Cytology consultations with associated image quality evaluation â€“ experiences of the Virtual International Pathology Institute (VIPI)
Background: The virtual international Pathology Institute (VIPI, www.diagnomx.eu/vipi) is the only image consultation forum that is organized in close organization to a conventional institute of pathology. Its approximately 160 experts in pathology and cytology consult and diagnose difficult cases on the basis of a convent weekly duty plan. Herein we report the consultation results of a specific series of cytology specimens, and discuss potential application in routine virtual cytology.
Material and Methods: Still images of fine needle aspirations sent for consultation to VIPI were evaluated by five members of VIPI. A total of forty and seven cases was analyzed, and scored in four classes (benign, probably benign, probably malignant, and malignant). In addition, the consultants evaluated and graded their impression of colour, focus and general image quality in 10 classes (10 = very good <> 1 = not acceptable). Automated measurements of objective image quality, calculation of the regions of interest (ROI), and automated diagnosis classifications were performed too.
Results: The expertsâ€™ diagnostic conformity was computed 4.2/5; i.e., at average 4.2 experts stated the same diagnosis of each case. The automated classification supported the summarized expertsâ€™ diagnoses in 38/47 cases. The experts interpreted the image quality diversely. Two of them evaluated with tendency of low, and two of them of high grades. The individual interactive image quality evaluations showed statistically significant relationship to the diagnostic accuracy (p<0.05). A helpful and correct automated ROI detection was stated in more than 95% of images.
Conclusion: The study indicates that electronic transmission of acquired conventional cytology smears is a useful tool to get access to expertsâ€™ knowledge worldwide. The case related diagnostic agreement of experts can serve for gold standard of virtual cytology (for example conformity > 80%). Additional automated measurements might support the diagnosis. Implementation of virtual slide technology and automated ROI visualization are additional tools in order to support the diagnostic accuracy. Virtual international pathology institutions are able to successfully work together with or even replace conventional cytology laboratories.
2. Krishna, S.G., et al., Diagnostic performance of endoscopic ultrasound for detection of pancreatic malignancy following an indeterminate multidetector CT scan: a systemic review and meta-analysis. Surg Endosc.
3. Sperandeo, M., et al., The role of ultrasound-guided fine needle aspiration biopsy in musculoskeletal diseases. Eur J Radiol. 90: p. 234-244.
4. Gorgulu, F.F., et al., Computed tomography-guided transthoracic biopsy: Factors influencing diagnostic and complication rates. J Int Med Res. 45(2): p. 808-815.
5. Hong, M.J., et al., Cytology-Ultrasonography Risk-Stratification Scoring System Based on Fine-Needle Aspiration Cytology and the Korean-Thyroid Imaging Reporting and Data System. Thyroid. 27(7): p. 953-959.
6. Mitchell, A.L., et al., Management of thyroid cancer: United Kingdom National Multidisciplinary Guidelines. J Laryngol Otol. 130(S2): p. S150-S160.
7. Kayser, C., et al., The application of structural entropy in tissue based diagnosis. Diagnostic Pathology, 2017. 3(1).
8. Kayser, G., et al., Vascular diffusion density and survival of patients with primary lung carcinomas. Virchows Arch, 2003.
9. Kayser, K. and H.J. Gabius, The application of thermodynamic principles to histochemical and morphometric tissue research: principles and practical outline with focus on the glycosciences. Cell Tissue Res, 1999. 296(3): p. 443-55.
10. Kayser, K., et al., Integrated optical density (IOD), syntactic structure analysis, and survival in operated lung carcinoma patients. Pathol Res Pract, 1994. 190(11): p. 1031-8.
11. Kayser, K., et al., Texture- and object-related automated information analysis in histological still images of various organs. Anal Quant Cytol Histol, 2008. 30(6): p. 323-35.
12. Kayser, K., G. Kayser, and K. Metze, The concept of structural entropy in tissue-based diagnosis. Anal Quant Cytol Histol, 2007. 29(5): p. 296-308.
13. Kayser, K., K. Baumgartner, and H.J. Gabius, Cytometry with DAPI-stained tumor imprints. A reliable tool for improved intraoperative analysis of lung neoplasms. Anal Quant Cytol Histol, 1996. 18(2): p. 115-20.
14. Kayser, K., et al., Application of attributed graphs in diagnostic pathology. Anal Quant Cytol Histol, 1996. 18(4): p. 286-92.
15. Kayser, K., et al., Combined morphometrical and syntactic structure analysis as tools for histomorphological insight into human lung carcinoma growth. Anal Cell Pathol, 1990. 2(3): p. 167-78.
16. Haroske, G., et al., Competence on demand in DNA image cytometry. Pathol Res Pract, 2000. 196(5): p. 285-91.
17. Haroske, G., et al., Remote quantitation server for quality assurance in DNA ploidy analysis. Anal Quant Cytol Histol, 1998. 20(4): p. 302-12.
18. Kayser, K., et al., Routine DNA cytometry of benign and malignant pleural effusions by means of the remote quantitation server Euroquant: a prospective study. J Clin Pathol, 2000. 53(10): p. 760-4.
19. Kayser, K., et al., New developments in digital pathology: from telepathology to virtual pathology laboratory. Stud Health Technol Inform, 2004. 105: p. 61-9.
20. Schmitt, F., Telepathology devoted to cytology. . ISSN . . Diagnostic Pathology, 2017. ECP 2017 SY_03_1.
21. Kayser, K., et al., Application of computer-assisted morphometry to the analysis of prenatal development of human lung. Anat Histol Embryol, 1997. 26(2): p. 135-9.
22. GÃ¶rtler, J., et al., Cognitive Algorithms and digitized Tissue â€“ based Diagnosis. Diagnostic Pathology, 2017. 3(1).
23. Kayser, K., et al., Quantitation of asbestos and asbestos-like fibers in human lung tissue by hot and wet ashing, and the significance of their presence for survival of lung carcinoma and mesothelioma patients. Lung Cancer, 1999. 24(2): p. 89-98.
24. Kayser, K., et al., How to measure image quality in tissue-based diagnosis (diagnostic surgical pathology). Diagn Pathol, 2008. 3 Suppl 1: p. S11.
25. Otsu, N., A threshold selection method from grey level histograms. EEE Transactions on Systems, Man, and Cybernetics.,, 1979. 9: p. 62-66.
26. Kayser, K., et al., Parameters derived from integrated nuclear fluorescence, syntactic structure analysis, and vascularization in human lung carcinomas. Anal Cell Pathol, 1997. 15(2): p. 73-83.
27. Leong, F.J. and A.S. Leong, Digital photography in anatomical pathology. J Postgrad Med, 2004. 50(1): p. 62-9.
28. Marsan, C. and M.C. Vacher-Lavenu, Telepathology: a tool to aid in diagnosis and quality assurance in cervicovaginal cytology. Cytopathology, 1995. 6(5): p. 339-42.
30. Kayser , K., B. Molnar, and R.S. Weinstein, Virtual Microscopy Fundamentals - Applications - Perspectives of Electronic Tissue - based Diagnosis. 2006, Berlin: VSV Interdisciplinary Medical Publishing.
31. Collins, B.T., Telepathology in cytopathology: challenges and opportunities. Acta Cytol. 57(3): p. 221-32.
32. Thrall, M.J., J.L. Wimmer, and M.R. Schwartz, Validation of multiple whole slide imaging scanners based on the guideline from the College of American Pathologists Pathology and Laboratory Quality Center. Arch Pathol Lab Med. 139(5): p. 656-64.
33. Higgins, C., Applications and challenges of digital pathology and whole slide imaging. Biotech Histochem. 90(5): p. 341-7.
34. Krupinski, E.A., et al., Observer performance using virtual pathology slides: impact of LCD color reproduction accuracy. J Digit Imaging. 25(6): p. 738-43.
35. Lin, D.Y., et al., The sensitivity and specificity of single-field nonmydriatic monochromatic digital fundus photography with remote image interpretation for diabetic retinopathy screening: a comparison with ophthalmoscopy and standardized mydriatic color photography. Am J Ophthalmol, 2002. 134(2): p. 204-13.
36. Smith, A.C., et al., Diagnostic accuracy of and patient satisfaction with telemedicine for the follow-up of paediatric burns patients. J Telemed Telecare, 2004. 10(4): p. 193-8.
37. Bautista, P.A. and Y. Yagi, Improving the visualization and detection of tissue folds in whole slide images through color enhancement. J Pathol Inform. 1: p. 25.
38. Ayad, E., et al., Cytology consultations with associated image quality evaluation and image measurements. Diagnostic Pathology, 2017. 3(ECP 2017 SY-03).
39. Litjens, G., et al., A survey on deep learning in medical image analysis. Med Image Anal. 42: p. 60-88.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
4. In case of virtual slide publication the authors agree to copy the article in a structural modified version to the journal's VS archive.