1
|
Mirza-Aghazadeh-Attari M, Srinivas T, Kamireddy A, Kim A, Weiss CR. Radiomics Features Extracted From Pre- and Postprocedural Imaging in Early Prediction of Treatment Response in Patients Undergoing Transarterial Radioembolization of Hepatic Lesions: A Systematic Review, Meta-Analysis, and Quality Appraisal Study. J Am Coll Radiol 2024; 21:740-751. [PMID: 38220040 DOI: 10.1016/j.jacr.2023.12.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Revised: 12/20/2023] [Accepted: 12/21/2023] [Indexed: 01/16/2024]
Abstract
INTRODUCTION Transarterial radioembolization (TARE) is one of the most promising therapeutic options for hepatic masses. Radiomics features, which are quantitative numeric features extracted from medical images, are considered to have potential in predicting treatment response in TARE. This article aims to provide meta-analytic evidence and critically appraise the methodology of radiomics studies published in this regard. METHODS A systematic search was performed on PubMed, Scopus, Embase, and Web of Science. All relevant articles were retrieved, and the characteristics of the studies were extracted. The Radiomics Quality Score and Checklist for Evaluation of Radiomics Research were used to assess the methodologic quality of the studies. Pooled sensitivity, specificity, and area under the receiver operating characteristic curve in predicting objective response were determined. RESULTS The systematic review included 15 studies. The average Radiomics Quality Score of these studies was 11.4 ± 2.1, and the average Checklist for Evaluation of Radiomics Research score was 33± 6.7. There was a notable correlation (correlation coefficient = 0.73) between the two metrics. Adherence to quality measures differed considerably among the studies and even within different components of the same studies. The pooled sensitivity and specificity of the radiomics models in predicting complete or partial response were 83.5% (95% confidence interval 76%-88.9%) and 86.7% (95% confidence interval 78%-92%), respectively. CONCLUSION Radiomics models show great potential in predicting treatment response in TARE of hepatic lesions. However, the heterogeneity seen between the methodologic quality of studies may limit the generalizability of the results. Future initiatives should aim to develop radiomics signatures using multiple external datasets and adhere to quality measures in radiomics methodology.
Collapse
Affiliation(s)
- Mohammad Mirza-Aghazadeh-Attari
- Division of Vascular and Interventional Radiology, Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Tara Srinivas
- Division of Vascular and Interventional Radiology, Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Arun Kamireddy
- Division of Vascular and Interventional Radiology, Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Alan Kim
- Division of Vascular and Interventional Radiology, Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University, Baltimore, Maryland
| | - Clifford R Weiss
- Division of Vascular and Interventional Radiology, Russell H. Morgan Department of Radiology and Radiological Sciences, Johns Hopkins University, Baltimore, Maryland.
| |
Collapse
|
2
|
Triggiani S, Contaldo MT, Mastellone G, Cè M, Ierardi AM, Carrafiello G, Cellina M. The Role of Artificial Intelligence and Texture Analysis in Interventional Radiological Treatments of Liver Masses: A Narrative Review. Crit Rev Oncog 2024; 29:37-52. [PMID: 38505880 DOI: 10.1615/critrevoncog.2023049855] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/21/2024]
Abstract
Liver lesions, including both benign and malignant tumors, pose significant challenges in interventional radiological treatment planning and prognostication. The emerging field of artificial intelligence (AI) and its integration with texture analysis techniques have shown promising potential in predicting treatment outcomes, enhancing precision, and aiding clinical decision-making. This comprehensive review aims to summarize the current state-of-the-art research on the application of AI and texture analysis in determining treatment response, recurrence rates, and overall survival outcomes for patients undergoing interventional radiological treatment for liver lesions. Furthermore, the review addresses the challenges associated with the implementation of AI and texture analysis in clinical practice, including data acquisition, standardization of imaging protocols, and model validation. Future directions and potential advancements in this field are discussed. Integration of multi-modal imaging data, incorporation of genomics and clinical data, and the development of predictive models with enhanced interpretability are proposed as potential avenues for further research. In conclusion, the application of AI and texture analysis in predicting outcomes of interventional radiological treatment for liver lesions shows great promise in augmenting clinical decision-making and improving patient care. By leveraging these technologies, clinicians can potentially enhance treatment planning, optimize intervention strategies, and ultimately improve patient outcomes in the management of liver lesions.
