Artificial intelligence-based radiomics for the prediction of nodal metastasis in early-stage lung cancer.

We aimed to investigate the value of computed tomography (CT)-based radiomics with artificial intelligence (AI) in predicting pathological lymph node metastasis (pN) in patients with clinical stage 0-IA non-small cell lung cancer (c-stage 0-IA NSCLC). This study enrolled 720 patients who underwent complete surgical resection for c-stage 0-IA NSCLC, and were assigned to the derivation and validation cohorts. Using the AI software Beta Version (Fujifilm Corporation, Japan), 39 AI imaging factors, including 17 factors from the AI ground-glass nodule analysis and 22 radiomics features from nodule characterization analysis, were extracted to identify factors associated with pN. Multivariate analysis showed that clinical stage IA3 (p = 0.028), solid-part size (p < 0.001), and average solid CT value (p = 0.033) were independently associated with pN. The receiver operating characteristic analysis showed that the area under the curve and optimal cut-off values of the average solid CT value relevant to pN were 0.761 and -103 Hounsfield units, and the threshold provided sensitivity, specificity, and negative predictive values of 69%, 65%, and 94% in the entire cohort, respectively. Measuring the average solid-CT value of tumors for pN may have broad applications such as guiding individualized surgical approaches and postoperative treatment.

Radiomics with Artificial Intelligence for the Prediction of Early Recurrence in Patients with Clinical Stage IA Lung Cancer.

BACKGROUND: We seek to explore the ability of computed tomography (CT)-based radiomics coupled with artificial intelligence (AI) to predict early recurrence (< 2 years after surgery) in patients with clinical stage 0-IA non-small cell lung cancer (c-stage 0-IA NSCLC). PATIENTS AND METHODS: Data of 642 patients were collected for early recurrence and assigned to the derivation and validation cohorts at a ratio of 2:1. Using the AI software Beta Version (Fujifilm Corporation, Japan), 39 AI imaging factors, including 17 factors from the AI ground-glass nodule analysis and 22 radiomic features from nodule characterization analysis, were extracted. RESULTS: Multivariate analysis showed that male sex (p = 0.016), solid part size (p < 0.001), CT value standard deviation (p = 0.038), solid part volume ratio (p = 0.016), and bronchus translucency (p = 0.007) were associated with recurrence-free survival (RFS). Receiver operating characteristics analysis showed that the area under the curve and optimal cutoff values relevant to recurrence were 0.707 and 1.49 cm for solid part size, and 0.710 and 22.9% for solid part volume ratio, respectively. The 5-year RFS rates for patients in the validation set with solid part size ≤ 1.49 cm and > 1.49 cm were 92.2% and 70.4% (p < 0.001), whereas those for patients with solid part volume ratios ≤ 22.9% and > 22.9% were 97.8% and 71.7% (p < 0.001), respectively. CONCLUSIONS: CT-based radiomics coupled with AI contributes to the noninvasive prediction of early recurrence in patients with c-stage 0-IA NSCLC.

Middle mesenteric artery: Angiographic and three-dimensional computed tomography findings.

The middle mesenteric artery, also known as the third mesenteric artery, is a very rare anomaly. Several anatomical variations of middle mesenteric artery have been reported; in these reports, the right colic artery and/or middle colic artery often originate directly from the aorta. Here, we report a middle mesenteric artery in which the middle colic artery originated directly from the abdominal aorta. We also provide three-dimensional computed tomography and angiography findings and discuss anatomical and embryological considerations.

Magnetic Resonance Imaging of Orbital Solitary Fibrous Tumors: Radiological-Pathological Correlation Analysis.

BACKGROUND: Solitary fibrous tumors (SFTs) are rare and can be misdiagnosed because of their various radiological appearances. PURPOSE: To clarify the characteristic MRI findings of SFTs by analyzing their radiological-pathological correlation. MATERIAL AND METHODS: Nine consecutive patients with SFT who underwent magnetic resonance imaging (MRI) prior to surgery were analyzed. Eight patients underwent contrast-enhanced MRI, and three underwent dynamic MRI. Radiological-pathological correlation analysis, co-occurrence matrix, run-length matrix, and histogram analysis were performed to assess the relationship between pathological findings T1- and T2-weighted images (T1-WI and T2-WI). RESULTS: All nine lesions ranged in size from 20 to 36 mm. Seven lesions were located in the superior portion of the retrobulbar space found outside of the muscle cone, and two lesions in the inferior portion were located within it. No significant correlation was observed between the amount of collagenous tissue and the qualitative evaluation of the signal on T1-WI and T2-WI. Kurtosis on T2-WI was significantly correlated with the amount of collagenous tissue (ρ = -0.97, p < 0.0001) and endothelial cells (ρ = -0.49, p = 0.0479). CONCLUSION: Kurtosis in the histogram analysis on T2WI showed a strong correlation with the amount of collagenous tissue.

