Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis
Abstract Computed tomographic pulmonary angiography (CTPA) is the gold standard for pulmonary embolism (PE) diagnosis. However, this diagnosis is susceptible to misdiagnosis. In this study, we aimed to perform a systematic review of current literature applying deep learning for the diagnosis of PE o...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-95249-3 |
| _version_ | 1818432538245332992 |
|---|---|
| author | Shelly Soffer Eyal Klang Orit Shimon Yiftach Barash Noa Cahan Hayit Greenspana Eli Konen |
| author_facet | Shelly Soffer Eyal Klang Orit Shimon Yiftach Barash Noa Cahan Hayit Greenspana Eli Konen |
| author_sort | Shelly Soffer |
| collection | DOAJ |
| description | Abstract Computed tomographic pulmonary angiography (CTPA) is the gold standard for pulmonary embolism (PE) diagnosis. However, this diagnosis is susceptible to misdiagnosis. In this study, we aimed to perform a systematic review of current literature applying deep learning for the diagnosis of PE on CTPA. MEDLINE/PUBMED were searched for studies that reported on the accuracy of deep learning algorithms for PE on CTPA. The risk of bias was evaluated using the QUADAS-2 tool. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted. Seven studies met our inclusion criteria. A total of 36,847 CTPA studies were analyzed. All studies were retrospective. Five studies provided enough data to calculate summary estimates. The pooled sensitivity and specificity for PE detection were 0.88 (95% CI 0.803–0.927) and 0.86 (95% CI 0.756–0.924), respectively. Most studies had a high risk of bias. Our study suggests that deep learning models can detect PE on CTPA with satisfactory sensitivity and an acceptable number of false positive cases. Yet, these are only preliminary retrospective works, indicating the need for future research to determine the clinical impact of automated PE detection on patient care. Deep learning models are gradually being implemented in hospital systems, and it is important to understand the strengths and limitations of these algorithms. |
| first_indexed | 2024-12-14T16:06:47Z |
| format | Article |
| id | doaj.art-652f12799e464eab8a41b8a92c1cf18a |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T16:06:47Z |
| publishDate | 2021-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-652f12799e464eab8a41b8a92c1cf18a2022-12-21T22:55:04ZengNature PortfolioScientific Reports2045-23222021-08-011111810.1038/s41598-021-95249-3Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysisShelly Soffer0Eyal Klang1Orit Shimon2Yiftach Barash3Noa Cahan4Hayit Greenspana5Eli Konen6Internal Medicine B, Assuta Medical Center, Samson Assuta Ashdod University HospitalDeep Vision Lab, The Chaim Sheba Medical CenterSackler Medical School, Tel Aviv UniversityDeep Vision Lab, The Chaim Sheba Medical CenterDepartment of Biomedical Engineering, Faculty of Engineering, Tel-Aviv UniversityDepartment of Biomedical Engineering, Faculty of Engineering, Tel-Aviv UniversityDepartment of Diagnostic Imaging, Sheba Medical CenterAbstract Computed tomographic pulmonary angiography (CTPA) is the gold standard for pulmonary embolism (PE) diagnosis. However, this diagnosis is susceptible to misdiagnosis. In this study, we aimed to perform a systematic review of current literature applying deep learning for the diagnosis of PE on CTPA. MEDLINE/PUBMED were searched for studies that reported on the accuracy of deep learning algorithms for PE on CTPA. The risk of bias was evaluated using the QUADAS-2 tool. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted. Seven studies met our inclusion criteria. A total of 36,847 CTPA studies were analyzed. All studies were retrospective. Five studies provided enough data to calculate summary estimates. The pooled sensitivity and specificity for PE detection were 0.88 (95% CI 0.803–0.927) and 0.86 (95% CI 0.756–0.924), respectively. Most studies had a high risk of bias. Our study suggests that deep learning models can detect PE on CTPA with satisfactory sensitivity and an acceptable number of false positive cases. Yet, these are only preliminary retrospective works, indicating the need for future research to determine the clinical impact of automated PE detection on patient care. Deep learning models are gradually being implemented in hospital systems, and it is important to understand the strengths and limitations of these algorithms.https://doi.org/10.1038/s41598-021-95249-3 |
| spellingShingle | Shelly Soffer Eyal Klang Orit Shimon Yiftach Barash Noa Cahan Hayit Greenspana Eli Konen Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis Scientific Reports |
| title | Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis |
| title_full | Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis |
| title_fullStr | Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis |
| title_full_unstemmed | Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis |
| title_short | Deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram: a systematic review and meta-analysis |
| title_sort | deep learning for pulmonary embolism detection on computed tomography pulmonary angiogram a systematic review and meta analysis |
| url | https://doi.org/10.1038/s41598-021-95249-3 |
| work_keys_str_mv | AT shellysoffer deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT eyalklang deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT oritshimon deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT yiftachbarash deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT noacahan deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT hayitgreenspana deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis AT elikonen deeplearningforpulmonaryembolismdetectiononcomputedtomographypulmonaryangiogramasystematicreviewandmetaanalysis |