3D texture analysis in renal cell carcinoma tissue image grading

Radiomic nomogram for predicting high-risk cytogenetic status in multiple myeloma based on fat-suppressed T2-weighted magnetic resonance imaging

Rationale and Objectives

Radiomics has demonstrated potential in predicting the cytogenetic status of multiple myeloma (MM). However, the role of single-sequence radiomic nomograms in predicting the high-risk cytogenetic (HRC) status of MM remains underexplored. This study aims to develop and validate radiomic nomograms based on fat-suppressed T2-weighted images (T2WI-FS) for predicting MM's HRC status, facilitating pre-treatment decision-making and prognostic assessment.

Materials and methods

A cohort of 159 MM patients was included, comprising 71 HRC and 88 non-HRC cases. Regions of interest within the most significant tumor lesions on T2WI-FS images were manually delineated, yielding 1688 features. Fourteen radiomic features were selected using 10-fold cross-validation, employing methods such as variance thresholds, Student's t-test, redundancy analysis, and least absolute shrinkage and selection operator (LASSO). Logistic regression was utilized to develop three prediction models: a clinical model (model 1), a T2WI-FS radiomic model (model 2), and a combined clinical-radiomic model (model 3). Receiver operating characteristic (ROC) curves evaluated and compared the diagnostic performance of these models. Kaplan-Meier survival analysis and log-rank tests assessed the prognostic value of the radiomic nomograms.

Results

Models 2 and 3 demonstrated significantly greater diagnostic efficacy compared to model 1 (p < 0.05). The areas under the ROC curve for models 1, 2, and 3 were as follows: training set-0.650, 0.832, and 0.846; validation set-0.702, 0.730, and 0.757, respectively. Kaplan-Meier survival analysis indicated comparable prognostic values between the radiomic nomogram and MM cytogenetic status, with log-rank test results (p < 0.05) and concordance indices of 0.651 and 0.659, respectively; z-score test results were not statistically significant (p = 0.153). Additionally, Kaplan-Meier analysis revealed that patients in the non-HRC group, low-RS group, and aged ≤ 60 years exhibited the longest overall survival, while those in the HRC group, high-RS group, and aged > 60 years demonstrated the shortest overall survival (p = 0.004, Log-rank test).

Conclusions

Radiomic nomograms are capable of predicting the HRC status in MM. The cytogenetic status, radiomics model Rad score, and age collectively influence the overall survival of MM patients. These factors potentially contribute to pre-treatment clinical decision-making and prognostic assessment.

CT-based deep learning radiomics nomogram for the prediction of pathological grade in bladder cancer: a multicenter study

BACKGROUND

To construct and assess a computed tomography (CT)-based deep learning radiomics nomogram (DLRN) for predicting the pathological grade of bladder cancer (BCa) preoperatively.

METHODS

We retrospectively enrolled 688 patients with BCa (469 in the training cohort, 219 in the external test cohort) who underwent surgical resection. We extracted handcrafted radiomics (HCR) features and deep learning (DL) features from three-phase CT images (including corticomedullary-phase [C-phase], nephrographic-phase [N-phase] and excretory-phase [E-phase]). We constructed predictive models using 11 machine learning classifiers, and we developed a DLRN by combining the radiomic signature with clinical factors. We assessed performance and clinical utility of the models with reference to the area under the curve (AUC), calibration curve, and decision curve analysis (DCA).

RESULTS

The support vector machine (SVM) classifier model based on HCR and DL combined features was the best radiomic signature, with AUC values of 0.953 and 0.943 in the training cohort and the external test cohort, respectively. The AUC values of the clinical model in the training cohort and the external test cohort were 0.752 and 0.745, respectively. DLRN performed well on both data cohorts (training cohort: AUC = 0.961; external test cohort: AUC = 0.947), and outperformed the clinical model and the optimal radiomic signature.

CONCLUSION

The proposed CT-based DLRN showed good diagnostic capability in distinguishing between high and low grade BCa.

