Efficacy and Safety of Dose-Escalated Alectinib in Patients With Metastatic ALK-Positive NSCLC and Central Nervous System Relapse on Standard-Dose Alectinib.

Introduction: Central nervous system (CNS) metastases remain a common challenge in patients with ALK-positive NSCLC. We previously reported reinduction of CNS responses using dose-intensified alectinib in two patients with CNS progression on standard-dose alectinib. Nevertheless, this strategy has not been assessed in larger cohorts. Methods: Patients were eligible for this retrospective study if they had metastatic ALK-positive NSCLC with CNS relapse on alectinib 600 mg twice daily dosing and subsequently received escalated dosing (900 mg twice daily) of alectinib. CNS efficacy was assessed per the modified Response Evaluation Criteria in Solid Tumors version 1.1. Results: Among 27 patients, median duration of dose-escalated alectinib was 7.7 months (95% confidence interval [CI]: 4.8-10.9), with median overall time-to-progression (TTP) of 7.1 months (95% CI: 4.4-9.6). Among 25 CNS response-assessable patients, CNS objective response rate was 12.0% (95% CI: 2.5-31.2) and CNS disease control rate was 92.0% (95% CI: 74.0-99.0), with median CNS duration of disease control of 5.3 months (95% CI: 3.4-8.3) and median CNS TTP of 7.1 months (95% CI: 4.4-9.6). Among four patients with measurable CNS disease at baseline, three experienced a best intracranial response of stable disease and one experienced intracranial partial response with CNS TTP ranging from 4.1 to 7.7 months. No patient required drug discontinuation due to treatment-related adverse event or experienced grade 3 or higher treatment-related adverse events. Conclusions: Dose-intensified alectinib was found to have tolerability and activity in patients with ALK-positive NSCLC who experienced CNS relapse on standard-dose alectinib and represents one clinically viable strategy for this population.

Correlation of Radiomics with Treatment Response in Liver Metastases.

RATIONALE AND OBJECTIVES: To assess differences in radiomics derived from semi-automatic segmentation of liver metastases for stable disease (SD), partial response (PR), and progressive disease (PD) based on RECIST1.1 and to assess if radiomics alone at baseline can predict response. MATERIALS AND METHODS: Our IRB-approved study included 203 women (mean age 54 ± 11 years) with metastatic liver disease from breast cancer. All patients underwent contrast abdomen-pelvis CT in the portal venous phase at two points: baseline (pre-treatment) and follow-up (between 3 and 12 months following treatment). Patients were subcategorized into three subgroups based on RECIST 1.1 criteria (Response Evaluation Criteria in Solid Tumors version 1.1): 66 with SD, 69 with PR, and 68 with PD on follow-up CT. The deidentified baseline and follow-up CT images were exported to the radiomics prototype. The prototype enabled semi-automatic segmentation of the target liver lesions for the extraction of first and high order radiomics. Statistical analyses with logistic regression and random forest classifiers were performed to differentiate SD from PD and PR. RESULTS: There was no significant difference between the radiomics on the baseline and follow-up CT images of patients with SD (area under the curve (AUC): 0.3). Random forest classifier differentiated patients with PR with an AUC of 0.845. The most relevant feature was the large dependence emphasis's high and low pass wavelet filter (derived gray level dependence matrix features). Random forest classifier differentiated PD with an AUC of 0.731, with the most relevant feature being the surface-to-volume ratio. There was no difference in radiomics among the three groups at baseline; therefore, a response could not be predicted. CONCLUSION: Radiomics of liver metastases with semi-automatic segmentation demonstrate differences between SD from PR and PD. SUMMARY STATEMENT: Semiautomatic segmentation and radiomics of metastatic liver disease demonstrate differences in SD from the PR and progressive metastatic on the baseline and follow-up CT. Despite substantial variations in the scanners, acquisition, and reconstruction parameters, radiomics had an AUC of 0.84-0.89 for differentiating stable hepatic metastases from decreasing and increasing metastatic disease.

Surgical Resection of Benign Nodules in Lung Cancer Screening: Incidence and Features.

