Observer Variability for Classification of Pulmonary Nodules on Low-Dose CT Images and Its Effect on Nodule Management

Personalised follow-up and management schema for patients with screen-detected pulmonary nodules: A dynamic modelling study

BACKGROUND

Selecting the time target for follow-up testing in lung cancer screening is challenging. We aim to devise dynamic, personalized lung cancer screening schema for patients with pulmonary nodules detected through low-dose computed tomography.

METHODS

We developed and validated dynamic models using data of pulmonary nodule patients (aged 55-74 years) from the National Lung Screening Trial. We predicted patient-specific risk profiles at baseline (R0) and updated the risk evaluation results in repeated screening rounds (R1 and R2). We used risk cutoffs to optimize time-dependent sensitivity at an early decision point (3 months) and time-dependent specificity at a late decision point (1 year).

RESULTS

In validation, area under receiver operating characteristic curve for predicting 12-month lung cancer onset was 0.867 (95 % confidence interval: 0.827-0.894) and 0.807 (0.765-0.948) at R0 and R1-R2, respectively. The personalized schema, compared with National Comprehensive Cancer Network (NCCN) guideline and Lung-RADS, yielded lower rates of delayed diagnosis (1.7% vs. 1.7% vs. 6.9 %) and over-testing (4.9% vs. 5.6% vs. 5.6 %) at R0, and lower rates of delayed diagnosis (0.0% vs. 18.2% vs. 18.2 %) and over-testing (2.6% vs. 8.3% vs. 7.3 %) at R2. Earlier test recommendation among cancer patients was more frequent using the personalized schema (vs. NCCN: 29.8% vs. 20.9 %, p = 0.0065; vs. Lung-RADS: 33.2% vs. 22.8 %, p = 0.0025), especially for women, patients aged ≥65 years, and part-solid or non-solid nodules.

CONCLUSIONS

The personalized schema is easy-to-implement and more accurate compared with rule-based protocols. The results highlight value of personalized approaches in realizing efficient nodule management.

Prognostic value of CT-defined ground-glass opacity in early-stage lung adenocarcinomas: a single-center study and meta-analysis

OBJECTIVES

The prognostic value of ground-glass opacity at preoperative chest CT scans in early-stage lung adenocarcinomas is a matter of debate. We aimed to clarify the existing evidence through a single-center, retrospective cohort study and to quantitatively summarize the body of literature by conducting a meta-analysis.

METHODS

In a retrospective cohort study, patients with clinical stage I lung adenocarcinoma were identified, and the prognostic value of ground-glass opacity was analyzed using multivariable Cox regression. Commercial artificial intelligence software was adopted as the second reader for the presence of ground-glass opacity. The primary end points were freedom from recurrence (FFR) and lung cancer-specific survival (LCSS). In a meta-analysis, we systematically searched Embase and OVID-MEDLINE up to December 30, 2021, for the studies based on the eighth-edition staging system. The pooled hazard ratios (HRs) of solid nodules (i.e., absence of ground-glass opacity) for various end points were calculated with a multi-level random effects model.

RESULTS

In a cohort of 612 patients, solid nodules were associated with worse outcomes for FFR (adjusted HR, 1.98; 95% CI: 1.17-3.51; p = 0.01) and LCSS (adjusted HR, 1.937; 95% CI: 1.002-4.065; p = 0.049). The artificial intelligence assessment and multiple sensitivity analyses revealed consistent results. The meta-analysis included 13 studies with 12,080 patients. The pooled HR of solid nodules was 2.13 (95% CI: 1.69-2.67; I2 = 30.4%) for overall survival, 2.45 (95% CI: 1.52-3.95; I2 = 0.0%) for FFR, and 2.50 (95% CI: 1.28-4.91; I2 = 30.6%) for recurrence-free survival.

CONCLUSIONS

The absence of ground-glass opacity in early-stage lung adenocarcinomas is associated with worse postoperative survival.

CLINICAL RELEVANCE STATEMENT

Early-stage lung adenocarcinomas manifesting as solid nodules at preoperative chest CT, which indicates the absence of ground-glass opacity, were associated with poor postoperative survival. There is room for improvement of the clinical T categorization in the next edition staging system.

KEY POINTS

• In a retrospective study of 612 patients with stage I lung adenocarcinoma, solid nodules were associated with shorter freedom from recurrence (adjusted hazard ratio [HR], 1.98; p = 0.01) and lung cancer-specific survival (adjusted HR, 1.937; p = 0.049). • Artificial intelligence-assessed solid nodules also showed worse prognosis (adjusted HR for freedom from recurrence, 1.94 [p = 0.01]; adjusted HR for lung cancer-specific survival, 1.93 [p = 0.04]). • In meta-analyses, the solid nodules were associated with shorter freedom from recurrence (HR, 2.45) and shorter overall survival (HR, 2.13).

Radiomics and artificial intelligence for risk stratification of pulmonary nodules: Ready for primetime?

Pulmonary nodules are ubiquitously found on computed tomography (CT) imaging either incidentally or via lung cancer screening and require careful diagnostic evaluation and management to both diagnose malignancy when present and avoid unnecessary biopsy of benign lesions. To engage in this complex decision-making, clinicians must first risk stratify pulmonary nodules to determine what the best course of action should be. Recent developments in imaging technology, computer processing power, and artificial intelligence algorithms have yielded radiomics-based computer-aided diagnosis tools that use CT imaging data including features invisible to the naked human eye to predict pulmonary nodule malignancy risk and are designed to be used as a supplement to routine clinical risk assessment. These tools vary widely in their algorithm construction, internal and external validation populations, intended-use populations, and commercial availability. While several clinical validation studies have been published, robust clinical utility and clinical effectiveness data are not yet currently available. However, there is reason for optimism as ongoing and future studies aim to target this knowledge gap, in the hopes of improving the diagnostic process for patients with pulmonary nodules.

Fleischner Society: Glossary of Terms for Thoracic Imaging

Members of the Fleischner Society have compiled a glossary of terms for thoracic imaging that replaces previous glossaries published in 1984, 1996, and 2008, respectively. The impetus to update the previous version arose from multiple considerations. These include an awareness that new terms and concepts have emerged, others have become obsolete, and the usage of some terms has either changed or become inconsistent to a degree that warranted a new definition. This latest glossary is focused on terms of clinical importance and on those whose meaning may be perceived as vague or ambiguous. As with previous versions, the aim of the present glossary is to establish standardization of terminology for thoracic radiology and, thereby, to facilitate communications between radiologists and clinicians. Moreover, the present glossary aims to contribute to a more stringent use of terminology, increasingly required for structured reporting and accurate searches in large databases. Compared with the previous version, the number of images (chest radiography and CT) in the current version has substantially increased. The authors hope that this will enhance its educational and practical value. All definitions and images are hyperlinked throughout the text. Click on each figure callout to view corresponding image. © RSNA, 2024 Supplemental material is available for this article. See also the editorials by Bhalla and Powell in this issue.

Application of computer-aided detection for NCCN-based follow-up recommendation in subsolid nodules: Effect on inter-observer agreement

RATIONALE AND OBJECTIVES

Computer-aided detection (CAD) of pulmonary nodules reduces the impact of observer variability, improving the reliability and reproducibility of nodule assessments in clinical practice. Therefore, this study aimed to assess the impact of CAD on inter-observer agreement in the follow-up management of subsolid nodules.

MATERIALS AND METHODS

A dataset comprising 60 subsolid nodule cases was constructed based on the National Cancer Center lung cancer screening data. Five observers independently assessed all low-dose computed tomography scans and assigned follow-up management strategies to each case according to the National Comprehensive Cancer Network (NCCN) guidelines, using both manual measurements and CAD assistance. The linearly weighted Cohen's kappa test was used to measure agreement between paired observers. Agreement among multiple observers was evaluated using the Fleiss kappa statistic.

RESULTS

The agreement of the five observers for NCCN follow-up management categorization was moderate when measured manually, with a Fleiss kappa score of 0.437. Utilizing CAD led to a notable enhancement in agreement, achieving a substantial consensus with a Fleiss kappa value of 0.623. After using CAD, the proportion of major and substantial management discrepancies decreased from 27.5% to 15.8% and 4.8% to 1.5%, respectively (p < 0.01). In 23 lung cancer cases presenting as part-solid nodules, CAD significantly elevates the average sensitivity in detecting lung cancer cases presenting as part-solid nodules (overall sensitivity, 82.6% vs. 92.2%; p < 0.05).

CONCLUSION

The application of CAD significantly improves inter-observer agreement in the follow-up management strategy for subsolid nodules. It also demonstrates the potential to reduce substantial management discrepancies and increase detection sensitivity in lung cancer cases presenting as part-solid nodules.

Deep learning for malignancy risk estimation of incidental sub-centimeter pulmonary nodules on CT images

OBJECTIVES

To establish deep learning models for malignancy risk estimation of sub-centimeter pulmonary nodules incidentally detected by chest CT and managed in clinical settings.

MATERIALS AND METHODS

Four deep learning models were trained using CT images of sub-centimeter pulmonary nodules from West China Hospital, internally tested, and externally validated on three cohorts. The four models respectively learned 3D deep features from the baseline whole lung region, baseline image patch where the nodule located, baseline nodule box, and baseline plus follow-up nodule boxes. All regions of interest were automatically segmented except that the nodule boxes were additionally manually checked. The performance of models was compared with each other and that of three respiratory clinicians.

