Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning

Aurélie Beaufrère (1, 2) , Nora Ouzir (3, 4, 5, 6) , Paul Emile Zafar (1, 3) , Astrid Laurent-Bellue (7, 8) , Miguel Albuquerque (2) , Gwladys Lubuela (9) , Jules Grégory (1, 10, 11) , Catherine Guettier (12, 8) , Kévin Mondet (1) , Jean-Christophe Pesquet (4, 3, 5, 6) , Valérie Paradis (2, 1)

1 Hôpital Beaujon [AP-HP]
2 CRI (UMR_S_1149 / ERL_8252 / U1149) - Centre de recherche sur l'Inflammation
3 CVN - Centre de vision numérique
4 OPIS - OPtimisation Imagerie et Santé
5 CentraleSupélec
6 Université Paris-Saclay
7 Service d'anatomie pathologique
8 Hôpital Bicêtre [AP-HP, Le Kremlin-Bicêtre]
9 UPCité - Université Paris Cité
10 McGill University = Université McGill [Montréal, Canada]
11 METHODS [CRESS - U1153 / UMR_A 1125] - Methods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques
12 Physiopathologie et traitement des maladies du foie

Background & Aims: The diagnosis of primary liver cancers (PLCs) can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified PLCs on routine-stained biopsies using a weakly supervised learning method. Method: We selected 166 PLC biopsies divided into training, internal and external validation sets: 90, 29 and 47 samples, respectively. Two liver pathologists reviewed each whole-slide hematein eosin saffron (HES)-stained image (WSI). After annotating the tumour/non-tumour areas, tiles of 256x256 pixels were extracted from the WSIs and used to train a ResNet18 neural network. The tumour/non-tumour annotations served as labels during training, and the network's last convolutional layer was used to extract new tumour tile features. Without knowledge of the precise labels of the malignancies, we then applied an unsupervised clustering algorithm. Results: Pathological review classified the training and validation sets into hepatocellular carcinoma (HCC, 33/90, 11/29 and 26/47), intrahepatic cholangiocarcinoma (iCCA, 28/90, 9/29 and 15/47), and cHCC-CCA (29/90, 9/29 and 6/47). In the two-cluster model, Clusters 0 and 1 contained mainly HCC and iCCA histological features. The diagnostic agreement between the pathological diagnosis and the two-cluster model predictions (major contingent) in the internal and external validation sets was 100% (11/11) and 96% (25/26) for HCC and 78% (7/9) and 87% (13/15) for iCCA, respectively. For cHCC-CCA, we observed a highly variable proportion of tiles from each cluster (cluster 0: 5-97%; cluster 1: 2-94%). Conclusion: Our method applied to PLC HES biopsy could identify specific morphological features of HCC and iCCA. Although no specific features of cHCC-CCA were recognized, assessing the proportion of HCC and iCCA tiles within a slide could facilitate the identification of cHCC-CCA. Impact and implications: The diagnosis of primary liver cancers can be challenging, especially on biopsies and for combined hepatocellular-cholangiocarcinoma (cHCC-CCA). We automatically classified primary liver cancers on routine-stained biopsies using a weakly supervised learning method. Our model identified specific features of hepatocellular carcinoma and intrahepatic cholangiocarcinoma. Despite no specific features of cHCC-CCA being recognized, the identification of hepatocellular carcinoma and intrahepatic cholangiocarcinoma tiles within a slide could facilitate the diagnosis of primary liver cancers, and particularly cHCC-CCA.

Mots clés: Primary liver cancer; biopsy; histological slides; artificial intelligence; weakly supervised learning

Domaines: Hépatologie et Gastroentérologie; Intelligence artificielle [cs.AI]; Imagerie médicale; Apprentissage [cs.LG]; Cancer; Anatomie, Histologie, Anatomopathologie [q-bio.TO]

Aurélie Beaufrère, Nora Ouzir, Paul Emile Zafar, Astrid Laurent-Bellue, Miguel Albuquerque, et al.. Primary liver cancer classification from routine tumour biopsy using weakly supervised deep learning. JHEP Reports Innovation in Hepatology, 2024, 6 (3), pp.101008. ⟨10.1016/j.jhepr.2024.101008⟩. ⟨hal-04534805⟩