Modified Gray-Level Haralick Texture Features for Early Detection of Diabetes Mellitus and High Cholesterol with Iris Image

Iris has specific advantages, which can record all organ conditions, body construction, and psychological disorders. Traces related to the intensity or deviation of organs caused by the disease are recorded systematically and patterned on the iris and its surroundings. The pattern that appears on the iris can be recognized by using image processing techniques. Based on the pattern in the iris image, this paper aims to provide an alternative noninvasive method for the early detection of DM and HC. In this paper, we perform detection based on iris images for two diseases, DM and HC simultaneously, by developing the invariant Haralick feature on quantized images with 256, 128, 64, 32, and 16 gray levels. The feature extraction process does early detection based on iris images. Researchers and scientists have introduced many methods, one of which is the feature extraction of the gray-level co-occurrence matrix (GLCM). Early detection based on the iris is done using the volumetric GLCM development, namely, 3D-GLCM. Based on 3D-GLCM, which is formed at a distance of d = 1 and in the direction of 0°, 45°, 90°, 135°, 180°, 225°, 270°, and 315°, it is used to calculate Haralick features and develop Haralick features which are invariant to the number of quantization gray levels. The test results show that the invariant feature with a gray level of 256 has the best identification performance. In dataset I, the accuracy value is 97.92, precision is 96.88, and recall is 95.83, while in dataset II, the accuracy value is 95.83, precision is 89.69, and recall is 91.67. The identification of DM and HC trained on invariant features showed higher accuracy than the original features.

DCE-MRI based radiomics nomogram for preoperatively differentiating combined hepatocellular-cholangiocarcinoma from mass-forming intrahepatic cholangiocarcinoma

OBJECTIVE

To establish a radiomics nomogram based on dynamic contrast-enhanced (DCE) MR images to preoperatively differentiate combined hepatocellular-cholangiocarcinoma (cHCC-CC) from mass-forming intrahepatic cholangiocarcinoma (IMCC).

METHODS

A total of 151 training cohort patients (45 cHCC-CC and 106 IMCC) and 65 validation cohort patients (19 cHCC-CC and 46 IMCC) were enrolled. Findings of clinical characteristics and MR features were analyzed. Radiomics features were extracted from the DCE-MR images. A radiomics signature was built based on radiomics features by the least absolute shrinkage and selection operator algorithm. Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical model. The radiomics signature and significant clinicoradiological variables were then incorporated into the radiomics nomogram by multivariate logistic regression analysis. Performance of the radiomics nomogram, radiomics signature, and clinical model was assessed by receiver operating characteristic and area under the curve (AUC) was compared.

RESULTS

Eleven radiomics features were selected to develop the radiomics signature. The radiomics nomogram integrating the alpha fetoprotein, background liver disease (cirrhosis or chronic hepatitis), and radiomics signature showed favorable calibration and discrimination performance with an AUC value of 0.945 in training cohort and 0.897 in validation cohort. The AUCs for the radiomics signature and clinical model were 0.848 and 0.856 in training cohort and 0.792 and 0.809 in validation cohort, respectively. The radiomics nomogram outperformed both the radiomics signature and clinical model alone (p < 0.05).

CONCLUSION

The radiomics nomogram based on DCE-MRI may provide an effective and noninvasive tool to differentiate cHCC-CC from IMCC, which could help guide treatment strategies.

KEY POINTS

• The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging is useful to preoperatively differentiate cHCC-CC from IMCC. • The radiomics nomogram showed the best performance in both training and validation cohorts for differentiating cHCC-CC from IMCC.

Magnetic resonance imaging-based radiomics signature for preoperative prediction of Ki67 expression in bladder cancer

PURPOSE

The Ki67 expression is associated with the advanced clinicopathological features and poor prognosis in bladder cancer (BCa). We aimed to develop and validate magnetic resonance imaging (MRI)-based radiomics signatures to preoperatively predict the Ki67 expression status in BCa.

METHODS AND MATERIALS

We retrospectively collected 179 BCa patients with Ki67 expression and preoperative MRI. Radiomics features were extracted from T2-weighted (T2WI) and dynamic contrast-enhancement (DCE) images. The synthetic minority over-sampling technique (SMOTE) was used to balance the minority group (low Ki67 expression group) in the training set. Minimum redundancy maximum relevance was used to identify the best features associated with Ki67 expression. Support vector machine and Least Absolute Shrinkage and Selection Operator algorithms (LASSO) were used to construct radiomics signatures in training and SMOTE-training sets, and diagnostic performance was assessed by the area under the curve (AUC) and accuracy. The decision curve analyses (DCA) and calibration curve and were used to investigate the clinical usefulness and calibration of radiomics signatures, respectively. The Kaplan-Meier test was performed to investigate the prognostic value of radiomics-predicted Ki67 expression status.

RESULTS

1218 radiomics features were extracted from T2WI and DCE images, respectively. The SMOTE-LASSO model based on nine features achieved the best predictive performance in the SMOTE-training (AUC, 0.859; accuracy, 80.3%) and validation sets (AUC, 0.819; accuracy, 81.5%) with a good calibration performance and clinical usefulness. Immunohistochemistry-based high Ki67 expression and radiomics-predicted high Ki67 expression based on the SMOTE-LASSO model were significantly associated with poor disease-free survival in training and validation sets (all P < 0.05).

CONCLUSIONS

The SMOTE-LASSO model could predict the Ki67 expression status and was associated with survival outcomes of the BCa patients, thereby may aid in clinical decision-making.

Combining Multiparametric MRI Radiomics Signature With the Vesical Imaging-Reporting and Data System (VI-RADS) Score to Preoperatively Differentiate Muscle Invasion of Bladder Cancer

Background

The treatment and prognosis for muscle-invasive bladder cancer (MIBC) and non-muscle-invasive bladder cancer (NMIBC) are different. We aimed to construct a nomogram based on the multiparametric MRI (mpMRI) radiomics signature and the Vesical Imaging-Reporting and Data System (VI-RADS) score for the preoperative differentiation of MIBC from NMIBC.

Method

The retrospective study involved 185 pathologically confirmed bladder cancer (BCa) patients (training set: 129 patients, validation set: 56 patients) who received mpMRI before surgery between August 2014 to April 2020. A total of 2,436 radiomics features were quantitatively extracted from the largest lesion located on the axial T2WI and from dynamic contrast-enhancement images. The minimum redundancy maximum relevance (mRMR) algorithm was used for feature screening. The selected features were introduced to construct radiomics signatures using three classifiers, including least absolute shrinkage and selection operator (LASSO), support vector machines (SVM) and random forest (RF) in the training set. The differentiation performances of the three classifiers were evaluated using the area under the curve (AUC) and accuracy. Univariable and multivariable logistic regression were used to develop a nomogram based on the optimal radiomics signature and clinical characteristics. The performance of the radiomics signatures and the nomogram was assessed and validated in the validation set.

Results

Compared to the RF and SVM classifiers, the LASSO classifier had the best capacity for muscle invasive status differentiation in both the training (accuracy: 90.7%, AUC: 0.934) and validation sets (accuracy: 87.5%, AUC: 0.906). Incorporating the radiomics signature and VI-RADS score, the nomogram demonstrated better discrimination and calibration both in the training set (accuracy: 93.0%, AUC: 0.970) and validation set (accuracy: 89.3%, AUC: 0.943). Decision curve analysis showed the clinical usefulness of the nomogram.

Conclusions

The mpMRI radiomics signature may be useful for the preoperative differentiation of muscle-invasive status in BCa. The proposed nomogram integrating the radiomics signature with the VI-RADS score may further increase the differentiation power and improve clinical decision making.

Label-free identification of human coronary atherosclerotic plaque based on a three-dimensional quantitative assessment of multiphoton microscopy images

The rupture of coronary atherosclerotic plaque (CAP) and the resulting intracoronary thrombosis account for most acute coronary syndromes. Thus, the early identification and risk assessment of CAP is crucial for timely medical intervention. In this study, we propose a quantitative and label-free method for human CAP identification using multiphoton microscopy (MPM) and three-dimensional (3D) image analysis techniques. By detecting the intrinsic MPM signals, the microstructures of collagen and elastin fibers within normal and CAP-lesioned human coronary artery walls were imaged. Using a 3D gray level co-occurrence matrix method and 3D weighted vector summation algorithm, quantitative indicators that characterize the spatial texture and orientation features of the fibers were extracted. We demonstrate that these indicators show superior accuracy and repeatability over 2D texture features in CAP discrimination. Furthermore, by combining the 3D microstructural indicators, a support vector machine model that classifies CAP from the normal arterial wall with an accuracy of >97% was established. In conjunction with advances in multiphoton endoscopy, the proposed method shows great potential in providing a quantitative, label-free, and real-time tool for the early identification and risk assessment of CAP in the future.