RESULTS

There were 1822 nodules (981 malignant) in the training set, 806 (416 malignant) in the testing set, and 357 (253 malignant) totally in the external sets. The area under the curve (AUC) in the testing set was 0.754, 0.855, 0.928, and 0.942, respectively, for models derived from baseline whole lung, image patch, nodule box, and the baseline plus follow-up nodule boxes. When baseline models externally validated (follow-up images not available), the nodule-box model outperformed the other two with AUC being 0.808, 0.848, and 0.939 respectively in the three external datasets. The resident, junior, and senior clinicians achieved an accuracy of 67.0%, 82.5%, and 90.0%, respectively, in the testing set. The follow-up model performed comparably to the senior clinician.

CONCLUSION

The deep learning algorithms solely mining nodule information can efficiently predict malignancy of incidental sub-centimeter pulmonary nodules.

CLINICAL RELEVANCE STATEMENT

The established models may be valuable for supporting clinicians in routine clinical practice, potentially reducing the number of unnecessary examinations and also delays in diagnosis.

KEY POINTS

• According to different regions of interest, four deep learning models were developed and compared to evaluate the malignancy of sub-centimeter pulmonary nodules by CT images. • The models derived from baseline nodule box or baseline plus follow-up nodule boxes demonstrated sufficient diagnostic accuracy (86.4% and 90.4% in the testing set), outperforming the respiratory resident (67.0%) and junior clinician (82.5%). • The proposed deep learning methods may aid clinicians in optimizing follow-up recommendations for sub-centimeter pulmonary nodules and may lead to fewer unnecessary diagnostic interventions.

Computed tomography imaging and clinical characteristics of pulmonary ground-glass nodules ≤2 cm with micropapillary pattern

BACKGROUND

The aim of this study was to investigate the imaging features, lymph node metastasis, and genetic mutations in micropapillary lung adenocarcinoma (imaging with mixed ground-glass nodules) ≤2 cm, to provide a more precise and refined basis for the selection of lung segment resection.

METHODS

A retrospective analysis of 162 patients with surgically resected pathologically confirmed cancers ≤2.0 cm in diameter (50 cases of micropapillary mixed ground-glass nodules [mGGNs], 50 cases of nonmicropapillary mGGNs, and 62 cases of micropapillary SNs [solid nodules]) was performed. mGGNs were classified into five categories according to imaging features. The distribution of these five morphologies in micropapillary with mGGN and nonmicropapillary with mGGN was analyzed. The postoperative pathology and prognosis of lymph node metastasis were also compared between micropapillary mGGNs and micropapillary with SNs. After searching the TCGA database, we demonstrated heterogeneity, high malignancy and high risk of microcapillary lung cancer cancers.

RESULTS

Different pathological subtypes of mGGN differed in morphological features (p < 0.05). The rate of lymph node metastasis was significantly higher in micropapillary mGGNs than in nonmicropapillary mGGNs. In the TCGA database samples, lactate transmembrane protein activity, collagen transcription score, and fibroblast EMT score were remarkably higher in micropapillary adenocarcinoma. Other pathological subtypes had a better survival prognosis and longer disease-free survival compared with micropapillary adenocarcinoma.

CONCLUSION

mGGNs ≤2 cm with a micropapillary pattern have a higher risk of lymph node metastasis compared with SNs, and computed tomography (CT) imaging features can assist in their diagnosis.

CT-based radiomics for prediction of pulmonary haemorrhage after percutaneous CT-guided transthoracic lung biopsy of pulmonary nodules

AIM

To evaluate the feasibility of intranodular and perinodular computed tomography (CT) radiomics features for predicting the occurrence of pulmonary haemorrhage after percutaneous CT-guided transthoracic lung biopsy (PCTLB) in pulmonary nodules.

MATERIALS AND METHODS

The data for 332 patients with pulmonary nodules who underwent PCTLB were reviewed retrospectively. Pulmonary haemorrhage after PCTLB was evaluated using CT (144 cases occurred). Radiomics features based on gross nodular (GNV) and perinodular volumes (PNV) were extracted from pre-biopsy CT images and features selection using least absolute shrinkage and selection operator (LASSO) regression, and three radiomics scores (rad-scores) were built. Rad-scores, clinical, and clinical-radiomic models were developed and evaluated to predict the occurrence of pulmonary haemorrhage.

RESULTS

Five, five, and six significant features were selected for prediction of pulmonary haemorrhage based on GNV, PNV, and GNV + PNV, respectively. Lesion depth was the only clinical characteristics related to pulmonary haemorrhage. Lesion depth and rad-score based on GNV, PNV, and GNV + PNV for predicting the pulmonary haemorrhage achieved areas under the curves (AUCs) of 0.656, 0.645, 0.651, and 0.635 in the validation group, respectively. Three clinical-radiomic models improved the AUCs to 0.743, 0.723, and 0.748. The performance of rad-score_GNV + PNV combined with lesion depth outperformed the clinical model (p=0.024) and the radiomics signature (p=0.038). In addition, the radiomics signatures were significantly associated with higher-grade pulmonary haemorrhage (p<0.05).

CONCLUSIONS

Radiomics features from intranodular and perinodular regions of pulmonary nodules have good predictive ability for pulmonary haemorrhage after PCTLB, which may provide additional predictive value for clinical practice.

Baseline whole-lung CT features deriving from deep learning and radiomics: prediction of benign and malignant pulmonary ground-glass nodules

Objective

To develop and validate the model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features deriving from deep learning and radiomics.

Methods

This retrospective study included 385 GGNs from 3 hospitals, confirmed by pathology. We used 239 GGNs from Hospital 1 as the training and internal validation set; 115 and 31 GGNs from Hospital 2 and Hospital 3 as the external test sets 1 and 2, respectively. An additional 32 stable GGNs from Hospital 3 with more than five years of follow-up were used as the external test set 3. We evaluated clinical and morphological features of GGNs at baseline chest CT and extracted the whole-lung radiomics features simultaneously. Besides, baseline whole-lung CT image features are further assisted and extracted using the convolutional neural network. We used the back-propagation neural network to construct five prediction models based on different collocations of the features used for training. The area under the receiver operator characteristic curve (AUC) was used to compare the prediction performance among the five models. The Delong test was used to compare the differences in AUC between models pairwise.

Results

The model integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features (CMRI) performed best among the five models, and achieved the highest AUC in the internal validation set, external test set 1, and external test set 2, which were 0.886 (95% CI: 0.841-0.921), 0.830 (95%CI: 0.749-0.893) and 0.879 (95%CI: 0.712-0.968), respectively. In the above three sets, the differences in AUC between the CMRI model and other models were significant (all P < 0.05). Moreover, the accuracy of the CMRI model in the external test set 3 was 96.88%.

Conclusion

The baseline whole-lung CT features were feasible to predict the benign and malignant of GGNs, which is helpful for more refined management of GGNs.

The solid component within part-solid nodules: 3-dimensional quantification, correlation with the malignant grade of nonmucinous pulmonary adenocarcinomas, and comparisons with 2-dimentional measures and semantic features in low-dose computed tomography

BACKGROUND

There is no consensus on 3-dimensional (3D) quantification method for solid component within part-solid nodules (PSNs). This study aimed to find the optimal attenuation threshold for the 3D solid component proportion in low-dose computed tomography (LDCT), namely the consolidation/tumor ratio of volume (CTRV), basing on its correlation with the malignant grade of nonmucinous pulmonary adenocarcinomas (PAs) according to the 5th edition of World Health Organization classification. Then we tested the ability of CTRV to predict high-risk nonmucinous PAs in PSNs, and compare its performance with 2-dimensional (2D) measures and semantic features.

METHODS

A total of 313 consecutive patients with 326 PSNs, who underwent LDCT within one month before surgery and were pathologically diagnosed with nonmucinous PAs, were retrospectively enrolled and were divided into training and testing cohorts according to scanners. The CTRV were automatically generated by setting a series of attenuation thresholds from - 400 to 50 HU with an interval of 50 HU. The Spearman's correlation was used to evaluate the correlation between the malignant grade of nonmucinous PAs and semantic, 2D, and 3D features in the training cohort. The semantic, 2D, and 3D models to predict high-risk nonmucinous PAs were constructed using multivariable logistic regression and validated in the testing cohort. The diagnostic performance of these models was evaluated by the area under curve (AUC) of receiver operating characteristic curve.

RESULTS

The CTRV at attenuation threshold of -250 HU (CTRV_- 250HU) showed the highest correlation coefficient among all attenuation thresholds (r = 0.655, P < 0.001), which was significantly higher than semantic, 2D, and other 3D features (all P < 0.001). The AUCs of CTRV_- 250HU to predict high-risk nonmucinous PAs were 0.890 (0.843-0.927) in the training cohort and 0.832 (0.737-0.904) in the testing cohort, which outperformed 2D and semantic models (all P < 0.05).

CONCLUSIONS

The optimal attenuation threshold was - 250 HU for solid component volumetry in LDCT, and the derived CTRV_- 250HU might be valuable for the risk stratification and management of PSNs in lung cancer screening.

Long-term follow-up of persistent pulmonary subsolid nodules: Natural course of pure, heterogeneous, and real part-solid ground-glass nodules

BACKGROUND

Previous studies have suggested the applicability of three classifications of subsolid nodules (SSNs). However, few studies have unraveled the natural history of the three types of SSNs.

METHODS

A retrospective study from two medical centers between November 2007 and November 2017 was conducted to explore the long-term follow-up results of three different types of SSNs, which were divided into pure ground-glass nodules (pGGNs), heterogeneous ground-glass nodules (hGGNs), and real part-solid nodules (rPSNs).

RESULTS

A total of 306 consecutive patients, including 361 SSNs with long-term follow-up, were reviewed. The median growth times of pGGNs, hGGNs, and rPSNs were 7.7, 6.0, and 2.0 years, respectively. For pGGNs, the median period of development into rPSNs was 4.6 years, while that of hGGNs was 1.8 years, and the time from pGGNs to hGGNs was 3.1 years (p < 0.05). In SSNs with an initial lung window consolidation tumor ratio (LW-CTR) >0.5 and mediastinum window (MW)-CTR >0.2, all cases with growth were identified within 5 years. Meanwhile, in SSNs whose LW-CTR and MW-CTR were 0, it took over 5 years to detect nodular growth. Pathologically, 90.6% of initial SSNs with LW-CTR >0 were invasive carcinomas (invasive adenocarcinoma and micro-invasive adenocarcinoma). Among patients with rPSNs in the initial state, 100.0% of the final pathological results were invasive carcinoma. Cox regression showed that age (p = 0.038), initial maximal diameter (p < 0.001), and LW-CTR (p = 0.002) were independent risk factors for SSN growth.

CONCLUSIONS

pGGNs, hGGNs, and rPSNs have significantly different natural histories. Age, initial nodule diameter, and LW-CTR are important risk factors for SSN growth.

Radiomics-based analysis of CT imaging for the preoperative prediction of invasiveness in pure ground-glass nodule lung adenocarcinomas

OBJECTIVE

The purpose of the study is to investigate the performance of radiomics-based analysis in prediction of pure ground-glass nodule (pGGN) lung adenocarcinomas invasiveness using thin-section computed tomography images.

METHODS

A total of 382 patients surgically resected single pGGN and pathologically confirmed were enrolled in the retrospective study. The pGGN cases were divided into two groups: the noninvasive group and the invasive adenocarcinoma (IAC) group. 330 patients were randomly assigned to the training and testing cohorts with a ratio of 7:3 (245 noninvasive lesions, 85 IAC lesions), while 52 patients (30 noninvasive lesions, 22 IAC lesions) were assigned to the external validation cohort. A model, radiomics model, and combined clinical-radiographic-radiomic model were built using the LASSO and multivariate backward stepwise regression analysis on the basis of the selected and radiomics features. The area under the curve (AUC) and decision curve analysis (DCA) were used to evaluate and compare the model performance for invasiveness discrimination among the three cohorts.

RESULTS

Three clinical-radiographic features (including age, gender and the mean CT value) and three radiomics features were selected for model building. The combined model and radiomics model performed better than the clinical-radiographic model. The AUCs of the combined model in the training, testing, and validation cohorts were 0.856, 0.859, and 0.765, respectively. The DCA demonstrated the radiomics signatures incorporating clinical-radiographic feature was clinically useful in predicting pGGN invasiveness.

CONCLUSIONS

The proposed radiomics-based analysis incorporating the clinical-radiographic feature could accurately predict pGGN invasiveness, providing a noninvasive biomarker for the individualized and precise medical treatment of patients.

Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT

OBJECTIVE

To evaluate whether an imaging classifier for radiology practice can improve lung nodule classification and follow-up.

METHODS

A machine learning classifier was developed and trained using imaging data from the National Lung Screening Trial (NSLT) to produce a malignancy risk score (malignancy Similarity Index [mSI]) for individual lung nodules. In addition to NLST cohorts, external cohorts were developed from a tertiary referral lung cancer screening program data set and an external nonscreening data set of all nodules detected on CT. Performance of the mSI combined with Lung-RADS was compared with Lung-RADS alone and the Mayo and Brock risk calculators.

RESULTS

We analyzed 963 subjects and 1,331 nodules across these cohorts. The mSI was comparable in accuracy (area under the curve = 0.89) to existing clinical risk models (area under the curve = 0.86-0.88) and independently predictive in the NLST cohort of 704 nodules. When compared with Lung-RADS, the mSI significantly increased sensitivity across all cohorts (25%-117%), with significant increases in specificity in the screening cohorts (17%-33%). When used in conjunction with Lung-RADS, use of mSI would result in earlier diagnoses and reduced follow-up across cohorts, including the potential for early diagnosis in 42% of malignant NLST nodules from prior-year CT scans.

CONCLUSION

A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI added predictive value independent of existing radiological and clinical variables. These results suggest the generalizability and potential clinical impact of a tool that is straightforward to implement in practice.

Identifying Solitary Granulomatous Nodules from Solid Lung Adenocarcinoma: Exploring Robust Image Features with Cross-Domain Transfer Learning

PURPOSE

This study aimed to find suitable source domain data in cross-domain transfer learning to extract robust image features. Then, a model was built to preoperatively distinguish lung granulomatous nodules (LGNs) from lung adenocarcinoma (LAC) in solitary pulmonary solid nodules (SPSNs).

METHODS

Data from 841 patients with SPSNs from five centres were collected retrospectively. First, adaptive cross-domain transfer learning was used to construct transfer learning signatures (TLS) under different source domain data and conduct a comparative analysis. The Wasserstein distance was used to assess the similarity between the source domain and target domain data in cross-domain transfer learning. Second, a cross-domain transfer learning radiomics model (TLRM) combining the best performing TLS, clinical factors and subjective CT findings was constructed. Finally, the performance of the model was validated through multicentre validation cohorts.

RESULTS

Relative to other source domain data, TLS based on lung whole slide images as source domain data (TLS-LW) had the best performance in all validation cohorts (AUC range: 0.8228-0.8984). Meanwhile, the Wasserstein distance of TLS-LW was 1.7108, which was minimal. Finally, TLS-LW, age, spiculated sign and lobulated shape were used to build the TLRM. In all validation cohorts, The AUC ranges were 0.9074-0.9442. Compared with other models, decision curve analysis and integrated discrimination improvement showed that TLRM had better performance.

CONCLUSIONS

The TLRM could assist physicians in preoperatively differentiating LGN from LAC in SPSNs. Furthermore, compared with other images, cross-domain transfer learning can extract robust image features when using lung whole slide images as source domain data and has a better effect.

[Lung Imaging Reporting and Data System (Lung-RADS) in Radiology: Strengths, Weaknesses and Improvement]

In 2019, the American College of Radiology announced Lung CT Screening Reporting & Data System (Lung-RADS) 1.1 to reduce lung cancer false positivity compared to that of Lung-RADS 1.0 for effective national lung cancer screening, and in December 2022, announced the new Lung-RADS 1.1, Lung-RADS^® 2022 improvement. The Lung-RADS^® 2022 measures the nodule size to the first decimal place compared to that of the Lung-RADS 1.0, to category 2 until the juxtapleural nodule size is < 10 mm, increases the size criterion of the ground glass nodule to 30 mm in category 2, and changes categories 4B and 4X to extremely suspicious. The category was divided according to the airway nodules location and shape or wall thickness of atypical pulmonary cysts. Herein, to help radiologists understand the Lung-RADS^® 2022, this review will describe its advantages, disadvantages, and future improvements.

Evaluation and Management of Indeterminate Pulmonary Nodules on Chest Computed Tomography in Asymptomatic Subjects: The Principles of Nodule Guidelines

With the rapidly increasing number of chest computed tomography (CT) examinations, the question of how to manage lung nodules found in asymptomatic patients has become increasingly important. Several nodule management guidelines have been developed that can be applied to incidentally found lung nodules (the Fleischner Society guideline), nodules found during lung cancer screening (International Early Lung Cancer Action Program protocol [I-ELCAP] and Lung CT Screening Reporting and Data System [Lung-RADS]), or both (American College of Chest Physicians guideline [ACCP], British Thoracic Society guideline [BTS], and National Comprehensive Cancer Network guideline [NCCN]). As the radiologic nodule type (solid, part-solid, and pure ground glass) and size are significant predictors of a nodule's nature, most guidelines categorize nodules in terms of these characteristics. Various methods exist for measuring the size of nodules, and the method recommended in each guideline should be followed. The diameter can be manually measured as a single maximal diameter or as an average of two-dimensional diameters, and software can be used to obtain volumetric measurements. It is important to properly evaluate and measure nodules and familiarize ourselves with the relevant guidelines to appropriately utilize medical resources and minimize unnecessary radiation exposure to patients.

Artificial Intelligence (AI) for Lung Nodules, From the AJR Special Series on AI Applications

Interest in artificial intelligence (AI) applications for lung nodules continues to grow among radiologists, particularly with the expanding eligibility criteria and clinical utilization of lung cancer screening CT. AI has been heavily investigated for detecting and characterizing lung nodules and for guiding prognostic assessment. AI tools have also been used for image postprocessing (e.g., rib suppression on radiography or vessel suppression on CT) and for noninterpretive aspects of reporting and workflow, including management of nodule follow-up. Despite growing interest in and rapid development of AI tools and FDA approval of AI tools for pulmonary nodule evaluation, integration into clinical practice has been limited. Challenges to clinical adoption have included concerns about generalizability, regulatory issues, technical hurdles in implementation, and human skepticism. Further validation of AI tools for clinical use and demonstration of benefit in terms of patient-oriented outcomes also are needed. This article provides an overview of potential applications of AI tools in the imaging evaluation of lung nodules and discusses the challenges faced by practices interested in clinical implementation of such tools.

Identification of pulmonary adenocarcinoma and benign lesions in isolated solid lung nodules based on a nomogram of intranodal and perinodal CT radiomic features

To develop and validate a predictive model based on clinical radiology and radiomics to enhance the ability to distinguish between benign and malignant solitary solid pulmonary nodules. In this study, we retrospectively collected computed tomography (CT) images and clinical data of 286 patients with isolated solid pulmonary nodules diagnosed by surgical pathology, including 155 peripheral adenocarcinomas and 131 benign nodules. They were randomly divided into a training set and verification set at a 7:3 ratio, and 851 radiomic features were extracted from thin-layer enhanced venous phase CT images by outlining intranodal and perinodal regions of interest. We conducted preprocessing measures of image resampling and eigenvalue normalization. The minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (lasso) methods were used to downscale and select features. At the same time, univariate and multifactorial analyses were performed to screen clinical radiology features. Finally, we constructed a nomogram based on clinical radiology, intranodular, and perinodular radiomics features. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUC), and the clinical decision curve (DCA) was used to evaluate the clinical practicability of the models. Univariate and multivariate analyses showed that the two clinical factors of sex and age were statistically significant. Lasso screened four intranodal and four perinodal radiomic features. The nomogram based on clinical radiology, intranodular, and perinodular radiomics features showed the best predictive performance (AUC=0.95, accuracy=0.89, sensitivity=0.83, specificity=0.96), which was superior to other independent models. A nomogram based on clinical radiology, intranodular, and perinodular radiomics features is helpful to improve the ability to predict benign and malignant solitary pulmonary nodules.

Artificial Intelligence Tool for Assessment of Indeterminate Pulmonary Nodules Detected with CT

Background Limited data are available regarding whether computer-aided diagnosis (CAD) improves assessment of malignancy risk in indeterminate pulmonary nodules (IPNs). Purpose To evaluate the effect of an artificial intelligence-based CAD tool on clinician IPN diagnostic performance and agreement for both malignancy risk categories and management recommendations. Materials and Methods This was a retrospective multireader multicase study performed in June and July 2020 on chest CT studies of IPNs. Readers used only CT imaging data and provided an estimate of malignancy risk and a management recommendation for each case without and with CAD. The effect of CAD on average reader diagnostic performance was assessed using the Obuchowski-Rockette and Dorfman-Berbaum-Metz method to calculate estimates of area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Multirater Fleiss κ statistics were used to measure interobserver agreement for malignancy risk and management recommendations. Results A total of 300 chest CT scans of IPNs with maximal diameters of 5-30 mm (50.0% malignant) were reviewed by 12 readers (six radiologists, six pulmonologists) (patient median age, 65 years; IQR, 59-71 years; 164 [55%] men). Readers' average AUC improved from 0.82 to 0.89 with CAD (P < .001). At malignancy risk thresholds of 5% and 65%, use of CAD improved average sensitivity from 94.1% to 97.9% (P = .01) and from 52.6% to 63.1% (P < .001), respectively. Average reader specificity improved from 37.4% to 42.3% (P = .03) and from 87.3% to 89.9% (P = .05), respectively. Reader interobserver agreement improved with CAD for both the less than 5% (Fleiss κ, 0.50 vs 0.71; P < .001) and more than 65% (Fleiss κ, 0.54 vs 0.71; P < .001) malignancy risk categories. Overall reader interobserver agreement for management recommendation categories (no action, CT surveillance, diagnostic procedure) also improved with CAD (Fleiss κ, 0.44 vs 0.52; P = .001). Conclusion Use of computer-aided diagnosis improved estimation of indeterminate pulmonary nodule malignancy risk on chest CT scans and improved interobserver agreement for both risk stratification and management recommendations. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Yanagawa in this issue.

Deep Learning with Multimodal Integration for Predicting Recurrence in Patients with Non-Small Cell Lung Cancer

Due to high recurrence rates in patients with non-small cell lung cancer (NSCLC), medical professionals need extremely accurate diagnostic methods to prevent bleak prognoses. However, even the most commonly used diagnostic method, the TNM staging system, which describes the tumor-size, nodal-involvement, and presence of metastasis, is often inaccurate in predicting NSCLC recurrence. These limitations make it difficult for clinicians to tailor treatments to individual patients. Here, we propose a novel approach, which applies deep learning to an ensemble-based method that exploits patient-derived, multi-modal data. This will aid clinicians in successfully identifying patients at high risk of recurrence and improve treatment planning.

Higher agreement between readers with deep learning CAD software for reporting pulmonary nodules on CT

Purpose

The aim was to evaluate the impact of CAD software on the pulmonary nodule management recommendations of radiologists in a cohort of patients with incidentally detected nodules on CT.

Methods

For this retrospective study, two radiologists independently assessed 50 chest CT cases for pulmonary nodules to determine the appropriate management recommendation, twice, unaided and aided by CAD with a 6-month washout period. Management recommendations were given in a 4-point grade based on the BTS guidelines. Both reading sessions were recorded to determine the reading times per case. A reduction in reading times per session was tested with a one-tailed paired t-test, and a linear weighted kappa was calculated to assess interobserver agreement.

Results

The mean age of the included patients was 65.0 ± 10.9. Twenty patients were male (40 %). For both readers 1 and 2, a significant reduction of reading time was observed of 33.4 % and 42.6 % (p < 0.001, p < 0.001). The linear weighted kappa between readers unaided was 0.61. Readers showed a better agreement with the aid of CAD, namely by a kappa of 0.84. The mean reading time per case was 226.4 ± 113.2 and 320.8 ± 164.2 s unaided and 150.8 ± 74.2 and 184.2 ± 125.3 s aided by CAD software for readers 1 and 2, respectively.

Conclusion

A dedicated CAD system for aiding in pulmonary nodule reporting may help improve the uniformity of management recommendations in clinical practice.

Unusual presentation of lepidic adenocarcinoma in a healthy female

Background

Lepidic adenocarcinoma represents a histologic pattern of non-small cell lung cancer that characteristically arises in the lung periphery with tracking alongside pre-existing alveolar walls. Noninvasive and invasive variants of lepidic adenocarcinoma are dependent on parenchymal destruction, vascular, or pleural invasion. The lepidic-predominant lung malignancies are collectively recognized as slow growing with rare metastasis and excellent prognosis. The World Health Organization classification of lung malignancies depends on molecular and histopathological findings. CT findings most commonly include ground-glass characteristics, commonly mistaken for inflammatory or infectious etiology. These tumors are generally surgically resectable and associated with better survival given infrequent nodal and extrathoracic involvement. Rarely these tumors present with diffuse pneumonic-type involvement associated with worse outcomes despite lack of nodal and distant metastases.

Case presentation

A 63-year-old Caucasian athletic immunocompetent female presented with 2 months of progressive shortness of breath, fatigue, loss of appetite and 15 pound weight loss. History was only notable for well controlled essential hypertension and hypothyroidism. Contrast computed tomography angiogram and positron emission tomography revealed diffuse hypermetabolic interstitial and airspace abnormalities of the lungs without lymphadenopathy (or distant involvement) in addition to right hydropneumothorax and left pleural effusion. Baseline laboratory testing was unremarkable, and extensive bacterial and fungal testing returned negative. Bronchoscopy and video-assisted thoracoscopic surgery was subsequently performed with pleural fluid cytology, lung and pleural biopsies returning positive for lepidic adenocarcinoma with 2% programmed death ligand 1 expression and genomic testing positive for PTEN gene deletion. Prior to treatment, the patient perished on day 15 of admission.

Conclusion

We present a rare case of lepidic predominant adenocarcinoma with extensive bilateral aerogenous spread in the context of no lymphovascular invasion in a healthy, low risk patient. This case presentation may add to the body of knowledge regarding the different behavior patterns of lepidic predominant adenocarcinomas.

Correlation between CT imaging characteristics and pathological diagnosis for subcentimeter pulmonary nodules

Background

Advances in chest computed tomography (CT) have resulted in more frequent detection of subcentimeter pulmonary nodules (SCPNs), some of which are non‐benign and may represent invasive lung cancer. The present study aimed to explore the correlation between pathological diagnosis and the CT imaging manifestations of SCPNs.

Methods

This retrospective study included patients who underwent pulmonary resection for SCPNs at Shandong Provincial Hospital in China. Lesions were divided into five categories according to their morphological characteristics on CT: cotton ball, solid‐filled with spiculation, solid‐filled with smooth edges, mixed‐density ground‐glass, and vacuolar. We further analyzed lesion size, enhancement patterns, vascular aggregation, and SCPN traversing. Chi‐square tests, Fisher's exact tests, and Welch's one‐way analysis of variance were used to examine the correlation between CT imaging characteristics and pathological type.

Results

There were statistically significant differences in the morphological distributions of SCPNs with different pathological types, including benign lesions and malignant lesions at different stages (p < 0.01). The morphological distributions of the four subtypes of invasive lung adenocarcinoma also exhibited significant differences (p < 0.01). In addition, size and enhancement patterns differed significantly among different pathological types of SCPNs.

Conclusion

Different pathological types of SCPNs exhibit significant differences based on their morphological category, size, and enhancement pattern on CT imaging. These CT characteristics may assist in the qualitative diagnosis of SCPNs.

[Research Progress in 3D-reconstruction Based Imaging Analysis in Partial Solid Pulmonary Nodule]

The incidence and mortality of lung cancer rank first among all malignant tumors in China. With the popularization of high resolution computed tomography (CT) in clinic, chest CT has become an important means of clinical screening for early lung cancer and reducing the mortality of lung cancer. Imaging findings of early lung adenocarcinoma often show partial solid nodules with ground glass components. With the development of imaging, the relationship between the imaging features of some solid nodules and their prognosis has attracted more and more attention. At the same time, with the development of 3D-reconstruction technology, clinicians can improve the accuracy of diagnosis and treatment of such nodules.This article focuses on the traditional imaging analysis of partial solid nodules and the imaging analysis based on 3D reconstruction, and systematically expounds the advantages and disadvantages of both.
.

