Histopathologic image-based deep learning classifier for predicting platinum-based treatment responses in high-grade serous ovarian cancer.

Platinum-based chemotherapy is the cornerstone treatment for female high-grade serous ovarian carcinoma (HGSOC), but choosing an appropriate treatment for patients hinges on their responsiveness to it. Currently, no available biomarkers can promptly predict responses to platinum-based treatment. Therefore, we developed the Pathologic Risk Classifier for HGSOC (PathoRiCH), a histopathologic image-based classifier. PathoRiCH was trained on an in-house cohort (n = 394) and validated on two independent external cohorts (n = 284 and n = 136). The PathoRiCH-predicted favorable and poor response groups show significantly different platinum-free intervals in all three cohorts. Combining PathoRiCH with molecular biomarkers provides an even more powerful tool for the risk stratification of patients. The decisions of PathoRiCH are explained through visualization and a transcriptomic analysis, which bolster the reliability of our model's decisions. PathoRiCH exhibits better predictive performance than current molecular biomarkers. PathoRiCH will provide a solid foundation for developing an innovative tool to transform the current diagnostic pipeline for HGSOC.

Evaluation of Vertical Level Differences Between Left and Right Vocal Folds Using Artificial Intelligence System in Excised Canine Larynx.

OBJECTIVES: This study aimed to establish an artificial intelligence (AI) system to classify vertical level differences between vocal folds during vocalization and to evaluate the accuracy of the classification. METHODS: We designed models with different depths between the right and left vocal folds using an excised canine larynx. Video files for the data set were obtained using a high-speed camera system and a color complementary metal oxide semiconductor camera with global shutter. The data sets were divided into training, validation, and testing. We used 20,000 images for building the model and 8000 images for testing. To perform deep learning multiclass classification and to estimate the vertical level difference, we introduced DenseNet121-ConvLSTM. RESULTS: The model was trained several times using different numbers of epochs. We achieved the most optimal results at 100 epochs, and the batch size used during training was 16. The proposed DenseNet121-ConvLSTM model achieved classification accuracies of 99.5% and 88.0% for training and testing, respectively. After verification using an external data set, the overall accuracy, precision, recall, and f1-score were 90.8%, 91.6%, 90.9%, and 91.2%, respectively. CONCLUSIONS: The newly developed AI system may be an easy and accurate method for classifying superior and inferior vertical level differences between vocal folds. Thus, this AI system can be applied and may help in the assessment of vertical level differences in patients with unilateral vocal fold paralysis.

Densely Convolutional Spatial Attention Network for nuclei segmentation of histological images for computational pathology.

Introduction: Automatic nuclear segmentation in digital microscopic tissue images can aid pathologists to extract high-quality features for nuclear morphometrics and other analyses. However, image segmentation is a challenging task in medical image processing and analysis. This study aimed to develop a deep learning-based method for nuclei segmentation of histological images for computational pathology. Methods: The original U-Net model sometime has a caveat in exploring significant features. Herein, we present the Densely Convolutional Spatial Attention Network (DCSA-Net) model based on U-Net to perform the segmentation task. Furthermore, the developed model was tested on external multi-tissue dataset - MoNuSeg. To develop deep learning algorithms for well-segmenting nuclei, a large quantity of data are mandatory, which is expensive and less feasible. We collected hematoxylin and eosin-stained image data sets from two hospitals to train the model with a variety of nuclear appearances. Because of the limited number of annotated pathology images, we introduced a small publicly accessible data set of prostate cancer (PCa) with more than 16,000 labeled nuclei. Nevertheless, to construct our proposed model, we developed the DCSA module, an attention mechanism for capturing useful information from raw images. We also used several other artificial intelligence-based segmentation methods and tools to compare their results to our proposed technique. Results: To prioritize the performance of nuclei segmentation, we evaluated the model's outputs based on the Accuracy, Dice coefficient (DC), and Jaccard coefficient (JC) scores. The proposed technique outperformed the other methods and achieved superior nuclei segmentation with accuracy, DC, and JC of 96.4% (95% confidence interval [CI]: 96.2 - 96.6), 81.8 (95% CI: 80.8 - 83.0), and 69.3 (95% CI: 68.2 - 70.0), respectively, on the internal test data set. Conclusion: Our proposed method demonstrates superior performance in segmenting cell nuclei of histological images from internal and external datasets, and outperforms many standard segmentation algorithms used for comparative analysis.

Region Segmentation of Whole-Slide Images for Analyzing Histological Differentiation of Prostate Adenocarcinoma Using Ensemble EfficientNetB2 U-Net with Transfer Learning Mechanism.

Recent advances in computer-aided detection via deep learning (DL) now allow for prostate cancer to be detected automatically and recognized with extremely high accuracy, much like other medical diagnoses and prognoses. However, researchers are still limited by the Gleason scoring system. The histopathological analysis involved in assigning the appropriate score is a rigorous, time-consuming manual process that is constrained by the quality of the material and the pathologist's level of expertise. In this research, we implemented a DL model using transfer learning on a set of histopathological images to segment cancerous and noncancerous areas in whole-slide images (WSIs). In this approach, the proposed Ensemble U-net model was applied for the segmentation of stroma, cancerous, and benign areas. The WSI dataset of prostate cancer was collected from the Kaggle repository, which is publicly available online. A total of 1000 WSIs were used for region segmentation. From this, 8100 patch images were used for training, and 900 for testing. The proposed model demonstrated an average dice coefficient (DC), intersection over union (IoU), and Hausdorff distance of 0.891, 0.811, and 15.9, respectively, on the test set, with corresponding masks of patch images. The manipulation of the proposed segmentation model improves the ability of the pathologist to predict disease outcomes, thus enhancing treatment efficacy by isolating the cancerous regions in WSIs.

Texture, Morphology, and Statistical Analysis to Differentiate Primary Brain Tumors on Two-Dimensional Magnetic Resonance Imaging Scans Using Artificial Intelligence Techniques.

OBJECTIVE: A primary brain tumor starts to grow from brain cells, and it occurs as a result of errors in the DNA of normal cells. Therefore, this study was carried out to analyze the two-dimensional (2D) texture, morphology, and statistical features of brain tumors and to perform a classification using artificial intelligence (AI) techniques. METHODS: AI techniques can help radiologists to diagnose primary brain tumors without using any invasive measurement techniques. In this paper, we focused on deep learning (DL) and machine learning (ML) techniques for texture, morphological, and statistical feature classification of three tumor types (namely, glioma, meningioma, and pituitary). T1-weighted magnetic resonance imaging (MRI) 2D scans were used for analysis and classification (multiclass and binary). A total of 102 features were calculated for each tumor, and the 20 most significant features were selected using the three-step feature selection method, which included removing duplicate features, Pearson correlations, and recursive feature elimination. RESULTS: From the predicted results of multiclass and binary classification, a long short-term memory binary classification (glioma vs. meningioma) showed the best performance, with an average accuracy, recall, precision, F1-score, and kappa coefficient of 97.7%, 97.2%, 97.5%, 97.0%, and 94.7%, respectively. CONCLUSIONS: The early diagnosis of primary brain tumors is very important because it can be the key to effective treatment. Therefore, this research presents a method for early diagnoses by effectively classifying three types of primary brain tumors.

Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering.

The optimal diagnostic and treatment strategies for prostate cancer (PCa) are constantly changing. Given the importance of accurate diagnosis, texture analysis of stained prostate tissues is important for automatic PCa detection. We used artificial intelligence (AI) techniques to classify dual-channel tissue features extracted from Hematoxylin and Eosin (H&E) tissue images, respectively. Tissue feature engineering was performed to extract first-order statistic (FOS)-based textural features from each stained channel, and cancer classification between benign and malignant was carried out based on important features. Recursive feature elimination (RFE) and one-way analysis of variance (ANOVA) methods were used to identify significant features, which provided the best five features out of the extracted six features. The AI techniques used in this study for binary classification (benign vs. malignant and low-grade vs. high-grade) were support vector machine (SVM), logistic regression (LR), bagging tree, boosting tree, and dual-channel bidirectional long short-term memory (DC-BiLSTM) network. Further, a comparative analysis was carried out between the AI algorithms. Two different datasets were used for PCa classification. Out of these, the first dataset (private) was used for training and testing the AI models and the second dataset (public) was used only for testing to evaluate model performance. The automatic AI classification system performed well and showed satisfactory results according to the hypothesis of this study.

