Imbalanced class distributions among different organs pose significant challenges in real-world semi-supervised multi-organ segmentation. Integrating anatomical priors offers a promising research direction to mitigate these imbalances. In this paper, we explore the capabilities of Multimodal Large Language Models (MLLM) to extract robust, generic textual anatomical insights serving as prior knowledge for segmentation model. Specifically, we employ GPT-4o to generate detailed textual descriptions of anatomical priors—including both inter-organ relative positional relationships and organ shape characteristics. These priors generated only once for the whole training and testing are then seamlessly integrated into the segmentation model as parameters within the segmentation head. Furthermore, we align the textual priors with visual features using contrastive learning. The inter-organ positional priors guide the model in localizing smaller organs relative to larger ones, while the organ shape priors help ensure that the learned morphological structures are more anatomically plausible. Extensive experiments demonstrate that our method significantly outperforms some state-of-the-art approaches. The source code is available at: https://github.com/Lunn88/TAK-Semi.

Doppler holography is an emerging retinal imaging technique that captures the dynamic behavior of blood flow with high temporal resolution, enabling quantitative assessment of retinal hemodynamics. This requires accurate segmentation of retinal arteries and veins, but traditional segmentation methods focus solely on spatial information and overlook the temporal richness of holographic data. In this work, we propose a simple yet effective approach for artery-vein segmentation in temporal Doppler holograms using standard segmentation architectures. By incorporating features derived from a dedicated pulse analysis pipeline, our method allows conventional U-Nets to exploit temporal dynamics and achieve performance comparable to more complex attention- or iteration-based models. These findings demonstrate that time-resolved preprocessing can unlock the full potential of deep learning for Doppler holography, opening new perspectives for quantitative exploration of retinal hemodynamics. The dataset is publicly available at https://huggingface.co/datasets/DigitalHolography/

Robust remote verification of identity documents relies on analyzing faint, transparent security features like Optically Variable Devices (OVDs), or "holograms", within user-captured videos under uncontrolled conditions. Current systems, however, face critical limitations: existing methods often treat video frames in isolation, neglecting the intrinsic dynamic nature of OVDs and leaving systems vulnerable to swapping attacks, or focus on general holographic presence and lack the ability to verify specific OVD types. Moreover, the economic infeasibility of frame-by-frame video annotation makes supervised training impractical. In this work, we introduce two novel approaches for verifying the dynamic behavior of transparent OVDs protecting the holder's portrait, specifically designed for open-set scenarios where attack types are unknown during training. We demonstrate that these approaches can be trained without any attack samples in a self-supervised setting, surpassing previous state-of-the-art methods on public datasets while adhering strictly to industrial constraints. Our results confirm that modeling temporal dynamics is essential for defeating sophisticated attacks under realistic conditions, and underscores the promise of sequence modeling and anomaly detection for OVD verification. Code is available at https://github.com/EPITAResearchLab/pouliquen.26.icdar.

In histopathology, intelligent diagnosis of Whole Slide Images (WSIs) is essential for automating and objectifying diagnoses, reducing the workload of pathologists. However, diagnostic models often face the challenge of forgetting previously learned data during incremental training on datasets from different sources. To address this issue, we propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification. Our framework introduces two key components into the common MIL model architecture. First, it leverages microscopic pathological prior to select more accurate and diverse representative patches for MIL. Secondly, it trains separate classification heads for each task and uses macroscopic pathological prior knowledge, treating the thumbnail as a prompt guide (PG) to select the appropriate classification head. We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets. PaGMIL achieves a better balance between the performance of the current task and the retention of previous tasks, outperforming other continual learning methods. Our code will be open-sourced upon acceptance.

This paper addresses the remote verification of the authenticity of Optically Variable Devices (commonly known as holograms) on identity documents. Typically placed over the cardholder's photo, these devices provide strong and easily verifiable security for human inspection but pose challenges for automated verification. Existing approaches easily cover static frauds (e.g., paper photocopy) and can be evaluated for such, but their capacity to detect real, dynamic fraud cases (e.g., hand-crafted hologram) has not been evaluated to date because of the lack of public datasets. Furthermore, they are usually trained to detect known attack types, and few of them can generalize to new, unseen attacks. This work features three contributions to address these limitations: 1) a new public dataset, MIDV-DynAttack, which extends the existing MIDV-Holo dataset with realistic, static, and dynamic attacks against identity document specimens, tripling the number of attack samples compared to the original dataset, 2) a novel verification method which can assess the authenticity of a specific hologram thanks to the analysis of its dynamic behavior and appearance, can be trained without dynamic attack samples, and exhibits new state-of-the-art performance, 3) a benchmark of existing approaches which follows a clear evaluation protocol and emphasizes the inability of other approaches to deal with dynamic attacks, as well as new challenging attacks to deal with. Code and dataset are publicly available at https://github.com/EPITAResearchLab/pouliquen.25.icdar.

