INbreast: toward a full-field digital mammographic database.

By Ines Moreira, Igor Amaral, Inês Domingues, A. Cardoso, M. Jorge Cardoso, Jaime S. Cardoso. Academic Radiology, 2012

1,155 citations recorded by the source corpus.

RATIONALE AND OBJECTIVES Computer-aided detection and diagnosis (CAD) systems have been developed in the past two decades to assist radiologists in the detection and diagnosis of lesions seen on breast imaging exams, thus providing a second opinion. Mammographic databases play an important role in the development of algorithms aiming at the detection and diagnosis of mammary lesions. However, available databases often do not take into consideration all the requirements needed for research and study purposes. This article aims to present and detail a new mammographic database. MATERIALS AND METHODS Images were acquired at a breast center located in a university hospital (Centro Hospitalar de S. João [CHSJ], Breast Centre, Porto) with the permission of the Portuguese National Committee of Data Protection and Hospital's Ethics Committee. MammoNovation Siemens full-field digital mammography, with a solid-state detector of amorphous selenium was used. RESULTS The new database-INbreast-has a total of 115 cases (410 images) from which 90 cases are from women with both breasts affected (four images per case) and 25 cases are from mastectomy patients (two images per case). Several types of lesions (masses, calcifications, asymmetries, and distortions) were included. Accurate contours made by specialists are also provided in XML format. CONCLUSION The strengths of the actually presented database-INbreast-relies on the fact that it was built with full-field digital mammograms (in opposition to digitized mammograms), it presents a wide variability of cases, and is made publicly available together with precise annotations. We believe that this database can be a reference for future works centered or related to breast cancer imaging.

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/93c5bb23406778eb421a3dfa5978a231e022792a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep Convolutional Neural Networks for breast cancer screening (2018, neutral): “INbreast [28] the INbreast database was built with full-ﬁeld digital mammograms (in opposition to digitized mammograms); it is made publicly available together with precise annotations.”
Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening (2019, background): “Some authors do not discuss design of their models (29–31), some evaluate their models on very small public datasets (32, 33), insuﬃcient for a meaningful evaluation, while others used private datasets with populations of diﬀerent distributions (on a spectrum between screening population and…”
Domain Adaptation for Medical Image Analysis: A Survey (2021, positive): “Their experimental results reveal that using only a small number of target training examples for ﬁne-tuning can improve the transferability of models.”
Deep Learning and Structured Prediction for the Segmentation of Mass in Mammograms (2015, methodology): “The INbreast dataset comprises a set of 56 cases containing 116 accurately annotated masses.”
A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification (2018, methodology): “against other existing deep learning models such as FCN [46], SegNet [48], and U-Net [47] is presented using the same data from the INbreast database [34].”
Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges (2019, neutral): “INbreast 116 samples 2D Mammography [21, 55]”
The Automated Learning of Deep Features for Breast Mass Classification from Mammograms (2016, methodology): “1) using the INbreast [10] dataset.”
Deep Learning and Its Applications in Biomedicine (2018, methodology): “Their methodology was tested on the publicly available datasets INbreast [110] and Digital Database for Screening Mammography (DDSM) [111], outperforming in terms of accuracy and efﬁciency several state-of-the-art methods when tested on DDSM. Additional medical applications employing a deep learning”
Detecting and classifying lesions in mammograms with Deep Learning (2017, methodology): “We have also evaluated the model on the publicly available INbreast dataset.”
Adversarial Deep Structural Networks for Mammographic Mass Segmentation (2016, methodology): “The INbreast dataset is a recently released mammographic mass analysis dataset, which contains 410 mammographic images [22].”
High-Resolution Breast Cancer Screening with Multi-View Deep Convolutional Neural Networks (2017, neutral): “For instance, INBreast has approximately achieved a balance between benign and malignant cases.”
Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification (2016, methodology): “The proposed deep multi-instance networks are shown to provide robust performance for whole mammogram classification on the INbreast dataset [16].”