The self-distillation trained multitask dense-attention network for diagnosing lung cancers based on CT scans

BACKGROUND

The latest international multidisciplinary histopathological classification of lung cancer indicates that a deeper study of the lung adenocarcinoma requires a comprehensive multidisciplinary platform. However, in the traditional pathological examination or previous computer-vision-based research, the entire lung is not considered in a comprehensive manner.

PURPOSE

The study aims to develop a deep learning model proposed for diagnosing the lung adenocarcinoma histopathologically based on CT scans. Instead of just classifying the lung adenocarcinoma, the pathological report should be inferred based on both the invasiveness and growth pattern of the tumors.

METHODS

A self-distillation trained multitask dense-attention network (SD-MdaNet) is proposed and validated based on 2412 labeled CT scans from 476 patients and 845 unlabeled scans. Inferring the pathological report is divided into two tasks, predicting the invasiveness of the lung tumor and inferring growth patterns of tumor cells in a comprehensive histopathological subtyping manner with excellent accuracy. In the proposed method, the dense-attention module is introduced to better extract features from a small dataset in the main branch of the MdaNet. Next, task-specific attention modules are utilized in different branches and finally integrated as a multitask model. The second task is a blend of classification and regression tasks. Thus, a specialized loss function is developed. In the proposed knowledge distillation (KD) process, the MdaNet as well as its main branch trained for solving two single tasks, respectively, are treated as multiple teachers to produce a student model. A novel KD loss function is developed to take the advantage of all the models as well as data with labels and without labels.

RESULTS

SD-MdaNet achieves an AUC of98.7 ± 0.4 % $98.7\pm 0.4\%$ on invasiveness prediction, and91.6 ± 1.0 % $91.6\pm 1.0\%$ on predominant growth pattern prediction on our dataset. Moreover, the average mean squared error in inferring growth pattern proportion reaches0.0217 ± 0.0019 $0.0217\pm 0.0019$ , and the AUC for predominant growth pattern proportion reaches91.6 ± 1.0 % $91.6\pm 1.0\%$ . The proposed SD-MdaNet is significantly better than all other benchmarking methods (F D R < 0.05 $FDR<0.05$ ).

CONCLUSIONS

Experimental results demonstrate that the proposed SD-MdaNet can significantly improve the performance of the lung adenocarcinoma pathological diagnosis using only CT scans. Analyses and discussions are conducted to interpret the advantages of the SD-MdaNet.

Assessing the effect of scanning parameter on the size and density of pulmonary nodules: a phantom study

BACKGROUND

Lung cancer remains a leading cause of death among cancer patients. Computed tomography (CT) plays a key role in lung cancer screening. Previous studies have not adequately quantified the effect of scanning protocols on the detected tumor size. The aim of this study was to assess the effect of various CT scanning parameters on tumor size and densitometry based on a phantom study and to investigate the optimal energy and mA image quality for screening assessment.

METHODS

We proposed a new model using the LUNGMAN N1 phantom multipurpose anthropomorphic chest phantom (diameters: 8, 10, and 12 mm; CT values: - 100, - 630, and - 800 HU) to evaluate the influence of changes in tube voltage and tube current on the size and density of pulmonary nodules. In the LUNGMAN N1 model, three types of simulated lung nodules representing solid tumors of different sizes were used. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were used to evaluate the image quality of each scanning combination. The consistency between the calculated results based on segmentation from two physicists was evaluated using the interclass correlation coefficient (ICC).

RESULTS

In terms of nodule size, the longest diameters of ground-glass nodules (GGNs) were closest to the ground truth on the images measured at 100 kVp tube voltage, and the longest diameters of solid nodules were closest to the ground truth on the images measured at 80 kVp tube voltage. In respect to density, the CT values of GGNs and solid nodules were closest to the ground truth when measured at 80 kVp and 100 kVp tube voltage, respectively. The overall agreement demonstrates that the measurements were consistent between the two physicists.

CONCLUSIONS

Our proposed model demonstrated that a combination of 80 kVp and 140 mA scans was preferred for measuring the size of the solid nodules, and a combination of 100 kVp and 100 mA scans was preferred for measuring the size of the GGNs when performing lung cancer screening. The CT values at 80 kVp and 100 kVp were preferred for the measurement of GGNs and solid nodules, respectively, which were closest to the true CT values of the nodules. Therefore, the combination of scanning parameters should be selected for different types of nodules to obtain more accurate nodal data.

Clinical implication of the 2020 International Association for the Study of Lung Cancer histologic grading in surgically resected pathologic stage 1 lung adenocarcinomas: Prognostic value and association with computed tomography characteristics

OBJECTIVES

To investigate the incremental prognostic value of the 2020 International Association for the Study of Lung Cancer (IASLC) histologic grading system over traditional prognosticators in surgically resected pathologic stage 1 lung adenocarcinomas and to identify the clinical and radiologic characteristics of lung adenocarcinomas reclassified by the 2020 histologic grading system.

MATERIALS AND METHODS

We retrospectively enrolled 356 patients who underwent surgery for pathologic stage 1 adenocarcinoma between January 2016 and December 2017. The histologic grading was classified according to the predominant histologic subtype (conventional system) and the updated 2020 IASLC grading system. The clinical and computed tomography (CT) characteristics were compared according to the reclassification of the updated system. The performance of prognostic models for recurrence-free survival based on the combination of pathologic tumor size, histologic grade, and CT-based information was compared using the c-index.

RESULTS

Postoperative recurrence occurred in 6.7% of patients during the follow-up period (mean, 1589.2 ± 406.7 days). Fifty-nine of 244 (24.2%) tumors with intermediate grades in the conventional system were reclassified as grade 3 with the updated grading system. They showed significantly larger solid proportions and higher percentages of pure solid nodules on CT compared to tumors without reclassification (n = 185) (P < 0.05). Prognostic prediction models based on pathology tumor size and histologic grades had significantly higher c-indices (0.754-0.803) compared to the model based on pathologic tumor size only (c-index:0.723, P < 0.05).

CONCLUSION

The 2020 IASLC histologic grading system has significant incremental prognostic value over the pathologic stage in surgically resected pathologic stage 1 lung adenocarcinoma. Reclassified lung adenocarcinomas using the updated grading system have a larger solid proportion and a higher percentage of pure solid nodules on CT.

B4GALT1 promotes immune escape by regulating the expression of PD-L1 at multiple levels in lung adenocarcinoma

BACKGROUND

Invasive adenocarcinoma (IAC), which is typically preceded by minimally invasive adenocarcinoma (MIA), is the dominant pathological subtype of early-stage lung adenocarcinoma (LUAD). Identifying the molecular events underlying the progression from MIA to IAC may provide a crucial perspective and boost the exploration of novel strategies for early-stage LUAD diagnosis and treatment.

METHODS

Transcriptome sequencing of four pairs of MIA and IAC tumours obtained from four multiple primary lung cancer patients was performed to screen out beta-1,4-galactosyltransferase1 (B4GALT1). Function and mechanism experiments in vitro and in vivo were performed to explore the regulatory mechanism of B4GALT1-mediated immune evasion by regulating programmed cell death ligand 1 (PD-L1).

RESULTS

B4GALT1, a key gene involved in N-glycan biosynthesis, was highly expressed in IAC samples. Further experiments revealed that B4GALT1 regulated LUAD cell proliferation and invasion both in vitro and in vivo and was related to the impaired antitumour capacity of CD8 + T cells. Mechanistically, B4GALT1 directly mediates the N-linked glycosylation of PD-L1 protein, thus preventing PD-L1 degradation at the posttranscriptional level. In addition, B4GALT1 stabilized the TAZ protein via glycosylation, which activated CD274 at the transcriptional level. These factors lead to lung cancer immune escape. Importantly, inhibition of B4GALT1 increased CD8 + T-cell abundance and activity and enhanced the antitumour immunity of anti-PD-1 therapy in vivo.

CONCLUSION

B4GALT1 is a critical molecule in the development of early-stage LUAD and may be a novel target for LUAD intervention and immunotherapy.

A delta-radiomics model for preoperative prediction of invasive lung adenocarcinomas manifesting as radiological part-solid nodules

Purpose

This study aims to explore the value of the delta-radiomics (DelRADx) model in predicting the invasiveness of lung adenocarcinoma manifesting as radiological part-solid nodules (PSNs).

Methods

A total of 299 PSNs histopathologically confirmed as lung adenocarcinoma (training set, n = 209; validation set, n = 90) in our hospital were retrospectively analyzed from January 2017 to December 2021. All patients underwent diagnostic noncontrast-enhanced CT (NCECT) and contrast-enhanced CT (CECT) before surgery. After image preprocessing and ROI segmentation, 740 radiomic features were extracted from NCECT and CECT, respectively, resulting in 740 DelRADx. A DelRADx model was constructed using the least absolute shrinkage and selection operator logistic (LASSO-logistic) algorithm based on the training cohort. The conventional radiomics model based on NCECT was also constructed following the same process for comparison purposes. The prediction performance was assessed using area under the ROC curve (AUC). To provide an easy-to-use tool, a radiomics-based integrated nomogram was constructed and evaluated by integrated discrimination increment (IDI), calibration curves, decision curve analysis (DCA), and clinical impact plot.

