AIM: To automate breast cancer diagnosis and to study the inter-observer and intra-observer variations in the manual evaluations. METHODS: Breast tissue specimens from sixty cases were stained separately for estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor-2 (HER-2/neu). All cases were assessed by manual grading as well as image analysis. The manual grading was performed by an experienced expert pathologist. To study inter-observer and intra-observer variations, we obtained readings from another pathologist as the second observer from a different laboratory who has a little less experience than the first observer. We also took a second reading from the second observer to study intra-observer variations. Image analysis was carried out using in-house developed software (TissueQuant). A comparison of the results from image analysis and manual scoring of ER, PR and HER-2/neu was also carried out. RESULTS: The performance of the automated analysis in the case of ER, PR and HER-2/neu expressions was compared with the manual evaluations. The performance of the automated system was found to correlate well with the manual evaluations. The inter-observer variations were measured using Spearman correlation coefficient r and 95% confidence interval. In the case of ER expression, Spearman correlation r = 0.53, in the case of PR expression, r = 0.63, and in the case of HER-2/neu expression, r = 0.68. Similarly, intra-observer variations were also measured. In the case of ER, PR and HER-2/neu expressions, r = 0.46, 0.66 and 0.70, respectively. CONCLUSION: The automation of breast cancer diagnosis from immunohistochemically stained specimens is very useful for providing objective and repeatable evaluations.
AIM: To automate breast cancer diagnosis and to study the inter-observer and intra-observer variations in the manual evaluations. METHODS: Breast tissue specimens from sixty cases were stained separately for estrogen receptor (ER), progesterone receptor (PR) and humanepidermal growth factor receptor-2 (HER-2/neu). All cases were assessed by manual grading as well as image analysis. The manual grading was performed by an experienced expert pathologist. To study inter-observer and intra-observer variations, we obtained readings from another pathologist as the second observer from a different laboratory who has a little less experience than the first observer. We also took a second reading from the second observer to study intra-observer variations. Image analysis was carried out using in-house developed software (TissueQuant). A comparison of the results from image analysis and manual scoring of ER, PR and HER-2/neu was also carried out. RESULTS: The performance of the automated analysis in the case of ER, PR and HER-2/neu expressions was compared with the manual evaluations. The performance of the automated system was found to correlate well with the manual evaluations. The inter-observer variations were measured using Spearman correlation coefficient r and 95% confidence interval. In the case of ER expression, Spearman correlation r = 0.53, in the case of PR expression, r = 0.63, and in the case of HER-2/neu expression, r = 0.68. Similarly, intra-observer variations were also measured. In the case of ER, PR and HER-2/neu expressions, r = 0.46, 0.66 and 0.70, respectively. CONCLUSION: The automation of breast cancer diagnosis from immunohistochemically stained specimens is very useful for providing objective and repeatable evaluations.
Entities:
Keywords:
Automation; Breast cancer diagnosis; Computer aided diagnosis; Image analysis; Immunohistochemical study
Authors: Spiros Kostopoulos; Dionisis Cavouras; Antonis Daskalakis; Panagiotis Bougioukos; Pantelis Georgiadis; George C Kagadis; Ioannis Kalatzis; Panagiota Ravazoula; George Nikiforidis Journal: Conf Proc IEEE Eng Med Biol Soc Date: 2007
Authors: T Vrekoussis; V Chaniotis; I Navrozoglou; V Dousias; K Pavlakis; E N Stathopoulos; O Zoras Journal: Anticancer Res Date: 2009-12 Impact factor: 2.480
Authors: Ulla Wilking; Eva Karlsson; Lambert Skoog; Thomas Hatschek; Elisabet Lidbrink; Goran Elmberger; Hemming Johansson; Linda Lindström; Jonas Bergh Journal: Breast Cancer Res Treat Date: 2010-07-14 Impact factor: 4.872
Authors: M Pauschinger; D Knopf; S Petschauer; A Doerner; W Poller; P L Schwimmbeck; U Kühl; H P Schultheiss Journal: Circulation Date: 1999-06-01 Impact factor: 29.690
Authors: G Santeusanio; A Mauriello; S Schiaroli; L Anemona; L G Spagnoli; G Scambia; M Oberholzer Journal: Pathol Res Pract Date: 1992-06 Impact factor: 3.250
Authors: A Molino; R Micciolo; M Turazza; F Bonetti; Q Piubello; A Corgnati; L Sperotto; G Martignoni; A Bonetti; R Nortilli Journal: Breast Cancer Res Treat Date: 1995-06 Impact factor: 4.872
Authors: Marilyn M Bui; Michael W Riben; Kimberly H Allison; Elizabeth Chlipala; Carol Colasacco; Andrea G Kahn; Christina Lacchetti; Anant Madabhushi; Liron Pantanowitz; Mohamed E Salama; Rachel L Stewart; Nicole E Thomas; John E Tomaszewski; M Elizabeth Hammond Journal: Arch Pathol Lab Med Date: 2019-01-15 Impact factor: 5.534