Introduction: Interventions and surgical procedures are common for nonmalignant lung lesions detected on lung cancer screening (LCS). Inadvertent surgical resection of benign nodules with a clinical suspicion of lung cancer can occur, can be associated with complications, and adds to the cost of screening. The objective of this study is to assess the characteristics of surgically resected benign nodules detected on LCS computed tomography which were presumed to be lung cancers. Methods: This retrospective study included 4798 patients who underwent LCS between June 2014 and January 2021. The benign lung nodules, surgically resected with a presumed cancer diagnosis, were identified from the LCS registry. Patient demographics, imaging characteristics, and pathologic diagnoses of benign nodules were analyzed. Results: Of the 4798 patients who underwent LCS, 148 (3.1%) underwent surgical resection of a lung nodule, and of those who had a resection, 19 of 148 (12.8%) had a benign diagnosis (median age = 64 y, range: 56-77 y; F = 12 of 19, 63.2%; M = seven of 19, 36.8%). The median nodule size was 10 mm (range: 6-31 mm). Most nodules were solid (15 of 19, 78.9%), located in the upper lobes (11 of 19; 57.9%), and were peripheral (17 of 19, 89.5%). Most nodules (13 of 17; 76.5%) had interval growth, and four of 17 (23.5%) had increased fluorodeoxyglucose uptake. Of the 19 patients, 17 (89.5%) underwent sublobar resection (16 wedge resection and one segmentectomy), whereas two central nodules (10.5%) had lobectomies. Pathologies identified included focal areas of fibrosis or scarring (n = 8), necrotizing granulomatous inflammation (n = 3), other nonspecific inflammatory focus (n = 3), benign tumors (n = 3), reactive lymphoid hyperplasia (n = 1), and organizing pneumonia (n = 1). Conclusions: Surgical resections of benign nodules that were presumed malignant are infrequent and may be unavoidable given overlapping imaging features of benign and malignant nodules. Knowledge of benign pathologies that can mimic malignancy may help reduce the incidence of unnecessary surgeries.

Lorlatinib and capmatinib in a ROS1-rearranged NSCLC with MET-driven resistance: tumor response and evolution.

Acquired drug resistance remains a major problem across oncogene-addicted cancers. Elucidation of mechanisms of resistance can inform rational treatment strategies for patients relapsing on targeted therapies while offering insights into tumor evolution. Here, we report acquired MET amplification as a resistance driver in a ROS1-rearranged lung adenocarcinoma after sequential treatment with ROS1 inhibitors. Subsequent combination therapy with lorlatinib plus capmatinib, a MET-selective inhibitor, induced intracranial and extracranial tumor response. At relapse, sequencing of the resistant tumor revealed a MET D1246N mutation and loss of MET amplification. We performed integrated molecular analyses of serial tumor and plasma samples, unveiling dynamic alterations in the ROS1 fusion driver and MET bypass axis at genomic and protein levels and the emergence of polyclonal resistance. This case illustrates the complexity of longitudinal tumor evolution with sequential targeted therapies, highlighting challenges embedded in the current precision oncology paradigm and the importance of developing approaches that prevent resistance.

Dual-Energy Computed Tomography Applications in Lung Cancer.

This article examines the intrathoracic applications for dual-energy computed tomography (DECT), focusing on lung cancer. The topics covered include the image data sets, methods for iodine quantification, and clinical applications. The applications of DECT are to differentiate benign and malignant lung nodules, determining the grade of lung cancer and expression of ki-67 expression. Iodine quantification has role in assessment of treatment response in both the primary tumor and nodal metastases.

Impact of Baseline Interstitial Lung Abnormalities on Pneumonitis Risk in Patients Receiving Immune Checkpoint Inhibitors for Non-Small-Cell Lung Cancer.

INTRODUCTION/BACKGROUND: Immune-related pneumonitis is a potentially fatal complication of treatment with immune checkpoint inhibitors (ICIs). Interstitial lung disease (ILD) is associated with increased risk for pneumonitis, but the impact of interstitial abnormalities (ILA) in the absence of ILD has not been extensively assessed. We examined the relationship between ILA on pretreatment chest computed tomography (CT) scans and risk of pneumonitis in patients with non-small-cell lung cancer (NSCLC). METHODS: This retrospective cohort study included consecutive adult patients who received ICI for NSCLC between January 2013 and January 2020 at our institution. Two thoracic radiologists blinded to clinical outcomes independently reviewed pre-ICI chest CTs to identify and categorize ILA using previously published definitions. We used uni- and multivariable analysis adjusted for age, radiation, and smoking status to assess for associations between ILA, clinicopathologic characteristics, and symptomatic (CTCAE grade ≥2) pneumonitis. RESULTS: Of 475 patients who received ICI treatment and met inclusion criteria, baseline ILA were present in 78 (16.4%) patients, most commonly as a subpleural nonfibrotic pattern. In total, 43 (9.1%) of 475 patients developed symptomatic pneumonitis. Pneumonitis occurred in 16.7% of patients with ILA compared to 7.6% patients without ILA (P < .05). Presence of ground glass and extent of lung parenchymal involvement were associated with an increased risk of pneumonitis. On multivariable analysis, baseline ILA remained associated with increased risk of symptomatic pneumonitis (OR 2.2, 95% CI, 1.0-4.5). CONCLUSIONS: Baseline ILAs are associated with the development of symptomatic pneumonitis in patients with NSCLC treated with ICI. Additional studies are needed to validate these observations.

