Introduction:Fine-needle aspiration cytology (FNAC) for identification of papillary carcinoma thyroid is a moderately sensitive and specific modality. The present machine learning tools can correctly classify images into broad categories. Training software for recognition of papillary thyroid carcinoma on FNAC smears will be a decisive step toward automation of cytopathology.Aim:The aim of this study is to develop an artificial neural network (ANN) for the purpose of distinguishing papillary carcinoma thyroid and nonpapillary carcinoma thyroid on microphotographs from thyroid FNAC smears.Subjects and Methods:An ANN was developed in the Python programming language. In the training phase, 186 microphotographs from Romanowsky/Pap-stained smears of papillary carcinoma and 184 microphotographs from smears of other thyroid lesions (at ×10 and ×40 magnification) were used for training the ANN. After completion of training, performance was evaluated with a set of 174 microphotographs (66 – nonpapillary carcinoma and 21 – papillary carcinoma, each photographed at two magnifications ×10 and ×40).Results:The performance characteristics and limitations of the neural network were assessed, assuming FNAC diagnosis as gold standard. Combined results from two magnifications showed good sensitivity (90.48%), moderate specificity (83.33%), and a very high negative predictive value (96.49%) and 85.06% diagnostic accuracy. However, vague papillary formations by benign follicular cells identified wrongly as papillary carcinoma remain a drawback.Conclusion:With further training with a diverse dataset and in conjunction with automated microscopy, the ANN has the potential to develop into an accurate image classifier for thyroid FNACs.
I read with extreme interest the Original article titled ''Prevalence of molecular subtypes of invasive breast cancer: A retrospective study'' by Kumar et al. published in Med J Armed Forces India 2015;71:254-258. 1 This article is regarding the interpretation of ER and Her2neu, hormonal receptors, which are very important prognostic and predictive markers in breast ductal carcinoma and are helpful in deciding appropriate therapy. I will provide the uniform format of how to interpret ER, PR, and Her2neu as per the ASCO/CAP American Society of Clinical Oncology and College of American Pathologists joint recommendations, which are practiced for breast cancer ER, PR, and Her2neu reporting worldwide and in India too in all Oncocenters. I am presenting the scoring system in detail so that the young budding reporting pathologists can know the exact uniform reporting format, which is approved worldwide and should be followed uniformly. (1) Percentage of cells that are nuclear immunoreactive should be reported. (2) Tumors having 1% or higher number of cells nuclear-positive stained for ER and PR are positive. (3) Average intensity of stain that is nuclear positive (weak, moderate, or strong) should be reported. (4) Allred, H, or Quick score should be given.
The most prevalent cancers in ladies are cervical, endometrial and Ovarian. The biomarkers prevalent in use for these gynaecological cancers are commonly Cancer antigen 125 (CA-125), B, Alpha-fetoprotein (AFP), Inhibin, Carcinoembryonic antigen (CEA), Squamous cell carcinoma (SCC) antigen, Carbohydrate antigen 19-9, Cancer antigen 27-29, Human epididymis protein 4 (HE4), Osteopontin, transthyretin, Immunosuppressive acidic protein(IAP), leptin, CA15-3, CK19 and Thymidine kinase. The biomarker marker Squamous cell carcinoma (SCC) antigen, CK19 and immunosuppressive acidic protein IAP are raised in cervical squamous cell carcinomas. Endometrial cancer is a common cancer in women. In 75% of endometrial cancer cases, the tumor remains confined to the uterus and has a favorable prognosis if early detected. The prognosis, however, worsens dramatically as the disease progresses. The objective of this review is to elucidate the importance of the tumor markers for early diagnosis of gynaecological malignancies which are vital and life saving. Similarly the relevant biomarkers in combination are found to have positive predictive values and significant p values in the endometrial and cervical cancer. In Cervix cancer the positive predictive value of these markers combined is usually 92% -95% and negative predictive value 93% -96%. The confidence interval is 98% and p value significant 0.005. Sensitivity of tumor markers combined CK19, SCC and immunosuppressive acidic protein IAP in Cervix cancer detection is 95% and specificity 96%. The highest sensitivity was for SCC antigen (98.7%) while the highest specificity was for Cytokeratin 19 (99.7%). The positive predictive value by combination of CK19, SCC and IAP for the detection of Cervix cancer was 90% -94%. In endometrial cancer the sensitivity of tumor markers combined CA19-9, CA125, leptin, thymidine kinase, CEA, CA15-3, and HE4 in endometrial cancer detection was 95% and specificity 96%. The highest sensitivity was for CA125 (99.7%) while the highest specificity was for CA19-9 (95.7%) which revealed that the efficacy of
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.