Dark Mode
Breast Tissue Electrical Impedance Features
Patient Health Records & Digital Health
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
Features derived from electrical impedance measurements of freshly excised tissue samples from the breast. The data is suitable for multivariate classification tasks within the subject area of health and medicine. These features represent the impedance spectrum, which is calculated from measurements taken across a spectrum of seven frequencies ranging from 15.625 KHz up to 1000 KHz. The primary purpose of this data is predicting the specific classification of the tissue sample.
Columns
- I0: Impedivity (ohm) at zero frequency.
- PA500: Phase angle at 500 KHz.
- HFS: High-frequency slope of phase angle.
- DA: Impedance distance between spectral ends.
- AREA: Area under spectrum.
- A/DA: Area normalized by DA.
- MAX IP: Maximum of the spectrum.
- DR: Distance between I0 and real part of the maximum frequency point.
- P: Length of the spectral curve.
- Class: Tissue type, which is the target variable (options include carcinoma, fibro-adenoma, mastopathy, glandular, connective, and adipose).
Distribution
This dataset contains 106 instances (samples). All 10 features are of a real numerical type. The data shows zero missing values or mismatched entries. The tissue type distribution shows 'adi' (adipose) and 'car' (carcinoma) as the most frequent classes. The data structure is fixed, and no further updates are anticipated.
Usage
This data product is highly suitable for various classification tasks, particularly:
- Predicting the type of breast tissue based on derived electrical characteristics.
- Machine learning applications focused on distinguishing between six distinct tissue classes.
- Experiments in reducing dimensionality or complexity, such as merging the fibro-adenoma, mastopathy, and glandular classes into a smaller set of four classes, due to the known difficulty in discriminating between these types.
- Benchmarking algorithms for multiclass classification problems in medical diagnostics.
Coverage
The data originates from electrical impedance measurements of freshly excised breast tissue. It provides insight into the biophysical characteristics of different tissue types. No information regarding geographical origin, specific time range of collection, or demographic details is included; the scope is confined to the measured electrical properties of the tissue samples.
License
CC BY-SA 4.0
Who Can Use It
- Data Scientists: For developing and tuning robust classification models related to medical diagnostics.
- Students and Researchers: Utilising the dataset for educational purposes or as a health-related benchmark for clustering and PCA studies.
- Bioengineers: Investigating the correlation between tissue type and electrical impedance spectral properties.
Dataset Name Suggestions
- Breast Tissue Electrical Impedance Features
- Biomedical Impedance Classification Data
- Excised Tissue Sample Biometrics
Attributes
Original Data Source: Breast Tissue Electrical Impedance Features
QUALITYLoading...