This dataset is taken from the UCI Machine Learning Repository (Link: https://data.world/health/breast-cancer-wisconsin) by the Donor: Nick Street

The main idea and inspiration behind the upload was to provide datasets for Machine Learning as practice and reference for my peers at college. The main purpose is to analyze data and experiment with different machine learning ideas and techniques for this binary classification task. As such, this dataset is a very useful resource to practice on.

Breast cancer is when breast cells mutate and become cancerous cells that multiply and form tumors. It accounts for 25% of all cancer cases and affected over 2.1 Million people in 2015 alone. Breast cancer typically affects women and people assigned female at birth (AFAB) age 50 and older, but it can also affect men and people assigned male at birth (AMAB), as well as younger women. Healthcare providers may treat breast cancer with surgery to remove tumors or treatment to kill cancerous cells.

Features are computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. They describe characteristics of the cell nuclei present in the image. A few of the images can be found at http://www.cs.wisc.edu/~street/images/

The task: To classify whether the tumor is benign (B) or malignant (M).

Relevant information

Features are computed from a digitized image of a fine needle
aspirate (FNA) of a breast mass. They describe
characteristics of the cell nuclei present in the image.
A few of the images can be found at
http://www.cs.wisc.edu/~street/images/

Separating plane described above was obtained using
Multisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree
Construction Via Linear Programming." Proceedings of the 4th
Midwest Artificial Intelligence and Cognitive Science Society,
pp. 97-101, 1992], a classification method which uses linear
programming to construct a decision tree. Relevant features
were selected using an exhaustive search in the space of 1-4
features and 1-3 separating planes.

The actual linear program used to obtain the separating plane
in the 3-dimensional space is that described in:
[K. P. Bennett and O. L. Mangasarian: "Robust Linear
Programming Discrimination of Two Linearly Inseparable Sets",
Optimization Methods and Software 1, 1992, 23-34].


This database is also available through the UW CS ftp server:

ftp ftp.cs.wisc.edu
cd math-prog/cpo-dataset/machine-learn/WDBC/

Number of instances: 569

Number of attributes: 32 (ID, diagnosis, 30 real-valued input features)

Original Creators:

Dr. William H. Wolberg, General Surgery Dept., University of
Wisconsin, Clinical Sciences Center, Madison, WI 53792
wolberg@eagle.surgery.wisc.edu

W. Nick Street, Computer Sciences Dept., University of
Wisconsin, 1210 West Dayton St., Madison, WI 53706
street@cs.wisc.edu 608-262-6619

Olvi L. Mangasarian, Computer Sciences Dept., University of
Wisconsin, 1210 West Dayton St., Madison, WI 53706
olvi@cs.wisc.edu 

Donor: Nick Street

Date: November 1995

Past Usage:

first usage:

W.N. Street, W.H. Wolberg and O.L. Mangasarian 
Nuclear feature extraction for breast tumor diagnosis.
IS&T/SPIE 1993 International Symposium on Electronic Imaging: Science
and Technology, volume 1905, pages 861-870, San Jose, CA, 1993.

OR literature:

O.L. Mangasarian, W.N. Street and W.H. Wolberg. 
Breast cancer diagnosis and prognosis via linear programming. 
Operations Research, 43(4), pages 570-577, July-August 1995.

Medical literature:

W.H. Wolberg, W.N. Street, and O.L. Mangasarian. 
Machine learning techniques to diagnose breast cancer from
fine-needle aspirates. 
Cancer Letters 77 (1994) 163-171.

W.H. Wolberg, W.N. Street, and O.L. Mangasarian. 
Image analysis and machine learning applied to breast cancer
diagnosis and prognosis. 
Analytical and Quantitative Cytology and Histology, Vol. 17
No. 2, pages 77-87, April 1995. 

W.H. Wolberg, W.N. Street, D.M. Heisey, and O.L. Mangasarian. 
Computerized breast cancer diagnosis and prognosis from fine
needle aspirates. 
Archives of Surgery 1995;130:511-516.

W.H. Wolberg, W.N. Street, D.M. Heisey, and O.L. Mangasarian. 
Computer-derived nuclear features distinguish malignant from
benign breast cytology. 
Human Pathology, 26:792--796, 1995.

See also: http://www.cs.wisc.edu/~olvi/uwmp/mpml.html http://www.cs.wisc.edu/~olvi/uwmp/cancer.html

Description:

Explore the field of breast cancer diagnosis with the insightful Wisconsin Breast Cancer dataset (Original). This dataset provides detailed attributes representing tumor characteristics observed in breast tissue samples. By analyzing these attributes, researchers and medical professionals can gain insights into tumor behavior and develop predictive models for cancer detection and prognosis.

