Annotation-Free Deep Learning-Based Prediction of Thyroid Molecular Cancer Biomarker BRAF (V600E) from Cytological Slides
Прогнозирование молекулярного онкологического биомаркера щитовидной железы BRAF (V600E) по цитологическим препаратам с использованием глубокого обучения без аннотаций
2023-01-28
SCID: 54.1/h374ak3k
Discuss with AI
BRAF (V600E) mutationdeep learningprecision oncologythyroid fine-needle aspiration cytologywhole slide images
Figures from the paper
Abstract (AI)
Thyroid cancer is the most common endocrine cancer. Papillary thyroid cancer (PTC) is the most prevalent form of malignancy among all thyroid cancers arising from follicular cells. Fine needle aspiration cytology (FNAC) is a non-invasive method regarded as the most cost-effective and accurate diagnostic method of choice in diagnosing PTC. Identification of BRAF (V600E) mutation in thyroid neoplasia may be beneficial because it is specific for malignancy, implies a worse prognosis, and is the target for selective BRAF inhibitors. To the authors' best knowledge, this is the first automated precision oncology framework effectively predict BRAF (V600E) immunostaining result in thyroidectomy specimen directly from Papanicolaou-stained thyroid fine-needle aspiration cytology and ThinPrep cytological slides, which is helpful for novel targeted therapies and prognosis prediction. The proposed deep learning (DL) framework is evaluated on a dataset of 118 whole slide images. The results show that the proposed DL-based technique achieves an accuracy of 87%, a precision of 94%, a sensitivity of 91%, a specificity of 71% and a mean of sensitivity and specificity at 81% and outperformed three state-of-the-art deep learning approaches. This study demonstrates the feasibility of DL-based prediction of critical molecular features in cytological slides, which not only aid in accurate diagnosis but also provide useful information in guiding clinical decision-making in patients with thyroid cancer. With the accumulation of data and the continuous advancement of technology, the performance of DL systems is expected to be improved in the near future. Therefore, we expect that DL can provide a cost-effective and time-effective alternative tool for patients in the era of precision oncology.
Key Findings
1
Evaluated on 118 whole-slide images, the framework achieved 87% accuracy, 94% precision, 91% sensitivity, and 71% specificity.
2
Introduces the first reported annotation-free deep learning framework predicting BRAF (V600E) immunostaining directly from thyroid FNAC and ThinPrep cytological slides.
3
The authors identify future data accumulation and technological advances as necessary for improving performance and enabling cost- and time-effective precision oncology.
4
The findings demonstrate the feasibility of predicting clinically relevant molecular biomarkers from cytological slides to support diagnosis, prognosis assessment, and targeted therapy decisions.
5
The model attained a mean sensitivity and specificity of 81% and outperformed three state-of-the-art deep learning approaches.
6
Авторы отмечают, что накопление данных и развитие технологий необходимы для дальнейшего повышения эффективности и реализации экономичного и быстрого инструмента прецизионной онкологии.
7
На наборе из 118 полноразмерных изображений модель достигла точности 87%, точности положительных предсказаний 94%, чувствительности 91% и специфичности 71%.
8
Представлен первый заявленный бессегментационный фреймворк глубокого обучения для прогнозирования иммуногистохимического статуса BRAF (V600E) непосредственно по цитологическим препаратам FNAC и ThinPrep щитовидной железы.
9
Результаты демонстрируют возможность прогнозирования клинически значимых молекулярных биомаркеров по цитологическим препаратам для поддержки диагностики, оценки прогноза и выбора таргетной терапии.
10
Среднее значение чувствительности и специфичности составило 81%, а предложенный метод превзошёл три современных подхода глубокого обучения.
Research Object
Papillary thyroid cancer represented in Papanicolaou-stained thyroid fine-needle aspiration and ThinPrep cytological slides
Research Subject
BRAF (V600E) immunostaining/molecular biomarker status and its prediction from cytological slide morphology
Publication Details
Publication Date
2023-01-28
Journal
Publisher
ISSN
Cited by
44
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Deep Residual Learning for Image Recognition2016
2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer2015
Deep learning in cancer diagnosis, prognosis and treatment selection2021