Asset Detail:

ML Ready Pathology Reports

ML Ready Pathology Reports

ASSET LINK:

https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-7423964

PROGRAM NAME:

NCI-DOE Collaboration

STUDY NAME:

NCI DOE Collaboration MOSSAIC project: Population Information Integration, Analysis, and Modeling for Precision Surveillance

ASSET NAME:

ML Ready Pathology Reports

ASSET PATH:

/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_3/ml_ready_pathology_reports

Asset Attributes

ATTRIBUTE: ASSET NAME	VALUE: ML Ready Pathology Reports
ATTRIBUTE: ASSET DESCRIPTION	VALUE: This asset contains 7187 pathology reports with the associated site and histology labels downloaded from the Genomic Data Commons Platform at the National Cancer Institute. The files in ml_ready_raw_text_pathology_reports.tar.gz were converted from PDF to text using an optical character recognition program (refer to the Tesseract link). An example of a report is available on the GDC archive portal (refer to the GDC link). The file ml_ready_raw_text_histo_metadata.csv contains annotations (such as site and histology) extracted from those reports. This data set is used as input to MT-CNN and HiSan (refer to the GitHub Repository links and Model links).
ATTRIBUTE: ASSET IDENTIFIER	VALUE: ml_ready_pathology_reports
ATTRIBUTE: ASSET TYPE	VALUE: Dataset
ATTRIBUTE: PLATFORM VERSION	VALUE: None
ATTRIBUTE: IS REFERENCE DATASET	VALUE: No
ATTRIBUTE: COLLECTION SIZE	VALUE: 11.9 MB
ATTRIBUTE: GDC	VALUE:
ATTRIBUTE: GITHUB REPOSITORY HISAN	VALUE:
ATTRIBUTE: GITHUB REPOSITORY MT-CNN	VALUE:
ATTRIBUTE: MODEL HISAN	VALUE:
ATTRIBUTE: MODEL MT-CNN	VALUE:
ATTRIBUTE: TESSERACT	VALUE:

Overview

ASSET LINK:	https://modac.cancer.gov/assetDetails?dme_data_id=NCI-DME-MS01-7423964
PROGRAM NAME:	NCI-DOE Collaboration
STUDY NAME:	NCI DOE Collaboration MOSSAIC project: Population Information Integration, Analysis, and Modeling for Precision Surveillance
ASSET NAME:	ML Ready Pathology Reports
ASSET PATH:	/NCI_DOE_Archive/JDACS4C/JDACS4C_Pilot_3/ml_ready_pathology_reports

Asset Attributes

ATTRIBUTE	VALUE
ASSET NAME	ML Ready Pathology Reports
ASSET DESCRIPTION	This asset contains 7187 pathology reports with the associated site and histology labels downloaded from the Genomic Data Commons Platform at the National Cancer Institute. The files in ml_ready_raw_text_pathology_reports.tar.gz were converted from PDF to text using an optical character recognition program (refer to the Tesseract link). An example of a report is available on the GDC archive portal (refer to the GDC link). The file ml_ready_raw_text_histo_metadata.csv contains annotations (such as site and histology) extracted from those reports. This data set is used as input to MT-CNN and HiSan (refer to the GitHub Repository links and Model links).
ASSET IDENTIFIER	ml_ready_pathology_reports
ASSET TYPE	Dataset
PLATFORM VERSION	None
IS REFERENCE DATASET	No
COLLECTION SIZE	11.9 MB
GDC	https://portal.gdc.cancer.gov/legacy-archive/files/a9a42650-4613-448d-895e-4f904285f508
GITHUB REPOSITORY HISAN	https://github.com/CBIIT/NCI-DOE-Collab-Pilot3-Pathology-Reports-Hierarchical-Self-Attention-Network
GITHUB REPOSITORY MT-CNN	https://github.com/CBIIT/NCI-DOE-Collab-Pilot3-Multitask-Convolutional_Neural_Network
MODEL HISAN	https://modac.cancer.gov/searchTab?dme_data_id=NCI-DME-MS01-7565752
MODEL MT-CNN	https://modac.cancer.gov/searchTab?dme_data_id=NCI-DME-MS01-7330732
TESSERACT	https://github.com/tesseract-ocr/

Asset Files

To download files, please login.

Batch Select	FILE/COLLECTION	FILE SIZE	ACTIONS

Metadata: