Datasets
Standard Dataset
Pathology of colorectal, breast, thyroid, and gastric cancer
- Citation Author(s):
- Submitted by:
- ensiyeh bahadoran
- Last updated:
- Wed, 10/25/2023 - 23:23
- DOI:
- 10.21227/5vk7-2w34
- License:
- Categories:
- Keywords:
Abstract
The pathology files of 194 colon cancer patients, 137 breast cancer patients, 124 gastric cancer patients, and 169 thyroid cancer patients who were referred to the healthcare facilities of Qazvin Province, Iran were examined for age, sex, surgery type, and pathological information. We collected information between 2010 and 2020.
The features extracted from the pathology files from colon cancer cases were sex, age, surgery type, tumor site, tumor size, tumor configuration, histologic type, histologic grade, extent of invasion (primary tumor, PT), number of involved regional lymph nodes, distant metastasis, surgical margin status, angiolymphatic invasion, perineural invasion, Duke's stage, and survival.
Recorded features from cases with breast cancer included sex, age, laterality, surgery type, tumor site, tumor size, histologic type, histologic grade, number of involved regional lymph nodes, distant metastasis, angiolymphatic invasion, microcalcification, in situ component, deep surgical margin status, and survival.
Data collected for gastric cancer include age, sex, surgery type, tumor site, tumor configuration, tumor size, histologic type, histologic grade, the extent of invasion (primary tumor, PT), number of involved regional lymph nodes, distant metastasis, surgical margin status, angiolymphatic invasion, perineural invasion, omentum involvement and survival.
Finally, the features of thyroid cancer patients include sex, age, surgery type, thyroid gland weight, tumor site, tumor size, encapsulation, capsular invasion, angiolymphatic invasion, extrathyroidal extension, multicentricity, C cell hyperplasia, additional findings, existence of the parathyroid gland, number of involved regional lymph nodes, and survival.
In our dataset files (ZIP file), we used "numbers" to determine the "different possibilities" of cancer variables.
In the PDF file, "numbers" that determine "different possibilities" for the variables of each cancer can be recognized.
In the supplementary file you will get a better understanding about the meanings of pathology and surgery expressions.
Documentation
Comments
I use this data for my university project