Dataset Information

Harmonizing the pixel size in retrospective computed tomography radiomics studies.

ABSTRACT: Consistent pixel sizes are of fundamental importance for assessing texture features that relate intensity and spatial information in radiomics studies. To correct for the effects of variable pixel sizes, we combined image resampling with Butterworth filtering in the frequency domain and tested the correction on computed tomography (CT) scans of lung cancer patients reconstructed 5 times with pixel sizes varying from 0.59 to 0.98 mm. One hundred fifty radiomics features were calculated for each preprocessing and field-of-view combination. Intra-patient agreement and inter-patient agreement were compared using the overall concordance correlation coefficient (OCCC). To further evaluate the corrections, hierarchical clustering was used to identify patient scans before and after correction. To assess the general applicability of the corrections, they were applied to 17 CT scans of a radiomics phantom. The reduction in the inter-scanner variability relative to non-small cell lung cancer patient scans was quantified. The variation in pixel sizes caused the intra-patient variability to be large (OCCC <95%) relative to the inter-patient variability in 79% of the features. However, with the resampling and filtering corrections, the intra-patient variability was relatively large in only 10% of the features. With the filtering correction, 8 of 8 patients were correctly clustered, in contrast to only 2 of 8 without the correction. In the phantom study, resampling and filtering the images of a rubber particle cartridge substantially reduced variability in 61% of the radiomics features and substantially increased variability in only 6% of the features. Surprisingly, resampling without filtering tended to increase the variability. In conclusion, applying a correction based on resampling and Butterworth low-pass filtering in the frequency domain effectively reduced variability in CT radiomics features caused by variations in pixel size. This correction may also reduce the variability introduced by other CT scan acquisition parameters.

SUBMITTER: Mackin D

PROVIDER: S-EPMC5608195 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Harmonizing the pixel size in retrospective computed tomography radiomics studies.

Mackin Dennis D Fave Xenia X Zhang Lifei L Yang Jinzhong J Jones A Kyle AK Ng Chaan S CS Court Laurence L

PloS one 20170921 9

Consistent pixel sizes are of fundamental importance for assessing texture features that relate intensity and spatial information in radiomics studies. To correct for the effects of variable pixel sizes, we combined image resampling with Butterworth filtering in the frequency domain and tested the correction on computed tomography (CT) scans of lung cancer patients reconstructed 5 times with pixel sizes varying from 0.59 to 0.98 mm. One hundred fifty radiomics features were calculated for each p ...[more]

PMID: 28934225

Similar Datasets

Project description:BackgroundPneumocystis jirovecii pneumonia (PCP) could be fatal to patients without human immunodeficiency virus (HIV) infection. Current diagnostic methods are either invasive or inaccurate. We aimed to establish an accurate and non-invasive radiomics-based way to identify the risk of PCP infection in non-HIV patients with computed tomography (CT) manifestation of pneumonia.MethodsThis is a retrospective study including non-HIV patients hospitalized for suspected PCP from January 2010 to December 2022 in one hospital. The patients were randomized in a 7:3 ratio into training and validation cohorts. Computed tomography (CT)-based radiomics features were extracted automatically and used to construct a radiomics model. A diagnostic model with traditional clinical and CT features was also built. The area under the curve (AUC) were calculated and used to evaluate the diagnostic performance of the models. The combination of the radiomics features and serum β-D-glucan levels was also evaluated for PCP diagnosis.ResultsA total of 140 patients (PCP: N = 61, non-PCP: N = 79) were randomized into training (N = 97) and validation (N = 43) cohorts. The radiomics model consisting of nine radiomic features performed significantly better (AUC = 0.954; 95% CI: 0.898-1.000) than the traditional model consisting of serum β-D-glucan levels (AUC = 0.752; 95% CI: 0.597-0.908) in identifying PCP (P = 0.002). The combination of radiomics features and serum β-D-glucan levels showed an accuracy of 95.8% for identifying PCP infection (positive predictive value: 95.7%, negative predictive value: 95.8%).ConclusionsRadiomics showed good diagnostic performance in differentiating PCP from other types of pneumonia in non-HIV patients. A combined diagnostic method including radiomics and serum β-D-glucan has the potential to provide an accurate and non-invasive way to identify the risk of PCP infection in non-HIV patients with CT manifestation of pneumonia.Trial registrationClinicalTrials.gov (NCT05701631).

Project description:BackgroundSerous cystic neoplasm (SCN), mucinous cystic neoplasm (MCN), and intraductal papillary mucinous neoplasm (IPMN) comprise a large proportion of pancreatic cystic neoplasms (PCNs). Patients with MCN and IPMN require surgery due to the potential of malignant transformation, whereas those with SCN require periodic surveillance. However, the differential diagnosis of patients with PCNs before treatment remains a great challenge for all surgeons. Therefore, the establishment of a reliable diagnostic tool is urgently required for the improvement of precision diagnostics.MethodsBetween February 2015 and December 2020, 143 consecutive patients with PCNs who were confirmed by postoperative pathology were retrospectively included in the study cohort, then randomized into development and test cohorts at a ratio of 7:3. The predictors of preoperative clinical-radiologic parameters were evaluated by univariate and multivariable logistic regression analyses. A total of 1,218 radiomics features were computationally extracted from the enhanced computed tomography (CT) scans of the tumor region, and a radiomics signature was established by the random forest algorithm. In the development cohort, multi- and binary-class radiomics models integrating preoperative variables and radiomics features were constructed to distinguish between the 3 types of PCNs. The receiver operating characteristic (ROC) curve and the area under the curve (AUC) were used to evaluate the predictive efficiency of the model. An independent internal test cohort was applied to validate the classification models.ResultsAll preoperative prediction models were built by integrating the radiomics signature with 13 diagnosis-related radiomics features and 3 important clinical-radiologic parameters: age, sex, and tumor diameter. The multiclass prediction model presented an overall accuracy of 0.804 in the development cohort and 0.707 in the test cohort. The binary-class prediction models displayed higher overall accuracies of 0.853, 0.866, and 0.928 in the development dataset and 0.750, 0.839, and 0.889 in the test dataset. In the test cohort, the binary-class radiomics models showed better predictive performances {AUC =0.914 [95% confidence interval (CI): 0.786 to 1.000], 0.863 (95% CI: 0.714 to 0.941), and 0.926 (95% CI: 0.824 to 1.000)} than the multiclass radiomics model [AUC =0.850 (95% CI: 0.696 to 1.000)], with a large net benefit in the decision curve analysis (DCA). The radiomics-based nomogram provided the correct predicted probability for the diagnosis of PCNs.ConclusionsThe proposed radiomics models with clinical-radiologic parameters and radiomics features help to predict the accurate diagnosis among PCNs to advance personalized medicine.

