Validation of diagnostic accuracy using digital slides in routine histopathology (original) (raw)

Validation of digital pathology imaging for primary histopathological diagnosis

Histopathology, 2015

Digital Pathology (DP) offers advantages over glass slide microscopy (GS), but data demonstrating a statistically valid equivalent (i.e. non-inferior) performance of DP against GS is required to permit its use in diagnosis. Seventeen pathologists re-reported 3,017 cases by DP. Of these 1,009 were re-reported by the same pathologist and 2,008 by a different pathologist. Re-examination of 10,138 scanned slides (2.22 terabytes) produced 72 variances between GS and DP reports, including 21 clinically significant variances. Ground truth lay with GS in 12 and DP in 9 cases. These results are within the 95% confidence interval for existing intra- and inter- observer variability, proving DP is non-inferior to GS. In three cases the digital platform was deemed responsible for the variance, including a gastric biopsy where Helicobacter pylori only became visible on slides scanned at the x60 setting, and a bronchial biopsy and penile biopsy where dysplasia was reported on DP but not present on...

Validation of Whole-Slide Imaging for Histolopathogical Diagnosis: Current State

Pathobiology, 2016

Rapid advances in informatics and technological improvements have led to the development of high-throughput whole-slide imaging (WSI) scanners able to produce high-quality digital images, which allow achieving a correct diagnosis of the biopsies using virtual viewers. This technology is currently prepared to be introduced in the departments of pathology for routine diagnosis. The aim of this review is to analyze the current evidence regarding the use of WSI in primary or routine diagnosis in the different subspecialties of pathology. An increasing number of studies have shown almost perfect inter- and intraobserver agreement between the diagnoses obtained with WSI and the classical diagnoses based on conventional light microscopy. The only exception seems to be cytology, which still requires some technological development. Although validation studies are needed in some areas of pathology, growing evidence indicates that WSI is a reliable tool for routine diagnosis. Pathologists have...

Primary histologic diagnosis using automated whole slide imaging: a validation study

2006

Background: Only prototypes 5 years ago, high-speed, automated whole slide imaging (WSI) systems (also called digital slide systems, virtual microscopes or wide field imagers) are becoming increasingly capable and robust. Modern devices can capture a slide in 5 minutes at spatial sampling periods of less than 0.5 micron/pixel. The capacity to rapidly digitize large numbers of slides should eventually have a profound, positive impact on pathology. It is important, however, that pathologists validate these systems during development, not only to identify their limitations but to guide their evolution.

Critical Comparison of 31 Commercially Available Digital Slide Systems in Pathology

Advances in new technologies for complete slide digitization in pathology have allowed the appearance of a wide spectrum of technologic solutions for whole-slide scanning, which have been classified into motorized microscopes and scanners. This article describes technical aspects of 31 different digital microscopy systems. The most relevant characteristics of the scanning devices are described, including the cameras used, the speed of digitization, and the image quality. Other aspects, such as the file format, the compression techniques, and the solutions for visualization of digital slides, (including diagnosis-aided tools) are also considered. Most of the systems evaluated allow a high-resolution digitization of the whole slide within about 1 hour using a Ă—40 objective. The image quality of the current virtual microscopy systems is suitable for clinical, educational, and research purposes. The efficient use of digital microscopy by means of image analysis systems can offer important benefits to pathology departments.

Diagnostic Validation of a Whole-Slide Imaging Scanner in Cytological Samples: Diagnostic Accuracy and Comparison With Light Microscopy

Veterinary Pathology, 2019

Digital slides created by whole-slide imaging scanners can be evaluated by pathologists located in remote sites, but the process must be validated before this technology can be applied to routine cytological diagnosis. The aim of this study was to validate a whole-slide imaging scanner for cytological samples. Sixty cytological samples, whose diagnoses were confirmed by gold-standard examinations (histology or flow cytometry), were digitalized using a whole-slide imaging scanner. Digital slides and glass slides were examined by 3 observers with different levels of cytopathological expertise. No significant differences were noted between digital and glass slides in regard to the number of cases correctly diagnosed, or the sensitivity, specificity, or diagnostic accuracy, irrespective of the observers’ expertise. The agreements between the digital slides and the gold-standard examinations were moderate to substantial, while the agreements between the glass slides and the gold-standard...

Manual Stage Acquisition and Interactive Display of Digital Slides in Histopathology

IEEE Journal of Biomedical and Health Informatics, 2014

More powerful PC architectures, high-resolution cameras working at increasing frame rates, and more and more accurate motorized microscopes have boosted new applications in the field of biomedicine and medical imaging. In histopathology, the use of digital slides (DSs) imaging through dedicated hardware for digital pathology is increasing for several reasons: digital annotation of suspicious lesions, recorded clinical history, and telepathology as a collaborative environment. In this paper, we propose the first method known in the literature for real-time whole slide acquisition and displaying conceived for conventional nonautomated microscopes. Differently from DS scanner, our software enables biologists and histopathologists to build and view the DS in real time while inspecting the sample, as they are accustomed to. In addition, since our approach is compliant with existing common microscope positions, provided with camera and PC, this could contribute to disseminate the whole slide technology in the majority of small labs not endowed with DS hardware facilities. Experiments performed with different histologic specimens (referring to tumor tissues of different body parts as well as to tumor cells), acquired under different setup conditions and devices, prove the effectiveness of our approach both in terms of quality and speed performances.

Review on Histopathological Slide Analysis using Digital Microscopy

International Journal of Advanced Science and Technology, 2014

With the increasing research on better algorithms for segmentation of image, it is important to categories the already known technique, their conceptual basis and their overview. This paper presents a systematic survey of the algorithms used in automated cancer diagnosis based on histopathology. The various computational processes involved like preprocessing, feature-extraction, post-processing and disease detection (classifying the area of malignancy) are reviewed.