Collapse
Affiliation(s)
- Sonia Triggiani
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono, 7, 20122 Milan, Italy
| | - Maria T Contaldo
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, 20122 Milan, Italy
| | - Giulia Mastellone
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, 20122 Milan, Italy
| | - Maurizio Cè
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono, 7, 20122 Milan, Italy
| | - Anna M Ierardi
- Radiology Department, Fondazione IRCCS Cà Granda, Policlinico di Milano Ospedale Maggiore, 20122 Milan, Italy
| | - Gianpaolo Carrafiello
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono, 7, 20122 Milan, Italy; Radiology Department, Fondazione IRCCS Cà Granda, Policlinico di Milano Ospedale Maggiore, Università di Milano, 20122 Milan, Italy
| | - Michaela Cellina
- Radiology Department, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Milano, Piazza Principessa Clotilde 3, 20121, Milan, Italy
| |
Collapse
|
3
|
Radiya K, Joakimsen HL, Mikalsen KØ, Aahlin EK, Lindsetmo RO, Mortensen KE. Performance and clinical applicability of machine learning in liver computed tomography imaging: a systematic review. Eur Radiol 2023; 33:6689-6717. [PMID: 37171491 PMCID: PMC10511359 DOI: 10.1007/s00330-023-09609-w] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2022] [Revised: 02/02/2023] [Accepted: 02/06/2023] [Indexed: 05/13/2023]
Abstract
OBJECTIVES Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging? METHODS A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography. RESULTS One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy. CONCLUSION Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this. KEY POINTS • ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.
Collapse
Affiliation(s)
- Keyur Radiya
- Department of Gastroenterological Surgery at University Hospital of North Norway (UNN), Tromso, Norway.
- Department of Clinical Medicine, UiT The Arctic University of Norway, Tromso, Norway.
| | - Henrik Lykke Joakimsen
- Institute of Clinical Medicine, UiT The Arctic University of Norway, Tromso, Norway
- Centre for Clinical Artificial Intelligence (SPKI), University Hospital of North Norway, Tromso, Norway
| | - Karl Øyvind Mikalsen
- Department of Clinical Medicine, UiT The Arctic University of Norway, Tromso, Norway
- Centre for Clinical Artificial Intelligence (SPKI), University Hospital of North Norway, Tromso, Norway
- UiT Machine Learning Group, Department of Physics and Technology, UiT the Arctic University of Norway, Tromso, Norway
| | - Eirik Kjus Aahlin
- Department of Gastroenterological Surgery at University Hospital of North Norway (UNN), Tromso, Norway
| | - Rolv-Ole Lindsetmo
- Department of Clinical Medicine, UiT The Arctic University of Norway, Tromso, Norway
- Head Clinic of Surgery, Oncology and Women Health, University Hospital of North Norway, Tromso, Norway
| | - Kim Erlend Mortensen
- Department of Gastroenterological Surgery at University Hospital of North Norway (UNN), Tromso, Norway
- Department of Clinical Medicine, UiT The Arctic University of Norway, Tromso, Norway
| |
Collapse
|
4
|
İnce O, Önder H, Gençtürk M, Cebeci H, Golzarian J, Young S. Prediction of Response of Hepatocellular Carcinoma to Radioembolization: Machine Learning Using Preprocedural Clinical Factors and MR Imaging Radiomics. J Vasc Interv Radiol 2023; 34:235-243.e3. [PMID: 36384224 DOI: 10.1016/j.jvir.2022.11.004] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Revised: 10/22/2022] [Accepted: 11/06/2022] [Indexed: 11/14/2022] Open
Abstract
PURPOSE To create and evaluate the ability of machine learning-based models with clinicoradiomic features to predict radiologic response after transarterial radioembolization (TARE). MATERIALS AND METHODS 82 treatment-naïve patients (65 responders and 17 nonresponders; median age: 65 years; interquartile range: 11) who underwent selective TARE were included. Treatment responses were evaluated using the European Association for the Study of the Liver criteria at 3-month follow-up. Laboratory, clinical, and procedural information were collected. Radiomic features were extracted from pretreatment contrast-enhanced T1-weighted magnetic resonance images obtained within 3 months before TARE. Feature selection