Comparing Diagnostic Accuracy of Radiologists versus GPT-4V and Gemini Pro Vision Using Image Inputs from Diagnosis Please Cases.

Background The diagnostic abilities of multimodal large language models (LLMs) using direct image inputs and the impact of the temperature parameter of LLMs remain unexplored. Purpose To investigate the ability of GPT-4V and Gemini Pro Vision in generating differential diagnoses at different temperatures compared with radiologists using Radiology Diagnosis Please cases. Materials and Methods This retrospective study included Diagnosis Please cases published from January 2008 to October 2023. Input images included original images and captures of the textual patient history and figure legends (without imaging findings) from PDF files of each case. The LLMs were tasked with providing three differential diagnoses, repeated five times at temperatures 0, 0.5, and 1. Eight subspecialty-trained radiologists solved cases. An experienced radiologist compared generated and final diagnoses, considering the result correct if the generated diagnoses included the final diagnosis after five repetitions. Accuracy was assessed across models, temperatures, and radiology subspecialties, with statistical significance set at P < .007 after Bonferroni correction for multiple comparisons across the LLMs at the three temperatures and with radiologists. Results A total of 190 cases were included in neuroradiology (n = 53), multisystem (n = 27), gastrointestinal (n = 25), genitourinary (n = 23), musculoskeletal (n = 17), chest (n = 16), cardiovascular (n = 12), pediatric (n = 12), and breast (n = 5) subspecialties. Overall accuracy improved with increasing temperature settings (0, 0.5, 1) for both GPT-4V (41% [78 of 190 cases], 45% [86 of 190 cases], 49% [93 of 190 cases], respectively) and Gemini Pro Vision (29% [55 of 190 cases], 36% [69 of 190 cases], 39% [74 of 190 cases], respectively), although there was no evidence of a statistically significant difference after Bonferroni adjustment (GPT-4V, P = .12; Gemini Pro Vision, P = .04). The overall accuracy of radiologists (61% [115 of 190 cases]) was higher than that of Gemini Pro Vision at temperature 1 (T1) (P < .001), while no statistically significant difference was observed between radiologists and GPT-4V at T1 after Bonferroni adjustment (P = .02). Radiologists (range, 45%-88%) outperformed the LLMs at T1 (range, 24%-75%) in most subspecialties. Conclusion Using direct radiologic image inputs, GPT-4V and Gemini Pro Vision showed improved diagnostic accuracy with increasing temperature settings. Although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making. © RSNA, 2024 See also the editorial by Nishino and Ballard in this issue.

CT-guided percutaneous transthoracic needle biopsy for anterior mediastinal lymphoma: the role of PET/CT.

BACKGROUND: Computed tomography (CT)-guided percutaneous transthoracic needle biopsy (PTNB) is not recommended as the diagnostic modality of choice for anterior mediastinal lymphoma, despite its advantages of minimal invasiveness and easy accessibility. PURPOSE: To identify the modifiable risk factors for non-diagnostic results from CT-guided PTNB for anterior mediastinal lymphoma. MATERIAL AND METHODS: This retrospective study identified CT-guided PTNB for anterior mediastinal lesions diagnosed as lymphoma between May 2007 and December 2021. The diagnostic sensitivity and complications were investigated. The appropriateness of PTNB targeting was evaluated using positron emission tomography (PET)/CT and images from intra-procedural CT-guided PTNB. Targeting was considered inappropriate when the supposed trajectory of the cutting needle was within a region of abnormally low metabolism. The risk factors for non-diagnostic results were determined using logistic regression analysis. RESULTS: A total of 67 PTNBs in 60 patients were included. The diagnostic sensitivity for lymphoma was 76.1% (51/67), with an immediate complication rate of 4.5% (3/67). According to the PET/CT images, PTNB targeting was inappropriate in 10/14 (71.4%) of the non-diagnostic PTNBs but appropriate in all diagnostic PTNBs (P <0.001). Inappropriate targeting was the only significant risk factor for non-diagnostic results (odds ratio = 203.69; 95% confidence interval = 8.17-999.99; P = 0.001). The number of specimen acquisitions was not associated with non-diagnostic results (P = 0.40). CONCLUSIONS: Only inappropriate targeting of the non-viable portion according to PET/CT was an independent risk factor for non-diagnostic results. Acquiring PET/CT scans before biopsy and targeting the viable portion on PET/CT may help improve the diagnostic sensitivity of PTNB.

Prognostic Implications of Synchronous Subsolid Nodules in Patients with Resected Subsolid Lung Adenocarcinoma.

Background For multiple subsolid nodules (SSNs) observed at lung CT, current management focuses on removal of the dominant (≥6 mm) nodule and monitoring of remaining SSNs. Whether the presence of these synchronous SSNs is related to postoperative patient outcomes has not been well established. Purpose To evaluate the prognostic value of single versus multiple synchronous SSNs at preoperative CT in patients with resected subsolid lung adenocarcinoma nodules. Materials and Methods This retrospective study included patients who underwent lobectomy or sublobar resection for lung adenocarcinoma manifesting as an SSN and clinical stage IA from January 2010 to December 2017. The radiologic features of the resected SSN (dominant nodule) and synchronous SSNs were assessed on preoperative CT scans. The effects of synchronous SSNs on time to secondary intervention, time to recurrence (TTR), and overall survival (OS) were evaluated using Cox regression analysis. Results Of the 684 included patients (mean age, 60.9 years ± 9.5 [SD]; 389 female), 515 (75.3%) had a single SSN and 169 (24.7%) had multiple SSNs on preoperative CT scans. During follow-up (median, 71.8 months), 38 secondary interventions were performed, primarily due to growth of synchronous SSNs (21 of 38) or metachronous nodules (14 of 38). As the number of synchronous SSNs greater than or equal to 6 mm in size increased, the time to secondary intervention decreased (P < .001). No association was observed between synchronous SSNs and TTR (P = .53) or OS (P = .65), but these measures were associated with features of the resected nodule, specifically solid portion size for TTR (P = .01) and histologic subtype for TTR and OS (P < .001 for both). Conclusion In patients with subsolid lung adenocarcinoma, the presence of synchronous SSNs on preoperative CT scans was not associated with TTR or OS, but the presence of synchronous SSNs greater than or equal to 6 mm in size was associated with an increased likelihood of secondary intervention. © RSNA, 2023 Supplemental material is available for this article.

Deep Learning for Automated Triaging of Stable Chest Radiographs in a Follow-up Setting.

Background Most artificial intelligence algorithms that interpret chest radiographs are restricted to an image from a single time point. However, in clinical practice, multiple radiographs are used for longitudinal follow-up, especially in intensive care units (ICUs). Purpose To develop and validate a deep learning algorithm using thoracic cage registration and subtraction to triage pairs of chest radiographs showing no change by using longitudinal follow-up data. Materials and Methods A deep learning algorithm was retrospectively developed using baseline and follow-up chest radiographs in adults from January 2011 to December 2018 at a tertiary referral hospital. Two thoracic radiologists reviewed randomly selected pairs of "change" and "no change" images to establish the ground truth, including normal or abnormal status. Algorithm performance was evaluated using area under the receiver operating characteristic curve (AUC) analysis in a validation set and temporally separated internal test sets (January 2019 to August 2021) from the emergency department (ED) and ICU. Threshold calibration for the test sets was conducted, and performance with 40% and 60% triage thresholds was assessed. Results This study included 3 304 996 chest radiographs in 329 036 patients (mean age, 59 years ± 14 [SD]; 170 433 male patients). The training set included 550 779 pairs of radiographs. The validation set included 1620 pairs (810 no change, 810 change). The test sets included 533 pairs (ED; 265 no change, 268 change) and 600 pairs (ICU; 310 no change, 290 change). The algorithm had AUCs of 0.77 (validation), 0.80 (ED), and 0.80 (ICU). With a 40% triage threshold, specificity was 88.4% (237 of 268 pairs) and 90.0% (261 of 290 pairs) in the ED and ICU, respectively. With a 60% triage threshold, specificity was 79.9% (214 of 268 pairs) and 79.3% (230 of 290 pairs) in the ED and ICU, respectively. For urgent findings (consolidation, pleural effusion, pneumothorax), specificity was 78.6%-100% (ED) and 85.5%-93.9% (ICU) with a 40% triage threshold. Conclusion The deep learning algorithm could triage pairs of chest radiographs showing no change while detecting urgent interval changes during longitudinal follow-up. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Czum in this issue.

Automated CT quantification of interstitial lung abnormality and interstitial lung disease according to the Fleischner Society in patients with resectable lung cancer: prognostic significance.

OBJECTIVE: To assess the prognostic significance of automatically quantified interstitial lung abnormality (ILA) according to the definition by the Fleischner Society in patients with resectable non-small-cell lung cancer (NSCLC). METHODS: Patients who underwent lobectomy or pneumonectomy for NSCLC between January 2015 and December 2019 were retrospectively included. Preoperative CT scans were analyzed using the commercially available deep-learning-based automated quantification software for ILA. According to quantified results and the definition by the Fleischner Society and multidisciplinary discussion, patients were divided into normal, ILA, and interstitial lung disease (ILD) groups. RESULTS: Of the 1524 patients, 87 (5.7%) and 20 (1.3%) patients had ILA and ILD, respectively. Both ILA (HR, 1.81; 95% CI: 1.25-2.61; p = .002) and ILD (HR, 5.26; 95% CI: 2.99-9.24; p < .001) groups had poor recurrence-free survival (RFS). Overall survival (OS) decreased (HR 2.13 [95% CI: 1.27-3.58; p = .004] for the ILA group and 7.20 [95% CI: 3.80-13.62, p < .001] for the ILD group) as the disease severity increased. Both quantified fibrotic and non-fibrotic ILA components were associated with poor RFS (HR, 1.57; 95% CI: 1.12-2.21; p = .009; and HR, 1.11; 95% CI: 1.01-1.23; p = .03) and OS (HR, 1.59; 95% CI: 1.06-2.37; p = .02; and HR, 1.17; 95% CI: 1.03-1.33; and p = .01) in normal and ILA groups. CONCLUSIONS: The automated CT quantification of ILA based on the definition by the Fleischner Society predicts outcomes of patients with resectable lung cancer based on the disease category and quantified fibrotic and non-fibrotic ILA components. CLINICAL RELEVANCE STATEMENT: Quantitative CT assessment of ILA provides prognostic information for lung cancer patients after surgery, which can help in considering active surveillance for recurrence, especially in those with a larger extent of quantified ILA. KEY POINTS: • Of the 1524 patients with resectable lung cancer, 1417 (93.0%) patients were categorized as normal, 87 (5.7%) as interstitial lung abnormality (ILA), and 20 (1.3%) as interstitial lung disease (ILD). • Both ILA and ILD groups were associated with poor recurrence-free survival (hazard ratio [HR], 1.81, p = .002; HR, 5.26, p < .001, respectively) and overall survival (HR, 2.13; p = .004; HR, 7.20; p < .001). • Both quantified fibrotic and non-fibrotic ILA components were associated with recurrence-free survival and overall survival in normal and ILA groups.

