1
|
Chen W, Sá RC, Bai Y, Napel S, Gevaert O, Lauderdale DS, Giger ML. Machine learning with multimodal data for COVID-19. Heliyon 2023; 9:e17934. [PMID: 37483733 PMCID: PMC10362086 DOI: 10.1016/j.heliyon.2023.e17934] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Accepted: 07/03/2023] [Indexed: 07/25/2023] Open
Abstract
In response to the unprecedented global healthcare crisis of the COVID-19 pandemic, the scientific community has joined forces to tackle the challenges and prepare for future pandemics. Multiple modalities of data have been investigated to understand the nature of COVID-19. In this paper, MIDRC investigators present an overview of the state-of-the-art development of multimodal machine learning for COVID-19 and model assessment considerations for future studies. We begin with a discussion of the lessons learned from radiogenomic studies for cancer diagnosis. We then summarize the multi-modality COVID-19 data investigated in the literature including symptoms and other clinical data, laboratory tests, imaging, pathology, physiology, and other omics data. Publicly available multimodal COVID-19 data provided by MIDRC and other sources are summarized. After an overview of machine learning developments using multimodal data for COVID-19, we present our perspectives on the future development of multimodal machine learning models for COVID-19.
Collapse
Affiliation(s)
- Weijie Chen
- Medical Imaging and Data Resource Center (MIDRC), USA
- Division of Imaging, Diagnostics, and Software Reliability, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, USA
| | - Rui C. Sá
- Medical Imaging and Data Resource Center (MIDRC), USA
- Department of Medicine, University of California, San Diego, USA
| | - Yuntong Bai
- Medical Imaging and Data Resource Center (MIDRC), USA
- Division of Imaging, Diagnostics, and Software Reliability, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, USA
| | - Sandy Napel
- Medical Imaging and Data Resource Center (MIDRC), USA
- Department of Radiology, Stanford University, USA
| | - Olivier Gevaert
- Medical Imaging and Data Resource Center (MIDRC), USA
- Department of Medicine and Department of Biomedical Data Science, Stanford University, USA
| | - Diane S. Lauderdale
- Medical Imaging and Data Resource Center (MIDRC), USA
- Department of Public Health Sciences, University of Chicago, USA
| | - Maryellen L. Giger
- Medical Imaging and Data Resource Center (MIDRC), USA
- Department of Radiology, University of Chicago, USA
| |
Collapse
|
2
|
Value of Quantitative CTTA in Differentiating Malignant From Benign Bosniak III Renal Lesions on CT Images. J Comput Assist Tomogr 2021; 45:528-536. [PMID: 34176873 DOI: 10.1097/rct.0000000000001181] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023]
Abstract
OBJECTIVE The aim of this study was to investigate whether computed tomography texture analysis can differentiate malignant from benign Bosniak III renal lesions on computed tomography (CT) images. METHODS This retrospective case-control study included 45 patients/lesions (22 benign and 23 malignant lesions) with Bosniak III renal lesions who underwent CT examination. Axial image slices in the unenhanced phase, corticomedullary phase, and nephrographic phase were selected and delineated manually. Computed tomography texture analysis was performed on each lesion during these 3 phases. Histogram-based, gray-level co-occurrence matrix, and gray-level run-length matrix features were extracted using open-source software and analyzed. In addition, receiver operating characteristic curve was constructed, and the area under the receiver operating characteristic curve (AUC) of each feature was constructed. RESULTS Of the 33 extracted features, 16 features showed significant differences (P < 0.05). Eight features were significantly different between the 2 groups after Holm-Bonferroni correction, including 3 histogram-based, 4 gray-level co-occurrence matrix, and 1 gray-level run-length matrix features (P < 0.01). The texture features resulted in the highest AUC of 0.769 ± 0.074. Renal cell carcinomas were labeled with a higher degree of lesion gray-level disorder and lower lesion homogeneity, and a model incorporating the 3 most discriminative features resulted in an AUC of 0.846 ± 0.058. CONCLUSIONS The results of this study showed that CT texture features were related to malignancy in Bosniak III renal lesions. Computed tomography texture analysis might help in differentiating malignant from benign Bosniak III renal lesions on CT images.
