Region Of Interest Identification Research Articles

Differential spatial transcriptome profile of the hippocampal formation of protected PSEN1 E280A familial Alzheimer’s disease cases

AbstractBackgroundWe have described two cases with ∼ 30 years of delayed disease onset among carriers of PSEN1 mutation E280A, suffering from familial Alzheimer’s disease (FAD). One case was homozygous for the ApoE Christchurch (hApoEch) mutation. This case showed sparse hyperphosphorylated tau (pTau) pathology in several cortical areas. The second case was heterozygous for the RELN‐COLBOS mutation and was globally affected by severe pTau and amyloid beta pathology, with evidence of localized cellular protection in the entorhinal cortex (EC). Here we used digital spatial profiling (DSP) transcriptomics to characterize the hippocampal formation of FAD protected cases and identify possible molecular mechanisms of protection.MethodsIn depth morphological characterization of the EC together with identification of thirteen different regions of interest (ROIs) were performed in Formalin‐fixed paraffinized 3 mm thick slides taken from the hippocampal formation (Fig. 1A) of the RELN‐COLBOS FAD case, the hApoEch FAD case, three FAD cases, and three sporadic Alzheimer’s cases (SAD). Slides were immunostained for NeuN and GFAP for morphological ROIs identification and processed for localized transcriptome analyses using the GeoMX DSP platform from Nanostring. Obtained data was processed for quality control, dimensionality reduction and differential gene expression (DGE) analyses.ResultsDimensionality reduction of transcriptomic data obtained from all ROIs and studied cases showed a distinctive distribution of ROIs belonging to both protected cases (Fig. 1B). Furthermore, DGE was observed in all sampled ROIs. ROIs such as hippocampal white matter or dentate gyri showed a higher number of differentially expressed genes due to a more homogeneous cellular composition of the ROIs (Fig. 1C). Also, EC and dentate gyrus from FAD protected cases showed distinctive molecular signatures compatible with excitatory neuronal pathways (Fig. 1D). Complementary morphological analyses showed increased neuronal density in the supragranular region of the EC in the RELN‐COLBOS FAD protected case, specifically in neuronal layer II.ConclusionOur results suggest that regardless of the protective gene conferring protection to FAD, the EC is one key protected structure with distinctive regional transcriptomic profiles suggesting the preservation of neuronal function in this region and hinting towards a possible therapeutic target in the protection against Alzheimer’s disease.

Melanoma Skin Cancer and Nevus Mole Classification using Intensity Value Estimation with Convolutional Neural Network

Melanoma skin cancer is one of the most dangerous and life-threatening cancer. Exposure to ultraviolet rays may damage the skin cell's DNA, which causes melanoma skin cancer. However, it is difficult to detect and classify melanoma and nevus mole at the immature stages. In this work, an automatic deep learning system is developed based on the intensity value estimation with a convolutional neural network model (CNN) to detect and classify melanoma and nevus mole more accurately. Since intensity levels are the most distinctive features for object or region of interest identification, the high-intensity pixel values are selected from the extracted lesion images. Incorporating those high-intensity features into the CNN improves the overall performance than the state-of-the-art methods for detecting melanoma skin cancer. To evaluate the system, we used 5-fold cross-validation. Experimental results show that a superior percentage of accuracy (92.58%), Sensitivity (93.76%), Specificity (91.56%), and Precision (90.68%) are achieved.

A transfer function optimization using visual saliency for region of interest-based direct volume rendering

