VertXNet: an ensemble method for vertebral body segmentation and identification from cervical and lumbar spinal X-rays.

Accurate annotation of vertebral bodies is crucial for automating the analysis of spinal X-ray images. However, manual annotation of these structures is a laborious and costly process due to their complex nature, including small sizes and varying shapes. To address this challenge and expedite the annotation process, we propose an ensemble pipeline called VertXNet. This pipeline currently combines two segmentation mechanisms, semantic segmentation using U-Net, and instance segmentation using Mask R-CNN, to automatically segment and label vertebral bodies in lateral cervical and lumbar spinal X-ray images. VertXNet enhances its effectiveness by adopting a rule-based strategy (termed the ensemble rule) for effectively combining segmentation outcomes from U-Net and Mask R-CNN. It determines vertebral body labels by recognizing specific reference vertebral instances, such as cervical vertebra 2 ('C2') in cervical spine X-rays and sacral vertebra 1 ('S1') in lumbar spine X-rays. Those references are commonly relatively easy to identify at the edge of the spine. To assess the performance of our proposed pipeline, we conducted evaluations on three spinal X-ray datasets, including two in-house datasets and one publicly available dataset. The ground truth annotations were provided by radiologists for comparison. Our experimental results have shown that the proposed pipeline outperformed two state-of-the-art (SOTA) segmentation models on our test dataset with a mean Dice of 0.90, vs. a mean Dice of 0.73 for Mask R-CNN and 0.72 for U-Net. We also demonstrated that VertXNet is a modular pipeline that enables using other SOTA model, like nnU-Net to further improve its performance. Furthermore, to evaluate the generalization ability of VertXNet on spinal X-rays, we directly tested the pre-trained pipeline on two additional datasets. A consistently strong performance was observed, with mean Dice coefficients of 0.89 and 0.88, respectively. In summary, VertXNet demonstrated significantly improved performance in vertebral body segmentation and labeling for spinal X-ray imaging. Its robustness and generalization were presented through the evaluation of both in-house clinical trial data and publicly available datasets.

Methodology for Good Machine Learning with Multi-Omics Data.

In 2020, Novartis Pharmaceuticals Corporation and the U.S. Food and Drug Administration (FDA) started a 4-year scientific collaboration to approach complex new data modalities and advanced analytics. The scientific question was to find novel radio-genomics-based prognostic and predictive factors for HR+/HER- metastatic breast cancer under a Research Collaboration Agreement. This collaboration has been providing valuable insights to help successfully implement future scientific projects, particularly using artificial intelligence and machine learning. This tutorial aims to provide tangible guidelines for a multi-omics project that includes multidisciplinary expert teams, spanning across different institutions. We cover key ideas, such as "maintaining effective communication" and "following good data science practices," followed by the four steps of exploratory projects, namely (1) plan, (2) design, (3) develop, and (4) disseminate. We break each step into smaller concepts with strategies for implementation and provide illustrations from our collaboration to further give the readers actionable guidance.

A deep learning approach to private data sharing of medical images using conditional generative adversarial networks (GANs).

Clinical data sharing can facilitate data-driven scientific research, allowing a broader range of questions to be addressed and thereby leading to greater understanding and innovation. However, sharing biomedical data can put sensitive personal information at risk. This is usually addressed by data anonymization, which is a slow and expensive process. An alternative to anonymization is construction of a synthetic dataset that behaves similar to the real clinical data but preserves patient privacy. As part of a collaboration between Novartis and the Oxford Big Data Institute, a synthetic dataset was generated based on images from COSENTYX® (secukinumab) ankylosing spondylitis (AS) clinical studies. An auxiliary classifier Generative Adversarial Network (ac-GAN) was trained to generate synthetic magnetic resonance images (MRIs) of vertebral units (VUs), conditioned on the VU location (cervical, thoracic and lumbar). Here, we present a method for generating a synthetic dataset and conduct an in-depth analysis on its properties along three key metrics: image fidelity, sample diversity and dataset privacy.

The impact of quantitative CT-based tumor volumetric features on the outcomes of patients with limited stage small cell lung cancer.

INTRODUCTION: Limited stage small cell lung cancer (LS-SCLC) has a poor prognosis. Additional prognostic markers are needed for risk-stratification and treatment intensification. This study compares quantitative CT-based volumetric tumor measurements versus International Association for the Study of Lung Cancer (IASLC) TNM staging to predict outcomes. MATERIALS & METHODS: A cohort of 105 patients diagnosed with LS-SCLC and treated with chemoradiation (CRT) from 2000 to 2013 were analyzed retrospectively. Patients were staged by the Union for International Cancer Control (UICC) TNM Classification, 8th edition. Tumor volumes and diameters were extracted from radiation planning CT imaging. Univariable and multivariable models were used to analyze relationships between CT features and overall survival (OS), locoregional recurrence (LRR), in-field LRR, any progression, and distant metastasis (DM). RESULTS: Median follow-up was 21.3 months. Two-year outcomes were as follows: 38% LRR, 31% in-field LRR, 52% DM, 62% any progression, and 47% OS (median survival 16.5 months). On univariable analysis, UICC T-stage and N-stage were not associated with any clinical outcome. UICC overall stage was only statistically associated with in-field LRR. One imaging feature (3D maximum tumor diameter) was found to be significantly associated with LRR (HR 1.10, p = 0.003), in-field LRR (HR 1.10, p = 0.007), DM (HR 1.10, p = 0.02), any progression (HR 1.10, p = 0.008), and OS (HR 1.10, p = 0.03). On multivariable analysis, this feature remained significantly associated with all outcomes. CONCLUSION: For LS-SCLC, quantitative CT-based volumetric tumor measurements were significantly associated with outcomes after CRT and may be better predictors of outcome than TNM stage.

Antibody-targeting of ultra-small nanoparticles enhances imaging sensitivity and enables longitudinal tracking of multiple myeloma.

Monitoring malignant progression and disease recurrence post-therapy are central challenges to improving the outcomes of patients with multiple myeloma (MM). Whereas current detection methods that rely upon bone marrow examination allow for precise monitoring of minimal residual disease and can help to elucidate clonal evolution, they do not take into account the spatial heterogeneity of the tumor microenvironment. As such, they are uninformative as to the localization of malignant plasma cells and may lead to false negative results. With respect to the latter challenge, clinically-available imaging agents are neither sufficiently sensitive nor specific enough to detect minute plasma cell populations. Here, we sought to explore methods by which to improve detection of MM cells within their natural bone marrow environment, using whole-animal magnetic resonance imaging to longitudinally monitor early-stage disease as well as to enhance tumor detection after systemic therapy. We conducted a proof-of-concept study to demonstrate that ultra-small (<5 nm) gadolinium-containing nanoparticles bound to full-length antibodies against the B-cell maturation antigen (BCMA) exhibit rapid tumor uptake followed by renal clearance, improving the signal-to-noise ratio for MM detection beyond levels that are currently afforded by other FDA-approved clinical imaging modalities. We anticipate that when combined with bone marrow or blood biopsy, such imaging constructs could help to augment the effective management of patients with MM.

Deep Learning Predicts Lung Cancer Treatment Response from Serial Medical Imaging.