Usage:

• Cancer diagnosis: Develop machine learning models to classify tumors as benign or malignant based on their characteristics, aiding in early detection and treatment planning.
• Feature importance analysis: Identify key attributes contributing to tumor malignancy and understand their biological significance.
• Clinical decision support: Assist healthcare professionals in interpreting biopsy results and making informed decisions about patient care.

Acknowledgements:

The Breast Cancer Wisconsin dataset is sourced from tissue samples collected for diagnostic purposes, with attributes derived from microscopic examination. The dataset is anonymized and made available for research purposes, contributing to advancements in cancer diagnosis and treatment.

The Breast Cancer Wisconsin dataset is a multiclass classification dataset. It contains 699 samples, each described by 9 features, and is used for cancer diagnosis.

BREAST CANCER WISCONSIN (DIAGNOSTIC) DATA SET Predict whether the cancer is benign or malignant. It consists of features that are computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. They describe characteristics of the cell nuclei present in the image.

Ten real-valued features are computed for each cell nucleus: a) radius (mean of distances from center to points on the perimeter) b) texture (standard deviation of gray-scale values) c) perimeter d) area e) smoothness (local variation in radius lengths) f) compactness (perimeter^2 / area - 1.0) g) concavity (severity of concave portions of the contour) h) concave points (number of concave portions of the contour) i) symmetry j) fractal dimension ("coastline approximation" - 1)

Dataset

This dataset was created by Arnab Saha

Contents

1) Data Introduction • The Breast Cancer Wisconsin (Diagnostic) data focuses on distinguishing between malignant (cancerous) and benign (non-cancerous) breast tumors. This dataset is crucial for developing machine learning models to aid in the early detection and classification of breast cancer, thereby potentially saving lives through timely intervention.

2) Data Utilization (1) Breast cancer data has characteristics that: • The dataset contains various features extracted from digitized images of fine needle aspirate (FNA) of breast masses, allowing for detailed analysis and classification of tumors. (2) Breast cancer data can be used to: • Healthcare and Medical Research: Useful for developing diagnostic tools and models to accurately classify breast tumors, aiding healthcare providers in making informed decisions. • Machine Learning and AI Development: Assists in creating and fine-tuning machine learning algorithms to improve predictive accuracy in medical diagnostics.

The dataset used in this study for exploring white-box attacks and defenses on quantum neural networks under depolarization noise.

This dataset, derived from the Wisconsin Breast Cancer (Diagnostic), is a comprehensive resource for developing and evaluating machine learning models focused on the binary classification of breast tumors as either benign (B) or malignant (M). The data consists of features computed from digitized images of fine needle aspirates (FNA) of breast masses, offering a rich set of quantitative metrics for computational pathology and diagnostic research. The dataset is a critical tool for healthcare… See the full description on the dataset page: https://huggingface.co/datasets/mnemoraorg/wisconsin-breast-cancer-diagnostic.

Analysis of ‘Breast Cancer Wisconsin (Diagnostic) Data Set’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/uciml/breast-cancer-wisconsin-data on 20 November 2021.

--- Dataset description provided by original source is as follows ---

Features are computed from a digitized image of a fine needle aspirate (FNA) of a breast mass. They describe characteristics of the cell nuclei present in the image. n the 3-dimensional space is that described in: [K. P. Bennett and O. L. Mangasarian: "Robust Linear Programming Discrimination of Two Linearly Inseparable Sets", Optimization Methods and Software 1, 1992, 23-34].

This database is also available through the UW CS ftp server: ftp ftp.cs.wisc.edu cd math-prog/cpo-dataset/machine-learn/WDBC/

Also can be found on UCI Machine Learning Repository: https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+%28Diagnostic%29

Attribute Information:

1) ID number 2) Diagnosis (M = malignant, B = benign) 3-32)

Ten real-valued features are computed for each cell nucleus:

a) radius (mean of distances from center to points on the perimeter) b) texture (standard deviation of gray-scale values) c) perimeter d) area e) smoothness (local variation in radius lengths) f) compactness (perimeter^2 / area - 1.0) g) concavity (severity of concave portions of the contour) h) concave points (number of concave portions of the contour) i) symmetry j) fractal dimension ("coastline approximation" - 1)

The mean, standard error and "worst" or largest (mean of the three largest values) of these features were computed for each image, resulting in 30 features. For instance, field 3 is Mean Radius, field 13 is Radius SE, field 23 is Worst Radius.