Collapse
|
3
|
Zhang Y, Li X, Lv Y, Gu X. Review of Value of CT Texture Analysis and Machine Learning in Differentiating Fat-Poor Renal Angiomyolipoma from Renal Cell Carcinoma. Tomography 2020; 6:325-332. [PMID: 33364422 PMCID: PMC7744193 DOI: 10.18383/j.tom.2020.00039] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
The diagnosis of patients with suspected angiomyolipoma relies on the detection of abundant macroscopic intralesional fat, which is always of no use to differentiate fat-poor angiomyolipoma (fp-AML) from renal cell carcinoma and diagnosis of fp-AML excessively depends on individual experience. Texture analysis was proven to be a potentially useful biomarker for distinguishing between benign and malignant tumors because of its capability of providing objective and quantitative assessment of lesions by analyzing features that are not visible to the human eye. This review aimed to summarize the literature on the use of texture analysis to diagnose patients with fat-poor angiomyolipoma vs those with renal cell carcinoma and to evaluate its current application, limitations, and future challenges in order to avoid unnecessary surgical resection.
Collapse
Affiliation(s)
- Yuhan Zhang
- Department of Urology, China-Japan Union Hospital of Jilin University, Changchun, China; and
| | - Xu Li
- Department of Urology, China-Japan Union Hospital of Jilin University, Changchun, China; and
| | - Yang Lv
- Department of Anesthesia, The Second Hospital of Jilin University, Changchun, China
| | - Xinquan Gu
- Department of Urology, China-Japan Union Hospital of Jilin University, Changchun, China; and
| |
Collapse
|
4
|
Radiomics Applications in Renal Tumor Assessment: A Comprehensive Review of the Literature. Cancers (Basel) 2020; 12:cancers12061387. [PMID: 32481542 PMCID: PMC7352711 DOI: 10.3390/cancers12061387] [Citation(s) in RCA: 37] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2020] [Revised: 05/22/2020] [Accepted: 05/26/2020] [Indexed: 12/21/2022] Open
Abstract
Radiomics texture analysis offers objective image information that could otherwise not be obtained by radiologists′ subjective radiological interpretation. We investigated radiomics applications in renal tumor assessment and provide a comprehensive review. A detailed search of original articles was performed using the PubMed-MEDLINE database until 20 March 2020 to identify English literature relevant to radiomics applications in renal tumor assessment. In total, 42 articles were included in the analysis and divided into four main categories: renal mass differentiation, nuclear grade prediction, gene expression-based molecular signatures, and patient outcome prediction. The main area of research involves accurately differentiating benign and malignant renal masses, specifically between renal cell carcinoma (RCC) subtypes and from angiomyolipoma without visible fat and oncocytoma. Nuclear grade prediction may enhance proper patient selection for risk-stratified treatment. Radiomics-predicted gene mutations may serve as surrogate biomarkers for high-risk disease, while predicting patients’ responses to targeted therapies and their outcomes will help develop personalized treatment algorithms. Studies generally reported the superiority of radiomics over expert radiological interpretation. Radiomics provides an alternative to subjective image interpretation for improving renal tumor diagnostic accuracy. Further incorporation of clinical and imaging data into radiomics algorithms will augment tumor prediction accuracy and enhance individualized medicine.
