Guidelines for Management of Incidental Pulmonary Nodules Detected on CT Images: From the Fleischner Society 2017

Quantitative features can predict further growth of persistent pure ground-glass nodule

Background

To evaluate whether quantitative features of persistent pure ground-glass nodules (PGGN) on the initial computed tomography (CT) scans can predict further nodule growth.

Methods

This retrospective study included 59 patients with 101 PGGNs from 2011 to 2012, who received regular CT follow-up for lung nodule surveillance. Nineteen quantitative image features consisting of 8 volumetric and 11 histogram parameters were calculated to detect lung nodule growth. For the extraction of the quantitative features, semi-automatic GrowCut segmentation was implemented on chest CT images in 3D slicer platform. Univariate and multivariate analyses were performed to identify risk factors for nodule growth.

Results

With a median follow-up of 52 months, nodule growth was detected in 10 nodules by radiological assessment and in 16 nodules by quantitative features. In univariate analysis, 3D maximum diameter (MD), volume, mass, surface area, 90% percentile, and standard deviation value (SD) of PGGN on the initial CT scan were significantly different between stable nodules and nodules with further growth. In multivariate analysis, MD [hazard ratio (HR), 3.75; 95% confidence interval (CI), 2.14-6.55] and SD (HR, 2.06; 95% CI, 1.35-3.14) were independent predictors of further nodule growth. Also, the area under the curve was 0.896 (95% CI: 0.820-0.948) and 0.813 (95% CI: 0.723-0.883) for MD with a cut-off value of 10.2mm and SD of 50.0 Hounsfield Unit (HU). Besides, the growth rate was 55.6% (n=15) of PGGNs with MD >10.2 mm and SD >50.0 HU.

Conclusions

Based on the initial CT scan, the quantitative features can predict PGGN growth more precisely. PGGN with MD >10.2 mm and SD >50.0 HU may require close follow-up or surgical intervention for the high incidence of growth.

Lung cancer screening with MRI: characterization of nodules with different non-enhanced MRI sequences

BACKGROUND

There is increased interest in pulmonary magnetic resonance imaging (MRI) as a radiation-free alternative to computed tomography (CT) for lung cancer screening.

PURPOSE

To analyze MRI characteristics of pulmonary nodules with different non-enhanced sequences.

MATERIAL AND METHODS

Eighty-two participants of a lung cancer screening were included. MRI datasets of 32 individuals with 46 different nodules ≥ 6 mm were prospectively evaluated together with 50 controls by two readers. Acquired sequences were T2- short tau inversion recovery (STIR), T2, balanced steady-state free precession (bSSFP), 3D-T1, and diffusion-weighted imaging (DWI). Each sequence was randomly and separately viewed blinded to low-dose CT (LDCT). Size, shape, and contrast of nodules were evaluated on each sequence and then correlated with LDCT and histopathology.

RESULTS

All eight carcinomas were detected by T2-STIR, T2, and bSSFP, and 7/8 by 3D-T1. Contrast was significantly higher for malignant nodules on all sequences. The highest contrast ratio between malignant and benign nodules was provided by T2-STIR. Of eight carcinomas, seven showed restricted diffusion. Size measurement correlated significantly between MRI and LDCT. Sensitivity/specificity for nodules ≥ 6 mm was 85-89%/92-94% for T2-STIR, 80-87%/93-96% for T2, 65-70%/96-98% for bSSFP, and 63-67%/96-100% for 3D-T1. Seven of eight subsolid nodules were visible on T2-sequences with significantly lower lesion contrast compared to solid nodules. Two of eight subsolid nodules were detected by bSFFP, none by 3D-T1. All three calcified nodules were detected by 3D-T1, one by bSSFP, and none by T2-sequences.

CONCLUSION

Malignant as well as calcified and subsolid nodules seem to have distinctive characteristics on different MRI sequences. T2-imaging was most suitable for the detection of nodules ≥ 6 mm.

Changes in quantitative parameters of pulmonary nonsolid nodule induced by lung inflation according to paired inspiratory and expiratory computed tomography imaging

OBJECTIVE

To evaluate quantitative parameters of nonsolid nodules on paired inspiratory and expiratory computed tomography (CT) and to examine whether these parameters are sensitive to lung inflation reflected by lung volume.

METHODS

Thirty-three patients with 41 nonsolid nodules were included in this prospective study. Paired inspiratory and low-dose respiratory plain chest CT were performed. The volume and density of nonsolid nodule(s), both lungs, the right and left lung, and five lobes, were analyzed in inspiratory and expiratory CT scans. The ratio of expiratory to inspiratory parameters was calculated and labeled as parameter_(E-I)/I. To standardize the changes in nonsolid nodule quantitative parameters, the ratio of nonsolid nodule parameter to lung parameter was also calculated. Quantitative parameters were compared between inspiratory and expiratory CT.

RESULTS

Nonsolid nodule volumes on expiratory CT were reduced by 19.8% ± 12.9%, while the density was increased by 11.4% ± 8.8%. The volume of nonsolid nodules was significantly greater on inspiratory compared with expiratory CT (p < 0.001). The density of nonsolid nodules was significantly greater on expiratory than inspiratory CT (p < 0.001). The volume_(E-I)/I was significantly greater than density_(E-I)/I both in nonsolid nodules and lung. The volume_(E-I)/I and density_(E-I)/I of nonsolid nodules were independent of size. The density_(E-I)/I of nonsolid nodule was greater in the lower lobe than that in the upper lobe (p = 0.002).

CONCLUSION

Volume changes in nonsolid nodules were more sensitive than density changes in expiratory phase. The density of lower lobe nodules was more susceptible to respiration. Expiratory scanning is not recommended for quantification of nonsolid nodules and/or follow-up.

KEY POINTS

• The nonsolid nodule volume on expiratory CT was reduced by 19.8% ± 12.9%. • The nonsolid nodule density on expiratory CT was increased by 11.4% ± 8.8%. • The volume _(E-I)/I and density _(E-I)/I of nonsolid nodules were independent of size.

Differentiation between intraspinal schwannoma and meningioma by MR characteristics and clinic features

OBJECTIVES

To retrospectively review the MRI characteristics and clinic features and evaluate the effectiveness of MR imaging in differentiating intraspinal schwannomas and meningiomas, with the excised histopathologic findings as the reference standard.

MATERIALS AND METHODS

One hundred and four schwannomas (M/F, 57:47) and 53 meningiomas (M/F, 13:40) underwent MR examinations before surgical treatment. Simple clinic data and imaging findings were considered:(a) location (craniocaudal and axial), (b) size, (c) morphology, (d) dural contact, (e) signal characteristics, (f) enhancement degree and patterns. The usefulness of the algorithm for differential diagnosis was examined between the two tumors.