PURPOSE: Tumors are continuously evolving biological systems, and medical imaging is uniquely positioned to monitor changes throughout treatment. Although qualitatively tracking lesions over space and time may be trivial, the development of clinically relevant, automated radiomics methods that incorporate serial imaging data is far more challenging. In this study, we evaluated deep learning networks for predicting clinical outcomes through analyzing time series CT images of patients with locally advanced non-small cell lung cancer (NSCLC).Experimental Design: Dataset A consists of 179 patients with stage III NSCLC treated with definitive chemoradiation, with pretreatment and posttreatment CT images at 1, 3, and 6 months follow-up (581 scans). Models were developed using transfer learning of convolutional neural networks (CNN) with recurrent neural networks (RNN), using single seed-point tumor localization. Pathologic response validation was performed on dataset B, comprising 89 patients with NSCLC treated with chemoradiation and surgery (178 scans). RESULTS: Deep learning models using time series scans were significantly predictive of survival and cancer-specific outcomes (progression, distant metastases, and local-regional recurrence). Model performance was enhanced with each additional follow-up scan into the CNN model (e.g., 2-year overall survival: AUC = 0.74, P < 0.05). The models stratified patients into low and high mortality risk groups, which were significantly associated with overall survival [HR = 6.16; 95% confidence interval (CI), 2.17-17.44; P < 0.001]. The model also significantly predicted pathologic response in dataset B (P = 0.016). CONCLUSIONS: We demonstrate that deep learning can integrate imaging scans at multiple timepoints to improve clinical outcome predictions. AI-based noninvasive radiomics biomarkers can have a significant impact in the clinic given their low cost and minimal requirements for human input.

Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study.

BACKGROUND: Non-small-cell lung cancer (NSCLC) patients often demonstrate varying clinical courses and outcomes, even within the same tumor stage. This study explores deep learning applications in medical imaging allowing for the automated quantification of radiographic characteristics and potentially improving patient stratification. METHODS AND FINDINGS: We performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median = 68.3 years [range 32.5-93.3], survival median = 1.7 years [range 0.0-11.7]). Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n = 771, age median = 68.0 years [range 32.5-93.3], survival median = 1.3 years [range 0.0-11.7]). We then employed a transfer learning approach to achieve the same for surgery patients (n = 391, age median = 69.1 years [range 37.2-88.0], survival median = 3.1 years [range 0.0-8.8]). We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] = 0.70 [95% CI 0.63-0.78], p < 0.001) and surgery (AUC = 0.71 [95% CI 0.60-0.82], p < 0.001) patients. The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p < 0.001) and surgery (p = 0.03) datasets. Additionally, the CNN was found to significantly outperform random forest models built on clinical parameters-including age, sex, and tumor node metastasis stage-as well as demonstrate high robustness against test-retest (intraclass correlation coefficient = 0.91) and inter-reader (Spearman's rank-order correlation = 0.88) variations. To gain a better understanding of the characteristics captured by the CNN, we identified regions with the most contribution towards predictions and highlighted the importance of tumor-surrounding tissue in patient stratification. We also present preliminary findings on the biological basis of the captured phenotypes as being linked to cell cycle and transcriptional processes. Limitations include the retrospective nature of this study as well as the opaque black box nature of deep learning networks. CONCLUSIONS: Our results provide evidence that deep learning networks may be used for mortality risk stratification based on standard-of-care CT images from NSCLC patients. This evidence motivates future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data.

Peritumoral radiomics features predict distant metastasis in locally advanced NSCLC.

PURPOSE: Radiomics provides quantitative tissue heterogeneity profiling and is an exciting approach to developing imaging biomarkers in the context of precision medicine. Normal-appearing parenchymal tissues surrounding primary tumors can harbor microscopic disease that leads to increased risk of distant metastasis (DM). This study assesses whether computed-tomography (CT) imaging features of such peritumoral tissues can predict DM in locally advanced non-small cell lung cancer (NSCLC). MATERIAL AND METHODS: 200 NSCLC patients of histological adenocarcinoma were included in this study. The investigated lung tissues were tumor rim, defined to be 3mm of tumor and parenchymal tissue on either side of the tumor border and the exterior region extended from 3 to 9mm outside of the tumor. Fifteen stable radiomic features were extracted and evaluated from each of these regions on pre-treatment CT images. For comparison, features from expert-delineated tumor contours were similarly prepared. The patient cohort was separated into training and validation datasets for prognostic power evaluation. Both univariable and multivariable analyses were performed for each region using concordance index (CI). RESULTS: Univariable analysis reveals that six out of fifteen tumor rim features were significantly prognostic of DM (p-value < 0.05), as were ten features from the visible tumor, and only one of the exterior features was. Multivariablely, a rim radiomic signature achieved the highest prognostic performance in the independent validation sub-cohort (CI = 0.64, p-value = 2.4×10-5) significantly over a multivariable clinical model (CI = 0.53), a visible tumor radiomics model (CI = 0.59), or an exterior tissue model (CI = 0.55). Furthermore, patient stratification by the combined rim signature and clinical predictor led to a significant improvement on the clinical predictor alone and also outperformed stratification using the combined tumor signature and clinical predictor. CONCLUSIONS: We identified peritumoral rim radiomic features significantly associated with DM. This study demonstrated that peritumoral imaging characteristics may provide additional valuable information over the visible tumor features for patient risk stratification due to cancer metastasis.

