Publications by authors named "Merhof D"

Due to the increasing workload of pathologists, the need for automation to support diagnostic tasks and quantitative biomarker evaluation is becoming more and more apparent. Foundation models have the potential to improve generalizability within and across centers and serve as starting points for data efficient development of specialized yet robust AI models. However, the training of foundation models themselves is usually very expensive in terms of data, computation, and time.

View Article and Find Full Text PDF

Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model has received tremendous attention from academic and industrial researchers who have extended it to address the scale and complexity created by medical tasks.

View Article and Find Full Text PDF

While neurosurgical interventions are frequently used in laboratory mice, refinement efforts to optimize analgesic management based on multimodal approaches appear to be rather limited. Therefore, we compared the efficacy and tolerability of combinations of the non-steroidal anti-inflammatory drug carprofen, a sustained-release formulation of the opioid buprenorphine, and the local anesthetic bupivacaine with carprofen monotherapy. Female and male C57BL/6J mice were subjected to isoflurane anesthesia and an intracranial electrode implant procedure.

View Article and Find Full Text PDF

Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more specialized datasets common in biomedical imaging. Here we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements.

View Article and Find Full Text PDF

Ultra high frequency (UHF) ultrasound enables the visualization of very small structures that cannot be detected by conventional ultrasound. The utilization of UHF imaging as a new imaging technique for the 3D-in-vivo chorioallantoic membrane (CAM) model can facilitate new insights into tissue perfusion and survival. Therefore, human renal cystic tissue was grafted onto the CAM and examined using UHF ultrasound imaging.

View Article and Find Full Text PDF

Modern microscopy techniques can be used to investigate soft nano-objects at the nanometer scale. However, time-consuming microscopy measurements combined with low numbers of observable polydisperse objects often limit the statistics. We propose a method for identifying the most representative objects from their respective point clouds.

View Article and Find Full Text PDF

The physiological performance of any sensory organ is determined by its anatomy and physical properties. Consequently, complex sensory structures with elaborate features have evolved to optimize stimulus detection. Understanding these structures and their physical nature forms the basis for mechanistic insights into sensory function.

View Article and Find Full Text PDF

Vision Transformer (ViT) models have demonstrated a breakthrough in a wide range of computer vision tasks. However, compared to the Convolutional Neural Network (CNN) models, it has been observed that the ViT models struggle to capture high-frequency components of images, which can limit their ability to detect local textures and edge information. As abnormalities in human tissue, such as tumors and lesions, may greatly vary in structure, texture, and shape, high-frequency information such as texture is crucial for effective semantic segmentation tasks.

View Article and Find Full Text PDF

Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to their heavy dependence on extensive labeled training data. To tackle this issue, we propose a novel self-supervised algorithm, , which integrates a robust framework based on the proposed Inception Large Kernel Attention (I-LKA) modules.

View Article and Find Full Text PDF

We propose a neural network-based framework to optimize the perceptions simulated by the in silico retinal implant model pulse2percept. The overall pipeline consists of a trainable encoder, a pre-trained retinal implant model and a pre-trained evaluator. The encoder is a U-Net, which takes the original image and outputs the stimulus.

View Article and Find Full Text PDF

Diffusion-MRI (dMRI) measures molecular diffusion, which allows to characterize microstructural properties of the human brain. Gliomas strongly alter these microstructural properties. Delineation of brain tumors currently mainly relies on conventional MRI-techniques, which are, however, known to underestimate tumor volumes in diffusely infiltrating glioma.

View Article and Find Full Text PDF

The remarkable performance of the Transformer architecture in natural language processing has recently also triggered broad interest in Computer Vision. Among other merits, Transformers are witnessed as capable of learning long-range dependencies and spatial correlations, which is a clear advantage over convolutional neural networks (CNNs), which have been the de facto standard in Computer Vision problems so far. Thus, Transformers have become an integral part of modern medical image analysis.