Extrathoracic Metastases in Pleural Mesothelioma.

Introduction: Guidelines recommend obtaining a computed tomography scan of the chest for the staging of pleural mesothelioma and for assessing response to treatment. Consensus is lacking regarding the necessity of serial imaging of distant extrathoracic sites. In this study, we determined the prevalence of extrathoracic metastases in patients with pleural mesothelioma. Methods: We conducted a retrospective review of patients with pleural mesothelioma treated at Massachusetts General Hospital between 1999 and 2022 who were referred for extrathoracic imaging during their disease course. Imaging reports were reviewed to determine sites of metastasis and calculate the time to development of extrathoracic metastasis. Overall survival and prevalence of extrathoracic metastasis were compared for patients with epithelioid versus nonepithelioid mesothelioma. Results: The study included 148 patients, 69 (47%) of whom had undergone cytoreductive surgery. Histologic types included epithelioid (n = 82, 55%), biphasic (n = 49, 33%), and sarcomatoid (n = 10, 7%) mesothelioma. The median overall survival for the cohort was 24.0 months, specifically 34.7 months and 16.7 months for patients with epithelioid and nonepithelioid tumors, respectively (p < 0.001). There were 65 (44%) patients who developed extrathoracic metastases, with a median time to extrathoracic metastasis of 11.5 months. The most common sites of involvement were extrathoracic nodes (22%), peritoneum (20%), bone (11%), and liver (11%). Of the 76 patients referred for brain imaging, seven (9%) had brain metastases. The frequency of extrathoracic metastasis was identical for epithelioid and nonepithelioid mesothelioma (44%). Overall survival was shorter for patients who developed extrathoracic metastases (hazard ratio 5.9, p < 0.001). Conclusions: Patients with pleural mesothelioma often develop extrathoracic metastases, providing a rationale for routinely obtaining imaging that encompasses sites outside of the thoracic cavity.

Efficacy and Tolerability of ALK/MET Combinations in Patients With ALK-Rearranged Lung Cancer With Acquired MET Amplification: A Retrospective Analysis.

Introduction: MET amplification is a potentially actionable resistance mechanism in ALK-rearranged (ALK+) lung cancer. Studies describing treatment outcomes of this molecular subgroup are lacking. Methods: We assembled a cohort of patients with ALK+ lung cancer and acquired MET amplification (identified by tissue or plasma) who received regimens targeting both ALK and MET. Efficacy and safety were assessed using the Response Evaluation Criteria in Solid Tumors version 1.1 and Common Terminology Criteria for Adverse Events version 4.03, respectively. Results: A total of 12 patients were included in the series. MET amplification was detected after a median of 1.5 (range 1-5) lines of therapy. Four distinct regimens were implemented to address MET amplification: crizotinib (n = 2), lorlatinib plus crizotinib (n = 6), alectinib plus capmatinib (n = 3), and alectinib plus crizotinib (n = 1). Partial responses were observed in five (42%) of 12 patients, including patients who received crizotinib (n = one of two), lorlatinib plus crizotinib (n = three of six), and alectinib plus capmatinib (n = one of three). Primary progression was observed in four patients (33%). Grades 1 to 2 peripheral edema, occurring in seven (58%) patients, was found with both crizotinib and capmatinib. One patient required dose reduction of capmatinib plus alectinib for persistent grade 2 edema. Across the regimens, one patient discontinued therapy for toxicity, specifically neurocognitive toxicity from lorlatinib plus crizotinib. At progression on ALK+ MET therapy, potential resistance mechanisms included MET copy number changes and ALK kinase domain mutations. Conclusions: Combined ALK and MET inhibition is associated with moderate antitumor activity in patients with ALK+ NSCLC with concurrent MET amplification. Prospective studies are indicated to confirm activity and identify individuals most likely to benefit from the treatment.