Radiographic prediction of meningioma grade by semantic and radiomic features.

OBJECTIVES: The clinical management of meningioma is guided by tumor grade and biological behavior. Currently, the assessment of tumor grade follows surgical resection and histopathologic review. Reliable techniques for pre-operative determination of tumor grade may enhance clinical decision-making. METHODS: A total of 175 meningioma patients (103 low-grade and 72 high-grade) with pre-operative contrast-enhanced T1-MRI were included. Fifteen radiomic (quantitative) and 10 semantic (qualitative) features were applied to quantify the imaging phenotype. Area under the curve (AUC) and odd ratios (OR) were computed with multiple-hypothesis correction. Random-forest classifiers were developed and validated on an independent dataset (n = 44). RESULTS: Twelve radiographic features (eight radiomic and four semantic) were significantly associated with meningioma grade. High-grade tumors exhibited necrosis/hemorrhage (ORsem = 6.6, AUCrad = 0.62-0.68), intratumoral heterogeneity (ORsem = 7.9, AUCrad = 0.65), non-spherical shape (AUCrad = 0.61), and larger volumes (AUCrad = 0.69) compared to low-grade tumors. Radiomic and sematic classifiers could significantly predict meningioma grade (AUCsem = 0.76 and AUCrad = 0.78). Furthermore, combining them increased the classification power (AUCradio = 0.86). Clinical variables alone did not effectively predict tumor grade (AUCclin = 0.65) or show complementary value with imaging data (AUCcomb = 0.84). CONCLUSIONS: We found a strong association between imaging features of meningioma and histopathologic grade, with ready application to clinical management. Combining qualitative and quantitative radiographic features significantly improved classification power.

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer.

Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR+ and EGFR- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR+ and KRAS+ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS+/KRAS- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost. Cancer Res; 77(14); 3922-30. ©2017 AACR.

Lymph node volume predicts survival but not nodal clearance in Stage IIIA-IIIB NSCLC.

BACKGROUND: Locally advanced non-small cell lung cancer (LA-NSCLC) patients have poorer survival and local control with mediastinal node (N2) tumor involvement at resection. Earlier assessment of nodal burden could inform clinical decision-making prior to surgery. This study evaluated the association between clinical outcomes and lymph node volume before and after neoadjuvant therapy. MATERIALS AND METHODS: CT imaging of patients with operable LA-NSCLC treated with chemoradiation and surgical resection was assessed. Clinically involved lymph node stations were identified by FDG-PET or mediastinoscopy. Locoregional recurrence (LRR), distant metastasis (DM), progression free survival (PFS) and overall survival (OS) were analyzed by the Kaplan Meier method, concordance index and Cox regression. RESULTS: 73 patients with Stage IIIA-IIIB NSCLC treated with neoadjuvant chemoradiation and surgical resection were identified. The median RT dose was 54 Gy and all patients received concurrent chemotherapy. Involved lymph node volume was significantly associated with LRR and OS but not DM on univariate analysis. Additionally, lymph node volume greater than 10.6 cm3 after the completion of preoperative chemoradiation was associated with increased LRR (p<0.001) and decreased OS (p = 0.04). There was no association between nodal volumes and nodal clearance. CONCLUSION: For patients with LA-NSCLC, large volume nodal disease post-chemoradiation is associated with increased risk of locoregional recurrence and decreased survival. Nodal volume can thus be used to further stratify patients within the heterogeneous Stage IIIA-IIIB population and potentially guide clinical decision-making.

Associations of Radiomic Data Extracted from Static and Respiratory-Gated CT Scans with Disease Recurrence in Lung Cancer Patients Treated with SBRT.

Radiomics aims to quantitatively capture the complex tumor phenotype contained in medical images to associate them with clinical outcomes. This study investigates the impact of different types of computed tomography (CT) images on the prognostic performance of radiomic features for disease recurrence in early stage non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiation therapy (SBRT). 112 early stage NSCLC patients treated with SBRT that had static free breathing (FB) and average intensity projection (AIP) images were analyzed. Nineteen radiomic features were selected from each image type (FB or AIP) for analysis based on stability and variance. The selected FB and AIP radiomic feature sets had 6 common radiomic features between both image types and 13 unique features. The prognostic performances of the features for distant metastasis (DM) and locoregional recurrence (LRR) were evaluated using the concordance index (CI) and compared with two conventional features (tumor volume and maximum diameter). P-values were corrected for multiple testing using the false discovery rate procedure. None of the FB radiomic features were associated with DM, however, seven AIP radiomic features, that described tumor shape and heterogeneity, were (CI range: 0.638-0.676). Conventional features from FB images were not associated with DM, however, AIP conventional features were (CI range: 0.643-0.658). Radiomic and conventional multivariate models were compared between FB and AIP images using cross validation. The differences between the models were assessed using a permutation test. AIP radiomic multivariate models (median CI = 0.667) outperformed all other models (median CI range: 0.601-0.630) in predicting DM. None of the imaging features were prognostic of LRR. Therefore, image type impacts the performance of radiomic models in their association with disease recurrence. AIP images contained more information than FB images that were associated with disease recurrence in early stage NSCLC patients treated with SBRT, which suggests that AIP images may potentially be more optimal for the development of an imaging biomarker.

Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC.

INTRODUCTION: Noninvasive biomarkers that capture the total tumor burden could provide important complementary information for precision medicine to aid clinical decision making. We investigated the value of radiomic data extracted from pretreatment computed tomography images of the primary tumor and lymph nodes in predicting pathological response after neoadjuvant chemoradiation before surgery. METHODS: A total of 85 patients with resectable locally advanced (stage II-III) NSCLC (median age 60.3 years, 65% female) treated from 2003 to 2013 were included in this institutional review board-approved study. Radiomics analysis was performed on 85 primary tumors and 178 lymph nodes to discriminate between pathological complete response (pCR) and gross residual disease (GRD). Twenty nonredundant and stable features (10 from each site) were evaluated by using the area under the curve (AUC) (all p values were corrected for multiple hypothesis testing). Classification performance of each feature set was evaluated by random forest and nested cross validation. RESULTS: Three radiomic features (describing primary tumor sphericity and lymph node homogeneity) were significantly predictive of pCR with similar performances (all AUC = 0.67, p < 0.05). Two features (quantifying lymph node homogeneity) were predictive of GRD (AUC range 0.72-0.75, p < 0.05) and performed significantly better than the primary features (AUC = 0.62). Multivariate analysis showed that for pCR, the radiomic features set alone had the best-performing classification (median AUC = 0.68). Furthermore, for GRD classification, the combination of radiomic and clinical data significantly outperformed all other feature sets (median AUC = 0.73). CONCLUSION: Lymph node phenotypic information was significantly predictive for pathological response and showed higher classification performance than radiomic features obtained from the primary tumor.

Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non-Small Cell Lung Cancer.

PET-based radiomics have been used to noninvasively quantify the metabolic tumor phenotypes; however, little is known about the relationship between these phenotypes and underlying somatic mutations. This study assessed the association and predictive power of 18F-FDG PET-based radiomic features for somatic mutations in non-small cell lung cancer patients. Methods: Three hundred forty-eight non-small cell lung cancer patients underwent diagnostic 18F-FDG PET scans and were tested for genetic mutations. Thirteen percent (44/348) and 28% (96/348) of patients were found to harbor epidermal growth factor receptor (EGFR) or Kristen rat sarcoma viral (KRAS) mutations, respectively. We evaluated 21 imaging features: 19 independent radiomic features quantifying phenotypic traits and 2 conventional features (metabolic tumor volume and maximum SUV). The association between imaging features and mutation status (e.g., EGFR-positive [EGFR+] vs. EGFR-negative) was assessed using the Wilcoxon rank-sum test. The ability of each imaging feature to predict mutation status was evaluated by the area under the receiver operating curve (AUC) and its significance was compared with a random guess (AUC = 0.5) using the Noether test. All P values were corrected for multiple hypothesis testing by controlling the false-discovery rate (FDRWilcoxon, FDRNoether) with a significance threshold of 10%. Results: Eight radiomic features and both conventional features were significantly associated with EGFR mutation status (FDRWilcoxon = 0.01-0.10). One radiomic feature (normalized inverse difference moment) outperformed all other features in predicting EGFR mutation status (EGFR+ vs. EGFR-negative, AUC = 0.67, FDRNoether = 0.0032), as well as differentiating between KRAS-positive and EGFR+ (AUC = 0.65, FDRNoether = 0.05). None of the features was associated with or predictive of KRAS mutation status (KRAS-positive vs. KRAS-negative, AUC = 0.50-0.54). Conclusion: Our results indicate that EGFR mutations may drive different metabolic tumor phenotypes that are captured in PET images, whereas KRAS-mutated tumors do not. This proof-of-concept study sheds light on genotype-phenotype interactions, using radiomics to capture and describe the phenotype, and may have potential for developing noninvasive imaging biomarkers for somatic mutations.

Radiologic-pathologic correlation of response to chemoradiation in resectable locally advanced NSCLC.

OBJECTIVES: Accurate assessment of tumor response to chemoradiation has the potential to guide clinical decision-making regarding surgical resection and/or dose escalation for patients. Early assessment has implications for Optimal local therapy for operable locally advanced non-small cell lung cancer (LA-NSCLC) is controversial. This study evaluated quantitative CT-based tumor measurements to predict pathologic response. MATERIALS AND METHODS: Patients with operable LA-NSCLC treated with chemoradiation followed by surgical resection were assessed. Tumor diameter and volume were quantified from CT imaging obtained prior to chemoradiation and post-chemoradiation prior to surgical resection. Univariate and multivariate logistic regression were used to determine association with the primary endpoint of pathologic complete response (pCR). Overall survival, locoregional recurrence, and distant metastasis were assessed as secondary endpoints. RESULTS: 101 LA-NSCLC patients were identified and treated with preoperative chemoradiation and surgical resection. The median RT dose was 54Gy (range, 46-70) and 98% of patients received concurrent chemoradiation as part of their preoperative treatment. Reduction of CT-defined tumor volume was associated with pCR (OR 1.06 [1.02-1.09], p=0.002) and LRR (HR 1.01 [1.00-1.02], p=0.048). Conventional response assessment determined by RECIST (p=0.213) was not associated with pCR or any secondary endpoints. CONCLUSION: CT-measured reductions in tumor volume after chemoradiation are associated with pCR and provide greater clinical information about tumor response than conventional response assessment (RECIST) or absolute tumor sizes or volumes. This study demonstrates that change in tumor volumes provides better radiologic-pathologic correlation and is thus an additional tool to assess tumor response following chemoradiation.

CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer.