Can Peritumoral Radiomics Improve the Prediction of Malignancy of Solid Pulmonary Nodule Smaller Than 2 cm?

RATIONALE AND OBJECTIVES

To compare the ability of radiomics models including the perinodular parenchyma and standard nodular radiomics model in lung cancer diagnosis of solid pulmonary nodules smaller than 2 cm.

MATERIALS AND METHODS

In this retrospective study, the computed tomography (CT) scans of 206 patients with a lung nodule from a single institution in 2012-2019 were collected. For each nodule, four volumes of interest were defined using the gross tumor volume (GTV) and peritumoral volumes (PTVs) of 5, 10, and 15 mm around the tumor.

RESULTS

Radiomics models created from GTV, GTV plus 5 mm of PTV, GTV plus 10 mm of PTV, and GTV plus 15 mm of PTV achieved AUCs of 0.89, 0.81, 0.81, and 0.73, respectively, in the validation cohort for the diagnostic classification of benign and malignant pulmonary nodules. The performance of the models gradually decreased as the PTV increased. Wavelet features were the primary features identified in optimal radiomics signatures (2/3 in R, 4/5 in GTV plus 5 mm PTV, 3/4 in GTV plus 10 mm PTV, 2/3 in GTV plus 15 mm PTV).

CONCLUSION

Our study indicated that the radiomics signatures of GTV had a good prediction ability in distinguishing benign and malignant solid pulmonary nodules smaller than 2 cm on CT. However, the radiomics feature of the surrounding parenchyma of the nodule did not enhance the effectiveness of the diagnostic model.

A CT-based deep learning model for subsolid pulmonary nodules to distinguish minimally invasive adenocarcinoma and invasive adenocarcinoma

OBJECTIVE

To develop and validate a deep learning nomogram (DLN) model constructed from non-contrast computed tomography (CT) images for discriminating minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IAC) in patients with subsolid pulmonary nodules (SSPNs).

MATERIALS AND METHODS

In total, 365 consecutive patients who presented with SSPNs and were pathologically diagnosed with MIA or IAC after surgery, were recruited from two medical institutions from 2016 to 2019. Deep learning features were selected from preoperative CT images using convolutional neural network. Deep learning signature (DLS) was developed via the least absolute shrinkage and selection operator (LASSO). New DLN integrating clinical variables, subjective CT findings, and DLS was constructed. The diagnostic efficiency and discriminative capability were analyzed using the receiver operating characteristic method and decision curve analysis (DCA).

RESULTS

In total, 18 deep learning features with non-zero coefficients were enrolled to develop the DLS, which was statistically different between the MIA and IAC groups. Independent predictors of DLS and lobulated sharp were used to build the DLN. The areas under the curves of the DLN were 0.889 (95% confidence interval (CI): 0.824-0.936), 0.915 (95% CI: 0.846-0.959), and 0.914 (95% CI: 0.848-0.958) in the training, internal validation, and external validation cohorts, respectively. After stratification analysis and DCA, the DLN showed potential generalization ability.

CONCLUSION

The DLN incorporating the DLS and subjective CT findings have strong potential to distinguish MIA from IAC in patients with SSPNs, and will facilitate the suitable treatment method selection for the management of SSPNs.

End-to-End Non-Small-Cell Lung Cancer Prognostication Using Deep Learning Applied to Pretreatment Computed Tomography

PURPOSE

Clinical TNM staging is a key prognostic factor for patients with lung cancer and is used to inform treatment and monitoring. Computed tomography (CT) plays a central role in defining the stage of disease. Deep learning applied to pretreatment CTs may offer additional, individualized prognostic information to facilitate more precise mortality risk prediction and stratification.

METHODS

We developed a fully automated imaging-based prognostication technique (IPRO) using deep learning to predict 1-year, 2-year, and 5-year mortality from pretreatment CTs of patients with stage I-IV lung cancer. Using six publicly available data sets from The Cancer Imaging Archive, we performed a retrospective five-fold cross-validation using pretreatment CTs of 1,689 patients, of whom 1,110 were diagnosed with non-small-cell lung cancer and had available TNM staging information. We compared the association of IPRO and TNM staging with patients' survival status and assessed an Ensemble risk score that combines IPRO and TNM staging. Finally, we evaluated IPRO's ability to stratify patients within TNM stages using hazard ratios (HRs) and Kaplan-Meier curves.

RESULTS

IPRO showed similar prognostic power (concordance index [C-index] 1-year: 0.72, 2-year: 0.70, 5-year: 0.68) compared with that of TNM staging (C-index 1-year: 0.71, 2-year: 0.71, 5-year: 0.70) in predicting 1-year, 2-year, and 5-year mortality. The Ensemble risk score yielded superior performance across all time points (C-index 1-year: 0.77, 2-year: 0.77, 5-year: 0.76). IPRO stratified patients within TNM stages, discriminating between highest- and lowest-risk quintiles in stages I (HR: 8.60), II (HR: 5.03), III (HR: 3.18), and IV (HR: 1.91).

CONCLUSION

Deep learning applied to pretreatment CT combined with TNM staging enhances prognostication and risk stratification in patients with lung cancer.

Analysis of the mandibular canal course using unsupervised machine learning algorithm

Objectives

Anatomical structure classification is necessary task in medical field, but the inevitable variability of interpretation among experts makes reliable classification difficult. This study aims to introduce cluster analysis, unsupervised machine learning method, for classification of three-dimensional (3D) mandibular canal (MC) courses, and to visualize standard MC courses derived from cluster analysis in the Korean population.

Materials and methods

A total of 429 cone-beam computed tomography images were used. Four sites in the mandible were selected for the measurement of the MC course and four parameters, two vertical and two horizontal parameters were measured per site. Cluster analysis was carried out as follows: parameter measurement, parameter normalization, cluster tendency evaluation, optimal number of clusters determination, and k-means cluster analysis. The 3D MC courses were classified into three types with statistically significant mean differences by cluster analysis.

Results

Cluster 1 showed a smooth line running towards the lingual side in the axial view and a steep slope in the sagittal view. Cluster 2 ran in an almost straight line closest to the lingual and inferior border of mandible. Cluster 3 showed the pathway with a bent buccally in the axial view and an increasing slope in the sagittal view in the posterior area. Cluster 2 showed the highest distribution (42.1%), and males were more widely distributed (57.1%) than the females (42.9%). Cluster 3 comprised similar ratio of male and female cases and accounted for 31.9% of the total distribution. Cluster 1 had the least distribution (26.0%) Distributions of the right and left sides did not show a statistically significant difference.

Conclusion

The MC courses were automatically classified as three types through cluster analysis. Cluster analysis enables the unbiased classification of the anatomical structures by reducing observer variability and can present representative standard information for each classified group.

Clinical Artificial Intelligence Applications in Radiology: Chest and Abdomen

Organ segmentation, chest radiograph classification, and lung and liver nodule detections are some of the popular artificial intelligence (AI) tasks in chest and abdominal radiology due to the wide availability of public datasets. AI algorithms have achieved performance comparable to humans in less time for several organ segmentation tasks, and some lesion detection and classification tasks. This article introduces the current published articles of AI applied to chest and abdominal radiology, including organ segmentation, lesion detection, classification, and predicting prognosis.

Developing of risk models for small solid and subsolid pulmonary nodules based on clinical and quantitative radiomics features

Background

Accurate evaluation of pulmonary nodule malignancy is important for lung cancer management. This current study aimed to develop risk models for small solid and subsolid pulmonary nodules based on clinical and quantitative radiomics features.

Methods

This study enrolled 5–20 mm pulmonary nodules detected on thoracic high-resolution computed tomography (HRCT), which were all confirmed pathologically. There were 548 solid nodules (242 malignant vs. 306 benign) and 623 subsolid nodules (SSNs 519 malignant vs. 104 benign). Relevant clinical characteristics were recorded. The CT image prior to the initial treatment was chosen for manual segmentation of the targeted nodule using the ITK-SNAP software. Subsequently, the marked image was processed to quantitatively extract 1218 radiomics features using PyRadiomics. We performed five-fold cross-validation to select potential predictors from clinical and radiomics features using the LASSO method and to evaluate the performance of the established models. In total, four types of models were tried: random forest, XGBOOST, SVM, and logistic models. The established models were compared with the Mayo model.

Results

Lung cancer risk models were developed among four nodule groups: all nodules (410 benign vs. 761 malignant; 1:1.86), nodules ≤10 mm (185 benign vs. 224 malignant; 1:1.21), solid nodules (306 benign vs. 242 malignant; 1.26:1), and SSNs (104 benign vs. 104 malignant; 1:1 matched). Significant clinical and radiomics predictors were selected for each group. The accuracy, area under the ROC curve, sensitivity, and specificity of the best model on validation dataset was 0.86, 0.91, 0.93, 0.73 for all nodules (XGBOOST), 0.82, 0.90, 0.86, 0.76 for nodules ≤10 mm (XGBOOST), 0.80, 0.89, 0.78, 0.82 for solid nodules (XGBOOST) and 0.70, 0.73, 0.73, 0.67 for SSNs (Random Forest). Except for the SSN models, the established clinical-radiomics models were superior to the Mayo model.

Conclusions

Predictive models based on both clinical and radiomics features can be used to assess the malignancy of small solid and subsolid pulmonary nodules, even for nodules that are 10 mm or smaller.

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

OBJECTIVES

To evaluate the effects of computer-aided diagnosis (CAD) on inter-reader agreement in Lung Imaging Reporting and Data System (Lung-RADS) categorization.

METHODS

Two hundred baseline CT scans covering all Lung-RADS categories were randomly selected from the National Lung Cancer Screening Trial. Five radiologists independently reviewed the CT scans and assigned Lung-RADS categories without CAD and with CAD. The CAD system presented up to five of the most risk-dominant nodules with measurements and predicted Lung-RADS category. Inter-reader agreement was analyzed using multirater Fleiss κ statistics.

RESULTS

The five readers reported 139-151 negative screening results without CAD and 126-142 with CAD. With CAD, readers tended to upstage (average, 12.3%) rather than downstage Lung-RADS category (average, 4.4%). Inter-reader agreement of five readers for Lung-RADS categorization was moderate (Fleiss kappa, 0.60 [95% confidence interval, 0.57, 0.63]) without CAD, and slightly improved to substantial (Fleiss kappa, 0.65 [95% CI, 0.63, 0.68]) with CAD. The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% [201/371] vs. 63.6% [232/365]). The proportion of disagreement in nodule size measurement was reduced from 5.1% (102/2000) to 3.1% (62/2000) with the use of CAD (p < 0.001). In 31 cancer-positive cases, substantial management discrepancies (category 1/2 vs. 4A/B) between reader pairs decreased with application of CAD (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).

CONCLUSIONS

Application of CAD demonstrated a minor improvement in inter-reader agreement of Lung-RADS category, while showing the potential to reduce measurement variability and substantial management change in cancer-positive cases.

KEY POINTS

• Inter-reader agreement of five readers for Lung-RADS categorization was minimally improved by application of CAD, with a Fleiss kappa value of 0.60 to 0.65. • The major cause for disagreement was assignment of different risk-dominant nodules in the reading sessions without and with CAD (54.2% vs. 63.6%). • In 31 cancer-positive cases, substantial management discrepancies between reader pairs, referring to a difference in follow-up interval of at least 9 months (category 1/2 vs. 4A/B), were reduced in half by application of CAD (32/310 to 16/310) (pooled sensitivity, 85.2% vs. 91.6%; p = 0.004).

Impact of computed tomography window settings on clinical T classifications and prognostic evaluation of patients with subsolid nodules

OBJECTIVES

To investigate the impact of lung window (LW) and mediastinal window (MW) settings on the clinical T classifications and prognostic prediction of patients with subsolid nodules.

METHODS

Seven hundred and nineteen surgically resected subsolid nodules were reviewed, grouping into pure ground-glass nodules (n = 179) or part-solid nodules (n = 540) using LW. Interobserver agreement on nodule classifications was assessed via kappa-value, and predictive performance of the solid portion measurement in LW and MW for pathological invasiveness and malignancy were compared using receiver-operating characteristic analysis. Cox regression was used to identify prognostic factors. Prognostic significance of T classifications based on LW (c[l]T) and MW (c[m]T) was evaluated by Kaplan-Meier method after propensity score matching. The performance of c(m)T for discrimination survival was estimated via the concordance index (C-index), net reclassification improvement and integrated-discrimination improvement.

RESULTS

By adopting MW, 124 part-solid nodules were reclassified as pure ground-glass nodules, and interobserver agreement improved to 0.917 (95% confidence interval 0.888-0.946). The solid portion size under MW more strongly predicted pathological invasiveness (P = 0.030), but did not better predict pathological malignancy. For remaining 416 part-solid nodules, c(l)T and c(m)T were both independent risk factors. c(m)T led to T classifications shifts in 321 nodules (14 upstaged and 307 downstaged) with no significant prognostic difference existing between the shifted c(m)T and matching c(l)T group after propensity score matching. The corrected C-index was improved to 0.695 (0.620-1.000) when adopting c(m)T with no significant difference in net reclassification improvement (P = 0.098) and integrated-discrimination improvement (P = 0.13) analysis.

CONCLUSIONS

As there is no significant benefit provided by MW in evaluating clinical T classification and prognosis, the current usage of LW is appropriate for assessing subsolid nodules.

Verification of the eighth edition of the UICC-TNM classification on surgically resected lung adenocarcinoma: Comparison with previous classification in a local center

BACKGROUND

The UICC 8th TNM classification of lung cancer has been changed dramatically, especially in measuring methods of T-desriptors. Different from squamous- or small-cell carcinomas, in which the solid- and the invasive-diameter mostly agree with each other, the diameter of the radiological solid part and that of pathological invasive part in adenocarcinomas often does not match.

AIM

We aimed to determine radiological and pathological tumor diameters of pulmonary adenocarcinomas with clinicopathological factors and evaluate the validity of the 8th edition in comparison with the 7th edition.

METHODS AND RESULTS

We retrospectively analyzed clinicopathological factors of 429 patients with surgically resected pulmonary adenocarcinomas. The maximum tumor and their solid-part diameters were measured using thin-sectioned computed tomography and compared with pathological tumor and invasive diameters. Overall survival (OS) rate was determined using the Kaplan-Meier method for different subgroups of clinicopathological factors. Akaike's information criteria (AIC) was used as a discriminative measure for the univariate Cox model for the 7th and 8th editions. Multivariate Cox regression analysis was performed to explore independent prognostic factors. Correlation coefficients between radiological and pathological diameters in the 7th and 8th editions were 0.911 and 0.888, respectively, without a significant difference. The major reasons for the difference in the 8th edition were the presence of intratumoral fibrosis and papillary growth pattern. The weighted kappa coefficients in the 8th edition were superior those in the 7th edition for both the T and Stage classifications. In the univariate Cox model, AIC levels were the lowest in the 8th edition. Multivariate analysis revealed that age, lymphovascular invasion, pT(8th), and stage were the most important determinants for OS.

CONCLUSION

The UICC 8th edition is a more discriminative classification than the 7th edition. For subsolid nodules, continuous efforts are necessary to increase the universality of the measurement of solid and invasive diameters.

Optimizing the timing of diagnostic testing after positive findings in lung cancer screening: a proof of concept radiomics study

BACKGROUND

The timeliness of diagnostic testing after positive screening remains suboptimal because of limited evidence and methodology, leading to delayed diagnosis of lung cancer and over-examination. We propose a radiomics approach to assist with planning of the diagnostic testing interval in lung cancer screening.

METHODS

From an institute-based lung cancer screening cohort, we retrospectively selected 92 patients with pulmonary nodules with diameters ≥ 3 mm at baseline (61 confirmed as lung cancer by histopathology; 31 confirmed cancer-free). Four groups of region-of-interest-based radiomic features (n = 310) were extracted for quantitative characterization of the nodules, and eight features were proven to be predictive of cancer diagnosis, noise-robust, phenotype-related, and non-redundant. A radiomics biomarker was then built with the random survival forest method. The patients with nodules were divided into low-, middle- and high-risk subgroups by two biomarker cutoffs that optimized time-dependent sensitivity and specificity for decisions about diagnostic workup within 3 months and about repeat screening after 12 months, respectively. A radiomics-based follow-up schedule was then proposed. Its performance was visually assessed with a time-to-diagnosis plot and benchmarked against lung RADS and four other guideline protocols.

RESULTS

The radiomics biomarker had a high time-dependent area under the curve value (95% CI) for predicting lung cancer diagnosis within 12 months; training: 0.928 (0.844, 0.972), test: 0.888 (0.766, 0.975); the performance was robust in extensive cross-validations. The time-to-diagnosis distributions differed significantly between the three patient subgroups, p < 0.001: 96.2% of high-risk patients (n = 26) were diagnosed within 10 months after baseline screen, whereas 95.8% of low-risk patients (n = 24) remained cancer-free by the end of the study. Compared with the five existing protocols, the proposed follow-up schedule performed best at securing timely lung cancer diagnosis (delayed diagnosis rate: < 5%) and at sparing patients with cancer-free nodules from unnecessary repeat screenings and examinations (false recommendation rate: 0%).

CONCLUSIONS

Timely management of screening-detected pulmonary nodules can be substantially improved with a radiomics approach. This proof-of-concept study's results should be further validated in large programs.

Interobserver variability in Lung CT Screening Reporting and Data System categorisation in subsolid nodule-enriched lung cancer screening CTs

OBJECTIVES

To assess interobserver agreement in Lung CT Screening Reporting and Data System (Lung-RADS) categorisation in subsolid nodule-enriched low-dose screening CTs.

METHODS

A retrospective review of low-dose screening CT reports from 2013 to 2017 using keyword searches for subsolid nodules identified 54 baseline CT scans. With an additional 108 negative screening CT scans, a total of 162 CT scans were categorised according to the Lung-RADS by two fellowship-trained thoracic radiologists in consensus. We randomly selected 20, 20, 10, and 10 scans from categories 1/2, 3, 4A, and 4B CT scans, respectively, to ensure balanced category representation. Five radiologists classified the 60 CT scans into Lung-RADS categories. The frequencies of concordance and minor and major discordance were calculated, with major discordance defined as at least 6 months of management discrepancy. We used Cohen's κ statistics to analyse reader agreement.

RESULTS

An average of 60.3% (181 of 300) of all cases and 45.0% (90 of 200) of positive screens were correctly categorised. The minor and major discordance rates were 12.3% and 27.3% overall and 18.5% and 36.5% in positive screens, respectively. The concordance rate was significantly higher among experienced thoracic radiologists. Overall, the interobserver agreement was moderate (mean κ, 0.45; 95% confidence interval: 0.40-0.51). The proportion of part-solid risk-dominant nodules was significantly higher in cases with low rates of accurate categorisation.