Profiles of Lung Adenocarcinoma With Multiple Ground-Glass Opacities and the Fate of Residual Lesions.

BACKGROUND: We aimed to clarify clinical profiles of patients with adenocarcinoma presenting as multifocal ground-glass opacities (MGGOs) to assess their prognosis and the optimal management method for residual satellite lesions. METHODS: We identified 190 patients with cN0 MGGOs (MGGO cohort) and 1426 patients with solitary lung adenocarcinoma (control cohort) who underwent complete resection between 2004 and 2016. Propensity score matching was performed to adjust for differences in baseline characteristics of both cohorts for survival analyses. MGGOs consist of a main tumor and satellite lesions and were subdivided into 3 groups: the PG group, with multifocal pure GGOs; the GD group, in which the main tumor presented as GGO dominant; and the SD group, where the main tumor presented as solid dominant. RESULTS: No significant differences in recurrence-free survival were observed between the 2 cohorts before and after the propensity score matching. For patients with MGGOs, 22 were in the PG group, 47 in the GD group, and 121 in the SD group. Type of MGGOs was a significant factor for recurrence-free survival recurrence-free survival both in the entire population (SD vs PG-GD, P = .008) and in p-stage I cohorts (P = .004) on multivariable analysis. Among 116 patients (61.1%) with residual satellite lesions, 38 patients had progressed lesions and 69 stable lesions. Although the emergence of new lesions during the follow-up period was an independent predictor for satellite lesion progression, neither progressed lesions nor the emergence of new lesions influenced survival. CONCLUSIONS: Patients with MGGOs and solitary adenocarcinoma had a similar prognosis. The biologic behavior of main tumors dominates clinical outcomes in patients with MGGOs.

Association between F-18 fluorodeoxyglucose uptake of noncancerous lung area and acute exacerbation of interstitial pneumonia in patients with lung cancer after resection.

BACKGROUND: Idiopathic pulmonary fibrosis is defined as a specific form of progressive fibrosing interstitial pneumonia. Postoperative acute exacerbation is considered a lethal comorbidity for patients with lung cancer, particularly when it is accompanied with idiopathic pulmonary fibrosis. Thus, pretherapeutic risk stratification for acute exacerbation has been anticipated. In this study, we aimed to investigate whether the maximum standardized uptake value of F-18 fluorodeoxyglucose is useful for assessing the postoperative risk of acute exacerbation and severe respiratory adverse events in patients with lung cancer after surgical resection. METHODS: A total of 822 patients with lung cancer who underwent preoperative high-resolution computed tomography, fluorodeoxyglucose-positron emission tomography/computed tomography, and pulmonary resection between July 2012 and July 2018 were assessed. Maximum standardized uptake value of the main tumor and that of the noncancerous lung area were measured using a 3-dimensional workstation. Multivariable analyses for acute exacerbation and severe respiratory adverse events were performed using the logistic regression model. RESULTS: Among all patients, 120 (14.6%) had idiopathic pulmonary fibrosis findings on high-resolution computed tomography whereas severe respiratory adverse events were observed in 35 (4.2%) patients, including those with acute exacerbation (n = 15, 1.8%). Maximum standardized uptake value of the main tumor and that of the noncancerous lung area were independently associated with both acute exacerbation and severe respiratory adverse events on multivariable analysis, both in all patients and in the 120 patients with idiopathic pulmonary fibrosis. Risk stratification analysis showed that 19.0% and 30.2% of patients who were positive for idiopathic pulmonary fibrosis on high-resolution computed tomography and with a maximum standardized uptake value of the main tumor and that of the noncancerous lung area 1.69 or greater (the optimal cutoff value relevant to acute exacerbation) experienced acute exacerbation and severe respiratory adverse events, respectively. CONCLUSIONS: Maximum standardized uptake value of the main tumor and that of the noncancerous lung area were independently associated with the incidence of postoperative acute exacerbation and severe respiratory adverse events in patients with lung cancer.