Imaging in Lung Transplantation: Surgical Techniques and Complications.

Lung transplant is an established treatment for patients with end-stage lung disease. As a result, there is increased demand for transplants. Despite improvements in pretransplant evaluation, surgical techniques, and postsurgical care, the average posttransplant life expectancy is only around 6.5 years. Early recognition of complications on imaging and treatment can improve survival. Knowledge of surgical techniques and imaging findings of surgical and nonsurgical complications is essential. This review covers surgical techniques and imaging appearance of postsurgical and nonsurgical complications, including allograft dysfunction, infections, neoplasms, and recurrence of primary lung disease.

Integrated Radiology, Pathology, and Pharmacy Program to Accelerate Access to Osimertinib.

PURPOSE: Targeted therapy yields superior outcomes relative to genotype-agnostic therapy for patients with epidermal growth factor receptor (EGFR)-mutant lung cancer. Workflows that facilitate timely detection of EGFR mutations and early dispensation of osimertinib can improve management of this disease. METHODS: We developed an Integrated Radiology, Pathology, and Pharmacy Program to minimize delays in initiating osimertinib. The intervention consisted of parallel workflows coupling interventional radiology, surgical pathology, and analysis of nucleic acids from frozen tissue with early pharmacy engagement. We compared time to EGFR testing results and time to treatment for participating patients with those of historical cohorts. RESULTS: Between January 2020 and December 2021, 222 patients participated in the intervention. The median turnaround time from biopsy to EGFR results was 1 workday. Forty-nine (22%) tumors harbored EGFR exon 19 deletions or EGFR L858R. Thirty-one (63%) patients were prescribed osimertinib via the intervention. The median interval between osimertinib prescription and osimertinib dispensation was 3 days; dispensation occurred within 48 hours for 42% of patients. The median interval between biopsy and osimertinib dispensation was 5 days. Three patients received osimertinib within 24 hours of EGFR results. Compared with patients with EGFR-mutant non-small-cell lung cancer who were diagnosed through routine workflows, the intervention led to a significant reduction in median time between biopsy and EGFR results (1 v 7 days; P < .01) and median time to treatment initiation (5 v 23 days; P < .01). CONCLUSION: Combining radiology and pathology workflows with early parallel pharmacy engagement leads to a significant reduction in time to initiating osimertinib. Multidisciplinary integration programs are essential to maximize clinical utility of rapid testing.

Low Contrast Volume Protocol in Routine Chest CT Amid the Global Contrast Shortage: A Single Institution Experience.

OBJECTIVE: To assess the effectiveness of low contrast volume (LCV) chest CT performed with multiple contrast agents on multivendor CT with varying scanning techniques. METHODS: The study included 361 patients (65 ± 15 years; M: F 173:188) who underwent LCV chest CT on one of the six 64-256 detector-row CT scanners using single-energy (SECT) or dual-energy (DECT) modes. All patients were scanned with either a fixed-LCV (LCVf, n = 103) or weight-based LCV (LCVw, n = 258) protocol. Two thoracic radiologists independently assessed all LCV CT and patients' prior standard contrast volume (SCV, n = 263) chest CT for optimality of contrast enhancement in thoracic vasculature, cardiac chambers, and in pleuro-parenchymal and mediastinal abnormalities. CT attenuations were recorded in the main pulmonary trunk, ascending, and descending thoracic aorta. To assess the interobserver agreement, pulmonary arterial enhancement was divided into two groups: optimal or suboptimal. RESULTS: There was no significant difference among patients' BMI (p = 0.883) in the three groups. DECT had a significantly higher aortic arterial enhancement (250 ± 99HU vs 228 ± 76 HU for SECT, p < 0.001). Optimal enhancement was present in 558 of 624 chest CT (89.4%), whereas 66 of 624 chest CT with suboptimal enhancement was noted in 48 of 258 LCVw (18.6%) and 14 of 103 LCVf (13.6%). Most patients with suboptimal enhancement with LCVw injection protocol were overweight/obese (30/48; 62.5%), (p < 0.001). CONCLUSION: LCV chest CT can be performed across complex multivendor, multicontrast media, multiscanner, and multiprotocol CT practices. However, LCV chest CT examinations can result in suboptimal contrast enhancement in patients with larger body habitus.