Application of computer-aided diagnosis for Lung-RADS categorization in CT screening for lung cancer: effect on inter-reader agreement.

OBJECTIVES: To evaluate the effects of computer-aided diagnosis (CAD) on inter-reader agreement in Lung Imaging Reporting and Data System (Lung-RADS) categorization. METHODS: Two hundred baseline CT scans covering all Lung-RADS categories were randomly selected from the National Lung Cancer Screening Trial. Five radiologists independently reviewed the CT scans and assigned Lung-RADS categories without CAD and with CAD. The CAD system presented up to five of the most risk-dominant nodules with measurements and predicted Lung-RADS category. Inter-reader agreement was analyzed using multirater Fleiss κ statistics. RESULTS: The five readers reported 139-151 negative screening results without CAD and 126-142 with CAD. With CAD, readers tended to upstage (average, 12.3%) rather than downstage Lung-RADS category (average, 4.4%). Inter-reader agreement of five readers for Lung-RADS categorization was moderate (Fleiss kappa, 0.60 [95% confidence interval, 0.57, 0.63]) without CAD, and slightly improved to substantial (Fleiss kappa, 0.65 [95% CI, 0.63, 0.68]) with CAD. The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% [201/371] vs. 63.6% [232/365]). The proportion of disagreement in nodule size measurement was reduced from 5.1% (102/2000) to 3.1% (62/2000) with the use of CAD (p < 0.001). In 31 cancer-positive cases, substantial management discrepancies (category 1/2 vs. 4A/B) between reader pairs decreased with application of CAD (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004). CONCLUSIONS: Application of CAD demonstrated a minor improvement in inter-reader agreement of Lung-RADS category, while showing the potential to reduce measurement variability and substantial management change in cancer-positive cases. KEY POINTS: • Inter-reader agreement of five readers for Lung-RADS categorization was minimally improved by application of CAD, with a Fleiss kappa value of 0.60 to 0.65. • The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% vs. 63.6%). • In 31 cancer-positive cases, substantial management discrepancies between reader pairs, referring to a difference in follow-up interval of at least 9 months (category 1/2 vs. 4A/B), were reduced in half by application of CAD (32/310 to 16/310) (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).

Identification of predictors for brain metastasis in newly diagnosed non-small cell lung cancer: a single-center cohort study.

OBJECTIVES: To identify clinical and staging chest CT characteristics predictive of brain metastasis in patients with newly diagnosed NSCLC dichotomized according to resectability. METHODS: Patients newly diagnosed with NSCLC of clinical stages II-IV between November 2017 and October 2018 were enrolled and classified into resectable (stage II+IIIA) and unresectable stages (stage IIIB/C+IV) according to chest CT. Associations of clinicopathological characteristics and CT findings with brain metastasis were analyzed using logistic regression. Predictive models were evaluated using receiver operating characteristics curve analysis. A subgroup analysis for unresectable-stage patients with known epidermal growth factor receptor gene (EGFR) mutation status was performed. RESULTS: This study included 911 NSCLC patients (mean age, 65 ± 11 years; 620 men), 194 of whom were diagnosed with brain metastasis. For resectable stages, independent predictors for brain metastasis were N2-stage (13 of 25 patients), absence of air-bronchogram/bubble lucency (23 of 25 patients), and presence of spiculation (15 of 25 patients), with a model combining the two imaging features showing an AUC of 0.723. In unresectable stages, independent predictors of brain metastasis were younger age, female sex, extrathoracic metastasis, and adenocarcinoma, with models combining these showing AUCs of 0.675-0.766. In the subgroup with known EGFR-mutation status, extrathoracic metastasis and positive EGFR mutation were independent predictors of brain metastasis, with the model showing AUCs of 0.641-0.732. CONCLUSION: CT-derived imaging features, clinical stages, lung cancer subtype, and EGFR mutation were associated with brain metastasis in patients with newly diagnosed NSCLC. The predictors were completely different between resectable and unresectable stages. KEY POINTS: • In resectable stages of NSCLC, two imaging features (absence of air-bronchogram/bubble lucency and presence of spiculation) and N2 stage were independent predictors of brain metastasis. • In unresectable stages of NSCLC, younger age, female sex, extrathoracic metastasis, and adenocarcinoma were associated with brain metastasis. • In the subgroup of NSCLC with known EGFR-mutation status, extrathoracic metastasis and positive EGFR mutation were independent predictors of brain metastasis.

