Innovative Diagnostic Method Using Immunocytochemistry (Estrogen Receptor) for Diagnosis and Management of Breast Cancer
DOI:
https://doi.org/10.9734/bpi/cpmmr/v9/6170BKeywords:
Breast cancer, ER, FNAC, histopathology, ICC, immunohistochemistry, Machine Learning (ML), Natural Language Processing (NLP), text data analysisAbstract
This study aimed to evaluate the effectiveness of Immunocytochemistry (ICC) on Fine Needle Aspiration Cytology (FNAC) using estrogen receptor (ER), in diagnosing breast lesions, comparing them to the gold standard Core Needle Biopsy with Immunohistochemistry (IHC). A total of 50 samples were collected and analyzed using both FNAC and Core Needle Biopsy techniques.
For FNAC, the results demonstrated excellent performance: Sensitivity=100%, Specificity=100%, Diagnostic Accuracy=100%, Positive Predictive Value (PPV)=100%, and Negative Predictive Value (NPV)=100%.
Similarly, the results for ICC using ER were also favorable: Sensitivity=100%, Accuracy=100%, Positive Predictive Value= 100% and Negative Predictive Value=100%.
These findings suggest that ICC using ER could serve as a reliable alternative to the gold-standard diagnostic tests. This technique proves particularly valuable in situations where resource limitations prevent the use of the standard test. However, it is imperative to note that further studies with a larger sample size are necessary to generalize these results.
Furthermore, this study involved the utilization of text data analysis on FNAC reports. The analysis revealed that approximately 11.35% of the dataset contained useful words, indicating that normalization processes can condense the data and make it valuable for assisting clinical chart reviews and clinical decision support systems.