RESULTS

Interobserver agreement was good (κ = 0.7-0.9). Ten cases meningiomas demonstrated multiple lesions. There was a female predominance in the meningiomas (P < 0.001). Meningiomas predominantly were located in the ventral or anterolateral areas of thoracic regions, while schwannomas in the posterolateral areas of the thoracic and the lumbar regions (P < 0.001). Mean size of the lesions was 1.47 ± 0.36 cm for meningioma, and 2.02 ± 1.13 cm for schwannoma (P < 0.001). A dumbbell shape with intervertebral foramen widening could detect schwannomas, while the "dural tail sign" did meningiomas (P < 0.001). Hypointense and miscellaneous signal implied meningioma on T₁WIs (P < 0.001). Isointense was more frequently observed in the meningiomas, while the fluid signal intensity and miscellaneous signal in the schwannomas on T₂WIs (P < 0.001). Schwannomas usually manifested rim enhancement, while meningiomas diffuse enhancement (P = 0.005). There were six variables including the logistic equation (age, size, dural tail sign, morphology, T₂WI, and axial location). The accuracy of the algorithm in diagnosis of schwannomas was 87.1%.

CONCLUSIONS

Combination of clinic data and MRI performs significantly for differentiating between intraspinal meningiomas and schwannomas.

Development and validation of a radiomics nomogram for identifying invasiveness of pulmonary adenocarcinomas appearing as subcentimeter ground-glass opacity nodules

The aim of the present study was to develop and validate a radiomics-based nomogram for differentiation of pre-invasive lesions from invasive lesions that appearing as ground-glass opacity nodules (GGNs) ≤10 mm (sub-centimeter) in diameter at CT. A total of 542 consecutive patients with 626 pathologically confirmed pulmonary subcentimeter GGNs were retrospectively studied from October 2011 to September 2017. All the GGNs were divided into a training set (n = 334) and a validation set (n = 292). Researchers extracted 475 radiomics features from the plain CT images; a radiomics signature was constructed with the least absolute shrinkage and selection operator (LASSO) based on multivariable regression in the training set. Based on the multivariable logistic regression model, a radiomics nomogram was developed in the training set. The performance of the nomogram was evaluated with respect to its calibration, discrimination, and clinical-utility and this was assessed in the validation set. The constructed radiomics signature, which consisted of 15 radiomics features, was significantly associated with the invasiveness of subcentimeter GGNs (P < 0.0001 for both training set and validation set). To build the nomogram model, radiomics signature and mean CT value were used. The nomogram model demonstrated good discrimination and calibration in both training set (C-index, 0.716 [95% CI, 0.632 to 0.801]) and validation set (C-index, 0.707 [95% CI, 0.625 to 0.788]). Decision curve analysis (DCA) indicated that radiomics-based nomogram was clinically useful. A radiomics-based nomogram that incorporates both radiomics signature and mean CT value is constructed in the study, which can be conveniently used to facilitate the preoperative individualized prediction of the invasiveness in patients with subcentimeter GGNs.

[Establishment and Verification of A Novel Predictive Model of Malignancy for Non-solid Pulmonary Nodules]

背景与目的

数学预测模型是判断肺小结节恶性概率的有效工具。伴随肺癌流行病学趋势的改变，以非实性肺小结节为影像学表现的早期肺癌检出率逐年升高，准确鉴别并及时治疗干预可有效改善预后。本研究旨在专门针对非实性肺小结节构建新型恶性概率预测模型，为有创诊疗提供客观依据，并尽量避免不必要的侵袭性操作及其可能造成的严重后果。

方法

回顾性分析自2013年1月-2018年4月，单中心经穿刺活检或手术切除获得明确病理诊断的362例非实性肺小结节病例资料，包括临床基本资料、血清肿瘤标记物和影像学特征等。病例分两组，应用建模组数据做单因素分析和二分类Logistic回归，判定独立危险因素，建立预测模型；应用验证组数据验证模型预测价值并与其他模型比较。

结果

362例非实性肺小结节病例中，313例（86.5%）确诊为非典型腺瘤样增生（atypical adenomatous hyperplasia, AAH）/原位腺癌（adenocarcinoma in situ, AIS）、微浸润腺癌（minimally invasive adenocarcinoma, MIA）或浸润性腺癌，49例诊断为良性病变。年龄、血清肿瘤标记物癌胚抗原（carcino-embryonic antigen, CEA）和Cyfra21-1、肿瘤实性成分比值（consolidation tumor ratio, CTR）、分叶征和钙化被确定为独立危险因素。模型受试者工作曲线下面积为0.894。预测灵敏度为87.6%，特异度为69.7%，阳性预测94.8%，阴性预测值为46.9%。经验证模型预测价值显著优于VA、Brock和GMUFH模型。

结论

本研究建立的新型非实性肺小结节恶性概率预测模型具备较高的诊断灵敏度和阳性预测值。经初步验证，其预测价值优于传统模型。未来经大样本验证后，可用作高危非实性肺小结节活检或手术切除前的初筛方法，具备临床应用价值。

Influencing factors of pneumothorax and parenchymal haemorrhage after CT-guided transthoracic needle biopsy: single-institution experience

Purpose

To evaluate the incidences and influencing factors of pneumothorax and parenchymal haemorrhage after computed tomography (CT)-guided transthoracic needle biopsy (TTNB).

Material and methods

A retrospective analysis of 216 patients who underwent CT-guided TTNB was performed. The frequencies and risk factors of pneumothorax and parenchymal haemorrhage were determined. P values less than 0.05 were considered statistically significant.

Results

The incidences of pneumothorax and parenchymal haemorrhage were 23.1% and 45.4%, respectively. Twenty-two per cent of patients with pneumothorax needed percutaneous drainage, but all patients with parenchymal haemorrhage had clinical improvement after conservative treatment. No procedure-related mortality was detected. Univariate analysis showed that underlying pulmonary infection, lesion size of less than 1 cm, and lesion depth of more than 2 cm were significant influencing factors of pneumothorax. A significant relationship between the underlying chronic obstructive pulmonary disease (COPD) and the need for drainage catheter insertion was found. Pulmonary haemorrhage was more likely to occur in patients with underlying malignancy, solid pulmonary nodule, lesion size of 3 cm or less, and lesion depth of more than 3 cm. Consolidation was the protective factor for pulmonary haemorrhage. Sensitivity, specificity, positive predictive values (PPV) and negative predictive values (NPV), and accuracy of CT-guided core needle biopsy (CNB) for the diagnosis of malignancy were 95.7%, 100%, 100%, 93.3%, and 97.3%, respectively. The rate of diagnostic failure was 10.2%.

Conclusions

Pulmonary hemorrhage is the most common complication after CT-guided TTNB. Influencing factors for pneumothorax are underlying pulmonary infection, lesion size < 1 cm, and lesion depth > 2 cm. Underlying malignancy, solid pulmonary nodule, lesion size ≤ 3 cm, and lesion depth > 3 cm are associated with pulmonary haemorrhage.

