Toward radiomics for assessment of response to systemic therapies in lung cancer.

This editorial comment explains recent developments in radiomics regarding the use of quantitative imaging biomarkers to predict lung cancer sensitivity to a variety of cancer therapies. Tumor response assessment has been a crucial component guiding cancer treatment. Evaluation of treatment response was standardized and classically based on measuring changes in tumor lesion size. Recent breakthroughs in artificial intelligence pave the way for the use of radiomics in tumor response assessment. Such objective techniques would bring a remarkable transformation to conventional methods, which can be inherently subjective. Successful implementation of these technologies would allow for faster and more accurate predictions of treatment efficacy, which will be critical to the advancement of personalized medicine.

A Web-Based Response-Assessment System for Development and Validation of Imaging Biomarkers in Oncology.

Quantitative imaging biomarkers are increasingly used in oncology clinical trials to assist the evaluation of tumor responses to novel therapies. To identify these biomarkers and ensure smooth clinical translation once they have been validated, it is critical to develop a reliable workflow-efficient imaging platform for integration in clinical settings. Here we will present a web-based volumetric response-assessment system that we developed based on an open-source image viewing platform (WEASIS) and a DICOM image archive (DCM4CHEE). Our web-based response-assessment system offers a DICOM imaging archiving function, standard imaging viewing and manipulation functions, efficient tumor segmentation and quantification algorithms, and a reliable database containing tumor segmentation and measurement results. The prototype system is currently used in our research lab to foster the development and validation of new quantitative imaging biomarkers, including the volumetric computed tomography technique, as a more accurate and early assessment method of solid tumor responses to targeted and immunotherapies.

Implementation strategy of a CNN model affects the performance of CT assessment of EGFR mutation status in lung cancer patients.

OBJECTIVE: To compare CNN models implemented using different strategies in the CT assessment of EGFR mutation status in patients with lung adenocarcinoma. METHODS: 1,010 consecutive lung adenocarcinoma patients with known EGFR mutation status were randomly divided into a training set (n=810) and a testing set (n=200). CNN models were constructed based on ResNet-101 architecture but implemented using different strategies: dimension filters (2D/3D), input sizes (small/middle/large and their fusion), slicing methods (transverse plane only and arbitrary multi-view planes), and training approaches (from scratch and fine-tuning a pre-trained CNN). The performance of the CNN models was compared using AUC. RESULTS: The fusion approach yielded consistently better performance than other input sizes, although the effect often did not reach statistical significance. Multi-view slicing was significantly superior to the transverse method when fine-tuning a pre-trained 2D CNN but not a CNN trained from scratch. The 3D CNN was significantly better than the 2D transverse plane method but only marginally better than the multi-view slicing method when trained from scratch. The highest performance (AUC=0.838) was achieved for the fine-tuned 2D CNN model when built using the fusion input size and multi-view slicing method. CONCLUSION: The assessment of EGFR mutation status in patients is more accurate when CNN models use more spatial information and are fine-tuned by transfer learning. Our finding about implementation strategy of a CNN model could be a guidance to other medical 3D images applications. Compared with other published studies which used medical images to identify EGFR mutation status, our CNN model achieved the best performance in a biggest patient cohort.

Impact of Variability in Portal Venous Phase Acquisition Timing in Tumor Density Measurement and Treatment Response Assessment: Metastatic Colorectal Cancer as a Paradigm.

PURPOSE: New response patterns to anticancer drugs have led tumor size-based response criteria to shift to also include density measurements. Choi criteria, for instance, categorize antiangiogenic therapy response as a decrease in tumor density > 15% at the portal venous phase (PVP). We studied the effect that PVP timing has on measurement of the density of liver metastases (LM) from colorectal cancer (CRC). METHODS: Pretreatment PVP computed tomography images from 291 patients with LM-CRC from the CRYSTAL trial (Cetuximab Combined With Irinotecan in First-Line Therapy for Metastatic Colorectal Cancer; ClinicalTrials.gov identifier: NCT00154102) were included. Four radiologists independently scored the scans' timing according to a three-point scoring system: early, optimal, late PVP. Using this, we developed, by machine learning, a proprietary computer-aided quality-control algorithm to grade PVP timing. The reference standard was a computer-refined consensus. For each patient, we contoured target liver lesions and calculated their mean density. RESULTS: Contrast-product administration data were not recorded in the digital imaging and communications in medicine headers for injection volume (94%), type (93%), and route (76%). The PVP timing was early, optimal, and late in 52, 194, and 45 patients, respectively. The mean (95% CI) accuracy of the radiologists for detection of optimal PVP timing was 81.7% (78.3 to 85.2) and was outperformed by the 88.6% (84.8 to 92.4) computer accuracy. The mean ± standard deviation of LM-CRC density was 68 ± 15 Hounsfield units (HU) overall and 59.5 ± 14.9 HU, 71.4 ± 14.1 HU, 62.4 ± 12.5 HU at early, optimal, and late PVP timing, respectively. LM-CRC density was thus decreased at nonoptimal PVP timing by 14.8%: 16.7% at early PVP ( P < .001) and 12.6% at late PVP ( P < .001). CONCLUSION: Nonoptimal PVP timing should be identified because it significantly decreased tumor density by 14.8%. Our computer-aided quality-control system outperformed the accuracy, reproducibility, and speed of radiologists' visual scoring. PVP-timing scoring could improve the extraction of tumor quantitative imaging biomarkers and the monitoring of anticancer therapy efficacy at the patient and clinical trial levels.

