A tumor vasculature-based imaging biomarker for predicting response and survival in patients with lung cancer treated with checkpoint inhibitors

Tumor vasculature is a key component of the tumor microenvironment that can influence tumor behavior and therapeutic resistance. We present a new imaging biomarker, quantitative vessel tortuosity (QVT), and evaluate its association with response and survival in patients with non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitor (ICI) therapies. A total of 507 cases were used to evaluate different aspects of the QVT biomarkers. QVT features were extracted from computed tomography imaging of patients before and after ICI therapy to capture the tortuosity, curvature, density, and branching statistics of the nodule vasculature. Our results showed that QVT features were prognostic of OS (HR = 3.14, 0.95% CI = 1.2 to 9.68, P = 0.0006, C-index = 0.61) and could predict ICI response with AUCs of 0.66, 0.61, and 0.67 on three validation sets. Our study shows that QVT imaging biomarker could potentially aid in predicting and monitoring response to ICI in patients with NSCLC.

Novel Radiomic Measurements of Tumor-Associated Vasculature Morphology on Clinical Imaging as a Biomarker of Treatment Response in Multiple Cancers

PURPOSE

The tumor-associated vasculature (TAV) differs from healthy blood vessels by its convolutedness, leakiness, and chaotic architecture, and these attributes facilitate the creation of a treatment-resistant tumor microenvironment. Measurable differences in these attributes might also help stratify patients by likely benefit of systemic therapy (e.g., chemotherapy). In this work, we present a new category of computational image-based biomarkers called quantitative tumor-associated vasculature (QuanTAV) features, and demonstrate their ability to predict response and survival across multiple cancer types, imaging modalities, and treatment regimens involving chemotherapy.

EXPERIMENTAL DESIGN

We isolated tumor vasculature and extracted mathematical measurements of twistedness and organization from routine pretreatment radiology (CT or contrast-enhanced MRI) of a total of 558 patients, who received one of four first-line chemotherapy-based therapeutic intervention strategies for breast (n = 371) or non-small cell lung cancer (NSCLC, n = 187).

RESULTS

Across four chemotherapy-based treatment strategies, classifiers of QuanTAV measurements significantly (P < 0.05) predicted response in held out testing cohorts alone (AUC = 0.63-0.71) and increased AUC by 0.06-0.12 when added to models of significant clinical variables alone. Similarly, we derived QuanTAV risk scores that were prognostic of recurrence-free survival in treatment cohorts who received surgery following chemotherapy for breast cancer [P = 0.0022; HR = 1.25; 95% confidence interval (CI), 1.08-1.44; concordance index (C-index) = 0.66] and chemoradiation for NSCLC (P = 0.039; HR = 1.28; 95% CI, 1.01-1.62; C-index = 0.66). From vessel-based risk scores, we further derived categorical QuanTAV high/low risk groups that were independently prognostic among all treatment groups, including patients with NSCLC who received chemotherapy only (P = 0.034; HR = 2.29; 95% CI, 1.07-4.94; C-index = 0.62). QuanTAV response and risk scores were independent of clinicopathologic risk factors and matched or exceeded models of clinical variables including posttreatment response.

CONCLUSIONS

Across these domains, we observed an association of vascular morphology on CT and MRI-as captured by metrics of vessel curvature, torsion, and organizational heterogeneity-and treatment outcome. Our findings suggest the potential of shape and structure of the TAV in developing prognostic and predictive biomarkers for multiple cancers and different treatment strategies.

An End-to-End Integrated Clinical and CT-Based Radiomics Nomogram for Predicting Disease Severity and Need for Ventilator Support in COVID-19 Patients: A Large Multisite Retrospective Study

OBJECTIVE

The disease COVID-19 has caused a widespread global pandemic with ~3. 93 million deaths worldwide. In this work, we present three models-radiomics (M_RM), clinical (M_CM), and combined clinical-radiomics (M_RCM) nomogram to predict COVID-19-positive patients who will end up needing invasive mechanical ventilation from the baseline CT scans.

METHODS

We performed a retrospective multicohort study of individuals with COVID-19-positive findings for a total of 897 patients from two different institutions (Renmin Hospital of Wuhan University, D₁ = 787, and University Hospitals, US D₂ = 110). The patients from institution-1 were divided into 60% training, D 1 T ( N = 473 ) , and 40% test set D 1 V ( N = 314 ) . The patients from institution-2 were used for an independent validation test set D 2 V ( N = 110 ) . A U-Net-based neural network (CNN) was trained to automatically segment out the COVID consolidation regions on the CT scans. The segmented regions from the CT scans were used for extracting first- and higher-order radiomic textural features. The top radiomic and clinical features were selected using the least absolute shrinkage and selection operator (LASSO) with an optimal binomial regression model within D 1 T .

