Digital Image Analysis in Pathology: Benefits and Obligation

Abstract

Abstract. Pathology has recently entered the era of personalized medicine. This brings new expectations for the accuracy and precision of tissue-based diagnosis, in particular, when quantification of histologic features and biomarker expression is required. While for many years traditional pathologic diagnosis has been regarded as ground truth, this concept is no longer sufficient in contemporary tissue-based biomarker research and clinical use. Another major change in pathology is brought by the advancement of virtual microscopy technology enabling digitization of microscopy slides and presenting new opportunities for digital image analysis. Computerized vision provides an immediate benefit of increased capacity (automation) and precision (reproducibility), but not necessarily the accuracy of the analysis. To achieve the benefit of accuracy, pathologists will have to assume an obligation of validation and quality assurance of the image analysis algorithms. Reference values are needed to measure and control the accuracy. Although pathologists' consensus values are commonly used to validate these tools, we argue that the ground truth can be best achieved by stereology methods, estimating the same variable as an algorithm is intended to do. Proper adoption of the new technology will require a new quantitative mentality in pathology. In order to see a complete and sharp picture of a disease, pathologists will need to learn to use both their analogue and digital eyes.Keywords: Quantitative pathology, image processing, quality control, stereologyIn the first decade of the twenty first century, pathology entered the era of personalized medicine. Yet, it is difficult to appraise the magnitude of the change that has been brought about by this commonly used concept. In practical terms, it means that pathology procedures will be required to retrieve much more clinically useful information from tissue samples which frequently will be smaller in size. The evolution of pathology is speeding up; the traditional domain of the pathologist providing qualitative diagnostic * Corresponding author: Arvydas Laurinavicius, National Center of Pathology, Affiliate of Vilnius University Hospital Santariskiu Klinikos, P.Baublio 5, LT-08406 Vilnius, Lithuania. Tel.: +370 5 272 0664 (W) and +370 5 272 0044 (F); E-mail: lauar@vpc.lt. information based on "holistic" view of pathology and limited clinical information is rapidly expanding by the increasing demand for semi-quantitative and quantitative evaluation of pathologic features and biomarker expression (Fig. 1). In this context, anatomic pathology is becoming increasingly quantitative or analytical. This poses new requirements for the accuracy and precision of the diagnostic process.The last decade was also marked by the advancement of virtual microscopy technology enabling high-resolution digitization of the whole microscopic specimen used for diagnosis and research in pathology [1,2]. As in many areas of human activity, switching from analogue to digital presents new opportunities to ...

Early prognosis of metastasis risk in inflammatory breast cancer by texture analysis of tumour microscopic images

“…Computational analysis of medical images by use of texture algorithms has emerged as a structure analysis tool to complement the molecular approaches in detection, diagnosis and prognosis of cancer (Dunn et al 2011;Laurinavicius et al 2012;Angell et al 2013;Laurinavicius et al 2014). Diagnostic and prognostic value of texture analysis has been experimentally established for mammographs (Mohd Khuzi et al 2009), breast ultrasound (Gomez et al 2012), and breast magnetic resonance images (Holli et al 2010).…”

Computer system for remote consultations in the diagnosis of urological malignancies

“…Digital technology and in particular scanning systems for virtual preparations (slides) are widely used in medical practice [2][3][4][5][6]. The use of modern digital technologies in diagnosis of prostate diseases will help to improve the accuracy of diagnosis.…”

Technologie des lames virtuelles

“…Enfin, la visualisation peut être faite en se connectant à une application web avec un navigateur internet usuel. Il y a trois priorités pour les logiciels de visualisation : la qualité des images, la rapidité de leur affichage [4] Enfin, ces fonctionnalités peuvent être complétées par des logiciels d'aide au diagnostic grâce à des outils d'analyse d'image [9,10], tels que le comptage automatique des noyaux de cellules présents sur la lame ou la mesure des surfaces de tissus.…”