Predicting adenocarcinoma recurrence using computational texture models of nodule components in lung CT

Artificial intelligence-based prediction of clinical outcome in immunotherapy and targeted therapy of lung cancer

Lung cancer accounts for the main proportion of malignancy-related deaths and most patients are diagnosed at an advanced stage. Immunotherapy and targeted therapy have great advances in application in clinics to treat lung cancer patients, yet the efficacy is unstable. The response rate of these therapies varies among patients. Some biomarkers have been proposed to predict the outcomes of immunotherapy and targeted therapy, including programmed cell death-ligand 1 (PD-L1) expression and oncogene mutations. Nevertheless, the detection tests are invasive, time-consuming, and have high demands on tumor tissue. The predictive performance of conventional biomarkers is also unsatisfactory. Therefore, novel biomarkers are needed to effectively predict the outcomes of immunotherapy and targeted therapy. The application of artificial intelligence (AI) can be a possible solution, as it has several advantages. AI can help identify features that are unable to be used by humans and perform repetitive tasks. By combining AI methods with radiomics, pathology, genomics, transcriptomics, proteomics, and clinical data, the integrated model has shown predictive value in immunotherapy and targeted therapy, which significantly improves the precision treatment of lung cancer patients. Herein, we reviewed the application of AI in predicting the outcomes of immunotherapy and targeted therapy in lung cancer patients, and discussed the challenges and future directions in this field.

Radiomics/Radiogenomics in Lung Cancer: Basic Principles and Initial Clinical Results

Simple Summary

Radiogenomics is a promising new approach in cancer assessment, providing an evaluation of the molecular basis of imaging phenotypes after establishing associations between radiological features and molecular features at the genomic–transcriptomic–proteomic level. This review focuses on describing key aspects of radiogenomics while discussing limitations of translatability to the clinic and possible solutions to these challenges, providing the clinician with an up-to-date handbook on how to use this new tool.

Abstract

Lung cancer is the leading cause of cancer-related deaths worldwide, and elucidation of its complicated pathobiology has been traditionally targeted by studies incorporating genomic as well other high-throughput approaches. Recently, a collection of methods used for cancer imaging, supplemented by quantitative aspects leading towards imaging biomarker assessment termed “radiomics”, has introduced a novel dimension in cancer research. Integration of genomics and radiomics approaches, where identifying the biological basis of imaging phenotypes is feasible due to the establishment of associations between molecular features at the genomic–transcriptomic–proteomic level and radiological features, has recently emerged termed radiogenomics. This review article aims to briefly describe the main aspects of radiogenomics, while discussing its basic limitations related to lung cancer clinical applications for clinicians, researchers and patients.

Cleaning Radiotherapy Contours for Radiomics Studies, is it Worth it? A Head and Neck Cancer Study

•

PET images features are more stable across different delineation of the same target.

•

Shape family features are more stable.

•

The survival model based on Dedicated contours achieved better performance for predicting PFS.

A vast majority of studies in the radiomics field are based on contours originating from radiotherapy planning. This kind of delineation (e.g. Gross Tumor Volume, GTV) is often larger than the true tumoral volume, sometimes including parts of other organs (e.g. trachea in Head and Neck, H&N studies) and the impact of such over-segmentation was little investigated so far. In this paper, we propose to evaluate and compare the performance between models using two contour types: those from radiotherapy planning, and those specifically delineated for radiomics studies. For the latter, we modified the radiotherapy contours to fit the true tumoral volume. The two contour types were compared when predicting Progression-Free Survival (PFS) using Cox models based on radiomics features extracted from FluoroDeoxyGlucose-Positron Emission Tomography (FDG-PET) and CT images of 239 patients with oropharyngeal H&N cancer collected from five centers, the data from the 2020 HECKTOR challenge. Using Dedicated contours demonstrated better performance for predicting PFS, where Harell’s concordance indices of 0.61 and 0.69 were achieved for Radiotherapy and Dedicated contours, respectively. Using automatically Resegmented contours based on a fixed intensity range was associated with a C-index of 0.63. These results illustrate the importance of using clean dedicated contours that are close to the true tumoral volume in radiomics studies, even when tumor contours are already available from radiotherapy treatment planning

Augmented Features Synergize Radiomics in Post-Operative Survival Prediction and Adjuvant Therapy Recommendation for Non-Small Cell Lung Cancer

Background

Owing to the cytotoxic effect, it is challenging for clinicians to decide whether post-operative adjuvant therapy is appropriate for a non-small cell lung cancer (NSCLC) patient. Radiomics has proven its promising ability in predicting survival but research on its actionable model, particularly for supporting the decision of adjuvant therapy, is limited.