Direct volume rendering (DVR) helps data interpretation by allowing users to focus attention on specific regions in a volume that are of most interest. The effective generation of these regions of interest (ROIs)-based DVR images, however, still remains a major challenge. It involved the intricate process of assigning appropriate optical parameters (opacity and/or color) to the ROIs and other regions in the volume using transfer function (TF) specification. Achieving an optimal TF often requires multiple iterations of a trial-and-error process, starting from scratch in each case, which is time-consuming and labor-intensive. To address this issue, there have been various TF optimization approaches, which could automatically fine-tune an initial TF toward an optimal solution satisfying a pre-defined objective metric. Although effective, the previous objective metrics exhibit two inherent limitations: (i) they were only capable of optimizing ROIs along an individual viewing ray of the volume, and the relationship with neighboring ROIs (as context) from other rays could not be controlled; (ii) the TF parameters to be optimized were restricted to opacity (i.e., the observability of ROIs) and did not include color which is also important to enhance the visual distinction of ROIs. In this work, we propose a new TF optimization approach by introducing an objective metric using visual saliency. Visual saliency is a biologically-inspired measure to aid the identification of ROIs considered important relative to other regions within an image according to the human visual system. Our novel adoption of visual saliency enables the TF optimization to take into account all ROIs in a volume (with its rendered image) implicitly. In addition, both opacity and color parameters can be applied to the TF optimization. Given the user-assigned target visual saliency of ROIs, our approach can produce more controllable and complete ROIs-based DVR images. We outline our approach by applications to a variety of volumetric datasets and highlight its advantages in comparison to the dominant TF optimization approaches that use visibility-based objective metrics.

A Space-Refine Paradigm for Automatic Carotid Artery Centerline Extraction in Magnetic Resonance Imaging.

Vessel centerline extraction is essential for carotid stenosis assessment and atherosclerotic plaque identification in clinical diagnosis. Simultaneously, it provides a region of interest identification and boundary initialization for computer-assisted diagnosis tools. In magnetic resonance imaging (MRI) cross-sectional images, the lumen shape and vascular topology result in a challenging task to extract the centerline accurately. To this end, we propose a space-refine framework, which exploits the positional continuity of the carotid artery from frame to frame to extract the carotid artery centerline. The proposed framework consists of a detector and a refinement module. Specifically, the detector roughly extracts the carotid lumen region from the original image. Then, we introduce a refinement module that uses the cascade of regressors from a detector to perform sequence realignment of lumen bounding boxes for each subject. It improves the lumen localization results and further enhances the centerline extraction accuracy. Verified by large carotid artery data, the proposed framework achieves state-of-the-art performance compared to conventional vessel centerline extraction methods or standard convolutional neural network approaches.Clinical relevance- Our proposed framework can be used as an important aid for physicians to quantitatively analyze the carotid artery in clinical practice. It is also used as a new paradigm for extracting the centerline of carotid vessels in computer-assisted tools.

Atomic Force Microscopy Cantilever-Based Nanoindentation: Mechanical Property Measurements at the Nanoscale in Air and Fluid.

An atomic force microscope (AFM) fundamentally measures the interaction between a nanoscale AFM probe tip and the sample surface. If the force applied by the probe tip and its contact area with the sample can be quantified, it is possible to determine the nanoscale mechanical properties (e.g., elastic or Young's modulus) of the surface being probed. A detailed procedure for performing quantitative AFM cantilever-based nanoindentation experiments is provided here, with representative examples of how the technique can be applied to determine the elastic moduli of a wide variety of sample types, ranging from kPa to GPa. These include live mesenchymal stem cells (MSCs) and nuclei in physiological buffer, resin-embedded dehydrated loblolly pine cross-sections, and Bakken shales of varying composition. Additionally, AFM cantilever-based nanoindentation is used to probe the rupture strength (i.e., breakthrough force) of phospholipid bilayers. Important practical considerations such as method choice and development, probe selection and calibration, region of interest identification, sample heterogeneity, feature size and aspect ratio, tip wear, surface roughness, and data analysis and measurement statistics are discussed to aid proper implementation of the technique. Finally, co-localization of AFM-derived nanomechanical maps with electron microscopy techniques that provide additional information regarding elemental composition is demonstrated.

CRISP: a deep learning architecture for GC × GC-TOFMS contour ROI identification, simulation and analysis in imaging metabolomics.

