30 results
Filters
Settings
Now showing1 - 10 of 30
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , On TotalSegmentator’s performance on low-dose CT imagesDeep neural networks have emerged as the preferred method for semantic segmentation of CT images in recent years. However, understanding their limitations and generalization properties remains an active area of research and a relevant topic for clinical applications. One crucial factor among many is the X-ray radiation dose, which is always kept as low as reasonably possible during CT acquisition. Therefore, potential dose reductions may pose a challenge for existing segmentation models. In this paper, we investigate robustness of the recently proposed TotalSegmentator model for anatomical segmentation with respect to dose reduction. TotalSegmentator combines a large CT dataset and the well-established nnU-Net framework to train deep learning models, resulting in state-of-the-art performance for anatomical segmentation. Our method relies on accurate low-dose simulations derived from acquired full-dose projections. For a set of registered low- and full-dose CT images, we measure the Dice score between the corresponding segmentations. Our results reveal a high level of robustness in the segmentation outcomes. Comprehensive quantitative comparisons demonstrate that at a 20% dose level, the Dice score declines by at most 3%. Visual comparisons reveal only minor differences at the boundaries of the segmented organs. These findings may have a large potential for dose reduction when CT data are acquired predominantly for segmentation purposes, such as for the planning of interventional or surgical procedures.Publicationtype: Conference Paper38 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Motion-compensated OCT imaging of laryngeal tissue(SPIE, 2024-02); ; ; Breda, Philippe C.The increasing incidence of laryngeal carcinomas requires approaches for early diagnosis and treatment. In clinical practice, white light endoscopy of the laryngeal region is typically followed by biopsy under general anesthesia. Thus, image based diagnosis using optical coherence tomography (OCT) has been proposed to study sub-surface tissue layers at high resolution. However, accessing the region of interest requires robust miniature OCT probes that can be forwarded through the working channel of a laryngoscope. Typically, such probes generate A-scans, i.e., single column depth images, which are rather difficult to interpret. We propose a novel approach using the endoscopic camera images to spatially align these A-scans. Given the natural tissue motion and movements of the laryngoscope, the resulting OCT images show a three-dimensional representation of the sub-surface structures, which is simpler to interpret. We present the overall imaging setup and the motion tracking method. Moreover, we describe an experimental setup to assess the precision of the spatial alignment. We study different tracking templates and report root-mean-squared errors of 0.08mm and 0.18mm for sinusoidal and freehand motion, respectively. Furthermore, we also demonstrate the in-vivo application of the approach, illustrating the benefit of spatially meaningful alignment of the A-scans to study laryngeal tissue.Publicationtype: Conference Paper12 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Convolutional transformer network for paranasal anomaly classification in the maxillary sinus(SPIE, 2024-02); ; ; ; Large-scale population studies have examined the detection of sinus opacities in cranial MRIs. Deep learning methods, specifically 3D convolutional neural networks (CNNs), have been used to classify these anomalies. However, CNNs have limitations in capturing long-range dependencies across the low and high level features, potentially reducing performance. To address this, we propose an end-to-end pipeline using a novel deep learning network called ConTra-Net. ConTra-Net combines the strengths of CNNs and self-attention mechanisms of transformers to classify paranasal anomalies in the maxillary sinuses. Our approach outperforms 3D CNNs and 3D Vision Transformer (ViT), with relative improvements in F1 score of 11.68% and 53.5%, respectively. Our pipeline with ConTra-Net could serve as an alternative to reduce misdiagnosis rates in classifying paranasal anomalies.Publicationtype: Conference Paper27 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Weakly supervised Medulloblastoma tumor classification using domain specific patch-level feature extractionMedulloblastoma (MB) is the most common embryonal tumour of the brain. In order to decide on an optimal therapy, laborious inspection of histopathological tissue slides by neuropathologists is necessary. Digital pathology with the support of deep learning methods can help to improve the clinical workflow. Due to the high resolution of histopathological images, previous work on MB classification involved manual