Results

The DelRADx signature, which consisted of nine robust selected features, showed significant differences between the AIS/MIA group and IAC group (p &lt; 0.05) in both training and validation sets. The DelRADx signature showed a significantly higher AUC (0.902) compared to the conventional radiomics model based on NCECT (AUC = 0.856) in the validation set. The IDI was significant at 0.0769 for the integrated nomogram compared with the DelRADx signature. The calibration curve of the integrated nomogram demonstrated favorable agreement both in the training set and validation set with a mean absolute error of 0.001 and 0.019, respectively. Decision curve analysis and clinical impact plot indicated that if the threshold probability was within 90%, the integrated nomogram showed a high clinical application value.

Conclusion

The DelRADx method has the potential to assist doctors in predicting the invasiveness for patients with PSNs. The integrated nomogram incorporating the DelRADx signature with the radiographic features could facilitate the performance and serve as an alternative way for determining management.

[Comparison of Two-dimensional and Three-dimensional Features of Chest CT in the Diagnosis of Invasion of Pulmonary Ground Glass Nodules]

BACKGROUND

At present, more and more studies predict invasive adenocarcinoma (IAC) through three-dimensional features of pulmonary nodules, but few studies have confirmed that three-dimensional features have more advantages in diagnosing IAC than traditional two-dimensional features of pulmonary nodules. This study analyzed the differences of chest computed tomography (CT) features between IAC and minimally invasive adenocarcinoma (MIA) from three-dimensional and two-dimensional levels, and compared the ability of diagnosing IAC. The non-invasive adenocarcinoma group includes precursor glandular lesions (PGL) and minimally invasive adenocarcinoma (MIA).

METHODS

The clinical data of 1,045 patients with ground glass opacity (GGO) from January to December 2019 were collected. Then the correlation between preoperative CT image characteristics and pathological results were analyzed retrospectively. The independent influencing factors for the identification of IAC were screened out according to two-dimensional and three-dimensional classification by multivariate Logistic regression and the cut-off point for the identification of IAC was found out through the receiver operating characteristic (ROC) curve. At last, the ability of diagnosing IAC was evaluated by Yoden index.

RESULTS

The diameter of nodule, the diameter of solid component, the diameter of mediastinal window nodule in two-dimensional factors, and the volume of nodule, the volume of solid part and the average CT value in three-dimensional factors were independent risk factors for the diagnosis of IAC. These factors were arranged by Yoden index: solid partial volume (0.601)>nodule volume (0.536)>solid component diameter (0.525)>nodule diameter (0.518)>mediastinal window nodule diameter (0.488)>proportion of solid component volume (0.471)>1-tumor disappearance ratio (TDR) (0.468)>consolidation tumor ratio (CTR) (0.394)>average CT value (0.380).

CONCLUSIONS

The CT features of three-dimensional are better than two-dimensional in the diagnosis of IAC, and the size of solid components is better than the overall size of nodules.

A radiomics nomogram for invasiveness prediction in lung adenocarcinoma manifesting as part-solid nodules with solid components smaller than 6 mm

Objective

To investigate whether radiomics can help radiologists and thoracic surgeons accurately predict invasive adenocarcinoma (IAC) manifesting as part-solid nodules (PSNs) with solid components <6 mm and provide a basis for rational clinical decision-making.

Materials and Methods

In total, 1,210 patients (mean age ± standard deviation: 54.28 ± 11.38 years, 374 men and 836 women) from our hospital and another hospital with 1,248 PSNs pathologically diagnosed with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or IAC were enrolled in this study. Among them, 1,050 cases from our hospital were randomly divided into a derivation set (n = 735) and an internal validation set (n = 315), 198 cases from another hospital were used for external validation. Each labeled nodule was segmented, and 105 radiomics features were extracted. Least absolute shrinkage and selection operator (LASSO) was used to calculate Rad-score and build the radiomics model. Multivariable logistic regression was conducted to identify the clinicoradiological predictors and establish the clinical-radiographic model. The combined model and predictive nomogram were developed based on identified clinicoradiological independent predictors and Rad-score using multivariable logistic regression analysis. The predictive performances of the three models were compared via receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was performed on both the internal and external validation sets to evaluate the clinical utility of the nomogram.

Results

The radiomics model showed superior predictive performance than the clinical-radiographic model in both internal and external validation sets (Az values, 0.884 vs. 0.810, p = 0.001; 0.924 vs. 0.855, p < 0.001, respectively). The combined model showed comparable predictive performance to the radiomics model (Az values, 0.887 vs. 0.884, p = 0.398; 0.917 vs. 0.924, p = 0.271, respectively). The clinical application value of the nomogram developed based on the Rad-score, maximum diameter, and lesion shape was confirmed, and DCA demonstrated that application of the Rad-score would be beneficial for radiologists predicting invasive lesions.

Conclusions

Radiomics has the potential as an independent diagnostic tool to predict the invasiveness of PSNs with solid components <6 mm.

Solid Attenuation Components Attention Deep Learning Model to Predict Micropapillary and Solid Patterns in Lung Adenocarcinomas on Computed Tomography

BACKGROUND

High-grade adenocarcinoma subtypes (micropapillary and solid) treated with sublobar resection have an unfavorable prognosis compared with those treated with lobectomy. We investigated the potential of incorporating solid attenuation component masks with deep learning in the prediction of high-grade components to optimize surgical strategy preoperatively.

METHODS

A total of 502 patients with pathologically confirmed high-grade adenocarcinomas were retrospectively enrolled between 2016 and 2020. The SACs attention DL model was developed to apply solid-attenuation-component-like subregion masks (tumor area ≥ - 190 HU) to guide the DL model for predicting high-grade subtypes. The SACA-DL was assessed using 5-fold cross-validation and external validation in the training and testing sets, respectively. The performance, which was evaluated using the area under the curve (AUC), was compared between SACA-DL and the DL model without SACs attention (DL_woSACs), the prior radiomics model, or the model based on the consolidation/tumor (C/T) diameter ratio.

RESULTS

We classified 313 and 189 patients into training and testing cohorts, respectively. The SACA-DL achieved an AUC of 0.91 for the cross-validation, which was significantly superior to those of the DL_woSACs (AUC = 0.88; P = 0.02), prior radiomics model (AUC = 0.85; P = 0.004), and C/T ratio (AUC = 0.84; P = 0.002). An AUC of 0.93 was achieved for external validation in the SACA-DL and was significantly better than those of the DL_woSACs (AUC = 0.89; P = 0.04), prior radiomics model (AUC = 0.85; P < 0.001), and C/T ratio (AUC = 0.85; P < 0.001).

CONCLUSIONS

The combination of solid-attenuation-component-like subregion masks with the DL model is a promising approach for the preoperative prediction of high-grade adenocarcinoma subtypes.

Predictors of Invasiveness in Adenocarcinoma of Lung with Lepidic Growth Pattern

Lung adenocarcinoma with lepidic growth pattern (LPA) is characterized by tumor cell proliferation along intact alveolar walls, and further classified as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA) and invasive lepidic predominant adenocarcinoma (iLPA). Accurate diagnosis of lepidic lesions is critical for appropriate prognostication and management as five-year survival in patients with iLPA is lower than in those with AIS and MIA. We aimed to evaluate the accuracy of CT-guided core needle lung biopsy classifying LPA lesions and identify clinical and radiologic predictors of invasive disease in biopsied lesions. Thirty-four cases of adenocarcinoma with non-invasive lepidic growth pattern on core biopsy pathology that subsequently were resected between 2011 and 2018 were identified. Invasive LPA vs. non-invasive LPA (AIS or MIA) was defined based on explant pathology. Histopathology of core biopsy and resected tumor specimens was compared for concordance, and clinical, radiologic and pathologic variables were analyzed to assess for correlation with invasive disease. The majority of explanted tumors (70.6%) revealed invasive disease. Asian race (p = 0.03), history of extrathoracic malignancy (p = 0.02) and absence of smoking history (p = 0.03) were associated with invasive disease. CT-measured tumor size was not associated with invasiveness (p = 0.15). CT appearance of density (p = 0.61), shape (p = 0.78), and margin (p = 0.24) did not demonstrate a significant difference between the two subgroups. Invasiveness of tumors with lepidic growth patterns can be underestimated on transthoracic core needle biopsies. Asian race, absence of smoking, and history of extrathoracic malignancy were associated with invasive disease.

Solitary Pulmonary Nodule Evaluation: Pearls and Pitfalls

Lung nodules are frequently encountered while interpreting chest CTs and are challenging to detect, characterize, and manage given they can represent both benign or malignant etiologies. An understanding of features associated with malignancy and causes of interpretive pitfalls is helpful to avoid misdiagnoses. This review addresses pertinent topics related to the etiologies for missed lung nodules on radiography and CT. Additionally, CT imaging technical pitfalls and challenges in addition to issues in the evaluation of nodule morphology, attenuation, and size will be discussed. Nodule management guidelines will be addressed as well as recent investigations that further our understanding of lung nodules.

Machine vision-assisted identification of the lung adenocarcinoma category and high-risk tumor area based on CT images

Computed tomography (CT) is a widely used medical imaging technique. It is important to determine the relationship between CT images and pathological examination results of lung adenocarcinoma to better support its diagnosis. In this study, a bilateral-branch network with a knowledge distillation procedure (KDBBN) was developed for the auxiliary diagnosis of lung adenocarcinoma. KDBBN can automatically identify adenocarcinoma categories and detect the lesion area that most likely contributes to the identification of specific types of adenocarcinoma based on lung CT images. In addition, a knowledge distillation process was established for the proposed framework to ensure that the developed models can be applied to different datasets. The results of our comprehensive computational study confirmed that our method provides a reliable basis for adenocarcinoma diagnosis supplementary to the pathological examination. Meanwhile, the high-risk area labeled by KDBBN highly coincides with the related lesion area labeled by doctors in clinical diagnosis.