Is 18F-fluorodeoxyglucose positron emission tomography/computed tomography useful to discriminate metachronous lung cancer from metastasis in patients with oncological history?

BACKGROUND

Solitary pulmonary nodules detected during follow-up in patients with previous cancer history have a high probability of malignancy being either a metachronous lung cancer or a metastasis. This distinction represents a crucial issue in the perspective of "personalized medicine," implying different treatments and prognosis. Aim, to evaluate the role of 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) in distinguishing whether solitary pulmonary nodules are metachronous cancers or metastases and the relationship between the nodule's characteristics and their nature.

METHODS

From a single-institution database, we retrospectively selected all patients with a previous cancer history who performed 18F-FDG PET/CT to evaluate pulmonary nodules detected during follow-up, ranging from 5 mm to 40 mm, and histologically diagnosed as malignant.

RESULTS

Between September 2009 and August 2017, 127 patients (80 males; mean age=70.2±8.5years) with 127 malignant nodules were included: 103/127 (81%) metachronous cancers, 24/127 (19%) metastases. In both groups, PET/CT provided good and equivalent detection rate of malignancy (81% vs. 83%). No differences between metachronous cancers and metastases were found in: patient's age (70.3±8.1 years vs. 69.5±9.7years), gender (males=63.1% vs. 62.5%), interval between previous cancer diagnosis and nodules' detection (median time=4years vs. 4.5years), location (right-lung=55% vs. 54%; upper-lobes=64% vs. 67%; central-site=31% vs. 25%), size (median size=17mm vs. 19.5mm), 18F-FDG standardized uptake value (median SUVmax=5.2 vs. 5.9).

CONCLUSIONS

In oncological patients, despite its high detection rate, 18F-FDG PET/CT, as well as any other clinico-anatomical features, cannot distinguish whether a malignant solitary pulmonary nodule is a metachronous lung cancer or a metastasis, supporting the need of histological differential diagnosis.

Lung Adenocarcinomas Manifesting as Radiological Part-Solid Nodules Define a Special Clinical Subtype

INTRODUCTION

The clinicopathologic features and prognostic predictors of radiological part-solid lung adenocarcinomas were unclear.

METHODS

We retrospectively compared the clinicopathologic features and survival times of part-solid tumors with those of pure ground glass nodules (pGGNs) and pure solid tumors treated with surgery at Fudan University Shanghai Cancer Center and evaluated the prognostic implications of consolidation-to-tumor ratio (CTR), solid component size, and tumor size for part-solid lung adenocarcinomas.

RESULTS

A total of 911 patients and 988 pulmonary nodules (including 329 part-solid nodules [PSNs], 501 pGGNs, and 158 pure solid nodules) were analyzed. More female patients (p = 0.015) and nonsmokers (p = 0.003) were seen with PSNs than with pure solid nodules. The prevalence of lymphatic metastasis was lower in patients with PSNs than in those with pure solid tumors (2.2% versus 27% [p < 0.001]). The 5-year lung cancer-specific (LCS) recurrence-free survival and LCS overall survival of patients with PSNs were worse than those of patients with pGGNs (p < 0.001 and p = .042, respectively) but better than those of patients with pure solid tumors ([p < 0.001 and p < 0.0001, respectively]). CTR (OR = 12.90; 95% confidence interval [CI]: 1.85-90.04), solid component size (OR = 1.45; 95% CI: 1.28-1.64), and tumor size (OR = 1.23; 95% CI: 1.15-1.31) could predict pathologic invasive adenocarcinoma for patients with PSNs. None of them could predict the prognosis. Patients receiving sublobar resection had prognoses comparable to those of patients receiving lobectomy (p = .178 for 5-year LCS recurrence-free survival and p = .319 for 5-year LCS overall survival). The prognostic differences between patients with systemic lymph node dissection and those without systemic lymph node dissection were statistically insignificant.

CONCLUSIONS

Part-solid lung adenocarcinoma showed clinicopathologic features different from those of pure solid tumor. CTR, solid component size, and tumor size could not predict the prognosis. Part-solid lung adenocarcinomas define one special clinical subtype.

Current Practice in the Management of Pulmonary Nodules Detected on Computed Tomography Chest Scans

Lung cancer is associated with high mortality. It can present as one or more pulmonary nodules identified on computed tomography (CT) chest scans. The National Lung Screening Trial has shown that the use of low-dose CT chest screening can reduce deaths due to lung cancer. High adherence to appropriate follow-up of positive results, including imaging or interventional approaches, is an important aspect of pulmonary nodule management. Our study is one of the first to evaluate the current practice in managing pulmonary nodules and to explore potential causes for nonadherence to follow-up. This is a retrospective analysis at St. Paul's Hospital, a tertiary healthcare center in Vancouver, British Columbia, Canada. We first identified CT chest scans between January 1 to June 30, 2014, that demonstrated one or more pulmonary nodules equal to or greater than 6 mm in diameter. We then looked for evidence of interventional (surgical resection or biopsy, or bronchoscopy for transbronchial biopsy and cytology) and radiological follow-up of the pulmonary nodule by searching on the province-wide CareConnect eHealth Viewer patient database. A total of 1614 CT reports were analyzed and 139 (8.6%) had a positive finding. Out of the 97 patients who received follow-up, 54.6% (N = 53) was referred for a repeat CT chest scan and 36.1% (N = 35) and 9.3% (N = 9) were referred for interventional biopsy and surgical resection, respectively. In our study, 30.2% (N = 42) of the patients with pulmonary nodules were nonadherent to follow-up. Despite the radiologist's recommendation for follow-up within a certain time interval, only 36% had repeat imaging in a timely manner. Our findings reflect the current practice in the management of pulmonary nodules and suggest that there is a need for improvement at our academic center. Adherence to follow-up is important for the potentially near-future implementation of lung cancer screening.

Solid Indeterminate Pulmonary Nodules Less Than or Equal to 250 mm3: Application of the Updated Fleischner Society Guidelines in Clinical Practice

Background

The latest version of the Fleischner Society guidelines for management of incidental pulmonary nodules was published in 2017. The main purpose of these guidelines is to reduce the number of unnecessary computed tomography (CT) examinations during the follow-up of small indeterminate nodules.

Objective

The present study aimed to evaluate the performance of these guidelines for management of solid indeterminate pulmonary nodules (SIPNs) ≤ 250 mm³.

Materials and Methods

During a 7-year period, we retrospectively reviewed the chest CT scans of 672 consecutive patients with SIPNs. The study sample was selected according to the following inclusion criteria: solitary SIPN; diameter ≥ 3 mm; volume ≤ 250 mm³; two or more CT scans performed with the same scanner and same acquisition/reconstruction protocol; thin-section 1-mm images in DICOM format; histologic diagnosis or follow-up ≥ 2 years; and no oncological history. Applying these criteria, a total of 27 patients with single SIPNs ≤ 250 mm³ were enrolled. For each SIPN, the volume and doubling time were calculated using semiautomatic software throughout the follow-up period. For each SIPN, we applied the Fleischner Society guidelines, and the recommended management was compared to what was actually done.

