Abstract
With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into “malignant” and “benign” cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.
Highlights
Introduction of a TIRADS reporting scheme that is validated would allow clinicians to be able to stop regular thyroid ultrasound evaluation with confidence that they are unlikely toJ Digit Imaging (2017) 30:477–486Many works utilizing different hand-crafted features extracted from thyroid ultrasound images have been recently proposed [4,5,6,7,8,9]
We selected the fine-tuned GoogLeNet model trained with image samples from both database 1 and database 2 to extract the deep features for the following classification step
Fine-tuning the existing deep convolutional neural network (DCNN) proves to have the advantage of needing less training samples to generate a domain-specific deep learning network, which can effectively extract high-level features for thyroid ultrasound images and classify malignant and benign thyroid images with high accuracy
Summary
Introduction of a TIRADS reporting scheme that is validated would allow clinicians to be able to stop regular thyroid ultrasound evaluation with confidence that they are unlikely toJ Digit Imaging (2017) 30:477–486Many works utilizing different hand-crafted features extracted from thyroid ultrasound images have been recently proposed [4,5,6,7,8,9]. Compared to the traditional feature extraction methods, it was claimed in [12] that DCNN had two advantages: (1) detection using DCNN is robust to distortions such as changes in shape due to camera lens, different lighting conditions, different poses, presence of partial occlusions, horizontal and vertical shifts, etc.; (2) the computational cost of feature extraction by DCNN is relatively low because the same coefficients in the convolutional layer are used across the input image Motivated by their observed advantages for non-medical images, DCNNs were applied to several medical image classification and detection problems. Radiologists have identified a few sonographic characteristics of thyroid nodules as suggestive features of malignancy, including hypo-echogenicity, absence of a halo, micro-calcifications, solidity, intra-nodular flow and tallerthan-wide shape [1] Based on these characteristics, a dedicated Thyroid Imaging Reporting and Data System (TI-RADS) [2] to categorize thyroid nodules and stratify their malignancy risk has been developed for used by radiologists. The accuracy is often based on radiologists’ personal experience, as current sonographic criteria to identify malignant nodules are imperfect with the variations in echo patterns of thyroid nodules limiting the judgement capability of radiologists [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