•

We study machine vision-assisted lung adenocarcinoma classification using CT images

•

We design a holistic machine vision framework, improving classification performance

•

Our method outperforms famous deep CNNs and medical imaging classification methods

•

Our method better explains relations between CT patterns and pathological diagnoses

Lung adenocarcinoma is the most common type of lung cancer; therefore, its early diagnosis is crucial. In this study, we develop a holistic machine vision framework to automatically analyze CT images and identify the lung adenocarcinoma category with impressive performance. Our developed method can provide a reliable supplementary basis for adenocarcinoma diagnosis in clinical settings and can be used to label high-risk areas in CT images so that the relationship between CT characteristics and pathological diagnosis can be determined. Our method can potentially be used as an artificial intelligence (AI) system for adenocarcinoma identification using CT images, which will upgrade adenocarcinoma identification from the traditional expert-based evidence investigation to an automated AI-assisted paradigm.

HRCT features between lepidic-predominant type and other pathological subtypes in early-stage invasive pulmonary adenocarcinoma appearing as a ground-glass nodule

Background

Different pathological subtypes of invasive pulmonary adenocarcinoma (IPA) have different surgical methods and heterogeneous prognosis. It is essential to clarify IPA subtypes before operation and high-resolution computed tomography (HRCT) plays a very important role in this regard. We aimed to investigate the HRCT features of lepidic-predominant type and other pathological subtypes of early-stage (T1N0M0) IPA appearing as a ground-glass nodule (GGN).

Methods

We performed a retrospective analysis on clinical data and HRCT features of 630 lesions in 589 patients with pathologically confirmed IPA (invasive foci > 5 mm) appearing as pure GGN (pGGN) and mixed GGN (mGGN) with consolidation-to-tumor ratio (CTR) ≤0.5 from January to December 2019. All GGNs were classified as lepidic-predominant adenocarcinoma (LPA) and nonlepidic-predominant adenocarcinoma (n-LPA) groups. Univariate analysis was performed to analyze the differences of clinical data and HRCT features between the LPA and n-LPA groups. Multivariate analysis was conducted to determine the variables to distinguish the LPA from n-LPA group independently. The diagnostic performance of different parameters was compared using receiver operating characteristic curves.

Results

In total, 367 GGNs in the LPA group and 263 GGNs in the n-LPA group were identified. In the univariate analysis, the CTR, mean CT values, and mean diameters as well as mixed GGN, deep lobulation, spiculation, vascular change, bronchial change, and tumor–lung interface were smaller in the LPA group than in the n-LPA group (P <  0.05). Logistic regression model was reconstructed including the mean CT value, CTR, deep lobulation, spiculation, vascular change, and bronchial change (P <  0.05). Area under the curve of the logistic regression model for differentiating LPA and n-LPA was 0.840 (76.4% sensitivity, 78.7% specificity), which was significantly higher than that of the mean CT value or CTR.

Conclusions

Deep lobulation, spiculation, vascular change, and bronchial change, CT value > − 472.5 HU and CTR > 27.4% may indicate nonlepidic predominant invasive pulmonary adenocarcinoma in GGNs.

Semi-Quantitative Analysis for Determining the Optimal Threshold Value on CT to Measure the Solid Portion of Pulmonary Subsolid Nodules

PURPOSE

This study aimed to investigate the optimal threshold value in Hounsfield units (HU) on CT to detect the solid components of pulmonary subsolid nodules using pathologic invasive foci as reference.

MATERIALS AND METHODS

Thin-section non-enhanced chest CT scans of 25 patients with pathologically confirmed minimally invasive adenocarcinoma were retrospectively reviewed. On CT images, the solid portion was defined as the area with higher attenuation than various HU thresholds ranging from -600 to -100 HU in 50-HU intervals. The solid portion was measured as the largest diameter on axial images and as the maximum diameter on multiplanar reconstruction images. A linear mixed model was used to evaluate bias in each threshold by using the pathological size of invasive foci as reference.

RESULTS

At a threshold of -400 HU, the biases were lowest between the largest/maximum diameter of the solid portion of subsolid nodule and the size of invasive foci of the pathological specimen, with 0.388 and -0.0176, respectively. They showed insignificant difference (p = 0.2682, p = 0.963, respectively) at a threshold of -400 HU.

CONCLUSION

For quantitative analysis, -400 HU may be the optimal threshold to define the solid portion of subsolid nodules as a surrogate marker of invasive foci.

Development and Validation a Nomogram Incorporating CT Radiomics Signatures and Radiological Features for Differentiating Invasive Adenocarcinoma From Adenocarcinoma In Situ and Minimally Invasive Adenocarcinoma Presenting as Ground-Glass Nodules Measuring 5-10mm in Diameter

Purpose

To develop and validate a nomogram for differentiating invasive adenocarcinoma (IAC) from adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs) measuring 5-10mm in diameter.

Materials and Methods

This retrospective study included 446 patients with 478 GGNs histopathologically confirmed AIS, MIA or IAC. These patients were assigned to a primary cohort, an internal validation cohort and an external validation cohort. The segmentation of these GGNs on thin-slice computed tomography (CT) were performed semi-automatically with in-house software. Radiomics features were then extracted from unenhanced CT images with PyRadiomics. Radiological features of these GGNs were also collected. Radiomics features were investigated for usefulness in building radiomics signatures by spearman correlation analysis, minimum redundancy maximum relevance (mRMR) feature ranking method and least absolute shrinkage and selection operator (LASSO) classifier. Multivariable logistic regression analysis was used to develop a nomogram incorporating the radiomics signature and radiological features. The performance of the nomogram was assessed with discrimination, calibration, clinical usefulness and evaluated on the validation cohorts.

Results

Five radiomics features remained after features selection. The model incorporating radiomics signatures and four radiological features (bubble-like appearance, tumor-lung interface, mean CT value, average diameter) showed good calibration and good discrimination with AUC of 0.831(95%CI, 0.772~0.890). Application of the nomogram in the internal validation cohort with AUC of 0.792 (95%CI, 0.712~0.871) and in the external validation cohort with AUC of 0.833 (95%CI, 0.729-0.938) also indicated good calibration and good discrimination. The decision curve analysis demonstrated that the nomogram was clinically useful.

Conclusion

This study presents a nomogram incorporating the radiomics signatures and radiological features, which can be used to predict the risk of IAC in patients with GGNs measuring 5-10mm in diameter individually.

Generalized chest CT and lab curves throughout the course of COVID-19

A better understanding of temporal relationships between chest CT and labs may provide a reference for disease severity over the disease course. Generalized curves of lung opacity volume and density over time can be used as standardized references from well before symptoms develop to over a month after recovery, when residual lung opacities remain. 739 patients with COVID-19 underwent CT and RT-PCR in an outbreak setting between January 21st and April 12th, 2020. 29 of 739 patients had serial exams (121 CTs and 279 laboratory measurements) over 50 ± 16 days, with an average of 4.2 sequential CTs each. Sequential volumes of total lung, overall opacity and opacity subtypes (ground glass opacity [GGO] and consolidation) were extracted using deep learning and manual segmentation. Generalized temporal curves of CT and laboratory measurements were correlated. Lung opacities appeared 3.4 ± 2.2 days prior to symptom onset. Opacity peaked 1 day after symptom onset. GGO onset was earlier and resolved later than consolidation. Lactate dehydrogenase, and C-reactive protein peaked earlier than procalcitonin and leukopenia. The temporal relationships of quantitative CT features and clinical labs have distinctive patterns and peaks in relation to symptom onset, which may inform early clinical course in patients with mild COVID-19 pneumonia, or may shed light upon chronic lung effects or mechanisms of medical countermeasures in clinical trials.

Distinguishing Adenocarcinomas from Granulomas in the CT scan of the chest: performance degradation evaluation in the automatic segmentation framework

OBJECTIVE

The most common histopathologic malignant and benign nodules are Adenocarcinoma and Granuloma, respectively, which have different standards of care. In this paper, we propose an automatic framework for the diagnosis of the Adenocarcinomas and the Granulomas in the CT scans of the chest from a private dataset. We use the radiomic features of the nodules and the attached vessel tortuosity for the diagnosis. The private dataset includes 22 CTs for each nodule type, i.e., adenocarcinoma and granuloma. The dataset contains the CTs of the non-smoker patients who are between 30 and 60 years old. To automatically segment the delineated nodule area and the attached vessels area, we apply a morphological-based approach. For distinguishing the malignancy of the segmented nodule, two texture features of the nodule, the curvature Mean and the number of the attached vessels are extracted.

RESULTS

We compare our framework with the state-of-the-art feature selection methods for differentiating Adenocarcinomas from Granulomas. These methods employ only the shape features of the nodule, the texture features of the nodule, or the torsion features of the attached vessels along with the radiomic features of the nodule. The accuracy of our framework is improved by considering the four selected features.

Deep learning-based differentiation of invasive adenocarcinomas from preinvasive or minimally invasive lesions among pulmonary subsolid nodules

OBJECTIVES

To evaluate a deep learning-based model using model-generated segmentation masks to differentiate invasive pulmonary adenocarcinoma (IPA) from preinvasive lesions or minimally invasive adenocarcinoma (MIA) on CT, making comparisons with radiologist-derived measurements of solid portion size.

