Using Intratumor Heterogeneity of Immunohistochemistry Biomarkers to Classify Laryngeal and Hypopharyngeal Tumors Based on Histologic Features

Haralick texture features are used to quantify the spatial distribution of signal intensities within an image. In this study, the heterogeneity of proliferation (Ki-67 expression) and immune cells (CD45 expression) within tumors was quantified and used to classify histologic characteristics of larynx and hypopharynx carcinomas. Of 21 laryngectomy specimens, 74 whole-mount tumor slides were scored on histologic characteristics. Ki-67 and CD45 immunohistochemistry was performed, and all sections were digitized. The tumor area was annotated in QuPath. Haralick features independent of the diaminobenzidine intensity were extracted from the isolated diaminobenzidine signal to quantify intratumor heterogeneity. Haralick features from both Ki-67 and CD45 were used as input for a principal component analysis. A linear support vector machine was fitted to the first 4 principal components for classification and validated with a leave-one-patient-out cross-validation method. Significant differences in individual Haralick features were found between cohesive and noncohesive tumors for CD45 (angular second motion: P =.03, inverse difference moment: P =.009, and entropy: P =.02) and between the larynx and hypopharynx tumors for both CD45 (angular second motion: P =.03, inverse difference moment: P =.007, and entropy: P =.005) and Ki-67 (correlation: P =.003). Therefore, these features were used for classification. The linear classifier resulted in a classification accuracy of 85% for site of origin and 81% for growth pattern. A leave-one-patient-out cross-validation resulted in an error rate of 0.27 and 0.35 for both classifiers, respectively. In conclusion, we show a method to quantify intratumor heterogeneity of immunohistochemistry biomarkers using Haralick features. This study also shows the feasibility of using these features to classify tumors by histologic characteristics. The classifiers created in this study are a proof of concept because more data are needed to create robust classifiers, but the method shows potential for automated tumor classification.

Assessment of Intratumor Heterogeneity in Parametric Dynamic Contrast-Enhanced MR Images: A Comparative Study of Novel and Established Methods

Intratumor heterogeneity is associated with aggressive disease and poor survival rates in several types of cancer. A novel method for assessing intratumor heterogeneity in medical images, named the spatial gradient method, has been developed in our laboratory. In this study, we measure intratumor heterogeneity in K^trans maps derived by dynamic contrast-enhanced magnetic resonance imaging using the spatial gradient method, and we compare the performance of the novel method with that of histogram analyses and texture analyses using the Haralick method. K^trans maps of 58 untreated and sunitinib-treated pancreatic ductal adenocaricoma (PDAC) xenografts from two PDAC models were investigated. Intratumor heterogeneity parameters derived by the spatial gradient method were sensitive to tumor line differences as well as sunitinib-induced changes in intratumor heterogeneity. Furthermore, the parameters provided additional information to the median value and were not severely affected by imaging noise. The parameters derived by histogram analyses were insensitive to spatial heterogeneity and were strongly correlated to the median value, and the Haralick features were severely influenced by imaging noise and did not differentiate between untreated and sunitinib-treated tumors. The spatial gradient method was superior to histogram analyses and Haralick features for assessing intratumor heterogeneity in K^trans maps of untreated and sunitinib-treated PDAC xenografts, and can possibly be used to assess intratumor heterogeneity in other medical images and to evaluate effects of other treatments as well.

Texture Analysis of F-18 Fluciclovine PET/CT to Predict Biochemically Recurrent Prostate Cancer: Initial Results

Predicting biochemical recurrence of prostate cancer is imperative for initiating early treatment, which can improve the outcome of cancer treatment. However, because of inter- and intrareader variability in interpretation of F-18 fluciclovine positron emission tomography/computed tomography (PET/CT), it is difficult to reliably discern between necrotic tissue owing to radiation therapy and tumor tissue. Our goal is to develop a computational methodology using Haralick texture analysis that can be used as an adjunct tool to improve and standardize the interpretation of F-18 fluciclovine PET/CT to identify biochemical recurrence of prostate cancer. Four main textural features were chosen by variable selection procedure using least absolute shrinkage and selection operator logistic regression and bootstrapping, and then included as predictors in subsequent logistic ridge regression model for prediction (n = 28). Age at prostatectomy, prostate-specific antigen (PSA) level before the PET/CT imaging, and number of days between the prostate-specific antigen measurement and PET/CT imaging were also included in the prediction model. The overfitting-corrected area under the curve and Brier score of the proposed model were 0.94 (95% CI: 0.81, 1.00) and 0.12 (95% CI: 0.03, 0.23), respectively. Compared with a model with textural features (TI model) and that with only clinical information (CI model), the proposed model achieved 2% and 32% increase in AUC and 8% and 48% reduction in Brier score, respectively. Combining Haralick textural features based on the PET/CT imaging data with clinical information shows a high potential of enhanced prediction of the biochemical recurrence of prostate cancer.

Assessment of internal refractive index profile of stochastically inhomogeneous nuclear models via analysis of two-dimensional optical scattering patterns

SIGNIFICANCE

Optical scattering signals obtained from tissue constituents contain a wealth of structural information. Conventional intensity features, however, are mostly dictated by the overall morphology and mean refractive index of these constituents, making it very difficult to exclusively sense internal refractive index fluctuations.

AIM

We perform a systematic analysis to elucidate how changes in internal refractive index profile of cell nuclei can best be detected via optical scattering.

APPROACH

We construct stochastically inhomogeneous nuclear models and numerically simulate their azimuth-resolved scattering patterns. We then process these two-dimensional patterns with the goal of identifying features that directly point to subnuclear structure.

RESULTS

Azimuth-dependent intensity variations over the side scattering range provide significant insights into subnuclear refractive index profile. A particular feature we refer to as contrast ratio is observed to be highly sensitive to the length scale and extent of refractive index fluctuations; further, this feature is not susceptible to changes in the overall size and mean refractive index of nuclei, thereby allowing for selective tracking of subnuclear structure that can be linked to chromatin distribution.

CONCLUSIONS

Our analysis will potentially pave the way for scattering-based assessment of chromatin reorganization that is considered to be a key hallmark of precancer progression.

A Method for the Assessment of Textile Pilling Tendency Using Optical Coherence Tomography

Pilling is caused by friction pulling and fuzzing the fibers of a material. Pilling is normally evaluated by visually counting the pills on a flat fabric surface. Here, we propose an objective method of pilling assessment, based on the textural characteristics of the fabric shown in optical coherence tomography (OCT) images. The pilling layer is first identified above the fabric surface. The percentage of protruding fiber pixels and Haralick’s textural features are then used as pilling descriptors. Principal component analysis (PCA) is employed to select strongly correlated features and then reduce the feature space dimensionality. The first principal component is used to quantify the intensity of fabric pilling. The results of experimental studies confirm that this method can determine the intensity of pilling. Unlike traditional methods of pilling assessment, it can also detect pilling in its early stages. The approach could help to prevent overestimation of the degree of pilling, thereby avoiding unnecessary procedures, such as mechanical removal of entangled fibers. However, the research covered a narrow group of fabrics and wider conclusions about the usefulness and limitations of this method can be drawn after examining fabrics of different thickness and chemical composition of fibers.

Application of Haralick texture features in brain [18F]-florbetapir positron emission tomography without reference region normalization

Objectives

Semi-quantitative image analysis methods in Alzheimer’s Disease (AD) require normalization of positron emission tomography (PET) images. However, recent studies have found variabilities associated with reference region selection of amyloid PET images. Haralick features (HFs) generated from the Gray Level Co-occurrence Matrix (GLCM) quantify spatial characteristics of amyloid PET radiotracer uptake without the need for intensity normalization. The objective of this study is to calculate several HFs in different diagnostic groups and determine the group differences.

Methods

All image and metadata were acquired through the Alzheimer’s Disease Neuroimaging Initiative database. Subjects were grouped in three ways: by clinical diagnosis, by APOE e4 allele, and by Alzheimer’s Disease Assessment Scale-cognitive subscale (ADAS-Cog) score. Several GLCM matrices were calculated for different direction and distances (1–4 mm) from multiple regions on PET images. The HFs, contrast, correlation, dissimilarity, energy, entropy, and homogeneity, were calculated from these GLCMs. Wilcoxon tests and Student t-tests were performed on Haralick features and standardized uptake value ratio (SUVR) values, respectively, to determine group differences. In addition to statistical testing, receiver operating characteristic (ROC) curves were generated to determine the discrimination performance of the selected regional HFs and the SUVR values.

Results

Preliminary results from statistical testing indicate that HFs were capable of distinguishing groups at baseline and follow-up (false discovery rate corrected p<0.05) in particular regions at much higher occurrences than SUVR (81 of 252). Conversely, we observed nearly no significant differences between all groups within ROIs at baseline or follow-up utilizing SUVR. From the ROC analysis, we found that the Energy and Entropy offered the best performance to distinguish Normal versus mild cognitive impairment and ADAS-Cog negative versus ADAS-Cog positive groups.

