Graph-based description of tertiary lymphoid organs at single-cell level.

Our aim is to complement observer-dependent approaches of immune cell evaluation in microscopy images with reproducible measures for spatial composition of lymphocytic infiltrates. Analyzing such patterns of inflammation is becoming increasingly important for therapeutic decisions, for example in transplantation medicine or cancer immunology. We developed a graph-based assessment of lymphocyte clustering in full whole slide images. Based on cell coordinates detected in the full image, a Delaunay triangulation and distance criteria are used to build neighborhood graphs. The composition of nodes and edges are used for classification, e.g. using a support vector machine. We describe the variability of these infiltrates on CD3/CD20 duplex staining in renal biopsies of long-term functioning allografts, in breast cancer cases, and in lung tissue of cystic fibrosis patients. The assessment includes automated cell detection, identification of regions of interest, and classification of lymphocytic clusters according to their degree of organization. We propose a neighborhood feature which considers the occurrence of edges with a certain type in the graph to distinguish between phenotypically different immune infiltrates. Our work addresses a medical need and provides a scalable framework that can be easily adjusted to the requirements of different research questions.

Image analysis of immune cell patterns in the human mammary gland during the menstrual cycle refines lymphocytic lobulitis.

PURPOSE: To improve microscopic evaluation of immune cells relevant in breast cancer oncoimmunology, we aim at distinguishing normal infiltration patterns from lymphocytic lobulitis by advanced image analysis. We consider potential immune cell variations due to the menstrual cycle and oral contraceptives in non-neoplastic mammary gland tissue. METHODS: Lymphocyte and macrophage distributions were analyzed in the anatomical context of the resting mammary gland in immunohistochemically stained digital whole slide images obtained from 53 reduction mammoplasty specimens. Our image analysis workflow included automated regions of interest detection, immune cell recognition, and co-registration of regions of interest. RESULTS: In normal lobular epithelium, seven CD8[Formula: see text] lymphocytes per 100 epithelial cells were present on average and about 70% of this T-lymphocyte population was lined up along the basal cell layer in close proximity to the epithelium. The density of CD8[Formula: see text] T-cell was 1.6 fold higher in the luteal than in the follicular phase in spontaneous menstrual cycles and 1.4 fold increased under the influence of oral contraceptives, and not co-localized with epithelial proliferation. CD4[Formula: see text] T-cells were infrequent. Abundant CD163[Formula: see text] macrophages were widely spread, including the interstitial compartment, with minor variation during the menstrual cycle. CONCLUSIONS: Spatial patterns of different immune cell subtypes determine the range of normal, as opposed to inflammatory conditions of the breast tissue microenvironment. Advanced image analysis enables quantification of hormonal effects, refines lymphocytic lobulitis, and shows potential for comprehensive biopsy evaluation in oncoimmunology.

Interhemispheric hypoconnectivity in schizophrenia: fiber integrity and volume differences of the corpus callosum in patients and unaffected relatives.

Changes in hemispheric asymmetry and inter-hemispheric connectivity have been reported in schizophrenia. However, the genetic contribution to these alterations is still unclear. In the current study, we applied an automatic segmentation method to structural MRI and diffusion tensor imaging (DTI) data and examined volume and fiber integrity of the corpus callosum (CC), the main interhemispheric fiber tract, in 16 chronic schizophrenia (SZ) patients, matched first degree relatives and controls. SZ patients and relatives had smaller CC volumes than controls, particularly in the posterior genu, isthmus and splenium. Fractional anisotropy (FA), an indicator of fiber integrity, was reduced in patients and relatives in the whole CC, the inferior genu, the superior genu and the isthmus. Correspondingly, the mean diffusivity (MD) values of the whole CC and the isthmus were higher in patients and their unaffected relatives, indicating decreased compactness and increased intercellular space. Relatives had intermediate values in the volumetric and fiber integrity measurements between patients and controls. Lower CC volume and fiber integrity in SZ patients were associated with more severe auditory hallucinations. These results support the connectivity hypothesis of SZ (Friston, 1998) and particularly highlight the altered interhemispheric connectivity, which appears to be a genetic feature of SZ risk.

Reduced laterality as a trait marker of schizophrenia--evidence from structural and functional neuroimaging.

