Go back

Study Complete Details




Project Accession: IBIAP_1000000010
Title: Histopathological images of thyroid lesions
Representative Image:
Description: The dataset comprises 154,498 images derived from 134 slides, representing 125 thyroid nodules from 118 patients. These images encompass six types of thyroid lesions: NIFTP, HTN, FA, IEFVPTC, IFSPTC, and CPTC.
Publications: https://link.springer.com/article/10.1007/s12022-025-09865-0
Associated Codes (URL only): N/A
Funding agency: DBT
Grant Number: BT/PR34211/AI/133/1/2019
Ethics Statement: N/A
Any Other Information : N/A
Additional File: N/A
Acknowledgments: This work was supported by the Department of Biotechnology (DBT) [grant numbers BT/PR34211/AI/133/1/2019 and BT/PR40151/BTIS/137/5/2021]. We would like to express our gratitude to the patients who participated in the study, as well as to the AIIMS and ICGEB for providing the necessary infrastructure for conducting the study. We acknowledge Chhaya, Ashish, Divya and Dhairya's crucial assistance in image QC data curation.

Sr.No First name Last name Email Organization Designation
1 Shweta Birla sbirla84@gmail.com International Centre for Genetic Engineering Biotechnology (ICGEB) Postdoctoral Researcher
2 Nimisha Tiwari nimi.tiwari08@gmail.com International Centre for Genetic Engineering Biotechnology (ICGEB) Research Scholar
3 Pragati Shyamal pragatishyamal1@gmail.com All India Institute of Medical Sciences (AIIMS) Unspecified
4 Arundhati Sharma arundhatisharma1@gmail.com All India Institute of Medical Sciences (AIIMS) Co-Investigator
5 Shipra Agarwal drshipra0902@gmail.com All India Institute of Medical Sciences (AIIMS) Principal Investigator
6 Dinesh Gupta dinesh@icgeb.res.in International Centre for Genetic Engineering Biotechnology (ICGEB) Co-Principal Investigator

Study Accession: HISTOS_1000000014
Title: Utility of Artificial Intelligence in differentiating Non- invasive Follicular Thyroid Neoplasm with Papillary like Nuclear Features from other follicular-patterned thyroid benign and malignant lesions
Imaging Type: Histopathology (HISTO)
Imaging Sub-type: Diagnostic Pathology
Summary: The introduction of the term non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTP) in 2016 marked a pivotal shift in the classification of encapsulated follicular variants of papillary thyroid carcinoma (eFVPTC) lacking invasive features. While this reclassification significantly reduced overtreatment, the histopathological diagnosis of NIFTP remains challenging due to overlapping features with other thyroid lesions and inter-observer variability. This study presents a novel deep learning (DL)-based, three-stage diagnostic pipeline for distinguishing NIFTP from a wide spectrum of thyroid lesions, including benign and malignant mimics. By replicating the diagnostic strategy of histopathologists, the algorithm evaluates architectural patterns and nuclear features with high precision. Our approach has a potential to enhance diagnostic accuracy in a cost-effective and scalable manner, complementing existing diagnostic methods and thus optimizing clinical decision-making and improving the management of patients with thyroid neoplasms.
Keywords: Histopathology; Deep-Learning; Differential Diagnosis; Thyroid Cancers
Additional / Any Other Information: N/A
Release Date: June 2, 2025
Access Licence Type: Open Access

Table 1. The sample types registered under this study are as follows:
Sample Type IDOrganismTaxon IDBiological EntityLateralitySource TissueSource Cell/Cell-lineCell Organelle
HISTOSMT_10000000038Homo sapiens 9606 Thyroid GlandNot ApplicableThyroid gland tissueN/AN/A

Table 2. The samples registered under this study are as follows:
Sample Type ID Sample ID Method used for Sample Collection Cell Phenotype Studied ICD-11 Code (patient health condition) Presentation / Clinical Diagnosis
HISTOSMT_10000000038 HISTOSM_10000198924 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198925 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198930 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198931 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198932 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198933 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198942 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198943 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198944 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198945 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198950 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198951 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198952 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198953 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198962 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198963 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198964 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198965 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198974 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features
HISTOSMT_10000000038 HISTOSM_10000198975 N/A N/A XH6SY0 / XH0Q59 / XH29M4 PTC like features

