Journal of Pathology Informatics Journal of Pathology Informatics
Contact us | Home | Login   |  Users Online: 1719  Print this pageEmail this pageSmall font sizeDefault font sizeIncrease font size 


TECHNICAL NOTE
Year : 2012  |  Volume : 3  |  Issue : 1  |  Page : 18

Investigation into diagnostic agreement using automated computer-assisted histopathology pattern recognition image analysis


1 Laboratory of Cancer Biology and Genetics, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892, USA
2 Department of Neurology and The Institute for Cell Engineering, Johns Hopkins University, Baltimore, MD 21231, USA

Correspondence Address:
R Mark Simpson
Laboratory of Cancer Biology and Genetics, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20892
USA
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/2153-3539.95130

Rights and Permissions

The extent to which histopathology pattern recognition image analysis (PRIA) agrees with microscopic assessment has not been established. Thus, a commercial PRIA platform was evaluated in two applications using whole-slide images. Substantial agreement, lacking significant constant or proportional errors, between PRIA and manual morphometric image segmentation was obtained for pulmonary metastatic cancer areas (Passing/Bablok regression). Bland-Altman analysis indicated heteroscedastic measurements and tendency toward increasing variance with increasing tumor burden, but no significant trend in mean bias. The average between-methods percent tumor content difference was -0.64. Analysis of between-methods measurement differences relative to the percent tumor magnitude revealed that method disagreement had an impact primarily in the smallest measurements (tumor burden <3%). Regression-based 95% limits of agreement indicated substantial agreement for method interchangeability. Repeated measures revealed concordance correlation of >0.988, indicating high reproducibility for both methods, yet PRIA reproducibility was superior (C.V.: PRIA = 7.4, manual = 17.1). Evaluation of PRIA on morphologically complex teratomas led to diagnostic agreement with pathologist assessments of pluripotency on subsets of teratomas. Accommodation of the diversity of teratoma histologic features frequently resulted in detrimental trade-offs, increasing PRIA error elsewhere in images. PRIA error was nonrandom and influenced by variations in histomorphology. File-size limitations encountered while training algorithms and consequences of spectral image processing dominance contributed to diagnostic inaccuracies experienced for some teratomas. PRIA appeared better suited for tissues with limited phenotypic diversity. Technical improvements may enhance diagnostic agreement, and consistent pathologist input will benefit further development and application of PRIA.


[FULL TEXT] [PDF]*
Print this article     Email this article
 Next article
 Previous article
 Table of Contents

 Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
 Citation Manager
 Access Statistics
 Reader Comments
 Email Alert *
 Add to My List *
 * Requires registration (Free)
 

 Article Access Statistics
    Viewed4587    
    Printed218    
    Emailed2    
    PDF Downloaded750    
    Comments [Add]    
    Cited by others 5    

Recommend this journal