Air embolism in CT-guided transthoracic needle biopsy: emphasis on pulmonary vein injury.

OBJECTIVE: To assess whether pulmonary vein injury is detectable on CT and associated with air embolism after percutaneous transthoracic needle biopsy (PTNB) in a tertiary referral hospital. METHODS: Between January 2012 and November 2021, 11,691 consecutive CT-guided PTNBs in 10,685 patients were retrospectively evaluated. Air embolism was identified by reviewing radiologic reports. Pulmonary vein injury was defined as the presence of the pulmonary vein in the needle pathway or shooting range of the cutting needle with the presence of parenchymal hemorrhage. The association between pulmonary vein injury and air embolism was assessed using logistic regression analysis in matched patients with and without air embolism with a ratio of 1:4. RESULTS: A total of 27 cases of air embolism (median age, 67 years; range, 48-80 years; 24 men) were found with an incidence of 0.23% (27/11,691). Pulmonary vein injury during the procedures was identifiable on CT in 24 of 27 patients (88.9%), whereas it was 1.9% (2/108) for matched patients without air embolism The veins beyond the target lesion (70.8% [17/24]) were injured more frequently than the veins in the needle pathway before the target lesion (29.2% [7/24]). In univariable and multivariable analyses, pulmonary vein injury was associated with air embolism (odds ratio, 485.19; 95% confidence interval, 68.67-3428.19, p <.001). CONCLUSION: Pulmonary vein injury was detected on CT and was associated with air embolism. Avoiding pulmonary vein injury with careful planning of the needle pathway on CT may reduce air embolism risk. KEY POINTS: • Pulmonary vein injury during CT-guided biopsy was identifiable on CT in most of the patients (88.9% [24/27]). • The veins beyond the target lesion (70.8% [17/24]) were injured more frequently than the veins in the needle pathway before the target lesion (29.2% [7/24]). • Avoiding the distinguishable pulmonary vein along the pathway or shooting range of the needle on CT may reduce the air embolism risk.

Utility of a Deep Learning Algorithm for Detection of Reticular Opacity on Chest Radiography in Patients With Interstitial Lung Disease.

BACKGROUND. Deep learning has been heavily explored for pulmonary nodule detection on chest radiographs. Detection of reticular opacity in interstitial lung disease (ILD) is challenging and may also benefit from a deep learning algorithm (DLA). OBJECTIVE. The purpose of this study was to evaluate the utility of a DLA for detection of reticular opacity on chest radiographs of patients with surgically confirmed ILD. METHODS. This retrospective study included 197 patients (130 men, 67 women; mean age, 62.6 ± 7.6 [SD] years) with surgically proven ILD between January 2017 and December 2018 who underwent preoperative chest radiography and chest CT within a 30-day interval. A total of 197 age- and sex-matched control patients with normal chest radiographs were randomly selected. A commercially available DLA was used to detect lower lobe or subpleural abnormalities; those matching the reticular opacity location on CT were deemed true-positive. Six readers (three thoracic radiologists, three residents) independently reviewed radiographs with and without the DLA for the presence of reticular opacity. Interobserver agreement was assessed. Diagnostic performance was compared among interpretations. Subanalysis was performed according to CT-based classification of the severity of reticular opacity. Performance of the DLA was also assessed on 102 chest radiographs from a second institution (51 patients with ILD, 51 matched patients in the control group). RESULTS. Interobserver agreement was moderate (κ = 0.517) for readers alone and almost perfect (κ = 0.870) for readers using the DLA. Sensitivity, specificity, and accuracy of the DLA for reticular opacity were 98.0%, 99.0%, and 98.5%; of pooled readers alone were 77.3%, 92.3%, and 84.8%; and of readers using the DLA were 93.8%, 97.3%, and 95.6%. All metrics were significantly better (all p ≤ .002) for the DLA and for readers using the DLA than for readers alone. Sensitivity for readers without and with the DLA were 66.7% and 86.8% for mild disease, 84.2% and 98.8% for moderate disease, and 87.3% and 100.0% for severe disease. The DLA had 100.0% accuracy at the second institution. CONCLUSION. The DLA outperformed readers in detection of reticular opacity, and use of the DLA improved reader performance and interobserver agreement. The benefit of the DLA was more notable in sensitivity than in specificity and was maintained in mild disease. CLINICAL IMPACT. Use of the DLA may facilitate detection of reticular opacity on chest radiographs in the early stages of ILD.

Impact of Brain MRI on the Diagnosis of Infective Endocarditis and Treatment Decisions: Systematic Review and Meta-Analysis.

