Artificial intelligence-based vessel suppression for detection of sub-solid nodules in lung cancer screening computed tomography.

BACKGROUND: Lung cancer screening (LCS) with low-dose computed tomography (LDCT) helps early lung cancer detection, commonly presenting as small pulmonary nodules. Artificial intelligence (AI)-based vessel suppression (AI-VS) and automatic detection (AI-AD) algorithm can improve detection of subsolid nodules (SSNs) on LDCT. We assessed the impact of AI-VS and AI-AD in detection and classification of SSNs [ground-glass nodules (GGNs) and part-solid nodules (PSNs)], on LDCT performed for LCS. METHODS: Following regulatory approval, 123 LDCT examinations with sub-solid pulmonary nodules (average diameter ≥6 mm) were processed to generate three image series for each examination-unprocessed, AI-VS, and AI-AD series with annotated lung nodules. Two thoracic radiologists in consensus formed the standard of reference (SOR) for this study. Two other thoracic radiologists (R1 and R2; 5 and 10 years of experience in thoracic CT image interpretation) independently assessed the unprocessed images alone, then together with AI-VS series, and finally with AI-AD for detecting all ≥6 mm GGN and PSN. We performed receiver operator characteristics (ROC) and Cohen's Kappa analyses for statistical analyses. RESULTS: On unprocessed images, R1 and R2 detected 232/310 nodules (R1: 114 GGN, 118 PSN) and 255/310 nodules (R2: 122 GGN, 133 PSN), respectively (P>0.05). On AI-VS images, they detected 249/310 nodules (119 GGN, 130 PSN) and 277/310 nodules (128 GGN, 149 PSN), respectively (P≥0.12). When compared to the SOR, accuracy (AUC) for detection of PSN on the AI-VS images (AUC 0.80-0.81) was greater than on the unprocessed images (AUC 0.70-0.76). AI-VS images enabled detection of solid components in five nodules deemed as GGN on the unprocessed images. Accuracy of AI-AD was lower than both the radiologists (AUC 0.60-0.72). CONCLUSIONS: AI-VS improved the detection and classification of SSN into GGN and PSN on LDCT of the chest for the two radiologist (R1 and R2) readers.

Practical application and validation of the 2018 ATS/ERS/JRS/ALAT and Fleischner Society guidelines for the diagnosis of idiopathic pulmonary fibrosis.

BACKGROUND: Accurate diagnosis of idiopathic pulmonary fibrosis (IPF) is essential to inform prognosis and treatment. In 2018, the ATS/ERS/JRS/ALAT and Fleischner Society released new diagnostic guidelines for usual interstitial pneumonitis (UIP)/IPF, adding Probable UIP as a CT category based on prior studies demonstrating this category had relatively high positive predictive value (PPV) for histopathologic UIP/Probable UIP. This study applies the 2018 ATS/ERS/JRS/ALAT and Fleischner Society guidelines to determine test characteristics of CT categories in academic clinical practice. METHODS: CT and histopathology were evaluated by three thoracic radiologists and two thoracic pathologists. Comparison of consensus categorization by the 2018 ATS and Fleischner Society guidelines by CT and histopathology was performed. RESULTS: Of patients with CT UIP, 87% (PPV, 95% CI: 60-98%) had histopathologic UIP with 97% (CI: 90-100%) specificity. Of patients with CT Probable UIP, 38% (PPV, CI: 14-68%) had histopathologic UIP and 46% (PPV, CI: 19-75%) had either histopathologic UIP or Probable UIP, with 88% (CI: 77-95%) specificity. Patients with CT Indeterminate and Alternative Diagnosis had histopathologic UIP in 27% (PPV, CI: 6-61%) and 21% (PPV, CI: 11-33%) of cases with specificities of 90% (CI: 80-96%) and 25% (CI: 16-37%). Interobserver variability (kappa) between radiologists ranged 0.32-0.81. CONCLUSIONS: CT UIP and Probable UIP have high specificity for histopathologic UIP, and CT UIP has high PPV for histopathologic UIP. PPV of CT Probable UIP was 46% for combined histopathologic UIP/Probable UIP. Our results indicate that additional studies are needed to further assess and refine the guideline criteria to improve classification performance.

Comparison of Baseline, Bone-Subtracted, and Enhanced Chest Radiographs for Detection of Pneumothorax.

