Segmentation of acute pulmonary embolism in computed tomography pulmonary angiography using the deep learning method
Introduction: Pulmonary embolism is a type of thromboembolism seen in the main pulmonary artery and its branches. This study aimed to diagnose acute pulmonary embolism using the deep learning method in computed tomographic pulmonary angiography (CTPA) and perform the segmentation of pulmonary embolism data.
Materials and Methods: The CTPA images of patients diagnosed with pulmonary embolism who underwent scheduled imaging were retrospectively evaluated. After data collection, the areas that were diagnosed as embolisms in the axial section images were segmented. The dataset was divided into three parts: training, validation, and testing. The results were calculated by selecting 50% as the cut-off value for the intersection over the union.
Result: Images were obtained from 1.550 patients. The mean age of the patients was 64.23 ± 15.45 years. A total of 2.339 axial computed tomography images obtained from the 1.550 patients were used. The PyTorch U-Net was used to train 400 epochs, and the best model, epoch 178, was recorded. In the testing group, the number of true positives was determined as 471, the number of false positives as 35, and 27 cases were not detected. The sensitivity of CTPA segmentation was 0.95, the precision value was 0.93, and the F1 score value was 0.94. The area under the curve value obtained in the receiver operating characteristic analysis was calculated as 0.88.
Conclusions: In this study, the deep learning method was successfully employed for the segmentation of acute pulmonary embolism in CTPA, yielding positive outcomes.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:71 |
|---|---|
| Enthalten in: |
Tuberkuloz ve toraks - 71(2023), 2 vom: 01. Juni, Seite 131-137 |
| Sprache: |
Türkisch |
|---|
| Weiterer Titel: |
Derin öğrenme yöntemiyle akut pulmoner embolinin bilgisayarlı tomografik pulmoner anjiografide segmentasyonu |
|---|
| Beteiligte Personen: |
Aydın, Nevin [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 23.06.2023 Date Revised 01.03.2024 published: Print Citation Status MEDLINE |
|---|
| doi: |
10.5578/tt.20239916 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM358468353 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM358468353 | ||
| 003 | DE-627 | ||
| 005 | 20240301231951.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||tur c | ||
| 024 | 7 | |a 10.5578/tt.20239916 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1313.xml |
| 035 | |a (DE-627)NLM358468353 | ||
| 035 | |a (NLM)37345395 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a tur | ||
| 100 | 1 | |a Aydın, Nevin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Segmentation of acute pulmonary embolism in computed tomography pulmonary angiography using the deep learning method |
| 246 | 3 | 3 | |a Derin öğrenme yöntemiyle akut pulmoner embolinin bilgisayarlı tomografik pulmoner anjiografide segmentasyonu |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 23.06.2023 | ||
| 500 | |a Date Revised 01.03.2024 | ||
| 500 | |a published: Print | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Introduction: Pulmonary embolism is a type of thromboembolism seen in the main pulmonary artery and its branches. This study aimed to diagnose acute pulmonary embolism using the deep learning method in computed tomographic pulmonary angiography (CTPA) and perform the segmentation of pulmonary embolism data | ||
| 520 | |a Materials and Methods: The CTPA images of patients diagnosed with pulmonary embolism who underwent scheduled imaging were retrospectively evaluated. After data collection, the areas that were diagnosed as embolisms in the axial section images were segmented. The dataset was divided into three parts: training, validation, and testing. The results were calculated by selecting 50% as the cut-off value for the intersection over the union | ||
| 520 | |a Result: Images were obtained from 1.550 patients. The mean age of the patients was 64.23 ± 15.45 years. A total of 2.339 axial computed tomography images obtained from the 1.550 patients were used. The PyTorch U-Net was used to train 400 epochs, and the best model, epoch 178, was recorded. In the testing group, the number of true positives was determined as 471, the number of false positives as 35, and 27 cases were not detected. The sensitivity of CTPA segmentation was 0.95, the precision value was 0.93, and the F1 score value was 0.94. The area under the curve value obtained in the receiver operating characteristic analysis was calculated as 0.88 | ||
| 520 | |a Conclusions: In this study, the deep learning method was successfully employed for the segmentation of acute pulmonary embolism in CTPA, yielding positive outcomes | ||
| 650 | 4 | |a English Abstract | |
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Cihan, Çağatay |e verfasserin |4 aut | |
| 700 | 1 | |a Çelik, Özer |e verfasserin |4 aut | |
| 700 | 1 | |a Aslan, Ahmet Faruk |e verfasserin |4 aut | |
| 700 | 1 | |a Odabaş, Alper |e verfasserin |4 aut | |
| 700 | 1 | |a Alataş, Füsun |e verfasserin |4 aut | |
| 700 | 1 | |a Yıldırım, Hüseyin |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Tuberkuloz ve toraks |d 2003 |g 71(2023), 2 vom: 01. Juni, Seite 131-137 |w (DE-627)NLM147934990 |x 2980-3187 |7 nnns |
| 773 | 1 | 8 | |g volume:71 |g year:2023 |g number:2 |g day:01 |g month:06 |g pages:131-137 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.5578/tt.20239916 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 71 |j 2023 |e 2 |b 01 |c 06 |h 131-137 | ||