METHODS

Four hundred eleven subsolid nodules (SSNs) (120 preinvasive lesions or MIAs and 291 IPAs) in 333 patients who underwent surgery between June 2010 and August 2016 were retrospectively included to develop the model (370 SSNs in 293 patients for training and 41 SSNs in 40 patients for tuning). Ninety SSNs of 2 cm or smaller (45 preinvasive lesions or MIAs and 45 IPAs) resected in 2018 formed a validation set. Six radiologists measured the solid portion of each nodule. Performances of the model and radiologists were assessed using receiver operating characteristics curve analysis.

RESULTS

The deep learning model differentiated IPA from preinvasive lesions or MIA with areas under the curve (AUCs) of 0.914, 0.956, and 0.833 for the training, tuning, and validation sets, respectively. The mean AUC of the radiologists was 0.835 in the validation set, without significant differences between radiologists and the model (p = 0.97). The sensitivity, specificity, and accuracy of the model were 71% (32/45), 87% (39/45), and 79% (71/90), respectively, whereas the corresponding values of the radiologists were 75.2% (203/270), 76.7% (207/270), and 75.9% (410/540) with a 5-mm threshold for the solid portion size.

CONCLUSIONS

The performance of the model for differentiating IPA from preinvasive lesions or MIA was comparable to that of the radiologists' measurements of solid portion size.

KEY POINTS

• A deep learning-based model differentiated IPA from preinvasive lesions or MIA with AUCs of 0.914 and 0.956 for the training and tuning sets, respectively. • In the validation set including subsolid nodules of 2 cm or smaller, the model showed an AUC of 0.833, being on par with the performance of the solid portion size measurements made by the radiologists (AUC, 0.835; p = 0.97). • SSNs with a solid portion measuring > 10 mm on CT showed a high probability of being IPA (positive predictive value, 93.5-100.0%).

Prediction of micropapillary and solid pattern in lung adenocarcinoma using radiomic values extracted from near-pure histopathological subtypes

OBJECTIVES

Near-pure lung adenocarcinoma (ADC) subtypes demonstrate strong stratification of radiomic values, providing basic information for pathological subtyping. We sought to predict the presence of high-grade (micropapillary and solid) components in lung ADCs using quantitative image analysis with near-pure radiomic values.

METHODS

Overall, 103 patients with lung ADCs of various histological subtypes were enrolled for 10-repetition, 3-fold cross-validation (cohort 1); 55 were enrolled for testing (cohort 2). Histogram and textural features on computed tomography (CT) images were assessed based on the "near-pure" pathological subtype data. Patch-wise high-grade likelihood prediction was performed for each voxel within the tumour region. The presence of high-grade components was then determined based on a volume percentage threshold of the high-grade likelihood area. To compare with quantitative approaches, consolidation/tumour (C/T) ratio was evaluated on CT images; we applied radiological invasiveness (C/T ratio > 0.5) for the prediction.

RESULTS

In cohort 1, patch-wise prediction, combined model (C/T ratio and patch-wise prediction), whole-lesion-based prediction (using only the "near-pure"-based prediction model), and radiological invasiveness achieved a sensitivity and specificity of 88.00 ± 2.33% and 75.75 ± 2.82%, 90.00 ± 0.00%, and 77.12 ± 2.67%, 66.67% and 90.41%, and 90.00% and 45.21%, respectively. The sensitivity and specificity, respectively, for cohort 2 were 100.0% and 95.35% using patch-wise prediction, 100.0% and 95.35% using combined model, 75.00% and 95.35% using whole-lesion-based prediction, and 100.0% and 69.77% using radiological invasiveness.

CONCLUSION

Using near-pure radiomic features and patch-wise image analysis demonstrated high levels of sensitivity and moderate levels of specificity for high-grade ADC subtype-detecting.

KEY POINTS

• The radiomic values extracted from lung adenocarcinoma with "near-pure" histological subtypes provide useful information for high-grade (micropapillary and solid) components detection. • Using near-pure radiomic features and patch-wise image analysis, high-grade components of lung adenocarcinoma can be predicted with high sensitivity and moderate specificity. • Using near-pure radiomic features and patch-wise image analysis has potential role in facilitating the prediction of the presence of high-grade components in lung adenocarcinoma prior to surgical resection.

Repeatability of small lung nodule measurement in low-dose lung screening: a phantom study

Background

Lung cancer screening revealed that people with small pulmonary nodules are mostly asymptomatic and that some of these people are at risk of developing lung cancer, so we intended to explore the repeatability of small lung nodule measurement in low-dose lung screening.

Methods

We scanned eight ground-glass nodules (GGNs) and solid nodules, with diameters of 3, 5, 8, and 10 mm. They were divided according to the different combination schemes of tube voltage (KV) and tube current (mA) as 70, 80, 100, and 120 KV, and currents of nine tubes were divided as 20, 30, 40, 50, 60, 70, 80, 90, and 100 mAs.

Results

Compared with the conventional dose group (120 kVp, 100 mAs), the nodule diameter and solid nodule volume measured by all scanning combinations were more consistent (P > 0.05), the volumes of 10 mm GGNs combinations were consistent (P > 0.05), the volumes of 8 mm GGNs were consistent (P > 0.05), the volumes of 5 mm GGNs combinations were consistent (P > 0.05), and the volumes of 3 mm were consistent (P > 0.05).

Conclusion

In lung cancer screening, CT parameters should be as follows: tube voltage is more than 80 kVp, and tube current is 80 mAs in order to meet the requirements for the accurate measurement of the diameter and volume of pulmonary nodules.

Subsolid pulmonary nodules: Controversy and perspective

Ground glass and part-solid nodules, collectively referred to as subsolid nodules, present a challenge in management, with a high risk of malignancy but, when malignant, demonstrating indolent behavior. Emerging data suggest longer follow-up intervals and shorter duration of follow-up is likely appropriate in these nodules. Additionally, definitive therapy is shifting to less aggressive approaches such as sub-lobar resection. Patients may benefit from individualized approaches, incorporating both patient and imaging features to determine whether treatment is necessary.

Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study

Background Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Purpose To develop and to validate radiomic signatures diagnosing invasive lung adenocarcinoma in PSNs compared with the Brock, clinical-semantic features, and volumetric models. Materials and Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range, 55-65 years; 191 women) from January 2013 to October 2017 with 297 PSN lung adenocarcinomas split into training (n = 229) and test (n = 68) data sets. Radiomic features were extracted from the different regions (gross tumor volume [GTV], solid, ground-glass, and perinodular). Random-forest models were trained using clinical-semantic, volumetric, and radiomic features, and an online nodule calculator was used to compute the Brock model. Performances of models were evaluated using standard metrics such as area under the curve (AUC), accuracy, and calibration. The integrated discrimination improvement was applied to assess model performance changes after the addition of perinodular features. Results The radiomics model based on ground-glass and solid features yielded an AUC of 0.98 (95% confidence interval [CI]: 0.96, 1.00) on the test data set, which was significantly higher than the Brock (AUC, 0.83 [95% CI: 0.72, 0.94]; P = .007), clinical-semantic (AUC, 0.90 [95% CI: 0.83, 0.98]; P = .03), volumetric GTV (AUC, 0.87 [95% CI: 0.78, 0.96]; P = .008), and radiomics GTV (AUC, 0.88 [95% CI: 0.80, 0.96]; P = .01) models. It also achieved the best accuracy (93% [95% CI: 84%, 98%]). Both this model and the model with added perinodular features showed good calibration, whereas adding perinodular features did not improve the performance (integrated discrimination improvement, -0.02; P = .56). Conclusion Separating ground-glass and solid CT radiomic features of part-solid nodules was useful in diagnosing the invasiveness of lung adenocarcinoma, yielding a better predictive performance than the Brock, clinical-semantic, volumetric, and radiomics gross tumor volume models. Online supplemental material is available for this article. See also the editorial by Nishino in this issue. Published under a CC BY 4.0 license.

Efficacy and Cost-effectiveness of Surgical Biopsy for Histologic Diagnosis of Indeterminate Nodules Suspected for Early Stage Lung Cancer: Comparison with Percutaneous Needle Biopsy

BACKGROUND

Indeterminate pulmonary nodules (IPN) suspected for early stage lung cancer mandate accurate diagnosis. Both percutaneous needle biopsy (PCNB) and surgical biopsy (SB) are valuable options. The present study aimed to compare the efficacy and cost-effectiveness between PCNB and SB for IPN suspected for early stage lung cancer.

METHODS

During January-November 2018, patients who underwent operation for IPN suspected for early stage lung cancer (SB group, n = 245) or operation after PCNB (PCNB group, n = 113) were included. Patient-level cost data were extracted from medical bills from the institution. Propensity score matching was performed between the two groups from a retrospectively-collected database.

RESULTS

Fifteen patients (11.5%) had complications after PCNB; thirteen (11.5%) were not confirmed to have lung cancer through PCNB but underwent operation for IPN. In SB group, 172 (70.2%) and 7 (2.9%) patients underwent wedge resection and segmentectomy for SB, respectively; 66 patients (26.9%) underwent direct lobectomy without SB. After propensity score matching, 58 paired samples were produced. Most patients in PCNB group were admitted twice (n = 55, 94.8%). The average hospital stay was longer in PCNB group (12.9 ± 5.3 vs. 7.3 ± 3.0, P < 0.001). Though the cost of the operation was comparable (USD 12,509 ± 2,909 vs. 12,669 ± 3,334; P = 0.782), the total cost was higher for PCNB group (USD 14,403 ± 3,085 vs. 12,669 ± 3,334; P = 0.006). The average subcategory cost, which increases proportional to hospital stay, was higher in PCNB group, whereas the cost of operation and surgical materials were comparable between the two groups.