Computed Tomography Histogram Approach to Predict Lymph Node Metastasis in Patients With Clinical Stage IA Lung Cancer.

BACKGROUND: Quantitative computed tomography (CT) histogram analysis of tumors is reported to help distinguish between invasive and less invasive lung cancers. This study aimed to clarify whether CT histogram analysis of tumors can be used to classify patients with clinical stage 0 to IA non-small cell lung cancer according to pathologic lymph node (pN) status. METHODS: Predictive factors associated with pN metastasis were identified from the derivation dataset including 629 patients with clinical stage 0 to IA non-small cell lung cancer who underwent complete resection with lymph node dissection (surgeries between 2008 and 2013). The validation dataset including 238 patients (surgeries between 2014 and 2015) were subsequently reevaluated. Clinicosurgical factors, including CT histogram analysis of tumors (CT value percentiles 2.5, 25, 50, 75, and 97.5, skewness, and kurtosis) were assessed. RESULTS: Seventy-three patients (12%) in the derivation cohort and 35 patients (15%) in the validation cohort had positive nodes. The pN status significantly affected survival in the entire population: 5-year overall survival of 93.1% vs 71.1% and 5-year disease-free survival of 85.9% vs 43.1% for negative vs positive (both P < .001). On multivariate analysis in the derivation cohort, the 75th percentile CT value (P < .001), age (P = .003), and comorbidities (P = .006) were significantly associated with pN metastasis. The area under the curve and the cutoff level of the 75th percentile CT value relevant to pN metastasis were 0.729 and 1.5 HU, respectively, and the threshold value provided accuracy of 71% for the validation cohort. CONCLUSIONS: Histogram analysis of CT imaging metrics of tumors contributes to noninvasive prediction of pN metastasis in patients with clinical stage 0 to IA non-small cell lung cancer.

Predictive accuracy of lepidic growth subtypes in early-stage adenocarcinoma of the lung by quantitative CT histogram and FDG-PET.

OBJECTIVES: The aim of this study was to analyze the accuracy of computed tomography (CT) and F-18 fluorodeoxyglucose-positron emission tomography/CT (FDG-PET/CT) to distinguish lepidic growth adenocarcinoma (LGA), including adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and lepidic-predominant adenocarcinoma, all of which have favorable survival outcomes, from the more aggressive and invasive non-LGA subtypes. MATERIALS AND METHODS: We identified 225 patients with c-0/I adenocarcinoma of the lung who underwent PET/CT and 3DCT followed by complete resection. Maximum standardized uptake values (SUVmax) of FDG and several histogram parameters were analyzed. Histological grades were classified according to the predominant subtype (G1: lepidic; G3: micropapillary or solid; and G2: subtypes other than G1/G3). RESULTS: The proportion of pathological invasive factors (lymphatic vessel involvement/blood vessel invasion/pleural invasion/lymph node metastasis) of patients with preinvasive adenocarcinoma, G1, G2, and G3 tumors were 0%, 3.6%, 48.0%, and 100%, respectively; p < 0.001). Multivariate analysis with CT-related parameters demonstrated that 75th percentile CT attenuation value (75th%, p < 0.001) and maximum CT attenuation value (maxCT, p = 0.009) were associated with incidence of non-LGA, whereas the value of SUVmax demonstrated a significant correlation (p < 0.001). When all patients were dichotomized according to ground-glass opacities (GGO)/solid-dominancy for CT maximum diameter, a significant correlation with non-LGA was shown in patients with solid-dominant tumor on SUVmax (p < 0.001) and with GGO-dominant tumor on 75th% (p = 0.006) and maxCT (p = 0.007). The combination of one of the two significant histogram parameters and SUVmax revealed higher predictive performance for pathological high malignant features (positive pathological invasive factors, non-LGA, and the highly malignant subtype covering G2 with moderately or poorly-differentiated carcinoma and G3) than the individual use of either factor. CONCLUSION: The 75th%, maxCT, and SUVmax were highly useful in distinguishing LGA from non-LGA in c-0/I adenocarcinoma.