RESULTS

The three out of the top five features identified using D 1 T were higher-order textural features (GLCM, GLRLM, GLSZM), whereas the last two features included the total absolute infection size on the CT scan and the total intensity of the COVID consolidations. The radiomics model (M_RM) was constructed using the radiomic score built using the coefficients obtained from the LASSO logistic model used within the linear regression (LR) classifier. The M_RM yielded an area under the receiver operating characteristic curve (AUC) of 0.754 (0.709-0.799) on D 1 T , 0.836 on D 1 V , and 0.748 D 2 V . The top prognostic clinical factors identified in the analysis were dehydrogenase (LDH), age, and albumin (ALB). The clinical model had an AUC of 0.784 (0.743-0.825) on D 1 T , 0.813 on D 1 V , and 0.688 on D 2 V . Finally, the combined model, M_RCM integrating radiomic score, age, LDH and ALB, yielded an AUC of 0.814 (0.774-0.853) on D 1 T , 0.847 on D 1 V , and 0.771 on D 2 V . The M_RCM had an overall improvement in the performance of ~5.85% ( D 1 T : p = 0.0031; D 1 V p = 0.0165; D 2 V : p = 0.0369) over M_CM.

CONCLUSION

The novel integrated imaging and clinical model (M_RCM) outperformed both models (M_RM) and (M_CM). Our results across multiple sites suggest that the integrated nomogram could help identify COVID-19 patients with more severe disease phenotype and potentially require mechanical ventilation.

37 Quantitative Lung Airway Morphology (QuaLM) features on chest CT scans are associated with response and overall survival in lung cancer patients treated with checkpoint inhibitors

Background

Immune checkpoint inhibitors (ICI) have revolutionized the management of lung tumors decreasing mortality rates. However, the response rates to these ICI drugs are limited, and identifying those patients who are most likely to benefit remains a clinical challenge. Due to the complex nature of the host immune response, tissue-based biomarker development for immunotherapy (IO) is challenging. Consequently, there is a critical unmet need to develop accurate, validated imaging biomarkers to predict which Non-Small Cell Lung Cancer (NSCLC) patients will benefit from IO. Airway deformations such as central airway obstruction can be considered an important manifestation of cancer aggressiveness or metastatic disease and may have a significant impact on therapeutic refractoriness. In this study, we sought to evaluate whether quantitative measurements of lung airway morphology (QuaLM) on baseline CT scans are associated with response and overall survival in NSCLC patients treated with ICI.

Methods

In this retrospective study, 80 cases who underwent 2–3 cycles of PD1/PD-L1 ICI therapy (nivolumab/pembrolizumab/atezolizumab) were included. RECIST v1.1 was used to define ‘responders’ and ‘non-responders’. Patients were randomly divided into a training (n=40) and a test set (n=40). A region growing algorithm is applied to the trachea, identified by Hough transform, to segment bronchi and bronchioles (figure 1a). 14 QuaLM features were extracted from segmented airway on CT scans. Wilcoxson ranksum test is used to identify the predictive QuaLM features. The top 4 QuaLM features in conjunction with a linear discriminant machine learning classifier were used to predict the response to IO. We also built a QuaLM risk score using the least absolute shrinkage and selection operator (LASSO) Cox regression model to predict overall survival (OS).

Results

The response prediction model trained with top QuaLM features (table 1) predicts responders to ICI with an area under research operating characteristic curve (ROC AUC) of 0.67±0.08 (figure 1.b) in the training (St) and AUC=0.63 in the test set (Sv). The airway radiomics risk-score was found to be significantly associated with OS in St (HR=2.34, 95% CI:[1.08–5.07], P=0.008) and Sv (HR=2.55, 95% CI:[0.8–8.1], P=0.034) (figure 1.c).

Conclusions

QuaLM features were able to distinguish responders from non-responders and also were found to be associated with OS for NSCLC patients treated with ICI. With additional validation, QuaLM could potentially serve as an imaging biomarker of ICI response assessment for NSCLC patients. This could allow the selection of NSCLC patients who will benefit from IO and help design more rational clinical trials with a combination of IO.

Abstract 37 Figure 1

a) The pipeline of airway segmentation includes trachea identification, segmenting the lung regions from surrounding anatomy, and segmenting the airway by applying a region-growing algorithm. b) ROC curve of QuaLM model for predicting IO response from baseline CT scans. c) Kaplan Meier curve analysis reveals dichotomization of patients into low risk and high-risk groups with distinct survival patterns based off QuaLM features. d,e) An example airway structure of a non-responder and a responder to ICI.