Diagnosing Alzheimer's Disease Based on Multiclass MRI Scans using Transfer Learning Techniques.

AIMS: To prevent Alzheimer's disease (AD) from progressing to dementia, early prediction and classification of AD are important and they play a crucial role in medical image analysis. BACKGROUND: In this study, we employed a transfer learning technique to classify magnetic resonance (MR) images using a pre-trained convolutional neural network (CNN). OBJECTIVE: To address the early diagnosis of AD, we employed a computer-assisted technique, specifically the deep learning (DL) model, to detect AD. METHODS: In particular, we classified Alzheimer's disease (AD), mild cognitive impairment (MCI), and normal control (NC) subjects using whole slide two-dimensional (2D) images. To illustrate this approach, we made use of state-of-the-art CNN base models, i.e., the residual networks Res- Net-101, ResNet-50, and ResNet-18, and compared their effectiveness in identifying AD. To evaluate this approach, an AD Neuroimaging Initiative (ADNI) dataset was utilized. We also showed uniqueness by using MR images selected only from the central slice containing left and right hippocampus regions to evaluate the models. RESULTS: All three models used randomly split data in the ratio of 70:30 for training and testing. Among the three, ResNet-101 showed 98.37% accuracy, better than the other two ResNet models, and performed well in multiclass classification. The promising results emphasize the benefit of using transfer learning, specifically when the dataset is low. CONCLUSION: From this study, we know that transfer learning helps to overcome DL problems mainly when the data available is insufficient to train a model from scratch. This approach is highly advantageous in medical image analysis to diagnose diseases like AD.

A Paradigm Shift in Nuclear Chromatin Interpretation: From Qualitative Intuitive Recognition to Quantitative Texture Analysis of Breast Cancer Cell Nuclei.

Assessing the pattern of nuclear chromatin is essential for pathological investigations. However, the interpretation of nuclear pattern is subjective. In this study, we performed the texture analysis of nuclear chromatin in breast cancer samples to determine the nuclear pleomorphism score thereof. We used three different algorithms for extracting high-level texture features: the gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and gray-level size zone matrix (GLSZM). Using these algorithms, 12 GLCM, 11 GLRLM, and 16 GLSZM features were extracted from three scores of breast carcinoma (Scores 1-3). Classification accuracy was assessed using the support vector machine (SVM) and k-nearest neighbor (KNN) classification models. Three features of GLCM, 11 of GLRLM, and 12 of GLSZM were consistent across the three nuclear pleomorphism scores of breast cancer. Comparing Scores 1 and 3, the GLSZM feature large zone high gray-level emphasis showed the largest difference among breast cancer nuclear scores among all features of the three algorithms. The SVM and KNN classifiers showed favorable results for all three algorithms. A multiclass classification was performed to compare and distinguish between the scores of breast cancer. Texture features of nuclear chromatin can provide useful information for nuclear scoring. However, further validation of the correlations of histopathologic features, and standardization of the texture analysis process, are required to achieve better classification results. © 2021 The Authors. Cytometry Part A published by Wiley Periodicals LLC on behalf of International Society for Advancement of Cytometry.

Cluster Analysis of Cell Nuclei in H&E-Stained Histological Sections of Prostate Cancer and Classification Based on Traditional and Modern Artificial Intelligence Techniques.

Biomarker identification is very important to differentiate the grade groups in the histopathological sections of prostate cancer (PCa). Assessing the cluster of cell nuclei is essential for pathological investigation. In this study, we present a computer-based method for cluster analyses of cell nuclei and performed traditional (i.e., unsupervised method) and modern (i.e., supervised method) artificial intelligence (AI) techniques for distinguishing the grade groups of PCa. Two datasets on PCa were collected to carry out this research. Histopathology samples were obtained from whole slides stained with hematoxylin and eosin (H&E). In this research, state-of-the-art approaches were proposed for color normalization, cell nuclei segmentation, feature selection, and classification. A traditional minimum spanning tree (MST) algorithm was employed to identify the clusters and better capture the proliferation and community structure of cell nuclei. K-medoids clustering and stacked ensemble machine learning (ML) approaches were used to perform traditional and modern AI-based classification. The binary and multiclass classification was derived to compare the model quality and results between the grades of PCa. Furthermore, a comparative analysis was carried out between traditional and modern AI techniques using different performance metrics (i.e., statistical parameters). Cluster features of the cell nuclei can be useful information for cancer grading. However, further validation of cluster analysis is required to accomplish astounding classification results.

Convolutional Neural Network-based MR Image Analysis for Alzheimer's Disease Classification.

BACKGROUND: In this study, we used a convolutional neural network (CNN) to classify Alzheimer's disease (AD), mild cognitive impairment (MCI), and normal control (NC) subjects based on images of the hippocampus region extracted from magnetic resonance (MR) images of the brain. METHODS: The datasets used in this study were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI). To segment the hippocampal region automatically, the patient brain MR images were matched to the International Consortium for Brain Mapping template (ICBM) using 3D-Slicer software. Using prior knowledge and anatomical annotation label information, the hippocampal region was automatically extracted from the brain MR images. RESULTS: The area of the hippocampus in each image was preprocessed using local entropy minimization with a bi-cubic spline model (LEMS) by an inhomogeneity intensity correction method. To train the CNN model, we separated the dataset into three groups, namely AD/NC, AD/MCI, and MCI/NC. The prediction model achieved an accuracy of 92.3% for AD/NC, 85.6% for AD/MCI, and 78.1% for MCI/NC. CONCLUSION: The results of this study were compared to those of previous studies, and summarized and analyzed to facilitate more flexible analyses based on additional experiments. The classification accuracy obtained by the proposed method is highly accurate. These findings suggest that this approach is efficient and may be a promising strategy to obtain good AD, MCI and NC classification performance using small patch images of hippocampus instead of whole slide images.

Multi-Features Classification of Prostate Carcinoma Observed in Histological Sections: Analysis of Wavelet-Based Texture and Colour Features.

Microscopic biopsy images are coloured in nature because pathologists use the haematoxylin and eosin chemical colour dyes for biopsy examinations. In this study, biopsy images are used for histological grading and the analysis of benign and malignant prostate tissues. The following PCa grades are analysed in the present study: benign, grade 3, grade 4, and grade 5. Biopsy imaging has become increasingly important for the clinical assessment of PCa. In order to analyse and classify the histological grades of prostate carcinomas, pixel-based colour moment descriptor (PCMD) and gray-level co-occurrence matrix (GLCM) methods were used to extract the most significant features for multilayer perceptron (MLP) neural network classification. Haar wavelet transformation was carried out to extract GLCM texture features, and colour features were extracted from RGB (red/green/blue) colour images of prostate tissues. The MANOVA statistical test was performed to select significant features based on F-values and P-values using the R programming language. We obtained an average highest accuracy of 92.7% using level-1 wavelet texture and colour features. The MLP classifier performed well, and our study shows promising results based on multi-feature classification of histological sections of prostate carcinomas.

Deep Learning for Alzheimer's Disease Classification using Texture Features.

BACKGROUND: We propose a classification method for Alzheimer's disease (AD) based on the texture of the hippocampus, which is the organ that is most affected by the onset of AD. METHODS: We obtained magnetic resonance images (MRIs) of Alzheimer's patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. This dataset consists of image data for AD, mild cognitive impairment (MCI), and normal controls (NCs), classified according to the cognitive condition. In this study, the research methods included image processing, texture analyses, and deep learning. Firstly, images were acquired for texture analyses, which were then re-spaced, registered, and cropped with Gabor filters applied to the resulting image data. In the texture analyses, we applied the 3-dimensional (3D) gray-level co-occurrence (GLCM) method to evaluate the textural features of the image, and used Fisher's coefficient to select the appropriate features for classification. In the last stage, we implemented a deep learning multi-layer perceptron (MLP) model, which we divided into three types, namely, AD-MCI, AD-NC, and MCI-NC. RESULTS: We used this model to assess the accuracy of the proposed method. The classification accuracy of the proposed deep learning model was confirmed in the cases of AD-MCI (72.5%), ADNC (85%), and MCI-NC (75%). We also evaluated the results obtained using a confusion matrix, support vector machine (SVM), and K-nearest neighbor (KNN) classifier and analyzed the results to objectively verify our model. We obtained the highest accuracy of 85% in the AD-NC. CONCLUSION: The proposed model was at least 6-19% more accurate than the SVM and KNN classifiers, respectively. Hence, this study confirms the validity and superiority of the proposed method, which can be used as a diagnostic tool for early Alzheimer's diagnosis.

One-year Follow-up Study of Hippocampal Subfield Atrophy in Alzheimer's Disease and Normal Aging.

BACKGROUND: In this study, we investigated the effect of hippocampal subfield atrophy on the development of Alzheimer's disease (AD) by analyzing baseline magnetic resonance images (MRI) and images collected over a one-year follow-up period. Previous studies have suggested that morphological changes to the hippocampus are involved in both normal ageing and the development of AD. The volume of the hippocampus is an authentic imaging biomarker for AD. However, the diverse relationship of anatomical and complex functional connectivity between different subfields implies that neurodegenerative disease could lead to differences between the atrophy rates of subfields. Therefore, morphometric measurements at subfield-level could provide stronger biomarkers. METHODS: Hippocampal subfield atrophies are measured using MRI scans, taken at multiple time points, and shape-based normalization to a Montreal neurological institute (MNI) ICBM 152 nonlinear atlas. Ninety subjects were selected from the Alzheimer's Disease Neuroimaging Initiative (ADNI), and divided equally into Healthy Controls (HC), AD, and mild cognitive impairment (MCI) groups. These subjects underwent serial MRI studies at three time-points: baseline, 6 months and 12 months. RESULTS: We analyzed the subfield-level hippocampal morphometric effects of normal ageing and AD based on radial distance mapping and volume measurements. We identified a general trend and observed the largest hippocampal subfield atrophies in the AD group. Atrophy of the bilateral CA1, CA2- CA4 and subiculum subfields was higher in the case of AD than in MCI and HC. We observed the highest rate of reduction in the total volume of the hippocampus, especially in the CA1 and subiculum regions, in the case of MCI. CONCLUSION: Our findings show that hippocampal subfield atrophy varies among the three study groups.

Alzheimer's Disease Classification Based on Multi-feature Fusion.