BACKGROUND. Despite increasing use of brain MRI to evaluate patients with suspected infective endocarditis, the clinical impact of brain MRI in this setting has not yet been systematically reviewed. OBJECTIVE. The purpose of this study was to evaluate the frequency of brain MRI findings in patients with suspected or confirmed infective endocarditis and to determine the impact of such findings on clinical decisions. EVIDENCE ACQUISITION. A systematic search of the PubMed, Embase, and Cochrane databases was performed from January 1, 1990, to December 31, 2020, to identify original research investigations of brain MRI in patients with suspected or confirmed infective endocarditis. Study quality was assessed with QUADAS-2. Study endpoints included the frequency of brain MRI findings and the frequency of diagnostic modifications, modification of therapeutic plan, and modification of valve surgery plan resulting from MRI findings. Frequencies were pooled by means of the inverse variance method. Subgroup analysis was performed. EVIDENCE SYNTHESIS. A total of 21 studies with 2133 patients were included. Overall study quality was considered moderate. In terms of brain MRI findings, the pooled frequency of acute ischemic lesions was 61.9% (95% CI, 50.7-71.9%); of cerebral microbleeds, 52.9% (95% CI, 41.6-63.9%); hemorrhagic lesions, 24.7% (95% CI, 15.1-37.9%); abscess or meningitis, 9.5% (95% CI, 5.6-15.6%); and intracranial mycotic aneurysm, 6.2% (95% CI, 4.0-9.4%). Subgroup analysis after exclusion of three studies in which neurologic findings were the indication for all brain MRI examinations yielded similar frequencies of these findings. Six studies included results on the impact of brain MRI findings on clinical decisions. The frequencies of diagnostic modifications in two studies were 5.4% and 32.1%. The pooled frequency of therapeutic plan modification in six studies was 12.8% (95% CI, 6.5-23.7%) and of surgical plan modification in five studies was 14.2% (95% CI, 8.2-23.4%). CONCLUSION. In patients with suspected or confirmed infective endocarditis, brain MRI examinations commonly show relevant abnormalities that affect diagnostic and therapeutic clinical decisions. CLINICAL IMPACT. The findings support a potential role for screening brain MRI in the evaluation of patients with suspected or confirmed infective endocarditis, regardless of the presence or absence of neurologic symptoms.

Volume Doubling Times of Pulmonary Metastases in Patients With Bone and Soft-Tissue Sarcomas: Associations With Subsequent New Metastases and Survival After Metastasectomy.

BACKGROUND. Pulmonary metastases of bone and soft-tissue sarcoma are common and have a high recurrence rate after metastasectomy. Factors associated with postmetastasectomy recurrence are not well studied. OBJECTIVE. The purpose of this study was to investigate the association of the volume doubling time (VDT) of pulmonary metastases with the subsequent development of new pulmonary nodules and survival after metastasectomy in patients with bone or soft-tissue sarcoma. METHODS. This retrospective study included patients with bone or soft-tissue sarcoma who, between January 2010 and December 2020, underwent first complete metastasectomy of pulmonary nodules visualized on two sequential preoperative CT scans. Semiautomatic volumetric segmentation of the pulmonary metastases was performed on the two CT scans, and VDTs were calculated. VDT was compared between patients with and without subsequent new metastases after metastasectomy. Cox proportional hazards regression analyses were performed to determine risk factors for recurrence-free survival (RFS) after metastasectomy and for postmetastasectomy overall survival (OS). RESULTS. Forty patients (21 women, 19 men; mean age, 51.1 ± 14.3 [SD] years) were included. Of these patients, 23 (57.5%) developed new metastatic nodules after metastasectomy, and 10 (25.0%) died during follow-up. Median VDT was shorter in patients with, versus those without, new metastases after metastasectomy (56 vs 140 days, p = .002). Only four of 23 patients with new metastases had VDT of 140 days or more. In multivariable analysis, older age (hazard ratio [HR], 1.06; p = .004), female sex (HR, 2.80; p = .03), and VDT less than 140 days (HR, 4.22; p = .01) were independent predictors of worse RFS. Also in multivariable analysis, only older age (HR, 1.17; p = .005) and VDT less than 50 days (HR, 8.60; p = .02) were independent predictors of worse OS. OS was significantly worse in patients with VDT less than 140 days (10 deaths among 27 patients) than in patients with VDT of 140 days or more (no deaths in 13 patients) (p = .01). CONCLUSION. In patients with bone and soft-tissue sarcoma, shorter VDT of pulmonary metastases is independently associated with subsequent new metastases after metastasectomy and worse OS. CLINICAL IMPACT. VDT of pulmonary nodules may be considered in patient selection for pulmonary metastasectomy and in postoperative patient management.

Use of a Commercially Available Deep Learning Algorithm to Measure the Solid Portions of Lung Cancer Manifesting as Subsolid Lesions at CT: Comparisons with Radiologists and Invasive Component Size at Pathologic Examination.

