How Few Annotations are Needed for Segmentation Using a Multi-planar U-Net?

Laprade, William Michael; Perslev, Mathias; Sporring, Jon

doi:10.1007/978-3-030-88210-5_20

Cited by 8 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To minimize animal usage during the initial validation phase, we performed segmentation on a limited dataset. Nevertheless, U-Net has consistently displayed its robustness in previous studies [33][34][35][36] , even when trained on small datasets, which was the case in our study. The segmentation results consistently aligned with expert opinions, even when the images were artificially manipulated to simulate various laboratory and lighting conditions, thus creating a more challenging environment for testing image quality.…”

Section: Discussionsupporting

confidence: 77%

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Laprade

Bartlett

Christensen

et al. 2023

Preprint

View full text Add to dashboard Cite

Snakebite envenoming is a global public health issue that causes significant morbidity and mortality, particularly in low-income regions of the world. The clinical manifestations of envenomings vary depending on the snake's venom, with paralysis, haemorrhage, and necrosis being the most common and medically relevant effects. To assess the efficacy of antivenoms against dermonecrosis, a preclinical testing approach involves in vivo mouse models that mimic local tissue effects of cytotoxic snakebites in humans. However, current methods for assessing necrosis severity are time-consuming and susceptible to human error. To address this, we present the Venom Induced Dermonecrosis Analysis tool (VIDAL), a machine-learning-guided image-based solution that can automatically identify dermonecrotic lesions in mice, adjust for lighting biases, scale the image, extract lesion area and discolouration, and calculate the severity of dermonecrosis. We also introduce a new unit, the dermonecrotic unit (DnU), to better capture the complexity of dermonecrosis severity. Our tool is comparable to the performance of state-of-the-art histopathological analysis, making it an accessible, accurate, and reproducible method for assessing dermonecrosis. Given the urgent need to address the neglected tropical disease that is snakebite, high-throughput technologies such as VIDAL are crucial in developing and validating new and existing therapeutics for this debilitating disease.

show abstract

Section: Discussionsupporting

confidence: 77%

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Laprade

Bartlett

Christensen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Processing of SRµCT data is described in detail in supplemental material. Preprocessed volumes were input into deep learning models for vessel/sinusoid and fibrosis/inflammation, trained and evaluated using the multi-planar U-Net approach (30). Visualization was performed using two software packages: Cytokine protein analysis.…”

Section: Synchrotron Radiation-based Microtomography (Srµct)mentioning

confidence: 99%

Structure-function analysis of time-resolved immunological phases in metabolic dysfunction- associated fatty liver disease

Schmidt-Christensen,

Eriksson,

Laprade

et al. 2024

Preprint

View full text Add to dashboard Cite

Metabolic dysfunction-associated steatohepatitis (MASH) is a common but frequently unrecognized complication of obesity and type 2 diabetes. The association between these conditions is multifaceted and involves complex interactions between metabolic, inflammatory, and genetic factors. Here we assess the underlying structural and molecular processes focusing on the immunological phase of MASH in the NIF mouse model and compare it to the human disease as well as other murine models. Histopathology together with synchrotron-radiation-based x-ray micro-computed tomography (SRµCT) was used to investigate structural changes within the hepatic sinusoids network in the NIF mouse in comparison to patients with different severities of MASH. A time-course, bulk RNA-sequencing analysis of liver tissue from NIF mice was performed to identify the dynamics of key processes contributing to the pathogenesis. Transcriptomics profiling of the NIF mouse revealed a gradual transition from an initially reactive inflammatory response to a regenerative, pro-fibrotic inflammatory response suggesting new avenues for treatment strategies that focus on immunological targets. Despite the lack of metabolic stress induced liver phenotype, a large similarity between the NIF mouse and the immunological phase of human MASH was detected. The translational value was further confirmed through comparative analyses with MASH patients and additional animal models. Finally, the impact of diets known to induce metabolic stress, was explored in the NIF mouse. An obesogenic diet was found to induce key physiological, metabolic, and histologic changes akin to those observed in human MASH.

show abstract

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Laprade,

Bartlett,

Christensen

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Snakebite envenoming is a global public health issue that causes significant morbidity and mortality, particularly in low-income regions of the world. The clinical manifestations of envenomings vary depending on the snake's venom, with paralysis, haemorrhage, and necrosis being the most common and medically relevant effects. To assess the efficacy of antivenoms against dermonecrosis, a preclinical testing approach involves in vivo mouse models that mimic local tissue effects of cytotoxic snakebites in humans. However, current methods for assessing necrosis severity are time-consuming and susceptible to human error. To address this, we present the Venom Induced Dermonecrosis Analysis tooL (VIDAL), a machine-learning-guided image-based solution that can automatically identify dermonecrotic lesions in mice, adjust for lighting biases, scale the image, extract lesion area and discolouration, and calculate the severity of dermonecrosis. We also introduce a new unit, the dermonecrotic unit (DnU), to better capture the complexity of dermonecrosis severity. Our tool is comparable to the performance of state-of-the-art histopathological analysis, making it an accessible, accurate, and reproducible method for assessing dermonecrosis in mice. Given the urgent need to address the neglected tropical disease that is snakebite, high-throughput technologies such as VIDAL are crucial in developing and validating new and existing therapeutics for this debilitating disease.

show abstract

How Few Annotations are Needed for Segmentation Using a Multi-planar U-Net?

Cited by 8 publications

References 5 publications

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Structure-function analysis of time-resolved immunological phases in metabolic dysfunction- associated fatty liver disease

Machine-learning guided Venom Induced Dermonecrosis Analysis tooL: VIDAL

Contact Info

Product

Resources

About