Assessment of Imaging Modalities and Response Metrics in Ewing Sarcoma: Correlation With Survival.

PURPOSE: Despite the rapidly increasing use of [18F]fluorodeoxyglucose (FDG) -positron emission tomography (PET), the comparison of anatomic and functional imaging in the assessment of clinical outcomes has been lacking. In addition, there has not been a rigorous evaluation of how common radiologic criteria or the location of the radiology reader (local v central) compare in the ability to predict benefit. In this study, we aimed to compare the effectiveness of various radiologic response assessments for the prediction of overall survival (OS) within the same data set of patients with sarcoma. METHODS: We analyzed assessments made during a clinical trial of a novel IGF1R antibody in Ewing sarcoma: PET Response Criteria in Solid Tumors (PERCIST) for functional imaging and WHO criteria (performed locally and centrally), RECIST, and volumetric analysis for anatomic imaging. We compared the effectiveness of the various criteria for the prediction of progression and survival. RESULTS: For volume analysis, progression-defined as cumulative lesion volume increase of 100% at 6 weeks-was the optimal cutoff for decreased OS (P < .001). Assessment of the day-9 FDG-PET scan was associated with reduced OS in progressors compared with nonprogressors (P = .001) and with improved OS in responders compared with nonresponders. Significant variations in response (18% to 44%) and progression (9% to 50%) were observed between the different criteria. The comparison of central and local interpretation of anatomic imaging produced similar outcomes. PET was superior to anatomic imaging in identification of a response. Volume analysis identified the most responders among the anatomic imaging criteria. CONCLUSION: An early signal with FDG-PET on day 9 and volume analysis were the best predictors of benefit. Validation of the volumetric analysis is required.

A Response Assessment Platform for Development and Validation of Imaging Biomarkers in Oncology.

Quantitative imaging biomarkers are increasingly used in both oncology clinical trials and clinical practice aid evaluation of tumor response to novel therapies. To obtain these biomarkers, and to ensure smooth clinical adoption once they have been validated, it is critical to develop reliable computer-aided methods and a workflow-efficient imaging platform for integration in research and clinical settings. Here, we present a volumetric response assessment system developed based on an open-source image-viewing platform (WEASIS). Our response assessment system is designed using the Model-View-Controller concept, and it offers standard image-viewing and -manipulation functions, efficient tumor segmentation and quantification algorithms, and a reliable database containing tumor segmentation and measurement results. This prototype system is currently used in our research laboratory to foster the development and validation of new quantitative imaging biomarkers including the volumetric computed tomography technique as a more accurate and early assessment method of solid tumor response to targeted therapy and immunotherapy.

Harnessing technology to improve clinical trials: study of real-time informatics to collect data, toxicities, image response assessments, and patient-reported outcomes in a phase II clinical trial.

PURPOSE: In clinical trials, traditional monitoring methods, paper documentation, and outdated collection systems lead to inaccuracies of study information and inefficiencies in the process. Integrated electronic systems offer an opportunity to collect data in real time. PATIENTS AND METHODS: We created a computer software system to collect 13 patient-reported symptomatic adverse events and patient-reported Karnofsky performance status, semi-automated RECIST measurements, and laboratory data, and we made this information available to investigators in real time at the point of care during a phase II lung cancer trial. We assessed data completeness within 48 hours of each visit. Clinician satisfaction was measured. RESULTS: Forty-four patients were enrolled, for 721 total visits. At each visit, patient-reported outcomes (PROs) reflecting toxicity and disease-related symptoms were completed using a dedicated wireless laptop. All PROs were distributed in batch throughout the system within 24 hours of the visit, and abnormal laboratory data were available for review within a median of 6 hours from the time of sample collection. Manual attribution of laboratory toxicities took a median of 1 day from the time they were accessible online. Semi-automated RECIST measurements were available to clinicians online within a median of 2 days from the time of imaging. All clinicians and 88% of data managers felt there was greater accuracy using this system. CONCLUSION: Existing data management systems can be harnessed to enable real-time collection and review of clinical information during trials. This approach facilitates reporting of information closer to the time of events, and improves efficiency, and the ability to make earlier clinical decisions.

Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field.

PURPOSE: Lung lesions vary considerably in size, density, and shape, and can attach to surrounding anatomic structures such as chest wall or mediastinum. Automatic segmentation of the lesions poses a challenge. This work communicates a new three-dimensional algorithm for the segmentation of a wide variety of lesions, ranging from tumors found in patients with advanced lung cancer to small nodules detected in lung cancer screening programs. METHODS: The authors' algorithm uniquely combines the image processing techniques of marker-controlled watershed, geometric active contours as well as Markov random field (MRF). The user of the algorithm manually selects a region of interest encompassing the lesion on a single slice and then the watershed method generates an initial surface of the lesion in three dimensions, which is refined by the active geometric contours. MRF improves the segmentation of ground glass opacity portions of part-solid lesions. The algorithm was tested on an anthropomorphic thorax phantom dataset and two publicly accessible clinical lung datasets. These clinical studies included a same-day repeat CT (prewalk and postwalk scans were performed within 15 min) dataset containing 32 lung lesions with one radiologist's delineated contours, and the first release of the Lung Image Database Consortium (LIDC) dataset containing 23 lung nodules with 6 radiologists' delineated contours. The phantom dataset contained 22 phantom nodules of known volumes that were inserted in a phantom thorax. RESULTS: For the prewalk scans of the same-day repeat CT dataset and the LIDC dataset, the mean overlap ratios of lesion volumes generated by the computer algorithm and the radiologist(s) were 69% and 65%, respectively. For the two repeat CT scans, the intra-class correlation coefficient (ICC) was 0.998, indicating high reliability of the algorithm. The mean relative difference was -3% for the phantom dataset. CONCLUSIONS: The performance of this new segmentation algorithm in delineating tumor contour and measuring tumor size illustrates its potential clinical value for assisting in noninvasive diagnosis of pulmonary nodules, therapy response assessment, and radiation treatment planning.

Multiphasic contrast-enhanced MRI: single-slice versus volumetric quantification of tumor enhancement for the assessment of renal clear-cell carcinoma fuhrman grade.

PURPOSE: To assess the association between clear-cell carcinoma pathology grade at nephrectomy and magnetic resonance imaging (MRI) tumor enhancement. MATERIALS AND METHODS: The Institutional Review Board approved this retrospective study and waived the informed consent requirement. In all, 32 patients underwent multiphase contrast-enhanced MRI prior to nephrectomy. MRI tumor enhancement was measured using two approaches: 1) the most enhancing portion of the tumor on a single slice and 2) volumetric analysis of enhancement in the entire tumor. Associations between pathological grade, tumor size, and enhancement were evaluated using the Kruskal-Wallis test and generalized logistic regression models. RESULTS: No significant association between pathology grade and enhancement was found when measurements were made on a single slice. When measured in the entire tumor, significant associations were found between higher pathology grades and lower mean, median, top 10%, top 25%, and top 50% tumor enhancement (P < 0.001-0.002). On multivariate analysis the association between grade and enhancement remained significant (P = 0.041-0.043), but tumor size did not make an additional contribution beyond tumor enhancement alone in differentiating between tumor grades. CONCLUSION: There is significant association between tumor grade and enhancement, but only when measured in the entire tumor and not on the most enhancing portion on a single slice.

Assessment of therapy responses and prediction of survival in malignant pleural mesothelioma through computer-aided volumetric measurement on computed tomography scans.

