Abstract
Medical images are valuable for clinical diagnosis and decision making. Image modality is an important primary step, as it is capable of aiding clinicians to access required medical image in retrieval systems. Traditional methods of modality classification are dependent on the choice of hand-crafted features and demand a clear awareness of prior domain knowledge. The feature learning approach may detect efficiently visual characteristics of different modalities, but it is limited to the number of training datasets. To overcome the absence of labeled data, on the one hand, we take deep convolutional neural networks (VGGNet, ResNet) with different depths pre-trained on ImageNet, fix most of the earlier layers to reserve generic features of natural images, and only train their higher-level portion on ImageCLEF to learn domain-specific features of medical figures. Then, we train from scratch deep CNNs with only six weight layers to capture more domain-specific features. On the other hand, we employ two data augmentation methods to help CNNs to give the full scope to their potential characterizing image modality features. The final prediction is given by our voting system based on the outputs of three CNNs. After evaluating our proposed model on the subfigure classification task in ImageCLEF2015 and ImageCLEF2016, we obtain new, state-of-the-art results—76.87% in ImageCLEF2015 and 87.37% in ImageCLEF2016—which imply that CNNs, based on our proposed transfer learning methods and data augmentation skills, can identify more efficiently modalities of medical images.
Highlights
With the ease of Internet access, the size of the medical literature has grown exponentially over the past few years [1]
This section describes the architecture of our proposed model including three types of deep convolutional neural networks (CNNs) with different depths and a different voting system
We have presented a model for medical image modality classification that is composed of three CNNs with different depths, which are combined by weighted averaging of the prediction probabilities
Summary
With the ease of Internet access, the size of the medical literature has grown exponentially over the past few years [1]. Medical images in articles provide basic knowledge in visualization of body parts, in their treatment, and in tracking disease, which makes the clinical care and diagnosis of diseases practicable [2,3,4]. Different sorts of medical image technologies provide an enormous amount of images with various medical modalities and other image types, such as Computerized Tomography, X-ray, or generic biomedical illustrations [5]. To aid the clinician and the researcher to retrieve required images, many tools have been developed to formulate and execute queries based on the visual content [6]. Content-based medical image retrieval systems, such as OPENi [7], could be improved by filtering our non-relevant image types using the modality information [6,8], but not all medical images are annotated appropriately.
Sign-in/Register to view highlights & summary 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.