Methods

Pre-operative contrast-enhanced CT images of 123 NSCLC cases were collected, including 76, 13, 16, and 18 cases from R01 and AMC cohorts of The Cancer Imaging Archive (TCIA), Jiangxi Cancer Hospital and Guangdong Provincial People’s Hospital respectively. From each tumor region, 851 radiomic features were extracted and two augmented features were derived therewith to estimate the likelihood of adjuvant therapy. Both Cox regression and machine learning models with the selected main and interaction effects of 853 features were trained using 76 cases from R01 cohort, and their test performances on survival prediction were compared using 47 cases from the AMC cohort and two hospitals. For those cases where adjuvant therapy was unnecessary, recommendations on adjuvant therapy were made again by the outperforming model and compared with those by IBM Watson for Oncology (WFO).

Results

The Cox model outperformed the machine learning model in predicting survival on the test set (C-Index: 0.765 vs. 0.675). The Cox model consists of 5 predictors, interestingly 4 of which are interactions with augmented features facilitating the modulation of adjuvant therapy option. While WFO recommended no adjuvant therapy for only 13.6% of cases that received unnecessary adjuvant therapy, the same recommendations by the identified Cox model were extended to 54.5% of cases (McNemar’s test p = 0.0003).

Conclusions

A Cox model with radiomic and augmented features could predict survival accurately and support the decision of adjuvant therapy for bettering the benefit of NSCLC patients.

Making Radiomics More Reproducible across Scanner and Imaging Protocol Variations: A Review of Harmonization Methods

Radiomics converts medical images into mineable data via a high-throughput extraction of quantitative features used for clinical decision support. However, these radiomic features are susceptible to variation across scanners, acquisition protocols, and reconstruction settings. Various investigations have assessed the reproducibility and validation of radiomic features across these discrepancies. In this narrative review, we combine systematic keyword searches with prior domain knowledge to discuss various harmonization solutions to make the radiomic features more reproducible across various scanners and protocol settings. Different harmonization solutions are discussed and divided into two main categories: image domain and feature domain. The image domain category comprises methods such as the standardization of image acquisition, post-processing of raw sensor-level image data, data augmentation techniques, and style transfer. The feature domain category consists of methods such as the identification of reproducible features and normalization techniques such as statistical normalization, intensity harmonization, ComBat and its derivatives, and normalization using deep learning. We also reflect upon the importance of deep learning solutions for addressing variability across multi-centric radiomic studies especially using generative adversarial networks (GANs), neural style transfer (NST) techniques, or a combination of both. We cover a broader range of methods especially GANs and NST methods in more detail than previous reviews.

Pleomorphic carcinoma of the lung: Prognostic models of semantic, radiomics and combined features from CT and PET/CT in 85 patients

Introduction

To demonstrate semantic, radiomics, and the combined risk models related to the prognoses of pulmonary pleomorphic carcinomas (PCs).

Methods

We included 85 patients (M:F = 71:14; age, 35–88 [mean, 63 years]) whose imaging features were divided into training (n = 60) and test (n = 25) sets. Nineteen semantic and 142 radiomics features related to tumors were computed. Semantic risk score (SRS) model was built using the Cox-least absolute shrinkage and selection operator (LASSO) approach. Radiomics risk score (RRS) from CT and PET features and combined risk score (CRS) adopting both semantic and radiomics features were also constructed. Risk groups were stratified by the median of the risk scores of the training set. Survival analysis was conducted with the Kaplan-Meier plots.

Results

Of 85 PCs, adenocarcinoma was the most common epithelial component found in 63 (73 %) tumors. In SRS model, four features were stratified into high- and low-risk groups (HR, 4.119; concordance index ([C-index], 0.664) in the test set. In RRS model, five features helped improve the stratification (HR, 3.716; C-index, 0.591) and in CRS model, three features helped perform the best stratification (HR, 4.795; C-index, 0.617). The two significant features of CRS models were the SUVmax and the histogram feature of energy ([CT Firstorder Energy]).

Conclusion

In PCs of the lungs, the combined model leveraging semantic and radiomics features provides a better prognosis compared to using semantic and radiomics features separately. The high SUVmax of solid portion (CT Firstorder Energy) of tumors is associated with poor prognosis in lung PCs.

Machine learning to identify lymph node metastasis from thyroid cancer in patients undergoing contrast-enhanced CT studies

INTRODUCTION

We compared the diagnostic performance of morphological methods such as the major axis, the minor axis, the volume and sphericity and of machine learning with texture analysis in the identification of lymph node metastasis in patients with thyroid cancer who had undergone contrast-enhanced CT studies.