We propose a method to remotely verify the authenticity of Optically Variable Devices (OVDs), often referred to as “holograms”, in identity documents. Our method processes video clips captured with smartphones under common lighting conditions, and is evaluated on two public datasets: MIDV-HOLO and MIDV-2020. Thanks to a weakly-supervised training, we optimize a feature extraction and decision pipeline which achieves a new leading performance on MIDV-HOLO, while maintaining a high recall on documents from MIDV-2020 used as attack samples. It is also the first method, to date, to effectively address the photo replacement attack task, and can be trained on either genuine samples, attack samples, or both for increased performance. By enabling to verify OVD shapes and dynamics with very little supervision, this work opens the way towards the use of massive amounts of unlabeled data to build robust remote identity document verification systems on commodity smartphones. Code is available at https://github.com/EPITAResearchLab/pouliquen.24.icdar

Interactive image segmentation is an important application in computer vision for selecting objects of interest in images. Several interactive segmentation methods are based on distance transform algorithms. However, the most known distance transform, geodesic distance, is sensitive to noise in the image and to seed placement. Recently, the Dahu pseudo-distance, a continuous version of the minimum barrier distance (MBD), is proved to be more powerful than the geodesic distance in noisy and blurred images. This paper presents a method for combining the Dahu pseudo-distance with edge information in a graph-cut optimization framework and leveraging each's complementary strengths. Our method works efficiently on both 2D/3D images and videos. Results show that our method achieves better performance than other distance-based and graph-cut methods, thereby reducing the user's effort s. (c) 2022 Elsevier Ltd. All rights reserved.

In this paper, we prove that the self-dual morphological hierarchical structure computed on a n-D gray-level wellcomposed image u by the algorithm of G{\'e}raud et al. [1] is exactly the mathematical structure defined to be the tree of shape of u in Najman et al [2]. We recall that this algorithm is in quasi-linear time and thus considered to be optimal. The tree of shapes leads to many applications in mathematical morphology and in image processing like grain filtering, shapings, image segmentation, and so on.

In Mathematical Morphology (MM), connected filters based on dynamics are used to filter the extrema of an image. Similarly, persistence is a concept coming from Persistent Homology (PH) and Morse Theory (MT) that represents the stability of the extrema of a Morse function. Since these two concepts seem to be closely related, in this paper we examine their relationship, and we prove that they are equal on n-D Morse functions, n $\ge$ 1. More exactly, pairing a minimum with a 1-saddle by dynamics or pairing the same 1-saddle with a minimum by persistence leads exactly to the same pairing, assuming that the critical values of the studied Morse function are unique. This result is a step further to show how much topological data analysis and mathematical morphology are related, paving the way for a more in-depth study of the relations between these two research fields.

In this paper, we prove that when a n -D cubical set is continuously well-composed (CWC), that is, when the boundary of its continuous analog is a topological (n-1) -manifold, then it is digitally well-composed (DWC), which means that it does not contain any critical configuration. We prove this result thanks to local homology. This paper is the sequel of a previous paper where we proved that DWCness does not imply CWCness in 4D.

C++ is a multi-paradigm language that enables the programmer to set up efficient image processing algorithms easily. This language strength comes from many aspects. C++ is high-level, so this enables developing powerful abstractions and mixing different programming styles to ease the development. At the same time, C++ is low-level and can fully take advantage of the hardware to deliver the best performance. It is also very portable and highly compatible which allows algorithms to be called from high-level, fast-prototyping languages such as Python or Matlab. One fundamental aspects where C++ shines is generic programming. Generic programming makes it possible to develop and reuse bricks of software on objects (images) of different natures (types) without performance loss. Nevertheless, conciliating genericity, efficiency, and simplicity at the same time is not trivial. Modern C++ (post-2011) has brought new features that made it simpler and more powerful. In this paper, we focus on some C++20 aspects of generic programming: ranges, views, and concepts, and see how they extend to images to ease the development of generic image algorithms while lowering the computation time.

Segmentation of curvilinear structures is important in many applications, such as retinal blood vessel segmentation for early detection of vessel diseases and pavement crack segmentation for road condition evaluation and maintenance. Currently, deep learning-based methods have achieved impressive performance on these tasks. Yet, most of them mainly focus on finding powerful deep architectures but ignore capturing the inherent curvilinear structure feature (e.g., the curvilinear structure is darker than the context) for a more robust representation. In consequence, the performance usually drops a lot on cross-datasets, which poses great challenges in practice. In this paper, we aim to improve the generalizability by introducing a novel local intensity order transformation (LIOT). Specifically, we transfer a gray-scale image into a contrast-invariant four-channel image based on the intensity order between each pixel and its nearby pixels along with the four (horizontal and vertical) directions. This results in a representation that preserves the inherent characteristic of the curvilinear structure while being robust to contrast changes. Cross-dataset evaluation on three retinal blood vessel segmentation datasets demonstrates that LIOT improves the generalizability of some state-of-the-art methods. Additionally, the cross-dataset evaluation between retinal blood vessel segmentation and pavement crack segmentation shows that LIOT is able to preserve the inherent characteristic of curvilinear structure with large appearance gaps. An implementation of the proposed method is available at https://github.com/TY-Shi/LIOT.

