Multicenter automatic detection of invasive carcinoma on breast whole slide images.

Autor:	Peyret R; Primaa, Paris, France., Pozin N; Primaa, Paris, France., Sockeel S; Primaa, Paris, France., Kammerer-Jacquet SF; Rennes University hospital, France., Adam J; Paris Saint-Joseph hospital, Paris, France., Bocciarelli C; Brest university hospital, France., Ditchi Y; Saint-Antoine hospital, APHP, Paris, France., Bontoux C; Henri-Mondor hospital, APHP, Paris, France., Depoilly T; René Dubos hospital, Pontoise, France., Guichard L; Bicêtre hospital, APHP, Paris Saclay University, France., Lanteri E; Nice University hospital, France., Sockeel M; Primaa, Paris, France.; Primaa, Paris, France., Prévot S; Bicêtre hospital, APHP, Paris Saclay University, France.
Jazyk:	angličtina
Zdroj:	PLOS digital health [PLOS Digit Health] 2023 Feb 28; Vol. 2 (2), pp. e0000091. Date of Electronic Publication: 2023 Feb 28 (Print Publication: 2023).
DOI:	10.1371/journal.pdig.0000091
Abstrakt:	Breast cancer is one of the most prevalent cancers worldwide and pathologists are closely involved in establishing a diagnosis. Tools to assist in making a diagnosis are required to manage the increasing workload. In this context, artificial intelligence (AI) and deep-learning based tools may be used in daily pathology practice. However, it is challenging to develop fast and reliable algorithms that can be trusted by practitioners, whatever the medical center. We describe a patch-based algorithm that incorporates a convolutional neural network to detect and locate invasive carcinoma on breast whole-slide images. The network was trained on a dataset extracted from a reference acquisition center. We then performed a calibration step based on transfer learning to maintain the performance when translating on a new target acquisition center by using a limited amount of additional training data. Performance was evaluated using classical binary measures (accuracy, recall, precision) for both centers (referred to as "test reference dataset" and "test target dataset") and at two levels: patch and slide level. At patch level, accuracy, recall, and precision of the model on the reference and target test sets were 92.1% and 96.3%, 95% and 87.8%, and 73.9% and 70.6%, respectively. At slide level, accuracy, recall, and precision were 97.6% and 92.0%, 90.9% and 100%, and 100% and 70.8% for test sets 1 and 2, respectively. The high performance of the algorithm at both centers shows that the calibration process is efficient. This is performed using limited training data from the new target acquisition center and requires that the model is trained beforehand on a large database from a reference center. This methodology allows the implementation of AI diagnostic tools to help in routine pathology practice. Competing Interests: I have read the journal’s policy and the authors of this manuscript have the following competing interests: S.S.1 and M.S.1-10 are co-founders and salaried employees of Primaa, R.P.1 and N.P.1 are salaried employees of Primaa. (Copyright: © 2023 Peyret et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu