Curated Breast Imaging Subset DDSM Dataset (Mammography)

tfrecords files of scans from the DDSM dataset

This Dataset contains the JPG images of Breast Cancer taken from the CBIS-DDSM.

https://i.imgur.com/rz4rtQI.png" alt="Breast Cancer Images">

Descripton

This dataset contains JPG format images (2.49 GB) of the original CBIS-DDSM dataset (163 GB) which are in DICOM format and by maintaining the same resolution of the images as it was in the original dataset.

The original dataset was split into train and test by having two cases one is Mass and another is Calcification(Calc) i.e. calc_case_description_test_set.csv, calc_case_description_train_set.csv, mass_case_description_test_set.csv, mass_case_description_train_set.csv, and metadata.csv but in here this dataset is made by converting the images from DICOM to JPG format, removing the unnecessary columns by Data Cleaning and concatenating both the Mass and Calcification(Calc) cases train test into one i.e. calc_case(with_jpg_img).csv, mass_case(with_jpg_img).csv, and metadata(with_jpg_img).csv.

| Collection | | | --- | --- | | Number of Studies | 6775 | | Number of Series | 6775 | | Number of Participants | 1,566(NB) | | Number of Images | 10239 | | Modalities | MG | | Image Size (GB) | 6(.jpg) |

NB: The image data for this collection is structured such that each participant has multiple patient IDs. For example, pat_id 00038 has 10 separate patient IDs which provide information about the scans within the IDs (e.g. Calc-Test_P_00038_LEFT_CC, Calc-Test_P_00038_RIGHT_CC_1) This makes it appear as though there are 6,671 participants according to the DICOM metadata, but there are only 1,566 actual participants in the cohort.

File Description

1. JPG image folder file structure

https://i.imgur.com/KtBMlVm.png" alt="Cancer Image file structure"> File naming: - Folder name: Subject ID > Study UID > Series UID - File name: Series Description > img_0 > 1.jpg

2. CSV files description

Summary

The CBIS-DDSM (Curated Breast Imaging Subset of DDSM) is an updated and standardized version of the Digital Database for Screening Mammography (DDSM). The DDSM is a database of 2,620 scanned film mammography studies. It contains normal, benign, and malignant cases with verified pathology information. The scale of the database along with ground truth validation makes the DDSM a useful tool in the development and testing of decision support systems. The CBIS-DDSM collection includes a subset of the DDSM data selected and curated by a trained mammographer. The images have been decompressed and converted to DICOM format. Updated ROI segmentation and bounding boxes, and pathologic diagnosis for training data are also included. A manuscript describing how to use this dataset in detail is available at https://www.nature.com/articles/sdata2017177.

Published research results from work in developing decision support systems in mammography are difficult to replicate due to the lack of a standard evaluation data set; most computer-aided diagnosis (CADx) and detection (CADe) algorithms for breast cancer in mammography are evaluated on private data sets or on unspecified subsets of public databases. Few well-curated public datasets have been provided for the mammography community. These include the DDSM, the Mammographic Imaging Analysis Society (MIAS) database, and the Image Retrieval in Medical Applications (IRMA) project. Although these public data sets are useful, they are limited in terms of data set size and accessibility.

For example, most researchers using the DDSM do not leverage all its images for a variety of historical reasons. When the database was released in 1997, computational resources to process hundreds or thousands of images were not widely available. Additionally, the DDSM images are saved in non-standard compression files that require the use of decompression code that has not been updated or maintained for modern computers. Finally, the ROI annotations for the abnormalities in the DDSM were provided to indicate a general position of lesions, but not a precise segmentation for them. Therefore, many researchers must implement segmentation algorithms for accurate feature extraction. This causes an inability to directly compare the performance of methods or to replicate prior results. The CBIS-DDSM collection addresses that challenge by publicly releasing a curated and standardized version of the DDSM for evaluation of future CADx and CADe systems (sometimes referred to generally as CAD) research in mammography.

Source of the Original dataset

https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY

Citations & Data Usage Policy

Users must abide by the TCIA Data Usage Policy and Restrictions. Attribution should include references to the following citations:

CBIS-DDSM Citation

Sawyer-Lee, R., Gimenez, F., Hoogi, A., & Rubin, D. (2016). Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) (Version 1) [Data set]. The Cancer Imaging Archive. https://doi.org/10.7937/K9/TCIA.2016.7O02S9CY

Publication Citation

Lee, R. S., Gimenez, F., Hoogi, A., Miyake, K. K., Gorovoy, M., & Rubin, D. L. (2017). A curated mammography data set for use in computer-aided detection and diagnosis research. In Scientific Data (Vol. 4, Issue 1). Springer Science and Business Media LLC. https://doi.org/10.1038/sdata.2017.177

TCIA Citation

Clark, K., Vendt, B., Smith, K., Freymann, J., Kirby, J., Koppel, P., Moore, S., Phillips, S., Maffitt, D., Pringle, M., Tarbox, L., & Prior, F. (2013). The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. In Journal of Digital Imaging (Vol. 26, Issue 6, pp. 1045–1057). Springer Science and Business Media LLC. https://doi.org/10.1007/s10278-013-9622-7

NOTE: The CBIS-DDSM dataset lack DICOM image for cropped and ROI images, so there are some cropped and ROI images that may not be found corresponding to their given path, so it is recommended to use the full mammography images from this dataset (only)

The dataset contains mammography with benign and malignant masses. Images in this dataset were first extracted 106 masses images from INbreast dataset, 53 masses images from MIAS dataset, and 2188 masses images DDSM dataset. Then we use data augmentation and contrast-limited adaptive histogram equalization to preprocess our images. After data augmentation, Inbreast dataset has 7632 images, MIAS dataset has 3816 images, DDSM dataset has 13128 images. In addition, we also integrate INbreast, MIAS, DDSM together. All the images were resized to 227*227 pixels.

Dataset

This dataset was created by Laurent Pourchot

Contents

This is a prepossessed version of the CBIS-DDSM data set for mammography segmentation.

The preprocessing pipeline used on this data is inspired from this github repository : https://github.com/CleonWong/Can-You-Find-The-Tumour

The Data is structered as follows : https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F13630556%2Fc7a7ba31b83470782decd9b2049ea9ef%2Ffolder.png?generation=1699352159040166&alt=media" alt="">

Breast cancer analysis implies that radiologists inspect mammograms to detect suspicious breast lesions and identify mass tumors. Artificial intelligence techniques offer automatic systems for breast mass segmentation to assist radiologists in their diagnosis. With the rapid development of deep learning and its application to medical imaging challenges, UNet and its variations is one of the state-of-the-art models for medical image segmentation that showed promising performance on mammography. In this paper, we propose an architecture, called Connected-UNets, which connects two UNets using additional modified skip connections. We integrate Atrous Spatial Pyramid Pooling (ASPP) in the two standard UNets to emphasize the contextual information within the encoder-decoder network architecture. We also apply the proposed architecture on the Attention UNet (AUNet) and the Residual UNet (ResUNet). We evaluated the proposed architectures on two publically available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Experiments were also conducted using additional synthetic data using the cycle-consistent Generative Adversarial Network (CycleGAN) model between two unpaired datasets to augment and enhance the images. Qualitative and quantitative results show that the proposed architecture can achieve better automatic mass segmentation with a high Dice score of 89.52%, 95.28%, and 95.88% and Intersection over Union (IoU) score of 80.02%, 91.03%, and 92.27%, respectively, on CBIS-DDSM, INbreast, and the private dataset.