A study on using texture analysis methods for identifying lobar fissure regions in isotropic CT images

Radiomics-Based Image Phenotyping of Kidney Apparent Diffusion Coefficient Maps: Preliminary Feasibility & Efficacy

Given the central role of interstitial fibrosis in disease progression in chronic kidney disease (CKD), a role for diffusion-weighted MRI has been pursued. We evaluated the feasibility and preliminary efficacy of using radiomic features to phenotype apparent diffusion coefficient (ADC) maps and hence to the clinical classification(s) of the participants. The study involved 40 individuals (10 healthy and 30 with CKD (eGFR < 60 mL/min/1.73 m2)). Machine learning methods, such as hierarchical clustering and logistic regression, were used. Clustering resulted in the identification of two clusters, one including all individuals with CKD (n = 17), while the second one included all the healthy volunteers (n = 10) and the remaining individuals with CKD (n = 13), resulting in 100% specificity. Logistic regression identified five radiomic features to classify participants as with CKD vs. healthy volunteers, with a sensitivity and specificity of 93% and 70%, respectively, and an AUC of 0.95. Similarly, four radiomic features were able to classify participants as rapid vs. non-rapid CKD progressors among the 30 individuals with CKD, with a sensitivity and specificity of 71% and 43%, respectively, and an AUC of 0.75. These promising preliminary data should support future studies with larger numbers of participants with varied disease severity and etiologies to improve performance.

Design and fabrication of heterogeneous lung nodule phantoms for assessing the accuracy and variability of measured texture radiomics features in CT

We aimed to design and fabricate synthetic lung nodules with patient-informed internal heterogeneity to assess the variability and accuracy of measured texture features in CT. To that end, 190 lung nodules from a publicly available database of chest CT images (Lung Image Database Consortium) were selected based on size ( > 3    mm ) and malignancy. The texture features of the nodules were used to train a statistical texture synthesis model based on clustered lumpy background. The model parameters were ascertained based on a genetic optimization of a Mahalanobis distance objective function. The resulting texture model defined internal heterogeneity within 24 anthropomorphic lesion models which were subsequently fabricated into physical phantoms using a multimaterial three-dimensional (3-D) printer. The 3-D-printed lesions were imbedded in an anthropomorphic chest phantom and imaged with a clinical scanner using different acquisition parameters including slice thickness, dose level, and reconstruction kernel. The imaged lesions were analyzed in terms of texture features to ascertain the impact of CT imaging on lesion texture quantification. The texture modeling method produced lesion models with low and stable Mahalanobis distance between real and synthetic textures. The virtual lesions were successfully printed into 3-D phantoms. The accuracy and variability of the measured features extracted from the CT images of the phantoms showed notable influence from the imaging acquisition parameters with contrast, energy, and texture entropy exhibiting most sensitivity in terms of accuracy, and contrast, dissimilarity, and texture entropy most variability. Thinner slice thicknesses yielded more accurate and edge reconstruction kernels more stable results. We conclude that printed textured models of lesions can be developed using a method that can target and minimize the mathematical distance between real and synthetic lesions. The synthetic lesions can be used as the basis to investigate how CT imaging conditions might affect radiomics features derived from CT images.

Prediction of fragmentation of kidney stones: A statistical approach from NCCT images

INTRODUCTION

We sought to develop a system to predict the fragmentation of stones using non-contrast computed tomography (NCCT) image analysis of patients with renal stone disease.

METHODS

The features corresponding to first order statistical (FOS) method were extracted from the region of interest in the NCCT scan image of patients undergoing extracorporeal shockwave lithotripsy (ESWL) treatment and the breakability was predicted using neural network.

RESULTS

When mean was considered as the feature, the results indicated that the model developed for prediction had sensitivity of 80.7% in true positive (TP) cases. The percent accuracy in identifying correctly the TP and true negative (TN) cases was 90%. TN cases were identified with a specificity of 98.4%.

CONCLUSIONS

Application of statistical methods and training the neural network system will enable accurate prediction of the fragmentation and outcome of ESWL treatment.

Identification of lobar fissures in pathological lungs

Identification of lobar fissures in human lungs is a non-trivial task due to their variable shape and appearance, along with the low contrast and high noise in computed tomographic (CT) images. Pathologies in the lungs can further complicate this identification by deforming and/or disrupting the lobar fissures. Current algorithms rely on the general anatomy of the lungs to find fissures affected by pathologies. This can be unreliable as deformations and/or disruptions of these fissures will alter the general lung anatomy. To overcome this, we developed an algorithm with the following novelties: (1) a new application of neural network based texture analysis to generalize fissure regions; and (2) a new method of fissure surface identification. We tested our algorithm on CT image stacks from 8 anonymous patients with pathological lungs. Compared to manually segmented fissures, our algorithm produced an average mean difference of 0.71 mm and 0.68 mm for identifying the left and right oblique fissures, respectively. Using a 3-mm percentile measure, the algorithm yielded an average accuracy of 86.8% for the left oblique fissure with a mean worst-case error of 3.18 mm. For the right oblique fissure, the algorithm produced an accuracy of 88.8% with a mean worst-case error of 3.13 mm. The above results show feasibility of using our algorithm for identifying fissures in pathological lungs.