All feature values are recoded with four significant digits.

Missing attribute values: none

Class distribution: 357 benign, 212 malignant

--- Original source retains full ownership of the source dataset ---

Source:

Copied from the original dataset

  Creators:

Dr. William H. Wolberg, General Surgery Dept. University of Wisconsin, Clinical Sciences Center Madison, WI 53792 wolberg '@' eagle.surgery.wisc.edu

W. Nick Street, Computer Sciences Dept. University of Wisconsin, 1210 West Dayton St., Madison, WI 53706 street '@' cs.wisc.edu 608-262-6619

Olvi L. Mangasarian, Computer Sciences Dept. University of Wisconsin, 1210 West Dayton St., Madison, WI 53706 olvi '@' cs.wisc.edu… See the full description on the dataset page: https://huggingface.co/datasets/wwydmanski/wisconsin-breast-cancer.

Analysis of ‘Breast Cancer Wisconsin (Diagnostic) ’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/faroukbenarous/breast-cancer-wisconsin-diagnostic on 30 September 2021.

--- No further description of dataset provided by original source ---

--- Original source retains full ownership of the source dataset ---

Breast Cancer Prognostics

Study the Wisconsin Dataset

By UCI [source]

About this dataset

The Breast Cancer Wisconsin (Prognostic) dataset brings together data collected from hundreds of breast cancer cases, making it valuable for predictive prognosis. It includes 30 features such as radius, texture, area, compactness and concavity that were generated from the a digitized fine needle aspirate (FNA) of the mass to generate characteristics of the cell nuclei present in each case. It also includes outcomes such as recurrence and nonrecurrence and also time-to-recurrence information for those cases that relapse.

This breaking dataset was created by some leading minds in medical science; Dr William H. Wolberg at the University Of Wisconsin Clinical Sciences Center alongside W. Nick Street at the university's Computer Sciences Dept., and Olvi L Mangasarian also based there - all credited with creating various decision tree construction systems using linear programming models to accurately predict disease recurrences within an incredibly short time frame.

The data is freely available through UW CS ftp server or on Kaggle's website making use easier than ever before - giving all researchers access up-to-date information regarding breast cancer prognosis and diagnosis via images taken from FNA tests conducted on masses in diagnosed patients' bodies - allowing each participant instantaneous access to a powerful set of features versus outcomes within both recurrent and nonrecurrent situations.. Moreover papers such as 'An inductive learning approach to prognostic prediction.' by WN street et al have utilized this database extensively mapping out how Artificial Neural Networks can be used for predictive tasks with noteworthy success! Armed with these tested ideas consequently anyone has access level ground in understanding how decisions are made as it relates to predicting breast cancer outcome effectively utilizing this dataset helping us better understand how a predictive model can significantly improve patient care processes!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset is designed to improve the prognostics of breast cancer using machine learning algorithms. The data consists of a time series of patient symptoms and various medical parameters, such as tumor size and malignancy, that can be used by programmatic algorithms to predict diagnosis and prognosis outcomes. Here are some steps on how to use this dataset:

• Pre-process and clean the data: Since the dataset contains incomplete or missing values across various parameters, it is important to clean and pre-process the data before attempting any machine learning algorithm (MLA). This includes sorting out what type of values need imputation, standardizing features for better performance, encoding categorical variables for MLAs, and normalizing numerical values for accuracy.

• Choose an appropriate MLA: Depending on your exact goal with this data set - for example if you wanted reliable classification results or weighted predictions based on factors - there are a variety of MLAs from which you may select; examples include logistic regression classifiers, least squares support vector machines (SVM), neural networks, nonsmooth optimization algorithms like A-Optimality or global optimization methods such as Extract M-of-N rule sets from trained neural nets.. It would be wise to read up on each algorithm in order to determine which one most appropriately meets your needs before starting experimentation with the dataset itself.

• Train the model using your selected MLA: Once you have identified an MLA that fits your desired result outcome best – or if you decide on experimenting with multiple approaches –it’s time turn back towards the data itself in order run experiments actually examine outcomes based upon training models built upon it through cross validation methods such as k-fold splitting.. Then test these trained models against validation datasets taken from specified subsets within the original larger data set structure held by Kaggle in order get general outputs results determining performance rates over various conditions presented by parameter combinations relevant when predicting breast cancer diagnostic &/or prognostic outcomes .. Establishing any trends revealed during these experiments will help inform future model selections during training process associated implementing an effective predictive solution fitting specific user requirements especially where particular MLA are not tailored handle purpose generally falling outside scope designing said model so guaranteeing ac...

Breast Cancer Wisconsin Dataset: African Physiognomy Adjusted

  Dataset Description

This dataset addresses representation bias in medical AI by providing an African physiognomy-adjusted version of the classic Wisconsin Breast Cancer Dataset. The adjustment methodology systematically modifies cellular morphology features to better reflect documented physiological differences in African populations.

  Dataset Summary

Original Dataset: Wisconsin Breast Cancer Dataset… See the full description on the dataset page: https://huggingface.co/datasets/electricsheepafrica/breast-cancer-africa-adjusted-dataset.

Dataset

This dataset was created by PAVAN KUMAR D

Contents

Description: Breast cancer is the most common cancer amongst women in the world. It accounts for 25% of all cancer cases, and affected over 2.1 Million people in 2015 alone. It starts when cells in the breast begin to grow out of control. These cells usually form tumors that can be seen via X-ray or felt as lumps in the breast area. The key challenges against it’s detection is how to classify tumors into malignant (cancerous) or benign(non cancerous). We ask you to complete the analysis of classifying these tumors using machine learning (with SVMs) and the Breast Cancer Wisconsin (Diagnostic) Dataset. Acknowledgements: This dataset has been referred from Kaggle. Objective: Understand the Dataset & cleanup (if required). Build classification models to predict whether the cancer type is Malignant or Benign. Also fine-tune the hyperparameters & compare the evaluation metrics of various classification algorithms.

Original data from: https://archive.ics.uci.edu/ml/datasets/Breast+Cancer+Wisconsin+(Diagnostic). Changes made: - 16 rows with '?' for Bare Nuclei removed, leaving 683 records # Attribute Domain -- ----------------------------------------- 0. Class: (-1 for benign, +1 for malignant) 1. Clump Thickness 1 - 10 2. Uniformity of Cell Size 1 - 10 3. Uniformity of Cell Shape 1 - 10 4. Marginal Adhesion 1 - 10 5. Single Epithelial Cell Size 1 - 10 6. Bare Nuclei 1 - 10 7. Bland Chromatin 1 - 10 8. Normal Nucleoli 1 - 10 9. Mitoses 1 - 10

Dataset

This dataset was created by Aditya_Sahu500096455

Released under MIT

Contents

1) Data Introduction • The Cancer Classification dataset is derived from the UCI ML Breast Cancer Wisconsin (Diagnostic) datasets, containing 569 instances with 30 numerical attributes. The features are computed from digitized images of fine needle aspirates (FNA) of breast masses, aimed at distinguishing between malignant and benign tumors.

2) Data Utilization (1) Cancer Classification data has characteristics that: • It includes detailed measurements of cell nuclei characteristics such as radius, texture, perimeter, area, smoothness, compactness, concavity, symmetry, and fractal dimension. These attributes are essential for accurate classification of breast cancer tumors. (2) Cancer Classification data can be used to: • Medical Diagnosis: Assists in developing predictive models to classify breast cancer tumors as malignant or benign, aiding in early detection and treatment planning. • Research and Development: Supports academic research and development of machine learning models in the medical field, providing a comprehensive dataset for testing various algorithms.

Timely and accurate diagnosis of breast cancer remains a critical clinical challenge. In this study, we propose Stacked Artificial Neural Network (StackANN), a robust stacking ensemble framework that integrates six classical machine learning classifiers with an Artificial Neural Network (ANN) meta-learner to enhance diagnostic precision and generalization. By incorporating the Synthetic Minority Over-Sampling Technique (SMOTE) to address class imbalance and employing SHapley Additive exPlanations (SHAP) for model interpretability. StackANN was comprehensively evaluated on Wisconsin Diagnostic Breast Cancer (WDBC) datasets, Ljubljana Breast Cancer (LBC) datasets and Wisconsin Breast Cancer Dataset (WBCD), as well as the METABRIC2 dataset for multi-subtype classification. Experimental results demonstrate that StackANN consistently outperforms individual classifiers and existing hybrid models, achieving near-perfect Recall and Area Under the Curve (AUC) values while maintaining balanced overall performance. Importantly, feature attribution analysis confirmed strong alignment with clinical diagnostic criteria, emphasizing tumor malignancy, size, and morphology as key determinants. These findings highlight StackANN as a reliable, interpretable, and clinically relevant tool with significant potential for early screening, subtype classification, and personalized treatment planning in breast cancer care.