Two-dimensional gas chromatography–time-of-flight mass spectrometry (GC × GC–TOFMS) provides a large amount of molecular information from biological samples. However, the lack of a comprehensive compound library or customizable bioinformatics tool is currently a challenge in GC × GC–TOFMS data analysis. We present an open-source deep learning (DL) software called contour regions of interest (ROI) identification, simulation and untargeted metabolomics profiler (CRISP). CRISP integrates multiple customizable deep neural network architectures for assisting the semi-automated identification of ROIs, contour synthesis, resolution enhancement and classification of GC × GC–TOFMS-based contour images. The approach includes the novel aggregate feature representative contour (AFRC) construction and stacked ROIs. This generates an unbiased contour image dataset that enhances the contrasting characteristics between different test groups and can be suitable for small sample sizes. The utility of the generative models and the accuracy and efficacy of the platform were demonstrated using a dataset of GC × GC–TOFMS contour images from patients with late-stage diabetic nephropathy and healthy control groups. CRISP successfully constructed AFRC images and identified over five ROIs to create a deepstacked dataset. The high fidelity, 512 × 512-pixels generative model was trained as a generator with a Fréchet inception distance of <47.00. The trained classifier achieved an AUROC of >0.96 and a classification accuracy of >95.00% for datasets with and without column bleed. Overall, CRISP demonstrates good potential as a DL-based approach for the rapid analysis of 4-D GC × GC–TOFMS untargeted metabolite profiles by directly implementing contour images. CRISP is available at https://github.com/vivekmathema/GCxGC-CRISP.

Aortic Dissection Diagnosis Based on Sequence Information and燚eep燣earning

Aortic dissection (AD) is one of the most serious diseases with high mortality, and its diagnosis mainly depends on computed tomography (CT) results. Most existing automatic diagnosis methods of AD are only suitable for AD recognition, which usually require preselection of CT images and cannot be further classified to different types. In this work, we constructed a dataset of 105 cases with a total of 49021 slices, including 31043 slices expert-level annotation and proposed a two-stage AD diagnosis structure based on sequence information and deep learning. The proposed region of interest (RoI) extraction algorithm based on sequence information (RESI) can realize high-precision for RoI identification in the first stage. Then DenseNet-121 is applied for further diagnosis. Specially, the proposed method can judge the type of AD without preselection of CT images. The experimental results show that the accuracy of Stanford typing classification of AD is 89.19%, and the accuracy at the slice-level reaches 97.41%, which outperform the state-of-art methods. It can provide important decision-making information for the determination of further surgical treatment plan for patients.

Emotion discrimination using source connectivity analysis based on dynamic ROI identification

Emotion plays a predominant role in external situations or events in daily life. Different emotions display different connectivity patterns through related information processing. Electroencephalography (EEG)-based emotional recognition is a controversial subject in the field of affective computing. However, EEG recordings are mixed-signals and cannot show the exact information about active sources from different emotional states. In this paper, we propose a method for emotion discrimination based on the source connectivity method. Features are extracted as connectivity patterns in different frequency bands based on emotion-based reconstructed EEG sources using sLORETA. In order to identify most related brain regions to emotions, we identify data-driven spatially compact regions, called regions of interest (ROIs), based on the reconstructed neural activity. Also, to estimates ROI time series with the intrinsic non-stationarity of neural activity, an iterative dynamic approach is used. The method explicitly contains a dynamic constraint, considering the neural activity evolution for advance connectivity analysis. Throughout this study, we consider three connectivity measures widely applied to emotion recordings including, iCoh, PLV, and WPLI. In the next step, the connectivity patterns are used as features to discriminate emotion states by training an SVM classifier. The performance of the proposed method is assessed over a real high-resolution emotional database. This study reveals that the proposed method can identify meaningful connection features between main emotion-related brain regions, leading to higher interpretability and accuracy. Our results demonstrate that the ROI-wise iCoh features enhance the average of accuracy up to 83.84% in comparison with raw EEG features (71.70%).

Aptamer Probes Labeled with Lanthanide-Doped Carbon Nanodots Permit Dual-Modal Fluorescence and Mass Cytometric Imaging.

High‐dimensional imaging mass cytometry (IMC) enables simultaneous quantification of over 35 biomarkers on one tissue section. However, its limited resolution and ultralow acquisition speed remain major issues for general clinical application. Meanwhile, conventional immunofluorescence microscopy (IFM) allows sub‐micrometer resolution and rapid identification of the region of interest (ROI), but only operates with low multiplicity. Herein, a series of lanthanide‐doped blue‐, green‐, and red‐fluorescent carbon nanodots (namely, B‐Cdots(Ln1), G‐Cdots(Ln2), and R‐Cdots(Ln3)) as fluorescence and mass dual‐modal tags are developed. Coupled with aptamers, B‐Cdots(159Tb)‐A10‐3.2, G‐Cdots(165Ho)‐AS1411, and R‐Cdots(169Tm)‐SYL3C dual‐functional aptamer probes, which are then multiplexed with commercially available Maxpar metal‐tagged antibodies for analyzing clinical formalin‐fixed, paraffin‐embedded (FFPE) prostatic adenocarcinoma (PaC) tissue, are further synthesized. The rapid identification of ROI with IFM using fluorescence signals and subsequent multiplexed detection of in situ ROI with IMC using the same tissue section is demonstrated. Dual‐modal probes save up to 90% IMC blind scanning time for a standard 3.5 mm × 3.5 mm overall image. Meanwhile, the IFM provides refined details and topological spatial distributions for the functional proteins at optical resolution, which compensates for the low resolution of the IMC imaging.

The cut-off value of ADC to differentiate benign from malignant breast lesions

Background: Diffusion-weighted MRI is a fast, unenhanced modality that shows promise in identifying mammographically occult malignancy and warrants further investigation as an alternative supplemental breast cancer screening tool.Aim of study: To estimate the diagnostic accuracy of diffusion wighted imaging and apparent diffusion coeffient (ADC) value in the differentiation between benign and malignant breast lesions, and to obtain a cutoff ADC value between benign and malignant breast lesions along with histopathological correlation. Materials and Methods: A prospective study of 56 patients with present with breast mass who examined at 1.5 tesla MRI & proved by histopathology. ADC value were a quired at b values of 0, 600, 850 s/mm² after identification of ROI (Region of interest) placement. ADC value with histopathology correlation was analyzed. Results: From total 56 lesions, 24 lesions were histologically malignant and 32 were histologically benign. With an ADC cut‑off value of 1.31 × 10−3 mm2/s for malignant lesions, a sensitivity of 100% and specificity of 72.1% was obtained. The false‑postive lesions were one intraductal papilloma & 3 abcesses in which a low ADC value was obtained. Purely DCIS (Ductal carcinoma in situ) lesions presenting as non‑mass‑like enhancement had a high ADC value of 1.2‑1.3 × 10−3 mm2/s, thereby decreasing specificity. Conclusion: Diffusion‑weighted Imaging is a functionl quantitative assessment by ADC value, may act as an efficient tool in increasing the diagnostic accuracy and specificity of breast MRI in the characterization of different breast lesions.

Folded concave penalized learning of high-dimensional MRI data in Parkinson’s disease

BackgroundBrain MRI is a promising technique for Parkinson’s disease (PD) biomarker development. Its analysis, however, is hindered by the high-dimensional nature of the data, particularly when the sample size is relatively small. New MethodThis study introduces a folded concave penalized machine learning scheme with spatial coupling fused penalty (fused FCP) to build biomarkers for PD directly from whole-brain voxel-wise MRI data. The penalized maximum likelihood estimation problem of the model is solved by local linear approximation. ResultsThe proposed approach is evaluated on synthetic and Parkinson’s Progression Marker Initiative (PPMI) data. It achieves good AUC scores, accuracy in classification, and biomarker identification with a relatively small sample size, and the results are robust for different tuning parameter choices. On the PPMI data, the proposed method discovers over 80 % of large regions of interest (ROIs) identified by the voxel-wise method, as well as potential new ROIs. Comparison with Existing MethodsThe fused FCP approach is compared with L1, fused-L1, and FCP method using three popular machine learning algorithms, logistic regression, support vector machine, and linear discriminant analysis, as well as the voxel-wise method, on both synthetic and PPMI datasets. The fused FCP method demonstrated better accuracy in separating PD from controls than L1 and fused-L1 methods, and similar performance when compared with FCP method. In addition, the fused FCP method showed better ROI identification. ConclusionsThe fused FCP method can be an effective approach for MRI biomarker discovery in PD and other studies using high dimensionality data/low sample sizes.

Automatic three‐dimensional detection and volume estimation of low‐grade gliomas

AbstractBrain tumor segmentation is routinely needed in diagnostic radiology. Automatic volume estimation has been used for diagnosis improvement and treatment process. This article presents a new approach for tumor volume estimation, using a variational level set method. The new adapted representation of intensity allows the method to be efficient in the region of interest identification, regardless the shape, size, and location of the tumor. For the estimation of an optimal bounding box, a fuzzy preference optimization model is used. The proposed approach is suitable for the zero level set initialization as well as for the reduction of the processing area, which ultimately speeds up the curve evolution. Moreover, tumor contours are determined using the hybrid level set technique, which combines the gradient and local phase information as an edge indicator term. Such an approach is robust to attenuation and intensity inhomogeneity. The proposed method is evaluated using a set of real and synthetic images. Our method achieved a performance of 96% accuracy, with an average execution time of 4.75 seconds. The proposed method is fast, accurate, and does not require training data or prior knowledge. With such experimental results, our approach outperforms 18 state‐of‐the‐art methods.

Intelligent Perception System of Robot Visual Servo for Complex Industrial Environment.

Robot control based on visual information perception is a hot topic in the industrial robot domain and makes robots capable of doing more things in a complex environment. However, complex visual background in an industrial environment brings great difficulties in recognizing the target image, especially when a target is small or far from the sensor. Therefore, target recognition is the first problem that should be addressed in a visual servo system. This paper considers common complex constraints in industrial environments and proposes a You Only Look Once Version 2 Region of Interest (YOLO-v2-ROI) neural network image processing algorithm based on machine learning. The proposed algorithm combines the advantages of YOLO (You Only Look Once) rapid detection with effective identification of ROI (Region of Interest) pooling structure, which can quickly locate and identify different objects in different fields of view. This method can also lead the robot vision system to recognize and classify a target object automatically, improve robot vision system efficiency, avoid blind movement, and reduce the calculation load. The proposed algorithm is verified by experiments. The experimental result shows that the learning algorithm constructed in this paper has real-time image-detection speed and demonstrates strong adaptability and recognition ability when processing images with complex backgrounds, such as different backgrounds, lighting, or perspectives. In addition, this algorithm can also effectively identify and locate visual targets, which improves the environmental adaptability of a visual servo system

A hybrid CAD system for lung nodule detection using CT studies based in soft computing

Lung modules are an initial indicator as to whether or not a patient will develop lung carcinoma which has a significant mortality rate if it is not detected at an early stage. The detection of these lung nodules is a complex task and is time-consuming for the radiologist.For these reasons, CAD systems have been developed and employed for the detection of lung nodules. In this article, we present a CAD system that uses a hybrid strategy: techniques for the analysis of medical images and soft computing (fuzzy clustering, SVM and ANN) with a description of the main stages: preprocessing, identification of ROIs (region of interest), creation of VOIs (volume interests) and ROI classifications. Remarkable elements of the system are: detection automation, a new phase to reduce the ROIs false positives and a new algorithm to build the VOIs in order to improve the location and a better detection. For its development, helical CT studies proceeding from the LIDC public database have been used.The system achieves similar and even better results to other CADs for the same purpose with a sensitivity of 82% and a number of false positives of 7.3 per study.

