Novel high-resolution computed tomography-based radiomic classifier for screen-identified pulmonary nodules in the National Lung Screening Trial

Imaging of Solid Pulmonary Nodules

Early detection with accurate classification of solid pulmonary nodules is critical in reducing lung cancer morbidity and mortality. Computed tomography (CT) remains the most widely used imaging examination for pulmonary nodule evaluation; however, other imaging modalities, such as PET/CT and MRI, are increasingly used for nodule characterization. Current advances in solid nodule imaging are largely due to developments in machine learning, including automated nodule segmentation and computer-aided detection. This review explores current multi-modality solid pulmonary nodule detection and characterization with discussion of radiomics and risk prediction models.

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.

Prospective Detection of Early Lung Cancer in Patients With COPD in Regular Care by Electronic Nose Analysis of Exhaled Breath

BACKGROUND

Patients with COPD are at high risk of lung cancer developing, but no validated predictive biomarkers have been reported to identify these patients. Molecular profiling of exhaled breath by electronic nose (eNose) technology may qualify for early detection of lung cancer in patients with COPD.

RESEARCH QUESTION

Can eNose technology be used for prospective detection of early lung cancer in patients with COPD?

STUDY DESIGN AND METHODS

BreathCloud is a real-world multicenter prospective follow-up study using diagnostic and monitoring visits in day-to-day clinical care of patients with a standardized diagnosis of asthma, COPD, or lung cancer. Breath profiles were collected at inclusion in duplicate by a metal-oxide semiconductor eNose positioned at the rear end of a pneumotachograph (SpiroNose; Breathomix). All patients with COPD were managed according to standard clinical care, and the incidence of clinically diagnosed lung cancer was prospectively monitored for 2 years. Data analysis involved advanced signal processing, ambient air correction, and statistics based on principal component (PC) analysis, linear discriminant analysis, and receiver operating characteristic analysis.

RESULTS

Exhaled breath data from 682 patients with COPD and 211 patients with lung cancer were available. Thirty-seven patients with COPD (5.4%) demonstrated clinically manifest lung cancer within 2 years after inclusion. Principal components 1, 2, and 3 were significantly different between patients with COPD and those with lung cancer in both training and validation sets with areas under the receiver operating characteristic curve of 0.89 (95% CI, 0.83-0.95) and 0.86 (95% CI, 0.81-0.89). The same three PCs showed significant differences (P < .01) at baseline between patients with COPD who did and did not subsequently demonstrate lung cancer within 2 years, with a cross-validation value of 87% and an area under the receiver operating characteristic curve of 0.90 (95% CI, 0.84-0.95).

INTERPRETATION

Exhaled breath analysis by eNose identified patients with COPD in whom lung cancer became clinically manifest within 2 years after inclusion. These results show that eNose assessment may detect early stages of lung cancer in patients with COPD.

Update on Biomarkers for the Stratification of Indeterminate Pulmonary Nodules

Lung cancer is the leading cause of cancer-related deaths. Early detection and diagnosis are critical, as survival decreases with advanced stages. Approximately 1.6 million nodules are incidentally detected every year on chest CT scan images in the United States. This number of nodules identified is likely much larger after accounting for screening-detected nodules. Most of these nodules, whether incidentally or screening detected, are benign. Despite this, many patients undergo unnecessary invasive procedures to rule out cancer because our current stratification approaches are suboptimal, particularly for intermediate probability nodules. Thus, noninvasive strategies are urgently needed. Biomarkers have been developed to assist through the continuum of lung cancer care and include blood protein-based biomarkers, liquid biopsies, quantitative imaging analysis (radiomics), exhaled volatile organic compounds, and bronchial or nasal epithelium genomic classifiers, among others. Although many biomarkers have been developed, few have been integrated into clinical practice as they lack clinical utility studies showing improved patient-centered outcomes. Rapid technologic advances and large network collaborative efforts will continue to drive the discovery and validation of many novel biomarkers. Ultimately, however, randomized clinical utility studies showing improved patient outcomes will be required to bring biomarkers into clinical practice.

Differentiation of Lung Metastases Originated From Different Primary Tumors Using Radiomics Features Based on CT Imaging

RATIONALE AND OBJECTIVES

To explore the feasibility of differentiating three predominant metastatic tumor types using lung computed tomography (CT) radiomics features based on supervised machine learning.