PURPOSE: To assess and compare detectability of pneumothorax on unprocessed baseline, single-energy, bone-subtracted, and enhanced frontal chest radiographs (chest X-ray, CXR). METHOD AND MATERIALS: Our retrospective institutional review board-approved study included 202 patients (mean age 53 ± 24 years; 132 men, 70 women) who underwent frontal CXR and had trace, moderate, large, or tension pneumothorax. All patients (except those with tension pneumothorax) had concurrent chest computed tomography (CT). Two radiologists reviewed the CXR and chest CT for pneumothorax on baseline CXR (ground truth). All baseline CXR were processed to generate bone-subtracted and enhanced images (ClearRead X-ray). Four radiologists (R1-R4) assessed the baseline, bone-subtracted, and enhanced images and recorded the presence of pneumothorax (side, size, and confidence for detection) for each image type. Area under the curve (AUC) was calculated with receiver operating characteristic analyses to determine the accuracy of pneumothorax detection. RESULTS: Bone-subtracted images (AUC: 0.89-0.97) had the lowest accuracy for detection of pneumothorax compared to the baseline (AUC: 0.94-0.97) and enhanced (AUC: 0.96-0.99) radiographs (P < .01). Most false-positive and false-negative pneumothoraces were detected on the bone-subtracted images and the least numbers on the enhanced radiographs. Highest detection rates and confidence were noted for the enhanced images (empiric AUC for R1-R4 0.96-0.99). CONCLUSION: Enhanced CXRs are superior to bone-subtracted and unprocessed radiographs for detection of pneumothorax. CLINICAL RELEVANCE/APPLICATION: Enhanced CXRs improve detection of pneumothorax over unprocessed images; bone-subtracted images must be cautiously reviewed to avoid false negatives.

Multiplatform, Non-Breath-Hold Fast Scanning Protocols: Should We Stop Giving Breath-Hold Instructions for Routine Chest CT? [Formula: see text].

OBJECTIVE: We assessed if non-breath-hold (NBH) fast scanning protocol can provide respiratory motion-free images for interpretation of chest computed tomography (CT). MATERIALS AND METHODS: In our 2-phase project, we first collected baseline data on frequency of respiratory motion artifacts on breath-hold chest CT in 826 adult patients. The second phase included 62 patients (mean age 66 ± 15 years; 21 females, 41 males) who underwent an NBH chest CT on either single-source (n = 32) or dual-source (n = 30) multidetector-row CT scanners. Clinical indications for chest CT, reason for using NBH CT, scanner type, scan duration, and radiation dose (CT dose index volume, dose length product) were recorded. Two thoracic radiologists (R1 and R2) independently graded respiratory motion artifacts (1 = no respiratory motion artifacts with unrestricted evaluation; 2 = minor motion artifacts limited to one lung lobe or less with good diagnostic quality; 3 = moderate motion artifacts limited to 2 to 3 lung lobes but adequate for clinical diagnosis; 4 = poor evaluability or unevaluable from severe motion artifacts; and 5 = limited quality due to other causes like high noise, beam hardening, or metallic artifacts), and recorded pulmonary and mediastinal findings. Descriptive analyses, Cohen κ test for interobserver agreement, and Student t test were performed for statistical analysis. RESULTS: No NBH chest CT were deemed uninterpretable by either radiologist; most NBH CT (R1-59 of 62, 95%; R2-62 of 62, 100%) had no or minimal motion artifacts. Only 3 of 62 (R1) NBH chest CT had motion artifacts limiting diagnostic evaluation for lungs but not in the mediastinum. CONCLUSION: Non-breath-hold fast protocol enables acquisition of diagnostic quality chest CT free of respiratory motion artifacts in patients who cannot hold their breath.

Initial diagnosis and successful treatment of pulmonary tumor embolism manifesting as the first clinical sign of prostatic adenocarcinoma.

Although pulmonary tumor embolism (PTE) is a well-recognized end-stage form of pulmonary metastases at postmortem examination, the entity is rarely the first clinical sign of prostate cancer. Diagnosis of this condition in patients who have no previous history of malignancy is a challenge. Herein, we reported a 79-year-old man presented with progressive, unexplained dyspnea on exertion. Microscopic PTE coinciding with pulmonary lymphangitic carcinomatosis were readily recognized based on the presence of multifocal dilatation and beading of the peripheral pulmonary arteries with thickening of the bronchial walls and interlobular septa on the initial thin-section chest CT images. Pathologic examination of the transbronchial lung biopsy specimen revealed tumor emboli occluding both the small muscular pulmonary arteries and lymphatic vessels. These tumor cells were positive for prostatic specific antigen on immunohistochemical staining. The final diagnosis of prostatic adenocarcinoma was confirmed. Remarkable clinical and radiographic improvement was achieved following bilateral orchiectomies and anti-androgen treatment.

Semiautomatic Segmentation and Radiomics for Dual-Energy CT: A Pilot Study to Differentiate Benign and Malignant Hepatic Lesions.