Automatic segmentation of melanoma using superpixel region growing technique

Melanoma is the most life threatening type of cancer which contributes to the highest mortality rate. Early detection of melanoma facilitates better prognosis and increases survival rates. High infiltration of melanoma and advanced digital imaging technologies have exhilarated concern among the public, calling for initial screenings. However, melanoma screening is considered as a non trivial problem even by expert medical practitioners, in spite of several diagnostic algorithms. There is an enthralling need for automated melanoma detection systems due to the surge in the melanoma population and lack of trained dermatologists. Computational models for Melanoma detection are based on learning from the Region of Interest (RoI). Nevertheless, identification of RoI itself poses several challenges due to the diverse structural and chromatic features on the surface of the skin. This paper proposes a superpixel region growing based approach for segmentation of the melanoma region for further analysis. It is based on the Gaussian Mixture Model superpixels which segment the candidate image into accurate homogenous regions. The superiority of the system is demonstrated with performance metrics and comparisons on a standard dataset. This system is an impending solution to perform melanoma screenings with ease.

Design space exploration and optimization using self-organizing maps

Identifying regions of interest (RoI) in the design space is extremely useful while building metamodels with limited computational budget. Self-organizing maps (SOM) are used as a visualization technique for design space exploration that permits identifying RoI. Conventional implementation of SOM is susceptible to folds or intersections that hinder visualizing the design space. This work proposes a modified SOM algorithm whose maps are interpretable and that does not fold and allows smoother input and performance space visualization. The modified algorithm enables identification of RoI and additional sampling in the identified RoI allows building accurate Kriging metamodel, which is then used for optimization. The proposed approach is demonstrated on benchmark nonlinear analytical examples and two practical engineering design examples. Results show that the proposed approach is highly efficient in identifying the RoI and in obtaining the optima with less samples.

Data-Driven Identification of the Regions of Interest for Fiber Tracking in Patients with Brain Tumors

We investigated the added value of combining information from direction-encoded color (DEC) maps with high-resolution structural magnetic resonance imaging scans (T1-weighted images [T1WIs]) to improve the identification of regions of interest (ROIs) for fiber tracking during preoperative planning for patients with brain tumors. The dataset included 42 patients with gliomas and 10 healthy subjects from the Human Connectome Project. For identification of the ROIs, we combined the structural information from high-resolution T1WIs and the directional information from DEC maps. To test our hypothesis, we examined the interrater and intrarater agreement. We identified specific ROIs to extract the main white matter bundles. The directional information from the DEC maps combined with the T1WIs (T1WI-DEC maps) had significantly facilitated ROI identification in patients with brain tumors, especially patients in whom the tracts had been displaced by the mass effect of the tumor. Fiber tracking using the combined T1WI-DEC maps showed significantly greater inter- and intrarater agreement compared with using either T1WI or DEC maps alone. Combining the information from diffusion-derived color-encoded maps with high-resolution anatomical details from structural imaging (T1WI-DEC map), especially in patients with brain tumors, could be useful for accurate identification of the ROIs.

Automated Artery Localization and Vessel Wall Segmentation using Tracklet Refinement and Polar Conversion.

Quantitative analysis of blood vessel wall structures is important to study atherosclerotic diseases and assess cardiovascular event risks. To achieve this, accurate identification of vessel luminal and outer wall contours is needed. Computer-assisted tools exist, but manual preprocessing steps, such as region of interest identification and/or boundary initialization, are still needed. In addition, prior knowledge of the ring shape of vessel walls has not been fully explored in designing segmentation methods. In this work, a fully automated artery localization and vessel wall segmentation system is proposed. A tracklet refinement algorithm was adapted to robustly identify the artery of interest from a neural network-based artery centerline identification architecture. Image patches were extracted from the centerlines and converted in a polar coordinate system for vessel wall segmentation. The segmentation method used 3D polar information and overcame problems such as contour discontinuity, complex vessel geometry, and interference from neighboring vessels. Verified by a large (>32000 images) carotid artery dataset collected from multiple sites, the proposed system was shown to better automatically segment the vessel wall than traditional vessel wall segmentation methods or standard convolutional neural network approaches. In addition, a segmentation uncertainty score was estimated to effectively identify slices likely to have errors and prompt manual confirmation of the segmentation. This robust vessel wall segmentation system has applications in different vascular beds and will facilitate vessel wall feature extraction and cardiovascular risk assessment.