BACKGROUND: In this study, we investigated the fusion of texture and morphometric features as a possible diagnostic biomarker for Alzheimer's Disease (AD). METHODS: In particular, we classified subjects with Alzheimer's disease, Mild Cognitive Impairment (MCI) and Normal Control (NC) based on texture and morphometric features. Currently, neuropsychiatric categorization provides the ground truth for AD and MCI diagnosis. This can then be supported by biological data such as the results of imaging studies. Cerebral atrophy has been shown to correlate strongly with cognitive symptoms. Hence, Magnetic Resonance (MR) images of the brain are important resources for AD diagnosis. In the proposed method, we used three different types of features identified from structural MR images: Gabor, hippocampus morphometric, and Two Dimensional (2D) and Three Dimensional (3D) Gray Level Co-occurrence Matrix (GLCM). The experimental results, obtained using a 5-fold cross-validated Support Vector Machine (SVM) with 2DGLCM and 3DGLCM multi-feature fusion approaches, indicate that we achieved 81.05% ±1.34, 86.61% ±1.25 correct classification rate with 95% Confidence Interval (CI) falls between (80.75-81.35) and (86.33-86.89) respectively, 83.33%±2.15, 84.21%±1.42 sensitivity and 80.95%±1.52, 85.00%±1.24 specificity in our classification of AD against NC subjects, thus outperforming recent works found in the literature. For the classification of MCI against AD, the SVM achieved a 76.31% ± 2.18, 78.95% ±2.26 correct classification rate, 75.00% ±1.34, 76.19%±1.84 sensitivity and 77.78% ±1.14, 82.35% ±1.34 specificity. RESULTS AND CONCLUSION: The results of the third experiment, with MCI against NC, also showed that the multiclass SVM provided highly accurate classification results. These findings suggest that this approach is efficient and may be a promising strategy for obtaining better AD, MCI and NC classification performance.

Mapping the Supratentorial Cerebral Arterial Territories Using 1160 Large Artery Infarcts.

Importance: Cerebral vascular territories are of key clinical importance in patients with stroke, but available maps are highly variable and based on prior studies with small sample sizes. Objective: To update and improve the state of knowledge on the supratentorial vascular supply to the brain by using the natural experiment of large artery infarcts and to map out the variable anatomy of the anterior, middle, and posterior cerebral artery (ACA, MCA, and PCA) territories. Design, Setting, and Participants: In this cross-sectional study, digital maps of supratentorial infarcts were generated using diffusion-weighted magnetic resonance imaging (MRI) of 1160 patients with acute (<1-week) stroke recruited (May 2011 to February 2013) consecutively from 11 Korean stroke centers. All had supratentorial infarction associated with significant stenosis or occlusion of 1 of 3 large supratentorial cerebral arteries but with patent intracranial or extracranial carotid arteries. Data were analyzed between February 2016 and August 2017. Main Outcomes and Measures: The 3 vascular territories were mapped individually by affected vessel, generating 3 data sets for which infarct frequency is defined for each voxel in the data set. By mapping these 3 vascular territories collectively, we generated data sets showing the Certainty Index (CI) to reflect the likelihood of a voxel being a member of a specific vascular territory, calculated as either ACA, MCA, or PCA infarct frequency divided by total infarct frequency in that voxel. Results: Of the 1160 patients (mean [SD] age, 67.0 [13.3] years old), 623 were men (53.7%). When the cutoff CI was set as 90%, the volume of the MCA territory (approximately 54% of the supratentorial parenchymal brain volume) was about 4-fold bigger than the volumes of the ACA and PCA territories (each approximately 13%). Quantitative studies showed that the medial frontal gyrus, superior frontal gyrus, and anterior cingulate were involved mostly in ACA infarcts, whereas the middle frontal gyrus and caudate were involved mostly by MCA infarcts. The PCA infarct territory was smaller and narrower than traditionally shown. Border-zone maps could be defined by using either relative infarct frequencies or CI differences. Conclusions and Relevance: We have generated statistically rigorous maps to delineate territorial border zones and lines. The new topographic brain atlas can be used in clinical care and in research to objectively define the supratentorial arterial territories and their borders.

Stroke outcomes are worse with larger leukoaraiosis volumes.

