Indian Biological Images Archive

Project Accession:	IBIAP_1000000044
Title:	Indian Mammography Database 2.0 (IMDB 2.0)
Representative Image:
Description:	This dataset consists of de-identified Full-Field Digital Mammography (FFDM) and Synthetic Mammography (SM) examinations acquired from women aged 18 years and older at a tertiary care oncology center between August and December 2025. The dataset includes BI-RADS assessments and breast density information extracted from radiology reports. Histopathology serves as the reference standard for suspicious lesions when available (BI-RADS 4/5), while follow-up imaging is available for probably benign cases (BI-RADS 3). Designed for artificial intelligence research, the dataset supports applications such as breast cancer detection, lesion classification, breast density assessment, and computer-aided diagnosis using deep learning and computer vision approaches.
Publications:	N/A
Associated Codes (URL only):	N/A
Funding agency:	N/A
Grant Number:	N/A
Ethics Statement:	Download
Any Other Information :	N/A
Additional File:	N/A
Acknowledgments:	The authors acknowledge the Department of Radiology, AIIMS New Delhi and Department of Oncoradiology, IRCH, AIIMS New Delhi, for technical and clinical support. The authors also acknowledge partial funding received by TANUH.

Sr.No	First name	Last name	Email	Organization	Designation
1	Varun	Holla	varunholla35@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
2	Ashish	Rastogi	ashishrastogi.3150@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
3	Omshivom	Nagpal	shivam.aiims.coe@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
4	Kushagra	Chaturvedi	kushagrachaturvedi15@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
5	Vipin	Thampi	thampi1990aiims@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
6	Aditi	Madame	aditimadame19@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
7	Hema	Malhotra	hemamalhotraaiims.2020@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
8	Sathish	R	sathishappu314@gmail.com	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Unspecified
9	Krithika	Rangarajan	krithikarangarajan@aiims.edu	Dr. B.R.A.IRCH, All India Institute of Medical Sciences (AIIMS), New Delhi, India	Principal Investigator

Study Accession:	MAMOS_1000000050
Title:	Indian Mammography Database 2.0 (IMDB 2.0)
Imaging Type:	Mammography (MAMO)
Imaging Sub-type:	Diagnostic Radiology
Summary:	This dataset consists of de-identified Full-Field Digital Mammography (FFDM) and Synthetic Mammography (SM) examinations acquired from women aged 18 years and older at a tertiary care oncology center between August and December 2025. The dataset includes BI-RADS assessments and breast density information extracted from radiology reports. Histopathology serves as the reference standard for suspicious lesions when available (BI-RADS 4/5), while follow-up imaging is available for probably benign cases (BI-RADS 3). Designed for artificial intelligence research, the dataset supports applications such as breast cancer detection, lesion classification, breast density assessment, and computer-aided diagnosis using deep learning and computer vision approaches.
Keywords:	Breast cancer; Mammography; Screening
Additional / Any Other Information:	N/A
Release Date:	June 18, 2026
Access Licence Type:	Open Access

Table 1. The sample types registered under this study are as follows:

Sample Type ID	Organism	Taxon ID	Biological Entity	Laterality	Source Tissue	Source Cell/Cell-line	Cell Organelle
MAMOSMT_10000000072	Homo sapiens	9606	Breast	Both	N/A	N/A	N/A

The total number of samples registered under this study is: 9097

Table 3. The experiment types registered under this study are as follows:

Experiment Type ID	Instrument Name	Instrument Type	Manufacturer	Model
MAMOET_10000000039	Mammography Machine	Digital mammography	Hologic	Selenia

Experimental Design Summary (MAMOET_10000000039)
All mammographic examinations included in the present study were acquired using the Hologic Selenia Dimensions mammography system at our institution. The standard imaging protocol consisted of two-dimensional (2D) mammographic views for each breast, namely the cranio-caudal (CC) and medio-lateral oblique (MLO) projections, along with digital breast tomosynthesis (DBT) and synthesized mammography (SM) images. These image sets were obtained during a single breast compression using the system’s combination acquisition mode. When mammographic findings appeared suspicious or when breast density was expected to reduce the sensitivity of mammography, supplementary breast ultrasonography (US) was performed during the same setting. In such cases, the final radiological interpretation incorporated findings from both mammography and ultrasound examinations.

Experimental Design Summary (MAMOET_10000000039)

All mammographic examinations included in the present study were acquired using the Hologic Selenia Dimensions mammography system at our institution. The standard imaging protocol consisted of two-dimensional (2D) mammographic views for each breast, namely the cranio-caudal (CC) and medio-lateral oblique (MLO) projections, along with digital breast tomosynthesis (DBT) and synthesized mammography (SM) images. These image sets were obtained during a single breast compression using the system’s combination acquisition mode. When mammographic findings appeared suspicious or when breast density was expected to reduce the sensitivity of mammography, supplementary breast ultrasonography (US) was performed during the same setting. In such cases, the final radiological interpretation incorporated findings from both mammography and ultrasound examinations.

Acquired Images Annotation Description (MAMOET_10000000039)
Assessments were reported according to the fifth edition of the Breast Imaging Reporting and Data System (BI-RADS). A single BI-RADS category was assigned to each breast based on the most clinically significant abnormality identified on either mammography or ultrasound. Mammography reports underwent a double-reading process, with an initial interpretation by a radiology trainee followed by a review by an experienced breast imaging specialist. In instances of disagreement, the final assessment was determined by the specialist radiologist. For reference standard determination, a composite ground truth approach was adopted. Lesions categorized as BI-RADS 4 or BI-RADS 5 were verified through histopathological examination of the image-guided biopsy procedures. Histopathology outcomes were classified as either malignant (cancer) or benign (non-cancer). For BI-RADS 3 lesions, follow-up imaging studies were reviewed to assess lesion stability over time and the available follow-ups are uploaded. For BI-RADS 1 and BI-RADS 2 categories, available follow-up examinations and clinical records were reviewed whenever possible. Cases without evidence of malignancy during the observation period were categorized as non-cancer. The finalized ground-truth labels were linked to unique patient identifiers and stored in a structured dataset for subsequent analysis and model development.

Acquired Images Annotation Description (MAMOET_10000000039)

Assessments were reported according to the fifth edition of the Breast Imaging Reporting and Data System (BI-RADS). A single BI-RADS category was assigned to each breast based on the most clinically significant abnormality identified on either mammography or ultrasound. Mammography reports underwent a double-reading process, with an initial interpretation by a radiology trainee followed by a review by an experienced breast imaging specialist. In instances of disagreement, the final assessment was determined by the specialist radiologist. For reference standard determination, a composite ground truth approach was adopted. Lesions categorized as BI-RADS 4 or BI-RADS 5 were verified through histopathological examination of the image-guided biopsy procedures. Histopathology outcomes were classified as either malignant (cancer) or benign (non-cancer). For BI-RADS 3 lesions, follow-up imaging studies were reviewed to assess lesion stability over time and the available follow-ups are uploaded. For BI-RADS 1 and BI-RADS 2 categories, available follow-up examinations and clinical records were reviewed whenever possible. Cases without evidence of malignancy during the observation period were categorized as non-cancer. The finalized ground-truth labels were linked to unique patient identifiers and stored in a structured dataset for subsequent analysis and model development.

The total number of experiments registered under this study is: 9097

The total number of images registered under this study is: 9097

IBIA: Indian Biological Images Archive

Address

Quick Links

IBIA: Indian Biological Images Archive

Project

Authors/Collaborators

Study

Sample(s)

Experiment(s)

Image Files

Address

Quick Links