Digital Imaging in Anatomic Pathology

Digital images are routinely used by the publishing industry, but most diagnostic pathologists are unfamiliar with the technology and its possibilities. This review aims to explain the basic principles of digital image acquisition, storage, manipulation and use, and the possibilities provided not only in research, but also in teaching and in routine diagnostic pathology. Images of natural objects are usually expressed digitally as 'bitmaps'--rectilinear arrays of small dots. The size of each dot can vary, but so can its information content in terms, for example, of colour, greyscale or opacity. Various file formats and compression algorithms are available. Video cameras connected to microscopes are familiar to most pathologists; video images can be converted directly to a digital form by a suitably equipped computer. Digital cameras and scanners are alternative acquisition tools of relevance to pathologists. Once acquired, a digital image can easily be subjected to the digital equivalent of any conventional darkroom manipulation and modern software allows much more flexibility, to such an extent that a new tool for scientific fraud has been created. For research, image enhancement and analysis is an increasingly powerful and affordable tool. Morphometric measurements are, after many predictions, at last beginning to be part of the toolkit of the diagnostic pathologist. In teaching, the potential to create dramatic yet informative presentations is demonstrated daily by the publishing industry; such methods are readily applicable to the classroom. The combination of digital images and the Internet raises many possibilities; for example, instead of seeking one expert diagnostic opinion, one could simultaneously seek the opinion of many, all around the globe. It is inevitable that in the coming years the use of digital images will spread from the laboratory to the medical curriculum and to the whole of diagnostic pathology.

Use of digital images has increased tremendously in medical science and with that has increased the query on authenticity of the image. Authenticity of the digital image is very important in the area of scientific research, forensic investigations, government documents, etc. With the help of powerful and user friendly image editing software like Microsoft Paint and Photoshop it became extremely easy to tamper with a digital image for malicious objective. Of late this problem has been encountered in medical imaging also for the purpose of fake insurance claims. We propose an algorithm to address this problem by which one can detect and localize tampering in a digital medical image. This algorithm is based on hash based representation of such image and uses discrete wavelet transform method to carry out detection and localization of tampering. We will show that our algorithm is robust against harmless manipulation and sensitive enough for even a minute tampering. Our proposed technique consumes less resource as it works with smaller hash function in comparison with the similar available techniques.

Digitizing high-quality microscopic images and developing input/output technology for displaying those results is critical to tele-pathology in which pathological microscopic images are transferred to remote locations where they are diagnosed by specialists. This paper will discuss the results achieved by directly digitizing pathological microscopic images at a 2k by 2k resolution, and then using a super high definition imaging system to analyze their signals and evaluate compression performance. We will start off by digitizing samples that a pathologist will actually use in making a diagnosis, and then analyze their color distribution and spatial frequencies characteristics by comparing them to general images. This will make it apparent that such pathological images characteristically contain high spatial frequency in their chrominance components. We will also discuss the evaluation results of color differences for L.a.b space and compression ratios achieved when using JPEG to encode pathological images. We will also present a subjective evaluation of the influence sub- sampling of chrominance components has on image quality.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Digital pathology analysis is an advancement in medical diagnostics that leverages digital imaging to enhance the examination and interpretation of pathology slides. By converting traditional glass slides into high-resolution digital images, digital pathology enables pathologists to review and analyze samples with greater precision and efficiency. Machine learning-based techniques in digital pathology are attracting significant attention from pathologists and biologists due to their ability to reduce analysis time and provide objective, accurate results. In particular, semantic segmentation approaches have been widely adopted to isolate specific proteins or cell areas within digital pathology images. However, these methods often exhibit biases toward particular datasets which leads to models that can only process specific targets and lack general applicability. To address this limitation, we propose a target-specific segmentation approach using conditional segmentation networks. We introduce a one-hot vector to control the isolation of target proteins in a conditional manner. The proposed method achieved a pixel accuracy of 83.6% and an intersection over union of 0.7954 on a public pathology segmentation dataset.

Japan has recently introduced the “Audio-Visual Recording of Custodial Interrogation” system to verify the voluntariness of confessions or other disadvantageous statements of the accused that are contained in their depositions. Although digital images recorded in the new system are supposed to be used as supplementary evidence, it appears that they can be used to directly prove the truth of the matter asserted, which is the question to be left open. This article considers whether the digital images can be used to prove guilt or innocence, and if so, whether they need to meet more strict requirements than those for depositions. First, the article discusses the legal grounds pertaining to the application of a conventional hearsay exception to the digital images. Second, it explains how the use of the digital images, which could be concerning, can meet the legal demands of the adversary system underlying the Hearsay Rule. The article concludes that these recordings may be used to prove guilt or innocence if the accused or defense counsels have the meaningful opportunity for impeachment.KeywordsAdmissibilityEvidenceDigital dataInterrogationHearsay