Comutations and KRASG12C Inhibitor Efficacy in Advanced NSCLC.

Molecular modifiers of KRASG12C inhibitor (KRASG12Ci) efficacy in advanced KRASG12C-mutant NSCLC are poorly defined. In a large unbiased clinicogenomic analysis of 424 patients with non-small cell lung cancer (NSCLC), we identified and validated coalterations in KEAP1, SMARCA4, and CDKN2A as major independent determinants of inferior clinical outcomes with KRASG12Ci monotherapy. Collectively, comutations in these three tumor suppressor genes segregated patients into distinct prognostic subgroups and captured ∼50% of those with early disease progression (progression-free survival ≤3 months) with KRASG12Ci. Pathway-level integration of less prevalent coalterations in functionally related genes nominated PI3K/AKT/MTOR pathway and additional baseline RAS gene alterations, including amplifications, as candidate drivers of inferior outcomes with KRASG12Ci, and revealed a possible association between defective DNA damage response/repair and improved KRASG12Ci efficacy. Our findings propose a framework for patient stratification and clinical outcome prediction in KRASG12C-mutant NSCLC that can inform rational selection and appropriate tailoring of emerging combination therapies. SIGNIFICANCE: In this work, we identify co-occurring genomic alterations in KEAP1, SMARCA4, and CDKN2A as independent determinants of poor clinical outcomes with KRASG12Ci monotherapy in advanced NSCLC, and we propose a framework for patient stratification and treatment personalization based on the comutational status of individual tumors. See related commentary by Heng et al., p. 1513. This article is highlighted in the In This Issue feature, p. 1501.

Genomic and transcriptomic analysis of checkpoint blockade response in advanced non-small cell lung cancer.

Anti-PD-1/PD-L1 agents have transformed the treatment landscape of advanced non-small cell lung cancer (NSCLC). To expand our understanding of the molecular features underlying response to checkpoint inhibitors in NSCLC, we describe here the first joint analysis of the Stand Up To Cancer-Mark Foundation cohort, a resource of whole exome and/or RNA sequencing from 393 patients with NSCLC treated with anti-PD-(L)1 therapy, along with matched clinical response annotation. We identify a number of associations between molecular features and outcome, including (1) favorable (for example, ATM altered) and unfavorable (for example, TERT amplified) genomic subgroups, (2) a prominent association between expression of inducible components of the immunoproteasome and response and (3) a dedifferentiated tumor-intrinsic subtype with enhanced response to checkpoint blockade. Taken together, results from this cohort demonstrate the complexity of biological determinants underlying immunotherapy outcomes and reinforce the discovery potential of integrative analysis within large, well-curated, cancer-specific cohorts.

Radiologist-Trained AI Model for Identifying Suboptimal Chest-Radiographs.

RATIONALE AND OBJECTIVES: Suboptimal chest radiographs (CXR) can limit interpretation of critical findings. Radiologist-trained AI models were evaluated for differentiating suboptimal(sCXR) and optimal(oCXR) chest radiographs. MATERIALS AND METHODS: Our IRB-approved study included 3278 CXRs from adult patients (mean age 55 ± 20 years) identified from a retrospective search of CXR in radiology reports from 5 sites. A chest radiologist reviewed all CXRs for the cause of suboptimality. The de-identified CXRs were uploaded into an AI server application for training and testing 5 AI models. The training set consisted of 2202 CXRs (n = 807 oCXR; n = 1395 sCXR) while 1076 CXRs (n = 729 sCXR; n = 347 oCXR) were used for testing. Data were analyzed with the Area under the curve (AUC) for the model's ability to classify oCXR and sCXR correctly. RESULTS: For the two-class classification into sCXR or oCXR from all sites, for CXR with missing anatomy, AI had sensitivity, specificity, accuracy, and AUC of 78%, 95%, 91%, 0.87(95% CI 0.82-0.92), respectively. AI identified obscured thoracic anatomy with 91% sensitivity, 97% specificity, 95% accuracy, and 0.94 AUC (95% CI 0.90-0.97). Inadequate exposure with 90% sensitivity, 93% specificity, 92% accuracy, and AUC of 0.91 (95% CI 0.88-0.95). The presence of low lung volume was identified with 96% sensitivity, 92% specificity, 93% accuracy, and 0.94 AUC (95% CI 0.92-0.96). The sensitivity, specificity, accuracy, and AUC of AI in identifying patient rotation were 92%, 96%, 95%, and 0.94 (95% CI 0.91-0.98), respectively. CONCLUSION: The radiologist-trained AI models can accurately classify optimal and suboptimal CXRs. Such AI models at the front end of radiographic equipment can enable radiographers to repeat sCXRs when necessary.