Results

A significant volumetric increase was detected in 5/27 (18.5%) SIPNs; all growing nodules were observed in high-risk patients. In these SIPNs, a histologic diagnosis of malignancy was obtained. Applying the Fleischner Society recommendations, all five malignant nodules would have been identified. None of the SIPNs < 100 mm³ in low-risk patients showed significant growth during the follow-up period. The application of the new guidelines would have led to a significant reduction in follow-up CT examinations (Hodges-Lehmann median difference, -2 CT scans; p = 0.0001).

Conclusion

The application of the updated Fleischner Society guidelines has been shown to be effective in the management of SIPNs ≤ 250 mm³ with a significant reduction in radiation dose.

The importance of appropriate reporting and investigation of incidental findings on computed tomography attenuation correction images during myocardial perfusion scintigraphy

We present a case of lung cancer incidentally detected as a pulmonary nodule on computed tomography attenuation correction (CTAC) images during myocardial perfusion scintigraphy (MPS). Unfortunately, the incidental lesion was not fully investigated following MPS report and had developed into metastatic lung carcinoma when diagnosed over 1 year later, with failure of subsequent emergent chemotherapy. The disease appeared to be localized when initially detected during MPS. This case highlights the importance and potential clinical value of routine review of CTAC images in MPS with appropriate reporting and further investigation of suspicious incidental findings. In addition, the importance of effective communication between nuclear medicine department and treating team is clear to ensure suspicious incidental findings are given sufficient credence and thoroughly investigated promptly to avoid adverse clinical outcomes.

Radiologists' recommendations for additional imaging (RAI) in the inpatient setting

OBJECTIVE

The aim of our study was to measure the rate of radiologists' additional recommended imaging examinations (RAI) at a hospital-based inpatient setting and to estimate the influence on RAI of clinical variables.

MATERIALS AND METHODS

This retrospective study was approved by the institutional review board. Inpatients CT and US examinations interpreted by fifteen radiologists between October and December 2016 were studied. Information about RAI from radiology report texts was extracted manually. The analytic data set included the interpreting radiologists' years of experience, patient age, patient gender, radiologist gender, ordering service and "clinical question to be answered" as collected from the radiology request forms.

RESULTS

Of the 1996 US and CT examinations performed between October and December 2016 in the inpatient setting, 34% (683 examinations) had a radiologists' RAI. The largest proportion of RAI was for chest CT, followed by PET-CT, abdominal CT and abdominal MRI. Patient age and gender had no impact on RAI. Radiologists' years of experience were inversely correlated to RAI. "Pneumonia" showed the highest rate of RAI due to follow-up of lung nodules.

CONCLUSION

A high percentage of RAI resulted from CT and US radiologists' reports. The largest proportion of RAI was for chest CT, followed by PET-CT, abdominal CT, and abdominal MRI. Radiologists' years of experience play an important role in the number of the requested RAI. Further studies with a larger cohort of radiologists are needed to confirm the role of radiologists' experience in RAI. Also, follow-up studies are warranted to assess the number of RAI that are actually acted upon by the referring physicians.

A new image-guided technique for intraoperative localization of lung small solid nodules or ground-glass opacities with a self-expanding tract sealant device: a preliminary experience

OBJECTIVES

The aim of this study was to evaluate a new self-expanding tract sealant device, designed to prevent pneumothorax after computed tomography (CT)-guided lung biopsy, as an intraoperative marker for small pulmonary nodules or ground-glass opacities during minimally invasive thoracic surgery.

METHODS

Three patients with pulmonary nodules underwent CT-guided biopsies in our radiology department. During the same procedure, using a 19-gauge coaxial needle, a self-expanding tract sealant device was positioned in the lung nodule to be used not only for the prevention of pneumothorax but also as an intraoperative marker. A few days later, conventional thoracoscopic surgery was scheduled. A visual examination was performed. The site of the deployment of the BioSentry device was determined by checking for the proximal end of it beyond the visceral pleura. Thoracoscopic wedge resections using endoscopic staplers were performed to confirm histological characteristics, surgical margins and correct placement of the plug.

RESULTS

Three consecutive patients underwent CT-guided placement of this self-expanding tract sealant device (BioSentry) before surgery, without complications. The thoracoscopic resection was performed with success. The plug was easy to visualize with the scope, and all removed nodules had surgical free margins and the plug was correctly positioned in all patients.

CONCLUSIONS

The self-expanding tract sealant device was created for the reduction of pneumothorax and chest tube placement rates after percutaneous lung biopsy. We used it for the first time for intraoperative localization of peripheral small solid nodules or ground-glass opacities with good results.

Lung nodules: A comprehensive review on current approach and management

In daily clinical practice, radiologists and pulmonologists are faced with incidental radiographic findings of pulmonary nodules. Deciding how to manage these findings is very important as many of them may be benign and require no further action, but others may represent early disease and importantly early-stage lung cancer and require prompt diagnosis and definitive treatment. As the diagnosis of pulmonary nodules includes invasive procedures which can be relatively minimal, such as bronchoscopy or transthoracic aspiration or biopsy, but also more invasive procedures such as thoracic surgical biopsies, and as these procedures are linked to anxiety and to cost, it is important to have clearly defined algorithms for the description, management, and follow-up of these nodules. Clear algorithms for the imaging protocols and the management of positive findings should also exist in lung cancer screening programs, which are already established in the USA and which will hopefully be established worldwide. This article reviews current knowledge on nodule definition, diagnostic evaluation, and management based on literature data and mainly recent guidelines.

A blueprint for cancer screening and early detection: Advancing screening's contribution to cancer control

From the mid-20th century, accumulating evidence has supported the introduction of screening for cancers of the cervix, breast, colon and rectum, prostate (via shared decisions), and lung. The opportunity to detect and treat precursor lesions and invasive disease at a more favorable stage has contributed substantially to reduced incidence, morbidity, and mortality. However, as new discoveries portend advancements in technology and risk-based screening, we fail to fulfill the greatest potential of the existing technology, in terms of both full access among the target population and the delivery of state-of-the art care at each crucial step in the cascade of events that characterize successful cancer screening. There also is insufficient commitment to invest in the development of new technologies, incentivize the development of new ideas, and rapidly evaluate promising new technology. In this report, the authors summarize the status of cancer screening and propose a blueprint for the nation to further advance the contribution of screening to cancer control.