METHODS

We sampled 772 lymph nodes with histology defined tissue types (84 metastatic and 688 benign lymph nodes) that were visualised on CT images of 117 patients. A support vector machine (SVM), free programming software (Python), and the scikit-learn machine learning library were used to discriminate metastatic-from benign lymph nodes. We assessed 96 texture and 4 morphological features (major axis, minor axis, volume, sphericity) that were reported useful for the differentiation between metastatic and benign lymph nodes on CT images. The area under the curve (AUC) obtained by receiver operating characteristic analysis of univariate logistic regression and SVM classifiers were calculated for the training and testing datasets.

RESULTS

The AUC for all classifiers in training and testing datasets was 0.96 and 0.86, at the SVM for machine learning. When we applied conventional methods to the training and testing datasets, the AUCs were 0.63 and 0.48 for the major axis, 0.70 and 0.44 for the minor axis, 0.66 and 0.43 for the volume, and 0.69 and 0.54 for sphericity, respectively. The SVM using texture features yielded significantly higher AUCs than univariate logistic regression models using morphological features (p = 0.001).

CONCLUSION

For the identification of metastatic lymph nodes from thyroid cancer on contrast-enhanced CT images, machine learning combined with texture analysis was superior to conventional diagnostic methods with the morphological parameters.

IMPLICATIONS FOR PRACTICE

Our findings suggest that in patients with thyroid cancer and suspected lymph node metastasis who undergo contrast-enhanced CT studies, machine learning using texture analysis is high diagnostic value for the identification of metastatic lymph nodes.

Identifying Cross-Scale Associations between Radiomic and Pathomic Signatures of Non-Small Cell Lung Cancer Subtypes: Preliminary Results

(1) Background: Despite the complementarity between radiology and histopathology, both from a diagnostic and a prognostic perspective, quantitative analyses of these modalities are usually performed in disconnected silos. This work presents initial results for differentiating two major non-small cell lung cancer (NSCLC) subtypes by exploring cross-scale associations between Computed Tomography (CT) images and corresponding digitized pathology images. (2) Methods: The analysis comprised three phases, (i) a multi-resolution cell density quantification to identify discriminant pathomic patterns for differentiating adenocarcinoma (ADC) and squamous cell carcinoma (SCC), (ii) radiomic characterization of CT images by using Haralick descriptors to quantify tumor textural heterogeneity as represented by gray-level co-occurrences to discriminate the two pathological subtypes, and (iii) quantitative correlation analysis between the multi-modal features to identify potential associations between them. This analysis was carried out using two publicly available digitized pathology databases (117 cases from TCGA and 54 cases from CPTAC) and a public radiological collection of CT images (101 cases from NSCLC-R). (3) Results: The top-ranked cell density pathomic features from the histopathology analysis were correlation, contrast, homogeneity, sum of entropy and difference of variance; which yielded a cross-validated AUC of 0.72 ± 0.02 on the training set (CPTAC) and hold-out validation AUC of 0.77 on the testing set (TCGA). Top-ranked co-occurrence radiomic features within NSCLC-R were contrast, correlation and sum of entropy which yielded a cross-validated AUC of 0.72 ± 0.01. Preliminary but significant cross-scale associations were identified between cell density statistics and CT intensity values using matched specimens available in the TCGA cohort, which were used to significantly improve the overall discriminatory performance of radiomic features in differentiating NSCLC subtypes (AUC = 0.78 ± 0.01). (4) Conclusions: Initial results suggest that cross-scale associations may exist between digital pathology and CT imaging which can be used to identify relevant radiomic and histopathology features to accurately distinguish lung adenocarcinomas from squamous cell carcinomas.

Radiomics in lung cancer for oncologists

Radiomics has revolutionized the world of medical imaging. The aim of this review is to guide oncologists in radiomics and its applications in diagnosis, prediction of response and damage, prediction of survival, and prognosis in lung cancer. In this review, we analyzed published literature on PubMed and MEDLINE with papers published in the last 10 years. We included papers in English language with information about radiomics features and diagnostic, predictive, and prognosis of radiomics in lung cancer. All citations were evaluated for relevant content and validation.

RELEVANCE FOR PATIENTS

The evolution of technology allows the development of computer algorithms that facilitate the diagnosis and evaluation of response after different oncological treatments and their non-invasive follow-up.

Use CT Imaging to Predict the Short-Term Outcome of Concurrent Chemoradiotherapy in Patients With Locally Advanced Esophageal Squamous Cell Carcinoma

Objective:

To extract the computed tomography (CT) imaging features of the primary lesions in patients with advanced esophageal squamous cell carcinoma (ESCC) and to study whether these imaging features can predict the short-term outcome after concurrent chemoradiotherapy (CCRT).

Methods:

From January 2014 to December 2015, a total of 49 patients with locally advanced ESCC who underwent CCRT were analyzed retrospectively. They were randomly categorized into the training and validation groups. Collection of CT imaging of patients before and intermediate stage undergoing radiotherapy. The correlations between imaging characteristics and short-term outcome were analyzed. The accuracy of cutoff value was verified by imaging characteristics of patients in validation group.

Result:

There were 38 patients in the training group and 11 patients in the validation group. 13 patients in the training group were classified as responders and 25 patients as nonresponders. According to the CT imaging before radiotherapy, there are no significant differences between responders and nonresponders. According to the CT imaging in the middle stage of radiotherapy, responders showed significantly higher Roundness than nonresponders (P = .004, 95% confidence interval [CI] = 0.0419-0.212). The areas under the ROC curves for the ability to predict significantly tumor response were 0.768 for Roundness (P = .001, 95% CI = 0.603-0.889). The cutoff value of Roundness is 0.3099. Roundness showed no significant associations with survival parameters.

Conclusions:

Computed tomography imaging in the middle stage of radiotherapy can predict the short-term outcome of concurrent chemoradiotherapy for patients with locally advanced ESCC but have no predictive effect on the total survival time.

Use of an Anthropomorphic Chest Model to Evaluate Multiple Scanning Protocols for High-Definition and Standard-Definition Computed Tomography to Detect Small Pulmonary Nodules

BACKGROUND This study aimed to use the LUNGMAN N1 anthropomorphic chest model to evaluate protocols for high-definition computed tomography (HDCT) and standard-definition CT (SDCT) to detect and compare small pulmonary nodules and determine the most appropriate low-dose scanning protocols. MATERIAL AND METHODS HDCT imaging used the Discovery HD750 scanner (80, 100, 120 and 140 kVp; 360, 320, 280, 240, 200, 160, 120, 80, 40, and 20 mA), and SDCT imaging used the Lightspeed VCT scanner (80, 120, and 140 kVp; 360, 320, 280, 240, 200, 160, 120, 80, 40, and 20 mA). The LUNGMAN N1 anthropomorphic chest model contained artificial pulmonary nodules (diameter: 5, 8, 10, and 12 mm). Low-dose scanning protocols were used in image acquisition. Two experienced radiologists evaluated the image quality. The combinations of voltage, tube current, image noise, and radiation dose were recorded. Consistency of the image quality between raters was assessed by kappa statistical analysis. RESULTS Seventy CT scans of pulmonary nodules (diameter, 5-12 mm) were performed. There was a high degree of consistency for image quality between the two observers (K=0.929 for 5 mm nodules; K=0.819 for overall image quality). For 8 mm nodules, 100% were detected on both SDCT and HDCT. HDCT outperformed SDCT by 5%, in terms of effective dose. There was no significant difference in image quality between the SDCT and HDCT scanners. CONCLUSIONS Using an anthropomorphic chest model, the identification and image quality using SDCT was similar to that of HDCT for small pulmonary nodules between 5-12 mm.

Revealing Tumor Habitats from Texture Heterogeneity Analysis for Classification of Lung Cancer Malignancy and Aggressiveness

We propose an approach for characterizing structural heterogeneity of lung cancer nodules using Computed Tomography Texture Analysis (CTTA). Measures of heterogeneity were used to test the hypothesis that heterogeneity can be used as predictor of nodule malignancy and patient survival. To do this, we use the National Lung Screening Trial (NLST) dataset to determine if heterogeneity can represent differences between nodules in lung cancer and nodules in non-lung cancer patients. 253 participants are in the training set and 207 participants in the test set. To discriminate cancerous from non-cancerous nodules at the time of diagnosis, a combination of heterogeneity and radiomic features were evaluated to produce the best area under receiver operating characteristic curve (AUROC) of 0.85 and accuracy 81.64%. Second, we tested the hypothesis that heterogeneity can predict patient survival. We analyzed 40 patients diagnosed with lung adenocarcinoma (20 short-term and 20 long-term survival patients) using a leave-one-out cross validation approach for performance evaluation. A combination of heterogeneity features and radiomic features produce an AUROC of 0.9 and an accuracy of 85% to discriminate long- and short-term survivors.