Collapse
|
5
|
[Study Progress of Radiomics in Precision Medicine for Lung Cancer]. ZHONGGUO FEI AI ZA ZHI = CHINESE JOURNAL OF LUNG CANCER 2019; 22:385-388. [PMID: 31196373 PMCID: PMC6580079 DOI: 10.3779/j.issn.1009-3419.2019.06.09] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Precision medicine, imaging first. Radiomics, a method of machine learning in artificial intelligence, provides valuable diagnostic, prognostic or predictive information through quantitative analysis on the tumor's region of interest to support personalized clinical decisions and improve individualized treatment, which could lay a solid foundation for achieving the precision medicine. This review provides a latest advance of the radiomic application of the precision medicine for lung cancer.
Collapse
|
6
|
Radiogenomics of rectal adenocarcinoma in the era of precision medicine: A pilot study of associations between qualitative and quantitative MRI imaging features and genetic mutations. Eur J Radiol 2019; 113:174-181. [PMID: 30927944 DOI: 10.1016/j.ejrad.2019.02.022] [Citation(s) in RCA: 31] [Impact Index Per Article: 6.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2018] [Revised: 01/24/2019] [Accepted: 02/17/2019] [Indexed: 12/16/2022]
Abstract
OBJECTIVE To investigate associations between genetic mutations and qualitative as well as quantitative features on MRI in rectal adenocarcinoma at primary staging. METHODS In this retrospective study, patients with rectal adenocarcinoma, genome sequencing, and pretreatment rectal MRI were included. Statistical analysis was performed to evaluate associations between qualitative features obtained from subjective evaluation of rectal MRI and gene mutations as well as between quantitative textural features and gene mutations. For the qualitative evaluation, Fisher's Exact test was used to analyze categorical associations and Wilcoxon Rank Sum test was used for continuous clinical variables. For the quantitative evaluation, we performed manual segmentation of T2-weighted images for radiomics-based quantitative image analysis. Thirty-four texture features consisting of first order intensity histogram-based features (n = 4), second order Haralick textures (n = 5), and Gabor-edge based Haralick textures were computed at two different orientations. Consensus clustering was performed with 34 computed texture features using the K-means algorithm with Euclidean distance between the texture features. The clusters resulting from the algorithm were then used to enumerate the prevalence of gene mutations in those clusters. RESULTS In 65 patients, 45 genes were mutated in more than 3/65 patients (5%) and were included in the statistical analysis. Regarding qualitative imaging features, on univariate analysis, tumor location was significantly associated with APC (p = 0.032) and RASA1 mutation (p = 0.032); CRM status was significantly associated with ATM mutation (p = 0.021); and lymph node metastasis was significantly associated with BRCA2 (p = 0.046) mutation. However, these associations were not significant after adjusting for multiple comparisons. Regarding quantitative imaging features, Cluster C1 had tumors with higher mean Gabor edge intensity compared with cluster C2 (θ = 0°, p = 0.018; θ = 45°, p = 0.047; θ = 90°, p = 0.037; cluster C3 (θ = 0°, p = 0.18; θ = 45°, p = 0.1; θ = 90°, p = 0.052), and cluster C4 (θ = 0°, p = 0.016; θ = 45°, p = 0.033; θ = 90°, p = 0.014) suggesting that the cluster C1 had tumors with more distinct edges or heterogeneous appearance compared with other clusters. CONCLUSIONS Although this preliminary study showed promising associations between quantitative features and genetic mutations, it did not show any correlation between qualitative features and genetic mutations. Further studies with larger sample size are warranted to validate our preliminary data.
Collapse
|
7
|
Radiogenomics analysis identifies correlations of digital mammography with clinical molecular signatures in breast cancer. PLoS One 2018; 13:e0193871. [PMID: 29596496 PMCID: PMC5875760 DOI: 10.1371/journal.pone.0193871] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2017] [Accepted: 02/19/2018] [Indexed: 12/21/2022] Open
Abstract
In breast cancer, well-known gene expression subtypes have been related to a specific clinical outcome. However, their impact on the breast tissue phenotype has been poorly studied. Here, we investigate the association of imaging data of tumors to gene expression signatures from 71 patients with breast cancer that underwent pre-treatment digital mammograms and tumor biopsies. From digital mammograms, a semi-automated radiogenomics analysis generated 1,078 features describing the shape, signal distribution, and texture of tumors along their contralateral image used as control. From tumor biopsy, we estimated the OncotypeDX and PAM50 recurrence scores using gene expression microarrays. Then, we used multivariate analysis under stringent cross-validation to train models predicting recurrence scores. Few univariate features reached Spearman correlation coefficients above 0.4. Nevertheless, multivariate analysis yielded significantly correlated models for both signatures (correlation of OncotypeDX = 0.49 ± 0.07 and PAM50 = 0.32 ± 0.10 in stringent cross-validation and OncotypeDX = 0.83 and PAM50 = 0.78 for a unique model). Equivalent models trained from the unaffected contralateral breast were not correlated suggesting that the image signatures were tumor-specific and that overfitting was not a considerable issue. We also noted that models were improved by combining clinical information (triple negative status and progesterone receptor). The models used mostly wavelets and fractal features suggesting their importance to capture tumor information. Our results suggest that molecular-based recurrence risk and breast cancer subtypes have observable radiographic phenotypes. To our knowledge, this is the first study associating mammographic information to gene expression recurrence signatures.
Collapse
|
8
|
Mancini M, Summers P, Faita F, Brunetto MR, Callea F, De Nicola A, Di Lascio N, Farinati F, Gastaldelli A, Gridelli B, Mirabelli P, Neri E, Salvadori PA, Rebelos E, Tiribelli C, Valenti L, Salvatore M, Bonino F. Digital liver biopsy: Bio-imaging of fatty liver for translational and clinical research. World J Hepatol 2018; 10:231-245. [PMID: 29527259 PMCID: PMC5838442 DOI: 10.4254/wjh.v10.i2.231] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/26/2017] [Revised: 01/27/2018] [Accepted: 02/25/2018] [Indexed: 02/06/2023] Open
Abstract
The rapidly growing field of functional, molecular and structural bio-imaging is providing an extraordinary new opportunity to overcome the limits of invasive liver biopsy and introduce a "digital biopsy" for in vivo study of liver pathophysiology. To foster the application of bio-imaging in clinical and translational research, there is a need to standardize the methods of both acquisition and the storage of the bio-images of the liver. It can be hoped that the combination of digital, liquid and histologic liver biopsies will provide an innovative synergistic tri-dimensional approach to identifying new aetiologies, diagnostic and prognostic biomarkers and therapeutic targets for the optimization of personalized therapy of liver diseases and liver cancer. A group of experts of different disciplines (Special Interest Group for Personalized Hepatology of the Italian Association for the Study of the Liver, Institute for Biostructures and Bio-imaging of the National Research Council and Bio-banking and Biomolecular Resources Research Infrastructure) discussed criteria, methods and guidelines for facilitating the requisite application of data collection. This manuscript provides a multi-Author review of the issue with special focus on fatty liver.
Collapse
Affiliation(s)
- Marcello Mancini
- Institute of Biostructure and Bioimaging, National Research Council, Naples 80145, Italy
| | - Paul Summers
- European Institute of Oncology (IEO) IRCCS, Milan 20141, Italy
| | - Francesco Faita
- Institute of Clinical Physiology (IFC), National Research Council (CNR), Pisa 56124, Italy
| | - Maurizia R Brunetto
- Hepatology Unit, Department of Clinical and Experimental Medicine, University Hospital of Pisa, Pisa 56125, Italy
| | - Francesco Callea
- Department of Pathology, Children Hospital Bambino Gesù IRCCS, Rome 00165, Italy
| | | | - Nicole Di Lascio
- Institute of Clinical Physiology (IFC), National Research Council (CNR), Pisa 56124, Italy
| | - Fabio Farinati
- Department of Gastroenterology, Oncology and Surgical Sciences, University of Padua, Padua 35121, Italy
| | - Amalia Gastaldelli
- Cardio-metabolic Risk Laboratory, Institute of Clinical Physiology (IFC), National Research Council (CNR), Pisa 56124, Italy
| | - Bruno Gridelli
- Institute for Health, University of Pittsburgh Medical Center (UPMC), Chianciano Terme 53042, Italy
| | | | - Emanuele Neri
- Diagnostic Radiology 3, Department of Translational Research, University of Pisa and "Ospedale S. Chiara" AOUP, Pisa 56126, Italy
| | - Piero A Salvadori
- Institute of Clinical Physiology (IFC), National Research Council (CNR), Pisa 56124, Italy
| | - Eleni Rebelos
- Hepatology Unit, Department of Clinical and Experimental Medicine, University Hospital of Pisa, Pisa 56125, Italy
| | - Claudio Tiribelli
- Fondazione Italiana Fegato (FIF), Area Science Park, Campus Basovizza, Trieste 34012, Italy
| | - Luca Valenti
- Department of Pathophysiology and Transplantation, Università degli Studi di Milano and Department of Internal Medicine and Metabolic Diseases, Fondazione IRCCS Ca' Granda Ospedale Policlinico, Milan 20122, Italy
| | | | - Ferruccio Bonino
- Institute of Biostructure and Bioimaging, National Research Council, Naples 80145, Italy
| |
Collapse
|
9
|
Valdora F, Houssami N, Rossi F, Calabrese M, Tagliafico AS. Rapid review: radiomics and breast cancer. Breast Cancer Res Treat 2018; 169:217-229. [PMID: 29396665 DOI: 10.1007/s10549-018-4675-4] [Citation(s) in RCA: 161] [Impact Index Per Article: 26.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2017] [Accepted: 01/16/2018] [Indexed: 12/13/2022]
Abstract
PURPOSE To perform a rapid review of the recent literature on radiomics and breast cancer (BC). METHODS A rapid review, a streamlined approach to systematically identify and summarize emerging studies was done (updated 27 September 2017). Clinical studies eligible for inclusion were those that evaluated BC using a radiomics approach and provided data on BC diagnosis (detection or characterization) or BC prognosis (response to therapy, morbidity, mortality), or provided data on technical challenges (software application: open source, repeatability of results). Descriptive statistics, results, and radiomics quality score (RQS) are presented. RESULTS N = 17 retrospective studies, all published after 2015, provided BC-related radiomics data on 3928 patients evaluated with a radiomics approach. Most studies were done for diagnosis and/or characterization (65%, 11/17) or to aid in prognosis (41%, 7/17). The mean number of radiomics features considered was 100. Mean RQS score was 11.88 ± 5.8 (maximum value 36). The RQS criteria related to validation, gold standard, potential clinical utility, cost analysis, and open science data had the lowest scores. The majority of studies n = 16/17 (94%) provided correlation with histological outcomes and staging variables or biomarkers. Only 4/17 (23%) studies provided evidence of correlation with genomic data. Magnetic resonance imaging (MRI) was used in most studies n = 14/17 (82%); however, ultrasound (US), mammography, or positron emission tomography with 2-deoxy-2-[fluorine-18]fluoro-D-glucose integrated with computed tomography (18F FDG PET/CT) was also used. Much heterogeneity was found for software usage. CONCLUSIONS The study of radiomics in BC patients is a new and emerging translational research topic. Radiomics in BC is frequently done to potentially improve diagnosis and characterization, mostly using MRI. Substantial quality limitations were found; high-quality prospective and reproducible studies are needed to further potential application.
