Scientific article
Open access

Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations

Published innpj digital medicine, vol. 5, no. 1, 102
Publication date2022-07-22
First online date2022-07-22

The digitalization of clinical workflows and the increasing performance of deep learning algorithms are paving the way towards new methods for tackling cancer diagnosis. However, the availability of medical specialists to annotate digitized images and free-text diagnostic reports does not scale with the need for large datasets required to train robust computer-aided diagnosis methods that can target the high variability of clinical cases and data produced. This work proposes and evaluates an approach to eliminate the need for manual annotations to train computer-aided diagnosis tools in digital pathology. The approach includes two components, to automatically extract semantically meaningful concepts from diagnostic reports and use them as weak labels to train convolutional neural networks (CNNs) for histopathology diagnosis. The approach is trained (through 10-fold cross-validation) on 3’769 clinical images and reports, provided by two hospitals and tested on over 11’000 images from private and publicly available datasets. The CNN, trained with automatically generated labels, is compared with the same architecture trained with manual labels. Results show that combining text analysis and end-to-end deep neural networks allows building computer-aided diagnosis tools that reach solid performance (micro-accuracy = 0.908 at image-level) based only on existing clinical data without the need for manual annotations.

  • European Commission - EXtreme-scale Analytics via Multimodal Ontology Discovery & Enhancement [825292]
Citation (ISO format)
MARINI, Niccolo et al. Unleashing the potential of digital pathology data by training computer-aided diagnosis models without human annotations. In: npj digital medicine, 2022, vol. 5, n° 1, p. 102. doi: 10.1038/s41746-022-00635-4
Main files (1)
Article (Published version)
Secondary files (1)
ISSN of the journal2398-6352

Technical informations

Creation09/20/2022 9:47:00 AM
First validation09/20/2022 9:47:00 AM
Update time03/16/2023 10:15:41 AM
Status update03/16/2023 10:15:38 AM
Last indexation08/31/2023 10:18:09 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack