3:54 PM Abstract No. 152 Factors associated with pneumothorax in 3719 computed tomography–guided lung biopsies: a machine learning pipeline approach

Mugu, Vamshi K.; Thompson, Spencer; Eiken, Patrick W.; Fleming, Chad J.; Young, Jesse T.

doi:10.1016/j.jvir.2019.12.186

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the multitude of factors associated with increased pneumothorax risk after lung biopsies, machine learning approaches have been recently utilized to better predict complication outcomes. In particular, a study determined which features of patient data were strongly associated with the incidence of a pneumothorax after lung biopsies, finding that patient and procedure characteristics such as age and needle size were important factors in pneumothorax incidence 10 . Another deep learning model based on clinical and demographic data predicted a pneumothorax after lung biopsy with 90% sensitivity and 81.6% specificity 11 .…”

Section: Introductionmentioning

confidence: 99%

Predicting pneumothorax after lung biopsy from pre-operative imaging using a deep convolutional neural network

Jang

Pua

Shih

2022

Preprint

View full text Add to dashboard Cite

Background: Pneumothorax remains one of the most common complications after computed tomography (CT)-guided lung biopsies. Radiographic features including bullae and nodule size are possible markers for post-biopsy pneumothorax. We determine whether a convolutional neural network (CNN) can accurately predict a pneumothorax after lung biopsy based on pre-operative imaging alone. Methods: With institutional review board approval, we retrospectively evaluated 3,822 patients who underwent a CT-guided lung biopsy between 2011 to 2019. Two image sets were created with CT scout images (1300 patients, 650 pneumothoraces) and chest x-rays (CXR) taken within three months pre-procedure (884 patients, 140 pneumothoraces). Using pre-operative images, CNNs of varying layer depths were trained using transfer learning to predict the development of a pneumothorax post-biopsy. Performance against models were compared using sensitivity analysis and the McNemar's test. Results: The CNN models trained with CT scout images performed near chance. However, the models performed better with CXR radiographs taken within three months pre-biopsy. For the anterior-posterior view, sensitivity was 0.40, specificity was 0.89, PPV was 0.43, and NPV was 0.87 (AUC = 0.67). For the lateral view, sensitivity was 0.4, specificity was 0.80, PPV was 0.32, and NPV was 0.86 (AUC = 0.65). Increasing CNN layers did not affect performance (p > 0.05). Conclusion: Chest radiographs taken within three months of lung biopsy may provide important radiographic information for CNNs to assess pneumothorax risk in patients prior to CT-guided lung biopsies. However, more baseline and standardized CXRs before biopsies are necessary to create a robust model for clinical application.

show abstract

Section: Introductionmentioning

confidence: 99%