A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories

Garima Jain; Abhijeet Patil; Surabhi Jain; Sanghamitra Pati; Amit Sethi; Sandeep Mathur; Pulkit Verma; Nishi Halduniya; Jatin Kashyap; Sharat Kumar; Simmi Kharb; Sunita Singh; Sucheta Devi Khuraijam; Sushma Khuraijam; Ratan Konjengbam; Arvind Kumar; Deepali Tirkey; Saurav Banerjee; Shivani Kalhan; Rakesh Kumar Gupta; Ranjana Solanki; Deepika Hemranjani; Shashank Nath Singh; Uma Handa; Manveen Kaur; B. G. Malathi; Yogender P.; Niraj Kumari; Shruti Gupta; Indu R. Nair; Vidya C.; Basumitra Das; Sunil Kumar Komanapalli; Ravindra Karle; Tanaya Kulkarni; Vandana Raphael; Biswajit Dey; Vaishali Gaikwad; Nilam Adhav

A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories

Computer Vision and Pattern Recognition 2026-06-29 v1 Artificial Intelligence

Authors: Garima Jain , Abhijeet Patil , Surabhi Jain , Sanghamitra Pati , Amit Sethi , Sandeep Mathur , Pulkit Verma , Nishi Halduniya , Jatin Kashyap , Sharat Kumar , Simmi Kharb , Sunita Singh , Sucheta Devi Khuraijam , Sushma Khuraijam , Ratan Konjengbam , Arvind Kumar , Deepali Tirkey , Saurav Banerjee , Shivani Kalhan , Rakesh Kumar Gupta , Ranjana Solanki , Deepika Hemranjani , Shashank Nath Singh , Uma Handa , Manveen Kaur , B. G. Malathi , Yogender P. , Niraj Kumari , Shruti Gupta , Indu R. Nair , Vidya C. , Basumitra Das , Sunil Kumar Komanapalli , Ravindra Karle , Tanaya Kulkarni , Vandana Raphael , Biswajit Dey , Vaishali Gaikwad , Nilam Adhav

View on arXiv ↗ PDF ↗

Abstract

We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary medical centers in India between May 2023 and March 2026. Slides were stained using Papanicolaou (190 WSIs) or MayGrunwald Giemsa (280 WSIs), scanned on a Hamamatsu NanoZoomer S360 at 40X magnification and 0.25 microns per pixel, and stored directly in NDPI format. Across the 470 WSIs, 446 WSIs contain annotated patch regions, yielding 7,398 PNG image patches with expert-verified C1 to C5 labels. The release includes NDPI WSIs, WSI-level GeoJSON annotation files, extracted patch images, deidentified metadata, a data dictionary, a validation summary, a manifest linking WSIs to Zenodo records, and code for dataset inspection and reuse. The complete dataset is approximately 950 GB and is available through Zenodo.

Keywords

breast FNAC whole-slide images cytology dataset patch-wise classification C1-C5 reporting multi-center AI-assisted diagnosis

Cite

@article{arxiv.2606.30209,
  title  = {A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories},
  author = {Garima Jain and Abhijeet Patil and Surabhi Jain and Sanghamitra Pati and Amit Sethi and Sandeep Mathur and Pulkit Verma and Nishi Halduniya and Jatin Kashyap and Sharat Kumar and Simmi Kharb and Sunita Singh and Sucheta Devi Khuraijam and Sushma Khuraijam and Ratan Konjengbam and Arvind Kumar and Deepali Tirkey and Saurav Banerjee and Shivani Kalhan and Rakesh Kumar Gupta and Ranjana Solanki and Deepika Hemranjani and Shashank Nath Singh and Uma Handa and Manveen Kaur and B. G. Malathi and Yogender P. and Niraj Kumari and Shruti Gupta and Indu R. Nair and Vidya C. and Basumitra Das and Sunil Kumar Komanapalli and Ravindra Karle and Tanaya Kulkarni and Vandana Raphael and Biswajit Dey and Vaishali Gaikwad and Nilam Adhav},
  journal= {arXiv preprint arXiv:2606.30209},
  year   = {2026}
}

Comments

9 pages, 1 figure