MATERIALS AND METHODS

This retrospective analysis included 252 lung metastases (LM) (from 78 patients), which were divided into the training (n = 176) and test (n = 76) cohort randomly. The metastases originated from colorectal cancer (n = 97), breast cancer (n = 87), and renal carcinoma (n = 68). An additional 77 LM (from 35 patients) were used for external validation. All radiomics features were extracted from lung CT using an open-source software called 3D slicer. The least absolute shrinkage and selection operator (LASSO) method selected the optimal radiomics features to build the model. Random forest and support vector machine (SVM) were selected to build three-class and two-class models. The performance of the classification model was evaluated with the area under the receiver operating characteristic curve (AUC) by two strategies: one-versus-rest and one-versus-one.

RESULTS

Eight hundred and fifty-one quantitative radiomics features were extracted from lung CT. By LASSO, 23 optimal features were extracted in three-class, and 25, 29, and 35 features in two-class for differentiating every two of three LM (colorectal cancer vs. renal carcinoma, colorectal cancer vs. breast cancer, and breast cancer vs. renal carcinoma, respectively). The AUCs of the three-class model were 0.83 for colorectal cancer, 0.79 for breast cancer, and 0.91 for renal carcinoma in the test cohort. In the external validation cohort, the AUCs were 0.77, 0.83, and 0.81, respectively. Swarmplot shows the distribution of radiomics features among three different LM types. In the two-class model, high accuracy and AUC were obtained by SVM. The AUC of discriminating colorectal cancer LM from renal carcinoma LM was 0.84, and breast cancer LM from colorectal cancer LM and renal carcinoma LM were 0.80 and 0.94, respectively. The AUCs were 0.77, 0.78, and 0.84 in the external validation cohort.

CONCLUSION

Quantitative radiomics features based on Lung CT exhibited good discriminative performance in LM of primary colorectal cancer, breast cancer, and renal carcinoma.

Non-Invasive Biomarkers for Early Lung Cancer Detection

Worldwide, lung cancer (LC) is the most common cause of cancer death, and any delay in the detection of new and relapsed disease serves as a major factor for a significant proportion of LC morbidity and mortality. Though invasive methods such as tissue biopsy are considered the gold standard for diagnosis and disease monitoring, they have several limitations. Therefore, there is an urgent need to identify and validate non-invasive biomarkers for the early diagnosis, prognosis, and treatment of lung cancer for improved patient management. Despite recent progress in the identification of non-invasive biomarkers, currently, there is a shortage of reliable and accessible biomarkers demonstrating high sensitivity and specificity for LC detection. In this review, we aim to cover the latest developments in the field, including the utility of biomarkers that are currently used in LC screening and diagnosis. We comment on their limitations and summarise the findings and developmental stages of potential molecular contenders such as microRNAs, circulating tumour DNA, and methylation markers. Furthermore, we summarise research challenges in the development of biomarkers used for screening purposes and the potential clinical applications of newly discovered biomarkers.

Deep Learning Algorithms for Diagnosis of Lung Cancer: A Systematic Review and Meta-Analysis

We conducted a systematic review and meta-analysis of the diagnostic performance of current deep learning algorithms for the diagnosis of lung cancer. We searched major databases up to June 2022 to include studies that used artificial intelligence to diagnose lung cancer, using the histopathological analysis of true positive cases as a reference. The quality of the included studies was assessed independently by two authors based on the revised Quality Assessment of Diagnostic Accuracy Studies. Six studies were included in the analysis. The pooled sensitivity and specificity were 0.93 (95% CI 0.85−0.98) and 0.68 (95% CI 0.49−0.84), respectively. Despite the significantly high heterogeneity for sensitivity (I2 = 94%, p < 0.01) and specificity (I2 = 99%, p < 0.01), most of it was attributed to the threshold effect. The pooled SROC curve with a bivariate approach yielded an area under the curve (AUC) of 0.90 (95% CI 0.86 to 0.92). The DOR for the studies was 26.7 (95% CI 19.7−36.2) and heterogeneity was 3% (p = 0.40). In this systematic review and meta-analysis, we found that when using the summary point from the SROC, the pooled sensitivity and specificity of DL algorithms for the diagnosis of lung cancer were 93% and 68%, respectively.

Form Factors as Potential Imaging Biomarkers to Differentiate Benign vs. Malignant Lung Lesions on CT Scans

Indeterminate lung nodules detected on CT scans are common findings in clinical practice. Their correct assessment is critical, as early diagnosis of malignancy is crucial to maximise the treatment outcome. In this work, we evaluated the role of form factors as imaging biomarkers to differentiate benign vs. malignant lung lesions on CT scans. We tested a total of three conventional imaging features, six form factors, and two shape features for significant differences between benign and malignant lung lesions on CT scans. The study population consisted of 192 lung nodules from two independent datasets, containing 109 (38 benign, 71 malignant) and 83 (42 benign, 41 malignant) lung lesions, respectively. The standard of reference was either histological evaluation or stability on radiological followup. The statistical significance was determined via the Mann-Whitney U nonparametric test, and the ability of the form factors to discriminate a benign vs. a malignant lesion was assessed through multivariate prediction models based on Support Vector Machines. The univariate analysis returned four form factors (Angelidakis compactness and flatness, Kong flatness, and maximum projection sphericity) that were significantly different between the benign and malignant group in both datasets. In particular, we found that the benign lesions were on average flatter than the malignant ones; conversely, the malignant ones were on average more compact (isotropic) than the benign ones. The multivariate prediction models showed that adding form factors to conventional imaging features improved the prediction accuracy by up to 14.5 pp. We conclude that form factors evaluated on lung nodules on CT scans can improve the differential diagnosis between benign and malignant lesions.

DeepLN: A Multi-Task AI Tool to Predict the Imaging Characteristics, Malignancy and Pathological Subtypes in CT-Detected Pulmonary Nodules

Objectives

Distinction of malignant pulmonary nodules from the benign ones based on computed tomography (CT) images can be time-consuming but significant in routine clinical management. The advent of artificial intelligence (AI) has provided an opportunity to improve the accuracy of cancer risk prediction.

Methods

A total of 8950 detected pulmonary nodules with complete pathological results were retrospectively enrolled. The different radiological manifestations were identified mainly as various nodules densities and morphological features. Then, these nodules were classified into benign and malignant groups, both of which were subdivided into finer specific pathological types. Here, we proposed a deep convolutional neural network for the assessment of lung nodules named DeepLN to identify the radiological features and predict the pathologic subtypes of pulmonary nodules.

Results

In terms of density, the area under the receiver operating characteristic curves (AUCs) of DeepLN were 0.9707 (95% confidence interval, CI: 0.9645-0.9765), 0.7789 (95%CI: 0.7569-0.7995), and 0.8950 (95%CI: 0.8822-0.9088) for the pure-ground glass opacity (pGGO), mixed-ground glass opacity (mGGO) and solid nodules. As for the morphological features, the AUCs were 0.8347 (95%CI: 0.8193-0.8499) and 0.9074 (95%CI: 0.8834-0.9314) for spiculation and lung cavity respectively. For the identification of malignant nodules, our DeepLN algorithm achieved an AUC of 0.8503 (95%CI: 0.8319-0.8681) in the test set. Pertaining to predicting the pathological subtypes in the test set, the multi-task AUCs were 0.8841 (95%CI: 0.8567-0.9083) for benign tumors, 0.8265 (95%CI: 0.8004-0.8499) for inflammation, and 0.8022 (95%CI: 0.7616-0.8445) for other benign ones, while AUCs were 0.8675 (95%CI: 0.8525-0.8813) for lung adenocarcinoma (LUAD), 0.8792 (95%CI: 0.8640-0.8950) for squamous cell carcinoma (LUSC), 0.7404 (95%CI: 0.7031-0.7782) for other malignant ones respectively in the malignant group.

Conclusions

The DeepLN based on deep learning algorithm represented a competitive performance to predict the imaging characteristics, malignancy and pathologic subtypes on the basis of non-invasive CT images, and thus had great possibility to be utilized in the routine clinical workflow.

Radiomics in Early Lung Cancer Diagnosis: From Diagnosis to Clinical Decision Support and Education

Lung cancer is the most frequent cause of cancer-related death around the world. With the recent introduction of low-dose lung computed tomography for lung cancer screening, there has been an increasing number of smoking- and non-smoking-related lung cancer cases worldwide that are manifesting with subsolid nodules, especially in Asian populations. However, the pros and cons of lung cancer screening also follow the implementation of lung cancer screening programs. Here, we review the literature related to radiomics for early lung cancer diagnosis. There are four main radiomics applications: the classification of lung nodules as being malignant/benign; determining the degree of invasiveness of the lung adenocarcinoma; histopathologic subtyping; and prognostication in lung cancer prediction models. In conclusion, radiomics offers great potential to improve diagnosis and personalized risk stratification in early lung cancer diagnosis through patient–doctor cooperation and shared decision making.

Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine

Medical imaging is the standard-of-care for early detection, diagnosis, treatment planning, monitoring, and image-guided interventions of lung cancer patients. Most medical images are stored digitally in a standardized Digital Imaging and Communications in Medicine format that can be readily accessed and used for qualitative and quantitative analysis. Over the several last decades, medical images have been shown to contain complementary and interchangeable data orthogonal to other sources such as pathology, hematology, genomics, and/or proteomics. As such, "radiomics" has emerged as a field of research that involves the process of converting standard-of-care images into quantitative image-based data that can be merged with other data sources and subsequently analyzed using conventional biostatistics or artificial intelligence (AI) methods. As radiomic features capture biological and pathophysiological information, these quantitative radiomic features have shown to provide rapid and accurate noninvasive biomarkers for lung cancer risk prediction, diagnostics, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics and emerging AI methods in lung cancer research are highlighted and discussed including advantages, challenges, and pitfalls.

Validation of the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a novel HRCT-based radiomic classifier for indeterminate pulmonary nodules

INTRODUCTION

Implementation of low-dose chest computed tomography (CT) lung cancer screening and the ever-increasing use of cross-sectional imaging are resulting in the identification of many screen- and incidentally detected indeterminate pulmonary nodules. While the management of nodules with low or high pre-test probability of malignancy is relatively straightforward, those with intermediate pre-test probability commonly require advanced imaging or biopsy. Noninvasive risk stratification tools are highly desirable.

METHODS

We previously developed the BRODERS classifier (Benign versus aggRessive nODule Evaluation using Radiomic Stratification), a conventional predictive radiomic model based on eight imaging features capturing nodule location, shape, size, texture and surface characteristics. Herein we report its external validation using a dataset of incidentally identified lung nodules (Vanderbilt University Lung Nodule Registry) in comparison to the Brock model. Area under the curve (AUC), as well as sensitivity, specificity, negative and positive predictive values were calculated.

RESULTS

For the entire Vanderbilt validation set (n=170, 54% malignant), the AUC was 0.87 (95% CI 0.81-0.92) for the Brock model and 0.90 (95% CI 0.85-0.94) for the BRODERS model. Using the optimal cut-off determined by Youden's index, the sensitivity was 92.3%, the specificity was 62.0%, the positive (PPV) and negative predictive values (NPV) were 73.7% and 87.5%, respectively. For nodules with intermediate pre-test probability of malignancy, Brock score of 5-65% (n=97), the sensitivity and specificity were 94% and 46%, respectively, the PPV was 78.4% and the NPV was 79.2%.

CONCLUSIONS

The BRODERS radiomic predictive model performs well on an independent dataset and may facilitate the management of indeterminate pulmonary nodules.

Comparison of Radiomic Models Based on Low-Dose and Standard-Dose CT for Prediction of Adenocarcinomas and Benign Lesions in Solid Pulmonary Nodules

Objectives

This study aimed to develop radiomic models based on low-dose CT (LDCT) and standard-dose CT to distinguish adenocarcinomas from benign lesions in patients with solid solitary pulmonary nodules and compare the performance among these radiomic models and Lung CT Screening Reporting and Data System (Lung-RADS). The reproducibility of radiomic features between LDCT and standard-dose CT were also evaluated.

Methods

A total of 141 consecutive pathologically confirmed solid solitary pulmonary nodules were enrolled including 50 adenocarcinomas and 48 benign nodules in primary cohort and 22 adenocarcinomas and 21 benign nodules in validation cohort. LDCT and standard-dose CT scans were conducted using same acquisition parameters and reconstruction method except for radiation dose. All nodules were automatically segmented and 104 original radiomic features were extracted. The concordance correlation coefficient was used to quantify reproducibility of radiomic features between LDCT and standard-dose CT. Radiomic features were selected to build radiomic signature, and clinical characteristics and radiomic signature were combined to develop radiomic nomogram for LDCT and standard-dose CT, respectively. The performance of radiomic models and Lung-RADS was assessed by area under curve (AUC) of receiver operating characteristic curve, sensitivity, and specificity.

Results

Shape and first order features, and neighboring gray tone difference matrix features were highly reproducible between LDCT and standard-dose CT. No significant differences of AUCs were found among radiomic signature and nomogram of LDCT and standard-dose CT in both primary and validation cohort (0.915 vs. 0.919 vs. 0.898 vs. 0.909 and 0.976 vs. 0.976 vs. 0.985 vs. 0.987, respectively). These radiomic models had higher specificity than Lung-RADS (all correct P < 0.05), while there were no significant differences of sensitivity between Lung-RADS and radiomic models.

Conclusions

The diagnostic performance of LDCT-based radiomic models to differentiate adenocarcinomas from benign lesions in solid pulmonary nodules were equivalent to that of standard-dose CT. The LDCT-based radiomic model with higher specificity and lower false-positive rate than Lung-RADS might help reduce overdiagnosis and overtreatment of solid pulmonary nodules in lung cancer screening.

MRI Texture-Based Models for Predicting Mitotic Index and Risk Classification of Gastrointestinal Stromal Tumors

BACKGROUND

Treatment regimens and prognoses of gastrointestinal stromal tumors (GIST) are quite different for tumors in different risk categories. Accurate preoperative grading of tumors is important for avoiding under- or overtreatment.

PURPOSE

To develop and validate an MRI texture-based model to predict the mitotic index and its risk classification.

STUDY TYPE

Retrospective.

POPULATION

Ninety-one patients with histologically-confirmed GIST; 64 patients in a training cohort, and 27 patients in a test cohort.

FIELD STRENGTH/SEQUENCE

T₂ -weighted imaging (T₂ WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced three-dimensional volumetric interpolated breath-hold examination (3D-VIBE) at 1.5T.

ASSESSMENT

GIST images were manually segmented by two independent radiologists using ITK-SNAP software and MRI features were extracted using Pyradiomics. Two pathologists reviewed the tissue specimens of the tumors to identify the mitotic index and risk classification in consensus.

STATISTICAL TESTS

The least absolute shrinkage and selection operator (LASSO) regression method was used to select texture features. A logistic regression model was established based on the radiomic score (radscore), tumor location, and maximum diameter to predict tumor classification and develop a nomogram. Receiver operator characteristic (ROC) curves were used to evaluate the ability of the nomogram to distinguish between two tumors with different risk classifications, and a calibration curve was used to evaluate the consistency between the predicted risk and the actual risk.

RESULTS

The texture signature achieved high efficacy in predicting the mitotic index area under the curve ([AUC], 0.906; 95% confidence interval [CI]: 0.813, 0.961). A nomogram for prediction of the risk classification of GIST, which incorporated this texture signature together with maximum tumor diameter and location, allowed good discrimination in the training cohort (AUC, 0.878; 95% CI: 0.769, 0.960) and the validation cohort (AUC, 0.903; 95% CI: 0.732, 0.922).

DATA CONCLUSION

The texture-based model can be used to predict GIST mitotic index and risk classification preoperatively.

LEVEL OF EVIDENCE

2.

TECHNICAL EFFICACY STAGE

3.

Tumor density is associated with response to endobronchial ultrasound-guided transbronchial needle injection of cisplatin

Background

Endobronchial ultrasound-guided transbronchial needle injection of cisplatin (EBUS-TBNI cisplatin) is a therapeutic option for patients with recurrent lung cancer. However, the tumor characteristics that influence the distribution of the agent following intratumoral delivery remain largely unknown.

Methods

We performed a retrospective evaluation of EBUS-TBNI cisplatin cases performed at two centers. Semi-automated tumor segmentation from CT scans was performed while blinded to the outcome of response. Twenty-four algorithmic radiomics features from two categories, Morphology (i.e., shape, volume) and Intensity (i.e., density), were extracted, and feature selection performed via least absolute shrinkage and selection operator (LASSO) regression. Models were constructed from clinicoepidemiologic variables and selected radiomics features and evaluated using the likelihood ratio chi-square assessment and Akaike’s information criterion (AIC).

Results

Thirty-eight patients with available imaging data were analyzed. Based on RECIST criteria, 27 of 38 treated sites demonstrated complete or partial remission (71%). The top three features identified by LASSO regression were variance, energy, and kurtosis. All three are measures of intensity, a surrogate for tumor density. Two logistic regression models with the outcome of response were created, each with the top 3 categorical features: (I) an Intensity model including variance, energy, and kurtosis, and (II) a Morphology model including surface-to-volume ratio, spherical disproportion, and maximum 3-dimensional (3D) diameter. Only the Intensity model met criteria for significance (P=0.024), and it resulted in a lower AIC and higher pseudo R square value vs. the Morphology model.

Conclusions

Measures of tumor density are more highly associated with response to EBUS-TBNI cisplatin than measures of morphology.

External validation of radiomics-based predictive models in low-dose CT screening for early lung cancer diagnosis

PURPOSE

Low-dose CT screening allows early lung cancer detection, but is affected by frequent false positive results, inter/intra observer variation and uncertain diagnoses of lung nodules. Radiomics-based models have recently been introduced to overcome these issues, but limitations in demonstrating their generalizability on independent datasets are slowing their introduction to clinic. The aim of this study is to evaluate two radiomics-based models to classify malignant pulmonary nodules in low-dose CT screening, and to externally validate them on an independent cohort. The effect of a radiomics features harmonization technique is also investigated to evaluate its impact on the classification of lung nodules from a multicenter data.

METHODS

Pulmonary nodules from two independent cohorts were considered in this study; the first cohort (110 subjects, 113 nodules) was used to train prediction models, and the second cohort (72 nodules) to externally validate them. Literature-based radiomics features were extracted and, after feature selection, used as predictive variables in models for malignancy identification. An in-house prediction model based on artificial neural network (ANN) was implemented and evaluated, along with an alternative model from the literature, based on a support vector machine (SVM) classifier coupled with a least absolute shrinkage and selection operator (LASSO). External validation was performed on the second cohort to evaluate models' generalization ability. Additionally, the impact of the Combat harmonization method was investigated to compensate for multicenter datasets variabilities. A new training of the models based on harmonized features was performed on the first cohort, then tested separately on the harmonized and non-harmonized features of the second cohort.

RESULTS

Preliminary results showed a good accuracy of the investigated models in distinguishing benign from malignant pulmonary nodules with both sets of radiomics features (i.e., non-harmonized and harmonized). The performance of the models, quantified in terms of Area Under the Curve (AUC), was > 0.89 in the training set and > 0.82 in the external validation set for all the investigated scenarios, outperforming the clinical standard (AUC of 0.76). Slightly higher performance was observed for the SVM-LASSO model than the ANN in the external dataset, although they did not result significantly different. For both harmonized and non-harmonized features, no statistical difference was found between Receiver operating characteristic (ROC) curves related to training and test set for both models.

CONCLUSIONS

Although no significant improvements were observed when applying the Combat harmonization method, both in-house and literature-based models were able to classify lung nodules with good generalization to an independent dataset, thus showing their potential as tools for clinical decision-making in lung cancer screening.

Do we need to see to believe?-radiomics for lung nodule classification and lung cancer risk stratification

Despite multiple recent advances, the diagnosis and management of lung cancer remain challenging and it continues to be the deadliest malignancy. In 2011, the National Lung Screening Trial (NLST) reported 20% reduction in lung cancer related mortality using annual low dose chest computed tomography (CT). These results led to the approval and nationwide establishment of lung cancer CT-based lung cancer screening programs. These findings have been further validated by the recently published Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON) and Multicentric Italian Lung Detection (MILD) trials, the latter showing benefit of screening even beyond the 5 years. However, the implementation of lung cancer screening has been impeded by several challenges, including the differentiation between benign and malignant nodules, the large number of false positive studies and the detection of indolent, potentially clinically insignificant lung cancers (overdiagnosis). Hence, the development of non-invasive strategies to accurately classify and risk stratify screen-detected pulmonary nodules in order to individualize clinical management remains a high priority area of research. Radiomics is a recently coined term which refers to the process of imaging feature extraction and quantitative analysis of clinical diagnostic images to characterize the nodule phenotype beyond what is possible with conventional radiologist assessment. Even though it is still in early phase, several studies have already demonstrated that radiomics approaches are potentially useful for lung nodule classification, risk stratification, individualized management and prediction of overall prognosis. The goal of this review is to summarize the current literature regarding the radiomics of screen-detected lung nodules, highlight potential challenges and discuss its clinical application along with future goals and challenges.

Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics

PURPOSE

The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological and non-oncological applications, in order to assess how far the image mining research stands from routine medical application. To do this, we applied a trial phases classification inspired from the drug development process.

METHODS

Among the articles we considered for inclusion from PubMed were multimodality AI and radiomics investigations, with a validation analysis aimed at relevant clinical objectives. Quality assessment of selected papers was performed according to the QUADAS-2 criteria. We developed the phases classification criteria for image mining studies.

RESULTS

Overall 34,626 articles were retrieved, 300 were selected applying the inclusion/exclusion criteria, and 171 high-quality papers (QUADAS-2 ≥ 7) were identified and analysed. In 27/171 (16%), 141/171 (82%), and 3/171 (2%) studies the development of an AI-based algorithm, radiomics model, and a combined radiomics/AI approach, respectively, was described. A total of 26/27(96%) and 1/27 (4%) AI studies were classified as phase II and III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), and 7/141 (5%) radiomics studies were classified as phase 0, I, II, and III, respectively. All three radiomics/AI studies were categorised as phase II trials.

CONCLUSIONS

The results of the studies are promising but still not mature enough for image mining tools to be implemented in the clinical setting and be widely used. The transfer learning from the well-known drug development process, with some specific adaptations to the image mining discipline could represent the most effective way for radiomics and AI algorithms to become the standard of care tools.

Prediction of lung cancer risk at follow-up screening with low-dose CT: a training and validation study of a deep learning method

Background

Current lung cancer screening guidelines use mean diameter, volume or density of the largest lung nodule in the prior computed tomography (CT) or appearance of new nodule to determine the timing of the next CT. We aimed at developing a more accurate screening protocol by estimating the 3-year lung cancer risk after two screening CTs using deep machine learning (ML) of radiologist CT reading and other universally available clinical information.

Methods

A deep machine learning (ML) algorithm was developed from 25,097 participants who had received at least two CT screenings up to two years apart in the National Lung Screening Trial. Double-blinded validation was performed using 2,294 participants from the Pan-Canadian Early Detection of Lung Cancer Study (PanCan). Performance of ML score to inform lung cancer incidence was compared with Lung-RADS and volume doubling time using time-dependent ROC analysis. Exploratory analysis was performed to identify individuals with aggressive cancers and higher mortality rates.

Findings

In the PanCan validation cohort, ML showed excellent discrimination with a 1-, 2- and 3-year time-dependent AUC values for cancer diagnosis of 0·968±0·013, 0·946±0·013 and 0·899±0·017. Although high ML score cohort included only 10% of the PanCan sample, it identified 94%, 85%, and 71% of incident and interval lung cancers diagnosed within 1, 2, and 3 years, respectively, after the second screening CT. Furthermore, individuals with high ML score had significantly higher mortality rates (HR=16·07, p<0·001) compared to those with lower risk.

Interpretation

ML tool that recognizes patterns in both temporal and spatial changes as well as synergy among changes in nodule and non-nodule features may be used to accurately guide clinical management after the next scheduled repeat screening CT.

Global heterogeneity assessed with 18F-FDG PET/CT. Relation with biological variables and prognosis in locally advanced breast cancer

AIM

To analyze the relationship between measurements of global heterogeneity, obtained from ¹⁸F-FDG PET/CT, with biological variables, and their predictive and prognostic role in patients with locally advanced breast cancer (LABC).

MATERIAL AND METHODS

68 patients from a multicenter and prospective study, with LABC and a baseline ¹⁸F-FDG PET/CT were included. Immunohistochemical profile [estrogen receptors (ER) and progesterone receptors (PR), expression of the HER-2 oncogene, Ki-67 proliferation index and tumor histological grade], response to neoadjuvant chemotherapy (NC), overall survival (OS) and disease-free survival (DFS) were obtained as clinical variables. Three-dimensional segmentation of the lesions, providing SUV, volumetric [metabolic tumor volume (MTV) and total lesion glycolysis (TLG)] and global heterogeneity variables [coefficient of variation (COV) and SUVmean/SUVmax ratio], as well as sphericity was performed. The correlation between the results obtained with the immunohistochemical profile, the response to NC and survival was also analyzed.

RESULTS

Of the patients included, 62 received NC. Only 18 responded. 13 patients relapsed and 11 died during follow-up. ER negative tumors had a lower COV (p=0.018) as well as those with high Ki-67 (p=0.001) and high risk phenotype (p=0.033) compared to the rest. No PET variable showed association with the response to NC nor OS. There was an inverse relationship between sphericity with DFS (p=0.041), so, for every tenth that sphericity increases, the risk of recurrence decreases by 37%.

CONCLUSIONS

Breast tumors in our LABC dataset behaved as homogeneous and spherical lesions. Larger volumes were associated with a lower sphericity. Global heterogeneity variables and sphericity do not seem to have a predictive role in response to NC nor in OS. More spherical tumors with less variation in gray intensity between voxels showed a lower risk of recurrence.

Quantitative CT texture analysis for diagnosing systemic sclerosis: Effect of iterative reconstructions and radiation doses

To test whether texture analysis (TA) can discriminate between Systemic Sclerosis (SSc) and non-SSc patients in computed tomography (CT) with different radiation doses and reconstruction algorithms.In this IRB-approved retrospective study, 85 CT scans at different radiation doses [49 standard dose CT (SDCT) with a volume CT dose index (CTDIvol) of 4.86 ± 2.1 mGy and 36 low-dose (LDCT) with a CTDIvol of 2.5 ± 1.5 mGy] were selected; 61 patients had Ssc ("cases"), and 24 patients had no SSc ("controls"). CT scans were reconstructed with filtered-back projection (FBP) and with sinogram-affirmed iterative reconstruction (SAFIRE) algorithms. 304 TA features were extracted from each manually drawn region-of-interest at 6 pre-defined levels: at the midpoint between lung apices and tracheal carina, at the level of the tracheal carina, and 4 between the carina and pleural recesses. Each TA feature was averaged between these 6 pre-defined levels and was used as input in the machine learning algorithm artificial neural network (ANN) with backpropagation (MultilayerPerceptron) for differentiating between SSc and non-SSc patients.Results were compared regarding correctly/incorrectly classified instances and ROC-AUCs.ANN correctly classified individuals in 93.8% (AUC = 0.981) of FBP-LDCT, in 78.5% (AUC = 0.859) of FBP-SDCT, in 91.1% (AUC = 0.922) of SAFIRE3-LDCT and 75.7% (AUC = 0.815) of SAFIRE3-SDCT, in 88.1% (AUC = 0.929) of SAFIRE5-LDCT and 74% (AUC = 0.815) of SAFIRE5-SDCT.Quantitative TA-based discrimination of CT of SSc patients is possible showing highest discriminatory power in FBP-LDCT images.

Correction: Novel high-resolution computed tomography-based radiomic classifier for screen-identified pulmonary nodules in the National Lung Screening Trial

[This corrects the article DOI: 10.1371/journal.pone.0196910.].

The narrow path to organized LDCT lung cancer screening programs in Europe

A recent position statement by a group of European experts reviewed the current evidence for low-dose computed tomography (LDCT) lung cancer screening, based on the outcomes and screening performance of the published randomized trials and identified actions needed for eventual future implementation. After the National Lung Screening Trial (NLST) outcome publication, guidelines changed in USA and Canada, but there are still problems in real-world screening practice. In Europe any decision was postponed to the publication of the European randomized trial outcomes and recommendations continue to discourage screening for lung cancer in all member countries. The NELSON randomized controlled trial (RCT), the largest one in Europe, outcome results are still waited, whereas the MILD, DANTE, DLSCT and ITALUNG (all with small sample size) RCTs have published mortality and incidence data with adequate follow up. The implementation of an organized screening in Europe is conditioned by a health technology assessment process at European level. According with the European policy, confirmed in the recent European Cancer Code [2015], screening is transferred in current public-health practice according with evidence-based recommendations and based on organized, usually population-based, programs. Guidelines, standard indicators of performance, training of dedicated radiologists and professionals and a comprehensive quality assurance system is requested in European countries to implement nationally a public health screening program. Waiting the NELSON randomized trial results, key issues as modality for selection of high risk subjects and recruitment, integration of screening and smoking cessation, optimal screening regimen and related research on biomarkers should be assessed, discussed and reviewed. Informed decision making, promotion of primary prevention and integration of screening and smoking cessation are all essential components of a comprehensive risk reduction policy. The path to an Evidence-based screening practice is narrow and, in the absence of a well-established decision-making process, the risk of a spontaneous, uncontrolled use of LDCT screening or, on the other side, an oversight of the screening opportunity is high.