Automated detection and segmentation of pulmonary embolisms on computed tomography pulmonary angiography (CTPA) using deep learning but without manual outlining.

Autor: Pu J; Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, PA 15213, USA; Department of Bioengineering, University of Pittsburgh, Pittsburgh, PA 15213, USA. Electronic address: puj@upmc.edu., Gezer NS; Department of Radiology, Dokuz Eylul University, Izmir, Turkey., Ren S; Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, PA 15213, USA., Alpaydin AO; Department of Pulmonary Diseases, Dokuz Eylul University, Izmir, Turkey., Avci ER; Department of Radiology, Dokuz Eylul University, Izmir, Turkey., Risbano MG; Department of Medicine, University of Pittsburgh, Pittsburgh, PA, USA., Rivera-Lebron B; Department of Medicine, University of Pittsburgh, Pittsburgh, PA, USA., Chan SY; Department of Medicine, University of Pittsburgh, Pittsburgh, PA, USA., Leader JK; Department of Radiology, University of Pittsburgh School of Medicine, Pittsburgh, PA 15213, USA.
Jazyk: angličtina
Zdroj: Medical image analysis [Med Image Anal] 2023 Oct; Vol. 89, pp. 102882. Date of Electronic Publication: 2023 Jul 14.
DOI: 10.1016/j.media.2023.102882
Abstrakt: We present a novel computer algorithm to automatically detect and segment pulmonary embolisms (PEs) on computed tomography pulmonary angiography (CTPA). This algorithm is based on deep learning but does not require manual outlines of the PE regions. Given a CTPA scan, both intra- and extra-pulmonary arteries were firstly segmented. The arteries were then partitioned into several parts based on size (radius). Adaptive thresholding and constrained morphological operations were used to identify suspicious PE regions within each part. The confidence of a suspicious region to be PE was scored based on its contrast in the arteries. This approach was applied to the publicly available RSNA Pulmonary Embolism CT Dataset (RSNA-PE) to identify three-dimensional (3-D) PE negative and positive image patches, which were used to train a 3-D Recurrent Residual U-Net (R2-Unet) to automatically segment PE. The feasibility of this computer algorithm was validated on an independent test set consisting of 91 CTPA scans acquired from a different medical institute, where the PE regions were manually located and outlined by a thoracic radiologist (>18 years' experience). An R2-Unet model was also trained and validated on the manual outlines using a 5-fold cross-validation method. The CNN model trained on the high-confident PE regions showed a Dice coefficient of 0.676±0.168 and a false positive rate of 1.86 per CT scan, while the CNN model trained on the manual outlines demonstrated a Dice coefficient of 0.647±0.192 and a false positive rate of 4.20 per CT scan. The former model performed significantly better than the latter model (p<0.01). The promising performance of the developed PE detection and segmentation algorithm suggests the feasibility of training a deep learning network without dedicating significant efforts to manual annotations of the PE regions on CTPA scans.
Competing Interests: Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Jiantao Pu reports financial support was provided by National Cancer Institute. Stephen Yu-Wah Chan reports financial support was provided by American Heart Association. Jiantao Pu reports financial support was provided by National Center for Complementary and Integrative Health. Dr. Stephen Yu-Wah Chan (SYC) has served as a consultant for Acceleron Pharma and United Therapeutics; SYC has held research grants from Actelion, Bayer, and Pfizer. SYC is a director, officer, and shareholder of Synhale Therapeutics. SYC has filed patents regarding metabolic dysregulation in pulmonary hypertension. The other authors declare no conflict of interest.
(Copyright © 2023 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: