Tissue Segmentation from Whole-Slide Images Using Lightweight Neural Networks

Pathology slides of malignancies are segmented using lightweight convolutional neural networks (CNNs) that may be deployed on mobile devices. This is made possible by preprocessing candidate images to make CNN analysis tractable and also to exclude regions unlikely to be diagnostically relevant. In a training phase, labeled whole-slide histopathology images are first downsampled and decomposed into square tiles. Tiles corresponding to diseased regions are analyzed to determine boundary values of a visual criterion, image entropy. A lightweight CNN is then trained to distinguish tiles of diseased and non-diseased tissue, and if more than one disease type is present, to discriminate among these as well. A segmentation is generated by downsampling and tiling a candidate image, and retaining only those tiles with values of the visual criterion falling within the previously established extrema. The sifted tiles, which now exclude much of the non-diseased image content, are efficiently and accurately classified by the trained CNN. Tiles classified as diseased tissue ¾ or in the case of multiple possible subtypes, as the dominant subtype in the tile set ¾ are combined, either as a simple union or at a pixel level, to produce a segmentation mask or map. This approach was applied successfully to two very different datasets of large whole-slide images, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast-cancer metastases. Scored using standard similarity metrics, the segmentations exhibited notably high recall, even when tiles were large relative to tumor features.

Edge Location Method for Multidimensional Image Based on Edge Symmetry Algorithm

The most basic feature of an image is edge, which is the junction of one attribute area and another attribute area in the image. It is the most uncertain place in the image and the place where the image information is most concentrated. The edge of an image contains rich information. So, the edge location plays an important role in image processing, and its positioning method directly affects the image effect. In order to further improve the accuracy of edge location for multidimensional image, an edge location method for multidimensional image based on edge symmetry is proposed. The method first detects and counts the edges of multidimensional image, sets the region of interest, preprocesses the image with the Gauss filter, detects the vertical edges of the filtered image, and superposes the vertical gradient values of each pixel in the vertical direction to obtain candidate image regions. The symmetry axis position of the candidate image region is analyzed, and its symmetry intensity is measured. Then, the symmetry of vertical gradient projection in the candidate image region is analyzed to verify whether the candidate region is a real edge region. The multidimensional pulse coupled neural network (PCNN) model is used to synthesize the real edge region after edge symmetry processing, and the result of edge location of the multidimensional image is obtained. The results show that the method has strong antinoise ability, clear edge contour, and precise location.

An Improved Algorithm Robust to Illumination Variations for Reconstructing Point Cloud Models from Images

Reconstructing 3D point cloud models from image sequences tends to be impacted by illumination variations and textureless cases in images, resulting in missing parts or uneven distribution of retrieved points. To improve the reconstructing completeness, this work proposes an enhanced similarity metric which is robust to illumination variations among images during the dense diffusions to push the seed-and-expand reconstructing scheme to a further extent. This metric integrates the zero-mean normalized cross-correlation coefficient of illumination and that of texture information which respectively weakens the influence of illumination variations and textureless cases. Incorporated with disparity gradient and confidence constraints, the candidate image features are diffused to their neighborhoods for dense 3D points recovering. We illustrate the two-phase results of multiple datasets and evaluate the robustness of proposed algorithm to illumination variations. Experiments show that ours recovers 10.0% more points, on average, than comparing methods in illumination varying scenarios and achieves better completeness with comparative accuracy.

“I’m F---ing Moving to Iowa:” Gender and Candidate Image in the 2020 Iowa Caucus

The 2020 presidential race started in Iowa, like it has since 1972. The slate of candidates was the most diverse ever and included six women. This study examines the relationship between candidates’ gender, image, and support among Iowa voters. Iowans have access to candidates that other voters do not, so their perceptions provide unique insight into the construction of candidate images. This study examines the image qualities of leading candidates as perceived by Iowa caucus-goers in the fall of 2019. Using survey data of 576 likely Democratic caucus attendees, I examine the relationship between candidates’ gender, image, and support. I find that women candidates did not benefit from stereotypical strengths of honesty and compassion, but they were perceived as strong leaders. I also find evidence of differences in image evaluations based on respondent sex, with women voters rating untraditional candidates higher than men voters.

Tissue Segmentation from Whole-Slide Images Using Lightweight Neural Networks

Pathology slides of malignancies are segmented using lightweight convolutional neural networks (CNNs) that may be deployed on mobile devices. This is made possible by preprocessing candidate images to make CNN analysis tractable and also to exclude regions unlikely to be diagnostically relevant. In a training phase, labeled whole-slide histopathology images are first downsampled and decomposed into square tiles. Tiles corresponding to diseased regions are analyzed to determine boundary values of a visual criterion, image entropy. A lightweight CNN is then trained to distinguish tiles of diseased and non-diseased tissue, and if more than one disease type is present, to discriminate among these as well. A segmentation is generated by downsampling and tiling a candidate image, and retaining only those tiles with values of the visual criterion falling within the previously established extrema. The sifted tiles, which now exclude much of the non-diseased image content, are efficiently and accurately classified by the trained CNN. Tiles classified as diseased tissue -- or in the case of multiple possible subtypes, as the dominant subtype in the tile set -- are combined, either as a simple union or at a pixel level, to produce a segmentation mask or map. This approach was applied successfully to two very different datasets of large whole-slide images, one (PAIP2020) involving multiple subtypes of colorectal cancer and the other (CAMELYON16) single-type breast-cancer metastases. Scored using standard similarity metrics, the segmentations exhibited notably high recall, even when tiles were large relative to tumor features. With segmentations that can be generated locally and broadcast widely, efficiencies in utilizing expert resources can be achieved.