In Mathematical Morphology, the max-tree is a region-based representation that encodes the inclusion relationship of the threshold sets of an image. This tree has proved useful in numerous image processing applications. For the last decade, work has led to improving the construction time of this structure; mixing algorithmic optimizations, parallel and distributed computing. Nevertheless, there is still no algorithm that benefits from the computing power of the massively parallel architectures. In this work, we propose the first GPU algorithm to compute the max-tree. The proposed approach leads to significant speed-ups, and is up to one order of magnitude faster than the current State-of-the-Art parallel CPU algorithms. This work paves the way for a max-tree integration in image processing GPU pipelines and real-time image processing based on Mathematical Morphology. It is also a foundation for porting other image representations from Mathematical Morphology on GPUs.

Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying. Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial-like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries. Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset.

In Mathematical Morphology (MM), dynamics are used to compute markers to proceed for example to watershed-based image decomposition. At the same time, persistence is a concept coming from Persistent Homology (PH) and Morse Theory (MT) and represents the stability of the extrema of a Morse function. Since these concepts are similar on Morse functions, we studied their relationship and we found, and proved, that they are equal on 1D Morse functions. Here, we propose to extend this proof to n-D, n ≥ 2 , showing that this equality can be applied to n-D images and not only to 1D functions. This is a step further to show how much MM and MT are related.

This paper presents the final results of the ICDAR 2021 Competition on Historical Map Segmentation (MapSeg), encouraging research on a series of historical atlases of Paris, France, drawn at 1/5000 scale between 1894 and 1937. The competition featured three tasks, awarded separately. Task 1 consists in detecting building blocks and was won by the L3IRIS team using a DenseNet-121 network trained in a weakly supervised fashion. This task is evaluated on 3 large images containing hundreds of shapes to detect. Task 2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy. Task 3 consists in locating intersection points of geo-referencing lines, and was also won by the UWB team who used a dedicated pipeline combining binarization, line detection with Hough transform, candidate filtering, and template matching for intersection refinement. Tasks 2 and 3 are evaluated on 95 map sheets with complex content. Dataset, evaluation tools and results are available under permissive licensing at https://icdar21-mapseg.github.io/.

In myocardium segmentation of cardiac magnetic resonance images, ambiguities often appear near the boundaries of the target domains due to tissue similarities. To address this issue, we propose a new architecture, called FOANet, which can be decomposed in three main steps: a localization step, a Gaussian-based contrast enhancement step, and a segmentation step. This architecture is supplied with a hybrid loss function that guides the FOANet to study the transformation relationship between the input image and the corresponding label in a three-level hierarchy (pixel-, patch- and map-level), which is helpful to improve segmentation and recovery of the boundaries. We demonstrate the efficiency of our approach on two public datasets in terms of regional and boundary segmentations.

Many approaches exist to compute the distance between two trees in pattern recognition. These trees can be structures with or without values on their nodes or edges. However, none of these distances take into account the shapes possibly associated to the nodes of the tree. For this reason, we propose in this paper a new distance between two trees of shapes based on the Hausdorff distance. This distance allows us to make inexact tree matching and to compute what we call residual forests, representing where two trees differ. We will also see that thanks to these residual forests, we can obtain good preliminary results in matter of brain tumor segmentation. This segmentation not only provides a segmentation but also the tree of shapes corresponding to the segmentation and its depth map.

Automatic segmentation of the left ventricle (LV) of a living human heart in a magnetic resonance (MR) image (2D+t) allows to measure some clinical significant indices like the regional wall thicknesses (RWT), cavity dimensions, cavity and myocardium areas, and cardiac phase. Here, we propose a novel framework made of a sequence of two fully convolutional networks (FCN). The first is a modified temporal-like VGG16 (the "localization network") and is used to localize roughly the LV (filled-in) epicardium position in each MR volume. The second FCN is a modified temporal-like VGG16 too, but devoted to segment the LV myocardium and cavity (the "segmentation network"). We evaluate the proposed method with 5-fold-cross-validation on the MICCAI 2019 LV Full Quantification Challenge dataset. For the network used to localize the epicardium, we obtain an average dice index of 0.8953 on validation set. For the segmentation network, we obtain an average dice index of 0.8664 on validation set (there, data augmentation is used). The mean absolute error (MAE) of average cavity and myocardium areas, dimensions, RWT are 114.77mm(2); 0.9220 mm; 0.9185mm respectively. The computation time of the pipeline is less than 2 s for an entire 3D volume. The error rate of phase classification is 7.6364%, which indicates that the proposed approach has a promising performance to estimate all these parameters.