CONCLUSION

This retrospective study observed variable accuracy and moderate interobserver agreement in radiologist categorisation of subsolid nodules in screening CTs. This inconsistency may affect management recommendations for lung cancer screening.

KEY POINTS

• Diagnostic performance for Lung-RADS categorisation is variable among radiologists with fair to moderate interobserver agreement in subsolid nodule-enriched CT scans. • Experienced thoracic radiologists showed more accurate and consistent Lung-RADS categorisation than radiology residents. • The relative abundance of part-solid nodules was a potential factor related to increased disagreement in Lung-RADS categorisation.

Screening for Lung Cancer With Low-Dose Computed Tomography: Updated Evidence Report and Systematic Review for the US Preventive Services Task Force

IMPORTANCE

Lung cancer is the leading cause of cancer-related death in the US.

OBJECTIVE

To review the evidence on screening for lung cancer with low-dose computed tomography (LDCT) to inform the US Preventive Services Task Force (USPSTF).

DATA SOURCES

MEDLINE, Cochrane Library, and trial registries through May 2019; references; experts; and literature surveillance through November 20, 2020.

STUDY SELECTION

English-language studies of screening with LDCT, accuracy of LDCT, risk prediction models, or treatment for early-stage lung cancer.

DATA EXTRACTION AND SYNTHESIS

Dual review of abstracts, full-text articles, and study quality; qualitative synthesis of findings. Data were not pooled because of heterogeneity of populations and screening protocols.

MAIN OUTCOMES AND MEASURES

Lung cancer incidence, lung cancer mortality, all-cause mortality, test accuracy, and harms.

RESULTS

This review included 223 publications. Seven randomized clinical trials (RCTs) (N = 86 486) evaluated lung cancer screening with LDCT; the National Lung Screening Trial (NLST, N = 53 454) and Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON, N = 15 792) were the largest RCTs. Participants were more likely to benefit than the US screening-eligible population (eg, based on life expectancy). The NLST found a reduction in lung cancer mortality (incidence rate ratio [IRR], 0.85 [95% CI, 0.75-0.96]; number needed to screen [NNS] to prevent 1 lung cancer death, 323 over 6.5 years of follow-up) with 3 rounds of annual LDCT screening compared with chest radiograph for high-risk current and former smokers aged 55 to 74 years. NELSON found a reduction in lung cancer mortality (IRR, 0.75 [95% CI, 0.61-0.90]; NNS to prevent 1 lung cancer death of 130 over 10 years of follow-up) with 4 rounds of LDCT screening with increasing intervals compared with no screening for high-risk current and former smokers aged 50 to 74 years. Harms of screening included radiation-induced cancer, false-positive results leading to unnecessary tests and invasive procedures, overdiagnosis, incidental findings, and increases in distress. For every 1000 persons screened in the NLST, false-positive results led to 17 invasive procedures (number needed to harm, 59) and fewer than 1 person having a major complication. Overdiagnosis estimates varied greatly (0%-67% chance that a lung cancer was overdiagnosed). Incidental findings were common, and estimates varied widely (4.4%-40.7% of persons screened).

CONCLUSIONS AND RELEVANCE

Screening high-risk persons with LDCT can reduce lung cancer mortality but also causes false-positive results leading to unnecessary tests and invasive procedures, overdiagnosis, incidental findings, increases in distress, and, rarely, radiation-induced cancers. Most studies reviewed did not use current nodule evaluation protocols, which might reduce false-positive results and invasive procedures for false-positive results.

Radiomics in immuno-oncology

With the ongoing advances in imaging techniques, increasing volumes of anatomical and functional data are being generated as part of the routine clinical workflow. This surge of available imaging data coincides with increasing research in quantitative imaging, particularly in the domain of imaging features. An important and novel approach is radiomics, where high-dimensional image properties are extracted from routine medical images. The fundamental principle of radiomics is the hypothesis that biomedical images contain predictive information, not discernible to the human eye, that can be mined through quantitative image analysis. In this review, a general outline of radiomics and artificial intelligence (AI) will be provided, along with prominent use cases in immunotherapy (e.g. response and adverse event prediction) and targeted therapy (i.e. radiogenomics). While the increased use and development of radiomics and AI in immuno-oncology is highly promising, the technology is still in its early stages, and different challenges still need to be overcome. Nevertheless, novel AI algorithms are being constructed with an ever-increasing scope of applications.

Lung-RADS Version 1.1: Challenges and a Look Ahead, From the AJR Special Series on Radiology Reporting and Data Systems

In 2014, the American College of Radiology (ACR) created Lung-RADS 1.0. The system was updated to Lung-RADS 1.1 in 2019, and further updates are anticipated as additional data become available. Lung-RADS provides a common lexicon and standardized nodule follow-up management paradigm for use when reporting lung cancer screening (LCS) low-dose CT (LDCT) chest examinations and serves as a quality assurance and outcome monitoring tool. The use of Lung-RADS is intended to improve LCS performance and lead to better patient outcomes. To date, the ACR's Lung Cancer Screening Registry is the only LCS registry approved by the Centers for Medicare & Medicaid Services and requires the use of Lung-RADS categories for reimbursement. Numerous challenges have emerged regarding the use of Lung-RADS in clinical practice, including the timing of return to LCS after planned follow-up diagnostic evaluation; potential substitution of interval diagnostic CT for future LDCT; role of volumetric analysis in assessing nodule size; assessment of nodule growth; assessment of cavitary, subpleural, and category 4X nodules; and variability in reporting of the S modifier. This article highlights the major updates between versions 1.0 and 1.1 of Lung-RADS, describes the system's ongoing challenges, and summarizes current evidence and recommendations.

Lessons learned in transitioning to AI in the medical imaging of COVID-19

The coronavirus disease 2019 (COVID-19) pandemic has wreaked havoc across the world. It also created a need for the urgent development of efficacious predictive diagnostics, specifically, artificial intelligence (AI) methods applied to medical imaging. This has led to the convergence of experts from multiple disciplines to solve this global pandemic including clinicians, medical physicists, imaging scientists, computer scientists, and informatics experts to bring to bear the best of these fields for solving the challenges of the COVID-19 pandemic. However, such a convergence over a very brief period of time has had unintended consequences and created its own challenges. As part of Medical Imaging Data and Resource Center initiative, we discuss the lessons learned from career transitions across the three involved disciplines (radiology, medical imaging physics, and computer science) and draw recommendations based on these experiences by analyzing the challenges associated with each of the three associated transition types: (1) AI of non-imaging data to AI of medical imaging data, (2) medical imaging clinician to AI of medical imaging, and (3) AI of medical imaging to AI of COVID-19 imaging. The lessons learned from these career transitions and the diffusion of knowledge among them could be accomplished more effectively by recognizing their associated intricacies. These lessons learned in the transitioning to AI in the medical imaging of COVID-19 can inform and enhance future AI applications, making the whole of the transitions more than the sum of each discipline, for confronting an emergency like the COVID-19 pandemic or solving emerging problems in biomedicine.

Approach to the Subsolid Nodule

Most focal persistent ground glass nodules (GGNs) do not progress over 10 years. Research suggests that GGNs that do not progress, those that do, and solid lung cancers are fundamentally different diseases, although histologically they seem similar. Surveillance of GGNs to identify those that gradually progress is safe and does not risk losing a window. GGNs with 5 mm solid component or less than 10 mm consolidation (mediastinal and lung windows, respectively, on thin slice CT) are highly curable with resection. The optimal type of resection is unclear; sublobar resection is reasonable but an adequate margin is critically important.

Putting artificial intelligence (AI) on the spot: machine learning evaluation of pulmonary nodules

Lung cancer remains the leading cause of cancer related death world-wide despite advances in treatment. This largely relates to the fact that many of these patients already have advanced diseases at the time of initial diagnosis. As most lung cancers present as nodules initially, an accurate classification of pulmonary nodules as early lung cancers is critical to reducing lung cancer morbidity and mortality. There have been significant recent advances in artificial intelligence (AI) for lung nodule evaluation. Deep learning (DL) and convolutional neural networks (CNNs) have shown promising results in pulmonary nodule detection and have also excelled in segmentation and classification of pulmonary nodules. This review aims to provide an overview of progress that has been made in AI recently for pulmonary nodule detection and characterization with the ultimate goal of lung cancer prediction and classification while outlining some of the pitfalls and challenges that remain to bring such advancements to routine clinical use.

Artificial neural networks improve LDCT lung cancer screening: a comparative validation study

BACKGROUND

This study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report.

METHODS

This comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models.

RESULTS

At the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P = 0.01). The two most important predictors used by the ANN for predicting lung cancer were the documented sizes of partially solid nodules and ground-glass nodules.

CONCLUSIONS

Compared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.

Clinical T category for lung cancer staging: A pragmatic approach for real-world practice

BACKGROUND

To determine which components should be measured and which window settings are appropriate for computerized tomography (CT) size measurements of lung adenocarcinoma (ADC) and to explore interobserver agreement and accuracy according to the eighth edition of TNM staging.

METHODS

A total of 165 patients with surgically resected lung ADC earlier than stage 3A were included in this study. One radiologist and two pulmonologists independently measured the total and solid sizes of components of tumors on different window settings and assessed solidity. CT measurements were compared with pathologic size measurements.