consisted of intraclass correlation, followed by Pearson correlation analysis and finally, sequential feature selection algorithm. Support vector machine, logistic regression, random forest, and LightGBM models were created with both clinicoradiomic features and clinical features alone. Performance metrics were calculated with a nested 5-fold cross-validation technique. The performances of the models were compared by Wilcoxon signed-rank and Friedman tests. RESULTS In total, 1,128 features were extracted. The feature selection process resulted in 12 features (8 radiomic and 4 clinical features) being included in the final analysis. The area under the receiver operating characteristic curve values from the support vector machine, logistic regression, random forest, and LightGBM models were 0.94, 0.94, 0.88, and 0.92 with clinicoradiomic features and 0.82, 0.83, 0.82, and 0.83 with clinical features alone, respectively. All models exhibited significantly higher performances when radiomic features were included (P = .028, .028, .043, and .028, respectively). CONCLUSIONS Based on clinical and imaging-based information before treatment, machine learning-based clinicoradiomic models demonstrated potential to predict response to TARE.
Collapse
Affiliation(s)
- Okan İnce
- Department of Radiology, Medical School, University of Minnesota, Minneapolis, Minnesota.
| | - Hakan Önder
- Department of Radiology, Prof. Dr. Cemil Taşcıoğlu City Hospital, Health Sciences University, Istanbul, Turkey
| | - Mehmet Gençtürk
- Department of Radiology, Medical School, University of Minnesota, Minneapolis, Minnesota
| | - Hakan Cebeci
- Department of Radiology, Medical School, University of Minnesota, Minneapolis, Minnesota
| | - Jafar Golzarian
- Department of Radiology, Medical School, University of Minnesota, Minneapolis, Minnesota
| | - Shamar Young
- Department of Radiology, College of Medicine, University of Arizona, Tucson, Arizona
| |
Collapse
|
5
|
A Review of Radiomics in Predicting Therapeutic Response in Colorectal Liver Metastases: From Traditional to Artificial Intelligence Techniques. Healthcare (Basel) 2022; 10:healthcare10102075. [DOI: 10.3390/healthcare10102075] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2022] [Revised: 10/12/2022] [Accepted: 10/13/2022] [Indexed: 11/17/2022] Open
Abstract
An early evaluation of colorectal cancer liver metastasis (CRCLM) is crucial in determining treatment options that ultimately affect patient survival rates and outcomes. Radiomics (quantitative imaging features) have recently gained popularity in diagnostic and therapeutic strategies. Despite this, radiomics faces many challenges and limitations. This study sheds light on these limitations by reviewing the studies that used radiomics to predict therapeutic response in CRCLM. Despite radiomics’ potential to enhance clinical decision-making, it lacks standardization. According to the results of this study, the instability of radiomics quantification is caused by changes in CT scan parameters used to obtain CT scans, lesion segmentation methods used for contouring liver metastases, feature extraction methods, and dataset size used for experimentation and validation. Accordingly, the study recommends combining radiomics with deep learning to improve prediction accuracy.
Collapse
|
6
|
Wei L, Cui C, Xu J, Kaza R, El Naqa I, Dewaraja YK. Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics. EJNMMI Phys 2020; 7:74. [PMID: 33296050 PMCID: PMC7726084 DOI: 10.1186/s40658-020-00340-9] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2020] [Accepted: 11/24/2020] [Indexed: 12/14/2022] Open
Abstract
Purpose To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy 90Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies Methods Given the noisy nature of 90Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, 90Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome. Results The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority. Conclusion We have developed new lesion-level response and progression models using textural radiomics features, derived from 90Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption. Supplementary Information Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.