Background The solid portion size of lung cancer lesions manifesting as subsolid lesions is key in their management, but the automatic measurement of such lesions by means of a deep learning (DL) algorithm needs evaluation. Purpose To evaluate the performance of a commercially available DL algorithm for automatic measurement of the solid portion of surgically proven lung adenocarcinomas manifesting as subsolid lesions. Materials and Methods Surgically proven lung adenocarcinomas manifesting as subsolid lesions on CT images between January 2018 and December 2018 were retrospectively included. Five radiologists independently measured the maximal axial diameter of the solid portion of lesions. The DL algorithm automatically segmented and measured the maximal axial diameter of the solid portion. Reader measurements, software measurements, and invasive component size at pathologic examination were compared by using intraclass correlation coefficient (ICC) and Bland-Altman plots. Results A total of 448 patients (mean age, 63 years ± 10 [standard deviation]; 264 women) with 448 lesions were evaluated (invasive component size, 3-65 mm). The measurement agreements between each radiologist and the DL algorithm were very good (ICC range, 0.82-0.89). When a radiologist was replaced with the DL algorithm, the ICCs ranged from 0.87 to 0.90, with an ICC of 0.90 among five radiologists. The mean difference between the DL algorithm and each radiologist ranged from -3.7 to 1.5 mm. The widest 95% limit of agreement between the DL algorithm and each radiologist (-15.7 to 8.3 mm) was wider than pairwise comparisons of radiologists (-7.7 to 13.0 mm). The agreement between the DL algorithm and invasive component size at pathologic evaluation was good, with an ICC of 0.67. Measurements by the DL algorithm (mean difference, -6.0 mm) and radiologists (mean difference, -7.5 to -2.3 mm) both underestimated invasive component size. Conclusion Automatic measurements of solid portions of lung cancer manifesting as subsolid lesions by the deep learning algorithm were comparable with manual measurements and showed good agreement with invasive component size at pathologic evaluation. © RSNA, 2021 Online supplemental material is available for this article.

Histogram analysis of arterial spin labeling perfusion data to determine the human papillomavirus status of oropharyngeal squamous cell carcinomas.

PURPOSE: To evaluate the correlation between histogram parameters derived from pseudo-continuous arterial spin labeling (PCASL) and human papillomavirus (HPV) status in patients with oropharyngeal squamous cell carcinoma (OPSCC). METHODS: This study included a total of 58 patients (HPV-positive: n = 45; -negative: n = 13) from a prospective cohort of consecutive patients aged ≥ 18 years, who were newly diagnosed with oropharyngeal squamous cell carcinoma. All patients were required to have undergone pre-treatment MRI with PCASL to measure regional perfusion. The region of interest was drawn by two radiologists, encompassing the entire tumor volume on all corresponding slices. Differences in the histogram parameters derived from tumor blood flow (TBF) in ASL were assessed for HPV-positive and -negative patients. Receiver operating characteristic curve analysis was performed to determine the best differentiating parameters, and a leave-one-out cross-validation was used. RESULTS: Patients with HPV-positive OPSCC showed a significantly lower overall standard deviation and 95th percentile value of tumor blood flow (P < .007). The standard deviation of TBF was the single best predictive parameter. Leave-one-out cross-validation tests revealed that the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.745, 75.9%, 75.6%, and 76.9%, respectively. CONCLUSION: PCASL revealed differences in perfusion parameters according to HPV status in patients with OPSCC, reflecting their distinct histopathology.

Tailored antiplatelet agent medication in clopidogrel hyporesponsive patients before stent-assisted coiling: single-center experience.

PURPOSE: In patients requiring stent procedures, resistance or hyperresponsiveness to antiplatelet medications is often observed. This study aims to evaluate the efficacy and safety of tailoring medications in these patients. METHODS: This retrospective study included 223 patients who underwent endovascular treatment for intracranial aneurysm between October 2018 and October 2019. Patients were categorized as hyporesponsive, hyperresponsive, and normoresponsive groups according to the initial PRU response. For the hypo- or hyperresponders, we tailored medication by modifying the dose or changing the drug. PRUs before and after tailoring were compared in each group. PRU reponses in patients who underwent Cytochrome P450 2C19 (CYP2C19) genotyping were also determined. RESULTS: Of the 73 clopidogrel-resistant patients, the mean PRU values after tailoring showed a greater decrease in the group that switched to prasugrel (n = 56), from 223 to 131, than in the clopidogrel reloading group (n = 17), from 238 to 209. In 31 hyperresponders, PRU increased from 49 to 94 after the dose adjustment. CYP2C19 genotyping showed that PRU tended to increase as the number of mutated alleles increased. There were five (2.3%) ischemic events (three transient ischemic attacks and two minor strokes) in a mean follow-up of 8 months, but no hemorrhage. CONCLUSIONS: The stent-assisted coiling was successfully performed with acceptable range of ischemic events and without hemorrhage in all patients, including those who applied tailored medication. Low-dose prasugrel was effective for obtaining appropriate PRU values for initial medication as well as for clopidogrel-resistant patients. The genetic test did not provide reliable results in determining clopidogrel resistance.

Deep Learning-Based CT Reconstruction Kernel Conversion in the Quantification of Interstitial Lung Disease: Effect on Reproducibility.