Osimertinib in NSCLC With Atypical EGFR-Activating Mutations: A Retrospective Multicenter Study.

Introduction: EGFR mutations drive a subset of NSCLC. Patients harboring the common EGFR mutations, deletion of exon 19 and L858R, respond well to osimertinib, a third-generation tyrosine kinase inhibitor. Nevertheless, the effect of osimertinib on NSCLC with atypical EGFR mutations is not well described. This multicenter retrospective study evaluates the efficacy of osimertinib among patients with NSCLC harboring atypical EGFR mutations. Methods: Patients with metastatic NSCLC treated with osimertinib, harboring at least one atypical EGFR mutation, excluding concurrent deletion of exon 19, L858R, or T790M mutations, from six U.S. academic cancer centers were included. Baseline clinical characteristics were collected. The primary end point was the time to treatment discontinuation (TTD) of osimertinib. Objective response rate by the Response Evaluation Criteria in Solid Tumors version 1.1 was also assessed. Results: A total of 50 patients with NSCLC with uncommon EGFR mutations were identified. The most frequent EGFR mutations were L861Q (40%, n = 18), G719X (28%, n = 14), and exon 20 insertion (14%, n = 7). The median TTD of osimertinib was 9.7 months (95% confidence interval [CI]: 6.5-12.9 mo) overall and 10.7 months (95% CI: 3.2-18.1 mo) in the first-line setting (n = 20). The objective response rate was 31.7% (95% CI: 18.1%-48.1%) overall and 41.2% (95% CI: 18.4%-67.1%) in the first-line setting. The median TTD varied among patients with L861Q (17.2 mo), G719X (7.8 mo), and exon 20 insertion (1.5 mo) mutations. Conclusions: Osimertinib has activity in patients with NSCLC harboring atypical EGFR mutations. Osimertinib activity differs by the type of atypical EGFR-activating mutation.

Auto-Detection of Motion Artifacts on CT Pulmonary Angiograms with a Physician-Trained AI Algorithm.

Purpose: Motion-impaired CT images can result in limited or suboptimal diagnostic interpretation (with missed or miscalled lesions) and patient recall. We trained and tested an artificial intelligence (AI) model for identifying substantial motion artifacts on CT pulmonary angiography (CTPA) that have a negative impact on diagnostic interpretation. Methods: With IRB approval and HIPAA compliance, we queried our multicenter radiology report database (mPower, Nuance) for CTPA reports between July 2015 and March 2022 for the following terms: "motion artifacts", "respiratory motion", "technically inadequate", and "suboptimal" or "limited exam". All CTPA reports were from two quaternary (Site A, n = 335; B, n = 259) and a community (C, n = 199) healthcare sites. A thoracic radiologist reviewed CT images of all positive hits for motion artifacts (present or absent) and their severity (no diagnostic effect or major diagnostic impairment). Coronal multiplanar images from 793 CTPA exams were de-identified and exported offline into an AI model building prototype (Cognex Vision Pro, Cognex Corporation) to train an AI model to perform two-class classification ("motion" or "no motion") with data from the three sites (70% training dataset, n = 554; 30% validation dataset, n = 239). Separately, data from Site A and Site C were used for training and validating; testing was performed on the Site B CTPA exams. A five-fold repeated cross-validation was performed to evaluate the model performance with accuracy and receiver operating characteristics analysis (ROC). Results: Among the CTPA images from 793 patients (mean age 63 ± 17 years; 391 males, 402 females), 372 had no motion artifacts, and 421 had substantial motion artifacts. The statistics for the average performance of the AI model after five-fold repeated cross-validation for the two-class classification included 94% sensitivity, 91% specificity, 93% accuracy, and 0.93 area under the ROC curve (AUC: 95% CI 0.89-0.97). Conclusion: The AI model used in this study can successfully identify CTPA exams with diagnostic interpretation limiting motion artifacts in multicenter training and test datasets. Clinical relevance: The AI model used in the study can help alert technologists about the presence of substantial motion artifacts on CTPA, where a repeat image acquisition can help salvage diagnostic information.

