Deep learning for intelligent diagnosis in thyroid scintigraphy
نویسندگان
چکیده
منابع مشابه
Diagnosis of deep vein thrombosis using platelet scintigraphy.
PURPOSE We reviewed the usefulness of platelet scintigraphy, in which autologous platelets labeled with indium-111-oxine reveal thrombotic activity, for evaluating deep vein thrombosis (DVT). MATERIALS During the past 2 years, 39 cases with DVT were enrolled in this study. DVT was definitely diagnosed by color duplex scanning, platelet scintigraphy or both in all cases. For semiquantitative a...
متن کاملMachine Learning Techniques for Thyroid Cancer Diagnosis
Drawing inspiration from Alexander’s paper on classification of thyroid cancer, we are interested in replicating and possibly improving the predictive results of a learning model for detecting thyroid cancer from gene expression data from thyroid nodules. This data set is the same data used in the paper by Alexander. We will develop our own gene expression classifier by applying different featu...
متن کاملMachine learning for thyroid cancer diagnosis
We investigate the use of high throughput gene expression data in the diagnosis of thyroid cancers. Using logistic regression and support vector machines (SVMs), we develop a classifier which gives similar performance (89% sensitivity and 80% specificity) to the currently bestknown classifier, but uses significantly fewer features. We used two different techniques, principal components analysis...
متن کاملPitfalls in the diagnosis of thyroid dysgenesis by thyroid ultrasonography and scintigraphy.
OBJECTIVES We aimed to investigate the reliability of thyroid ultrasonography (US) and scintigraphy in determining the type of thyroid dysgenesis (TD). METHODS The study included 82 children (8.0±5.6 years) with a diagnosis of TD by thyroid scintigraphy with (99m)Tc and/or US. The patients were re-evaluated 6.0±5.1 years after the diagnosis. Thyroid US was performed in all cases, regardless o...
متن کاملMultimodal Deep Learning for Cervical Dysplasia Diagnosis
To improve the diagnostic accuracy of cervical dysplasia, it is important to fuse multimodal information collected during a patient’s screening visit. However, current multimodal frameworks suffer from low sensitivity at high specificity levels, due to their limitations in learning correlations among highly heterogeneous modalities. In this paper, we design a deep learning framework for cervica...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of International Medical Research
سال: 2021
ISSN: 0300-0605,1473-2300
DOI: 10.1177/0300060520982842