Pedro R F Rende, Joel Machado Pires, Kátia Sakimi Nakadaira, Sara Lopes, João Vale, Fabio Hecht, Fabyan E L Beltrão, Gabriel J R Machado, Edna T Kimura, Catarina Eloy, Helton E Ramos
{"title":"Revisiting the utility of identifying nuclear grooves as unique nuclear changes by an object detector model.","authors":"Pedro R F Rende, Joel Machado Pires, Kátia Sakimi Nakadaira, Sara Lopes, João Vale, Fabio Hecht, Fabyan E L Beltrão, Gabriel J R Machado, Edna T Kimura, Catarina Eloy, Helton E Ramos","doi":"10.4132/jptm.2024.03.07","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Among other structures, nuclear grooves are vastly found in papillary thyroid carcinoma (PTC). Considering that the application of artificial intelligence in thyroid cytology has potential for diagnostic routine, our goal was to develop a new supervised convolutional neural network capable of identifying nuclear grooves in Diff-Quik stained whole-slide images (WSI) obtained from thyroid fineneedle aspiration.</p><p><strong>Methods: </strong>We selected 22 Diff-Quik stained cytological slides with cytological diagnosis of PTC and concordant histological diagnosis. Each of the slides was scanned, forming a WSI. Images that contained the region of interest were obtained, followed by pre-formatting, annotation of the nuclear grooves and data augmentation techniques. The final dataset was divided into training and validation groups in a 7:3 ratio.</p><p><strong>Results: </strong>This is the first artificial intelligence model based on object detection applied to nuclear structures in thyroid cytopathology. A total of 7,255 images were obtained from 22 WSI, totaling 7,242 annotated nuclear grooves. The best model was obtained after it was submitted 15 times with the train dataset (14th epoch), with 67% true positives, 49.8% for sensitivity and 43.1% for predictive positive value.</p><p><strong>Conclusions: </strong>The model was able to develop a structure predictor rule, indicating that the application of an artificial intelligence model based on object detection in the identification of nuclear grooves is feasible. Associated with a reduction in interobserver variability and in time per slide, this demonstrates that nuclear evaluation constitutes one of the possibilities for refining the diagnosis through computational models.</p>","PeriodicalId":46933,"journal":{"name":"Journal of Pathology and Translational Medicine","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11106606/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Pathology and Translational Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4132/jptm.2024.03.07","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/4/30 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"PATHOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Among other structures, nuclear grooves are vastly found in papillary thyroid carcinoma (PTC). Considering that the application of artificial intelligence in thyroid cytology has potential for diagnostic routine, our goal was to develop a new supervised convolutional neural network capable of identifying nuclear grooves in Diff-Quik stained whole-slide images (WSI) obtained from thyroid fineneedle aspiration.
Methods: We selected 22 Diff-Quik stained cytological slides with cytological diagnosis of PTC and concordant histological diagnosis. Each of the slides was scanned, forming a WSI. Images that contained the region of interest were obtained, followed by pre-formatting, annotation of the nuclear grooves and data augmentation techniques. The final dataset was divided into training and validation groups in a 7:3 ratio.
Results: This is the first artificial intelligence model based on object detection applied to nuclear structures in thyroid cytopathology. A total of 7,255 images were obtained from 22 WSI, totaling 7,242 annotated nuclear grooves. The best model was obtained after it was submitted 15 times with the train dataset (14th epoch), with 67% true positives, 49.8% for sensitivity and 43.1% for predictive positive value.
Conclusions: The model was able to develop a structure predictor rule, indicating that the application of an artificial intelligence model based on object detection in the identification of nuclear grooves is feasible. Associated with a reduction in interobserver variability and in time per slide, this demonstrates that nuclear evaluation constitutes one of the possibilities for refining the diagnosis through computational models.
期刊介绍:
The Journal of Pathology and Translational Medicine is an open venue for the rapid publication of major achievements in various fields of pathology, cytopathology, and biomedical and translational research. The Journal aims to share new insights into the molecular and cellular mechanisms of human diseases and to report major advances in both experimental and clinical medicine, with a particular emphasis on translational research. The investigations of human cells and tissues using high-dimensional biology techniques such as genomics and proteomics will be given a high priority. Articles on stem cell biology are also welcome. The categories of manuscript include original articles, review and perspective articles, case studies, brief case reports, and letters to the editor.