Conclusion

These results suggest that this technique could improve subject stratification in AD drug trials and help to evaluate the disease progression and treatment effects longitudinally without the disadvantages associated with intensity normalization.

Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm

PURPOSE

Fatty liver disease (FLD) is one of the most common diseases in liver. Early detection can improve the prognosis considerably. Using ultrasound for FLD detection is highly desirable due to its non-radiation nature, low cost and easy use. However, the results can be slow and ambiguous due to manual detection. The lack of computer trained systems leads to low image quality and inefficient disease classification. Thus, the current study proposes novel, accurate and reliable detection system for the FLD using computer-based training system.

MATERIALS AND METHODS

One hundred twenty-four ultrasound sample images were selected retrospectively from a database of 62 patients consisting of normal and cancerous. The proposed training system was generated offline parameters using training liver image database. The classifier applied transformation parameters to an online system in order to facilitate real-time detection during the ultrasound scan. The system utilized six sets of features (a total of 128 features), namely Haralick, basic geometric, Fourier transform, discrete cosine transform, Gupta transform and Gabor transform. These features were extracted for both offline training and online testing. Levenberg-Marquardt back propagation network (BPN) classifier was used to classify the liver disease into normal and abnormal categories.

RESULTS

Random partitioning approach was adapted to evaluate the classifier performance and compute its accuracy. Utilizing all the six sets of 128 features, the computer aided diagnosis (CAD) system achieved classification accuracy of 97.58%. Furthermore, the four performance metrics consisting of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) realized 98.08%, 97.22%, 96.23%, and 98.59%, respectively.

CONCLUSION

The proposed system was successfully able to detect and classify the FLD. Furthermore, the proposed system was benchmarked against previous methods. The comparison established an advanced set of features in the Levenberg-Marquardt back propagation network reports a significant improvement compared to the existing techniques.

Analysis of framelets for breast cancer diagnosis

Breast cancer is the second threatening tumor among the women. The effective way of reducing breast cancer is its early detection which helps to improve the diagnosing process. Digital mammography plays a significant role in mammogram screening at earlier stage of breast carcinoma. Even though, it is very difficult to find accurate abnormality in prevalent screening by radiologists. But the possibility of precise breast cancer screening is encouraged by predicting the accurate type of abnormality through Computer Aided Diagnosis (CAD) systems. The two most important indicators of breast malignancy are microcalcifications and masses. In this study, framelet transform, a multiresolutional analysis is investigated for the classification of the above mentioned two indicators. The statistical and co-occurrence features are extracted from the framelet decomposed mammograms with different resolution levels and support vector machine is employed for classification with k-fold cross validation. This system achieves 94.82% and 100% accuracy in normal/abnormal classification (stage I) and benign/malignant classification (stage II) of mass classification system and 98.57% and 100% for microcalcification system when using the MIAS database.

Advances in quantitative muscle ultrasonography using texture analysis of ultrasound images

Musculoskeletal ultrasound imaging can be used to investigate the skeletal muscle structure in terms of architecture (thickness, cross-sectional area, fascicle length and fascicle pennation angle) and texture. Gray-scale analysis is commonly used to characterize transverse scans of the muscle. Gray mean value is used to distinguish between normal and pathologic muscles, but it depends on the image acquisition system and its settings. In this study, quantitative ultrasonography was performed on five muscles (biceps brachii, vastus lateralis, rectus femoris, medial gastrocnemius and tibialis anterior) of 20 healthy patients (10 women, 10 men) to assess the characterization performance of higher-order texture descriptors to differentiate genders and muscle types. A total of 53 features (7 first-order descriptors, 24 Haralick features, 20 Galloway features and 2 local binary pattern features) were extracted from each muscle region of interest (ROI) and were used to perform the multivariate linear regression analysis (MANOVA). Our results show that first-order descriptors, Haralick features (energy, entropy and correlation measured along different angles) and local binary pattern (LBP) energy and entropy were highly linked to the gender, whereas Haralick entropy and symmetry, Galloway texture descriptors and LBP entropy helped to distinguish muscle types. Hence, the combination of first-order and higher-order texture descriptors (Haralick, Galloway and LBP) can be used to discriminate gender and muscle types. Therefore, multi-texture analysis may be useful to investigate muscle damage and myopathic disorders.