CONCLUSION

Lung cancer operation following SB for IPN was associated with lesser cost, shorter hospital stays, and lesser admission time than lung cancer operation after PCNB. The increased cost and longer hospital stay appear largely related to the admission for PCNB.

Optimization of CT windowing for diagnosing invasiveness of adenocarcinoma presenting as sub-solid nodules

PURPOSE

To evaluate the optimal window setting to diagnose the invasiveness of lung adenocarcinoma in sub-solid nodules (SSNs).

METHODS

We retrospectively included 437 SSNs and randomly divided them 3:1 into a training group (327) and a testing group (110). The presence of a solid component was regarded as indicator of invasiveness. At fixed window level (WL) of 35 Hounsfield Units (HU), two readers adjusted the window width (WW) in the training group and recorded once a solid component appeared or disappeared on CT images acquired at 120 kVp. The optimal WW cut-off value to differentiate between invasive and pre-invasive lesions, based on the receiver operating characteristic (ROC) curve, was defined as "core" WW. The diagnostic performances of the mediastinal window setting (WW/WL, 350/35 HU) and core window setting were then compared in the testing group.

RESULTS

Of the 437 SSNs, 88 were pre-invasive [17 atypical adenomatous hyperplasia (AAH) and 71 adenocarcinoma in situ (AIS)], 349 were invasive [233 minimally invasive adenocarcinoma (MIA), 116 invasive adenocarcinoma (IA)]. In training group, the core WW of 1175 HU was the optimal cut-off to detect solid components of SSNs (AUC:0.79). In testing group, the sensitivity, specificity, positive, negative predictive value, and diagnostic accuracy for SSN invasiveness were 49.4%, 90.5%, 95.7%, 29.7%, and 57.3% for mediastinal window setting, and 87.6%, 76.2%, 91.6%, 76.2%, and 85.5% for core window setting.

CONCLUSION

At 120 kVp, core window setting (WW/WL, 1175/35 HU) outperformed the traditional mediastinal window setting to diagnose the invasiveness of SSNs.

Value of TSCT Features for Differentiating Preinvasive and Minimally Invasive Adenocarcinoma From Invasive Adenocarcinoma Presenting as Subsolid Nodules Smaller Than 3 cm

BACKGROUND

To distinguish preinvasive (adenocarcinoma in situ/atypical adenomatous hyperplasia) and minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IA) appearing as solitary subsolid nodules (SSNs) less than 3 cm based on thin-section computed tomography (TSCT) features to guide therapeutic approaches.

METHODS

A total of 154 lesions that were histopathologically confirmed to have pre/minimally invasive adenocarcinoma (hereafter pre/MIA) and IA presenting as part-solid nodules (PSNs) or pure ground-glass nodules (pGGNs) were retrospectively reviewed. The TSCT features, including diameter, area, CT value, shape, air bronchogram, margins, and location, were compared and assessed. Receiver operating characteristic analyses were conducted to determine the cut-off values for the qualitative variables and their diagnostic performances.

RESULTS

Of 154 nodules, 89 IA, 53 MIA, eight adenocarcinoma in situ, and four atypical adenomatous hyperplasia lesions were found. Univariate and multivariate logistic regression of the pre/MIA and IA lesions were compared and analyzed among PSNs and pGGNs. Among pGGNs, a significant difference was found in the area (p = 0.004, odds ratio [OR] = 0.124, 95% confidence interval [CI] = 0.300-0.515) between the pre/MIA and IA groups. In PSNs, significant differences were found in the diameter (p = 0.001, OR = 0.171, 95% CI = 0.063-0.467) and CT value (p = 0.001, OR = 0.996, 95% CI = 0.993-0.998) between the pre/MIA and IA groups. According to the corresponding receiver operating characteristic curves, the optimal cut-off tumor area in pGGNs to differentiate pre/MIA from IA was 0.595 cm². A higher CT value of the lesion (≥ -298.500 HU) and a larger diameter (≥1.450 cm) in PSNs were significantly associated with IA.

CONCLUSION

Imaging features from TSCT contribute to distinguishing pre/MIA from IA in solitary subsolid nodules and may contribute to guide the clinical management of these lesions.

A quantitative imaging biomarker for predicting disease-free-survival-associated histologic subgroups in lung adenocarcinoma

OBJECTIVES

Classification of histologic subgroups has significant prognostic value for lung adenocarcinoma patients who undergo surgical resection. However, clinical histopathology assessment is generally performed on only a small portion of the overall tumor from biopsy or surgery. Our objective is to identify a noninvasive quantitative imaging biomarker (QIB) for the classification of histologic subgroups in lung adenocarcinoma patients.

METHODS

We retrospectively collected and reviewed 1313 CT scans of patients with resected lung adenocarcinomas from two geographically distant institutions who were seen between January 2014 and October 2017. Three study cohorts, the training, internal validation, and external validation cohorts, were created, within which lung adenocarcinomas were divided into two disease-free-survival (DFS)-associated histologic subgroups, the mid/poor and good DFS groups. A comprehensive machine learning- and deep learning-based analytical system was adopted to identify reproducible QIBs and help to understand QIBs' significance.

RESULTS

Intensity-Skewness, a QIB quantifying tumor density distribution, was identified as the optimal biomarker for predicting histologic subgroups. Intensity-Skewness achieved high AUCs (95% CI) of 0.849(0.813,0.881), 0.820(0.781,0.856) and 0.863(0.827,0.895) on the training, internal validation, and external validation cohorts, respectively. A criterion of Intensity-Skewness ≤ 1.5, which indicated high tumor density, showed high specificity of 96% (sensitivity 46%) and 99% (sensitivity 53%) on predicting the mid/poor DFS group in the training and external validation cohorts, respectively.

CONCLUSIONS

A QIB derived from routinely acquired CT was able to predict lung adenocarcinoma histologic subgroups, providing a noninvasive method that could potentially benefit personalized treatment decision-making for lung cancer patients.

KEY POINTS

• A noninvasive imaging biomarker, Intensity-Skewness, which described the distortion of pixel-intensity distribution within lesions on CT images, was identified as a biomarker to predict disease-free-survival-associated histologic subgroups in lung adenocarcinoma. • An Intensity-Skewness of ≤ 1.5 has high specificity in predicting the mid/poor disease-free survival histologic patient group in both the training cohort and the external validation cohort. • The Intensity-Skewness is a feature that can be automatically computed with high reproducibility and robustness.

Utility of CT radiomics for prediction of PD-L1 expression in advanced lung adenocarcinomas

Background

We aimed to assess if quantitative radiomic features can predict programmed death ligand 1 (PD‐L1) expression in advanced stage lung adenocarcinoma.

Methods

This retrospective study included 153 patients who had advanced stage (>IIIA by TNM classification) lung adenocarcinoma with pretreatment thin section computed tomography (CT) images and PD‐L1 expression test results in their pathology reports. Clinicopathological data were collected from electronic medical records. Visual analysis and radiomic feature extraction of the tumor from pretreatment CT were performed. We constructed two models for multivariate logistic regression analysis (one based on clinical variables, and the other based on a combination of clinical variables and radiomic features), and compared c‐statistics of the receiver operating characteristic curves of each model to identify the model with the higher predictability.

Results

Among 153 patients, 53 patients were classified as PD‐L1 positive and 100 patients as PD‐L1 negative. There was no significant difference in clinical characteristics or imaging findings on visual analysis between the two groups (P > 0.05 for all). Rad‐score by radiomic analysis was higher in the PD‐L1 positive group than in the PD‐L1 negative group with a statistical significance (−0.378 ± 1.537 vs. −1.171 ± 0.822, P = 0.0008). A prediction model that uses clinical variables and CT radiomic features showed higher performance compared to a prediction model that uses clinical variables only (c‐statistic = 0.646 vs. 0.550, P = 0.0299).

Conclusions

Quantitative CT radiomic features can predict PD‐L1 expression in advanced stage lung adenocarcinoma. A prediction model composed of clinical variables and CT radiomic features may facilitate noninvasive assessment of PD‐L1 expression.

Key points

Significant findings of the study

Quantitative CT radiomic features can help predict PD‐L1 expression, whereas none of the qualitative imaging findings is associated with PD‐L1 positivity.

What this study adds

A prediction model composed of clinical variables and CT radiomic features may facilitate noninvasive assessment of PD‐L1 expression.

Spectral CT imaging parameters and Ki-67 labeling index in lung adenocarcinoma

Objective

To explore the correlation between the spectral computed tomography (CT) imaging parameters and the Ki-67 labeling index in lung adenocarcinoma.

Methods

Spectral CT imaging parameters [iodine concentrations of lesions (ICLs) in the arterial phase (ICLa) and venous phase (ICLv), normalized IC in the aorta (NICa/NICv), slope of the spectral HU curve (λHUa/λHUv) and monochromatic CT number enhancement on 40 keV and 70 keV images (CT40keVa/v, CT70keVa/v)] in 34 lung adenocarcinomas were analyzed, and common molecular markers, including the Ki-67 labeling index, were detected with immunohistochemistry. Different Ki-67 labeling indexes were measured and grouped into four grades according to the number of positive-stained cells (grade 0, ≤1%; 1%<grade 1≤10%; 10%<grade 2≤30%; and grade 3, >30%). One-way analysis of variance (ANOVA) was used to compare the four different grades, and the Bonferroni method was used to correct the P value for multiple comparisons. A Spearman correlation analysis was performed to further research a quantitative correlation between the Ki-67 labeling index and spectral CT imaging parameters.

Results

CT40keVa, CT40keVv, CT70keVa and CT70keVv increased as the grade increased, and CT70keVa and CT70keVv were statistically significant (P<0.05). These four parameters and the Ki-67 labeling index showed a moderate positive correlation with lung adenocarcinoma nodules. ICL, NIC and λHU in the arterial and venous phases were not significantly different among the four grades.

Conclusions

The spectral CT imaging parameters CT40keVa, CT40keVv, CT70keVa and CT70keVv gradually increased with Ki-67 expression and showed a moderate positive correlation with lung adenocarcinomas. Therefore, spectral CT imaging parameter-enhanced monochromatic CT numbers at 70 keV may indicate the extent of proliferation of lung adenocarcinomas.

One-slice CT image based kernelized radiomics model for the prediction of low/mid-grade and high-grade HNSCC

An accurate grade prediction can help to appropriate treatment strategy and effective diagnosis to Head and neck squamous cell carcinoma (HNSCC). Radiomics has been studied for the prediction of carcinoma characteristics in medical images. The success of previous researches in radiomics is attributed to the availability of annotated all-slice medical images. However, it is very challenging to annotate all slices, as annotating biomedical images is not only tedious, laborious, and time consuming, but also demanding of costly, specialty-oriented skills, which are not easily accessible. To address this problem, this paper presents a model to integrate radiomics and kernelized dimension reduction into a single framework, which maps handcrafted radiomics features to a kernelized space where they are linearly separable and then reduces the dimension of features through principal component analysis. Three methods including baseline radiomics models, proposed kernelized model and convolutional neural network (CNN) model were compared in experiments. Results suggested proposed kernelized model best fit in one-slice data. We reached AUC of 95.91 % on self-made one-slice dataset, 67.33 % in predicting localregional recurrence on H&N dataset and 64.33 % on H&N1 dataset. While all other models were <76 %, <65 %, and <62 %. Though CNN model reached an incredible performance when predicting distant metastasis on H&N (AUC 0.88), model faced serious problem of overfitting in small datasets. When changing all-slice data to one-slice on both H&N and H&N1, proposed model suffered less loss on AUC (<1.3 %) than any other models (>3 %). These proved our proposed model is efficient to deal with the one-slice problem and makes using one-slice data to reduce annotation cost practical. This is attributed to the several advantages derived from the proposed kernelized radiomics model, including (1) the prior radiomics features reduced the demanding of huge amount of data and avoided overfitting; (2) the kernelized method mined the potential information contributed to predict; (3) generating principal components in kernelized features reduced redundant features.

Minor components of micropapillary and solid subtypes in lung invasive adenocarcinoma (≤ 3 cm): PET/CT findings and correlations with lymph node metastasis

OBJECTIVE

To investigate the PET/CT findings in lung invasive adenocarcinoma with minor components of micropapillary or solid contents and its association with lymph node metastasis.

MATERIALS AND METHODS

A total of 506 lung invasive adenocarcinoma (≤ 3 cm) patients who underwent a PET/CT examination and resection surgery were included. According to the proportion of solid/micropapillary components, the patients were classified into three groups: solid/micropapillary-negative (SMPN) (n = 258), solid/micropapillary-minor (SMPM; > 5% not predominant) (n = 158) and solid/micropapillary-predominant (SMPP; > 5% most dominant) (n = 90). The patients' PET/CT findings, including SUVmax, MTV, TLG and CT characteristics, and other clinical factors were compared by one-way ANOVA test. Logistic regression analysis was done to identify the most predictive findings for lymph node metastasis.

RESULTS

The value of SUVmax, MTV, TLG and tumor size was highest in SMPP group, followed by SMPM and SMPN group (P < 0.001).The areas under the curve for SUVmax, MTV and TLG for node metastasis were 0.822, 0.843 and 0.835, respectively. Univariate analysis found that the SMPP and SMPM group had more lymph node metastasis than the SMPN group (P < 0.001). Furthermore, the lymph node metastasis group had higher CEA, SUVmax, MTV, TLG, tumor size and more pleural invasion (P < 0.001). Logistic regression analysis found that SMPP pathological type, SMPM pathological type, higher CEA and male patients were risk factors for lymph node metastasis (P < 0.01).

CONCLUSIONS

Lung invasive adenocarcinoma with micropapillary or solid contents had higher SUVmax, MTV, TLG and tumor size and was associated with lymph node metastasis, even if they were not predominant.

Management of incidental pulmonary nodules: current strategies and future perspectives

Introduction: Detection and characterization of pulmonary nodules is an important issue, because the process is the first step in the management of lung cancers.Areas covered: Literature review was performed on May 15 2019 by using the PubMed, US National Library of Medicine National Institutes of Health, and the National Center for Biotechnology information. CT features helping identify the druggable mutations and predict the prognosis of malignant nodules were presented. Technical advancements in MRI and PET/CT were introduced for providing functional information about malignant nodules. Advances in various tissue biopsy techniques enabling molecular analysis and histologic diagnosis of indeterminate nodules were also presented. New techniques such as radiomics, deep learning (DL) technology, and artificial intelligence showing promise in differentiating between malignant and benign nodules were summarized. Recently, updated management guidelines for solid and subsolid nodules incidentally detected on CT were described. Risk stratification and prediction models for indeterminate nodules under active investigation were briefly summarized.Expert opinion: Advancement in CT knowledge has led to a better correlation between CT features and genomic alterations or tumor histology. Recent advances like PET/CT, MRI, radiomics, and DL-based approach have shown promising results in the characterization and prognostication of pulmonary nodules.

A Novel Algorithm to Differentiate Between Multiple Primary Lung Cancers and Intrapulmonary Metastasis in Multiple Lung Cancers With Multiple Pulmonary Sites of Involvement

INTRODUCTION

Differentiating between multiple primary lung cancer (MPLC) and intrapulmonary metastasis (IPM) is critical for developing a therapeutic strategy to treat multiple lung cancers with multiple pulmonary sites of involvement.

METHODS

We retrospectively included 252 lesions (126 pairs) from 126 patients with surgically resected multiple lung adenocarcinomas. Each pair was classified as MPLC or IPM based on histopathologic findings as the reference standard. A novel algorithm was established with four sequential decision steps based on the combination of computed tomography (CT) lesion types (step 1), CT lesion morphology (step 2), difference of maximal standardized uptake values on positron-emission tomography/CT (step 3), and presence of N2/3 lymph node metastasis or distant metastasis (step 4). The diagnostic accuracy of the algorithm was analyzed. Performances of 11 observers were assessed without and with knowledge of algorithm.

RESULTS

Among 126 pairs, 90 (71.4%) were classified as MPLCs and 36 (28.6%) as IPMs. On applying the diagnostic algorithm, the overall accuracy for diagnosis of IPM among conclusive cases up to step 4 was 88.9%, and 65 and 44 pairs were correctly diagnosed based on step 1 and step 2, respectively. Specificity and positive predictive value for diagnosis of IPM increased significantly in all observers compared with reading rounds without the algorithm.

CONCLUSIONS

Application of the algorithm based on comprehensive information on clinical and imaging variables can allow differentiation between MPLCs and IPMs. When both of two suspected malignant lesions appear as solid predominant lesions without spiculation or air-bronchogram on CT, IPM should be considered.

Non-invasive classification of non-small cell lung cancer: a comparison between random forest models utilising radiomic and semantic features

OBJECTIVE

Non-invasive distinction between squamous cell carcinoma and adenocarcinoma subtypes of non-small-cell lung cancer (NSCLC) may be beneficial to patients unfit for invasive diagnostic procedures or when tissue is insufficient for diagnosis. The purpose of our study was to compare the performance of random forest algorithms utilizing CT radiomics and/or semantic features in classifying NSCLC.

METHODS

Two thoracic radiologists scored 11 semantic features on CT scans of 106 patients with NSCLC. A set of 115 radiomics features was extracted from the CT scans. Random forest models were developed from semantic (RM-sem), radiomics (RM-rad), and all features combined (RM-all). External validation of models was performed using an independent test data set (n = 100) of CT scans. Model performance was measured with out-of-bag error and area under curve (AUC), and compared using receiver-operating characteristics curve analysis on the test data set.

RESULTS

The median (interquartile-range) error rates of the models were: RF-sem 24.5 % (22.6 - 37.5 %), RF-rad 35.8 % (34.9 - 38.7 %), and RM-all 37.7 % (37.7 - 37.7). On training data, both RF-rad and RF-all gave perfect discrimination (AUC = 1), which was significantly higher than that achieved by RF-sem (AUC = 0.78; p < 0.0001). On test data, however, RM-sem model (AUC = 0.82) out-performed RM-rad and RM-all (AUC = 0.5 and AUC = 0.56; p < 0.0001), neither of which was significantly different from random guess ( p = 0.9 and 0.6 respectively).