View Article and Find Full Text PDF

This study presents a novel concept for a smart home cage design, tools, and software used to monitor the physiological parameters of mice and rats in animal-based experiments. The proposed system focuses on monitoring key clinical parameters, including heart rate, respiratory rate, and body temperature, and can also assess activity and circadian rhythm. As the basis of the smart home cage system, an in-depth analysis of the requirements was performed, including camera positioning, imaging system types, resolution, frame rates, external illumination, video acquisition, data storage, and synchronization.

View Article and Find Full Text PDF

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients.

View Article and Find Full Text PDF

Denoising diffusion models, a class of generative models, have garnered immense interest lately in various deep-learning problems. A diffusion probabilistic model defines a forward diffusion stage where the input data is gradually perturbed over several steps by adding Gaussian noise and then learns to reverse the diffusion process to retrieve the desired noise-free data from noisy data samples. Diffusion models are widely appreciated for their strong mode coverage and quality of the generated samples in spite of their known computational burdens.

View Article and Find Full Text PDF
Article Synopsis
  • Early-life immune development is essential for long-term health, but the factors influencing postnatal immune maturation are not well understood.
  • The study focused on mononuclear phagocytes in Peyer's patches, showing significant age-related changes that led to reduced T cell priming in young organisms.
  • The research identified that the differentiation of follicle-associated epithelium M cells is crucial for driving the maturation of these immune cells after weaning.
View Article and Find Full Text PDF

Background: Deep learning tasks, which require large numbers of images, are widely applied in digital pathology. This poses challenges especially for supervised tasks since manual image annotation is an expensive and laborious process. This situation deteriorates even more in the case of a large variability of images.

View Article and Find Full Text PDF

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients.

View Article and Find Full Text PDF

Multiple Myeloma (MM) is an emerging ailment of global concern. Its diagnosis at the early stages is critical for recovery. Therefore, efforts are underway to produce digital pathology tools with human-level intelligence that are efficient, scalable, accessible, and cost-effective.

View Article and Find Full Text PDF

Whole slide images contain a magnitude of quantitative information that may not be fully explored in qualitative visual assessments. We propose: (1) a novel pipeline for extracting a comprehensive set of visual features, which are detectable by a pathologist, as well as sub-visual features, which are not discernible by human experts and (2) perform detailed analyses on renal images from mice with experimental unilateral ureteral obstruction. An important criterion for these features is that they are easy to interpret, as opposed to features obtained from neural networks.

View Article and Find Full Text PDF

Background: In digital pathology, many image analysis tasks are challenged by the need for large and time-consuming manual data annotations to cope with various sources of variability in the image domain. Unsupervised domain adaptation based on image-to-image translation is gaining importance in this field by addressing variabilities without the manual overhead. Here, we tackle the variation of different histological stains by unsupervised stain-to-stain translation to enable a stain-independent applicability of a deep learning segmentation model.

View Article and Find Full Text PDF

The beet cyst nematode is a plant pest responsible for crop loss on a global scale. Here, we introduce a high-throughput system based on computer vision that allows quantifying beet cyst nematode infestation and measuring phenotypic traits of cysts. After recording microscopic images of soil sample extracts in a standardized setting, an instance segmentation algorithm serves to detect nematode cysts in these images.

View Article and Find Full Text PDF
Article Synopsis
  • Image segmentation models using only image-level labels are gaining traction because they require less annotation effort compared to detailed methods like scribbles or bounding boxes.
  • The proposed deep network architecture incorporates Global Weighted Pooling and low-level image cues to enhance the segmentation of fine structures found in biological images.
  • Applied to datasets of nematodes and their cysts, this approach achieved Dice coefficients of 79.72% for nematodes and 58.51% for cysts, demonstrating effective segmentation.
View Article and Find Full Text PDF

Signal propagation along the structural connectome of the brain induces changes in the patterns of activity. These activity patterns define global brain states and contain information in accordance with their expected probability of occurrence. Being the physical substrate upon which information propagates, the structural connectome, in conjunction with the dynamics, determines the set of possible brain states and constrains the transition between accessible states.

View Article and Find Full Text PDF