OBJECTIVE. This study assessed a machine learning-based dual-energy CT (DECT) tumor analysis prototype for semiautomatic segmentation and radiomic analysis of benign and malignant liver lesions seen on contrast-enhanced DECT. MATERIALS AND METHODS. This institutional review board-approved study included 103 adult patients (mean age, 65 ± 15 [SD] years; 53 men, 50 women) with benign (60/103) or malignant (43/103) hepatic lesions on contrast-enhanced dual-source DECT. Most malignant lesions were histologically proven; benign lesions were either stable on follow-up CT or had characteristic benign features on MRI. Low- and high-kilovoltage datasets were deidentified, exported offline, and processed with the DECT tumor analysis for semiautomatic segmentation of the volume and rim of each liver lesion. For each segmentation, contrast enhancement and iodine concentrations as well as radiomic features were derived for different DECT image series. Statistical analyses were performed to determine if DECT tumor analysis and radiomics can differentiate benign from malignant liver lesions. RESULTS. Normalized iodine concentration and mean iodine concentration in the benign and malignant lesions were significantly different (p < 0.0001-0.0084; AUC, 0.695-0.856). Iodine quantification and radiomic features from lesion rims (AUC, ≤ 0.877) had higher accuracy for differentiating liver lesions compared with the values from lesion volumes (AUC, ≤ 0.856). There was no difference in the accuracies of DECT iodine quantification (AUC, 0.91) and radiomics (AUC, 0.90) for characterizing liver lesions. CONCLUSION. DECT radiomics were more accurate than iodine quantification for differentiating solid benign and malignant hepatic lesions.

Deep learning-enabled system for rapid pneumothorax screening on chest CT.

PURPOSE: Prompt diagnosis and quantitation of pneumothorax impact decisions pertaining to patient management. The purpose of our study was to develop and evaluate the accuracy of a deep learning (DL)-based image classification program for detection of pneumothorax on chest CT. METHOD: In an IRB approved study, an eight-layer convolutional neural network (CNN) using constant-size (36*36 pixels) 2D image patches was trained on a set of 80 chest CTs, with (n = 50) and without (n = 30) pneumothorax. Image patches were classified based on their probability of representing pneumothorax with subsequent generation of 3D heat-maps. The heat maps were further defined to include 1) pneumothorax area size, 2) relative location of the region to the lung boundary, and 3) a shape descriptor based on regional anisotropy. A support vector machine (SVM) was trained for classification. RESULT: We assessed performance of our program in a separate test dataset of 200 chest CT examinations, with (160/200, 75%) and without (40/200, 25%) pneumothorax. Data were analyzed to determine the accuracy, sensitivity, specificity. The subject-wise sensitivity was 100% (all 160/160 pneumothoraces detected) and specificity was 82.5% (33 true negative/40). False positive classifications were primarily related to emphysema and/or artifacts in the test images. CONCLUSION: This deep learning-based program demonstrated high accuracy for automatic detection of pneumothorax on chest CTs. By implementing it on a high-performance computing platform and integrating the domain knowledge of radiologists into the analytics framework, our method can be used to rapidly pre-screen large numbers of cases for presence of pneumothorax, a critical finding.

Extent of Intraprotocol and Intersite Variability of Thoracic Magnetic Resonance Acquisition Times at a Large Quaternary Institution: MR Technologist Insights as to Its Causes.

PURPOSE: The purpose of this study was to describe Thoracic magnetic resonance (MR) acquisition time (AT) variability, associations, and technologist insights as to its causes at a large quaternary institution, by MR protocol and imaging site. MATERIALS AND METHODS: A retrospective review of our 2017 QI database of 1.5 T MR imaging ATs for adults 19 years and above at the main hospital and outpatient (OPT) satellites was performed for all 5 Thoracic MR protocols. Summary statistics were calculated for ATs. Multivariable linear regression was adjusted for age, sex, body mass index, time of examination relative to shift change, technologist experience, and language interpreter. An anonymous REDCap survey of our MR technologists sought their assessment of reasons for AT variability and techniques that help reduce it. RESULTS: A total of 174 adult OPT 1.5 T mediastinal, pleural, and lung MR examinations were analyzed, revealing high variability of median AT by protocol and site (P<0.001)-for example, mean, median, slowest, and fastest ATs for Thymus I- protocol (n=38) were 34, 32, 66, and 8 minutes, respectively. OPT site with fewest MR technologists and a single MR scanner had shortest mean AT across all protocols (35±15 min). Full Chest I- protocol had shortest AT across all sites (mean AT=33±13 min), compared with focused imaging protocols. All I-/I+ protocols had greater than expected AT, compared with the same protocol performed (I-). Surveyed MR technologists noted limited Thoracic MR training/experience, discomfort with thoracic anatomy and Thoracic MR performance, and AT-related benefit of effective communication with the radiologist with regard to lesion location. CONCLUSIONS: There was tremendous intraprotocol and intersite variability of Thoracic MR ATs. Increased technologist training, amplified experience, and a solid understanding of lesion location for focused examinations may all help reduce Thoracic MR AT.

Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction.

Commercial iterative reconstruction techniques help to reduce CT radiation dose but altered image appearance and artifacts limit their adoptability and potential use. Deep learning has been investigated for low-dose CT (LDCT). Here we design a modularized neural network for LDCT and compared it with commercial iterative reconstruction methods from three leading CT vendors. While popular networks are trained for an end-to-end mapping, our network performs an end-to-process mapping so that intermediate denoised images are obtained with associated noise reduction directions towards a final denoised image. The learned workflow allows radiologists-in-the-loop to optimize the denoising depth in a task-specific fashion. Our network was trained with the Mayo LDCT Dataset, and tested on separate chest and abdominal CT exams from Massachusetts General Hospital. The best deep learning reconstructions were systematically compared to the best iterative reconstructions in a double-blinded reader study. This study confirms that our deep learning approach performed either favorably or comparably in terms of noise suppression and structural fidelity, and is much faster than the commercial iterative reconstruction algorithms.

Assessment of proximal and peripheral airway dysfunction by computed tomography and respiratory impedance in asthma and COPD patients with fixed airflow obstruction.

OBJECTIVE: To ascertain: (i) if elderly patients with fixed airflow obstruction (FAO) due to asthma and chronic obstructive pulmonary disease (COPD) have distinct airway morphologic and physiologic changes; (ii) the correlation between the morphology of proximal/peripheral airways and respiratory impedance. METHODS: Twenty-five asthma cases with FAO and 22 COPD patients were enrolled. High-resolution computed tomography was used to measure the wall area (WA) and lumen area (LA) of the proximal airway at the apical segmental bronchus of the right upper lobe (RB1) adjusted by body surface area (BSA) and bronchial wall thickening (BWT r ) of the peripheral airways and extent of expiratory air trapping (AT exp ). Respiratory impedance included resistance at 5 Hz (R5) and 20 Hz (R20) and resonant frequency (Fres). Total lung capacity (TLC) and residual volume (RV) were measured. RESULTS: Asthma patients had smaller RB1-LA/BSA than COPD patients (10.5 ± 3.4 vs. 13.3 ± 5.0 mm2/m2, P = 0.037). R5(5.5 ± 2.0 vs. 3.4 ± 1.0 cmH2O/L/s, P = 0.02) and R20(4.2 ± 1.7 vs. 2.6 ± 0.7 cmH2O/L/s, P = 0.001) were higher in asthma cases. AT exp and BWT r were similar in both groups. Regression analysis in asthma showed that forced expiratory volume in one second (FEV1) and Fres were associated with RB1-WA/BSA (R2= 0.34, P = 0.005) and BWT r (0.5, 0.012), whereas RV/TLC was associated with AT exp (0.38, 0.001). CONCLUSIONS: Asthma patients with FAO had a smaller LA and higher resistance of the proximal airways than COPD patients. FEV1 and respiratory impedance correlated with airway morphology.

Deep learning in chest radiography: Detection of findings and presence of change.

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.

Thin-section CT findings of thoracolithiasis.

PURPOSE: To review thin-section CT findings of thoracolithiasis. MATERIALS AND METHODS: Thirty-three thin-section CT scans of 9 patients with thoracolithiasis diagnosed between 2008 and 2016 were reviewed for the location, shape, longest diameter, and calcification of each freely mobile nodule (thoracolith) and for the presence of coexisting abnormalities. RESULTS: The mean age of 9 patients (5 women) was 65.8 years (SD 14.9; range 37-83 years). Eight were > 50 years of age. Three patients had two thoracoliths, and the remaining 6 patients had one. Thoracoliths were in the left (n = 9) or right (n = 3) pleural cavity, with most in the lower pleural cavity. Nine thoracoliths were found to be larger at follow-up. The median diameters of the 12 thoracoliths were 4.9 mm (range 2.1-10.6 mm) and 6.2 mm (range 3.6-11.0 mm) on the initial and latest follow-up CT scans, respectively. Concomitant old granulomatous disease (n = 6) and diffuse systemic sclerosis-related interstitial lung disease (n = 2) were noted. CONCLUSION: Thoracolithiasis can manifest as one or two small calcified nodules. It tends to occur in the left lower pleural cavity, occur in a patient aged > 50 years, be larger on follow-up, and coincide with other diseases.