A validation study of whole slide imaging for primary diagnosis of lymphoma

Validation of a whole slide image management system for metabolic-associated steatohepatitis for clinical trials

The gold standard for enrollment and endpoint assessment in metabolic dysfunction-associated steatosis clinical trials is histologic assessment of a liver biopsy performed on glass slides. However, obtaining the evaluations from several expert pathologists on glass is challenging, as shipping the slides around the country or around the world is time-consuming and comes with the hazards of slide breakage. This study demonstrated that pathologic assessment of disease activity in steatohepatitis, performed using digital images on the AISight whole slide image management system, yields results that are comparable to those obtained using glass slides. The accuracy of scoring for steatohepatitis (nonalcoholic fatty liver disease activity score ≥4 with ≥1 for each feature and absence of atypical features suggestive of other liver disease) performed on the system was evaluated against scoring conducted on glass slides. Both methods were assessed for overall percent agreement with a consensus "ground truth" score (defined as the median score of a panel of three pathologists' glass slides). Each case was also read by three different pathologists, once on glass and once digitally with a minimum 2-week washout period between the modalities. It was demonstrated that the average agreement across three pathologists of digital scoring with ground truth was noninferior to the average agreement of glass scoring with ground truth [noninferiority margin: -0.05; difference: -0.001; 95% CI: (-0.027, 0.026); and p < 0.0001]. For each pathologist, there was a similar average agreement of digital and glass reads with glass ground truth (pathologist A, 0.843 and 0.849; pathologist B, 0.633 and 0.605; and pathologist C, 0.755 and 0.780). Here, we demonstrate that the accuracy of digital reads for steatohepatitis using digital images is equivalent to glass reads in the context of a clinical trial for scoring using the Clinical Research Network scoring system.

Discrepancies in digital hematopathology diagnoses for consultation and expert panel analysis

Digital pathology with whole-slide imaging (WSI) has a large potential to make the process of expert consultation and expert panel diagnosis more rapid and more efficient. However, comparison with the current methods is necessary for validation of the technique. In this study, we determined if digital assessment of whole-slide images of hematopathology specimens with a focus on the assessment of lymphoma can be used for consultation and panel diagnostics. Ninety-three histological specimens with a suspicion for lymphoma were assessed both with conventional microscopy and digital microscopy with a wash out period between assessments. A consensus diagnosis was based on full concordance between the pathologists or, in case of discordances, was reached at a joint session at a multi-headed microscope. In 81% of the cases, there was a full concordance between digital and light microscopical assessment for all three pathologists. Discordances between conventional microscopy and digital pathology were present in 3% of assessments. In comparison with the consensus diagnosis, discordant diagnoses were made in 5 cases with digital microscopy and in 3 cases with light microscopy. The reported level of confidence and need for additional investigations were similar between assessment by conventional and by digital microscopy. In conclusion, the performance of assessment by digital pathology is in general comparable with that of conventional light microscopy and pathologists feel confident using digital pathology for this subspecialty.

Recommendations for pathologic practice using digital pathology: consensus report of the Korean Society of Pathologists

Digital pathology (DP) using whole slide imaging (WSI) is becoming a fundamental issue in pathology with recent advances and the rapid development of associated technologies. However, the available evidence on its diagnostic uses and practical advice for pathologists on implementing DP remains insufficient, particularly in light of the exponential growth of this industry. To inform DP implementation in Korea, we developed relevant and timely recommendations. We first performed a literature review of DP guidelines, recommendations, and position papers from major countries, as well as a review of relevant studies validating WSI. Based on that information, we prepared a draft. After several revisions, we released this draft to the public and the members of the Korean Society of Pathologists through our homepage and held an open forum for interested parties. Through that process, this final manuscript has been prepared. This recommendation contains an overview describing the background, objectives, scope of application, and basic terminology; guidelines and considerations for the hardware and software used in DP systems and the validation required for DP implementation; conclusions; and references and appendices, including literature on DP from major countries and WSI validation studies.

Artificial intelligence (AI) and big data in cancer and precision oncology

Artificial intelligence (AI) and machine learning have significantly influenced many facets of the healthcare sector. Advancement in technology has paved the way for analysis of big datasets in a cost- and time-effective manner. Clinical oncology and research are reaping the benefits of AI. The burden of cancer is a global phenomenon. Efforts to reduce mortality rates requires early diagnosis for effective therapeutic interventions. However, metastatic and recurrent cancers evolve and acquire drug resistance. It is imperative to detect novel biomarkers that induce drug resistance and identify therapeutic targets to enhance treatment regimes. The introduction of the next generation sequencing (NGS) platforms address these demands, has revolutionised the future of precision oncology. NGS offers several clinical applications that are important for risk predictor, early detection of disease, diagnosis by sequencing and medical imaging, accurate prognosis, biomarker identification and identification of therapeutic targets for novel drug discovery. NGS generates large datasets that demand specialised bioinformatics resources to analyse the data that is relevant and clinically significant. Through these applications of AI, cancer diagnostics and prognostic prediction are enhanced with NGS and medical imaging that delivers high resolution images. Regardless of the improvements in technology, AI has some challenges and limitations, and the clinical application of NGS remains to be validated. By continuing to enhance the progression of innovation and technology, the future of AI and precision oncology show great promise.

Density and size of lymphoid follicles are useful clues in differentiating primary intestinal follicular lymphoma from intestinal reactive lymphoid hyperplasia

Background

Primary intestinal follicular lymphoma (PI-FL) is a rare and indolent lymphoma and is challenging for diagnosis with endoscopic biopsy specimens. Whole slide imaging (WSI) has been increasingly used for assisting pathologic diagnosis, but not for lymphoma yet, probably because there are usually too many immunostained sections in a single case. In this study we attempted to identify morphological clues of PI-FL in the endoscopic biopsy specimens by measuring various parameters using WSI.

Methods

We retrospectively investigated 21 PI-FL cases, and scanned the HE sections from 17 of these cases with endoscopic biopsy specimens. Sections from 17 intestinal biopsies showing reactive lymphoid hyperplasia were scanned for comparison. The density and diameter of lymphoid follicles and the shortest distance of these follicles to the surface epithelia were measured on WSI. Comparisons of the aforementioned parameters were made between the neoplastic and reactive follicles.

Results

The density of follicles was significantly higher in PI-FL than that of reactive hyperplasia (median 0.5 vs. 0.2/mm²; p < 0.01). Furthermore, the neoplastic follicles were significantly larger (median diameter 756.9 vs. 479.7 μm; p < 0.01). The shortest distance of follicles to the surface epithelia tended to be closer in PI-FL (104.7 vs. 177.8 μm, p = 0.056), but not statistically significant.

Conclusions

In this study we found that in PI-FL the density and diameter of lymphoid follicles as measured from WSI were significantly different from that of intestinal reactive lymphoid hyperplasia. When facing the diagnostic challenge between these two entities in routine practice, pathologists might be alerted by these morphological clues and request for immunohistochemistry for differential diagnosis.