Evaluation of Virtual Reality for Detection of Lung Nodules on Computed Tomography

Virtual reality (VR) systems can offer benefits of improved ergonomics, but their resolution may currently be limited for the detection of small features. For detection of lung nodules, we compared the performance of VR versus standard picture archiving and communication system (PACS) monitor. Four radiologists and 1 novice radiologist reviewed axial computed tomography (CTs) of the thorax using standard PACS monitors (SM) and a VR system (HTC Vive, HTC). In this study, 3 radiologists evaluated axial lung-window CT images of a Lungman phantom. One radiologist and the novice radiologist reviewed axial lung-window patient CT thoracic images (32 patients). This HIPAA-compliant study was approved by the institutional review board. Detection of 227 lung nodules on patient CTs did not result in different sensitivity with SM compared with VR. Detection of 23 simulated Lungman phantom lung nodules on CT with SM resulted in statistically greater sensitivity (78.3%) than with VR (52.2%, P = .041) for 1 of 3 radiologists. The trend was similar but not significant for the other radiologists. There was no significant difference in the time spent by readers reviewing CT images with VR versus SM. These findings indicate that performance of a commercially available VR system for detection of lung nodules may be similar to traditional radiology monitors for assessment of small lung nodules on CTs of the thorax for most radiologists. These results, along with the potential of improving ergonomics for radiologists, are promising for the future development of VR in diagnostic radiology.

Variable radiological lung nodule evaluation leads to divergent management recommendations

Radiological evaluation of incidentally detected lung nodules on computed tomography (CT) influences management. We assessed international radiological variation in 1) pulmonary nodule characterisation; 2) hypothetical guideline-derived management; and 3) radiologists' management recommendations.107 radiologists from 25 countries evaluated 69 CT-detected nodules, recording: 1) first-choice composition (solid, part-solid or ground-glass, with percentage confidence); 2) morphological features; 3) dimensions; 4) recommended management; and 5) decision-influencing factors. We modelled hypothetical management decisions on the 2005 and updated 2017 Fleischner Society, and both liberal and parsimonious interpretations of the British Thoracic Society 2015 guidelines.Overall agreement for first-choice nodule composition was good (Fleiss' κ=0.65), but poorest for part-solid nodules (weighted κ 0.62, interquartile range 0.50-0.71). Morphological variables, including spiculation (κ=0.35), showed poor-to-moderate agreement (κ=0.23-0.53). Variation in diameter was greatest at key thresholds (5 mm and 6 mm). Agreement for radiologists' recommendations was poor (κ=0.30); 21% disagreed with the majority. Although agreement within the four guideline-modelled management strategies was good (κ=0.63-0.73), 5-10% of radiologists would disagree with majority decisions if they applied guidelines strictly.Agreement was lowest for part-solid nodules, while significant measurement variation exists at important size thresholds. These variations resulted in generally good agreement for guideline-modelled management, but poor agreement for radiologists' actual recommendations.

Cyst-related primary lung malignancies: an important and relatively unknown imaging appearance of (early) lung cancer

It is well known that lung cancer can manifest itself in imaging as solid and subsolid nodules or masses. However, in this era of increased computed tomography use another morphological computed tomography appearance of lung cancer is increasingly being recognised, presenting as a malignancy in relation to cystic airspaces. Despite the fact that it seems to be a relatively common finding in daily practice, literature on this entity is scarce and presumably the overall awareness is limited. This can lead to misinterpretation and delay in diagnosis and, therefore, increased awareness is urgently needed. This review aims to illustrate the imaging appearances of cyst-related primary lung malignancies, demonstrate its mimickers and potential pitfalls, and discuss the clinical implications based on the available literature and our own experience in four different hospitals.

Real-world evaluation of carboplatin plus a weekly dose of nab-paclitaxel for patients with advanced non-small-cell lung cancer with interstitial lung disease

Background

The optimal chemotherapy regimen for non-small-cell lung cancer (NSCLC) patients with interstitial lung disease (ILD) remains unknown. Therefore, in this study, we investigated the real-world efficacy and safety of carboplatin (CBDCA) plus nab-paclitaxel (nab-PTX) as a first-line regimen for NSCLC patients with ILD.

Patients and methods

We retrospectively reviewed advanced NSCLC patients with ILD who had received CBDCA plus nab-PTX as a first-line chemotherapy regimen between April 2013 and March 2018. Patients were diagnosed with ILD based on the findings of a pretreatment high-resolution computed tomography of the chest.

Results

The 34 patients enrolled in this study were included in the efficacy and safety analysis. Collagen vascular disease or a history of exposure to dust or asbestos was not reported for any patients. The median age of patients was 71 years (range, 59–83 years), and 32 patients had a performance status of 0 or 1. The overall response rate was 38.2%. The median progression-free survival and overall survival were 5.8 months and 12.7 months, respectively. Chemotherapy-related acute exacerbation of ILD was observed in two patients (5.7%). Other toxicities were feasible, and no treatment-related deaths occurred.

Conclusion

CBDCA plus nab-PTX, as a first-line chemotherapy regimen for NSCLC, showed favorable efficacy and safety in patients with preexisting ILD.

Comparison of lung imaging using three-dimensional ultrashort echo time and zero echo time sequences: preliminary study

OBJECTIVE

To determine the feasibility of using high-resolution volumetric zero echo time (ZTE) sequence in routine lung magnetic resonance imaging (MRI) and compare free breathing 3D ultrashort echo time (UTE) and ZTE lung MRI in terms of image quality and small-nodule detection.

MATERIALS AND METHODS

Our Institutional Review Board approved this study. Twenty patients underwent both UTE and ZTE sequences during routine lung MR. UTE and ZTE images were compared in terms of subjective image quality and detection of lung parenchymal signal, intrapulmonary structures, and sub-centimeter nodules. Differences between the two sequences were compared through statistical analysis.

RESULTS

Lung parenchyma showed significantly (p < 0.05) higher signal-to-noise ratio (SNR) in ZTE than in UTE. The SNR and contrast-to-noise ratio (CNR) of peripheral bronchus and small pulmonary arteries were significantly (all p < 0.05) higher in ZTE. Subjective image quality evaluated by two independent radiologists in terms of depicting normal structures and overall acceptability was superior in ZTE (p < 0.05). The diagnostic accuracy for sub-centimeter nodules was significantly higher for ZTE (reader 1: AUC, 0.972; p = 0.044; reader 2: AUC, 0.946; p = 0.045) than that for UTE (reader 1: AUC, 0.885; reader 2: AUC, 0.855). Mean scan time was 131 s (125-141 s) in ZTE and 467 s (453-508 s) in UTE. ZTE images were obtained with less acoustic noise.

CONCLUSION

Implementing ZTE as an additional sequence in routine lung MR is feasible. ZTE can provide high-resolution pulmonary structural information with better SNR and CNR using shorter time than UTE.

KEY POINTS

• Both UTE and ZTE techniques use very short TEs to capture signals from very short T2/T2* tissues. • ZTE is superior in capturing lung parenchymal signal than UTE. • ZTE provides high-resolution structural information with better SNR and CNR for normal intrapulmonary structures and small nodules using shorter scan time than UTE.