Radiomics signature on dynamic contrast-enhanced MR images: a potential imaging biomarker for prediction of microvascular invasion in mass-forming intrahepatic cholangiocarcinoma

OBJECTIVE

To develop a radiomics signature based on dynamic contrast-enhanced (DCE) MR images for preoperative prediction of microvascular invasion (MVI) in patients with mass-forming intrahepatic cholangiocarcinoma (IMCC).

METHODS

One hundred twenty-six patients with surgically resected single IMCC (34 MVI-positive and 92 MVI-negative) were enrolled and allocated to training and validation cohorts (7:3 ratio). Findings of clinical characteristics and MR features were analyzed. A radiomics signature was built on the basis of reproducible features by using the least absolute shrinkage and selection operator (LASSO) regression algorithm in the training cohort. The prediction performance of radiomics signature was evaluated by receiver operating characteristics curve (ROC) analysis. Internal validation was performed on an independent cohort containing 38 patients.

RESULTS

Larger tumor size and higher radiomics score were positively correlated with MVI in both training cohort (p < 0.001, < 0.001, respectively) and validation cohort (p = 0.008, 0.001, respectively). The radiomics signature, consisting of seven wavelet features, showed optimal prediction performance in both training (AUC = 0.873) and validation cohorts (AUC = 0.850).

CONCLUSION

A radiomics signature derived from DCE-MRI of the liver can be a reliable imaging biomarker for predicting MVI of IMCC, which could aid in tailoring treatment strategies.

KEY POINTS

• The radiomics signature based on dynamic contrast-enhanced magnetic resonance imaging can be a useful tool to preoperatively predict MVI of IMCC. • Larger tumor size is positively correlated with MVI of IMCC.

Prediction of Glioma Grades Using Deep Learning with Wavelet Radiomic Features

Gliomas are the most common primary brain tumors. They are classified into 4 grades (Grade I–II-III–IV) according to the guidelines of the World Health Organization (WHO). The accurate grading of gliomas has clinical significance for planning prognostic treatments, pre-diagnosis, monitoring and administration of chemotherapy. The purpose of this study is to develop a deep learning-based classification method using radiomic features of brain tumor glioma grades with deep neural network (DNN). The classifier was combined with the discrete wavelet transform (DWT) the powerful feature extraction tool. This study primarily focuses on the four main aspects of the radiomic workflow, namely tumor segmentation, feature extraction, analysis, and classification. We evaluated data from 121 patients with brain tumors (Grade II, n = 77; Grade III, n = 44) from The Cancer Imaging Archive, and 744 radiomic features were obtained by applying low sub-band and high sub-band 3D wavelet transform filters to the 3D tumor images. Quantitative values were statistically analyzed with MannWhitney U tests and 126 radiomic features with significant statistical properties were selected in eight different wavelet filters. Classification performances of 3D wavelet transform filter groups were measured using accuracy, sensitivity, F1 score, and specificity values using the deep learning classifier model. The proposed model was highly effective in grading gliomas with 96.15% accuracy, 94.12% precision, 100% recall, 96.97% F1 score, and 98.75% Area under the ROC curve. As a result, deep learning and feature selection techniques with wavelet transform filters can be accurately applied using the proposed method in glioma grade classification.

Effect of phase of enhancement on texture analysis in renal masses evaluated with non-contrast-enhanced, corticomedullary, and nephrographic phase-enhanced CT images

OBJECTIVE

To compare texture analysis (TA) features of solid renal masses on renal protocol (non-contrast enhanced [NECT], corticomedullary [CM], nephrographic [NG]) CT.

MATERIALS AND METHODS

A total of 177 consecutive solid renal masses (116 renal cell carcinoma [RCC]; 51 clear cell [cc], 40 papillary, 25 chromophobe, and 61 benign masses; 49 oncocytomas, 12 fat-poor angiomyolipomas) with three-phase CT between 2012 and 2017 were studied. Two blinded radiologists independently assessed tumor heterogeneity (5-point Likert scale) and segmented tumors. TA features (N = 25) were compared between groups and between phases. Accuracy (area under the curve [AUC]) for RCC versus benign and cc-RCC versus other masses was compared.

RESULTS

Subjectively, tumor heterogeneity differed between phases (p < 0.01) and between tumors within the same phase (p = 0.03 [NECT] and p < 0.01 [CM, NG]). Inter-observer agreement was moderate to substantial (intraclass correlation coefficient = 0.55-0.73). TA differed in 92.0% (23/25) features between phases (p < 0.05) except for GLNU and f6. More TA features differed significantly on CM (80.0% [20/25]) compared with NG (40.0% [10/25]) and NECT (16.0% [4/25]) (p < 0.01). For RCC versus benign, AUCs of texture features did not differ comparing CM and NG (p > 0.05), but were higher for 20% (5/25) and 28% (7/25) of features comparing CM and NG with NECT (p < 0.05). For cc-RCC versus other, 36% (9/25) and 40% (10/25) features on CM had higher AUCs compared with NECT and NG images (p < 0.05).

CONCLUSION

Texture analysis of renal masses differs, when evaluated subjectively and quantitatively, by phase of CT enhancement. The corticomedullary phase had the highest discriminatory value when comparing masses and for differentiating cc-RCC from other masses.

KEY POINTS

• Subjectively evaluated renal tumor heterogeneity on CT differs by phase of enhancement. • Quantitative CT texture analysis features in renal tumors differ by phases of enhancement with the corticomedullary phase showing the highest number and most significant differences compared with non-contrast-enhanced and nephrographic phase images. • For diagnosis of clear cell RCC, corticomedullary phase texture analysis features had improved accuracy of classification in approximately 40% of features studied compared with non-contrast-enhanced and nephrographic phase images.

Application of Gray Level co-Occurrence Matrix Algorithm for Detection of Discrete Structural Changes in Cell Nuclei After Exposure to Iron Oxide Nanoparticles and 6-Hydroxydopamine

The gray level co-occurrence matrix (GLCM) algorithm is a contemporary computational biology method which, today, is frequently used to detect small changes in texture that are not visible using conventional techniques. We demonstrate that the toxic compound 6-hydroxydopamine (6-OHDA) and iron oxide nanoparticles (IONPS) have opposite effects on GLCM features of cell nuclei. Saccharomyces cerevisiae yeast cells were treated with 6-OHDA and IONPs, and imaging with GLCM analysis was performed at three different time points: 30 min, 60 min, and 120 min after the treatment. A total of 200 cell nuclei were analyzed, and for each nucleus, 5 GLCM parameters were calculated: Angular second moment (ASM), Inverse difference moment (IDM), Contrast (CON), Correlation (COR) and Sum Variance (SVAR). Exposure to IONPs was associated with the increase of ASM and IDM while the values of SVAR and COR were reduced. Treatment with 6-OHDA was associated with the increase of SVAR and CON, while the values of nuclear ASM and IDM were reduced. This is the first study to indicate that IONPs and 6-OHDA have opposite effects on nuclear texture. Also, to the best of our knowledge, this is the first study to apply the GLCM algorithm in Saccharomyces cerevisiae yeast cells in this experimental setting.

Modified Quality Threshold Clustering for Temporal Analysis and Classification of Lung Lesions

Lung cancer is the type of cancer that most often kills after the initial diagnosis. To aid the specialist in its diagnosis, temporal evaluation is a potential tool for analyzing indeterminate lesions, which may be benign or malignant, during treatment. With this goal in mind, a methodology is herein proposed for the analysis, quantification, and visualization of changes in lung lesions. This methodology uses a modified version of the quality threshold clustering algorithm to associate each voxel of the lesion to a cluster, and changes in the lesion over time are defined in terms of voxel moves to another cluster. In addition, statistical features are extracted for classification of the lesion as benign or malignant. To develop the proposed methodology, two databases of pulmonary lesions were used, one for malignant lesions in treatment (public) and the other for indeterminate cases (private). We determined that the density change percentage varied from 6.22% to 36.93% of lesion volume in the public database of malignant lesions under treatment and from 19.98% to 38.81% in the private database of lung nodules. Additionally, other inter-cluster density change measures were obtained. These measures indicate the degree of change in the clusters and how each of them is abundant in relation to volume. From the statistical analysis of regions in which the density changes occurred, we were able to discriminate lung lesions with an accuracy of 98.41%, demonstrating that these changes can indicate the true nature of the lesion. In addition to visualizing the density changes occurring in lesions over time, we quantified these changes and analyzed the entire set through volumetry, which is the technique most commonly used to analyze changes in pulmonary lesions.

Gray-level co-occurrence matrix analysis of chromatin architecture in periportal and perivenous hepatocytes

Periportal hepatocytes (PPHs) and perivenous hepatocytes (PVHs) in standard optical microscopy appear to be morphologically identical. However, the functional properties of these two cell populations and their roles in liver lobules are not the same. Despite significant differences in gene expression between these two hepatocyte populations, it is still unclear whether the differences are present at the higher levels of chromatin organization. In this study, we present results, indicating that periportal and perivenous hepatocytes, when stained using toluidine blue histological dye, have different chromatin textural patterns quantified with gray-level co-occurrence matrix (GLCM) method. Hepatic tissue was obtained from ten male, healthy mice. Chromatin structures were analyzed using GLCM. For each structure, we measured the values of angular second moment, inverse difference moment, GLCM Contrast, GLCM Variance, and GLCM Sum Variance. The results indicate that there is a statistically significant difference in all GLCM mathematical parameters except the contrast. In addition, some chromatin GLCM features were in correlation with serum aminotransferase levels in perivenous, but not in periportal hepatocytes. To the best of our knowledge, this is the first study to test the nuclear morphological differences between hepatocytes using GLCM and to investigate the respective relation with serum liver enzymes.

Label-Free Imaging of Melanoma with Confocal Photothermal Microscopy: Differentiation between Malignant and Benign Tissue

Label-free confocal photothermal (CPT) microscopy was utilized for the first time to investigate malignancy in mouse skin cells. Laser diodes (LDs) with 405 nm or 488 nm wavelengths were used as pumps, and a 638 nm LD was used as a probe for the CPT microscope. A Grey Level Cooccurrence Matrix (GLCM) for texture analysis was applied to the CPT images. Nine GLCM parameters were calculated with definite definitions for the intracellular super-resolved CPT images, and the parameters Entropy, Contrast, and Variance were found to be most suited among the nine parameters to discriminate clearly between healthy cells and malignant cells when a 405 nm pump was used. Prominence, Variance, and Shade were most suited when a pump wavelength of 488 nm was used.

Radiomics Evaluation of Histological Heterogeneity Using Multiscale Textures Derived From 3D Wavelet Transformation of Multispectral Images

Purpose

Colorectal cancer (CRC) is markedly heterogeneous and develops progressively toward malignancy through several stages which include stroma (ST), benign hyperplasia (BH), intraepithelial neoplasia (IN) or precursor cancerous lesion, and carcinoma (CA). Identification of the malignancy stage of CRC pathology tissues (PT) allows the most appropriate therapeutic intervention.

Methods

This study investigates multiscale texture features extracted from CRC pathology sections using 3D wavelet transform (3D-WT) filter. Multiscale features were extracted from digital whole slide images of 39 patients that were segmented in a pre-processing step using an active contour model. The capacity for multiscale texture to compare and classify between PTs was investigated using ANOVA significance test and random forest classifier models, respectively.

Results

12 significant features derived from the multiscale texture (i.e., variance, entropy, and energy) were found to discriminate between CRC grades at a significance value of p < 0.01 after correction. Combining multiscale texture features lead to a better predictive capacity compared to prediction models based on individual scale features with an average (±SD) classification accuracy of 93.33 (±3.52)%, sensitivity of 88.33 (± 4.12)%, and specificity of 96.89 (± 3.88)%. Entropy was found to be the best classifier feature across all the PT grades with an average of the area under the curve (AUC) value of 91.17, 94.21, 97.70, 100% for ST, BH, IN, and CA, respectively.

Conclusion

Our results suggest that multiscale texture features based on 3D-WT are sensitive enough to discriminate between CRC grades with the entropy feature, the best predictor of pathology grade.