Abstract 37 Table 1

Predictive airway features that found to be significantly different among responders and non-responders to IO

Risk factors for major complications after liver resection: A large liver resection study from Morocco and audit of a non-Eastern/non-Western experience

BACKGROUND AND STUDY AIMS

In developing countries, endemic indications, blood shortages, and the scarcity of liver surgeons and intensive care providers can affect liver resection (LR) outcomes, but these have been rarely addressed in the literature. Therefore, in this study we determined risk factors for major complications after LR in a North African general surgery and teaching department.

PATIENTS AND METHODS

From January 2010 to December 2015, 213 consecutive LRs were performed on 203 patients. All patients underwent a postoperative follow-up of >90 days. Postoperative complications were assessed according to the Clavien-Dindo (CD) classification of surgical complications. A score of CD ≥III is considered as major postoperative complications. In this study, we analyzed the variables assumed to affect these complications.

RESULTS

The overall 90-day complication rate was 35.7% (n = 76), including a CD ≥III of 14% (n = 30) and a mortality rate of 6.1% (n = 14). According to the multivariate analysis, a preoperative performance status (PS) of ≥2 (P = 0.011; odds ratios [OR], 6.8; 95% confidence intervals [CI], 1.55-29.8), an estimated intraoperative blood loss of >500 ml (P = 0.002; OR, 3.71; 95% CI, 1.23-11.20), and bilioenteric anastomosis (P < 0.004; OR, 7.76; 95% CI, 1.5-3.89) were independent risk factors for major complications after LR.

CONCLUSION

We recommend that, in the setting of a non-Eastern/non-Western general surgery and teaching department, patients with a PS of ≥2 should undergo a specific selection and preoperative optimization protocol; intermittent clamping indications should be extended; and special attention should paid to patients undergoing LR associated with biliary reconstruction, such as for perihilar cholangiocarcinoma.

Integrated Clinical and CT based Artificial Intelligence nomogram for predicting severity and need for ventilator support in COVID-19 patients: A multi-site study

Almost 25% of COVID-19 patients end up in ICU needing critical mechanical ventilation support. There is currently no validated objective way to predict which patients will end up needing ventilator support, when the disease is mild and not progressed. N = 869 patients from two sites (D₁: N = 822, D₂: N = 47) with baseline clinical characteristics and chest CT scans were considered for this study. The entire dataset was randomly divided into 70% training, D₁^train (N = 606) and 30% test-set (D^test: D₁^test (N = 216) + D₂ (N = 47)). An expert radiologist delineated ground-glass-opacities (GGOs) and consolidation regions on a subset of D₁^train, (D₁^train_sub, N = 88). These regions were automatically segmented and used along with their corresponding CT volumes to train an imaging AI predictor (AIP) on D₁^train to predict the need of mechanical ventilators for COVID-19 patients. Finally, top five prognostic clinical factors selected using univariate analysis were integrated with AIP to construct an integrated clinical and AI imaging nomogram (ClAIN). Univariate analysis identified lactate dehydrogenase, prothrombin time, aspartate aminotransferase, %lymphocytes, albumin as top five prognostic clinical features. AIP yielded an AUC of 0.81 on D^test and was independently prognostic irrespective of other clinical parameters on multivariable analysis (p<0.001). ClAIN improved the performance over AIP yielding an AUC of 0.84 (p = 0.04) on D^test. ClAIN outperformed AIP in predicting which COVID-19 patients ended up needing a ventilator. Our results across multiple sites suggest that ClAIN could help identify COVID-19 with severe disease more precisely and likely to end up on a life-saving mechanical ventilation.

Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade

Purpose

Hyperprogression is an atypical response pattern to immune checkpoint inhibition that has been described within non-small cell lung cancer (NSCLC). The paradoxical acceleration of tumor growth after immunotherapy has been associated with significantly shortened survival, and currently, there are no clinically validated biomarkers to identify patients at risk of hyperprogression.

Experimental design

A total of 109 patients with advanced NSCLC who underwent monotherapy with Programmed cell death protein-1 (PD1)/Programmed death-ligand-1 (PD-L1) inhibitors were included in the study. Using RECIST measurements, we divided the patients into responders (n=50) (complete/partial response or stable disease) and non-responders (n=59) (progressive disease). Tumor growth kinetics were used to further identify hyperprogressors (HPs, n=19) among non-responders. Patients were randomized into a training set (D₁=30) and a test set (D₂=79) with the essential caveat that HPs were evenly distributed among the two sets. A total of 198 radiomic textural patterns from within and around the target nodules and features relating to tortuosity of the nodule associated vasculature were extracted from the pretreatment CT scans.

Results

The random forest classifier using the top features associated with hyperprogression was able to distinguish between HP and other radiographical response patterns with an area under receiver operating curve of 0.85±0.06 in the training set (D₁=30) and 0.96 in the validation set (D₂=79). These features included one peritumoral texture feature from 5 to 10 mm outside the tumor and two nodule vessel-related tortuosity features. Kaplan-Meier survival curves showed a clear stratification between classifier predicted HPs versus non-HPs for overall survival (D₂: HR=2.66, 95% CI 1.27 to 5.55; p=0.009).

Conclusions

Our study suggests that image-based radiomics markers extracted from baseline CTs of advanced NSCLC treated with PD-1/PD-L1 inhibitors may help identify patients at risk of hyperprogressions.

Radiomics-based assessment of ultra-widefield leakage patterns and vessel network architecture in the PERMEATE study: insights into treatment durability

AIM

To evaluate the potential of radiomics-based ultra-widefield fluorescein angiography (UWFA)-derived imaging biomarkers in retinal vascular disease for predicting therapeutic durability of intravitreal aflibercept injection (IAI).

METHODS

The Peripheral and Macular Retinal Vascular Perfusion and Leakage Dynamics in Diabetic Macular Edema and Retinal Venous Occlusions During Intravitreal Aflibercept Injection (IAI) Treatment for Retinal Edema (PERMEATE) study prospectively evaluated quantitative UWFA dynamics in diabetic macular oedema or macular oedema secondary to retinal vascular occlusion. 27 treatment-naïve eyes were treated with 2 mg IAI q4 weeks for the first 6 months, and then administered q8 weeks. Morphological and graph-based attributes were used to model the spatial distribution of leakage areas, while tortuosity measures were used to model the vessel network disorder. Eyes were grouped based on functional tolerance of the first 8-week treatment interval challenge. 'Non-rebounders' (N=15) maintained/improved best-corrected visual acuity (BCVA) following the 8-week challenge. 'Rebounders' (N=12) exhibited worsened BVCA. The image biomarkers were used with a machine learning classifier to preliminarily evaluate their ability to predict BCVA stability.

RESULTS

Two new UWFA image-derived biomarkers were identified and extracted. The cross-validated area under the receiver operating characteristic curve (AUC) was 0.77±0.14 using baseline leakage distribution features and 0.73±0.10 for the UWFA baseline tortuosity measures. Additionally, the change in vascular tortuosity between month 4 and baseline yielded an AUC of 0.73±0.08. Three baseline clinical features of letter score, macular volume and central subfield thickness yielded a corresponding AUC of 0.42±0.09.

CONCLUSIONS

Two computer-extracted UWFA radiomics-based descriptors were identified as potential biomarkers for predicting treatment durability and tolerance of longer treatment intervals. Conventional treatment parameters were not significantly different between these same groups.

Stable and discriminating radiomic predictor of recurrence in early stage non-small cell lung cancer: Multi-site study

OBJECTIVES

To evaluate whether combining stability and discriminability criteria in building radiomic classifiers will improve the prognosis of cancer recurrence in early stage non-small cell lung cancer on non-contrast computer tomography (CT).

MATERIALS AND METHODS

CT scans of 610 patients with early stage (IA, IB, IIA) NSCLC from four independent cohorts were evaluated. A total of 350 patients from Cleveland Clinic Foundation and University of Pennsylvania were divided into two equal sets for training (D₁) and validation set (D₂). 80 patients from The Cancer Genome Atlas Lung Adenocarcinoma and Squamous Cell Carcinoma and 195 patients from The Cancer Imaging Archive, were used as independent second (D₃) and third (D₄) validation sets. A linear discriminant analysis (LDA) classifier was built based on the most stable and discriminate features. In addition, a radiomic risk score (RRS) was generated by using least absolute shrinkage and selection operator, Cox regression model to predict time to progression (TTP) following surgery.

RESULTS

A feature selection strategy focusing on both feature discriminability and stability resulted in the classifier having a higher discriminability on validation datasets compared to the discriminability alone criteria in discriminating cancer recurrence (D₂, AUC of 0.75 vs. 0.65; D₃, 0.74 vs. 0.62; D₄, 0.76 vs. 0.63). The RRS generated by most stable-discriminating features was significantly associated with TTP compared to discriminating alone criteria (HR = 1.66, C-index of 0.72 vs. HR = 1.04, C-index of 0.62).

CONCLUSION

Accounting for both stability and discriminability yielded a more generalizable classifier for predicting cancer recurrence and TTP in early stage NSCLC.

Abstract P1-10-06: Radiomic measurements of tumor-associated vasculature morphology and function on pretreatment dynamic MRI identifies responders to neoadjuvant chemotherapy

Background: Angiogenesis is crucial to a tumor's growth and an important factor in therapeutic outcome. Although quantitative analysis of tumors on dynamic contrast enhanced (DCE) MRI can provide indirect characterization of a tumor's vascularization, direct computational analysis of the tumor-associated vessel network remains a promising, but under-explored potential marker of therapeutic response. For instance, surrounding vasculature with a convoluted 3-dimensional shape and poor blood flow may indicate a more aggressive tumor and poorly facilitate delivery of therapeutic agents. In this work, we present a computational approach for the prediction of neoadjuvant chemotherapy response using quantitative imaging features describing the morphology and function of tumor associated vasculature on pretreatment MRI.

Methods: 243 patients who received DCE-MRI scans prior to neo-adjuvant chemotherapy (NAC) at institution A [n=83], B [n=76], or one of nine other institutions as part of the ISPY1 Trial [n=84] were divided randomly into training (n=123) and testing (n=120) sets. 148 patients were HER2- and received neoadjuvant AC-T, while the 95 HER2+ patients were treated with TCHP (ISPY predates anti-HER2 therapy and HER2+ ISPY patients were excluded). 79 patients achieved pathological complete response [pCR, ypT0/is] following NAC. MRI exams were collected with a 1.5 or 3 Tesla scanner in the axial or sagittal plane. A baseline scan and 2-5 scans after injection of a gadolinium-based contrast agent with a median temporal resolution of 2.5 minutes were acquired. A portion of the tumor was manually delineated, then semi-automatically expanded to 3D. Vasculature was isolated from subtraction images with a specialized filtering approach to detect vessel-shaped objects. Features describing the 3D shape and architecture of the tumor-associated vessel network (e.g. curvature, torsion, and local orientation) and functional semi-quantitative pharmacokinetic (PK) measurements of temporal contrast enhancement changes (e.g. signal enhancement ratio, time to peak enhancement, and rates of uptake and washout) were calculated. Performance was assessed by area under the receiver operating characteristic curve (AUC), as well as the accuracy, sensitivity, and specificity at the operating point corresponding to the Youden Index. The most discriminating features were determined based on frequency of selection by the random forest classifier.

Results: Within the training set, PK parameters of the vessels (AUC=.66) outperformed relative to the PK of tumor (AUC=.63) and the PK of peritumoral regions (AUC=.64); however, a combination of the three yielded best performance (AUC=.75). Vessel shape features alone achieved AUC=.67 in the training set. When multi-region PK features and tumor shape features were combined and applied to the 120-patient independent testing set, the random forest classifier achieved an AUC of 0.70 and identified 81% of patients who would achieve pCR. Non-pCR was best characterized by increased vessel curvature and PK parameters indicating poor perfusion, such as greater time to peak enhancement, slower uptake rate, and quicker washout.

Conclusions: Our findings suggest that properties of the tumor-associated vessel network, such as its shape and enhancement profile, might provide value in identifying patients who will respond to NAC before administration of treatment.

Accuracy (%)Sensitivity (%)Specificity (%)Full testing set (n=120)678160HER2+ (n=44)709548HER2- (n=76)646365HER2-, HR+ (n=51)678364Triple Negative (n=25)605067

Citation Format: Nathaniel Braman, Prateek Prasanna, Kaustav Bera, Mehdi Alilou, Manasa Vulchi, Maryam Etesami, Paulette Turk, Jame Abraham, Donna Plecha, Anant Madabhushi. Radiomic measurements of tumor-associated vasculature morphology and function on pretreatment dynamic MRI identifies responders to neoadjuvant chemotherapy [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P1-10-06.

Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non-Small Cell Lung Cancer

No predictive biomarkers can robustly identify patients with non-small cell lung cancer (NSCLC) who will benefit from immune checkpoint inhibitor (ICI) therapies. Here, in a machine learning setting, we compared changes ("delta") in the radiomic texture (DelRADx) of CT patterns both within and outside tumor nodules before and after two to three cycles of ICI therapy. We found that DelRADx patterns could predict response to ICI therapy and overall survival (OS) for patients with NSCLC. We retrospectively analyzed data acquired from 139 patients with NSCLC at two institutions, who were divided into a discovery set (D1 = 50) and two independent validation sets (D2 = 62, D3 = 27). Intranodular and perinodular texture descriptors were extracted, and the relative differences were computed. A linear discriminant analysis (LDA) classifier was trained with 8 DelRADx features to predict RECIST-derived response. Association of delta-radiomic risk score (DRS) with OS was determined. The association of DelRADx features with tumor-infiltrating lymphocyte (TIL) density on the diagnostic biopsies (n = 36) was also evaluated. The LDA classifier yielded an AUC of 0.88 ± 0.08 in distinguishing responders from nonresponders in D1, and 0.85 and 0.81 in D2 and D3 DRS was associated with OS [HR: 1.64; 95% confidence interval (CI), 1.22-2.21; P = 0.0011; C-index = 0.72). Peritumoral Gabor features were associated with the density of TILs on diagnostic biopsy samples. Our results show that DelRADx could be used to identify early functional responses in patients with NSCLC.

Predicting pathologic response to neoadjuvant chemoradiation in resectable stage III non-small cell lung cancer patients using computed tomography radiomic features

OBJECTIVE

The use of a neoadjuvant chemoradiation followed by surgery in patients with stage IIIA NSCLC is controversial and the benefit of surgery is limited. There are currently no clinically validated biomarkers to select patients for such an approach. In this study we evaluate computed tomography (CT) derived intratumoral and peritumoral texture and nodule shape features in their ability to predict major pathological response (MPR). MPR being defined as ≤10% of residual viable tumor, assessed at the time of surgery.

MATERIAL AND METHODS

Ninety patients with stage III NSCLC treated with chemoradiation prior to surgical resection were selected. The patients were divided randomly into two equal sets, one for training and one for independent testing. The radiomic texture and shape features were extracted from within the nodule (intra) and from the parenchymal regions immediately surrounding the nodule (peritumoral). A univariate regression analysis was performed on the image and clinicopathologic variables and then included into a multivariable logistic regression (MLR) for binary outcome prediction of MPR. The radiomic signature risk-score was generated by using a multivariate Cox regression model and association of the signature with OS and DFS was also evaluated.

RESULTS

Thirteen stable and predictive intratumoral and peritumoral radiomic texture features were found to be predictive of MPR. The MLR classifier yielded an AUC of 0.90 ± 0.025 within the training set and a corresponding AUC = 0.86 in prediction of MPR within the test set. The radiomic signature was also significantly associated with OS (HR = 11.18, 95% CI = 3.17, 44.1; p-value = 0.008) and DFS (HR = 2.78, 95% CI = 1.11, 4.12; p-value = 0.0042) in the testing set.

CONCLUSION

Texture features extracted within and around the lung tumor on CT images appears to be associated with the likelihood of MPR, OS and DFS to chemoradiation.

Intra and perinodular CT delta radiomic features associated with early response to predict overall survival (OS) in immunotherapy-treated non-small cell lung cancer (NSCLC): A multisite multi-agent study

2588

Background: None of the current biomarkers for predicting response to checkpoint inhibitors (ICIT) for advanced NSCLC are associated with long-term benefits, such as improved OS. In this multi-agent (nivolumab, pembrolizumab, or atezolizumab) multi-site study (Cleveland Clinic, Univ. of Pennsylvania), we demonstrate that changes in computer-extracted textural patterns, from within and 30mm outside the nodules, between baseline and post-treatment CT following ICIT correlate with RECIST-derived responses, and are prognostic of OS. Methods: CT scans from 139 NSCLC patients both pre-, and post 2-3 cycles of ICIT were acquired from 2 sites. Patients with objective response/stable disease per RECIST v1.1 were defined as ‘responders’, and those with progressive disease were ‘non-responders’. The cohort was divided into a discovery (D1 = 50) and two validation sets (D2 = 62, D3 = 27). 454 intranodular texture (IT) features, and 7426 perinodular features (PT) were extracted from the temporalscans, Relative differences were computed to yield a set of ‘delta-radiomic’ descriptors. In D1, 8 features that evolved the most between baseline and post-treatment CT, and performed the best in identifying responders, were determined. These were then used with a Linear Discriminant Analysis classifier to identify the responders from the non-responders. We then computed a radiomic risk score (RRS) system and tested its prognostic ability in assessing differences in OS. Results: A combination of 5 IT, 3 PT delta radiomic features yielded an AUC of 0.88 ± 0.08 in D1 and a corresponding AUC = 0.85 and 0.81 in D2 and D3, respectively. Multivariate survival metrics are shown in Table. Conclusions: Delta-radiomic features, both from inside and outside the nodules, could be used to identify patients likely to derive clinical benefit from ICIT (eg: OS) beyond anatomic response. [Table: see text]

Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas

Purpose To evaluate ability of radiomic (computer-extracted imaging) features to distinguish non-small cell lung cancer adenocarcinomas from granulomas at noncontrast CT. Materials and Methods For this retrospective study, screening or standard diagnostic noncontrast CT images were collected for 290 patients (mean age, 68 years; range, 18-92 years; 125 men [mean age, 67 years; range, 18-90 years] and 165 women [mean age, 68 years; range, 33-92 years]) from two institutions between 2007 and 2013. Histopathologic analysis was available for one nodule per patient. Corresponding nodule of interest was identified on axial CT images by a radiologist with manual annotation. Nodule shape, wavelet (Gabor), and texture-based (Haralick and Laws energy) features were extracted from intra- and perinodular regions. Features were pruned to train machine learning classifiers with 145 patients. In a test set of 145 patients, classifier results were compared against a convolutional neural network (CNN) and diagnostic readings of two radiologists. Results Support vector machine classifier with intranodular radiomic features achieved an area under the receiver operating characteristic curve (AUC) of 0.75 on the test set. Combining radiomics of intranodular with perinodular regions improved the AUC to 0.80. On the same test set, CNN resulted in an AUC of 0.76. Radiologist readers achieved AUCs of 0.61 and 0.60, respectively. Conclusion Radiomic features from intranodular and perinodular regions of nodules can distinguish non-small cell lung cancer adenocarcinomas from benign granulomas at noncontrast CT. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Nishino in this issue.

Combination of computer extracted shape and texture features enables discrimination of granulomas from adenocarcinoma on chest computed tomography

Differentiation between benign and malignant nodules is a problem encountered by radiologists when visualizing computed tomography (CT) scans. Adenocarcinomas and granulomas have a characteristic spiculated appearance and may be fluorodeoxyglucose avid, making them difficult to distinguish for human readers. In this retrospective study, we aimed to evaluate whether a combination of radiomic texture and shape features from noncontrast CT scans can enable discrimination between granulomas and adenocarcinomas. Our study is composed of CT scans of 195 patients from two institutions, one cohort for training ([Formula: see text]) and the other ([Formula: see text]) for independent validation. A set of 645 three-dimensional texture and 24 shape features were extracted from CT scans in the training cohort. Feature selection was employed to identify the most informative features using this set. The top ranked features were also assessed in terms of their stability and reproducibility across the training and testing cohorts and between scans of different slice thickness. Three different classifiers were constructed using the top ranked features identified from the training set. These classifiers were then validated on the test set and the best classifier (support vector machine) yielded an area under the receiver operating characteristic curve of 77.8%.

An integrated segmentation and shape-based classification scheme for distinguishing adenocarcinomas from granulomas on lung CT

PURPOSE

Distinguishing between benign granulmoas and adenocarcinomas is confounded by their similar visual appearance on routine CT scans. Unfortunately, owing to the inability to discriminate these lesions radigraphically, many patients with benign granulomas are subjected to unnecessary surgical wedge resections and biopsies for pathologic confirmation of cancer presence or absence. This suggests the need for improved computerized characterization of these nodules in order to distinguish between these two classes of lesions on CT scans. While there has been substantial interest in the use of textural analysis for radiomic characterization of lung nodules, relatively less work has been done in shape based characterization of lung nodules, particularly with respect to granulmoas and adenocarcinomas. The primary goal of this study is to evaluate the role of 3D shape features for discrimination of benign granulomas from malignant adenocarcinomas on lung CT images. Towards this end we present an integrated framework for segmentation, feature characterization and classification of these nodules on CT.

METHODS

The nodule segmentation method starts with separation of lung regions from the surrounding lung anatomy. Next, the lung CT scans are projected into and represented in a three dimensional spectral embedding (SE) space, allowing for better determination of the boundaries of the nodule. This then enables the application of a gradient vector flow active contour (SEGvAC) model for nodule boundary extraction. A set of 24 shape features from both 2D slices and 3D surface of the segmented nodules are extracted, including features pertaining to the angularity, spiculation, elongation and nodule compactness. A feature selection scheme, PCA-VIP, is employed to identify the most discriminating set of features to distinguish granulmoas from adenocarcinomas within a learning set of 82 patients. The features thus identified were then combined with a support vector machine classifier and independently validated on a distinct test set comprising 67 patients. The performance of the classifier for both of the training and validation cohorts was evaluated by the area under receiver characteristic curve (ROC).

