Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Department of Pathology and Laboratory Medicine, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Histopathology. 2023 Dec;83(6):981-988. doi: 10.1111/his.15048. Epub 2023 Sep 14.
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.
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.
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.
2022 年引入的国际髓样甲状腺癌分级系统要求评估 Ki67 增殖指数，以确定髓样甲状腺癌的组织学分级。然而，手动计数仍然是一项繁琐且耗时的任务。
我们旨在评估三种其他 Ki67 指数计数技术的性能，包括由经验丰富的训练有素的研究人员进行的目测、基于机器学习的深度学习算法（DeepLIIF）和具有内部阈值的图像分析软件，与手动计数相比，在 260 例主要切除的髓样甲状腺癌的大队列中评估其性能。所有三种方法生成的 Ki67 增殖指数与手动 Ki67 指数非常接近，kappa 值范围为 0.884 至 0.979，组内相关系数范围为 0.969 至 0.983。只有在手动 Ki67 读数处于边缘的情况下才会出现 Ki67 结果不一致的情况，范围为 3%至 7%。使用这四种方法中的任何一种确定的高 Ki67 指数（≥5%）的髓样甲状腺癌与疾病特异性生存率和远处无转移生存率显著降低相关。
我们在此验证了一种基于机器学习的深度学习平台和一种具有内部阈值的图像分析软件，可在髓样甲状腺癌中生成准确的自动 Ki67 增殖指数。当面临 Ki67 增殖指数为 3%至 7%的边界肿瘤时，手动 Ki67 计数仍然有用。在日常实践中，在实施之前，需要对替代的 Ki67 指数评估方法在 MTC 中的验证。