CONCLUSION

Non-invasive classification of NSCLC can be done accurately using random forest classification models based on well-known CT-derived descriptive features. However, radiomics-based classification models performed poorly in this scenario when tested on independent data and should be used with caution, due to their possible lack of generalizability to new data.

ADVANCES IN KNOWLEDGE

Our study describes novel CT-derived random forest models based on radiologist-interpretation of CT scans (semantic features) that can assist NSCLC classification when histopathology is equivocal or when histopathological sampling is not possible. It also shows that random forest models based on semantic features may be more useful than those built from computational radiomic features.

Can Quantitative Volumetric Analysis Predict Tumor Recurrence in the Patients with Mucinous Adenocarcinoma of the Lung After Surgical Resection?

RATIONALE AND OBJECTIVES

Mucinous adenocarcinoma (MAC) is a distinct histologic variant subtype of lung adenocarcinomas. However, detailed radiologic findings and prognostic factors are still poorly understood. Thus, this study aimed to investigate the prognostic value of quantitative volumetric analysis of the computed tomography images of patients with MAC after. surgical resection.

MATERIALS AND METHODS

Semiautomatic segmentation from computed tomography images of 60 patients with pathologically confirmed MAC was performed and retrospectively reviewed. The main cutoff value in Hounsfield Units (HU) to predict tumor recurrence was defined by receiver-operating curve analysis. Solid volume of mass (SVM) was defined as the volume of HU greater than this cutoff, and solid ratio (Sratio) was defined as SVM divided by total volume. Each parameter was compared to clinicopathologic characteristics and maximum standardized uptake value. Disease-free survival (DFS) was assessed and was compared among patients. Univariate and multivariate Cox regression was performed to predict DFS of MAC.

RESULTS

The cutoff value of HU as determined by ROC analysis was 20 HU. SVM and Sratio were positively correlated with the maximum standardized uptake and pathologic invasion size, respectively (p < 0.001). SVM and Sratio were significantly higher in the recurrence group than in the no-recurrence group (p < 0.001). Multivariate Cox proportional hazards regression analysis revealed that the SVM (Hazard Ratio 1.016; 95% Confidence Interval 1.000-1.032; p = 0.048) and Sratio (Hazard Ratio 29.136; 95% Confidence Interval 1.419-598.191; p = 0.029) were independent significant predictors of DFS.

CONCLUSION

Quantitative volumetric parameters can predict the prognosis of patients with MAC after surgical resection.

Histogram-based models on non-thin section chest CT predict invasiveness of primary lung adenocarcinoma subsolid nodules

109 pathologically proven subsolid nodules (SSN) were segmented by 2 readers on non-thin section chest CT with a lung nodule analysis software followed by extraction of CT attenuation histogram and geometric features. Functional data analysis of histograms provided data driven features (FPC1,2,3) used in further model building. Nodules were classified as pre-invasive (P1, atypical adenomatous hyperplasia and adenocarcinoma in situ), minimally invasive (P2) and invasive adenocarcinomas (P3). P1 and P2 were grouped together (T1) versus P3 (T2). Various combinations of features were compared in predictive models for binary nodule classification (T1/T2), using multiple logistic regression and non-linear classifiers. Area under ROC curve (AUC) was used as diagnostic performance criteria. Inter-reader variability was assessed using Cohen’s Kappa and intra-class coefficient (ICC). Three models predicting invasiveness of SSN were selected based on AUC. First model included 87.5 percentile of CT lesion attenuation (Q.875), interquartile range (IQR), volume and maximum/minimum diameter ratio (AUC:0.89, 95%CI:[0.75 1]). Second model included FPC1, volume and diameter ratio (AUC:0.91, 95%CI:[0.77 1]). Third model included FPC1, FPC2 and volume (AUC:0.89, 95%CI:[0.73 1]). Inter-reader variability was excellent (Kappa:0.95, ICC:0.98). Parsimonious models using histogram and geometric features differentiated invasive from minimally invasive/pre-invasive SSN with good predictive performance in non-thin section CT.

Clinical Significance of Pleural Attachment and Indentation of Subsolid Nodule Lung Cancer

Purpose

Lung cancers presenting as subsolid nodule commonly have peripheral location, making the cancer-pleura relationship noteworthy. We aimed to evaluate the effect of pleural attachment and/or indentation on visceral pleural invasion (VPI) and recurrence-free survival.

Materials and Methods

Patients who underwent curative resection of lung cancer as subsolid nodules from April 2007 to January 2016 were retrospectively evaluated. They were divided into four groups according to their relationship with the pleura. Clinical, radiographical, and pathological findings were analyzed.

Results

Among 404 patients with malignant subsolid nodule, 120 (29.7%) had neither pleural attachment nor indentation, 26 (6.4%) had attachment only, 117 (29.0%) had indentation only, and 141 (34.9%) had both. VPI was observed in nodules of 36 patients (8.9%), but absent in nonsolid nodules and in those without pleural attachment and/or indentation. Compared to subsolid nodules with concurrent pleural attachment and indentation, those with attachment only (odds ratio, 0.12; 95% confidence interval [CI], 0.02 to 0.98) and indentation only (odds ratio, 0.10; 95% CI, 0.03 to 0.31) revealed lower odds of VPI. On subgroup analysis, the size of the solid portion was associated with VPI among those with pleural attachment and indentation (p=0.021). Such high-risk features for VPI were associated with earlier lung cancer recurrence (adjusted hazard ratio, 3.31; 95% CI, 1.58 to 6.91).

Conclusion

Concurrent pleural attachment and indentation are risk factors for VPI, and the odds increase with larger solid portion in subsolid nodules. Considering the risk of recurrence, early surgical resection could be encouraged in these patients.

Histogram analysis combined with morphological characteristics to discriminate adenocarcinoma in situ or minimally invasive adenocarcinoma from invasive adenocarcinoma appearing as pure ground-glass nodule

OBJECTIVE

To construct a predictive model to discriminate adenocarcinoma in situ (AIS) or minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IAC) appearing as pure ground-glass nodules (pGGNs) using computed tomography (CT) histogram analysis combined with morphological characteristics and to evaluate its diagnostic performance.

MATERIALS AND METHODS

Two hundred eighty-nine patients with surgically resected solitary pGGN and pathologically diagnosed with AIS, MIA, or IAC in our institution from January 2014 to May 2018 were enrolled in our study. Two hundred twenty-six pGGNs (79 AIS, 84 MIA, and 63 IAC) were randomly selected and assigned to a model-development cohort, and the remaining 63 pGGNs (11 AIS, 29 MIA and 23 IAC) were assigned to a validation cohort. The morphological characteristics were established as model A and histogram parameters as model B. The diagnostic performances of model A, model B, and model A + B were evaluated and compared via receiver operating curve (ROC) analysis and logistic regression analysis.

RESULTS

Entropy (odd ratio [OR] = 23.25, 95%CI: 6.83-79.15, p < 0.001), microvascular sign (OR = 8.62, 95%CI: 3.72-19.98, p < 0.001) and the maximum diameter (OR = 4.37, 95%CI: 2.44-7.84, p < 0.001) were identified as independent predictors in the IAC group. The area under the ROC (Az value), accuracy, sensitivity and specificity of model A + B were 0.896, 88.1%, 79.4% and 91.4%, respectively, exhibiting a significantly higher Az value than either model A or model B alone (0.785 vs 0.896, p < 0.001; 0.849 vs 0.896, p = 0.029). Model A + B also conveyed a good diagnostic performance in the validation cohort, with an Az value of 0.851.

CONCLUSION

Histogram analysis combined with morphological characteristics exhibit a superior diagnostic performance in discriminating AIS-MIA from IAC appearing as pGGNs.

Pathologic T Descriptor of Nonmucinous Lung Adenocarcinomas Now Based on Invasive Tumor Size: How Should Pathologists Measure Invasion?

OBJECTIVES

The eighth edition of the American Joint Committee on Cancer staging manual now stratifies nonmucinous lung adenocarcinomas (nmLACAs) by the size of the invasive component only. This is determined by direct gross or microscopic measurement; however, a calculated invasive size based on the percentage of invasive growth patterns has been proposed as an alternative option.

METHODS

To compare radiologic with different pathologic assessments of invasive tumor size, we retrospectively reviewed a cohort of resected nmLACAs with a part-solid appearance on computed tomography (CT) scan (n = 112).

RESULTS

The median direct microscopic pathologic invasive measurements were not significantly different from the median calculated pathologic invasive measurements; however, the median CT invasive measurements were 0.26 cm larger than the median direct pathologic measurements (P < .001).

CONCLUSIONS

Our results show that pathologic calculated invasive tumor measurements are comparable to direct microscopic measurements of invasive tumor, thereby supporting the recommendation for use of calculated invasive tumor size by the pathologist if necessary.

High versus low attenuation thresholds to determine the solid component of ground-glass opacity nodules

Objectives

To evaluate and compare the diagnostic accuracy of high versus low attenuation thresholds for determining the solid component of ground-glass opacity nodules (GGNs) for the differential diagnosis of adenocarcinoma in situ (AIS) from minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IA).

Methods

Eighty-six pathologically confirmed GGNs < 3 cm observed in 86 patients (27 male, 59 female; mean age, 59.3 ± 11.0 years) between January 2013 and December 2015 were retrospectively included. The solid component of each GGN was defined using two different attenuation thresholds: high (-160 Hounsfield units [HU]) and low (-400 HU). According to the presence or absence of solid portions, each GGN was categorized as a pure GGN or part-solid GGN. Solid components were regarded as indicators of invasive foci, suggesting MIA or IA.