Laterality is a characteristic principle of the organization of the brain systems for language, and reduced hemispheric asymmetry has been considered a risk factor for schizophrenia. Here we sought support for the risk factor hypothesis by investigating whether reduced asymmetry of temporal lobe structure and function is also present in unaffected relatives. Sixteen schizophrenia patients, 16 age-matched first-degree relatives, and 15 healthy controls underwent high-resolution three-dimensional anatomical imaging and functional magnetic resonance imaging during auditory stimulation. Both the overall auditory cortex and planum temporale volumes and the lateralization to the left hemisphere were markedly reduced in patients. The decrease of lateralization correlated with increased severity of symptoms. In addition, both the overall functional activation in response to auditory stimulation and its asymmetry were reduced in the patients. Relatives had intermediate values between patients and controls on both structural and functional measures. This study provides added support for the idea that reduced hemispheric asymmetry is a biological risk factor for schizophrenia.

Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma.

In the context of precision medicine with immunotherapies there is an increasing need for companion diagnostic tests to identify potential therapy responders and avoid treatment coming along with severe adverse events for non-responders. Here, we present a retrospective case study to discover image-based signatures for developing a potential companion diagnostic test for ipilimumab (IPI) in malignant melanoma. Signature discovery is based on digital pathology and fully automatic quantitative image analysis using virtual multiplexing as well as machine learning and deep learning on whole-slide images. We systematically correlated the patient outcome data with potentially relevant local image features using a Tissue Phenomics approach with a sound cross validation procedure for reliable performance evaluation. Besides uni-variate models we also studied combinations of signatures in several multi-variate models. The most robust and best performing model was a decision tree model based on relative densities of CD8+ tumor infiltrating lymphocytes in the intra-tumoral infiltration region. Our results are well in agreement with observations described in previously published studies regarding the predictive value of the immune contexture, and thus, provide predictive potential for future development of a companion diagnostic test.

Automated segmentation of lateral ventricles from human and primate magnetic resonance images using cognition network technology.

Automatic segmentation of different types of tissue from magnetic resonance images is of great importance for clinical and research applications, particularly large-scale and longitudinal studies of brain pathology. We developed a fully automated algorithm for the segmentation of lateral ventricles from cranial magnetic resonance images. This problem is of interest in the study of schizophrenia, dementia and other neuropsychiatric disorders. Our algorithm achieves comparable results to expert human raters. The theoretical approach, which is based on an emerging object-oriented technology that has been adapted and evaluated to process 3D data for the first time, may, in the future, be transferred to other important problems of magnetic resonance image analysis like gray/white matter segmentation.

Detection of lobular structures in normal breast tissue.

BACKGROUND: Ongoing research into inflammatory conditions raises an increasing need to evaluate immune cells in histological sections in biologically relevant regions of interest (ROIs). Herein, we compare different approaches to automatically detect lobular structures in human normal breast tissue in digitized whole slide images (WSIs). This automation is required to perform objective and consistent quantitative studies on large data sets. METHODS: In normal breast tissue from nine healthy patients immunohistochemically stained for different markers, we evaluated and compared three different image analysis methods to automatically detect lobular structures in WSIs: (1) a bottom-up approach using the cell-based data for subsequent tissue level classification, (2) a top-down method starting with texture classification at tissue level analysis of cell densities in specific ROIs, and (3) a direct texture classification using deep learning technology. RESULTS: All three methods result in comparable overall quality allowing automated detection of lobular structures with minor advantage in sensitivity (approach 3), specificity (approach 2), or processing time (approach 1). Combining the outputs of the approaches further improved the precision. CONCLUSIONS: Different approaches of automated ROI detection are feasible and should be selected according to the individual needs of biomarker research. Additionally, detected ROIs could be used as a basis for quantification of immune infiltration in lobular structures.

Cognition Network Technology prototype of a CAD system for mammography to assist radiologists by finding similar cases in a reference database.

PURPOSE: We present a new approach for computer-aided detection and diagnosis in mammography based on Cognition Network Technology (CNT). Originally designed for image processing, CNT has been extended to also perform context- and knowledge-driven analysis of tabular data. For the first time using this technology, an application was created and evaluated for fully automatic searching of patient cases from a reference database of verified findings. The application aims to support radiologists in providing cases of similarity and relevance to a given query case. It adopts an extensible and knowledge-driven concept as a similarity measure. METHODS: As a preprocessing step, all input images from more than 400 patients were fully automatically segmented and the resulting objects classified--this includes the complete breast shape, the position of the mammilla, the pectoral muscle, and various potential candidate objects for suspicious mass lesions. For the similarity search, collections of object properties and metadata from many patients were combined into a single table analysis project. Extended CNT allows for a convenient implementation of knowledge-based structures, for example, by meaningfully linking detected objects in different breast views that might represent identical lesions. Objects from alternative segmentation methods are also be considered, so as to collectively become a sufficient set of base-objects for identifying suspicious mass lesions. RESULTS: For 80% of 112 patient cases with suspicious lesions, the system correctly identified at least one corresponding mass lesion as an object of interest. In this database, consisting of 1,024 images from a total of 303 patients, an average of 0.66 false-positive objects per image were detected. An additional testing database contained 480 images from 120 patients, 15 of whom were annotated with suspicious mass lesions. Here, 47% (7 out of 15) of these were detected automatically with 1.13 false-positive objects per image. A diagnosis is predicted for each patient case by applying a majority vote from the reference findings of the ten most similar cases. Two separate evaluation scenarios suggest a fraction of correct predictions of respectively 79 and 76%. CONCLUSION: Cognition Network Technology was extended to process table data, making it possible to access and relate records from different images and non-image sources, such as demographic patient data or parameters from clinical examinations. A prototypal application enables efficient searching of a patient and image database for similar patient cases. Using concepts of knowledge-driven configuration and flexible extension, the application illustrates a path to a new generation of future CAD systems.

Mild cognitive impairment in the elderly is associated with volume loss of the cholinergic basal forebrain region.

BACKGROUND: Cholinergic neurons within the basal forebrain are assumed to be an early (preclinical) manifestation site of pathological changes in Alzheimer's disease (AD). METHODS: We used morphometric magnetic resonance imaging (MRI) to detect and quantify atrophic changes in the basal forebrain of subjects suffering from amnestic mild cognitive impairment (aMCI). Three Tesla magnetic resonance (MR) data of 26 aMCI patients, 46 cognitively normal elderly control subjects (CO), and 12 patients suffering from Alzheimer's dementia were analyzed, including segmentation and quantification of brain tissue as well as a segmentation of basal forebrain structures (substantia innominata [SI]). RESULTS: We found the volume of the SI to be significantly different between groups in that control subjects showed the largest SI volumes, followed by aMCI and AD patients. CONCLUSIONS: These results are in line with the hypothesis that cell loss within the cholinergic basal forebrain regions occurs already in the early (predementia) stage of AD. In vivo quantification of these changes might be of use as a novel neuroimaging marker of cholinergic neurodegeneration in AD.

The corpus callosum in schizophrenia-volume and connectivity changes affect specific regions.

The corpus callosum (CC) is of great interest for pathophysiological models of schizophrenia. Volume and structural integrity of the CC have been examined by volumetric and diffusion tensor imaging (DTI) studies, but results were not consistent across methods or studies. A possible explanation may be varying methodologies and accuracy of measurements based on a single slice or small regions of interest. In addition, none of the studies examined volume and diffusion values in the same group of patients, and thus the relationship between these anatomical measures is not clear. We used an automatic algorithm to segment seven midline slices of the CC from DTI images. We compared volume and the DTI measures fractional anisotropy (FA) and mean diffusivity (MD) in the CC and its subdivisions in the schizophrenia patients and matched controls. Patients had decreased volume, decreased FA and increased MD of the whole CC. The important novel finding is, however, that not all regions were equally affected by anatomical changes. The results emphasize the importance of using different methods in evaluation of white matter (WM) in schizophrenia to avoid false negative findings. In addition, the measures were highly correlated with each other, implying a common pathological process influencing FA, MD and volume of the CC. Although we cannot rule out other mechanisms affecting volume, FA and MD, converging evidence from cytoarchitectonic and genetic studies suggests that WM changes observed in schizophrenia may involve disintegration of healthy, functional axons and strengthening of aberrant connections resulting in increased severity of clinical symptoms.