Automatic segmentation and measurement of tracheal collapsibility in tracheomalacia.

PURPOSE: To assess feasibility of automated segmentation and measurement of tracheal collapsibility for detecting tracheomalacia on inspiratory and expiratory chest CT images. METHODS: Our study included 123 patients (age 67 ± 11 years; female: male 69:54) who underwent clinically indicated chest CT examinations in both inspiration and expiration phases. A thoracic radiologist measured anteroposterior length of trachea in inspiration and expiration phase image at the level of maximum collapsibility or aortic arch (in absence of luminal change). Separately, another investigator separately processed the inspiratory and expiratory DICOM CT images with Airway Segmentation component of a commercial COPD software (IntelliSpace Portal, Philips Healthcare). Upon segmentation, the software automatically estimated average lumen diameter (in mm) and lumen area (sq.mm) both along the entire length of trachea and at the level of aortic arch. Data were analyzed with independent t-tests and area under the receiver operating characteristic curve (AUC). RESULTS: Of the 123 patients, 48 patients had tracheomalacia and 75 patients did not. Ratios of inspiration to expiration phases average lumen area and lumen diameter from the length of trachea had the highest AUC of 0.93 (95% CI = 0.88-0.97) for differentiating presence and absence of tracheomalacia. A decrease of ≥25% in average lumen diameter had sensitivity of 82% and specificity of 87% for detecting tracheomalacia. A decrease of ≥40% in the average lumen area had sensitivity and specificity of 86% for detecting tracheomalacia. CONCLUSION: Automatic segmentation and measurement of tracheal dimension over the entire tracheal length is more accurate than a single-level measurement for detecting tracheomalacia.

Evaluation of an Artificial Intelligence Model for Detection of Pneumothorax and Tension Pneumothorax in Chest Radiographs.

Importance: Early detection of pneumothorax, most often via chest radiography, can help determine need for emergent clinical intervention. The ability to accurately detect and rapidly triage pneumothorax with an artificial intelligence (AI) model could assist with earlier identification and improve care. Objective: To compare the accuracy of an AI model vs consensus thoracic radiologist interpretations in detecting any pneumothorax (incorporating both nontension and tension pneumothorax) and tension pneumothorax. Design, Setting, and Participants: This diagnostic study was a retrospective standalone performance assessment using a data set of 1000 chest radiographs captured between June 1, 2015, and May 31, 2021. The radiographs were obtained from patients aged at least 18 years at 4 hospitals in the Mass General Brigham hospital network in the United States. Included radiographs were selected using 2 strategies from all chest radiography performed at the hospitals, including inpatient and outpatient. The first strategy identified consecutive radiographs with pneumothorax through a manual review of radiology reports, and the second strategy identified consecutive radiographs with tension pneumothorax using natural language processing. For both strategies, negative radiographs were selected by taking the next negative radiograph acquired from the same radiography machine as each positive radiograph. The final data set was an amalgamation of these processes. Each radiograph was interpreted independently by up to 3 radiologists to establish consensus ground-truth interpretations. Each radiograph was then interpreted by the AI model for the presence of pneumothorax and tension pneumothorax. This study was conducted between July and October 2021, with the primary analysis performed between October and November 2021. Main Outcomes and Measures: The primary end points were the areas under the receiver operating characteristic curves (AUCs) for the detection of pneumothorax and tension pneumothorax. The secondary end points were the sensitivities and specificities for the detection of pneumothorax and tension pneumothorax. Results: The final analysis included radiographs from 985 patients (mean [SD] age, 60.8 [19.0] years; 436 [44.3%] female patients), including 307 patients with nontension pneumothorax, 128 patients with tension pneumothorax, and 550 patients without pneumothorax. The AI model detected any pneumothorax with an AUC of 0.979 (95% CI, 0.970-0.987), sensitivity of 94.3% (95% CI, 92.0%-96.3%), and specificity of 92.0% (95% CI, 89.6%-94.2%) and tension pneumothorax with an AUC of 0.987 (95% CI, 0.980-0.992), sensitivity of 94.5% (95% CI, 90.6%-97.7%), and specificity of 95.3% (95% CI, 93.9%-96.6%). Conclusions and Relevance: These findings suggest that the assessed AI model accurately detected pneumothorax and tension pneumothorax in this chest radiograph data set. The model's use in the clinical workflow could lead to earlier identification and improved care for patients with pneumothorax.