Turkish Twitter Emotion Dataset (TURTED)
Turkish Emotion Lexicon (TEL)
Emotion Dataset in Turkish (TREMO)
Dokuz Eylul Mammography Set (DEMS)
DEMS (Dokuz Eylul University Mammogram Set) is a fully annotated Mammography Dataset. It is annotated using Mammography Annotation Ontology (MAO) using Mammography Annotation Retrieval Tool (MART). MAO is a domain ontology for mammography and it was created based on 3th edition of ACR (American College of Radiologists) BI-RADS (Breast Imaging Reporting and Data System) Mammography Atlas .
DEMS contains 485 cases, where each case contains four mammograms, MLO and CC views for two breasts, and one XML file called as “DEMS Annotation XML”. Each image converted from DICOM images into lossless PNG and name of the each images is set according to its view, e.g. LCC.png, LMLO.png. Resulting PNG images have 16-bit intensity depth, 70 µm effective resolution and, 2560×3328 or 3328×4096 size. The following figure shows a sample mammography case in DEMS which have more than one abnormality.
The case contains one mass and two associated findings in the left breast. The mass is indicated with red contour and it has irregular shape, spiculated margin and equal density. Additionally, there are skin retraction and skin thickening as the associated findings. The breast density of the case is Almost Entirely Fat and final BI‑RADS score of the case is 6. This means that the mass is pathologically proven malignancy.
Download DEMS Mammography Dataset
Contrary to any existing mammogram datasets, we provide a set of low‑level features of mammogram cases in DEMS, where these features can be used to improve CBR results. Moreover, low‑level features are mandatory components of a Content-based Image Retrieval (CBIR) system. Without them, the system becomes a metadata‑based retrieval system. Each mass in DEMS has 29 different low‑level features describing the content and the characteristics of the masses for their shape, texture, margin, mass intensity and size. Low‑level features are represented with a vector of floating point numbers, whose the total length of the all feature vector is 578. These features are typically used for classification and clustering of breast masses, and to improve CBR results of breast masses.
Download Feature Sets of DDSM and DEMDS Datasets.
If you use the DEMS as the source of the data in your studies, please credit and reference the following publication:
- Hakan Bulu, Adil Alpkocak, Pinar Balci, “Uncertainty Modeling for Ontology-based Mammography Annotation with Intelligent BI_RADS Scoring”, Computers in Biology and Medicine, Vol.43, Issue.4, pp.301-3011, 2013, DOI: 10.1016/j.compbiomed.2013.01.001.
- Tolga Berber, Integration of Content-based Image Retrieval and Database Management Systems: A CAse Study with Digital Mammography, PhD Dissertation, Dokuz Eylul University Department of Computer Enginerring, 203 pages, 2013.
DEMS Web Browser
You may browse the whole cases in DEMS on web. The web application has three main parts; filter, display and annotations. In the filter part, user can easily filter the cases in DEMS by using combo boxes. Then, the filtered cases are listed in ‘Case List’ list box. When user selects one case from the list, display options are listed above list box. The list box is filled dynamically according to lesion types of the selected case. When user clicks on ‘Load The Case’ button, selected case is displayed with selected display option. In the display part, mammogram(s) are displayed. Finally, annotation part shows annotations of all lesions in selected case. We use color-coding to connect the ROIs and annotations. In other words, same color is used for both ROI and its annotation.
Mammography Annotation and Retrieval Tool (MART)
MART is an ontology-based mammography annotation and retrieval toool, written in C++ using QT framework for Linux, Mac and Windows environment. It uses Mammography annotation ontology (MAO) to focus main concepts and relations. MART enables to annotate mammograms using MAO, and performs case‑based retrieval queries on the mammography repositories. We used MART to develop a sample mammography dataset, which includes 485 mammography cases where 255 of them contain one or more abnormalities. Both the dataset and tool are publicly available, and hope that that DEMS dataset will be useful for benchmarking mammography related studies in research community.
Sample cases can be dowloaded here. You can refer to document for a detailed instruction on installation of MART and Sample cases.