Multi-View Instance Matching with Learned Geometric Soft-Constraints

We present a new approach for matching urban object instances across multiple ground-level images for the ultimate goal of city-scale mapping of objects with high positioning accuracy. What makes this task challenging is the strong change in view-point, different lighting conditions, high similarity of neighboring objects, and variability in scale. We propose to turn object instance matching into a learning task, where image-appearance and geometric relationships between views fruitfully interact. Our approach constructs a Siamese convolutional neural network that learns to match two views of the same object given many candidate image cut-outs. In addition to image features, we propose utilizing location information about the camera and the object to support image evidence via soft geometric constraints. Our method is compared to existing patch matching methods to prove its edge over state-of-the-art. This takes us one step closer to the ultimate goal of city-wide object mapping from street-level imagery to benefit city administration.

Tweeting Along Partisan Lines: Identity-Motivated Elaboration and Presidential Debates

The influence of partisan identification infiltrates all aspects of a democracy. This study employs an innovative design to explore the presidential debate-viewing experience among young citizens. Data were collected from across the United States for all three 2016 presidential debates between Hillary Clinton and Donald Trump using pretest/posttest surveys and debate viewers’ Twitter posts. Examining Twitter expression as a form of political elaboration, the study employs a social identity theoretical perspective to better understand the process through which viewers form political attitudes. Applying the theory of identity-motivated elaboration (TIME) to presidential debates, the current research illuminates how partisan social identification changes the way viewers think about political issues and, resultantly, evaluate candidates and form political opinions. A strong partisan social identification results in greater identity-consistent elaboration and Twitter expression throughout one’s presidential debate viewing, which results in more biased candidate image evaluations and, subsequently, stronger preference for the in-party candidate.

Shape Similarity Measurement for Known-Object Localization: A New Normalized Assessment

This paper presents a new, normalized measure for assessing a contour-based object pose. Regarding binary images, the algorithm enables supervised assessment of known-object recognition and localization. A performance measure is computed to quantify differences between a reference edge map and a candidate image. Normalization is appropriate for interpreting the result of the pose assessment. Furthermore, the new measure is well motivated by highlighting the limitations of existing metrics to the main shape variations (translation, rotation, and scaling), by showing how the proposed measure is more robust to them. Indeed, this measure can determine to what extent an object shape differs from a desired position. In comparison with 6 other approaches, experiments performed on real images at different sizes/scales demonstrate the suitability of the new method for object-pose or shape-matching estimation.

Peran Kepercayaan Memediasi Hubungan Promosi Politik dan Citra Kandidat Terhadap Keputusan Pemilihan Kepala Desa

<p><em>The purpose of the research was to investigate the intervening effect of trust on the relationship between political promotian and candidate image and selection decision of The Rural Districts Major in Siulak Kecil Hilir. The research of sample was all constituents who used voting rights in the Period of 2016 which accounted for 263 constituents using simple random sampling method. Data was colected through questionnaire with Likert’s scale which analysis using deskriptive qualitative and quantitative as test of validity and reliability, coefisien of determination, hypothesis testing performs hierarchical regression analysis by processing the data using SPSS 19.0 for windows. The result of analysis found that: a) political promotian and candidate image significantly influeced constituens trust and selection decision of The Rural Districts Major in Siulak Kecil Hilir. b) Constituens trust significantly influeced selection decision. While, c) Constituens trust was found as intervening variable between political promotian and candidate image and selection decision of The Rural Districts Major in Siulak Kecil Hilir. The research findings provide practical contribution especially for candidates The Rural Districts Major to future to consider constituents trust and enhancing both political promotion and candidate image.</em></p><p> </p><p>Penelitian ini bertujuan untuk mengetahui pengaruh kepercayaan sebagai variabel pemediasi promosi politik dan citra kandidat terhadap keputusan pemilihan Kepala Desa Siulak kecil Hilir Tahun 2016. Sampel dalam penelitian ini adalah pemilih yang menggunakan hak pilihnya yang berjumlah 263 pemilih dengan metode pengambilan sampel menggunakan cara acak sederhana. Data dikumpulkan melalui kuesioner dengan skala Likert yang dianalisis dengan metode deskriptif kualitatif dan deskriptif kuantitatif seperti uji validitas dan reliabilitas, koefisien determinasi, uji hipotesis dengan analisis regresi bertingkat dengan pengolahan data menggunakan SPSS 19.0 for windows. Hasil penelitian menemukan bahwa: a) Promosi politik dan citra kandidat berpengaruh signifikan terhadap kepercayaan dan keputusan pemilihan Kepala Desa Siulak Kecil Hilir. b) Kepercayaan berpengaruh signifikan terhadap keputusan pemilihan Kepala Desa. Disamping itu, c) Kepercayaan berperan sebagai variabel pemediasi antara promosi politik dan citra kandidat terhadap keputusan pemilihan Kepala Desa Siulak Kecil Hilir, Kerinci. Hasil penelitian ini memberikan rekomendasi praktis khususnya kepada para kandidat Kepala Desa di masa yang akan datang, meningkatkan kepercayaan melalui peningkatan promosi politik dan citra kandidat.</p>