Prognostic impact of the integration of volumetric quantification of the solid part of the tumor on 3DCT and FDG-PET imaging in clinical stage IA adenocarcinoma of the lung.

OBJECTIVES: The aim of this study was to conduct comparative analyses of the biological malignant potential of clinical stage IA adenocarcinoma using positron emission tomography/computed tomography (PET/CT), high-resolution CT (HRCT), and three-dimensional CT (3DCT). The predictive performance of these parameters was evaluated in terms of clinical outcomes and pathological invasiveness (positive lymphatic permeation, blood-vessel invasion, pleural invasion, and lymph-node metastasis). MATERIALS AND METHODS: We enrolled 170 patients with c-IA adenocarcinoma who underwent PET/CT, HRCT, and 3D reconstruction of lung structures using the Synapse Vincent system (Fujifilm Corporation, Tokyo, Japan) followed by complete resection. Maximum standardized uptake values (SUVmax) of F18-fluorodeoxyglucose and the size and volume of the solid part of the tumor were quantified and analyzed in relation to surgical outcomes. RESULTS: Univariate analysis demonstrated that all the three parameters and whole-tumor volume were associated with unfavorable disease-free survival (DFS), while the volume of the solid part was the independent predictor on multivariate analysis (p < .001). The receiver operating characteristic curves for pathological invasiveness, determined using the variables dichotomized at each cut-off level (SUVmax 2.4; solid-part size 1.23 cm; solid-part volume 779 mm3), showed that all were significantly correlated with pathological invasiveness and prognosis, whereas the combination of SUVmax and the solid-part volume was the most powerful predictor of survival and pathological invasiveness compared to any other parameters: the 4-year DFS and proportion of pathological invasiveness in patients with SUVmax > 2.4 and solid-part volume > 779 mm3 versus those with SUVmax ≤ 2.4 or solid-part volume ≤779 mm3 were 81.2% versus 98.3% (p < .001) and 84.3% versus 15.1% (p < .001), respectively. CONCLUSION: In c-IA adenocarcinoma, the volume of the solid part of the tumor was the independent predictor for unfavorable DFS, and the integration of the volume of the solid part and SUVmax was highly beneficial for the prediction of survival and pathological invasiveness.

Prognostic value of tumor solid-part size and solid-part volume in patients with clinical stage I non-small cell lung cancer.

BACKGROUND: This study aimed to predict the malignant potential of clinical stage I non-small cell lung cancer (c-I NSCLC) by semiautomatic three-dimensional (3D) volumetric measurement of a tumor (3D-data) and the axial computed tomography (CT) data derived from a 3D volumetric dataset (2D-data). The predictive performance was evaluated in terms of overall survival (OS), disease-free survival (DFS), and pathological invasive factors (positive lymphatic invasion, blood vessel invasion, pleural invasion, or lymph node metastasis). METHODS: We identified 252 patients (122 male; mean age, 68 years; range, 23-84 years) with c-I NSCLC who underwent high resolution CT and reconstruction of 3D imaging, followed by complete resection between January 2012 and December 2015. In this study, 2D-data including whole tumor size (WTS) and solid-part size (SPS) and 3D-data including whole tumor volume (WTV) and solid-part volume (SPV) acquired by a 3D volume rendering software were analyzed. RESULTS: The area under the receiver operating characteristic (ROC) curve for WTS, SPS, WTV, SPV relevant to recurrence was 0.667, 0.727, 0.654, and 0.751 while analyses of ROC curves revealed optimal WTS, SPS, WTV, and SPV cut-off values to predict recurrence of 2.48 cm, 2.03 cm, 3,258 mm3 and 1,889 mm3, respectively. The association between SPS and SPV was the coefficient of determination (R 2) =0.59. Multivariate analysis showed that SPV >1,889 mm3 (P=0.016) and male (P=0.041) were significant predictors of OS whereas SPV >1,889 mm3 (P=0.001), male (P=0.003), and the serum carcinoembryonic antigen value (P=0.041) were significantly correlated with DFS. SPS, SPV as well as the combination of SPS and SPV were all significantly correlated with the prediction of OS and DFS, and the incidence of pathological invasive factors. CONCLUSIONS: SPV and the integrated use of SPS and SPV was highly beneficial for the prediction of postoperative prognosis in c-I NSCLC.