RESULTS

We used 82 and 67 studies from two different institutions respectively for training and independent validation of the model and the shape features. The Dice coefficient between automatically segmented nodules by SEGvAC and the manual delineations by expert radiologists (readers) was 0.84± 0.04 whereas inter-reader segmentation agreement was 0.79± 0.12. We also identified a set of consistent features (Roughness, Convexity and Spherecity) that were found to be strongly correlated across both manual and automated nodule segmentations (R > 0.80, p < 0.0001) and capture the marginal smoothness and 3D compactness of the nodules. On the independent validation set of 67 studies our classifier yielded a ROC AUC of 0.72 and 0.64 for manually- and automatically segmented nodules respectively. On a subset of 20 studies, the AUCs for the two expert radiologists and 1 pulmonologist were found to be 0.82, 0.68 and 0.58 respectively.

CONCLUSIONS

The major finding of this study was that certain shape features appear to differentially express between granulomas and adenocarcinomas and thus computer extracted shape cues could be used to distinguish these radiographically similar pathologies.

Changes in computer extracted features of vessel tortuosity on CT scans post-treatment in responders compared to non-responders for non-small cell lung cancer on immunotherapy

11518

Background: Immune-checkpoint blockade treatments demonstrate promising clinical efficacy in patients with non-small cell lung cancer (NSCLC). Nivolumab is a PD-1 inhibitor that is FDA approved for treatment of patients with chemotherapy refractory advanced NSCLC. The current standard clinical approach to evaluating tumor response is sub-optimal in defining clinical benefit from immunotherapy drugs. We sought to evaluate whether computer extracted measurements of vessel tortuosity significantly and differentially change post treatment between NSCLC patients who do and do not respond to immunotherapy. Methods: A total of 50 NSCLC patients including pre- and post- treatment CT scans were included in this study. The patients were either responders or non-responders to Nivolumab. Patients who did not receive Nivolumab after 2 cycles due to lack of response or progression as per RECIST were classified as ‘non-responders’. A total of 35 tortuosity features of the vessels around the lung nodules were investigated. In the training cohort (N = 25), the features were ranked based on the degree of change between pre- and post- treatment CT. The top 4 features were used for training a Support Vector Machine (SVM) classifier to identify which patients did and did not respond to immunotherapy on a validation cohort of N = 25 patients. Results: The top features identified were the ones associated with the curvature of the vessel branches. The AUC for the SVM classifier was 0.75 for the training and 0.79 for the test set. Conclusions: Changes in specific vessel tortuosity features between baseline and post-treatment CT scans following nivolumab were different between NSCLC patients who did and did not respond. Multi-site validation of the vessel tortuosity features is needed to establish it as a predictive biomarker for NSCLC patients treated with immunotherapy.

Computer extracted measurements of vessel tortuosity on baseline CT scans to predict response to nivolumab immunotherapy for non-small cell lung cancer

11566

Background: Immune-checkpoint blockade treatments, particularly drugs targeting the programmed death-1 (PD-1) receptor, demonstrate promising clinical efficacy in patients with non-small cell lung cancer (NSCLC). We sought to evaluate whether computer extracted measurements of tortuosity of vessels in lung nodules on baseline CT scans in NSCLC patients(pts) treated with a PD-1 inhibitor, nivolumab could distinguish responders and non-responders. Methods: A total of 61 NSCLC pts who underwent treatment with nivolumab were included in this study. Pts who did not receive nivolumab after 2 cycles due to lack of response or progression per RECIST were classified as ‘non-responders’, patients who had radiological response per RECIST or had clinical benefit (defined as stable disease >10 cycles) were classified as ‘responders’. A total of 35 quantitative tortuosity features of the vessels associated with lung nodule were investigated. In the training cohort (N=33), the features were ranked in their ability to identify responders to nivolumab using a support vector machine (SVM) classifier. The three most informative features were then used for training the SVM, which was then validated on a cohort of N=28 pts. Results: The maximum curvature ( f1), standard deviation of the torsion ( f2) and mean curvature ( f3) were identified as the most discriminating features. The area under Receiver operating characteristic (ROC) curve (AUC) of the SVM was 0.84 for the training and 0.72 for the validation cohort. Conclusions: Vessel tortuosity features were able to distinguish responders from non-responders for patients with NSCLC treated with nivolumab. Large scale multi-site validation will need to be done to establish vessel tortuosity as a predictive biomarker for immunotherapy. [Table: see text]