Collapse
Affiliation(s)
- Lise Wei
- Applied Physics Program, University of Michigan, Ann Arbor, MI, USA
| | - Can Cui
- Department of Electrical Engineering, University of Michigan, Ann Arbor, MI, USA
| | - Jiarui Xu
- Department of Electrical Engineering, University of Michigan, Ann Arbor, MI, USA
| | - Ravi Kaza
- Department of Radiology, University of Michigan, Ann Arbor, MI, USA
| | - Issam El Naqa
- Applied Physics Program, University of Michigan, Ann Arbor, MI, USA.,Department of Radiation Oncology, University of Michigan, Ann Arbor, MI, USA.,Machine Learning Department, Moffitt Cancer Center, Tampa, FL, USA
| | - Yuni K Dewaraja
- Department of Radiology, University of Michigan, Ann Arbor, MI, USA.
| |
Collapse
|
7
|
Ponnoprat D, Inkeaw P, Chaijaruwanich J, Traisathit P, Sripan P, Inmutto N, Na Chiangmai W, Pongnikorn D, Chitapanarux I. Classification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma based on multi-phase CT scans. Med Biol Eng Comput 2020; 58:2497-2515. [PMID: 32794015 DOI: 10.1007/s11517-020-02229-2] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Accepted: 07/07/2020] [Indexed: 02/07/2023]
Abstract
Liver and bile duct cancers are leading causes of worldwide cancer death. The most common ones are hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC). Influencing factors and prognosis of HCC and ICC are different. Precise classification of these two liver cancers is essential for treatment and prevention plans. The aim of this study is to develop a machine-based method that differentiates between the two types of liver cancers from multi-phase abdominal computerized tomography (CT) scans. The proposed method consists of two major steps. In the first step, the liver is segmented from the original images using a convolutional neural network model, together with task-specific pre-processing and post-processing techniques. In the second step, by looking at the intensity histograms of the segmented images, we extract features from regions that are discriminating between HCC and ICC, and use them as an input for classification using support vector machine model. By testing on a dataset of labeled multi-phase CT scans provided by Maharaj Nakorn Chiang Mai Hospital, Thailand, we have obtained 88% in classification accuracy. Our proposed method has a great potential in helping radiologists diagnosing liver cancer.
Collapse
Affiliation(s)
- Donlapark Ponnoprat
- Data Science Research Center, Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Papangkorn Inkeaw
- Advanced Research Center for Computational Simulation, Chiang Mai University, Chiang Mai, 50200, Thailand.
| | - Jeerayut Chaijaruwanich
- Data Science Research Center, Department of Computer Science, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Patrinee Traisathit
- Data Science Research Center, Department of Statistics, Faculty of Science, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Patumrat Sripan
- Research Institute for Health Sciences, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Nakarin Inmutto
- Department of Radiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Wittanee Na Chiangmai
- Department of Radiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| | - Donsuk Pongnikorn
- Cancer Registry Unit, Lampang Cancer Hospital, Lampang, 52000, Thailand
| | - Imjai Chitapanarux
- Department of Radiology, Faculty of Medicine, Chiang Mai University, Chiang Mai, 50200, Thailand
| |
Collapse
|
8
|
Oliveira S, Thomas S, Dos Santos CLG, Berdeguez MBT, de Sa LV, de Souza SAL. Outpatient treatment for haemophilic arthropathy with radiosynovectomy: Radiation dose to family members. Haemophilia 2019; 25:509-513. [PMID: 30866133 DOI: 10.1111/hae.13710] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2018] [Revised: 10/15/2018] [Accepted: 01/28/2019] [Indexed: 11/30/2022]
Abstract
One of the key features of good practice in medicine is the doctor-patient communication. Radiation protection standards for radiosynovectomy (RS) is limited. Yttrium-90 is a beta-emitting radioisotope used in RS to treat joint pain from haemophilic arthritis. ICRP 94 states that if a patient is treated with up to 200 MBq, there is no need for further precautions when it comes to public exposure, however, activities can go up to 370 MBq in RS for the knee. This study analysed 119 family members' safety (16.7% pregnant women). The ambient dose equivalent rate was measured within four distances. A survey was carried analysing risk groups and time spent next to patients. Results showed that family members should be advised to remain at 1.0 m from the patient to decrease accumulated dose by 97.6%. The dose per activity factors estimated in this study is also a useful tool during the risk assessment and doctor/patient communication. Pamphlets were distributed with radiation protection recommendations. Ambient dose equivalent was low enough to show that RS is a safe procedure for family members, which is essential to promote adherence to RS in countries where it is needed but not performed due to lack of information on radiation safety.