Acquisition, Visualization and Potential Applications of 3D Data in Anatomic Pathology

Although human anatomy and histology are naturally three-dimensional (3D), commonly used diagnostic and educational tools are technologically restricted to providing two-dimensional representations (e.g. gross photography and glass slides). This limitation may be overcome by employing techniques to acquire and display 3D data, which refers to the digital information used to describe a 3D object mathematically. There are several established and experimental strategies to capture macroscopic and microscopic 3D data. In addition, recent hardware and software innovations have propelled the visualization of 3D models, including virtual and augmented reality. Accompanying these advances are novel clinical and non-clinical applications of 3D data in pathology. Medical education and research stand to benefit a great deal from utilizing 3D data as it can change our understanding of complex anatomical and histological structures. Although these technologies are yet to be adopted in routine surgical pathology, forensic pathology has embraced 3D scanning and model reconstruction. In this review, we intend to provide a general overview of the technologies and emerging applications involved with 3D data.

Early detection of chemotherapy-refractory patients by monitoring textural alterations in diffuse optical spectroscopic images

PURPOSE

Changes in textural characteristics of diffuse optical spectroscopic (DOS) functional images, accompanied by alterations in their mean values, are demonstrated here for the first time as early surrogates of ultimate treatment response in locally advanced breast cancer (LABC) patients receiving neoadjuvant chemotherapy (NAC). NAC, as a standard component of treatment for LABC patient, induces measurable heterogeneous changes in tumor metabolism which were evaluated using DOS-based metabolic maps. This study characterizes such inhomogeneous nature of response development, by determining alterations in textural properties of DOS images apparent at early stages of therapy, followed later by gross changes in mean values of these functional metabolic maps.

METHODS

Twelve LABC patients undergoing NAC were scanned before and at four times after treatment initiation, and tomographic DOS images were reconstructed at each time. Ultimate responses of patients were determined clinically and pathologically, based on a reduction in tumor size and assessment of residual tumor cellularity. The mean-value parameters and textural features were extracted from volumetric DOS images for several functional and metabolic parameters prior to the treatment initiation. Changes in these DOS-based biomarkers were also monitored over the course of treatment. The measured biomarkers were applied to differentiate patient responses noninvasively and compared to clinical and pathologic responses.

RESULTS

Responding and nonresponding patients demonstrated different changes in DOS-based textural and mean-value parameters during chemotherapy. Whereas none of the biomarkers measured prior the start of therapy demonstrated a significant difference between the two patient populations, statistically significant differences were observed at week one after treatment initiation using the relative change in contrast/homogeneity of seven functional maps (0.001<p<0.049), and mean value of water content in tissue (p=0.010). The cross-validated sensitivity and specificity of these parameters at week one of therapy ranged between 80%-100% and 67%-100%, respectively. Higher levels of statistically significant differences were exhibited at week four after start of treatment, with cross-validated sensitivities and specificities ranging between 80% and 100% for three textural and three mean-value parameters. The combination of the textural and mean-value parameters in a "hybrid" profile could better separate the two patient populations early on during a course of treatment, with cross-validated sensitivities and specificities of up to 100% (p=0.001).

CONCLUSIONS

The results of this study suggest that alterations in textural characteristics of DOS images, in conjunction with changes in their mean values, can classify noninvasively the ultimate clinical and pathologic response of LABC patients to chemotherapy, as early as one week after start of their treatment. This provides a basis for using DOS imaging as a tool for therapy personalization.

Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery

PURPOSE

This paper proposes to characterize the continuum of colorectal cancer (CRC) using multiple texture features extracted from multispectral optical microscopy images. Three types of pathological tissues (PT) are considered: benign hyperplasia, intraepithelial neoplasia and carcinoma.

MATERIALS AND METHODS

In the proposed approach, the region of interest containing PT is first extracted from multispectral images using active contour segmentation. This region is then encoded using texture features based on the Laplacian-of-Gaussian (LoG) filter, discrete wavelets (DW) and gray level co-occurrence matrices (GLCM). To assess the significance of textural differences between PT types, a statistical analysis based on the Kruskal-Wallis test is performed. The usefulness of texture features is then evaluated quantitatively in terms of their ability to predict PT types using various classifier models.

RESULTS

Preliminary results show significant texture differences between PT types, for all texture features (p-value < 0.01). Individually, GLCM texture features outperform LoG and DW features in terms of PT type prediction. However, a higher performance can be achieved by combining all texture features, resulting in a mean classification accuracy of 98.92%, sensitivity of 98.12%, and specificity of 99.67%.

CONCLUSIONS

These results demonstrate the efficiency and effectiveness of combining multiple texture features for characterizing the continuum of CRC and discriminating between pathological tissues in multispectral images.