selection of patches, making it a time consuming task. In order to leverage only slide labels for histopathology image classification, weakly supervised approaches first encode small patches into feature vectors using an ImageNet pretrained encoder based on convolutional neural networks. The representations of patches are further utilized to train a data-efficient attention-based learning method. Due to the domain shift between natural images and histopathology images, the encoder is not optimal for feature extraction for MB classification. In this study, we adapt weakly supervised learning for MB classification and examine different histopathological specific encoder architectures and weights for the MB classification task. The results show that ResNet encoders pretrained with histopathology images lead to better MB classification results compared to encoders pretrained on ImageNet. The best performing method uses a ResNet50 architecture, pretrained on histopathology images and achieves an area under the receiver operating curve (AUROC) value of 71.89%, improving the baseline model by 2%.Publicationtype: Conference Paper10 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Quantitative evaluation of activation maps for weakly-supervised lung nodule segmentation(SPIE, 2024-01); ; ; ; The manual assessment of chest radiographs by radiologists is a time-consuming and error-prone process that relies on the availability of trained professionals. Deep learning methods have the potential to alleviate the workload of radiologists in pathology detection and diagnosis. However, one major drawback of deep learning methods is their lack of explainable decision-making, which is crucial in computer-aided diagnosis. To address this issue, activation maps of the underlying convolutional neural networks (CNN) are frequently used to indicate the regions of focus for the network during predictions. However, often, an evaluation of these activation maps concerning the actual predicted pathology is missing. In this study, we quantitatively evaluate the usage of activation maps for segmenting pulmonary nodules in chest radiographs. We compare transformer-based, CNN-based, and hybrid architectures using different visualization methods. Our results show that although high performance can be achieved in the classification task across all models, the activation masks show little correlation with the actual position of the nodules.Publicationtype: Conference Paper12 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Unsupervised Anomaly Detection of Paranasal Anomalies in the Maxillary SinusDeep learning (DL) algorithms can be used to automate paranasal anomaly detection from Magnetic Resonance Imaging (MRI). However, previous works relied on supervised learning techniques to distinguish between normal and abnormal samples. This method limits the type of anomalies that can be classified as the anomalies need to be present in the training data. Further, many data points from normal and anomaly class are needed for the model to achieve satisfactory classification performance. However, experienced clinicians can segregate between normal samples (healthy maxillary sinus) and anomalous samples (anomalous maxillary sinus) after looking at a few normal samples. We mimic the clinicians ability by learning the distribution of healthy maxillary sinuses using a 3D convolutional auto-encoder (cAE) and its variant, a 3D variational autoencoder (VAE) architecture and evaluate cAE and VAE for this task. Concretely, we pose the paranasal anomaly detection as an unsupervised anomaly detection problem. Thereby, we are able to reduce the labelling effort of the clinicians as we only use healthy samples during training. Additionally, we can classify any type of anomaly that differs from the training distribution. We train our 3D cAE and VAE to learn a latent representation of healthy maxillary sinus volumes using L1 reconstruction loss. During inference, we use the reconstruction error to classify between normal and anomalous maxillary sinuses. We extract sub-volumes from larger head and neck MRIs and analyse the effect of different fields of view on the detection performance. Finally, we report which anomalies are easiest and hardest to classify using our approach. Our results demonstrate the feasibility of unsupervised detection of paranasal anomalies from MRIs with an AUPRC of 85% and 80% for cAE and VAE, respectively.Publicationtype: Conference Paper25 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Ultrasound Shear Wave Velocity Estimation in a small Field of View via Spatio-Temporal Deep Learning(SPIE, 2023-04-03); ; ; ; A change in tissue stiffness can indicate pathological diseases and therefore supports physicians in diagnosis and treatment. Ultrasound shear wave elastography (US-SWEI) can be used to quantify tissue stiffness by estimating the velocity of propagating shear waves. While a linear US probe