Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer.

Published on Apr 18, 2017in Scientific Reports3.998
· DOI :10.1038/SREP46349
Yucheng Zhang4
Estimated H-index: 4
(Sunnybrook Research Institute),
Anastasia Oikonomou24
Estimated H-index: 24
(Sunnybrook Research Institute)
+ 2 AuthorsFarzad Khalvati20
Estimated H-index: 20
(Sunnybrook Research Institute)
Sources
Abstract
Radiomics characterizes tumor phenotypes by extracting large numbers of quantitative features from radiological images. Radiomic features have been shown to provide prognostic value in predicting clinical outcomes in several studies. However, several challenges including feature redundancy, unbalanced data, and small sample sizes have led to relatively low predictive accuracy. In this study, we explore different strategies for overcoming these challenges and improving predictive performance of radiomics-based prognosis for non-small cell lung cancer (NSCLC). CT images of 112 patients (mean age 75 years) with NSCLC who underwent stereotactic body radiotherapy were used to predict recurrence, death, and recurrence-free survival using a comprehensive radiomics analysis. Different feature selection and predictive modeling techniques were used to determine the optimal configuration of prognosis analysis. To address feature redundancy, comprehensive analysis indicated that Random Forest models and Principal Component Analysis were optimum predictive modeling and feature selection methods, respectively, for achieving high prognosis performance. To address unbalanced data, Synthetic Minority Over-sampling technique was found to significantly increase predictive accuracy. A full analysis of variance showed that data endpoints, feature selection techniques, and classifiers were significant factors in affecting predictive accuracy, suggesting that these factors must be investigated when building radiomics-based predictive models for cancer prognosis.
Download
📖 Papers frequently viewed together
2,200 Citations
20167.93Radiology
2,480 Citations
1,001 Citations
References39
Newest
#1Masoom A. Haider (Sunnybrook Health Sciences Centre)H-Index: 40
#1Masoom A. Haider (Sunnybrook Health Sciences Centre)H-Index: 8
Last. Georg A. Bjarnason (U of T: University of Toronto)H-Index: 55
view all 6 authors...
Background To assess CT texture based quantitative imaging biomarkers in the prediction of progression free survival (PFS) and overall survival (OS) in patients with clear cell renal cell carcinoma undergoing treatment with Sunitinib.
48 CitationsSource
#1Junjie ZhangH-Index: 8
#2Sameer BaigH-Index: 4
Last. Farzad KhalvatiH-Index: 20
view all 5 authors...
Segmentation of prostate and related anatomic structure, such as transitional zone, in medical images facilitates prostate cancer detection, as well as a number of other clinical practices. In this paper, we propose a semi-automatic local ROI-specific atlas-based segmentation (LABS) method to segment prostate gland and transitional zone in diffusion magnetic resonance images. Inspired by a sequential registration-based segmentation method, the proposed method further reduces the amount of user i...
14 CitationsSource
#1Yanqi HuangH-Index: 15
#1Ying-Sheng HuangH-Index: 56
Last. Changhong LiangH-Index: 28
view all 9 authors...
A multi-feature–based radiomics signature was identified to be an independent biomarker for the estimation of disease-free survival (DFS) in patients with early-stage non–small cell lung cancer in this study, with incremental value to traditional staging system and other clinical-pathologic risk factors for individualized DFS estimation.
327 CitationsSource
#1Andrew Cameron (UW: University of Waterloo)H-Index: 11
#2Farzad Khalvati (U of T: University of Toronto)H-Index: 20
Last. Alexander Wong (UW: University of Waterloo)H-Index: 55
view all 4 authors...
This paper presents a quantitative radiomics feature model for performing prostate cancer detection using multiparametric MRI (mpMRI). It incorporates a novel tumor candidate identification algorithm to efficiently and thoroughly identify the regions of concern and constructs a comprehensive radiomics feature model to detect tumorous regions. In contrast to conventional automated classification schemes, this radiomics-based feature model aims to ground its decisions in a way that can be interpre...
100 CitationsSource
#1Jia Wu (Stanford University)H-Index: 28
#2Todd A. Aguilera (Stanford University)H-Index: 18
Last. Ruijiang Li (Stanford University)H-Index: 32
view all 8 authors...