Centralized Lung Nodule Management at A Veterans Hospital Using A Multidisciplinary Lung Nodule Evaluation Team (LNET)

Introduction

Lung nodules are frequently identified on imaging studies and can represent early lung cancers. We instituted the Lung Nodule Evaluation Team (LNET) to optimize management of these nodules by a lung specialist physician. All lung nodules identified by a radiologist prompted a direct consultation to this service. We report our initial experience with this process.

Methods

This is a retrospective review of patients with lung nodules at a single institution from 2008 to 2015. Since October 2014, lung nodules > 3 mm identified on computed tomography (CT) scanning of the chest generate an automatic consult to LNET from the radiology service. Demographic, nodule and follow up data was entered into a surveillance database and summarized.

Results

There were 1, 873 patients identified in the database. Of these, 900 patients were undergoing active surveillance. Consults increased from 5.5 to 93 per month after the start of the new consult program. Lung nodules were identified on 64% of chest CT scans. Prior to the direct radiology consult the average size of a nodule was 1.7 cm and 0.7 cm after. The overall time from initial nodule imaging to initiating a management plan by a thoracic specialist physician was 3.7 days.

Conclusion

Assessment of lung nodules by a specialist physician is important to ensure appropriate long term management and optimize utilization of diagnostic interventions. A direct radiology consult to a specialized team of chest physicians decreased the time in initiating a management plan, identified smaller nodules and may lead to a more judicious use of health care resources in the management of lung nodules.

Updated Fleischner Society Guidelines for Managing Incidental Pulmonary Nodules: Common Questions and Challenging Scenarios

The new guidelines for managing incidental pulmonary nodules published by the Fleischner Society in 2017 reflect an improved understanding of the risk factors and biologic features of lung cancer. Specific topics emphasized in the updated guidelines include a new threshold size for follow-up, the importance of the morphologic features of nodules, accurate nodule measurements, recognition of subsolid components, understanding interval growth or change in nodule morphology, and knowledge of patient risk factors. The updated guidelines enable greater personal flexibility in the decision-making process and encourage individualized management of pulmonary nodules. These factors may introduce new challenges for radiologists, who previously used solely nodule size to make management recommendations. The authors describe eight scenarios that illustrate the challenges potentially encountered when applying the new guidelines to pulmonary nodule management. ^©RSNA, 2018.

CT screening for lung cancer: comparison of three baseline screening protocols

PURPOSE

Clinical management decisions arising from the baseline round for lung cancer screening are the most challenging, as findings have accumulated over a lifetime and may be of no clinical concern. To minimize unnecessary harms and costs of workup prior to the first, annual repeat screening, workup should be limited to participants with the highest suspicion of lung cancer while still aiming to identify small, early lung cancers.

METHODS

We compared recommendations for immediate, delayed (by 3 or 6 months) workup to assess growth at a malignant rate, and the resulting overall and potential biopsies of three baseline screening protocols: I-ELCAP, the two scenarios of ACR-LungRADS, and the European Consortium. For each protocol, the efficiency ratio (ER) of each recommendation was calculated by dividing the number of participants recommended for that workup by the number of resulting lung cancer diagnoses. The ER for potential biopsies was calculated, assuming that biopsies were performed on all participants recommended for immediate workup as well as those diagnosed with lung cancer after delayed workup.

RESULTS

For I-ELCAP, ACR-LungRADS Scenario 1, ACR-LungRADS Scenario 2, and the European consortium, the overall ER was 13.9, 18.3, 18.3, and 31.9, respectively, and for potential biopsies, it was 2.2, 8.1, 3.2, and 4.4, respectively. ER for immediate workup was 2.9, 8.6, 3.9, and 5.6, respectively, and for delayed workup was 36.1, 160.3, 57.8, and 111.9, respectively.

CONCLUSIONS

I-ELCAP recommendations had the lowest ER values for overall, immediate, and delayed workup, and for potential biopsies.

KEY POINTS

• Small differences in protocol thresholds can lead to many unnecessary diagnostic workups. • I-ELCAP recommendations were the most efficient for immediate and overall workup, and potential biopsies. • Definition of a "positive result" and recommendations for further workup in the baseline round needs to be continually reevaluated and updated.

Fluorine 18-FDG PET/CT and Diffusion-weighted MRI for Malignant versus Benign Pulmonary Lesions: A Meta-Analysis

Purpose To perform a meta-analysis of the literature to compare the diagnostic performance of fluorine 18 fluorodeoxyglucose PET/CT and diffusion-weighted (DW) MRI in the differentiation of malignant and benign pulmonary nodules and masses. Materials and Methods Published English-language studies on the diagnostic accuracy of PET/CT and/or DW MRI in the characterization of pulmonary lesions were searched in relevant databases through December 2017. The primary focus was on studies in which joint DW MRI and PET/CT were performed in the entire study population, to reduce interstudy heterogeneity. For DW MRI, lesion-to-spinal cord signal intensity ratio and apparent diffusion coefficient were evaluated; for PET/CT, maximum standard uptake value was evaluated. The pooled sensitivities, specificities, diagnostic odds ratios, and areas under the receiver operating characteristic curve (AUCs) for PET/CT and DW MRI were determined along with 95% confidence intervals (CIs). Results Thirty-seven studies met the inclusion criteria, with a total of 4224 participants and 4463 lesions (3090 malignant lesions [69.2%]). In the primary analysis of joint DW MRI and PET/CT studies (n = 6), DW MRI had a pooled sensitivity and specificity of 83% (95% CI: 75%, 89%) and 91% (95% CI: 80%, 96%), respectively, compared with 78% (95% CI: 70%, 84%) (P = .01 vs DW MRI) and 81% (95% CI: 72%, 88%) (P = .056 vs DW MRI) for PET/CT. DW MRI yielded an AUC of 0.93 (95% CI: 0.90, 0.95), versus 0.86 (95% CI: 0.83, 0.89) for PET/CT (P = .001). The diagnostic odds ratio of DW MRI (50 [95% CI: 19, 132]) was superior to that of PET/CT (15 [95% CI: 7, 32]) (P = .006). Conclusion The diagnostic performance of diffusion-weighted MRI is comparable or superior to that of fluorine 18 fluorodeoxyglucose PET/CT in the differentiation of malignant and benign pulmonary lesions. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Schiebler in this issue.