Collapse
Affiliation(s)
- Susie Oliveira
- Radiology Departament, Clementino Fraga Filho University Hospital, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Sylvia Thomas
- Nuclear Medicine Department, Clementino Fraga Filho University Hospital, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Clara Lorena Glória Dos Santos
- Nuclear Medicine Department, Clementino Fraga Filho University Hospital, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Mirta Barbara Torres Berdeguez
- Nuclear Engineering Department, Alberto Luiz Coimbra Institute of Post Graduation and Engineering Research, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| | - Lidia Vasconcellos de Sa
- Medical Physics Department, Radiation Protection and Dosimetry Institute, Rio de Janeiro, Brazil
| | - Sergio Augusto Lopes de Souza
- Radiology Departament, Clementino Fraga Filho University Hospital, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil
| |
Collapse
|
9
|
Suo ST, Zhuang ZG, Cao MQ, Qian LJ, Wang X, Gao RL, Fan Y, Xu JR. Differentiation of pyogenic hepatic abscesses from malignant mimickers using multislice-based texture acquired from contrast-enhanced computed tomography. Hepatobiliary Pancreat Dis Int 2016; 15:391-8. [PMID: 27498579 DOI: 10.1016/s1499-3872(15)60031-5] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Abstract
BACKGROUND Pyogenic hepatic abscess may mimic primary or secondary carcinoma of the liver on contrast-enhanced computed tomography (CECT). The present study was to explore the usefulness of the analysis of multislice-based texture acquired from CECT in the differentiation between pyogenic hepatic abscesses and malignant mimickers. METHODS This retrospective study included 25 abscesses in 20 patients and 33 tumors in 26 subjects who underwent CECT. To make comparison, we also enrolled 19 patients with hepatic single simple cyst. The images from CECT were analyzed using a Laplacian of Gaussian band-pass filter (5 filter levels with sigma weighting ranging from 1.0 to 2.5). We also quantified the uniformity, entropy, kurtosis and skewness of the multislice-based texture at different sigma weightings. Statistical significance for these parameters was tested with one-way ANOVA followed by Tukey honestly significant difference (HSD) test. Diagnostic performance was evaluated using the receiver operating characteristic (ROC) curve analysis. RESULTS There were significant differences in entropy and uniformity at all sigma weightings (P<0.001) among hepatic abscesses, malignant mimickers and simple cysts. The significant difference in kurtosis and skewness was shown at sigma 1.8 and 2.0 weightings (P=0.002-0.006). Tukey HSD test showed that the abscesses had a significantly higher entropy and lower uniformity compared with malignant mimickers (P=0.000-0.004). Entropy (at a sigma 2.0 weighting) had the largest area under the ROC curve (0.888) in differentiating abscesses from malignant mimickers, with a sensitivity of 81.8% and a specificity of 88.0% when the cutoff value was set to 3.64. CONCLUSION Multislice-based texture analysis may be useful for differentiating pyogenic hepatic abscesses from malignant mimickers.
Collapse
Affiliation(s)
- Shi-Teng Suo
- Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai 200127, China.
