Search

Objective: To investigate the predictive factors for a non-diagnostic result and the final diagnosis of pulmonary lesions with an initial non-diagnostic result on CT-guided percutaneous transthoracic needle biopsy., Materials and Methods: All percutaneous transthoracic needle biopsies performed over a 4-year period were retrospectively reviewed. The initial pathological results were classified into three categories-malignant, benign, and non-diagnostic. A non-diagnostic result was defined when no malignant cells were seen and a specific benign diagnosis could not be made. The demographic data of patients, lesions' characteristics, technique, complications, initial pathological results, and final diagnosis were reviewed. Statistical analysis was performed using binary logistic regression., Results: Of 894 biopsies in 861 patients (male:female, 398:463; mean age 67, range 18-92 years), 690 (77.2%) were positive for malignancy, 55 (6.2%) were specific benign, and 149 (16.7%) were non-diagnostic. Of the 149 non-diagnostic biopsies, excluding 27 cases in which the final diagnosis could not be confirmed, 36% revealed malignant lesions and 64% revealed benign lesions. Predictive factors for a non-diagnostic biopsy included the size ≤ 15 mm, needle tract traversing emphysematous lung parenchyma, introducer needle outside the lesion, procedure time > 60 minutes, and presence of alveolar hemorrhage. Non-diagnostic biopsies with a history of malignancy or atypical cells on pathology were more likely to be malignant ( p = 0.043 and p = 0.001)., Conclusion: The predictive factors for a non-diagnostic biopsy were lesion size ≤ 15 mm, needle tract traversing emphysema, introducer needle outside the lesion, procedure time > 60 minutes, and presence of alveolar hemorrhage. Thirty-six percent of the non-diagnostic biopsies yielded a malignant diagnosis. In cases with a history of malignancy or the presence of atypical cells in the biopsy sample, a repeat biopsy or surgical intervention should be considered., Competing Interests: The authors have no potential conflicts of interest to disclose., (Copyright © 2019 The Korean Society of Radiology.)

Background: Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs., Methods and Findings: We processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis., Results: About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2-0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837-0.929 and 0.693-0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities., Conclusions: DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings., Competing Interests: Mannudeep K. Kalra, MD, has received unrelated industrial research grants from Siemens Healthineers and Cannon Medical Systems. Co-authors, PR, and PP are employees of Qure AI, Mumbai, India. This does not alter our adherence to PLOS ONE policies on sharing data and materials.