Ki67 proliferation index in medullary thyroid carcinoma : a comparative study of multiple counting methods and validation of image analysis and deep learning platforms
© 2023 John Wiley & Sons Ltd..
AIMS: The 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 RESULTS: We 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.
CONCLUSIONS: We 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.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:83 |
|---|---|
| Enthalten in: |
Histopathology - 83(2023), 6 vom: 08. Dez., Seite 981-988 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Nadeem, Saad [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Deep learning |
|---|
| Anmerkungen: |
Date Completed 07.11.2023 Date Revised 07.02.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1111/his.15048 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM362034915 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM362034915 | ||
| 003 | DE-627 | ||
| 005 | 20240207232040.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1111/his.15048 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1283.xml |
| 035 | |a (DE-627)NLM362034915 | ||
| 035 | |a (NLM)37706239 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Nadeem, Saad |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Ki67 proliferation index in medullary thyroid carcinoma |b a comparative study of multiple counting methods and validation of image analysis and deep learning platforms |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 07.11.2023 | ||
| 500 | |a Date Revised 07.02.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2023 John Wiley & Sons Ltd. | ||
| 520 | |a AIMS: The 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 | ||
| 520 | |a METHODS AND RESULTS: We 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 | ||
| 520 | |a CONCLUSIONS: We 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 | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Ki67 proliferation index | |
| 650 | 4 | |a deep learning | |
| 650 | 4 | |a grade | |
| 650 | 4 | |a machine learning | |
| 650 | 4 | |a medullary thyroid carcinoma | |
| 650 | 7 | |a Ki-67 Antigen |2 NLM | |
| 700 | 1 | |a Hanna, Matthew G |e verfasserin |4 aut | |
| 700 | 1 | |a Viswanathan, Kartik |e verfasserin |4 aut | |
| 700 | 1 | |a Marino, Joseph |e verfasserin |4 aut | |
| 700 | 1 | |a Ahadi, Mahsa |e verfasserin |4 aut | |
| 700 | 1 | |a Alzumaili, Bayan |e verfasserin |4 aut | |
| 700 | 1 | |a Bani, Mohamed-Amine |e verfasserin |4 aut | |
| 700 | 1 | |a Chiarucci, Federico |e verfasserin |4 aut | |
| 700 | 1 | |a Chou, Angela |e verfasserin |4 aut | |
| 700 | 1 | |a De Leo, Antonio |e verfasserin |4 aut | |
| 700 | 1 | |a Fuchs, Talia L |e verfasserin |4 aut | |
| 700 | 1 | |a Lubin, Daniel J |e verfasserin |4 aut | |
| 700 | 1 | |a Luxford, Catherine |e verfasserin |4 aut | |
| 700 | 1 | |a Magliocca, Kelly |e verfasserin |4 aut | |
| 700 | 1 | |a Martinez, Germán |e verfasserin |4 aut | |
| 700 | 1 | |a Shi, Qiuying |e verfasserin |4 aut | |
| 700 | 1 | |a Sidhu, Stan |e verfasserin |4 aut | |
| 700 | 1 | |a Al Ghuzlan, Abir |e verfasserin |4 aut | |
| 700 | 1 | |a Gill, Anthony J |e verfasserin |4 aut | |
| 700 | 1 | |a Tallini, Giovanni |e verfasserin |4 aut | |
| 700 | 1 | |a Ghossein, Ronald |e verfasserin |4 aut | |
| 700 | 1 | |a Xu, Bin |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Histopathology |d 1985 |g 83(2023), 6 vom: 08. Dez., Seite 981-988 |w (DE-627)NLM000284408 |x 0309-0167 |7 nnns |
| 773 | 1 | 8 | |g volume:83 |g year:2023 |g number:6 |g day:08 |g month:12 |g pages:981-988 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1111/his.15048 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 83 |j 2023 |e 6 |b 08 |c 12 |h 981-988 | ||