Project description:BackgroundClear cell renal cell carcinoma (ccRCC) is the most common renal cancer and it has the worst prognosis among all renal cancers. However, traditional radiological characteristics on computed tomography (CT) scans of ccRCC have been insufficient to predict the pathological grade of ccRCC before surgery.MethodsPatients with ccRCC were retrospectively enrolled into this study and were separated into two groups according to the World Health Organization (WHO)/International Society of Urological Pathology (ISUP) grading system, i.e., low-grade (Grade I and II) group and high-grade (Grade III and IV) group. Traditional CT radiological characteristics such as tumor size, pre- and post-enhancing CT densities were assessed. In addition, radiomic texture analysis based on the CT imaging of the ccRCC were also performed. A CT-based machine learning method combining the traditional radiological characteristics and radiomic features was used in the predictive modeling for differentiating the low-grade from the high-grade ccRCC. Model performance was evaluated with the receiver operating characteristic curve (ROC) analysis.ResultsA total of 264 patients with pathologically confirmed ccRCC were included in this study. In this cohort, 206 patients had the low-grade tumors and 58 had the high-grade tumors. The model built with traditional radiological characteristics achieved an area under the curve (AUC) of 0.9175 (95% CI: 0.8765-0.9585) and 0.8088 (95% CI: 0.7064-0.9113) in differentiating the low-grade from the high-grade ccRCC for the training cohort and the validation cohort respectively. The model built with the radiomic textural features yielded an AUC value of 0.8170 (95% CI: 0.7353-0.8987) and 0.8017 (95% CI: 0.6878-0.9157) for the training cohort and the validation cohort, respectively. The combined model integrating both the traditional radiological characteristics and the radiomic textural features achieved the highest efficacy, with an AUC of 0.9235 (95% CI: 0.8646-0.9824) and an AUC of 0.9099 (95% CI: 0.8324-0.9873) for the training cohort and validation cohort, respectively.ConclusionWe developed a machine learning radiomic model achieving a satisfying performance in differentiating the low-grade from the high-grade ccRCC. Our study presented a potentially useful non-invasive imaging-focused method to predict the pathological grade of renal cancers prior to surgery.

Project description:ObjectivesThe aim of this study was to precisely phenotype culprit and nonculprit lesions in myocardial infarction (MI) and lesions in stable coronary artery disease (CAD) using coronary computed tomography angiography (CTA)-based radiomic analysis.BackgroundIt remains debated whether any single coronary atherosclerotic plaque within the vulnerable patient exhibits unique morphology conferring an increased risk of clinical events.MethodsA total of 60 patients with acute MI prospectively underwent coronary CTA before invasive angiography and were matched to 60 patients with stable CAD. For all coronary lesions, high-risk plaque (HRP) characteristics were qualitatively assessed, followed by semiautomated plaque quantification and extraction of 1,103 radiomic features. Machine learning models were built to examine the additive value of radiomic features for discriminating culprit lesions over and above HRP and plaque volumes.ResultsCulprit lesions had higher mean volumes of noncalcified plaque (NCP) and low-density noncalcified plaque (LDNCP) compared with the highest-grade stenosis nonculprits and highest-grade stenosis stable CAD lesions (NCP: 138.1 mm3 vs 110.7 mm3 vs 102.7 mm3; LDNCP: 14.2 mm3 vs 9.8 mm3 vs 8.4 mm3; both Ptrend < 0.01). In multivariable linear regression adjusted for NCP and LDNCP volumes, 14.9% (164 of 1,103) of radiomic features were associated with culprits and 9.7% (107 of 1,103) were associated with the highest-grade stenosis nonculprits (critical P < 0.0007) when compared with highest-grade stenosis stable CAD lesions as reference. Hierarchical clustering of significant radiomic features identified 9 unique data clusters (latent phenotypes): 5 contained radiomic features specific to culprits, 1 contained features specific to highest-grade stenosis nonculprits, and 3 contained features associated with either lesion type. Radiomic features provided incremental value for discriminating culprit lesions when added to a machine learning model containing HRP and plaque volumes (area under the receiver-operating characteristic curve 0.86 vs 0.76; P = 0.004).ConclusionsCulprit lesions and highest-grade stenosis nonculprit lesions in MI have distinct radiomic signatures compared with lesions in stable CAD. Within the vulnerable patient may exist individual vulnerable plaques identifiable by coronary CTA-based precision phenotyping.

Dataset Information

Harmonizing the pixel size in retrospective computed tomography radiomics studies.

Publications

Harmonizing the pixel size in retrospective computed tomography radiomics studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets