Weakly Supervised Learning using Attention gates for colon cancer histopathological image segmentation.

Recently, Artificial Intelligence namely Deep Learning methods have revolutionized a wide range of domains and applications. Besides, Digital Pathology has so far played a major role in the diagnosis and the prognosis of tumors. However, the characteristics of the Whole Slide Images namely the gigapixel size, high resolution and the shortage of richly labeled samples have hindered the efficiency of classical Machine Learning methods. That goes without saying that traditional methods are poor in generalization to different tasks and data contents. Regarding the success of Deep learning when dealing with Large Scale applications, we have resorted to the use of such models for histopathological image segmentation tasks. First, we review and compare the classical UNet and Att-UNet models for colon cancer WSI segmentation in a sparsely annotated data scenario. Then, we introduce novel enhanced models of the Att-UNet where different schemes are proposed for the skip connections and spatial attention gates positions in the network. In fact, spatial attention gates assist the training process and enable the model to avoid irrelevant feature learning. Alternating the presence of such modules namely in our Alter-AttUNet model adds robustness and ensures better image segmentation results. In order to cope with the lack of richly annotated data in our AiCOLO colon cancer dataset, we suggest the use of a multi-step training strategy that also deals with the WSI sparse annotations and unbalanced class issues. All proposed methods outperform state-of-the-art approaches but Alter-AttUNet generates the best compromise between accurate results and light network. The model achieves 95.88% accuracy with our sparse AiCOLO colon cancer datasets. Finally, to evaluate and validate our proposed architectures we resort to publicly available WSI data: the NCT-CRC-HE-100K, the CRC-5000 and the Warwick colon cancer histopathological dataset. Respective accuracies of 99.65%, 99.73% and 79.03% were reached. A comparison with state-of-art approaches is established to view and compare the key solutions for histopathological image segmentation.

Deep learning for colon cancer histopathological images analysis.

Nowadays, digital pathology plays a major role in the diagnosis and prognosis of tumours. Unfortunately, existing methods remain limited when faced with the high resolution and size of Whole Slide Images (WSIs) coupled with the lack of richly annotated datasets. Regarding the ability of the Deep Learning (DL) methods to cope with the large scale applications, such models seem like an appealing solution for tissue classification and segmentation in histopathological images. This paper focuses on the use of DL architectures to classify and highlight colon cancer regions in a sparsely annotated histopathological data context. First, we review and compare state-of-the-art Convolutional Neural networks (CNN) including the AlexNet, vgg, ResNet, DenseNet and Inception models. To cope with the shortage of rich WSI datasets, we have resorted to the use of transfer learning techniques. This strategy comes with the hallmark of relying on a large size computer vision dataset (ImageNet) to train the network and generate a rich collection of learnt features. The testing and evaluation of such models on our AiCOLO colon cancer dataset ensure accurate patch-level classification results reaching up to 96.98% accuracy rate with ResNet. The CNN models have also been tested and evaluated with the CRC-5000, nct-crc-he-100k and merged datasets. ResNet respectively achieves 96.77%, 99.76% and 99.98% for the three publicly available datasets. Then, we present a pixel-wise segmentation strategy for colon cancer WSIs through the use of both UNet and SegNet models. We introduce a multi-step training strategy as a remedy for the sparse annotation of histopathological images. UNet and SegNet are used and tested in different training scenarios including data augmentation and transfer learning and ensure up to 76.18% and 81.22% accuracy rates. Besides, we test our training strategy and models on the CRC-5000, nct-crc-he-100k and Warwick datasets. Respective accuracy rates of 98.66%, 99.12% and 78.39% were achieved by SegNet. Finally, we analyze the existing models to discover the most suitable network and the most effective training strategy for our colon tumour segmentation case study.1.

[Do artificial intelligence systems reason in the same way as clinicians when making diagnoses?] / Une intelligence artificielle raisonne-t-elle de la même façon que les cliniciens pour poser des diagnostics ?

Clinical reasoning is at the heart of physicians' competence, as it allows them to make diagnoses. However, diagnostic errors are common, due to the existence of reasoning biases. Artificial intelligence is undergoing unprecedented development in this context. It is increasingly seen as a solution to improve the diagnostic performance of physicians, or even to perform this task for them, in a totally autonomous and more efficient way. In order to understand the challenges associated with the development of artificial intelligence, it is important to understand how the machine works to make diagnoses, what are the similarities and differences with the physician's diagnostic reasoning, and what are the consequences for medical training and practice.

In-silico insights on the prognostic potential of immune cell infiltration patterns in the breast lobular epithelium.

Scattered inflammatory cells are commonly observed in mammary gland tissue, most likely in response to normal cell turnover by proliferation and apoptosis, or as part of immunosurveillance. In contrast, lymphocytic lobulitis (LLO) is a recurrent inflammation pattern, characterized by lymphoid cells infiltrating lobular structures, that has been associated with increased familial breast cancer risk and immune responses to clinically manifest cancer. The mechanisms and pathogenic implications related to the inflammatory microenvironment in breast tissue are still poorly understood. Currently, the definition of inflammation is mainly descriptive, not allowing a clear distinction of LLO from physiological immunological responses and its role in oncogenesis remains unclear. To gain insights into the prognostic potential of inflammation, we developed an agent-based model of immune and epithelial cell interactions in breast lobular epithelium. Physiological parameters were calibrated from breast tissue samples of women who underwent reduction mammoplasty due to orthopedic or cosmetic reasons. The model allowed to investigate the impact of menstrual cycle length and hormone status on inflammatory responses to cell turnover in the breast tissue. Our findings suggested that the immunological context, defined by the immune cell density, functional orientation and spatial distribution, contains prognostic information previously not captured by conventional diagnostic approaches.