RATIONALE AND OBJECTIVES: The effect of different computed tomography (CT) reconstruction kernels on the quantification of interstitial lung disease (ILD) has not been clearly demonstrated. The study aimed to investigate the effect of reconstruction kernels on the quantification of ILD on CT and determine whether deep learning-based kernel conversion can reduce the variability of automated quantification results between different CT kernels. MATERIALS AND METHODS: Patients with ILD or interstitial lung abnormality who underwent noncontrast high-resolution CT between June 2022 and September 2022 were retrospectively included. Images were reconstructed with three different kernels: B30f, B50f, and B60f. B60f was regarded as the reference standard for quantification, and B30f and B50f images were converted to B60f images using a deep learning-based algorithm. Each disease pattern of ILD and the fibrotic score were quantified using commercial software. The effect of kernel conversion on measurement variability was estimated using intraclass correlation coefficient (ICC) and Bland-Altman method. RESULTS: A total of 194 patients were included in the study. Application of different kernels induced differences in the quantified extent of each pattern. Reticular opacity and honeycombing were underestimated on B30f images and overestimated on B50f images. After kernel conversion, measurement variability was reduced (mean difference, from -2.0 to 3.9 to -0.3 to 0.4%, and 95% limits of agreement [LOA], from [-5.0, 12.7] to [-2.7, 2.1]). The fibrotic score for converted B60f from B50f images was almost equivalent to the original B60f (ICC, 1.000; mean difference, 0.0; and 95% LOA [-0.4, 0.4]). CONCLUSION: Quantitative CT analysis of ILD was affected by the application of different kernels, but deep learning-based kernel conversion effectively reduced measurement variability, improving the reproducibility of quantification.

Reference ranges of computed tomography-derived strains in four cardiac chambers.

Research on cardiovascular diseases using CT-derived strain is gaining momentum, yet there is a paucity of information regarding reference standard values beyond echocardiography, particularly in cardiac chambers other than the left ventricle (LV). We aimed to compile CT-derived strain values from the four cardiac chambers in healthy adults and assess the impact of age and sex on myocardial strains. This study included 101 (mean age: 55.2 ± 9.0 years, 55.4% men) consecutive healthy individuals who underwent multiphase cardiac CT. CT-derived cardiac strains, including LV global and segmental longitudinal, circumferential, and transverse strains, left atrial (LA), right atrial (RA), and right ventricle (RV) strains were measured by the commercially available software. Strain values were classified and compared by their age and sex. The normal range of CT-derived LV global longitudinal strain (GLS), global circumferential strain (GCS), and global radial strain (GRS) were -20.2 ± 2.7%, -27.9 ± 4.1%, and 49.4 ± 12.1%, respectively. For LA, reservoir strain, pump strain, and conduit strain were 28.6 ± 8.5%, 13.2 ± 6.4%, and 15.5 ± 8.6%, respectively. The GLS of RA and RV were 27.9 ± 10.9% and -22.0 ± 5.7%, respectively. The absolute values of GLS of RA and RV of women were higher than that in men (32.4 ± 11.4 vs. 24.3 ± 9.1 and -25.2 ± 4.7 vs. -19.4 ± 5.0, respectively; p<0.001, both). Measurement of CT-derived strain in four cardiac chambers is feasible. The reference ranges of CT strains in four cardiac chambers can be used for future studies of various cardiac diseases using the cardiac strains.

Usefulness of CT Quantification-Based Assessment in Defining Progressive Pulmonary Fibrosis.

RATIONALE AND OBJECTIVES: To establish a quantitative CT threshold for radiological disease progression of progressive pulmonary fibrosis (PPF) and evaluate its feasibility in patients with connective tissue disease-related interstitial lung disease (CTD-ILD). MATERIALS AND METHODS: Between April 2007 and October 2022, patients diagnosed with CTD-ILD retrospectively evaluated. CT quantification was conducted using a commercial software by summing the percentages of ground-glass opacity, consolidation, reticular opacity, and honeycombing. The quantitative threshold for radiological progression was determined based on the highest discrimination on overall survival (OS). Two thoracic radiologists independently evaluated visual radiological progression, and the senior radiologist's assessment was used as the final result. Cox regression was used to assess prognosis of PPF based on the visual assessment and quantitative threshold. RESULTS: 97 patients were included and followed up for a median of 30.3 months (range, 4.7-198.1 months). For defining radiological disease progression, the optimal quantitative CT threshold was 4%. Using this threshold, 12 patients were diagnosed with PPF, while 14 patients were diagnosed with PPF based on the visual assessment, with an agreement rate of 97.9% (95/97). Worsening respiratory symptoms (hazard ratio [HR], 12.73; P < .001), PPF based on the visual assessment (HR, 8.86; P = .002) and based on the quantitative threshold (HR, 6.72; P = .009) were independent risk factors for poor OS. CONCLUSION: The quantitative CT threshold for radiological disease progression (4%) was feasible in defining PPF in terms of its agreement with PPF grouping and prognostic performance when compared to visual assessment.

Efficacy and safety of transcatheter arterial embolization for hemodynamically unstable bleeding after percutaneous transthoracic needle biopsy.