Collapse
Affiliation(s)
- Francesca Valdora
- Department of Health Sciences, University of Genova, Via L.B. Alberti 2, 16132, Genoa, Italy
| | - Nehmat Houssami
- Sydney School of Public Health, Sydney Medical School, University of Sydney, Sydney, NSW, Australia
| | - Federica Rossi
- Department of Health Sciences, University of Genova, Via L.B. Alberti 2, 16132, Genoa, Italy
| | | | - Alberto Stefano Tagliafico
- Department of Health Sciences, University of Genova, Via L.B. Alberti 2, 16132, Genoa, Italy. .,Ospedale Policlinico San Martino IST, Genoa, Italy.
| |
Collapse
|
10
|
Bakr S, Echegaray S, Shah R, Kamaya A, Louie J, Napel S, Kothary N, Gevaert O. Noninvasive radiomics signature based on quantitative analysis of computed tomography images as a surrogate for microvascular invasion in hepatocellular carcinoma: a pilot study. J Med Imaging (Bellingham) 2017; 4:041303. [PMID: 28840174 DOI: 10.1117/1.jmi.4.4.041303] [Citation(s) in RCA: 38] [Impact Index Per Article: 5.4] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2017] [Accepted: 05/25/2017] [Indexed: 12/16/2022] Open
Abstract
We explore noninvasive biomarkers of microvascular invasion (mVI) in patients with hepatocellular carcinoma (HCC) using quantitative and semantic image features extracted from contrast-enhanced, triphasic computed tomography (CT). Under institutional review board approval, we selected 28 treatment-naive HCC patients who underwent surgical resection. Four radiologists independently selected and delineated tumor margins on three axial CT images and extracted computational features capturing tumor shape, image intensities, and texture. We also computed two types of "delta features," defined as the absolute difference and the ratio computed from all pairs of imaging phases for each feature. 717 arterial, portal-venous, delayed single-phase, and delta-phase features were robust against interreader variability ([Formula: see text]). An enhanced cross-validation analysis showed that combining robust single-phase and delta features in the arterial and venous phases identified mVI (AUC [Formula: see text]). Compared to a previously reported semantic feature signature (AUC 0.47 to 0.58), these features in our cohort showed only slight to moderate agreement (Cohen's kappa range: 0.03 to 0.59). Though preliminary, quantitative analysis of image features in arterial and venous phases may be potential surrogate biomarkers for mVI in HCC. Further study in a larger cohort is warranted.
Collapse
Affiliation(s)
- Shaimaa Bakr
- Stanford University, Department of Electrical Engineering, Stanford, California, United States
| | - Sebastian Echegaray
- Stanford University, Department of Electrical Engineering, Stanford, California, United States
| | - Rajesh Shah
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| | - Aya Kamaya
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| | - John Louie
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| | - Sandy Napel
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| | - Nishita Kothary
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| | - Olivier Gevaert
- Stanford University, Department of Radiology, James H. Clark Center, Stanford, California, United States
| |
Collapse
|
11
|
Abstract
The domain of investigation of radiomics consists of large-scale radiological image analysis and association with biological or clinical endpoints. The purpose of the present study is to provide a recent update on the status of this rapidly emerging field by performing a systematic review of the literature on radiomics, with a primary focus on oncologic applications. The systematic literature search, performed in Pubmed using the keywords: "radiomics OR radiomic" provided 97 research papers. Based on the results of this search, we describe the methods used for building a model of prognostic value from quantitative analysis of patient images. Then, we provide an up-to-date overview of the results achieved in this field, and discuss the current challenges and future developments of radiomics for oncology.
Collapse
|
12
|
Echegaray S, Nair V, Kadoch M, Leung A, Rubin D, Gevaert O, Napel S. A Rapid Segmentation-Insensitive "Digital Biopsy" Method for Radiomic Feature Extraction: Method and Pilot Study Using CT Images of Non-Small Cell Lung Cancer. ACTA ACUST UNITED AC 2016; 2:283-294. [PMID: 28612050 PMCID: PMC5466872 DOI: 10.18383/j.tom.2016.00163] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/25/2022]
Abstract
Quantitative imaging approaches compute features within images' regions of interest. Segmentation is rarely completely automatic, requiring time-consuming editing by experts. We propose a new paradigm, called “digital biopsy,” that allows for the collection of intensity- and texture-based features from these regions at least 1 order of magnitude faster than the current manual or semiautomated methods. A radiologist reviewed automated segmentations of lung nodules from 100 preoperative volume computed tomography scans of patients with non–small cell lung cancer, and manually adjusted the nodule boundaries in each section, to be used as a reference standard, requiring up to 45 minutes per nodule. We also asked a different expert to generate a digital biopsy for each patient using a paintbrush tool to paint a contiguous region of each tumor over multiple cross-sections, a procedure that required an average of <3 minutes per nodule. We simulated additional digital biopsies using morphological procedures. Finally, we compared the features extracted from these digital biopsies with our reference standard using intraclass correlation coefficient (ICC) to characterize robustness. Comparing the reference standard segmentations to our digital biopsies, we found that 84/94 features had an ICC >0.7; comparing erosions and dilations, using a sphere of 1.5-mm radius, of our digital biopsies to the reference standard segmentations resulted in 41/94 and 53/94 features, respectively, with ICCs >0.7. We conclude that many intensity- and texture-based features remain consistent between the reference standard and our method while substantially reducing the amount of operator time required.
Collapse
Affiliation(s)
- Sebastian Echegaray
- Department of Electrical Engineering, Stanford University, Stanford, California
| | - Viswam Nair
- Department of Radiology, Stanford University School of Medicine, Stanford, California.,Department of Medicine, Stanford University School of Medicine, Stanford, California.,Canary Center for Cancer Early Detection, Stanford University, Stanford, California
| | - Michael Kadoch
- Department of Radiology, Stanford University School of Medicine, Stanford, California
| | - Ann Leung
- Department of Radiology, Stanford University School of Medicine, Stanford, California
| | - Daniel Rubin
- Department of Radiology, Stanford University School of Medicine, Stanford, California.,Department of Medicine, Stanford University School of Medicine, Stanford, California
| | - Olivier Gevaert
- Department of Medicine, Stanford University School of Medicine, Stanford, California
| | - Sandy Napel
- Department of Radiology, Stanford University School of Medicine, Stanford, California
| |
Collapse
|
13
|
Cirujeda P, Dicente Cid Y, Muller H, Rubin D, Aguilera TA, Loo BW, Diehn M, Binefa X, Depeursinge A. A 3-D Riesz-Covariance Texture Model for Prediction of Nodule Recurrence in Lung CT. IEEE TRANSACTIONS ON MEDICAL IMAGING 2016; 35:2620-2630. [PMID: 27429433 DOI: 10.1109/tmi.2016.2591921] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
This paper proposes a novel imaging biomarker of lung cancer relapse from 3-D texture analysis of CT images. Three-dimensional morphological nodular tissue properties are described in terms of 3-D Riesz-wavelets. The responses of the latter are aggregated within nodular regions by means of feature covariances, which leverage rich intra- and inter-variations of the feature space dimensions. When compared to the classical use of the average for feature aggregation, feature covariances preserve spatial co-variations between features. The obtained Riesz-covariance descriptors lie on a manifold governed by Riemannian geometry allowing geodesic measurements and differentiations. The latter property is incorporated both into a kernel for support vector machines (SVM) and a manifold-aware sparse regularized classifier. The effectiveness of the presented models is evaluated on a dataset of 110 patients with non-small cell lung carcinoma (NSCLC) and cancer recurrence information. Disease recurrence within a timeframe of 12 months could be predicted with an accuracy of 81.3-82.7%. The anatomical location of recurrence could be discriminated between local, regional and distant failure with an accuracy of 78.3-93.3%. The obtained results open novel research perspectives by revealing the importance of the nodular regions used to build the predictive models.
Collapse
|