Memory institutions have already started to make digital copies of their documents and objects in order to use modern Information Communications Technologies (ICT) to make their contents easily available. With increasing levels of digitisation, particularly in the cultural heritage sector, the quantity of digital files to be stored very slightly beyond what was produced by Sudanese nation of text processing and much of the hard- and software have been launched or adopted recently. However, there has been little work about the perceptions of SMIs' professionals who are the potential adopters of this technology. Knowledge about such perceptions and their relationship to the application of digital technology by them is important because it can help these professionals to become more aware of the relevance and adaptability technological tools for memory institutions practice. This study focused on these perceptions in regard to the use of a particular technological tool. Its aim was to explore SMIs professionals' perceptions of the ways in which digital collections affect their work, and the reasons why those who don't use digital images or avoid them. To this end, they were asked to describe their use of digital images, the advantages of using digital images, and problems they have faced and to speculate about which impediments need to be overcome in order to begin using digital images. The perspectives of working SMIs professionals on the use digital collections in their institution practice can contribute to our knowledge of how these collections have, and will continue to, influence work. Digital collections cannot be all things to all SMIs professionals. Much debate exists over the role and value of the use of digital images in relation to day-to-day art. The respondents to this study were asked to articulate the potential of digital technology, but this potential is already evidenced by the wide success of distance- researching environments, multimedia projects, animated reconstructions, and research guides in our big multicultural community. In the realm of digital use, many more opportunities await the SMIs profession as related technologies continue to evolve. It is concluded that SMIs constitute local repositories of tacit or explicit contents which will be represented in the digital memory of Sudan (DMS) as an effective gateway to national cultural, historical and heritage image collections of great value to research and development in the country as well as a fully the value of the linkage to global memory net. Finally, the recommendations of this study have been elaborated from UNESCO initiatives in sustainable digital archival and preservation system.

Chapter 10 - Digital Imaging Technologies

In this chapter, the goal is to discuss various types of standards which are relevant to digital pathology images, especially whole slide imaging (WSI), discussing the role they play as well as their current status. We will consider standards primarily in relation to their use in the clinical practice of pathology. In the last ten years much work has been done to extend the DICOM medical imaging standard to include additional metadata relevant to pathology images and specimens as well as to accommodate the special requirements of whole slide microscopic images. This work, along with efforts underway in other organizations, such as HL7 and Integrating the Healthcare Enterprise are laying the foundations for standards based interoperability in pathology that should allow for integration of digital imaging into the clinical workflow of pathologists.

Recent advancements in artificial intelligence applications have highlighted the effectiveness of generative models for domain transfer, image enhancement and simulation. However, when applied to large-scale gigapixel images, the use of traditional patch-based image aggregation methods introduces checkerboard or blocking artifacts, which compromises image quality and fidelity. In this paper, we propose a parametric kernel that is specifically designed to target the underlying grid structure to mitigate these artifacts. With the use of adjustable zero-padding and linear-padding parameters, our kernel provides fine control over the fusion process by combining a central area of constant weights with border regions of gradually decreasing weights. The proposed method was validated using three medical imaging modalities (digital pathology, fluorescence microscopy and ultrasound imaging) for different generative model tasks. The results showed statistically significant improvements (p < 0.0001) in artifact removal when compared to state-of-the-art methods. Quantitative analysis revealed improvements in fusion quality measures for digital pathology, fluorescence microscopy and ultrasound imaging of 7.1%, 27.4% and 20.0%, respectively. Additionally, expert evaluators confirmed superior visual quality and reduced artifacts in blind assessments of reconstructed images, with our method achieving significantly higher scores across all modalities. Our method is versatile, compatible with various generative models and can be easily adjusted by modifying kernel parameters. This kernel-based approach significantly advances the quality of synthesized medical images, directly supporting more reliable clinical assessment and automated analysis. • Novel parametric kernel for mitigating artifacts in patch-based image aggregation. • Our kernel outperforms existing methods across multiple medical imaging modalities. • Versatile and adaptable formulation, independent of the generative model. • Quantitative evaluation demonstrates improved visual quality and reduced artifacts. • Promising applicability to various large field-of-view imaging tasks.

A resource guide for practice development through technology

The use of digital images could be a faster and cheaper alternative technique to assess BW, HCW, and body composition of beef cattle. The objective of this study was to develop equations to predict body and carcass weight and body fat content of young bulls using digital images obtained through a Microsoft Kinect device. Thirty-five bulls with an initial BW of 383 (±5.38) kg (20 Black Angus, 390 [±7.48] kg initial BW, and 15 Nellore, 377 [±8.66] kg initial BW) were used. The Kinect sensor, installed on the top of a cattle chute, was used to take infrared light-based depth videos, recorded before the slaughter. For each animal, a quality control was made, running and pausing the video at the moment that the animal was standing with its body and head in line. One frame from recorded videos was selected and used to analyze the following body measurements: chest width, thorax width, abdomen width, body length, dorsal height, and dorsal area. From these body measurements, 23 indexes were generated and tested as potential predictors. The BW and HCW were assessed with a digital scale, whereas empty body fat (EBF) was estimated through ground samples of all tissues. To better understand the relationship among the measurements, the correlations between final BW (488 [±10.4] kg), HCW (287 [±12.5] kg), EBF (14 [±0.610] % empty BW) content, body measurements (taken through digital images), and developed indexes were evaluated. The REG procedure was used to develop the regressions, and the important independent variables were identified using the options STEPWISE and Mallow's Cp in the SELECTION statement. Chest width was the trait most related to weights and the correlations between this measurement and BW and HCW were above 0.85. The analysis of linear regressions between observed and predicted values showed that all models pass through the origin and have a slope of unity (null hypothesis [H]: = 0 and = 1; ≥ 0.993). The models to estimate BW and HCW of Angus and Nellore presented between 0.69 and 0.84 ( < 0.001), whereas from equations to estimate the EBF were lower ( = 0.43-0.45; ≤ 0.006). Index I5 [(chest width) × body length], related to the animal volume, was significant in all models created to estimate BW and HCW, and it explained more than 70% of the variation. This study indicates that digital images taken through a Microsoft Kinect system have the potential to be used as a tool to estimate body and carcass weight of beef cattle.

An alternative approach for soil characterization is proposed, using digital images and machine learning. The present work investigated the Red, Green, and Blue (RGB) pattern with Artificial Neural Network (ANN) and Random Forest (RF) in the classification of Oxisol and Inceptisol collected in South Brazil. Furthermore, we also built ANN, RF, Partial Least Squares (PLS), and Support Vector Machine (SVM) models from digital images to quantify Total Carbon (TC) content in soil samples. Preliminary evaluations considered the hypothesis that alternative methods of classification and quantification of soil properties might provide results comparable to traditional methods. The TC content of 91 soil samples, 40 from Oxisol and 51 from Inceptisol were determined by dry combustion. ANN and RF as machine learning algorithms were applied to classify the two kinds of soils. The classification quality was assessed by the percentage of correctly classified instances. The results suggest using digital images and machine learning algorithms as a new methodology to soil classification. The best machine learning method was RF which can be used to classify soil types by the RGB channel colors of the soil images. The use of digital images and RF is a clean (eco-friendly), rapid, and affordable strategy analysis for TC quantification in soils. Therefore, the proposed methods represent an advancement in soil classification, such as the determination of the TC content of soils.

Digital Image Security is one of the most important information security topics today. Along with the increasing use of digital images both for communication and documentation purposes, the security of information contained in digital images needs serious attention. Rijndael is a cryptographic method that is not only used for text encryption but also for digital image encryption. Just like block-based cryptographic methods in general, encoding data bytes only has an effect on the internal environment of the block, because the transformation process in Rijndael is done separately for each input block. In digital images, this can result in visible patterns or shapes of objects contained in the image, especially when using the Rijndael standard block size of 4x4. To improve the quality of digital image encryption on Rijndael, several studies have made modifications, especially at the transformation stage. In terms of data, the statistical values obtained from the encryption results such as the correlation coefficient do show an increase, but visually the pattern of objects is still visible and modifications tend to be high. This research proposes a modification of Rijndael which focuses on increasing the input block size from 4x4 to 8x8 with minimal changes to the transformation function. The results showed that the value of the correlation coefficient was better and the results of the encryption visually disguised the shape of the object more than the usual Rijndael, especially in text images, logos and caricatures. From the process carried out there is an increase in the quality of security for the encryption process by 13.22% to 91.48%.

Caveat Spectator: Digital Imaging and Data Manipulation

Inspired by facial recognition, we define an analogous problem in digital pathology called tissue matching. The objective is to match histology image patches to the patient. Unlike many classification problems in pathology, tissue matching comes with its own ground truth, and does not require subjective annotation. Using tissue-matching via deep neural networks, we developed strategies to overcome common sources of noise in histology data, including H&amp;E and slide scanner variability. We demonstrate that the typical approach of increasing the training set size, in the current study up to 12,000 tissue cores, yields only moderate gains in test accuracy, while including a loss term promoting style-invariance cooperatively improves the impact of scaling training set size. Our best neural network learned features that matched patients from the test set of H&amp;E image patches with 93% accuracy (n=104 patients, baseline accuracy &amp;lt;1%). Leveraging this network’s identification ability, we applied its internal representation as a feature vector (tissue fingerprint) to apply to other problems in pathology. We found that a fingerprint-based classifier could predict estrogen receptor status from breast cancer whole-slides on two separate cohorts with high accuracy (AUCROC=0.89), a sizeable improvement over previous approaches. This work presents a novel, scalable, and transparent approach to train neural networks to identify distinctive features of pathology images. These features have demonstrated utility in classifying biomarkers from morphology and have the potential to assist in a number of difficult tasks in pathology, including tissue subtype classification and patient tumor similarity assessments based on morphometry. Citation Format: Rishi Rawat, Fei Sha, Darryl Shibata, Daniel Ruderman, David Agus. Deep learning tissue "fingerprints" to identify patients and predict clinical subtypes of breast cancer from digital pathology images [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 1648.