PURPOSE: To evaluate the safety and efficacy of transcatheter arterial embolization (TAE) in controlling hemodynamically unstable bleeding following a percutaneous transthoracic needle biopsy (PTNB). METHODS: A total of seven patients (four men and three women; mean age, 62 ± 12 years) who received TAE for post-PTNB bleeding between May 2007 and March 2022 were included. The observed types of bleeding were hemothorax (n = 3), hemoptysis (n = 2), and a combination of both (n = 2). In patients with active bleeding, the technical success of TAE was defined as superselective embolization of the target artery with no active bleeding visible on post-TAE angiography. Clinical success was defined as sustained cessation of bleeding without hemodynamic instability, requirement of repeat TAE, or the need for post-TAE hemostatic surgery during the initial admission. The metrics analyzed included technical and clinical success rates, complications, and 30-day mortality. RESULTS: All seven patients achieved technical success, with a clinical success rate of 86% (6/7). Six patients were discharged alive, while one patient died of respiratory failure accompanied by hemothorax 19 days post-biopsy. The angiographic findings associated with bleeding were contrast media extravasation or pseudoaneurysm (n = 3) and vascular hypertrophy with tortuosity (n = 2). The implicated bleeding arteries included the intercostal artery (n = 2), bronchial artery (n = 2), and internal thoracic artery (n = 1). In two cases, no clear bleeding foci were identified; nonetheless, prophylactic embolization was performed on the right intercostal artery (n = 1) and right intercostobronchial trunk (n = 1). The embolic agents utilized included microcoils (n = 1), gelatin sponge particles (n = 2), polyvinyl alcohol (PVA) with gelatin sponge particles (n = 1), PVA with microcoils (n = 1), microcoils with gelatin sponge particles (n = 1), and microcoils with n-butyl-2-cyanoacrylate and gelatin sponge particles (n = 1). The 30-day mortality rate was 14% (1/7). No ischemic complications related to TAE were observed. CONCLUSION: The study suggests that TAE is safe and effective for controlling hemodynamically unstable bleeding following a PTNB.

Evaluation of Chylothorax Using Dynamic Contrast-Enhanced Magnetic Resonance Lymphangiography After Lung Cancer Surgery.

Background: To determine the role of dynamic contrast-enhanced magnetic resonance lymphangiography (DCMRL) in the management of postoperative chylothorax after lung cancer surgery. Methods and Results: Between July 2017 and November 2021, patients who developed postoperative chylothorax following pulmonary resection and mediastinal lymph node dissection were assessed and those who underwent DCMRL for the evaluation of chyle leak were evaluated. The findings of DCMRL and conventional lymphangiography were compared. The incidence of postoperative chylothorax was 0.9% (50/5587). Among the patients with chylothorax, a total of 22 patients (44.0% [22/50]; mean age, 67.6 ± 7.9 years; 15 men) underwent DCMRL. Treatment outcomes were compared between patients with conservative management (n = 10) and those with intervention (n = 12). The patients demonstrated unilateral pleural effusion, ipsilateral to the operation site, and showed right-sided dominance. The most frequent site of thoracic duct injury showing contrast media leakage was visualized at the subcarinal level. No DCMRL-related complication occurred. DCMRL showed comparable performance to conventional lymphangiography in visualizing the central lymphatics, including cisterna chyli (DCMRL vs. conventional lymphangiography, 72.7% vs. 45.5%, p = 0.25) and thoracic duct (90.9% vs. 54.5%, p = 0.13), and in localizing thoracic duct injury (90.9% vs. 54.5%, p = 0.13). On follow-up, the amount of chest tube drainage after lymphatic intervention showed a significant difference over time from that after medical treatment only (p = 0.02). Conclusion: DCMRL can provide detailed information about the leak site and the central lymphatic anatomy in patients with chylothorax after lung cancer surgery. The findings of DCMRL can guide subsequent treatment planning for optimal outcomes.

Dynamic Contrast-Enhanced Magnetic Resonance Lymphangiography and Lymphatic Interventions for Pediatric Patients with Various Lymphatic Diseases.

Background: To demonstrate the magnetic resonance lymphangiography (MRL) imaging findings of lymphatic diseases and the clinical outcomes of lymphatic embolization in pediatric patients. Methods and Results: This retrospective study included 10 consecutive pediatric patients who underwent MRL for lymphatic diseases between June 2017 and June 2021. Nine patients underwent dynamic contrast-enhanced MRL with bilateral inguinal lymph node injection of diluted gadolinium, and one patient underwent nonenhanced MRL with a heavily T2-weighted image. The etiology of lymphatic disease was classified into three categories based on the magnetic resonance findings. The resolution of chylous fluid and weight-adjusted amounts of chylous fluid collected from a drainage tube were evaluated as outcomes. Patients were classified as postoperative lymphatic leak (n = 3), pulmonary lymphatic perfusion syndrome (n = 3), central lymphatic flow disorder (CLFD; n = 3), and primary lymphatic dysfunction (Gorham-Stout syndrome; n = 1). Three patients underwent radiological lymphatic intervention, and one CLFD patient underwent surgical intervention. In patients with postoperative lymphatic leak, the median chest tube drainage decreased significantly after the intervention [from 87.9 to 12.4 mL/(kg·d); p = 0.02]. However, in one CLFD patient, the amount of chylous fluid did not decrease until 7 days after intervention. Conclusion: The etiology of lymphatic disease in pediatrics can be recognized on MRL, and lymphatic intervention can be performed for cessation of lymphatic leak, even though the treatment outcomes may differ according to the underlying etiology. MRL can play an important role in classifying lymphatic disease, and in planning treatment on the basis of the lymphatic anatomy and underlying etiology.