Contrastive image adaptation for acquisition shift reduction in medical imaging.

The domain shift, or acquisition shift in medical imaging, is responsible for potentially harmful differences between development and deployment conditions of medical image analysis techniques. There is a growing need in the community for advanced methods that could mitigate this issue better than conventional approaches. In this paper, we consider configurations in which we can expose a learning-based pixel level adaptor to a large variability of unlabeled images during its training, i.e. sufficient to span the acquisition shift expected during the training or testing of a downstream task model. We leverage the ability of convolutional architectures to efficiently learn domain-agnostic features and train a many-to-one unsupervised mapping between a source collection of heterogeneous images from multiple unknown domains subjected to the acquisition shift and a homogeneous subset of this source set of lower cardinality, potentially constituted of a single image. To this end, we propose a new cycle-free image-to-image architecture based on a combination of three loss functions : a contrastive PatchNCE loss, an adversarial loss and an edge preserving loss allowing for rich domain adaptation to the target image even under strong domain imbalance and low data regimes. Experiments support the interest of the proposed contrastive image adaptation approach for the regularization of downstream deep supervised segmentation and cross-modality synthesis models.

A CT-Based Clinical, Radiological and Radiomic Machine Learning Model for Predicting Malignancy of Solid Renal Tumors (UroCCR-75).

BACKGROUND: Differentiating benign from malignant renal tumors is important for patient management, and it may be improved by quantitative CT features analysis including radiomic. PURPOSE: This study aimed to compare performances of machine learning models using bio-clinical, conventional radiologic and 3D-radiomic features for the differentiation of benign and malignant solid renal tumors using pre-operative multiphasic contrast-enhanced CT examinations. MATERIALS AND METHODS: A unicentric retrospective analysis of prospectively acquired data from a national kidney cancer database was conducted between January 2016 and December 2020. Histologic findings were obtained by robotic-assisted partial nephrectomy. Lesion images were semi-automatically segmented, allowing for a 3D-radiomic features extraction in the nephrographic phase. Conventional radiologic parameters such as shape, content and enhancement were combined in the analysis. Biological and clinical features were obtained from the national database. Eight machine learning (ML) models were trained and validated using a ten-fold cross-validation. Predictive performances were evaluated comparing sensitivity, specificity, accuracy and AUC. RESULTS: A total of 122 patients with 132 renal lesions, including 111 renal cell carcinomas (RCCs) (111/132, 84%) and 21 benign tumors (21/132, 16%), were evaluated (58 +/- 14 years, men 74%). Unilaterality (100/111, 90% vs. 13/21, 62%; p = 0.02), necrosis (81/111, 73% vs. 8/21, 38%; p = 0.02), lower values of tumor/cortex ratio at portal time (0.61 vs. 0.74, p = 0.01) and higher variation of tumor/cortex ratio between arterial and portal times (0.22 vs. 0.05, p = 0.008) were associated with malignancy. A total of 35 radiomics features were selected, and "intensity mean value" was associated with RCCs in multivariate analysis (OR = 0.99). After ten-fold cross-validation, a C5.0Tree model was retained for its predictive performances, yielding a sensitivity of 95%, specificity of 42%, accuracy of 87% and AUC of 0.74. CONCLUSION: Our machine learning-based model combining clinical, radiologic and radiomics features from multiphasic contrast-enhanced CT scans may help differentiate benign from malignant solid renal tumors.

Numerical workflow of irreversible electroporation for deep-seated tumor.

The paper provides a numerical workflow, based on the 'real-life' clinical workflow of irreversible electroporation (IRE) performed for the treatment of deep-seated liver tumors. Thanks to a combination of numerical modeling, image registration algorithm and clinical data, our numerical workflow enables to provide the distribution of the electric field as effectively delivered by the clinical IRE procedure. As a proof of concept, we show on a specific clinical case of IRE ablation of liver tumor that clinical data could be advantageously combined to numerical simulations in a near future, in order to give to the interventional radiologists information on the effective IRE ablation. We also corroborate the simulated treated region with the post-treatment MRI performed 3 d after the treatment.

Tumor growth model of ductal carcinoma: from in situ phase to stroma invasion.

This paper aims at modeling breast cancer transition from the in situ stage -when the tumor is confined to the duct- to the invasive phase. Such a transition occurs thanks to the degradation of the duct membrane under the action of specific enzymes so-called matrix metalloproteinases (MMPs). The model consists of advection-reaction equations that hold in the duct and in the surrounding tissue, in order to describe the proliferation and the necrosis of the cancer cells in each subdomain. The divergence of the velocity is given by the increase of the cell densities. Darcy law is imposed in order to close the system. The key-point of the modeling lies in the description of the transmission conditions across the duct. Nonlinear Kedem-Katchalsky transmission conditions across the membrane describe the discontinuity of the pressure as a linear function of the flux. These transmission conditions make it possible to describe the transition from the in situ stage to the invasive phase at the macroscopic level. More precisely, the membrane permeability increases with respect to the local concentration of MMPs. The cancer cells are no more confined to the duct and the tumor invades the surrounding tissue. The model is enriched by the description of nutrients concentration, tumor necrosis factors, and MMPs production. The mathematical model is implemented in a 3D C++-code, which is based on well-adapted finite difference schemes on Cartesian grid. The membrane interface is described by a level-set, and the transmission conditions are precisely approached at the second order thanks to well-suited sharp stencils. Our continuous approach provides new significant insights in the macroscopic modeling of the breast cancer phase transition, due to the membrane degradation by MMP enzymes.

Free boundary problem for cell protrusion formations: theoretical and numerical aspects.

In this paper, a free boundary problem for cell protrusion formation is studied theoretically and numerically. The cell membrane is precisely described thanks to a level set function, whose motion is due to specific signalling pathways. The aim is to model the chemical interactions between the cell and its environment, in the process of invadopodia or pseudopodia formation. The model consists of Laplace equation with Dirichlet condition inside the cell coupled to Laplace equation with Neumann condition in the outer domain. The actin polymerization is accounted for as the gradient of the inner signal, which drives the motion of the interface. We prove the well-posedness of our free boundary problem under a sign condition on the datum. This criterion ensures the consistency of the model, and provides conditions to focus on for any enrichment of the model. We then propose a new first order Cartesian finite-difference method to solve the problem. We eventually exhibit the main biological features that can be accounted for by the model: the formation of thin and elongated protrusions as for invadopodia, or larger protrusion as for pseudopodia, depending on the source term in the equation. The model provides the theoretical and numerical grounds for single cell migration modeling, whose formulation is valid in 2D and 3D. In particular, specific chemical reactions that occurred at the cell membrane could be precisely described in forthcoming works.