Representation of Deep Features using Radiologist defined Semantic Features

Semantic features are common radiological traits used to characterize a lesion by a trained radiologist. These features have been recently formulated, quantified on a point scale in the context of lung nodules by our group. Certain radiological semantic traits have been shown to extremely predictive of malignancy [26]. Semantic traits observed by a radiologist at examination describe the nodules and the morphology of the lung nodule shape, size, border, attachment to vessel or pleural wall, location and texture etc. Deep features are numeric descriptors often obtained from a convolutional neural network (CNN) which are widely used for classification and recognition. Deep features may contain information about texture and shape, primarily. Lately, with the advancement of deep learning, convolutional neural networks (CNN) are also being used to analyze lung nodules. In this study, we relate deep features to semantic features by looking for similarity in ability to classify. Deep features were obtained using a transfer learning approach from both an ImageNet pre-trained CNN and our trained CNN architecture. We found that some of the semantic features can be represented by one or more deep features. In this process, we can infer that some deep feature(s) have similar discriminatory ability as semantic features.

The decision to biopsy in a lung cancer screening program: Potential impact of risk calculators

OBJECTIVE

The National Lung Screening Trial demonstrated the benefits of lung cancer screening, but the potential high incidence of unnecessary invasive testing for ultimately benign radiologic findings causes concern. We aimed to review current biopsy patterns and outcomes in our community-based program, and retrospectively apply malignancy prediction models in a lung cancer screening population, to identify the potential impact these calculators could have on biopsy decisions.

METHODS

Retrospective review of lung cancer-screening program participants from 2013 to 2016. Demographic, biopsy, and outcome data were collected. Malignancy risk calculators were retrospectively applied and results compared in patients with positive imaging findings.

RESULTS

From 520 individuals enrolled in the screening program, pulmonary nodule(s) ≥6 mm were identified in 166, with biopsy in 30. Malignancy risk probabilities were significantly higher (Brock p < 0.00001; Mayo p < 0.00001) in those undergoing diagnostic sampling than those not undergoing sampling. However, there was no difference in the Brock ( p = 0.912) or Mayo ( p = 0.435) calculators when discriminating a final diagnosis of cancer from not cancer in those undergoing sampling.

CONCLUSIONS

In our screening program, 5.7% of individuals undergo invasive testing, comparable with the National Lung Screening Trial (6.1%). Both Brock and Mayo calculators perform well in indicating who may be at risk of malignancy, based on clinical and radiologic factors. However, in our invasive testing group, the Brock and Mayo calculators and Lung Cancer Screening Program clinical assessment all lacked clarity in distinguishing individuals who have a cancer from those with a benign abnormality.

Use of Risk Assessment Tools to Guide Decision-Making in the Primary Prevention of Atherosclerotic Cardiovascular Disease: A Special Report From the American Heart Association and American College of Cardiology

Risk assessment is a critical step in the current approach to primary prevention of atherosclerotic cardiovascular disease. Knowledge of the 10-year risk for atherosclerotic cardiovascular disease identifies patients in higher-risk groups who are likely to have greater net benefit and lower number needed to treat for both statins and antihypertensive therapy. Current US prevention guidelines for blood pressure and cholesterol management recommend use of the pooled cohort equations to start a process of shared decision-making between clinicians and patients in primary prevention. The pooled cohort equations have been widely validated and are broadly useful for the general US clinical population. But, they may systematically underestimate risk in patients from certain racial/ethnic groups, those with lower socioeconomic status or with chronic inflammatory diseases, and overestimate risk in patients with higher socioeconomic status or who have been closely engaged with preventive healthcare services. If uncertainty remains for patients at borderline or intermediate risk, or if the patient is undecided after a patient-clinician discussion with consideration of risk enhancing factors (eg, family history), additional testing with measurement of coronary artery calcium can be useful to reclassify risk estimates and improve selection of patients for use or avoidance of statin therapy. This special report summarizes the rationale and evidence base for quantitative risk assessment, reviews strengths and limitations of existing risk scores, discusses approaches for refining individual risk estimates for patients, and provides practical advice regarding implementation of risk assessment and decision-making strategies in clinical practice.

Use of Risk Assessment Tools to Guide Decision-Making in the Primary Prevention of Atherosclerotic Cardiovascular Disease: A Special Report From the American Heart Association and American College of Cardiology

Risk assessment is a critical step in the current approach to primary prevention of atherosclerotic cardiovascular disease. Knowledge of the 10-year risk for atherosclerotic cardiovascular disease identifies patients in higher-risk groups who are likely to have greater net benefit and lower number needed to treat for both statins and antihypertensive therapy. Current U.S. prevention guidelines for blood pressure and cholesterol management recommend use of the pooled cohort equations to start a process of shared decision-making between clinicians and patients in primary prevention. The pooled cohort equations have been widely validated and are broadly useful for the general U.S. clinical population. But, they may systematically underestimate risk in patients from certain racial/ethnic groups, those with lower socioeconomic status or with chronic inflammatory diseases, and overestimate risk in patients with higher socioeconomic status or who have been closely engaged with preventive healthcare services. If uncertainty remains for patients at borderline or intermediate risk, or if the patient is undecided after a patient-clinician discussion with consideration of risk enhancing factors (e.g., family history), additional testing with measurement of coronary artery calcium can be useful to reclassify risk estimates and improve selection of patients for use or avoidance of statin therapy. This special report summarizes the rationale and evidence base for quantitative risk assessment, reviews strengths and limitations of existing risk scores, discusses approaches for refining individual risk estimates for patients, and provides practical advice regarding implementation of risk assessment and decision-making strategies in clinical practice.

Primary lung cancer in patients with previous malignancies: a nationwide study

Overall survival of patients with cancer continues to increase and so they receive more frequent CT imaging, making oncological patients a growing population that effectively receives lung cancer screening in the course of daily practice. However, it is currently uncertain how early lung cancer detection in this subgroup of patients should be optimally managed. We describe the relationship between primary lung cancer and prior malignancies in a nationwide cohort, in an attempt to identify possible areas of improvement in nodule management. We found that a substantial number of subjects with lung cancer suffered from a prior malignancy; however, with the exception of otorhinolaryngeal malignancies, they did not show a high absolute risk for lung cancer. Future research should provide more data on how to handle this subgroup of patients in clinical and screening setting.

Assessing the Prevalence of Incidental Findings Identified by CTPA in Women of Reproductive Age

Background and Objective

Though multiple studies have evaluated the prevalence of incidental findings identified by CTPA, none have done so with a focus on reproductive-age females with normal chest X-ray (CXR). Due to a comparatively lower breast radiation dose, the oft-recommended alternative to CTPA in this patient group is a V/Q scan. However, these are limited in their assessment of these alternate findings; therefore, it is of particular importance to evaluate the likelihood of these findings on CT in this patient group, which is the goal of this study.

Methods

Through a review of our PACS system, female patients aged 18-50 years who underwent diagnostic CTPA prior to April 1, 2017, were identified. The 100 most recent cases which had a normal CXR within 48 hours of CTPA were included. Incidental/non-PE findings were then divided into PE-positive (PE+) and PE-negative (PE-), and subcategorized into types I, II, III, and nil non-PE finding groups. Type I findings required immediate follow-up or intervention, type II findings required outpatient follow-up, and type III findings required no follow-up or were previously known.

Results

PE was detected in 15% of scans. Type I findings were found in 8% of patients (0% of PE+, 9.4% of PE-), type II findings in 10% of patients (13.3% of PE+, 9.4% of PE-), type III findings in 34% of patients (40% of PE+, 32.9% of PE-), and nil non-PE finding in 48% of patients (46.7% PE+, 48.2% of PE-).

Conclusion

While CTPA identifies incidental findings in the majority of patients, a small minority of these findings are likely to alter immediate management. In the context in increased radiation risk, this strengthens the argument that alternate imaging modalities such as V/Q should be strongly considered for the investigation of potential PE in women of reproductive age with normal CXR.

Current Practices in the Management of Pulmonary Ground-Glass Opacities: A Survey of SICT Members

BACKGROUND

Several gray areas and controversies exist concerning the management of pulmonary ground-glass opacities (GGOs), and there is a lack of consensus among clinicians on this topic. One of the main aims of the Italian Society of Thoracic Surgery is to promote education and research, so we decided to perform a survey on this topic to estimate current trends in practice in a large sample of thoracic surgeons.

METHODS

A total of 160 thoracic surgeons responded, namely, completed our questionnaire (response rate, 53%; 160 of 302). The survey was composed of 36 questions divided into six subsections: (1) demographic characteristics of the respondents; (2) terminology and taxonomy; (3) radiologic and radiometabolic evaluation; (4) diagnostic approach and indications for surgery; (5) surgical management; and (6) radiologic surveillance.

RESULTS

We observed some divergence of opinion regarding the definition of mixed GGOs, the role of 18F fluorodeoxyglucose positron emission tomography and computed tomography scans, indications for nonsurgical biopsy, intraoperative techniques for localizing GGOs, indications for surgery, extension of lung resection and lymph node dissection according to the radiologic scenario, use of intraoperative frozen section analysis, and radiologic surveillance of pure GGOs.

CONCLUSIONS

This topic warrants more investigation in the future. An upcoming consensus conference of Italian Society of Thoracic Surgery experts (also open to experts in other specialties) could provide updated indications for GGO management based on the literature, expert opinions, and the results of the present survey.

Predictive factors for invasive adenocarcinoma in patients with clinical non-invasive or minimally invasive lung cancer

Background

Pure ground glass opacity (GGO) or part-solid GGO with small solid component (≤5 mm) are likely to be non-invasive or minimally invasive lung cancer. However, those lesions sometimes are diagnosed as invasive adenocarcinoma postoperatively. The aim of this study was to determine the predictors of invasive adenocarcinoma in clinical non- or minimally invasive lung cancer.

Methods

From January 2010 to December 2017, 203 patients were diagnosed as clinical adenocarcinoma in situ (AIS) or minimally invasive adenocarcinoma (MIA) identified on chest computed tomography (CT) and they underwent surgical resection. A retrospective study was performed to analyze the prediction of invasive adenocarcinoma in clinical non- or minimally invasive lung cancer.

Results

Of all clinical AIS or MIA patients, invasive adenocarcinoma was diagnosed in 55 patients (27.1%). In clinical AIS, invasive adenocarcinoma was diagnosed in 19 patients (17.9%) and 36 patients (37.1%) were diagnosed as invasive adenocarcinoma in clinical MIA (P=0.002). Tumor diameter and the presence of solid component were confirmed to be significant predictive factors for invasive adenocarcinoma in a multivariate analysis [hazard ratio (HR) 1.071, P=0.037; HR 2.573, P=0.005; respectively].

Conclusions

Large tumor size and the presence of solid component in clinical AIS or MIA are predictive factors for invasive adenocarcinoma. Therefore, early surgical intervention is recommended for those lesions.

Performance and clinical impact of machine learning based lung nodule detection using vessel suppression in melanoma patients

PURPOSE

To evaluate performance and the clinical impact of a novel machine learning based vessel-suppressing computer-aided detection (CAD) software in chest computed tomography (CT) of patients with malignant melanoma.

MATERIALS AND METHODS

We retrospectively included consecutive malignant melanoma patients with a chest CT between 01/2015 and 01/2016. Machine learning based CAD software was used to reconstruct additional vessel-suppressed axial images. Three radiologists independently reviewed a maximum of 15 lung nodules per patient. Vessel-suppressed reconstructions were reviewed independently and results were compared. Follow-up CT examinations and clinical follow-up were used to assess the outcome. Impact of additional nodules on clinical management was assessed.

RESULTS

In 46 patients, vessel-suppressed axial images led to the detection of additional nodules in 25/46 (54.3%) patients. CT or clinical follow up was available in 25/25 (100%) patients with additionally detected nodules. 2/25 (8%) of these patients developed new pulmonary metastases. None of the additionally detected nodules were found to be metastases. None of the lung nodules detected by the radiologists was missed by the CAD software. The mean diameter of the 92 additional nodules was 1.5 ± 0.8 mm. The additional nodules did not affect therapeutic management. However, in 14/46 (30.4%) of patients the additional nodules might have had an impact on the radiological follow-up recommendations.

CONCLUSION

Machine learning based vessel suppression led to the detection of significantly more lung nodules in melanoma patients. Radiological follow-up recommendations were altered in 30% of the patients. However, all lung nodules turned out to be non-malignant on follow-up.

Predicting Malignancy Risk of Screen-Detected Lung Nodules-Mean Diameter or Volume

OBJECTIVE

In lung cancer screening practice low-dose computed tomography, diameter, and volumetric measurement have been used in the management of screen-detected lung nodules. The aim of this study was to compare the performance of nodule malignancy risk prediction tools using diameter or volume and between computer-aided detection (CAD) and radiologist measurements.

METHODS

Multivariable logistic regression models were prepared by using data from two multicenter lung cancer screening trials. For model development and validation, baseline low-dose computed tomography scans from the Pan-Canadian Early Detection of Lung Cancer Study and a subset of National Lung Screening Trial (NLST) scans with lung nodules 3 mm or more in mean diameter were analyzed by using the CIRRUS Lung Screening Workstation (Radboud University Medical Center, Nijmegen, the Netherlands). In the NLST sample, nodules with cancer had been matched on the basis of size to nodules without cancer.

RESULTS

Both CAD-based mean diameter and volume models showed excellent discrimination and calibration, with similar areas under the receiver operating characteristic curves of 0.947. The two CAD models had predictive performance similar to that of the radiologist-based model. In the NLST validation data, the CAD mean diameter and volume models also demonstrated excellent discrimination: areas under the curve of 0.810 and 0.821, respectively. These performance statistics are similar to those of the Pan-Canadian Early Detection of Lung Cancer Study malignancy probability model with use of these data and radiologist-measured maximum diameter.

CONCLUSION

Either CAD-based nodule diameter or volume can be used to assist in predicting a nodule's malignancy risk.