PURPOSE: The purposes of this study were (1) to calculate the tumor volume in patients with malignant pleural mesothelioma using computed tomography (CT) scan images and a computer-aided measurement technique and (2) to investigate whether the baseline volume, or volume change after chemotherapy, predicts patient survival. METHODS: We compiled the clinical characteristics and outcome from 30 patients enrolled in two clinical trials at our cancer center in which the patients were treated with induction chemotherapy followed by surgery and radiation. CT scans of 30 patients were obtained at baseline and after two cycles of chemotherapy. Tumor volumes were calculated using a semiautomated computer algorithm. Overall survival was measured using a landmark time at 3 months post-treatment start date such that all patients had already received two cycles of chemotherapy and a follow-up scan. Association of volume changes with overall survival were determined by a Cox Proportional Hazards Model or log-rank test. The relationship between both pre and postoperative clinical stage and baseline tumor volume was analyzed using the rank sum test. RESULTS: The median baseline tumor volume was 473 cm(3) (range, 61 cm(3)-2108 cm(3)). Patients with high preoperative stages (III and IV) had larger baseline tumor volume than those with low preoperative stages (I and II) (p = 0.05). Patients with baseline volumes smaller than 619 cm(3) tended to survive longer than those with baseline volumes larger than or equal to 619 cm(3) (p = 0.07). Percentage change of tumor volume from baseline to first follow-up CT after two cycles of chemotherapy was significantly associated with overall survival (hazard ratio: 1.94 [95% confidence interval, 1.05-3.60], p = 0.04). Whereas the relative change in modified RECIST measurements was not significantly associated with overall survival (hazard ratio: 1.06 [95% confidence interval, 0.96-1.16], p = 0.25). By classifying changes of tumor volumes between two scans into two groups, i.e., "increase" and "decrease," a significant difference in survival was found between those who increased and decreased after two cycles of chemotherapy (p = 0.03). CONCLUSIONS: Changes in tumor volume after two cycles of chemotherapy predicted overall survival in patients with malignant pleural mesothelioma. Tumor volume at baseline was shown to be associated with preoperative clinical stage and survival. Computer-aided volumetric measurements may enable more reliable therapeutic response assessment and could provide additional prognostic information.

Computed tomography assessment of response to therapy: tumor volume change measurement, truth data, and error.

RATIONALE AND OBJECTIVES: This article describes issues and methods that are specific to the measurement of change in tumor volume as measured from computed tomographic (CT) images and how these would relate to the establishment of CT tumor volumetrics as a biomarker of patient response to therapy. The primary focus is on the measurement of lung tumors, but the approach should be generalizable to other anatomic regions. MATERIALS AND METHODS: The first issues addressed are the various sources of bias and variance in the measurement of tumor volumes, which are discussed in the context of measurement variation and its impact on the early detection of response to therapy. RESULTS AND RESOURCES: Research that seeks to identify the magnitude of some of these sources of error is ongoing, and several of these efforts are described herein. In addition, several resources for these investigations are being made available through the National Institutes of Health-funded Reference Image Database to Evaluate Response to therapy in cancer project, and these are described as well. Other measures derived from CT image data that might be predictive of patient response are described briefly, as well as the additional issues that each of these metrics may encounter in real-life applications. CONCLUSIONS: The article concludes with a brief discussion of moving from the assessment of measurement variation to the steps necessary to establish the efficacy of a metric as a biomarker for response.

Prospective assessment of discontinuation and reinitiation of erlotinib or gefitinib in patients with acquired resistance to erlotinib or gefitinib followed by the addition of everolimus.

PURPOSE: Ten percent of U.S. patients with non-small cell lung cancer experience partial radiographic responses to erlotinib or gefitinib. Despite initial regressions, these patients develop acquired resistance to erlotinib or gefitinib. In these patients, we sought to assess changes in tumor metabolism and size after stopping and restarting erlotinib or gefitinib and to determine the effect of adding everolimus. EXPERIMENTAL DESIGN: Patients with non-small cell lung cancer and acquired resistance to erlotinib or gefitinib were eligible. Patients had 18-fluoro-2-deoxy-d-glucose-positron emission tomography/computed tomography and computed tomography scans at baseline, 3 weeks after stopping erlotinib or gefitinib, and 3 weeks after restarting erlotinib or gefitinib. Three weeks after restarting erlotinib or gefitinib, everolimus was added to treatment. RESULTS: Ten patients completed all four planned studies. Three weeks after stopping erlotinib or gefitinib, there was a median 18% increase in SUV(max) and 9% increase in tumor diameter. Three weeks after restarting erlotinib or gefitinib, there was a median 4% decrease in SUV(max) and 1% decrease in tumor diameter. No partial responses (0 of 10; 95% confidence interval, 0-31%) were seen with the addition of everolimus to erlotinib or gefitinib. CONCLUSIONS: In patients who develop acquired resistance, stopping erlotinib or gefitinib results in symptomatic progression, increase in SUV(max), and increase in tumor size. Symptoms improve and SUV(max) decreases after restarting erlotinib or gefitinib, suggesting that some tumor cells remain sensitive to epidermal growth factor receptor blockade. No responses were observed with combined everolimus and erlotinib or gefitinib. We recommend a randomized trial to assess the value of continuing erlotinib or gefitinib after development of acquired resistance.