Table 3. The experiment types registered under this study are as follows:
Experiment Type IDInstrument NameInstrument TypeManufacturerModel
HISTOET_10000000015Digital Slide Scanning SystemDigital Slide ScannerMoticVM1


Experimental Design Summary (HISTOET_10000000015)
Hematoxylin and Eosin (H&E)-stained slides of histopathologically-confirmed cases of FND, HTN,FA, NIFTP, IEFVPTC, IFSPTC, and CPTC patients were retrieved from the archives of the Department of Pathology, All India Institute of Medical Sciences (AIIMS), New Delhi, India, spanning the period from 2015 to 2023. The corresponding slides were further reviewed by an experienced endocrine pathologist to reconfirm the diagnosis and select representative slides for further analysis. The diagnosis adhered to the criteria outlined in the most recent WHO classification of thyroid neoplasms The selected H&E slides were scanned at 40x magnification (equivalent to 0.25 μm/pixel) using the Motic VM1 whole slide scanner to generate whole slide images (WSIs). The slides were than subjected to AI studies.

Acquired Images Annotation Description (HISTOET_10000000015)
WHO defining criteria for the various thyroid lesions included in the study. For more details, please refer to "Additional File" of the "Project" section for this record.

Table 4. The experiments registered under this study are as follows:
Sample ID Experiment Type ID Experiment ID Image type (Original / Derived / Unknown) Any Other Information Staining Type Images Magnification Tissue / Tumor Fixative Used Dataset Split Type (Training / Validation / Test)
HISTOSM_10000078779 HISTOET_10000000015 HISTOE_10000078699 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000098308 HISTOET_10000000015 HISTOE_10000098308 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108708 HISTOET_10000000015 HISTOE_10000107352 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108710 HISTOET_10000000015 HISTOE_10000107354 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108712 HISTOET_10000000015 HISTOE_10000107356 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000068014 HISTOET_10000000015 HISTOE_10000068283 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108714 HISTOET_10000000015 HISTOE_10000107358 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000098314 HISTOET_10000000015 HISTOE_10000098314 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108716 HISTOET_10000000015 HISTOE_10000107360 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000108493 HISTOET_10000000015 HISTOE_10000107362 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000078795 HISTOET_10000000015 HISTOE_10000078715 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000078796 HISTOET_10000000015 HISTOE_10000078716 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000078798 HISTOET_10000000015 HISTOE_10000078718 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000120248 HISTOET_10000000015 HISTOE_10000120248 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000195969 HISTOET_10000000015 HISTOE_10000189917 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000161247 HISTOET_10000000015 HISTOE_10000151371 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000161249 HISTOET_10000000015 HISTOE_10000151372 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000098327 HISTOET_10000000015 HISTOE_10000098327 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000161253 HISTOET_10000000015 HISTOE_10000151374 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset
HISTOSM_10000078815 HISTOET_10000000015 HISTOE_10000078734 Derived N/A Hematoxylin and Eosin (H&E) 40x 10% Neutral buffered formalin Training Dataset

Experiment ID Image File Name (with path) Image Preview Image Size
HISTOE_10000138545thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12161.tiff Unable to preview image
Download Image
44K
HISTOE_10000138546thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12162.tiff Unable to preview image
Download Image
52K
HISTOE_10000138547thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12163.tiff Unable to preview image
Download Image
52K
HISTOE_10000138548thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12164.tiff Unable to preview image
Download Image
48K
HISTOE_10000138549thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12165.tiff Unable to preview image
Download Image
48K
HISTOE_10000138550thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12166.tiff Unable to preview image
Download Image
48K
HISTOE_10000138551thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12167.tiff Unable to preview image
Download Image
44K
HISTOE_10000138552thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12168.tiff Unable to preview image
Download Image
28K
HISTOE_10000138553thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_12169.tiff Unable to preview image
Download Image
48K
HISTOE_10000138554thyroid_lesions/STAGE2_STID/MT_STID/MT_NPTCLF/MT_NPTCLF_1216.tiff Unable to preview image
Download Image
60K