In this study, the authors identified prognostic imaging signatures in patients with early-stage non–small cell lung cancer by using a quantitative radiomic approach; if prospectively validated, these imaging biomarkers could aid in identifying patients who might benefit from adjuvant systemic therapy.
98 CitationsSource
#1Vishwa S. Parekh (JHUSOM: Johns Hopkins University School of Medicine)H-Index: 9
#2Michael A. Jacobs (JHUSOM: Johns Hopkins University School of Medicine)H-Index: 59
ABSTRACTThe increasing use of biomarkers in cancer have led to the concept of personalized medicine for patients. Personalized medicine provides better diagnosis and treatment options available to clinicians. Radiological imaging techniques provide an opportunity to deliver unique data on different types of tissue. However, obtaining useful information from all radiological data is challenging in the era of ‘big data’. Recent advances in computational power and the use of genomics have generated...
136 CitationsSource
#1Robert J. GilliesH-Index: 106
#2Paul E. Kinahan (UW: University of Washington)H-Index: 69
Last. Hedvig Hricak (MSK: Memorial Sloan Kettering Cancer Center)H-Index: 137
view all 3 authors...
This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision making, particularly in the care of patients with cancer.
2,480 CitationsSource
#1Chintan Parmar (ISI: Indian Statistical Institute)H-Index: 24
#2Patrick Grossmann (Harvard University)H-Index: 16
Last. Hugo J.W.L. Aerts (Harvard University)H-Index: 65
view all 5 authors...
Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pretreatment computed tom...
486 CitationsSource
#1Farzad Khalvati (U of T: University of Toronto)H-Index: 20
#2Alexander Wong (UW: University of Waterloo)H-Index: 55
Last. Masoom A. Haider (U of T: University of Toronto)H-Index: 39
view all 3 authors...
Background Prostate cancer is the most common form of cancer and the second leading cause of cancer death in North America. Auto-detection of prostate cancer can play a major role in early detection of prostate cancer, which has a significant impact on patient survival rates. While multi-parametric magnetic resonance imaging (MP-MRI) has shown promise in diagnosis of prostate cancer, the existing auto-detection algorithms do not take advantage of abundance of data available in MP-MRI to improve ...
114 CitationsSource
#1Zena M. Hira (Imperial College London)H-Index: 2
#2Duncan Fyfe Gillies (Imperial College London)H-Index: 15
We summarise various ways of performing dimensionality reduction on high-dimensional microarray data. Many different feature selection and feature extraction methods exist and they are being widely used. All these methods aim to remove redundant and irrelevant features so that classification of new instances will be more accurate. A popular source of data is microarrays, a biological platform for gathering gene expressions. Analysing microarrays can be difficult due to the size of the data they ...
415 CitationsSource
Cited By124
Newest
#1Carol Oliveira (Queen's University)H-Index: 2
#2Florian Amstutz (UZH: University of Zurich)H-Index: 1
Last. Miklos Pless (Winterthur Museum, Garden and Library)H-Index: 33
view all 0 authors...
Background null Radiomics is a promising tool for identifying imaging-based biomarkers. Radiomics-based models are often trained on single-institution datasets; however, multi-centre imaging datasets are preferred for external generalizability owing to the influence of inter-institutional scanning differences and acquisition settings. The study aim was to determine the value of preselection of robust radiomic features in routine clinical positron emission tomography (PET) images to predict clini...
Source
#1Jeffrey Wong (UNMC: University of Nebraska Medical Center)
#2Michael J. Baine (UNMC: University of Nebraska Medical Center)H-Index: 14
Last. Dandan Zheng (UNMC: University of Nebraska Medical Center)H-Index: 8
view all 10 authors...
Radiomics is a method to mine large numbers of quantitative imaging features and develop predictive models. It has shown exciting promise for improved cancer decision support from early detection to personalized precision treatment, and therefore offers a desirable new direction for pancreatic cancer where the mortality remains high despite the current care and intense research. For radiomics, interobserver segmentation variability and its effect on radiomic feature stability is a crucial consid...
