Next Article in Journal
The Ability of Metabolomics to Discriminate Non-Small-Cell Lung Cancer Subtypes Depends on the Stage of the Disease and the Type of Material Studied
Next Article in Special Issue
Microwave Ablation for Colorectal Liver Metastases: A Systematic Review and Pooled Oncological Analyses
Previous Article in Journal
Clinically Advanced Pheochromocytomas and Paragangliomas: A Comprehensive Genomic Profiling Study
Previous Article in Special Issue
Thermal Ablation Compared to Partial Hepatectomy for Recurrent Colorectal Liver Metastases: An Amsterdam Colorectal Liver Met Registry (AmCORE) Based Study
Article

Development of a Deep-Learning Pipeline to Recognize and Characterize Macrophages in Colo-Rectal Liver Metastasis

1
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089 Rozzano, Italy
2
Department of Pathology, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089 Rozzano, Italy
3
Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy
4
Department of Immunology and Inflammation, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089 Rozzano, Italy
5
Department of Biomedical Science, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090 Milan, Italy
6
Department of Hepatobiliary and General Surgery Humanitas, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089 Rozzano, Italy
7
Hepatobiliary Immunopathology Unit, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089 Rozzano, Italy
8
Department of Biotechnology and Translational Medicine, University of Milan, 20133 Milan, Italy
9
The William Harvey Research Institute, Queen Mary University of London, London EC1M 6BQ, UK
*
Authors to whom correspondence should be addressed.
Academic Editors: Yasunori Minami and David A. Geller
Cancers 2021, 13(13), 3313; https://doi.org/10.3390/cancers13133313
Received: 22 March 2021 / Revised: 20 May 2021 / Accepted: 24 June 2021 / Published: 1 July 2021
(This article belongs to the Special Issue Colorectal Liver Metastasis)
We recently proved that in human colorectal cancer, the presence of small or large tumor-associated macrophages (TAMs) is associated with different outcomes. To translate this biological data into a robust clinical marker means to identify in a single slide all TAMs, hundreds of cells, and then evaluate the area of each of them, a task unfeasible in the routine pathology workout. With the aim to develop a deep-learning pipeline to tackle this challenge, we selected, trained and tested three different approaches. The deep-learning pipeline based on the DeepLab-v3 architecture and semantic segmentation technique warrants the separation of TAMs from the background and the identification of single TAMs: this will easily allow the evaluation of their area.
Quantitative analysis of Tumor Microenvironment (TME) provides prognostic and predictive information in several human cancers but, with few exceptions, it is not performed in daily clinical practice since it is extremely time-consuming. We recently showed that the morphology of Tumor Associated Macrophages (TAMs) correlates with outcome in patients with Colo-Rectal Liver Metastases (CLM). However, as for other TME components, recognizing and characterizing hundreds of TAMs in a single histopathological slide is unfeasible. To fasten this process, we explored a deep-learning based solution. We tested three Convolutional Neural Networks (CNNs), namely UNet, SegNet and DeepLab-v3, with three different segmentation strategies, semantic segmentation, pixel penalties and instance segmentation. The different experiments are compared according to the Intersection over Union (IoU), a metric describing the similarity between what CNN predicts as TAM and the ground truth, and the Symmetric Best Dice (SBD), which indicates the ability of CNN to separate different TAMs. UNet and SegNet showed intrinsic limitations in discriminating single TAMs (highest SBD 61.34±2.21), whereas DeepLab-v3 accurately recognized TAMs from the background (IoU 89.13±3.85) and separated different TAMs (SBD 79.00±3.72). This deep-learning pipeline to recognize TAMs in digital slides will allow the characterization of TAM-related metrics in the daily clinical practice, allowing the implementation of prognostic tools. View Full-Text
Keywords: macrophages; colo-rectal liver metastases; deep learning; artificial intelligence; digital pathology macrophages; colo-rectal liver metastases; deep learning; artificial intelligence; digital pathology
Show Figures

Graphical abstract

MDPI and ACS Style

Cancian, P.; Cortese, N.; Donadon, M.; Di Maio, M.; Soldani, C.; Marchesi, F.; Savevski, V.; Santambrogio, M.D.; Cerina, L.; Laino, M.E.; Torzilli, G.; Mantovani, A.; Terracciano, L.; Roncalli, M.; Di Tommaso, L. Development of a Deep-Learning Pipeline to Recognize and Characterize Macrophages in Colo-Rectal Liver Metastasis. Cancers 2021, 13, 3313. https://doi.org/10.3390/cancers13133313

AMA Style

Cancian P, Cortese N, Donadon M, Di Maio M, Soldani C, Marchesi F, Savevski V, Santambrogio MD, Cerina L, Laino ME, Torzilli G, Mantovani A, Terracciano L, Roncalli M, Di Tommaso L. Development of a Deep-Learning Pipeline to Recognize and Characterize Macrophages in Colo-Rectal Liver Metastasis. Cancers. 2021; 13(13):3313. https://doi.org/10.3390/cancers13133313

Chicago/Turabian Style

Cancian, Pierandrea, Nina Cortese, Matteo Donadon, Marco Di Maio, Cristiana Soldani, Federica Marchesi, Victor Savevski, Marco D. Santambrogio, Luca Cerina, Maria E. Laino, Guido Torzilli, Alberto Mantovani, Luigi Terracciano, Massimo Roncalli, and Luca Di Tommaso. 2021. "Development of a Deep-Learning Pipeline to Recognize and Characterize Macrophages in Colo-Rectal Liver Metastasis" Cancers 13, no. 13: 3313. https://doi.org/10.3390/cancers13133313

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop