Dataset Information

Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research.

ABSTRACT: Contrast-enhanced spectral mammography (CESM) is a relatively recent imaging modality with increased diagnostic accuracy compared to digital mammography (DM). New deep learning (DL) models were developed that have accuracies equal to that of an average radiologist. However, most studies trained the DL models on DM images as no datasets exist for CESM images. We aim to resolve this limitation by releasing a Categorized Digital Database for Low energy and Subtracted Contrast Enhanced Spectral Mammography images (CDD-CESM) to evaluate decision support systems. The dataset includes 2006 images, with an average resolution of 2355 × 1315, consisting of 310 mass images, 48 architectural distortion images, 222 asymmetry images, 238 calcifications images, 334 mass enhancement images, 184 non-mass enhancement images, 159 postoperative images, 8 post neoadjuvant chemotherapy images, and 751 normal images, with 248 images having more than one finding. This is the first dataset to incorporate data selection, segmentation annotation, medical reports, and pathological diagnosis for all cases. Moreover, we propose and evaluate a DL-based technique to automatically segment abnormal findings in images.

SUBMITTER: Khaled R

PROVIDER: S-EPMC8967853 | biostudies-literature | 2022 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research.

Khaled Rana R Helal Maha M Alfarghaly Omar O Mokhtar Omnia O Elkorany Abeer A El Kassas Hebatalla H Fahmy Aly A

Scientific data 20220330 1

Contrast-enhanced spectral mammography (CESM) is a relatively recent imaging modality with increased diagnostic accuracy compared to digital mammography (DM). New deep learning (DL) models were developed that have accuracies equal to that of an average radiologist. However, most studies trained the DL models on DM images as no datasets exist for CESM images. We aim to resolve this limitation by releasing a Categorized Digital Database for Low energy and Subtracted Contrast Enhanced Spectral Mamm ...[more]

PMID: 35354835

Similar Datasets

Project description:Contrast-enhanced MRI (CE-MRI) is the most sensitive technique for breast cancer detection. Contrast-enhanced mammography (CEM) is emerging as a possible alternative to CE-MRI.PurposeTo evaluate the diagnostic performance of a low radiation dose contrast-enhanced mammography (L-CEM) in women with suspicious findings on conventional imaging compared to CE-MRI of the breast.Study typeProspective, single center.PopulationWomen with suspicious findings on mammography, tomosynthesis, or ultrasound, and no contraindications for L-CEM or CE-MRI. Eighty women were included.Field strength/sequence1.5 and 3T CE-MRI, standard protocol for breast, with dedicated coils, according to international guidelines. L-CEM was performed using a dedicated prototype.AssessmentThree, off-site, blinded readers evaluated the images according to the BI-RADS lexicon in a randomized order, each in two separate reading sessions. Histology served as a gold standard.Statistical testLesion detection rate, sensitivity, specificity, and negative and positive predictive values (NPV, PPV) were calculated and compared with multivariate statistics.ResultsIncluded were 80 women (mean age, 54.3 years ±11.2 standard deviation) with 93 lesions (32 benign, 61 malignant). The detection rate was significantly higher with CE-MRI (92.5-94.6%; L-CEM 79.6-91.4%, P = 0.014). Sensitivity (L-CEM 65.6-90.2%; CE-MRI 83.6-93.4%, P = 0.086) and NPV (L-CEM 59.6-71.4%; CE-MRI 63.0-76.5%, P = 0.780) did not differ between the modalities. Specificity (L-CEM 46.9-96.9%; CE-MRI 37.5-53.1%, P = 0.001) and PPV (L-CEM 76.4-97.6%; CE-MRI 73.3-77.3%, P = 0.007) were significantly higher with L-CEM. Variations between readers were significant for sensitivity and NPV. The accuracy of L-CEM was as good as CE-MRI (75.3-76.3% vs. 72.0-75.3%, P = 0.514).Data conclusionL-CEM showed a high sensitivity and accuracy in women with suspicious findings on conventional imaging. Compared to CE-MRI, L-CEM has the potential to increase specificity and PPV. L-CEM might help to reduce false-positive biopsies while obtaining sensitivity comparable to that of CE-MRI LEVEL OF EVIDENCE: 1 TECHNICAL EFFICACY STAGE: 2 J. Magn. Reson. Imaging 2020;52:589-595.

Project description:ObjectivesTo evaluate the feasibility of contrast-enhanced mammography (CEM)-guided biopsy at Hospital del Mar, a Spanish university hospital.MethodsWe retrospectively reviewed all consecutive women with a suspicious enhancing finding eligible for CEM-guided biopsy, who were prospectively enrolled in a pre-marketing clinical validation and feasibility study (October 2019 to September 2021). CEM-guided biopsy is a stereotactic-based procedure that, by using intravenous iodinated contrast media administration and dual-energy acquisition, provides localisation of enhancing lesions. All the biopsies were performed using a vacuum-assisted device. We collected procedural characteristics (patient position and type of approach), and histopathological results. Feasibility endpoints included success (visualisation of the enhancing lesion, post-procedural biopsy changes and clip placement), procedural time, number of scout acquisitions and complications.ResultsA total of 66 suspicious enhancing lesions (18.0% foci, 44.0% mass, 38.0% non-mass enhancement; median size 8.5 mm) in 64 patients (median age 59 years, mostly minimal [48.4%] or mild [32.8%] background parenchymal enhancement) were referred for CEM-guided biopsy in the study period. The success rate was 63/66 (95.4%). Amongst successful procedures, patients were most frequently seated (52/63, 82.5%) and the preferred approach was horizontal (48/63, 76.2%). Median total time per procedure was 15 min. Median number of acquisitions needed before targeting was 2 (range 1-4). Complications consisted of hematoma (17/63, 27%) and vasovagal reaction (2/63, 3.2%). At histology, the malignancy rate was 25/63 (39.7%).ConclusionIn this first patient series, CEM-guided breast biopsy was feasible, with success and complication rates similar to those previously reported for magnetic resonance guidance.Key points• CEM may be used to guide biopsy of enhancing lesions through a stereotactic-based procedure combined with intravenous iodinated contrast media administration and dual-energy acquisition. • In this first patient series (n = 64), the success rate of CEM-guided biopsy was above 95%, the only complications were hematoma (22.2%) and vasovagal reaction (3.2%), and median total time per procedure was 15 min. • CEM-guided biopsy is feasible and could potentially be a widely available biopsy technique for enhancing-only lesions.

Dataset Information

Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research.

Publications

Categorized contrast enhanced mammography dataset for diagnostic and artificial intelligence research.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets