Artificial neural network model to distinguish follicular adenoma from follicular carcinoma on fine needle aspiration of thyroid

Savala, Rajiv; Dey, Pranab; Gupta, Nalini

doi:10.1002/dc.23880

Cited by 53 publications

(44 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sassi et al and Slowińska‐Klencka et al also reported standard deviation of nuclear area (SDNA) as the best predictor of malignant (PTC and FC) versus benign. Recently, Savala et al reported a neural network approach that was able to reliably distinguish FC from FA in 9 test cases after a training set of 39 cases and a validation set of 9 cases; a variety of nuclear morphometric features as well as qualitative factors were included, and among the morphometric features the system weighted the SDNA highest, further supporting the hypothesis that variation in nuclear size may be important in distinguishing follicular lesions. Such machine learning approaches offer an interesting tactic, very different from our own.…”

Section: Discussionmentioning

confidence: 89%

Digital image‐assisted quantitative nuclear analysis improves diagnostic accuracy of thyroid fine‐needle aspiration cytology

Chain

Legesse

Heath

et al. 2019

Cancer Cytopathology

View full text Add to dashboard Cite

Background Thyroid fine‐needle aspiration (FNA) plays a key role in triaging thyroid nodules. Yet many cases are assigned to indeterminate categories. The new category “noninvasive follicular thyroid neoplasm with papillary‐like features” (NIFTP) complicates thyroid cytology. Digital image‐derived nuclear measurements might objectively distinguish papillary thyroid carcinoma (PTC) from benign nodules and NIFTP. Methods All thyroid FNAs from 2012 to 2016 of atypia of undetermined significance (A; n = 8) and suspicious for malignancy (S; n = 2) with sufficient cellularity and surgical follow‐up, all FNAs preceding NIFTP (n = 6), and a random sample of PTC (n = 9) and benign (n = 10) cytology were studied. A modified Giemsa‐stained slide from each case was scanned using the Aperio imaging system, and long (dl) and short (ds)‐axis diameters were measured for 125 nuclei per case. Nuclear area and elongation were calculated. Results Nuclear area was larger in PTC (mean, 77.2 μm2 [range, 70.6‐86.0 μm2]) than benign (mean, 43.3 μm2 [range 38.2‐52.2 μm2]) (P < .001). Nuclear areas from indeterminate FNAs segregated according to final histology (A/S PTC mean 72.7 μm2, A/S benign mean 53.7 μm2; P = 0.004), and were not significantly different from definitive FNAs of the same diagnosis. NIFTP nuclear area was smaller than PTC (mean, 54.8 μm2 [range, 46.7‐66.1 μm2]; P < .001). Nuclear elongation showed similar results, but with greater group overlap. Conclusion Nuclear area and elongation can be calculated using a commercial digital imager; both correlate with the final surgical pathology diagnosis of PTC versus benign, including NIFTP. Area provides greater resolution than elongation. This technique could be used to resolve indeterminate cytology in which PTC is considered.

show abstract

Section: Discussionmentioning

confidence: 89%

Digital image‐assisted quantitative nuclear analysis improves diagnostic accuracy of thyroid fine‐needle aspiration cytology

Chain

Legesse

Heath

et al. 2019

Cancer Cytopathology

View full text Add to dashboard Cite

show abstract

“…Unlike many artificial intelligence studies using thyroid cytopathology, our methods required relatively little human effort or expertise in the training process . Only 145 WSIs were annotated for follicular cells with an average of 38 ROIs per scan.…”

Section: Discussionmentioning

confidence: 99%

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Range

Dov

Kovalsky

et al. 2020

Cancer Cytopathology

View full text Add to dashboard Cite

BACKGROUND:The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) comprises 6 categories used for the diagnosis of thyroid fine-needle aspiration biopsy (FNAB). Each category has an associated risk of malignancy, which is important in the management of a thyroid nodule. More accurate predictions of malignancy may help to reduce unnecessary surgery. A machine learning algorithm (MLA) was developed to evaluate thyroid FNAB via whole slide images (WSIs) to predict malignancy. METHODS: Files were searched for all thyroidectomy specimens with preceding FNAB over 8 years.All cytologic and surgical pathology diagnoses were recorded and correlated for each nodule. One representative slide from each case was scanned to create a WSI. An MLA was designed to identify follicular cells and predict the malignancy of the final pathology. The test set comprised cases blindly reviewed by a cytopathologist who assigned a TBSRTC category. The area under the receiver operating characteristic curve was used to assess the MLA performance. RESULTS: Nine hundred eight FNABs met the criteria. The MLA predicted malignancy with a sensitivity and specificity of 92.0% and 90.5%, respectively. The areas under the curve for the prediction of malignancy by the cytopathologist and the MLA were 0.931 and 0.932, respectively. CONCLUSIONS: The performance of the MLA in predicting thyroid malignancy from FNAB WSIs is comparable to the performance of an expert cytopathologist. When the MLA and electronic medical record diagnoses are combined, the performance is superior to the performance of either alone. An MLA may be used as an adjunct to FNAB to assist in refining the indeterminate categories. Cancer Cytopathol 2020;128:287-295.

show abstract

“…Indeed, the ability of automated algorithms to separate nodules according to precisely measured features which are difficult to quantify manually could be of great help for diagnosis, especially in indeterminate cytology cases. This was evident prior to the advent of WSI, when traditional machine learning was applied to static images acquired by cameras mounted on microscope, attempting to extract features from follicular cell nuclei in order to discriminate between benign and malignant follicular lesions in fine‐needle smears …”

Section: Discussionmentioning

confidence: 99%

“…Thyroid pathology is another field with great potential for the use of image analysis and AI algorithms. There is already abundant literature on the application of these computer tools to digital images of thyroid pathology, and even more concerning application to thyroid ultrasound scans, as many studies have explored AI clinical usefulness to discriminate malignant from benign thyroid nodules with radiological features . Indeed, thyroid pathology has great potential for automated algorithm application as the incidence of thyroid nodules is increasing, the diagnosis of these lesions can be challenging especially with the introduction of new entities such as noninvasive follicular thyroid neoplasm with papillary‐like nuclear features (NIFTP), and the indeterminate interpretation rate of fine‐needle aspiration (FNA) remains relatively high.…”

Section: Introductionmentioning

confidence: 99%

Impact of image analysis and artificial intelligence in thyroid pathology, with particular reference to cytological aspects

Girolami¹,

Marletta²,

Pantanowitz

et al. 2020

Cytopathology

View full text Add to dashboard Cite

Objective Thyroid pathology has great potential for automated/artificial intelligence algorithm application as the incidence of thyroid nodules is increasing and the indeterminate interpretation rate of fine‐needle aspiration remains relatively high. The aim of the study is to review the published literature on automated image analysis and artificial intelligence applications to thyroid pathology with whole‐slide imaging. Methods Systematic search was carried out in electronic databases. Studies dealing with thyroid pathology and use of automated algorithms applied to whole‐slide imaging were included. Quality of studies was assessed with a modified QUADAS‐2 tool. Results Of 919 retrieved articles, 19 were included. The main themes addressed were the comparison of automated assessment of immunohistochemical staining with manual pathologist's assessment, quantification of differences in cellular and nuclear parameters among tumour entities, and discrimination between benign and malignant nodules. Correlation coefficients with manual assessment were higher than 0.76 and diagnostic performance of automated models was comparable with an expert pathologist diagnosis. Computational difficulties were related to the large size of whole‐slide images. Conclusions Overall, the results are promising and it is likely that, with the resolution of technical issues, the application of automated algorithms in thyroid pathology will increase and be adopted following suitable validation studies.

show abstract

Artificial neural network model to distinguish follicular adenoma from follicular carcinoma on fine needle aspiration of thyroid

Cited by 53 publications

References 21 publications

Digital image‐assisted quantitative nuclear analysis improves diagnostic accuracy of thyroid fine‐needle aspiration cytology

Digital image‐assisted quantitative nuclear analysis improves diagnostic accuracy of thyroid fine‐needle aspiration cytology

Application of a machine learning algorithm to predict malignancy in thyroid cytopathology

Impact of image analysis and artificial intelligence in thyroid pathology, with particular reference to cytological aspects

Contact Info

Product

Resources

About