Analytical and quantitative cytology and histology · 2002
Fine needle aspiration of the thyroid: can an image processing system improve differentiation?
Оценочное исследованиеСтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Harms Harry, Hofmann Manfred, Ruschenburg Ilka
Аннотация
OBJECTIVE: To differentiate thyroid nodules by means of fine needle aspiration with subsequent computer-aided diagnosis.
STUDY DESIGN: Fine needle aspiration biopsies obtained from 137 patients for whom histopathologic diagnosis was available were investigated: 16 hyperplastic nodules (12%), 39 adenomas (28%), 25 follicular thyroid carcinomas (18%), 19 follicular variants of papillary thyroid carcinoma (14%) and 38 papillary thyroid carcinomas (28%). From each stained specimen 100 cell scenes were scanned and analyzed, constituting a total of 62,325 cell images.
RESULTS: All the entities described could be well discriminated from each other by automated image analysis methods. Both the diagnosis of tumor type and the differentiation between benign and malignant could be achieved with a sensitivity of .98.
CONCLUSION: With only 7-10 calculated cell features (texture line analysis) and classification with decision trees, a tool for high-quality cell image diagnosis is available. Subtypes of cells characterized by the calculated features could be found in all the specimens and could be assigned to the malignancies with high statistical significance. The method increases the relevance of image processing as an additional diagnostic tool for cytologic examination of thyroid nodules.
STUDY DESIGN: Fine needle aspiration biopsies obtained from 137 patients for whom histopathologic diagnosis was available were investigated: 16 hyperplastic nodules (12%), 39 adenomas (28%), 25 follicular thyroid carcinomas (18%), 19 follicular variants of papillary thyroid carcinoma (14%) and 38 papillary thyroid carcinomas (28%). From each stained specimen 100 cell scenes were scanned and analyzed, constituting a total of 62,325 cell images.
RESULTS: All the entities described could be well discriminated from each other by automated image analysis methods. Both the diagnosis of tumor type and the differentiation between benign and malignant could be achieved with a sensitivity of .98.
CONCLUSION: With only 7-10 calculated cell features (texture line analysis) and classification with decision trees, a tool for high-quality cell image diagnosis is available. Subtypes of cells characterized by the calculated features could be found in all the specimens and could be assigned to the malignancies with high statistical significance. The method increases the relevance of image processing as an additional diagnostic tool for cytologic examination of thyroid nodules.