Abstract 489: Multi-parameter tissue section imaging and retrieval of image-defined micro-regions for RNA sequencing using the RareCyte® platform

Abstract Background: Tumor tissue imaging allows for a contextual understanding of tumor cells in relation to the immune microenvironment. The ability to interrogate tissues for multiple proteins that define microscopic regions of interest (ROI) and investigate gene expression of cells in those regions is needed for advancing immuno-oncology therapeutic and biomarker discovery. The RareCyte CyteFinder® instrument provides integrated multi-parameter imaging and micro-region retrieval capabilities for sequencing and transcript-level analysis. Methods: Formalin-fixed, paraffin-embedded (FFPE) sections of tonsil and breast carcinoma sections were stained with a panel of antibodies to CD3, CD8, CD20, cytokeratin, and Ki-67. Frozen sections were stained with antibodies to CD3, CD4, CD8, CD19, and Ki-67. All sections were also stained with SYTOX Orange (nuclear dye). Whole-slide six-color scanning and ROI identification was performed with the CyteFinder instrument. For frozen sections, 40µm diameter micro-regions were retrieved directly from the antibody-stained section using the CytePicker® module. For FFPE sections, ROI were identified on the antibody-stained sample and micro-regions were retrieved from the same location on an adjacent section stained with DRAQ5 only. RNA from retrieved micro-regions was amplified and sequenced and differential gene expression analysis was performed. Results: Tonsil staining distinctly identified crypt lining (cytokeratin), T cell (CD3, CD4, CD8) and B cell (CD19, CD20) compartments; Ki-67 was prominently expressed in germinal centers. Breast carcinoma staining distinctly identified tumor cells (cytokeratin) and CD8-positive T cells that were prominent at the periphery of the tumor with smaller numbers interspersed. Ki-67 staining was variably present in tumor cell nuclei. Comparative RNA analysis of four frozen tonsil T cell zone micro-regions against four B cell zone micro-regions resulted identified genes with expected differential gene expression pattern, including T cell zone upregulation of CD8a, CCL19, and CCL21 and downregulation of CD38, CR2, and CXCL13. Analysis of FFPE tonsil micro-regions comparing four germinal centers with areas outside the follicle identified genes differentially regulated within the germinal center, including B cell markers CD19, CD22 and CD79a. Out of 20 selected genes preferentially expressed in the germinal center, 16 (80%) were confirmed by interrogation of the Human Protein Atlas to be specific or enriched in germinal centers by immunohistochemical staining. Conclusions: This study demonstrates high quality six-parameter imaging of tonsil and breast carcinoma tissues. Confirmation of tonsil immune cell type by gene expression analysis supports use of the RareCyte platform for retrieval of defined tissue micro-regions for RNA sequencing in frozen and FFPE samples. Citation Format: Rebecca Podyminogin, Nolan Ericson, Jia-Ren Lin, Yu-An Chen, Peter Sorger, Eric Kaldjian, Tad George, Lance U'Ren. Multi-parameter tissue section imaging and retrieval of image-defined micro-regions for RNA sequencing using the RareCyte® platform [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 489.

Embedded Automated Vision for Double Parking Identification System

&lt;span&gt;The aim of this work is to assist the city administration issue which involve the traffic flow disruption in an urban area. One of the causes of traffic flow disruption is double parking; thus, in this work, an automated double parking identification and alert system was developed using embedded vision system and internet of things. A camera was utilized to acquire the image of a parking area, and the image was processed using Beaglebone Black processor. A computer vision algorithm was developed to process the image using background subtraction, region of interest identification, and color analysis. When a double parked vehicle is detected, the data was sent into the cloud automatically to alert the city administrator for further action. The developed system achieved 91% accuracy in detecting the traffic violation of double parking.&lt;/span&gt;