Leukoaraiosis or white matter hyperintensities are frequently observed on magnetic resonance imaging of stroke patients. We investigated how white matter hyperintensity volumes affect stroke outcomes, generally and by subtype. In total, 5035 acute ischaemic stroke patients were enrolled. Strokes were classified as large artery atherosclerosis, small vessel occlusion, or cardioembolism. White matter hyperintensity volumes were stratified into quintiles. Mean age (± standard deviation) was 66.3 ± 12.8, 59.6% male. Median (interquartile range) modified Rankin Scale score was 2 (1-3) at discharge and 1 (0-3) at 3 months; 16.5% experienced early neurological deterioration, and 3.3% recurrent stroke. The Cochran-Mantel-Haenszel test with adjustment for age, stroke severity, sex, and thrombolysis status showed that the distributions of 3-month modified Rankin Scale scores differed across white matter hyperintensity quintiles (P < 0.001). Multiple ordinal logistic regression analysis showed that higher white matter hyperintensity quintiles were independently associated with worse 3-month modified Rankin Scale scores; adjusted odds ratios (95% confidence interval) for the second to fifth quintiles versus the first quintile were 1.29 (1.10-1.52), 1.40 (1.18-1.66), 1.69 (1.42-2.02) and 2.03 (1.69-2.43), respectively. For large artery atherosclerosis (39.0%), outcomes varied by white matter hyperintensity volume (P = 0.01, Cochran-Mantel-Haenszel test), and the upper three white matter hyperintensity quintiles (versus the first quintile) had worse 3-month modified Rankin Scale scores; adjusted odds ratios were 1.45 (1.10-1.90), 1.86 (1.41-2.47), and 1.89 (1.41-2.54), respectively. Patients with large artery atherosclerosis were vulnerable to early neurological deterioration (19.4%), and the top two white matter hyperintensity quintiles were more vulnerable still: 23.5% and 22.3%. Moreover, higher white matter hyperintensities were associated with poor modified Rankin Scale improvement: adjusted odds ratios for the upper two quintiles versus the first quintile were 0.66 (0.47-0.94) and 0.62 (0.43-0.89), respectively. For small vessel occlusion (17.8%), outcomes tended to vary by white matter hyperintensitiy volume (P = 0.10, Cochran-Mantel-Haenszel test), and the highest quintile was associated with worse 3-month modified Rankin Scale scores: adjusted odds ratio for the fifth quintile versus first quintile, 1.98 (1.23-3.18). In this subtype, worse white matter hyperintensities were associated with worse National Institute of Health Stroke Scale scores at presentation. For cardioembolism (20.6%), outcomes did not vary significantly by white matter hyperintensity volume (P = 0.19, Cochran-Mantel-Haenszel test); however, the adjusted odds ratio for the highest versus lowest quintiles was 1.62 (1.09-2.40). Regardless of stroke subtype, white matter hyperintensities were not associated with stroke recurrence within 3 months of follow-up. In conclusion, white matter hyperintensity volume independently correlates with stroke outcomes in acute ischaemic stroke. There are some suggestions that stroke outcomes may be affected by leukoaraiosis differentially depending on stroke subtypes, to be confirmed in future investigations.

3D texture analysis in renal cell carcinoma tissue image grading.

One of the most significant processes in cancer cell and tissue image analysis is the efficient extraction of features for grading purposes. This research applied two types of three-dimensional texture analysis methods to the extraction of feature values from renal cell carcinoma tissue images, and then evaluated the validity of the methods statistically through grade classification. First, we used a confocal laser scanning microscope to obtain image slices of four grades of renal cell carcinoma, which were then reconstructed into 3D volumes. Next, we extracted quantitative values using a 3D gray level cooccurrence matrix (GLCM) and a 3D wavelet based on two types of basis functions. To evaluate their validity, we predefined 6 different statistical classifiers and applied these to the extracted feature sets. In the grade classification results, 3D Haar wavelet texture features combined with principal component analysis showed the best discrimination results. Classification using 3D wavelet texture features was significantly better than 3D GLCM, suggesting that the former has potential for use in a computer-based grading system.

Grading and interpretation of white matter hyperintensities using statistical maps.

BACKGROUND AND PURPOSE: We aimed to generate rigorous graphical and statistical reference data based on volumetric measurements for assessing the relative severity of white matter hyperintensities (WMHs) in patients with stroke. METHODS: We prospectively mapped WMHs from 2699 patients with first-ever ischemic stroke (mean age=66.8±13.0 years) enrolled consecutively from 11 nationwide stroke centers, from patient (fluid-attenuated-inversion-recovery) MRIs onto a standard brain template set. Using multivariable analyses, we assessed the impact of major (age/hypertension) and minor risk factors on WMH variability. RESULTS: We have produced a large reference data library showing the location and quantity of WMHs as topographical frequency-volume maps. This easy-to-use graphical reference data set allows the quantitative estimation of the severity of WMH as a percentile rank score. For all patients (median age=69 years), multivariable analysis showed that age, hypertension, atrial fibrillation, and left ventricular hypertrophy were independently associated with increasing WMH (0-9.4%, median=0.6%, of the measured brain volume). For younger (≤69) hypertensives (n=819), age and left ventricular hypertrophy were positively associated with WMH. For older (≥70) hypertensives (n=944), age and cholesterol had positive relationships with WMH, whereas diabetes mellitus, hyperlipidemia, and atrial fibrillation had negative relationships with WMH. For younger nonhypertensives (n=578), age and diabetes mellitus were positively related to WMH. For older nonhypertensives (n=328), only age was positively associated with WMH. CONCLUSIONS: We have generated a novel graphical WMH grading (Kim statistical WMH scoring) system, correlated to risk factors and adjusted for age/hypertension. Further studies are required to confirm whether the combined data set allows grading of WMH burden in individual patients and a tailored patient-specific interpretation in ischemic stroke-related clinical practice.

A new image-based stroke registry containing quantitative magnetic resonance imaging data.

BACKGROUND: Conventional stroke registries contain alphanumeric text-based data on the clinical status of stroke patients, but this format captures imaging data in a very limited form. There is a need for a new type of stroke registry to capture both text- and image-based data. METHODS AND RESULTS: We designed a next-generation stroke registry containing quantitative magnetic resonance imaging (MRI) data, 'DUIH_SRegI', developed a supporting software package, 'Image_QNA', and performed experiments to assess the feasibility and utility of the system. Image_QNA enabled the mapping of stroke-related lesions on MR onto a standard brain template and the storage of this extracted imaging data in a visual database. Interuser and intrauser variability of the lesion mapping procedure was low. We compared the results from the semi automatic lesion registration using Image_QNA with automatic lesion registration using SPM5 (Statistical Parametric Mapping version 5), a well-regarded standard neuroscience software package, in terms of lesion location, size and shape, and found Image_QNA to be superior. We assessed the clinical usefulness of an image-based registry by studying 47 consecutive patients with first-ever lacunar infarcts in the corona radiata. We used the enriched dataset comprised of both image-based and alphanumeric databases to show that diffusion MR lesions overlapped in a more posterolateral brain location for patients with high NIH Stroke Scale scores (≥4) than for patients with low scores (≤3). In April 2009, we launched the first prospective image-based acute (≤1 week) stroke registry at our institution. The registered data include high signal intensity ischemic lesions on diffusion, T(2)-weighted, or fluid attenuation inversion recovery MRIs, and low signal intensity hemorrhagic lesions on gradient-echo MRIs. An interim analysis at 6 months showed that the time requirement for the lesion registration (183 consecutive patients, 3,226 MR slices with visible stroke-related lesions) was acceptable at about 1 h of labor per patient by a trained assistant with physician oversight. CONCLUSIONS: We have developed a novel image-based stroke registry, with database functions that allow the formulation and testing of intuitive, image-based hypotheses in a manner not easily achievable with conventional alphanumeric stroke registries.

Grading of renal cell carcinoma by 3D morphological analysis of cell nuclei.

This study attempted to develop a method for 3D visualization and quantitative analysis of cell nuclei for renal cell carcinoma (RCC) grading and evaluated the feasibility of such quantitative analysis. We compared the correct classification rate (CCR) for each of the classifiers based on the 2D features of cell nuclei (diameter, area, perimeter, and circularity) and the 3D features of cell nuclei (volume, surface area, and spherical shape factor). The results showed that the classifier using the 3D features provided better results for grading. Our method could overcome the limitations inherent in 2D analysis and could improve the accuracy and reproducibility of quantification of cell nuclei.