Exploration of Digital Image Analysis for Ki67 Quantification in the Grading of Medullary Thyroid Carcinoma: A Pilot Study with 85 Cases

Behrman, David; Lubin, Daniel; Magliocca, Kelly R.; Shi, Qiuying; Viswanathan, Kartik

doi:10.1007/s12105-023-01564-8

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Ki67 stain (MIB-1 clone, 1:80 dilution, Dako antibody; Agilent Technologies, Santa Clara, California) was performed on the surgical resection material, and the surgical Ki67 PR (Ki67SURG) was calculated via a manual count in "hot spot" regions as previously described. 11 Ki67SURG was generally performed on the primary tumor but was calculated on the metastatic tumor for cases without adequate primary tumor material or with discrepant histologic grade in the primary and metastatic tumors. The surgical resection specimens were reviewed by two pathologists and assigned an IMTCGS grade on the basis of established criteria.…”

Section: Methodsmentioning

confidence: 99%

Grading medullary thyroid carcinoma on fine‐needle aspiration cytology specimens with the International Medullary Thyroid Carcinoma Grading System: A cytologic–histologic correlation

Viswanathan,

Behrman,

Lubin

2023

Cancer Cytopathology

View full text Add to dashboard Cite

BackgroundMedullary thyroid carcinoma (MTC) is a rare cancer of parafollicular C‐cell origin. The International MTC Grading System (IMTCGS) incorporates mitotic activity, the presence of necrosis, and the Ki67 proliferation rate (PR) to classify MTCs as low or high grade. The ability to predict IMTCGS grade in cytology was assessed.MethodsMTCs with cytology and subsequent surgical follow‐up were reviewed. Cytology slides were reviewed for mitotic figures, apoptoses, and necrosis, and a Ki67 PR was calculated when possible. Findings were correlated with final IMTCGS grade.ResultsTwenty‐five MTC fine‐needle aspirations (FNAs) were identified, with nine identified as high grade (36%). By using a PR cutoff of 5%, Ki67 on FNA material (Ki67FNA) showed 92% concordance (n = 22 of 24) with surgical Ki67 and a correlation coefficient (R2) of 0.72. Sensitivity and specificity of Ki67FNA for predicting high‐grade MTC were 38% and 100%, respectively. Multiple mitotic figures were present in a single slide of 43% (n = 3 of 7) of evaluable high‐grade MTCs, whereas only one of 16 low‐grade MTCs showed a single mitotic figure. Definitive apoptoses were present in five of seven high‐grade MTC FNAs but were absent in 16 low‐grade MTCs. The sensitivity and specificity of apoptoses/necrosis on cytology for high‐grade MTCs were 71% and 88%, respectively.ConclusionsKi67FNA ≥5% shows low sensitivity but high specificity for predicting high‐grade MTC. The presence of multiple mitotic figures in a single slide or definitive apoptotic bodies are both highly suggestive of high‐grade MTC, and should warrant a close examination for necrosis and a careful Ki67 PR count.

show abstract

Section: Methodsmentioning

confidence: 99%

Grading medullary thyroid carcinoma on fine‐needle aspiration cytology specimens with the International Medullary Thyroid Carcinoma Grading System: A cytologic–histologic correlation

Viswanathan,

Behrman,

Lubin

2023

Cancer Cytopathology

View full text Add to dashboard Cite

show abstract

Ki67 proliferation index in medullary thyroid carcinoma: a comparative study of multiple counting methods and validation of image analysis and deep learning platforms

Nadeem,

Hanna,

Viswanathan

et al. 2023

Histopathology

Self Cite

View full text Add to dashboard Cite

AimsThe International Medullary Thyroid Carcinoma Grading System, introduced in 2022, mandates evaluation of the Ki67 proliferation index to assign a histological grade for medullary thyroid carcinoma. However, manual counting remains a tedious and time‐consuming task.Methods and resultsWe aimed to evaluate the performance of three other counting techniques for the Ki67 index, eyeballing by a trained experienced investigator, a machine learning‐based deep learning algorithm (DeepLIIF) and an image analysis software with internal thresholding compared to the gold standard manual counting in a large cohort of 260 primarily resected medullary thyroid carcinoma. The Ki67 proliferation index generated by all three methods correlate near‐perfectly with the manual Ki67 index, with kappa values ranging from 0.884 to 0.979 and interclass correlation coefficients ranging from 0.969 to 0.983. Discrepant Ki67 results were only observed in cases with borderline manual Ki67 readings, ranging from 3 to 7%. Medullary thyroid carcinomas with a high Ki67 index (≥ 5%) determined using any of the four methods were associated with significantly decreased disease‐specific survival and distant metastasis‐free survival.ConclusionsWe herein validate a machine learning‐based deep‐learning platform and an image analysis software with internal thresholding to generate accurate automatic Ki67 proliferation indices in medullary thyroid carcinoma. Manual Ki67 count remains useful when facing a tumour with a borderline Ki67 proliferation index of 3–7%. In daily practice, validation of alternative evaluation methods for the Ki67 index in MTC is required prior to implementation.

show abstract

Exploration of Digital Image Analysis for Ki67 Quantification in the Grading of Medullary Thyroid Carcinoma: A Pilot Study with 85 Cases

Cited by 2 publications

References 20 publications

Grading medullary thyroid carcinoma on fine‐needle aspiration cytology specimens with the International Medullary Thyroid Carcinoma Grading System: A cytologic–histologic correlation

Grading medullary thyroid carcinoma on fine‐needle aspiration cytology specimens with the International Medullary Thyroid Carcinoma Grading System: A cytologic–histologic correlation

Ki67 proliferation index in medullary thyroid carcinoma: a comparative study of multiple counting methods and validation of image analysis and deep learning platforms

Contact Info

Product

Resources

About