| | | | | | | | | | | | | | | |
Collapse
|
10
|
Rao SX, Lambregts DM, Schnerr RS, Beckers RC, Maas M, Albarello F, Riedl RG, Dejong CH, Martens MH, Heijnen LA, Backes WH, Beets GL, Zeng MS, Beets-Tan RG. CT texture analysis in colorectal liver metastases: A better way than size and volume measurements to assess response to chemotherapy? United European Gastroenterol J 2015; 4:257-63. [PMID: 27087955 DOI: 10.1177/2050640615601603] [Citation(s) in RCA: 88] [Impact Index Per Article: 9.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/18/2015] [Accepted: 07/27/2015] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Response Evaluation Criteria In Solid Tumors (RECIST) are known to have limitations in assessing the response of colorectal liver metastases (CRLMs) to chemotherapy. OBJECTIVE The objective of this article is to compare CT texture analysis to RECIST-based size measurements and tumor volumetry for response assessment of CRLMs to chemotherapy. METHODS Twenty-one patients with CRLMs underwent CT pre- and post-chemotherapy. Texture parameters mean intensity (M), entropy (E) and uniformity (U) were assessed for the largest metastatic lesion using different filter values (0.0 = no/0.5 = fine/1.5 = medium/2.5 = coarse filtration). Total volume (cm(3)) of all metastatic lesions and the largest size of one to two lesions (according to RECIST 1.1) were determined. Potential predictive parameters to differentiate good responders (n = 9; histological TRG 1-2) from poor responders (n = 12; TRG 3-5) were identified by univariable logistic regression analysis and subsequently tested in multivariable logistic regression analysis. Diagnostic odds ratios were recorded. RESULTS The best predictive texture parameters were Δuniformity and Δentropy (without filtration). Odds ratios for Δuniformity and Δentropy in the multivariable analyses were 0.95 and 1.34, respectively. Pre- and post-treatment texture parameters, as well as the various size and volume measures, were not significant predictors. Odds ratios for Δsize and Δvolume in the univariable logistic regression were 1.08 and 1.05, respectively. CONCLUSIONS Relative differences in CT texture occurring after treatment hold promise to assess the pathologic response to chemotherapy in patients with CRLMs and may be better predictors of response than changes in lesion size or volume.
Collapse
Affiliation(s)
- Sheng-Xiang Rao
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands; Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Doenja Mj Lambregts
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Roald S Schnerr
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Rianne Cj Beckers
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands; Department of Surgery, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Monique Maas
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Fabrizio Albarello
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands; Department of Radiology, S. Anna Hospital, University of Ferrara, Ferrara, Italy
| | - Robert G Riedl
- Department of Pathology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Cornelis Hc Dejong
- Department of Surgery, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Milou H Martens
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands; Department of Surgery, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Luc A Heijnen
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands; Department of Surgery, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Walter H Backes
- Department of Radiology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Geerard L Beets
- Department of Surgery, The Netherlands Cancer Institute, Amsterdam, The Netherlands; Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Meng-Su Zeng
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Regina Gh Beets-Tan
- Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands; Maastricht University Medical Centre, Maastricht, The Netherlands
| |
Collapse
|
11
|
False Discovery Rates in PET and CT Studies with Texture Features: A Systematic Review. PLoS One 2015; 10:e0124165. [PMID: 25938522 PMCID: PMC4418696 DOI: 10.1371/journal.pone.0124165] [Citation(s) in RCA: 248] [Impact Index Per Article: 27.6] [Reference Citation Analysis] [Abstract] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2014] [Accepted: 03/13/2015] [Indexed: 11/28/2022] Open
Abstract
Purpose A number of recent publications have proposed that a family of image-derived indices, called texture features, can predict clinical outcome in patients with cancer. However, the investigation of multiple indices on a single data set can lead to significant inflation of type-I errors. We report a systematic review of the type-I error inflation in such studies and review the evidence regarding associations between patient outcome and texture features derived from positron emission tomography (PET) or computed tomography (CT) images. Methods For study identification PubMed and Scopus were searched (1/2000–9/2013) using combinations of the keywords texture, prognostic, predictive and cancer. Studies were divided into three categories according to the sources of the type-I error inflation and the use or not of an independent validation dataset. For each study, the true type-I error probability and the adjusted level of significance were estimated using the optimum cut-off approach correction, and the Benjamini-Hochberg method. To demonstrate explicitly the variable selection bias in these studies, we re-analyzed data from one of the published studies, but using 100 random variables substituted for the original image-derived indices. The significance of the random variables as potential predictors of outcome was examined using the analysis methods used in the identified studies. Results Fifteen studies were identified. After applying appropriate statistical corrections, an average type-I error probability of 76% (range: 34–99%) was estimated with the majority of published results not reaching statistical significance. Only 3/15 studies used a validation dataset. For the 100 random variables examined, 10% proved to be significant predictors of survival when subjected to ROC and multiple hypothesis testing analysis. Conclusions We found insufficient evidence to support a relationship between PET or CT texture features and patient survival. Further fit for purpose validation of these image-derived biomarkers should be supported by appropriate biological and statistical evidence before their association with patient outcome is investigated in prospective studies.
Collapse
|
12
|
Alic L, Niessen WJ, Veenland JF. Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review. PLoS One 2014; 9:e110300. [PMID: 25330171 PMCID: PMC4203782 DOI: 10.1371/journal.pone.0110300] [Citation(s) in RCA: 110] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2014] [Accepted: 09/15/2014] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice. METHODOLOGY The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared. PRINCIPAL FINDINGS Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description. CONCLUSIONS In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.
Collapse
Affiliation(s)
- Lejla Alic
- Biomedical Imaging Group Rotterdam, Department of Radiology and Medical Informatics, Erasmus Medical Center Rotterdam, Rotterdam, The Netherlands
- Department of Intelligent Imaging, Netherlands Organization for Applied Scientific Research (TNO), The Hague, The Netherlands
| | - Wiro J. Niessen
- Biomedical Imaging Group Rotterdam, Department of Radiology and Medical Informatics, Erasmus Medical Center Rotterdam, Rotterdam, The Netherlands
- Imaging Physics, Faculty of Applied Sciences, Delft University of Technology, Delft, The Netherlands
| | - Jifke F. Veenland
- Biomedical Imaging Group Rotterdam, Department of Radiology and Medical Informatics, Erasmus Medical Center Rotterdam, Rotterdam, The Netherlands
| |
Collapse
|
13
|
Tsunoyama T, Pham TD, Fujita T, Sakamoto T. Identification of intestinal wall abnormalities and ischemia by modeling spatial uncertainty in computed tomography imaging findings. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2014; 117:30-39. [PMID: 24938748 DOI: 10.1016/j.cmpb.2014.05.003] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/24/2014] [Revised: 05/07/2014] [Accepted: 05/07/2014] [Indexed: 06/03/2023]
Abstract
Intestinal abnormalities and ischemia are medical conditions in which inflammation and injury of the intestine are caused by inadequate blood supply. Acute ischemia of the small bowel can be life-threatening. Computed tomography (CT) is currently a gold standard for the diagnosis of acute intestinal ischemia in the emergency department. However, the assessment of the diagnostic performance of CT findings in the detection of intestinal abnormalities and ischemia has been a difficult task for both radiologists and surgeons. Little effort has been found in developing computerized systems for the automated identification of these types of complex gastrointestinal disorders. In this paper, a geostatistical mapping of spatial uncertainty in CT scans is introduced for medical image feature extraction, which can be effectively applied for diagnostic detection of intestinal abnormalities and ischemia from control patterns. Experimental results obtained from the analysis of clinical data suggest the usefulness of the proposed uncertainty mapping model.
Collapse
Affiliation(s)
- Taichiro Tsunoyama
- School of Medicine, Department of Emergency Medicine, Trauma and Resuscitation Center, Teikyo University, Tokyo 173-8606, Japan.
| | - Tuan D Pham
- Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu, Aizu-Wakamatsu, Fukushima 965-8580, Japan.
| | - Takashi Fujita
- School of Medicine, Department of Emergency Medicine, Trauma and Resuscitation Center, Teikyo University, Tokyo 173-8606, Japan.
| | - Tetsuya Sakamoto
- School of Medicine, Department of Emergency Medicine, Trauma and Resuscitation Center, Teikyo University, Tokyo 173-8606, Japan.
| |
Collapse
|
14
|
|
15
|
Pham TD. Geostatistical Entropy for Texture Analysis: An Indicator Kriging Approach. INT J INTELL SYST 2013. [DOI: 10.1002/int.21639] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/17/2023]
Affiliation(s)
- Tuan D. Pham
- Aizu Research Cluster for Medical Engineering and Informatics; Research Center for Advanced Information Science and Technology, The University of Aizu; Aizuwakamatsu Fukushima 965-8580 Japan
| |
Collapse
|