Automated grading of renal cell carcinoma using whole slide imaging

Abstract

Introduction:Recent technology developments have demonstrated the benefit of using whole slide imaging (WSI) in computer-aided diagnosis. In this paper, we explore the feasibility of using automatic WSI analysis to assist grading of clear cell renal cell carcinoma (RCC), which is a manual task traditionally performed by pathologists.Materials and Methods:Automatic WSI analysis was applied to 39 hematoxylin and eosin-stained digitized slides of clear cell RCC with varying grades. Kernel regression was used to estimate the spatial distribution of nuclear size across the entire slides. The analysis results were correlated with Fuhrman nuclear grades determined by pathologists.Results:The spatial distribution of nuclear size provided a panoramic view of the tissue sections. The distribution images facilitated locating regions of interest, such as high-grade regions and areas with necrosis. The statistical analysis showed that the maximum nuclear size was significantly different (P < 0.001) between low-grade (Grades I and II) and high-grade tumors (Grades III and IV). The receiver operating characteristics analysis showed that the maximum nuclear size distinguished high-grade and low-grade tumors with a false positive rate of 0.2 and a true positive rate of 1.0. The area under the curve is 0.97.Conclusion:The automatic WSI analysis allows pathologists to see the spatial distribution of nuclei size inside the tumors. The maximum nuclear size can also be used to differentiate low-grade and high-grade clear cell RCC with good sensitivity and specificity. These data suggest that automatic WSI analysis may facilitate pathologic grading of renal tumors and reduce variability encountered with manual grading.

Automated Clear Cell Renal Carcinoma Grade Classification with Prognostic Significance

“…To the best of our knowledge, this is the first computational pathology system created to predict 2-tiered ccRCC grade with prognostic significance. Previously, Yeh and colleagues developed an automated system to predict grade using a dataset of 39 patients and one feature (i.e., maximum nuclei size), and correlated their predicted grade with manual grade assessed by one pathologist 28 . Our system, trained using a much larger and more diverse dataset of 277 cases from seven TCGA participating institutions, captures 72 nuclei details in addition to morphological features (i.e., nuclei size and shape) typically observed by pathologists.…”

“…While qualitative evaluation of the segmentation results revealed that our image processing pipeline produced reasonably good results, the nuclei segmentation may not be optimal in more challenging cases. A solution is to employ deep learning based techniques to improve nuclei segmentation in future studies 28,30,31 .…”

MRI Investigation of New Approach to Improve the Recovery of Myocardial Ischemia Reperfusion Injury by Treatment with Intralipid&lt;sup&gt;&#174;&lt;/sup&gt;

“…Selection and grading of the field-of-interest can be subjective and biased. The WSI method that we have developed provides an overall and quantitative evaluation of the whole pathology slide without pre-selecting field-of-interest [28]. The computational detection algorithm provides an objective and quantitative evaluation of the true pathological evaluation of the tissue.…”

“…The whole-slide images were then processed by WS-Recognizer (http://ws-recognizer.labsolver.org) [28]. The cell nuclei in the H&E-stained slides were recognized to calculate the cell density across the entire tissue section, whereas the ED1 + macrophages were recognized to calculate the spatial distribution of macrophages.…”

Aktualny stan wiedzy na temat patomorfologii cyfrowej

“…Aplikacje te korzystają zarówno z WSI, jak i narzędzi do automatycznej analizy obrazu. Zastosowanie CAD może obejmować między innymi stopniowanie histologiczne nowotworów (grading) i kwalifikację chorych do terapii [44]. Ponadto pozwala ono na automatyczne wybieranie obszarów do analizy w celu oceny tak zwanych hot spotów, czyli obszarów nowotworów o najwyższej aktywności proliferacyjnej [45].…”