Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification

He, Qiming; Liu, Yiqing; Pan, Feiyang; Duan, Hufei; Guan, Jian; Liang, Zhendong; Zhong, Hui; Wang, Xing; He, Yonghong; Huang, Wenting; Guan, Tian

doi:10.1007/s11548-022-02781-2

Cited by 3 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ki67 was a nuclear protein closely related to the cell cycle and proliferation. 45,46 Compared with the control group and the RB-CDs@RGD group, the expression of Ki67 in the RB-CDs@RGD + US group was the lowest, indicating that the malignancy and proliferation rate of tumors in the RB-CDs@RGD + US group were much lower than those in the other two groups. Caspase-3 was an important terminal shear enzyme in the process of apoptosis.…”

Section: Resultsmentioning

confidence: 97%

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

Ren,

Shi,

Yang

et al. 2024

Mater. Chem. Front.

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 97%

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

Ren,

Shi,

Yang

et al. 2024

Mater. Chem. Front.

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

“…Several recent studies have demonstrated that deep learning algorithms could be used to generate automatic Ki67 proliferation index with high sensitivity and specificity in breast carcinomas and pancreatic neuroendocrine neoplasms. [6][7][8][9] Both breast carcinomas and pancreatic neuroendocrine neoplasms use three-tiered Ki67 cut-offs that are different from the two-tiered 5% cut-off of MTC. Recently, we have validated an ML-based deep learning platform (DeepLIIF), freely available online at https://deepliif.org/, 14,15 and a commercially available image analysis software (Leica Aperio image analysis) internally validated for automatic Ki67 reading in breast carcinoma.…”

Section: Discussionmentioning

confidence: 99%

“…Various digital image analysis platforms and machine learning (ML)-based algorithms have shown to be highly sensitive and specific to obtain an automatic reading of the Ki67 index in pancreatic neuroendocrine neoplasms and breast carcinomas. [5][6][7][8][9][10][11] The utility of these platforms in determining the Ki67 index in MTC is yet to be determined.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

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

Automatic Annotation Diagnostic Framework for Nasopharyngeal Carcinoma via Pathology–Fidelity GAN and Prior-Driven Classification

Zeng,

Li,

Liu

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Non-keratinizing carcinoma is the most common subtype of nasopharyngeal carcinoma (NPC). Its poorly differentiated tumor cells and complex microenvironment present challenges to pathological diagnosis. AI-based pathological models have demonstrated potential in diagnosing NPC, but the reliance on costly manual annotation hinders development. To address the challenges, this paper proposes a deep learning-based framework for diagnosing NPC without manual annotation. The framework includes a novel unpaired generative network and a prior-driven image classification system. With pathology–fidelity constraints, the generative network achieves accurate digital staining from H&E to EBER images. The classification system leverages staining specificity and pathological prior knowledge to annotate training data automatically and to classify images for NPC diagnosis. This work used 232 cases for study. The experimental results show that the classification system reached a 99.59% accuracy in classifying EBER images, which closely matched the diagnostic results of pathologists. Utilizing PF-GAN as the backbone of the framework, the system attained a specificity of 0.8826 in generating EBER images, markedly outperforming that of other GANs (0.6137, 0.5815). Furthermore, the F1-Score of the framework for patch level diagnosis was 0.9143, exceeding those of fully supervised models (0.9103, 0.8777). To further validate its clinical efficacy, the framework was compared with experienced pathologists at the WSI level, showing comparable NPC diagnosis performance. This low-cost and precise diagnostic framework optimizes the early pathological diagnosis method for NPC and provides an innovative strategic direction for AI-based cancer diagnosis.

show abstract

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification

Cited by 3 publications

References 28 publications

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

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

Automatic Annotation Diagnostic Framework for Nasopharyngeal Carcinoma via Pathology–Fidelity GAN and Prior-Driven Classification

Contact Info

Product

Resources

About

Unsupervised domain adaptive tumor region recognition for Ki67 automated assisted quantification

Cited by 3 publications

References 28 publications

Integrin αvβ3-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

Integrin αvβ3-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

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

Automatic Annotation Diagnostic Framework for Nasopharyngeal Carcinoma via Pathology–Fidelity GAN and Prior-Driven Classification

Contact Info

Product

Resources

About

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas

Integrin α_vβ₃-targeted engineered carbon dots for efficacious sonodynamic therapy and fluorescence navigation surgery against gliomas