Source
OBJECTIVES: To investigate whether quantitative textural features, extracted from pretreatment MRI, can predict sustained complete response to radiofrequency ablation (RFA) in patients with hepatocellular carcinoma (HCC). METHODS: In this IRB-approved study, patients were selected from a maintained six-year database of consecutive patients who underwent both pretreatment MRI imaging with a probable or definitive imaging diagnosis of HCC (LI-RADS 4 or 5) and loco-regional treatment with RFA. An e...
Source
#1Karl Spuhler (NYU: New York University)H-Index: 7
#1Karl D. Spuhler (NYU: New York University)
Last. P Galavis (NYU: New York University)H-Index: 4
view all 3 authors...
Purpose null Radiomics modelling is an exciting avenue for enhancing clinical decision-making and personalized treatment. Radiation oncology patients often undergo routine imaging for position verification, particularly using LINAC-mounted cone-beam computed tomography (CBCT). The wealth of imaging data collected in modern radiation therapy presents an ideal use case for radiomics modelling. Despite this, texture feature (TF) calculation can be limited by concerns over feature stability and repr...
Source
#2David M. VockH-Index: 23
Last. Guadalupe CanahuateH-Index: 12
view all 6 authors...
Source
#1Ping Wang (Hebei University)
#2Xu Pei (Hebei University)
Last. Bu-Lang Gao (Hebei University)
view all 8 authors...
This study was to assess the effect of the predictive model for distinguishing clear cell RCC (ccRCC) from non-clear cell RCC (non-ccRCC) by establishing predictive radiomic models based on enhanced-computed tomography (CT) images of renal cell carcinoma (RCC). A total of 190 cases with RCC confirmed by pathology were retrospectively analyzed, with the patients being randomly divided into two groups, including the training set and testing set according to the ratio of 7:3. A total of 396 radiomi...
Source
#1Allegra Conti (University of Rome Tor Vergata)H-Index: 9
#2Andrea Duggento (University of Rome Tor Vergata)H-Index: 18
Last. Nicola Toschi (University of Rome Tor Vergata)H-Index: 37
view all 5 authors...
Breast Cancer (BC) is the common form of cancer in women. Its diagnosis and screening are usually performed through different imaging modalities such as mammography, magnetic resonance imaging and ultrasound. However, mammography and ultrasound-imaging techniques have limited sensitivity and specificity both in identifying lesions and in differentiating malign from benign lesions, especially in presence of dense breast parenchyma. Due to the higher resolution of magnetic resonance images, MRI re...
9 CitationsSource
Respiratory muscle function has a significant effect on stroke. Stroke is one of the most common cardiovascular and cerebrovascular diseases in the clinic and has a significant impact on the quality of life of patients. Hemiplegia, cerebral hemorrhage, and even death can occur, mainly in the elderly. In this paper, we meta-analyzed the effect of inspiratory muscle training on respiratory muscle function. In this article, we used a topic search method to search for relevant literature on respirat...
1 CitationsSource
#1Menglin Chen (Southern Medical University)H-Index: 2
#2Fu Yin (SZU: Shenzhen University)
Last. Ge Wen (Southern Medical University)H-Index: 3
view all 5 authors...
BACKGROUND The aim of the study is to compare the diagnostic value of models that based on a set of CT texture and non-texture features for differentiating clear cell renal cell carcinomas(ccRCCs) from non-clear cell renal cell carcinomas(non-ccRCCs). METHODS A total of 197 pathologically proven renal tumors were divided into ccRCC(n = 143) and non-ccRCC (n = 54) groups. The 43 non-texture features and 296 texture features that extracted from the 3D volume tumor tissue were assessed for each tum...
Source
#1Federica Corso (Polytechnic University of Milan)H-Index: 1
#2Giulia Tini (IEO: European Institute of Oncology)H-Index: 2
Last. Daniela Origgi (IEO: European Institute of Oncology)H-Index: 15
view all 18 authors...
Radiomics uses high-dimensional sets of imaging features to predict biological characteristics of tumors and clinical outcomes. The choice of the algorithm used to analyze radiomic features and perform predictions has a high impact on the results, thus the identification of adequate machine learning methods for radiomic applications is crucial. In this study we aim to identify suitable approaches of analysis for radiomic-based binary predictions, according to sample size, outcome balancing and t...
Source