Results

Among the 86 GGNs, there were 57 cases of IA, 19 of MIA, and 10 of AIS. Using the high attenuation threshold, 44 were categorized as pure GGNs and 42 as part-solid GGNs. Using the low attenuation threshold, 13 were categorized as pure GGNs and 73 as part-solid GGNs. The sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy for the invasive focus were 55.2%, 100%, 100%, 22.7%, and 60.4%, respectively, for the high attenuation threshold, and 93.4%, 80%, 97.2%, 61.5%, and 91.8%, respectively, for the low attenuation threshold.

Conclusion

The low attenuation threshold was better than the conventional high attenuation threshold for determining the solid components of GGNs, which indicate invasive foci.

A simple prediction model using size measures for discrimination of invasive adenocarcinomas among incidental pulmonary subsolid nodules considered for resection

OBJECTIVES

To develop and validate a concise prediction model using simple size measures for the discrimination of invasive pulmonary adenocarcinomas (IPAs) among incidentally detected subsolid nodules (SSNs) considered for resection and to compare its diagnostic performance with the Brock model.

METHODS

This retrospective institutional review board-approved study included 427 surgically resected SSNs (121 preinvasive lesions/minimally invasive adenocarcinomas [MIAs] and 306 IPAs) from 407 patients. After stratified random splitting of the study population into the training and validation sets (3:1), a simple logistic model was constructed using nodule size, solid proportion, and type for the differentiation of IPAs. Diagnostic performance of this model was compared with the original and modified Brock models using the DeLong method for area under the receiver-operating characteristic curve (AUC) and McNemar test for diagnostic sensitivity and specificity.

RESULTS

Our proposed model had an AUC of 0.859 in the validation set, while the original Brock model showed an AUC of 0.775 (p = 0.035) and the modified Brock model exhibited an AUC of 0.787 (p = 0.006). At equally high specificity of 90%, our proposed model exhibited significantly higher sensitivity (65.8%) than the original and modified Brock models (38.2% and 50.0%; p < 0.001 and 0.008, respectively).

CONCLUSIONS

Our study results demonstrated that the proposed concise model outperformed both Brock models, demonstrating its potential to be utilized as a specific tool to differentiate IPAs from preinvasive lesions and MIAs, which were considered for resection. External validation studies are warranted for the population with incidentally detected SSNs including small SSNs to confirm our observations.

KEY POINTS

• Size measures provided sufficient information for the risk stratification of surgical candidate incidental subsolid nodules. • Our proposed concise model showed higher diagnostic performance than the Brock model for incidentally detected subsolid nodules. • Our proposed model can specifically differentiate invasive adenocarcinomas among incidentally detected subsolid nodules and reduce overtreatment for indolent subsolid nodules.

Radiomics-based features for pattern recognition of lung cancer histopathology and metastases

BACKGROUND AND OBJECTIVES

lung cancer is the leading cause of cancer-related deaths in the world, and its poor prognosis varies markedly according to tumor staging. Computed tomography (CT) is the imaging modality of choice for lung cancer evaluation, being used for diagnosis and clinical staging. Besides tumor stage, other features, like histopathological subtype, can also add prognostic information. In this work, radiomics-based CT features were used to predict lung cancer histopathology and metastases using machine learning models.

METHODS

local image datasets of confirmed primary malignant pulmonary tumors were retrospectively evaluated for testing and validation. CT images acquired with same protocol were semiautomatically segmented. Tumors were characterized by clinical features and computer attributes of intensity, histogram, texture, shape, and volume. Three machine learning classifiers used up to 100 selected features to perform the analysis.

RESULTS

radiomics-based features yielded areas under the receiver operating characteristic curve of 0.89, 0.97, and 0.92 at testing and 0.75, 0.71, and 0.81 at validation for lymph nodal metastasis, distant metastasis, and histopathology pattern recognition, respectively.

CONCLUSIONS

the radiomics characterization approach presented great potential to be used in a computational model to aid lung cancer histopathological subtype diagnosis as a "virtual biopsy" and metastatic prediction for therapy decision support without the necessity of a whole-body imaging scanning.

Validation of prediction models for risk stratification of incidentally detected pulmonary subsolid nodules: a retrospective cohort study in a Korean tertiary medical centre

OBJECTIVES

To validate the performances of two prediction models (Brock and Lee models) for the differentiation of minimally invasive adenocarcinoma (MIA) and invasive pulmonary adenocarcinoma (IPA) from preinvasive lesions among subsolid nodules (SSNs).

DESIGN

A retrospective cohort study.

SETTING

A tertiary university hospital in South Korea.

PARTICIPANTS

410 patients with 410 incidentally detected SSNs who underwent surgical resection for the pulmonary adenocarcinoma spectrum between 2011 and 2015.

PRIMARY AND SECONDARY OUTCOME MEASURES

Using clinical and radiological variables, the predicted probability of MIA/IPA was calculated from pre-existing logistic models (Brock and Lee models). Areas under the receiver operating characteristic curve (AUCs) were calculated and compared between models. Performance metrics including sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were also obtained.

RESULTS

For pure ground-glass nodules (n=101), the AUC of the Brock model in differentiating MIA/IPA (59/101) from preinvasive lesions (42/101) was 0.671. Sensitivity, specificity, accuracy, PPV and NPV based on the optimal cut-off value were 64.4%, 64.3%, 64.4%, 71.7% and 56.3%, respectively. Sensitivity, specificity, accuracy, PPV and NPV according to the Lee criteria were 76.3%, 42.9%, 62.4%, 65.2% and 56.3%, respectively. AUC was not obtained for the Lee model as a single cut-off of nodule size (≥10 mm) was suggested by this model for the assessment of pure ground-glass nodules. For part-solid nodules (n=309; 26 preinvasive lesions and 283 MIA/IPAs), the AUC was 0.746 for the Brock model and 0.771 for the Lee model (p=0.574). Sensitivity, specificity, accuracy, PPV and NPV were 82.3%, 53.8%, 79.9%, 95.1% and 21.9%, respectively, for the Brock model and 77.0%, 69.2%, 76.4%, 96.5% and 21.7%, respectively, for the Lee model.

CONCLUSIONS

The performance of prediction models for the incidentally detected SSNs in differentiating MIA/IPA from preinvasive lesions might be suboptimal. Thus, an alternative risk calculation model is required for the incidentally detected SSNs.

Evaluation of T categories for pure ground-glass nodules with semi-automatic volumetry: is mass a better predictor of invasive part size than other volumetric parameters?

OBJECTIVES

This study aimed to investigate the diagnostic advantage of nodule mass in differentiating invasive pulmonary adenocarcinomas (IPAs) among pure ground-glass nodules (pGGNs) over other volumetric measurements. Another aim of this study was to analyse the correlation between volumetric measurements on computed tomography (CT) scans and the pathological invasive component size.

METHODS

This Institutional Review Board-approved retrospective study included 117 patients (men:women = 53:64; mean age, 57.3 years) with 117 pGGNs. Semi-automatic segmentation was performed for all nodules, and volumetric measurements, such as nodule volume, attenuation, mass, two-dimensional (2D) average diameter and three-dimensional (3D) longest diameter, were obtained. Receiver operating characteristic (ROC) curve analyses were performed to evaluate the diagnostic performances of the volumetric parameters in discriminating IPAs. Spearman correlation coefficients were calculated between the volumetric measurements and the invasive component size.

RESULTS

Area under the ROC curve for mass was 0.792 (95% CI, 0.691-0.872) in non-enhanced CT and 0.730 (95% CI, 0.607-0.832) in contrast-enhanced CT. Nodule mass was not superior to 2D average diameter for the differentiation of IPAs in both non-enhanced (0.792 vs 0.780; p = 0.501) CT and contrast-enhanced CT scans (0.730 vs 0.700; p = 0.319). The correlation between the volumetric measurements (mass, 3D longest diameter and 2D average diameter) and the invasive component size was moderate (Spearman's rho, 0.401-0.422) in non-enhanced CT and weak (Spearman's rho, 0.276-0.310) in contrast-enhanced CT.

CONCLUSIONS

Nodule mass measurement had no strength over other volumetric parameters for the prediction of pathological invasiveness in the diagnosis of pGGNs.

KEY POINTS

• Mass is not superior to other volumetric measurements for the diagnosis of pure ground-glass nodules. • Mass and two-dimensional average diameter exhibited comparable performance for the discrimination of invasive adenocarcinomas among pure ground-glass nodules. • The diagnostic performance of volumetric measurements was lower on contrast-enhanced CT scans. • The correlation between the volumetric measurements and the invasive component size was moderate on non-enhanced CT scans and weak on contrast-enhanced CT scans.

Screening for early stage lung cancer and its correlation with lung nodule detection

Currently, the most effective way of reducing lung cancer mortality is early diagnosis of lung cancer. The National Lung Screening Trial has proved the efficacy of lung cancer screening using low-dose computed tomography to reduce lung cancer mortality. However, many questions remain surrounding lung cancer screening implementation, among which include how to select the optimal risk population, the personalized screening interval based different levels of risk, methods to improve diagnostic discrimination between malignant and benign disease in detected lung nodules, and the roles of biomolecular markers in stratifying risk and in guiding the management of indeterminate nodules. This review concentrates on the latest developments of lung cancer screening and provides an overview of the main unanswered questions on lung nodule detection.