RESULTS

In categorizing solidity, 25% of the cases showed discordant results among observers. Measuring the total size of a lung adenocarcinoma predicted pathologic invasive components to a degree similar to measuring the solid component. Lung windows were more accurate (intraclass correlation [ICC] = 0.65-0.81) than mediastinal windows (ICC = 0.20-0.72) at predicting pathologic invasive components, especially in a part-solid nodule. Interobserver agreements for measurement of solid components were good with little significant difference (lung windows, ICC = 0.89; mediastinal windows, ICC = 0.91). A high level of interobserver agreement was seen between the radiologist and pulmonologists and between residents (from the division of pulmonology and critical care) versus a fellow (from the division of pulmonology and critical care) on different windows.

CONCLUSIONS

A considerable percentage (25%) of discrepancies was encountered in categorizing the solidity of lesions, which may decrease the accuracy of measurements. Lung window settings may be superior to mediastinal windows for measuring lung ADCs, with comparable interobserver agreement and moderate accuracy for predicting pathologic invasive components.

KEY POINTS

SIGNIFICANT FINDINGS OF THE STUDY: Lung window settings are better for evaluating part-solid lung adenocarcinoma (ADC), with comparable interobserver agreement and moderate accuracy for predicting pathologic invasive components. The considerable percentage (25%) of discrepancies in categorizing solidity of the lesions may also have decreased the accuracy of measurements.

WHAT THIS STUDY ADDS

For accurate measurement and categorization of lung ADC, robust quantitative analysis is needed rather than a simple visual assessment.

Assessing invasiveness of subsolid lung adenocarcinomas with combined attenuation and geometric feature models

The aim of this study was to develop and test multiclass predictive models for assessing the invasiveness of individual lung adenocarcinomas presenting as subsolid nodules on computed tomography (CT). 227 lung adenocarcinomas were included: 31 atypical adenomatous hyperplasia and adenocarcinomas in situ (class H1), 64 minimally invasive adenocarcinomas (class H2) and 132 invasive adenocarcinomas (class H3). Nodules were segmented, and geometric and CT attenuation features including functional principal component analysis features (FPC1 and FPC2) were extracted. After a feature selection step, two predictive models were built with ordinal regression: Model 1 based on volume (log) (logarithm of the nodule volume) and FPC1, and Model 2 based on volume (log) and Q.875 (CT attenuation value at the 87.5% percentile). Using the 200-repeats Monte-Carlo cross-validation method, these models provided a multiclass classification of invasiveness with discriminative power AUCs of 0.83 to 0.87 and predicted the class probabilities with less than a 10% average error. The predictive modelling approach adopted in this paper provides a detailed insight on how the value of the main predictors contribute to the probability of nodule invasiveness and underlines the role of nodule CT attenuation features in the nodule invasiveness classification.

Development and clinical application of deep learning model for lung nodules screening on CT images

Lung cancer screening based on low-dose CT (LDCT) has now been widely applied because of its effectiveness and ease of performance. Radiologists who evaluate a large LDCT screening images face enormous challenges, including mechanical repetition and boring work, the easy omission of small nodules, lack of consistent criteria, etc. It requires an efficient method for helping radiologists improve nodule detection accuracy with efficiency and cost-effectiveness. Many novel deep neural network-based systems have demonstrated the potential for use in the proposed technique to detect lung nodules. However, the effectiveness of clinical practice has not been fully recognized or proven. Therefore, the aim of this study to develop and assess a deep learning (DL) algorithm in identifying pulmonary nodules (PNs) on LDCT and investigate the prevalence of the PNs in China. Radiologists and algorithm performance were assessed using the FROC score, ROC-AUC, and average time consumption. Agreement between the reference standard and the DL algorithm in detecting positive nodules was assessed per-study by Bland-Altman analysis. The Lung Nodule Analysis (LUNA) public database was used as the external test. The prevalence of NCPNs was investigated as well as other detailed information regarding the number of pulmonary nodules, their location, and characteristics, as interpreted by two radiologists.

Assessing the Accuracy of a Deep Learning Method to Risk Stratify Indeterminate Pulmonary Nodules

Rationale: The management of indeterminate pulmonary nodules (IPNs) remains challenging, resulting in invasive procedures and delays in diagnosis and treatment. Strategies to decrease the rate of unnecessary invasive procedures and optimize surveillance regimens are needed.Objectives: To develop and validate a deep learning method to improve the management of IPNs.Methods: A Lung Cancer Prediction Convolutional Neural Network model was trained using computed tomography images of IPNs from the National Lung Screening Trial, internally validated, and externally tested on cohorts from two academic institutions.Measurements and Main Results: The areas under the receiver operating characteristic curve in the external validation cohorts were 83.5% (95% confidence interval [CI], 75.4-90.7%) and 91.9% (95% CI, 88.7-94.7%), compared with 78.1% (95% CI, 68.7-86.4%) and 81.9 (95% CI, 76.1-87.1%), respectively, for a commonly used clinical risk model for incidental nodules. Using 5% and 65% malignancy thresholds defining low- and high-risk categories, the overall net reclassifications in the validation cohorts for cancers and benign nodules compared with the Mayo model were 0.34 (Vanderbilt) and 0.30 (Oxford) as a rule-in test, and 0.33 (Vanderbilt) and 0.58 (Oxford) as a rule-out test. Compared with traditional risk prediction models, the Lung Cancer Prediction Convolutional Neural Network was associated with improved accuracy in predicting the likelihood of disease at each threshold of management and in our external validation cohorts.Conclusions: This study demonstrates that this deep learning algorithm can correctly reclassify IPNs into low- or high-risk categories in more than a third of cancers and benign nodules when compared with conventional risk models, potentially reducing the number of unnecessary invasive procedures and delays in diagnosis.

A CT-based radiomics nomogram for prediction of lung adenocarcinomas and granulomatous lesions in patient with solitary sub-centimeter solid nodules

PURPOSE

To develop a radiomics nomogram based on computed tomography (CT) images that can help differentiate lung adenocarcinomas and granulomatous lesions appearing as sub-centimeter solid nodules (SCSNs).

MATERIALS AND METHODS

The records of 214 consecutive patients with SCSNs that were surgically resected and histologically confirmed as lung adenocarcinomas (n = 112) and granulomatous lesions (n = 102) from 2 medical institutions between October 2011 and June 2019 were retrospectively analyzed. Patients from center 1 ware enrolled as training cohort (n = 150) and patients from center 2 were included as external validation cohort (n = 64), respectively. Radiomics features were extracted from non-contrast chest CT images preoperatively. The least absolute shrinkage and selection operator (LASSO) regression model was used for radiomics feature extraction and radiomics signature construction. Clinical characteristics, subjective CT findings, and radiomics signature were used to develop a predictive radiomics nomogram. The performance was examined by assessment of the area under the receiver operating characteristic curve (AUC).

RESULTS

Lung adenocarcinoma was significantly associated with an irregular margin and lobulated shape in the training set (p = 0.001, < 0.001) and external validation set (p = 0.016, = 0.018), respectively. The radiomics signature consisting of 22 features was significantly associated with lung adenocarcinomas of SCSNs (p < 0.001). The radiomics nomogram incorporated the radiomics signature, gender and lobulated shape. The AUCs of combined model in the training and external validation dataset were 0.885 (95% confidence interval [CI]: 0.823-0.931), 0.808 (95% CI: 0.690-0.896), respectively. Decision curve analysis (DCA) demonstrated that the radiomics nomogram was clinically useful.

CONCLUSION

A radiomics signature based on non-enhanced CT has the potential to differentiate between lung adenocarcinomas and granulomatous lesions. The radiomics nomogram incorporating the radiomics signature and subjective findings may facilitate the individualized, preoperative treatment in patients with SCSNs.

Radiological-pathological correlation of subsolid pulmonary nodules: A single centre retrospective evaluation of the 2011 IASLC adenocarcinoma classification system

INTRODUCTION

The 2011 IASLC classification system proposes guidelines for radiologists and pathologists to classify adenocarcinomas spectrum lesions as preinvasive, minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IA). IA portends the worst clinical prognosis, and the imaging distinction between MIA and IA is controversial.

MATERIALS AND METHODS

Subsolid pulmonary nodules resected by microcoil localization over a three-year period were retrospectively reviewed by three chest radiologists and a pulmonary pathologist. Nodules were classified radiologically based on preoperative computed tomography (CT), with the solid nodule component measured on mediastinal windows applied to high-frequency lung kernel reconstructions, and pathologically according to 2011 IASLC criteria. Radiology interobserver and radiological-pathological variability of nodule classification, and potential reasons for nodule classification discordance were assessed.

RESULTS

Seventy-one subsolid nodules in 67 patients were included. The average size of invasive disease focus at histopathology was 5 mm (standard deviation 5 mm). Radiology interobserver agreement of nodule classification was good (Cohen's Kappa = 0.604, 95 % CI: 0.447 to 0.761). Agreement between consensus radiological interpretation and pathological category was fair (Cohen's Kappa = 0.236, 95 % CI: 0.054-0.421). Radiological and pathological nodule classification were concordant in 52 % (37 of 71) of nodules. The IASLC proposed CT solid component cut-off of 5 mm to distinguish MIA and IA yielded a sensitivity of 59 % and specificity of 80 %. Common reasons for nodule classification discordance included multiple solid components within a nodule on CT, scar and stromal collapse at pathology, and measurement variability.

CONCLUSION

Solid component(s) within persistent part-solid pulmonary nodules raise suspicion for invasive adenocarcinoma. Preoperative imaging classification is frequently discordant from final pathology, reflecting interpretive and technical challenges in radiological and pathological analysis.