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

Although cancer often is referred to as "a disease of the genes," it is indisputable that the (epi)genetic properties of individual cancer cells are highly variable, even within the same tumor. Hence, preexisting resistant clones will emerge and proliferate after therapeutic selection that targets sensitive clones. Herein, the authors propose that quantitative image analytics, known as "radiomics," can be used to quantify and characterize this heterogeneity. Virtually every patient with cancer is imaged radiologically. Radiomics is predicated on the beliefs that these images reflect underlying pathophysiologies, and that they can be converted into mineable data for improved diagnosis, prognosis, prediction, and therapy monitoring. In the last decade, the radiomics of cancer has grown from a few laboratories to a worldwide enterprise. During this growth, radiomics has established a convention, wherein a large set of annotated image features (1-2000 features) are extracted from segmented regions of interest and used to build classifier models to separate individual patients into their appropriate class (eg, indolent vs aggressive disease). An extension of this conventional radiomics is the application of "deep learning," wherein convolutional neural networks can be used to detect the most informative regions and features without human intervention. A further extension of radiomics involves automatically segmenting informative subregions ("habitats") within tumors, which can be linked to underlying tumor pathophysiology. The goal of the radiomics enterprise is to provide informed decision support for the practice of precision oncology.

Identifying the morphologic basis for radiomic features in distinguishing different Gleason grades of prostate cancer on MRI: Preliminary findings

Translation of radiomics into the clinic may require a more comprehensive understanding of the underlying morphologic tissue characteristics they reflect. In the context of prostate cancer (PCa), some studies have correlated gross histological measurements of gland lumen, epithelium, and nuclei with disease appearance on MRI. Quantitative histomorphometry (QH), like radiomics for radiologic images, is the computer based extraction of features for describing tumor morphology on digitized tissue images. In this work, we attempt to establish the histomorphometric basis for radiomic features for prostate cancer by (1) identifying the radiomic features from T2w MRI most discriminating of low vs. intermediate/high Gleason score, (2) identifying QH features correlated with the most discriminating radiomic features previously identified, and (3) evaluating the discriminative ability of QH features found to be correlated with spatially co-localized radiomic features. On a cohort of 36 patients (23 for training, 13 for validation), Gabor texture features were identified as being most predictive of Gleason grade on MRI (AUC of 0.69) and gland lumen shape features were identified as the most predictive QH features (AUC = 0.75). Our results suggest that the PCa grade discriminability of Gabor features is a consequence of variations in gland shape and morphology at the tissue level.

The developing role of FDG PET imaging for prognostication and radiotherapy target volume delineation in non-small cell lung cancer

Advancements in functional imaging technology have allowed new possibilities in contouring of target volumes, monitoring therapy, and predicting treatment outcome in non-small cell lung cancer (NSCLC). Consequently, the role of ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) has expanded in the last decades from a stand-alone diagnostic tool to a versatile instrument integrated with computed tomography (CT), with a prominent role in lung cancer radiotherapy. This review outlines the most recent literature on developments in FDG PET imaging for prognostication and radiotherapy target volume delineation (TVD) in NSCLC. We also describe the challenges facing the clinical implementation of these developments and present new ideas for future research.

Towards precision medicine: from quantitative imaging to radiomics

Radiology (imaging) and imaging-guided interventions, which provide multi-parametric morphologic and functional information, are playing an increasingly significant role in precision medicine. Radiologists are trained to understand the imaging phenotypes, transcribe those observations (phenotypes) to correlate with underlying diseases and to characterize the images. However, in order to understand and characterize the molecular phenotype (to obtain genomic information) of solid heterogeneous tumours, the advanced sequencing of those tissues using biopsy is required. Thus, radiologists image the tissues from various views and angles in order to have the complete image phenotypes, thereby acquiring a huge amount of data. Deriving meaningful details from all these radiological data becomes challenging and raises the big data issues. Therefore, interest in the application of radiomics has been growing in recent years as it has the potential to provide significant interpretive and predictive information for decision support. Radiomics is a combination of conventional computer-aided diagnosis, deep learning methods, and human skills, and thus can be used for quantitative characterization of tumour phenotypes. This paper discusses the overview of radiomics workflow, the results of various radiomics-based studies conducted using various radiological images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET), the challenges we are facing, and the potential contribution of radiomics towards precision medicine.

Added Value of Computer-aided CT Image Features for Early Lung Cancer Diagnosis with Small Pulmonary Nodules: A Matched Case-Control Study

