fig. 5. False positive case of AI-based software triggering associated with pronounced subcutaneous fat.

Download (80KB)
Indexing metadata
7. Fig. 6. Shadow of the mammary gland nipple, mistakenly labeled as a pulmonary nodule.

Download (101KB)
Indexing metadata
8. Fig. 7. Hiatal hernia undetected by AI-based software behind the heart shadow.

Download (213KB)
Indexing metadata
9. Fig. 8. On the lateral projection, a lesion in the projection of the upper lobe is visually determined (all software based on artificial intelligence technologies naturally did not determine it due to the processing of only the direct projection).

Download (462KB)
Indexing metadata
10. Fig. 9. The lateral projection shows fibrous changes in the posterior costophrenic sinus on the right, which are not visible on the direct projection (the artificial intelligence service did not detect them due to processing only the direct projection). Similarly to these changes, the service can "miss" minimal pleural effusion.

Download (119KB)
Indexing metadata
11. Fig. 10. Hydrothorax in a bedridden patient was not recognized by the AI-based software.

Download (110KB)
Indexing metadata

Copyright (c) 2024 Eco-Vector

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Согласие на обработку персональных данных с помощью сервиса «Яндекс.Метрика»

1. Я (далее – «Пользователь» или «Субъект персональных данных»), осуществляя использование сайта https://journals.rcsi.science/ (далее – «Сайт»), подтверждая свою полную дееспособность даю согласие на обработку персональных данных с использованием средств автоматизации Оператору - федеральному государственному бюджетному учреждению «Российский центр научной информации» (РЦНИ), далее – «Оператор», расположенному по адресу: 119991, г. Москва, Ленинский просп., д.32А, со следующими условиями.

2. Категории обрабатываемых данных: файлы «cookies» (куки-файлы). Файлы «cookie» – это небольшой текстовый файл, который веб-сервер может хранить в браузере Пользователя. Данные файлы веб-сервер загружает на устройство Пользователя при посещении им Сайта. При каждом следующем посещении Пользователем Сайта «cookie» файлы отправляются на Сайт Оператора. Данные файлы позволяют Сайту распознавать устройство Пользователя. Содержимое такого файла может как относиться, так и не относиться к персональным данным, в зависимости от того, содержит ли такой файл персональные данные или содержит обезличенные технические данные.

3. Цель обработки персональных данных: анализ пользовательской активности с помощью сервиса «Яндекс.Метрика».

4. Категории субъектов персональных данных: все Пользователи Сайта, которые дали согласие на обработку файлов «cookie».

5. Способы обработки: сбор, запись, систематизация, накопление, хранение, уточнение (обновление, изменение), извлечение, использование, передача (доступ, предоставление), блокирование, удаление, уничтожение персональных данных.

6. Срок обработки и хранения: до получения от Субъекта персональных данных требования о прекращении обработки/отзыва согласия.

7. Способ отзыва: заявление об отзыве в письменном виде путём его направления на адрес электронной почты Оператора: info@rcsi.science или путем письменного обращения по юридическому адресу: 119991, г. Москва, Ленинский просп., д.32А

8. Субъект персональных данных вправе запретить своему оборудованию прием этих данных или ограничить прием этих данных. При отказе от получения таких данных или при ограничении приема данных некоторые функции Сайта могут работать некорректно. Субъект персональных данных обязуется сам настроить свое оборудование таким способом, чтобы оно обеспечивало адекватный его желаниям режим работы и уровень защиты данных файлов «cookie», Оператор не предоставляет технологических и правовых консультаций на темы подобного характера.

9. Порядок уничтожения персональных данных при достижении цели их обработки или при наступлении иных законных оснований определяется Оператором в соответствии с законодательством Российской Федерации.

10. Я согласен/согласна квалифицировать в качестве своей простой электронной подписи под настоящим Согласием и под Политикой обработки персональных данных выполнение мною следующего действия на сайте: https://journals.rcsi.science/ нажатие мною на интерфейсе с текстом: «Сайт использует сервис «Яндекс.Метрика» (который использует файлы «cookie») на элемент с текстом «Принять и продолжить».