BACKGROUND: Radiomics uses a large number of quantitative imaging features that describe the tumor phenotype to develop imaging biomarkers for clinical outcomes. Radiomic analysis of pre-treatment computed-tomography (CT) scans was investigated to identify imaging predictors of clinical outcomes in early stage non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiation therapy (SBRT). MATERIALS AND METHODS: CT images of 113 stage I-II NSCLC patients treated with SBRT were analyzed. Twelve radiomic features were selected based on stability and variance. The association of features with clinical outcomes and their prognostic value (using the concordance index (CI)) was evaluated. Radiomic features were compared with conventional imaging metrics (tumor volume and diameter) and clinical parameters. RESULTS: Overall survival was associated with two conventional features (volume and diameter) and two radiomic features (LoG 3D run low gray level short run emphasis and stats median). One radiomic feature (Wavelet LLH stats range) was significantly prognostic for distant metastasis (CI=0.67, q-value<0.1), while none of the conventional and clinical parameters were. Three conventional and four radiomic features were prognostic for overall survival. CONCLUSION: This exploratory analysis demonstrates that radiomic features have potential to be prognostic for some outcomes that conventional imaging metrics cannot predict in SBRT patients.

Radiomic phenotype features predict pathological response in non-small cell lung cancer.

BACKGROUND AND PURPOSE: Radiomics can quantify tumor phenotype characteristics non-invasively by applying advanced imaging feature algorithms. In this study we assessed if pre-treatment radiomics data are able to predict pathological response after neoadjuvant chemoradiation in patients with locally advanced non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: 127 NSCLC patients were included in this study. Fifteen radiomic features selected based on stability and variance were evaluated for its power to predict pathological response. Predictive power was evaluated using area under the curve (AUC). Conventional imaging features (tumor volume and diameter) were used for comparison. RESULTS: Seven features were predictive for pathologic gross residual disease (AUC>0.6, p-value<0.05), and one for pathologic complete response (AUC=0.63, p-value=0.01). No conventional imaging features were predictive (range AUC=0.51-0.59, p-value>0.05). Tumors that did not respond well to neoadjuvant chemoradiation were more likely to present a rounder shape (spherical disproportionality, AUC=0.63, p-value=0.009) and heterogeneous texture (LoG 5mm 3D - GLCM entropy, AUC=0.61, p-value=0.03). CONCLUSION: We identified predictive radiomic features for pathological response, although no conventional features were significantly predictive. This study demonstrates that radiomics can provide valuable clinical information, and performed better than conventional imaging features.

Relationship between the Temporal Changes in Positron-Emission-Tomography-Imaging-Based Textural Features and Pathologic Response and Survival in Esophageal Cancer Patients.

PURPOSE: Although change in standardized uptake value (SUV) measures and PET-based textural features during treatment have shown promise in tumor response prediction, it is unclear which quantitative measure is the most predictive. We compared the relationship between PET-based features and pathologic response and overall survival with the SUV measures in esophageal cancer. METHODS: Fifty-four esophageal cancer patients received PET/CT scans before and after chemoradiotherapy. Of these, 45 patients underwent surgery and were classified into complete, partial, and non-responders to the preoperative chemoradiation. SUVmax and SUVmean, two cooccurrence matrix (Entropy and Homogeneity), two run-length matrix (RLM) (high-gray-run emphasis and Short-run high-gray-run emphasis), and two size-zone matrix (high-gray-zone emphasis and short-zone high-gray emphasis) textures were computed. The relationship between the relative difference of each measure at different treatment time points and the pathologic response and overall survival was assessed using the area under the receiver-operating-characteristic curve (AUC) and Kaplan-Meier statistics, respectively. RESULTS: All Textures, except Homogeneity, were better related to pathologic response than SUVmax and SUVmean. Entropy was found to significantly distinguish non-responders from the complete (AUC = 0.79, p = 1.7 × 10(-4)) and partial (AUC = 0.71, p = 0.01) responders. Non-responders can also be significantly differentiated from partial and complete responders by the change in the run-length and size-zone matrix textures (AUC = 0.71-0.76, p ≤ 0.02). Homogeneity, SUVmax, and SUVmean failed to differentiate between any of the responders (AUC = 0.50-0.57, p ≥ 0.46). However, none of the measures were found to significantly distinguish between complete and partial responders with AUC <0.60 (p = 0.37). Median Entropy and RLM textures significantly discriminated patients with good and poor survival (log-rank p < 0.02), while all other textures and survival were poorly related (log-rank p > 0.25). CONCLUSION: For the patients studied, temporal changes in Entropy and all RLM were better correlated with pathological response and survival than the SUV measures. The hypothesis that these metrics can be used as clinical predictors of better patient outcomes will be tested in a larger patient dataset in the future.

Use of registration-based contour propagation in texture analysis for esophageal cancer pathologic response prediction.

Change in PET-based textural features has shown promise in predicting cancer response to treatment. However, contouring tumour volumes on longitudinal scans is time-consuming. This study investigated the usefulness of contour propagation in texture analysis for the purpose of pathologic response prediction in esophageal cancer. Forty-five esophageal cancer patients underwent PET/CT scans before and after chemo-radiotherapy. Patients were classified into responders and non-responders after the surgery. Physician-defined tumour ROIs on pre-treatment PET were propagated onto the post-treatment PET using rigid and ten deformable registration algorithms. PET images were converted into 256 discrete values. Co-occurrence, run-length, and size zone matrix textures were computed within all ROIs. The relative difference of each texture at different treatment time-points was used to predict the pathologic responders. Their predictive value was assessed using the area under the receiver-operating-characteristic curve (AUC). Propagated ROIs from different algorithms were compared using Dice similarity index (DSI). Contours propagated by the fast-demons, fast-free-form and rigid algorithms did not fully capture the high FDG uptake regions of tumours. Fast-demons propagated ROIs had the least agreement with other contours (DSI = 58%). Moderate to substantial overlap were found in the ROIs propagated by all other algorithms (DSI = 69%-79%). Rigidly propagated ROIs with co-occurrence texture failed to significantly differentiate between responders and non-responders (AUC = 0.58, q-value = 0.33), while the differentiation was significant with other textures (AUC = 0.71-0.73, p < 0.009). Among the deformable algorithms, fast-demons (AUC = 0.68-0.70, q-value < 0.03) and fast-free-form (AUC = 0.69-0.74, q-value < 0.04) were the least predictive. ROIs propagated by all other deformable algorithms with any texture significantly predicted pathologic responders (AUC = 0.72-0.78, q-value < 0.01). Propagated ROIs using deformable registration for all textures can lead to accurate prediction of pathologic response, potentially expediting the temporal texture analysis process. However, fast-demons, fast-free-form, and rigid algorithms should be applied with care due to their inferior performance compared to other algorithms.

CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma.

BACKGROUND AND PURPOSE: Radiomics provides opportunities to quantify the tumor phenotype non-invasively by applying a large number of quantitative imaging features. This study evaluates computed-tomography (CT) radiomic features for their capability to predict distant metastasis (DM) for lung adenocarcinoma patients. MATERIAL AND METHODS: We included two datasets: 98 patients for discovery and 84 for validation. The phenotype of the primary tumor was quantified on pre-treatment CT-scans using 635 radiomic features. Univariate and multivariate analysis was performed to evaluate radiomics performance using the concordance index (CI). RESULTS: Thirty-five radiomic features were found to be prognostic (CI>0.60, FDR<5%) for DM and twelve for survival. It is noteworthy that tumor volume was only moderately prognostic for DM (CI=0.55, p-value=2.77×10(-5)) in the discovery cohort. A radiomic-signature had strong power for predicting DM in the independent validation dataset (CI=0.61, p-value=1.79×10(-17)). Adding this radiomic-signature to a clinical model resulted in a significant improvement of predicting DM in the validation dataset (p-value=1.56×10(-11)). CONCLUSIONS: Although only basic metrics are routinely quantified, this study shows that radiomic features capturing detailed information of the tumor phenotype can be used as a prognostic biomarker for clinically-relevant factors such as DM. Moreover, the radiomic-signature provided additional information to clinical data.