Purpose To test whether computer-aided diagnosis (CAD) approaches can increase the positive predictive value (PPV) and reduce the false-positive rate in lung cancer screening for small nodules compared with human reading by thoracic radiologists. Materials and Methods A matched case-control sample of low-dose computed tomography (CT) studies in 186 participants with 4-20-mm noncalcified lung nodules who underwent biopsy in the National Lung Screening Trial (NLST) was selected. Variables used for matching were age, sex, smoking status, chronic obstructive pulmonary disease status, body mass index, study year of the positive screening test, and screening results. Studies before lung biopsy were randomly split into a training set (70 cancers plus 70 benign controls) and a validation set (20 cancers plus 26 benign controls). Image features from within and outside dominant nodules were extracted. A CAD algorithm developed from the training set and a random forest classifier were applied to the validation set to predict biopsy outcomes. Receiver operating characteristic analysis was used to compare the prediction accuracy of CAD with the NLST investigator's diagnosis and readings from three experienced and board-certified thoracic radiologists who used contemporary clinical practice guidelines. Results In the validation cohort, the area under the receiver operating characteristic curve for CAD was 0.9154. By default, the sensitivity, specificity, and PPV of the NLST investigators were 1.00, 0.00, and 0.43, respectively. The sensitivity, specificity, PPV, and negative predictive value of CAD and the three radiologists' combined reading were 0.95, 0.88, 0.86, and 0.96 and 0.70, 0.69, 0.64, and 0.75, respectively. Conclusion CAD could increase PPV and reduce the false-positive rate in the early diagnosis of lung cancer. © RSNA, 2017 Online supplemental material is available for this article.

Quantitative texture analysis on pre-treatment computed tomography predicts local recurrence in stage I non-small cell lung cancer following stereotactic radiation therapy

Background

The prediction of local recurrence (LR) of stage I non-small cell lung cancer (NSCLC) after definitive stereotactic body radiotherapy (SBRT) remains elusive. The purpose of this study was to assess whether quantitative imaging features on pre-treatment computed tomography (CT) can predict LR beyond 18 (¹⁸F) fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET)/CT maximum standard uptake value (SUV_max).

Methods

This retrospective study evaluated 36 patients with 37 stage I NSCLC who had local tumor control (LC; n=19) and (LR; n=18). Textural features were extracted on pre-treatment CT. Mann-Whitney U tests were used to compare LC and LR groups. Receiver-operating characteristic (ROC) curves were constructed and the area under the curve (AUC) calculated with LR as outcome.

Results

Gray-level correlation and sum variance were greater in the LR group, compared with the LC group (P=0.02 and P=0.04, respectively). Gray-level difference variance was lower in the LR group (P=0.004). The logistic regression model generated using gray-level correlation and difference variance features resulted in AUC (SE) 0.77 (0.08) (P=0.0007). The addition of 18F-FDG PET/CT SUV_max did not improve the AUC (P=0.75).

Conclusions

CT textural features were found to be predictors of LR of early stage NSCLC on baseline CT prior to SBRT.

The effects of segmentation algorithms on the measurement of 18F-FDG PET texture parameters in non-small cell lung cancer

BACKGROUND

Measures of tumour heterogeneity derived from 18-fluoro-2-deoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) scans are increasingly reported as potential biomarkers of non-small cell lung cancer (NSCLC) for classification and prognostication. Several segmentation algorithms have been used to delineate tumours, but their effects on the reproducibility and predictive and prognostic capability of derived parameters have not been evaluated. The purpose of our study was to retrospectively compare various segmentation algorithms in terms of inter-observer reproducibility and prognostic capability of texture parameters derived from non-small cell lung cancer (NSCLC) 18F-FDG PET/CT images. Fifty three NSCLC patients (mean age 65.8 years; 31 males) underwent pre-chemoradiotherapy 18F-FDG PET/CT scans. Three readers segmented tumours using freehand (FH), 40% of maximum intensity threshold (40P), and fuzzy locally adaptive Bayesian (FLAB) algorithms. Intraclass correlation coefficient (ICC) was used to measure the inter-observer variability of the texture features derived by the three segmentation algorithms. Univariate cox regression was used on 12 commonly reported texture features to predict overall survival (OS) for each segmentation algorithm. Model quality was compared across segmentation algorithms using Akaike information criterion (AIC).

RESULTS

40P was the most reproducible algorithm (median ICC 0.9; interquartile range [IQR] 0.85-0.92) compared with FLAB (median ICC 0.83; IQR 0.77-0.86) and FH (median ICC 0.77; IQR 0.7-0.85). On univariate cox regression analysis, 40P found 2 out of 12 variables, i.e. first-order entropy and grey-level co-occurence matrix (GLCM) entropy, to be significantly associated with OS; FH and FLAB found 1, i.e., first-order entropy. For each tested variable, survival models for all three segmentation algorithms were of similar quality, exhibiting comparable AIC values with overlapping 95% CIs.

CONCLUSIONS

Compared with both FLAB and FH, segmentation with 40P yields superior inter-observer reproducibility of texture features. Survival models generated by all three segmentation algorithms are of at least equivalent utility. Our findings suggest that a segmentation algorithm using a 40% of maximum threshold is acceptable for texture analysis of 18F-FDG PET in NSCLC.

Clinical applications of textural analysis in non-small cell lung cancer

Lung cancer is the leading cause of cancer mortality worldwide. Treatment pathways include regular cross-sectional imaging, generating large data sets which present intriguing possibilities for exploitation beyond standard visual interpretation. This additional data mining has been termed "radiomics" and includes semantic and agnostic approaches. Textural analysis (TA) is an example of the latter, and uses a range of mathematically derived features to describe an image or region of an image. Often TA is used to describe a suspected or known tumour. TA is an attractive tool as large existing image sets can be submitted to diverse techniques for data processing, presentation, interpretation and hypothesis testing with annotated clinical outcomes. There is a growing anthology of published data using different TA techniques to differentiate between benign and malignant lung nodules, differentiate tissue subtypes of lung cancer, prognosticate and predict outcome and treatment response, as well as predict treatment side effects and potentially aid radiotherapy planning. The aim of this systematic review is to summarize the current published data and understand the potential future role of TA in managing lung cancer.

In-vivo Comparison of 18F-FLT uptake, CT Number, Tumor Volume in Evaluation of Repopulation during Radiotherapy for Lung cancer

Accelerated repopulation has been observed in various tumors. This study was aimed to evaluate the potential of 3'-deoxy-3'-¹⁸F-fluorothymidine (¹⁸F-FLT) uptake and Computed Tomography Number (CTN) in monitoring tumor responses to radiotherapy compared with tumor volume (TV) changes. Tumor bearing nude mice were assigned to either irradiated daily or every second day group and then randomized to 6 sub-groups to receive 0Gy, 6Gy, 12Gy, 18Gy, 24Gy, 36Gy irradiation, respectively. TV was measured every 3 days. ¹⁸F-FLT micro-PET/CT scans were performed after irradiation being completed. Tumor sections were stained to calculate the immunohistochemical (Ki-67) labeling index (LI). Comparison analysis between FLT uptake parameters, CTNs, VTs and Ki-67 LI results were conducted to determine the correlation. Ki-67 LI increased significantly after 6 times of irradiation at irradiated daily group and after 3 times at irradiated every second day group, suggesting accelerated repopulation. No shrinkage of TV was noticed at two groups during irradiation delivery. Both ¹⁸F-FLT uptake and CTN increased significantly after irradiation of 12Gy/6f/6d and 6Gy/3f/6d. Comparison analysis found a significant relationship between Ki-67 LI and ¹⁸F-FLT uptake parameters as well as CTN. Both ¹⁸F-FLT PET and CT have the potential to reflect the tumor proliferative response during radiation delivery.

Quantitative Computed Tomography Features for Predicting Tumor Recurrence in Patients with Surgically Resected Adenocarcinoma of the Lung

Purpose

The purpose of this study was to determine if preoperative quantitative computed tomography (CT) features including texture and histogram analysis measurements are associated with tumor recurrence in patients with surgically resected adenocarcinoma of the lung.

Methods

The study included 194 patients with surgically resected lung adenocarcinoma who underwent preoperative CT between January 2013 and December 2013. Quantitative CT feature analysis of the lung adenocarcinomas were performed using in-house software based on plug-in package for ImageJ. Ten quantitative features demonstrating the tumor size, attenuation, shape and texture were extracted. The CT parameters obtained from 1-mm and 5-mm data were compared using intraclass correlation coefficients. Univariate and multivariable logistic regression methods were used to investigate the association between tumor recurrence and preoperative CT findings.

Results

The 1-mm and 5-mm data were highly correlated in terms of diameter, perimeter, area, mean attenuation and entropy. Circularity and aspect ratio were moderately correlated. However, skewness and kurtosis were poorly correlated. Multivariable logistic regression analysis revealed that area (odds ratio [OR], 1.002 for each 1-mm² increase; P = 0.003) and mean attenuation (OR, 1.005 for each 1.0-Hounsfield unit increase; P = 0.022) were independently associated with recurrence. The receiver operating curves using these two independent predictive factors showed high diagnostic performance in predicting recurrence (C-index = 0.81, respectively).

Conclusion

Tumor area and mean attenuation are independently associated with recurrence in patients with surgically resected adenocarcinoma of the lung.

A 3-D Riesz-Covariance Texture Model for Prediction of Nodule Recurrence in Lung CT

This paper proposes a novel imaging biomarker of lung cancer relapse from 3-D texture analysis of CT images. Three-dimensional morphological nodular tissue properties are described in terms of 3-D Riesz-wavelets. The responses of the latter are aggregated within nodular regions by means of feature covariances, which leverage rich intra- and inter-variations of the feature space dimensions. When compared to the classical use of the average for feature aggregation, feature covariances preserve spatial co-variations between features. The obtained Riesz-covariance descriptors lie on a manifold governed by Riemannian geometry allowing geodesic measurements and differentiations. The latter property is incorporated both into a kernel for support vector machines (SVM) and a manifold-aware sparse regularized classifier. The effectiveness of the presented models is evaluated on a dataset of 110 patients with non-small cell lung carcinoma (NSCLC) and cancer recurrence information. Disease recurrence within a timeframe of 12 months could be predicted with an accuracy of 81.3-82.7%. The anatomical location of recurrence could be discriminated between local, regional and distant failure with an accuracy of 78.3-93.3%. The obtained results open novel research perspectives by revealing the importance of the nodular regions used to build the predictive models.

Imaging Heterogeneity in Lung Cancer: Techniques, Applications, and Challenges

OBJECTIVE

Texture analysis involves the mathematic processing of medical images to derive sets of numeric quantities that measure heterogeneity. Studies on lung cancer have shown that texture analysis may have a role in characterizing tumors and predicting patient outcome. This article outlines the mathematic basis of and the most recent literature on texture analysis in lung cancer imaging. We also describe the challenges facing the clinical implementation of texture analysis.

CONCLUSION

Texture analysis of lung cancer images has been applied successfully to FDG PET and CT scans. Different texture parameters have been shown to be predictive of the nature of disease and of patient outcome. In general, it appears that more heterogeneous tumors on imaging tend to be more aggressive and to be associated with poorer outcomes and that tumor heterogeneity on imaging decreases with treatment. Despite these promising results, there is a large variation in the reported data and strengths of association.

Early-Stage Non-Small Cell Lung Cancer: Quantitative Imaging Characteristics of (18)F Fluorodeoxyglucose PET/CT Allow Prediction of Distant Metastasis

Purpose To identify quantitative imaging biomarkers at fluorine 18 ((18)F) positron emission tomography (PET) for predicting distant metastasis in patients with early-stage non-small cell lung cancer (NSCLC). Materials and Methods In this institutional review board-approved HIPAA-compliant retrospective study, the pretreatment (18)F fluorodeoxyglucose PET images in 101 patients treated with stereotactic ablative radiation therapy from 2005 to 2013 were analyzed. Data for 70 patients who were treated before 2011 were used for discovery purposes, while data from the remaining 31 patients were used for independent validation. Quantitative PET imaging characteristics including statistical, histogram-related, morphologic, and texture features were analyzed, from which 35 nonredundant and robust features were further evaluated. Cox proportional hazards regression model coupled with the least absolute shrinkage and selection operator was used to predict distant metastasis. Whether histologic type provided complementary value to imaging by combining both in a single prognostic model was also assessed. Results The optimal prognostic model included two image features that allowed quantification of intratumor heterogeneity and peak standardized uptake value. In the independent validation cohort, this model showed a concordance index of 0.71, which was higher than those of the maximum standardized uptake value and tumor volume, with concordance indexes of 0.67 and 0.64, respectively. The prognostic model also allowed separation of groups with low and high risk for developing distant metastasis (hazard ratio, 4.8; P = .0498, log-rank test), which compared favorably with maximum standardized uptake value and tumor volume (hazard ratio, 1.5 and 2.0, respectively; P = .73 and 0.54, log-rank test, respectively). When combined with histologic types, the prognostic power was further improved (hazard ratio, 6.9; P = .0289, log-rank test; and concordance index, 0.80). Conclusion PET imaging characteristics associated with distant metastasis that could potentially help practitioners to tailor appropriate therapy for individual patients with early-stage NSCLC were identified. (©) RSNA, 2016 Online supplemental material is available for this article.

3D Riesz-wavelet based Covariance descriptors for texture classification of lung nodule tissue in CT

In this paper we present a novel technique for characterizing and classifying 3D textured volumes belonging to different lung tissue types in 3D CT images. We build a volume-based 3D descriptor, robust to changes of size, rigid spatial transformations and texture variability, thanks to the integration of Riesz-wavelet features within a Covariance-based descriptor formulation. 3D Riesz features characterize the morphology of tissue density due to their response to changes in intensity in CT images. These features are encoded in a Covariance-based descriptor formulation: this provides a compact and flexible representation thanks to the use of feature variations rather than dense features themselves and adds robustness to spatial changes. Furthermore, the particular symmetric definite positive matrix form of these descriptors causes them to lay in a Riemannian manifold. Thus, descriptors can be compared with analytical measures, and accurate techniques from machine learning and clustering can be adapted to their spatial domain. Additionally we present a classification model following a "Bag of Covariance Descriptors" paradigm in order to distinguish three different nodule tissue types in CT: solid, ground-glass opacity, and healthy lung. The method is evaluated on top of an acquired dataset of 95 patients with manually delineated ground truth by radiation oncology specialists in 3D, and quantitative sensitivity and specificity values are presented.