Maria Klusmann

Bio: Maria Klusmann is an academic researcher from University College Hospital. The author has contributed to research in topics: Segmentation & Image segmentation. The author has an hindex of 3, co-authored 3 publications receiving 64 citations.

Progressive destructive bone changes in patients with cystinosis.

Abstract: Nephropathic cystinosis is an autosomal recessive lysosomal storage disorder in which intracellular cystine accumulates. It is caused by mutations in the CTNS gene. Clinical manifestations include renal tubular Fanconi syndrome in the first year of life, rickets, hypokalaemia, polyuria, dehydration and acidosis, growth retardation, hypothyroidism, photophobia and renal glomerular deterioration. Late complications include myopathy, pancreatic insufficiency and retinal blindness. Skeletal manifestations described in these patients include failure to thrive, osteomalacia, rickets and short stature. This paper describes progressive bony abnormalities in three unrelated patients with nephropathic cystinosis that have not been reported previously.

Dynamically Balanced Online Random Forests for Interactive Scribble-Based Segmentation

Abstract: Interactive scribble-and-learning-based segmentation is attractive for its good performance and reduced number of user interaction. Scribbles for foreground and background are often imbalanced. With the arrival of new scribbles, the imbalance ratio may change largely. Failing to deal with imbalanced training data and a changing imbalance ratio may lead to a decreased sensitivity and accuracy for segmentation. We propose a generic Dynamically Balanced Online Random Forest (DyBa ORF) to deal with these problems, with a combination of a dynamically balanced online Bagging method and a tree growing and shrinking strategy to update the random forests. We validated DyBa ORF on UCI machine learning data sets and applied it to two different clinical applications: 2D segmentation of the placenta from fetal MRI and adult lungs from radiographic images. Experiments show it outperforms traditional ORF in dealing with imbalanced data with a changing imbalance ratio, while maintaining a comparable accuracy and a higher efficiency compared with its offline counterpart. Our results demonstrate that DyBa ORF is more suitable than existing ORF for learning-based interactive image segmentation.

Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning

Abstract: Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

Abstract: Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.

Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning

Abstract: Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes. To address these problems, we propose a novel deep learning-based framework for interactive segmentation by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine-tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine-tuning. We applied this framework to two applications: 2D segmentation of multiple organs from fetal MR slices, where only two types of these organs were annotated for training; and 3D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only tumor cores in one MR sequence were annotated for training. Experimental results show that 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine-tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

The renal Fanconi syndrome in cystinosis: pathogenic insights and therapeutic perspectives

Abstract: Cystinosis is an autosomal recessive metabolic disease that belongs to the family of lysosomal storage disorders. It is caused by a defect in the lysosomal cystine transporter, cystinosin, which results in an accumulation of cystine in all organs. Despite the ubiquitous expression of cystinosin, a renal Fanconi syndrome is often the first manifestation of cystinosis, usually presenting within the first year of life and characterized by the early and severe dysfunction of proximal tubule cells, highlighting the unique vulnerability of this cell type. The current therapy for cystinosis, cysteamine, facilitates lysosomal cystine clearance and greatly delays progression to kidney failure but is unable to correct the Fanconi syndrome. This Review summarizes decades of studies that have fostered a better understanding of the pathogenesis of the renal Fanconi syndrome associated with cystinosis. These studies have unraveled some of the early molecular changes that occur before the onset of tubular atrophy and identified a role for cystinosin beyond cystine transport, in endolysosomal trafficking and proteolysis, lysosomal clearance, autophagy and the regulation of energy balance. These studies have also led to the identification of new potential therapeutic targets and here, we outline the potential role of stem cell therapy for cystinosis and provide insights into the mechanism of haematopoietic stem cell-mediated kidney protection.