Biological Sciences Division
Published April 29, 2024 | Version v1
Journal article Open

Deep learning detects premalignant lesions in the Fallopian tube

Creators

  • 1. Radboud University
  • 2. University of Groningen
  • 3. Dartmouth College
  • 4. Leiden University
  • 5. Johns Hopkins University
  • 6. Roswell Park Comprehensive Cancer Center
  • 7. University of Chicago
  • 8. Mayo Clinic
  • 9. University of Pennsylvania
  • 10. University of Pittsburgh
  • 11. Emory University Hospital
  • 12. Royal Women's Hospital

Description

Tubo-ovarian high-grade serous carcinoma is believed to originate in the fallopian tubes, arising from precursor lesions like serous tubal intraepithelial carcinoma (STIC) and serous tubal intraepithelial lesion (STIL). Adequate diagnosis of these precursors is important, but can be challenging for pathologists. Here we present a deep-learning algorithm that could assist pathologists in detecting STIC/STIL. A dataset of STIC/STIL (n = 323) and controls (n = 359) was collected and split into three groups; training (n = 169), internal test set (n = 327), and external test set (n = 186). A reference standard was set for the training and internal test sets, by a panel review amongst 15 gynecologic pathologists. The training set was used to train and validate a deep-learning algorithm (U-Net with resnet50 backbone) to differentiate STIC/STIL from benign tubal epithelium. The model's performance was evaluated on the internal and external test sets by ROC curve analysis, achieving an AUROC of 0.98 (95% CI: 0.96–0.99) on the internal test set, and 0.95 (95% CI: 0.90–0.99) on the external test set. Visual inspection of all cases confirmed the accurate detection of STIC/STIL in relation to the morphology, immunohistochemistry, and the reference standard. This model's output can aid pathologists in screening for STIC, and can contribute towards a more reliable and reproducible diagnosis.

Data availability

Images are subject to various data transfer agreements. These images can be requested at the respective pathology institutions. Source codes to train and assess the deep learning model and data from the reference standard are available from the corresponding author on reasonable request. The deep-learning model will be made freely accessible for research purposes and can be accessed on-line (grand-challenge.org), after this manuscript is accepted for publication.

Files

Deep-learning-detects-premalignant-lesions-in-the-Fallopian-tube.pdf

Files (3.6 MB)

Name Size Download all
Supplementary information
md5:89681e4766e9ff87ec4aaa46fbb2f413
236.8 kB Preview Download
Article
md5:2f727d24b4c84272b4e1aaaf42815f67
3.4 MB Preview Download

Additional details

Identifiers

DOI
10.1038/s44294-024-00016-0
Other
oai:uchicago.tind.io:11610

Funding

Dutch Cancer Society (KWF)
12950

UChicago Information

Division(s)
Biological Sciences Division
Department(s)
Pathology