with a lateral imaging width of approximately 40 mm is commonly used and US-SWEI has been successfully demonstrated, some clinical applications, such as laparoscopic or endoscopic interventions, require small probes. This limits the lateral image width to the millimeter range and reduces the available information in the US images substantially. In this work, we systematically analyze the effect of a reduced lateral imaging width for shear wave velocity estimation using the conventional time-of-flight (ToF) method and spatio-temporal convolutional neural networks (ST-CNNs). For our study, we use tissue mimicking gelatin phantoms with varying stiffness and resulting shear wave velocities in the range from 3.63 m/s to 7.09 m/s. We find that lateral imaging width has a substantial impact on the performance of ToF, while shear wave velocity estimation with ST-CNNs remains robust. Our results show that shear wave velocity estimation with ST-CNN can even be performed for a lateral imaging width of 2.1 mm resulting in a mean absolute error of 0.81 ± 0.61 m/s.Publicationtype: Conference Paper51 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Automated assessment for grinding spots on aircraft landing gear components using robotic white light interferometryThe current method for rework inspection of previously defective surface areas on aircraft landing gear components involves manual inspection. Measuring tools such as micrometers and gauges are utilized to obtain positions and dimensions of reworks. This information is required for determining whether re-entry of the component into service is possible. Overall, the manual process is time-consuming, highly dependent on the skill and experience of the inspector, and prone to errors. This paper presents a novel approach to inspect reworks on aircraft landing gear components using a robotic inspection system based on white light interferometry (WLI). The proposed method is aimed at improving accuracy, repeatability as well as efficiency of rework inspection. The robotic system handles the WLI and positions it over the component, allowing for detailed 3D measurements of the surface and reworked area. Considering the typical measuring spot size of a WLI, the overall positioning accuracy of industrial robots is crucial. Measures to address this problem as well as general limitations and the potential of the system for the use case are discussed. An exemplary rework inspection validates the applicability and demonstrates the potential of this approach. Future research and optimizations are discussed which could lead to more widespread adoption of this technology and further advancements in the maintenance of aircraft landing gears.Publicationtype: Conference Paper22 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Self-supervised U-Net for segmenting flat and sessile polypsColorectal Cancer(CRC) poses a great risk to public health. It is the third most common cause of cancer in the US. Development of colorectal polyps is one of the earliest signs of cancer. Early detection and resection of polyps can greatly increase survival rate to 90%. Manual inspection can cause misdetections because polyps vary in color, shape, size and appearance. To this end, Computer-Aided Diagnosis systems(CADx) has been proposed that detect polyps by processing the colonoscopic videos. The system acts a secondary check to help clinicians reduce misdetections so that polyps may be resected before they transform to cancer. Polyps vary in color, shape, size, texture and appearance. As a result, the miss rate of polyps is between 6% and 27% despite the prominence of CADx solutions. Furthermore, sessile and flat polyps which have diameter less than 10 mm are more likely to be undetected. Convolutional Neural Networks(CNN) have shown promising results in polyp segmentation. However, all of these works have a supervised approach and are limited by the size of the dataset. It was observed that smaller datasets reduce the segmentation accuracy of ResUNet++. Self-supervision is a stronger alternative to fully supervised learning especially in medical image analysis since it redresses the limitations posed by small annotated datasets. From the self-supervised approach proposed by Jamaludin et al., it is evident that pretraining a network with a proxy task helps in extracting meaningful representations from the underlying data which can then be used to improve the performance of the final downstream supervised task. In summary, we train a U-Net to inpaint randomly dropped out pixels in the image as a proxy task. The dataset we use for pretraining is Kvasir-SEG dataset. This is followed by a supervised training on the limited Kvasir-Sessile dataset. Our experimental results demonstrate that with limited annotated dataset and a larger unlabeled dataset, self-supervised approach is a better alternative than fully supervised approach. Specifically, our self-supervised U-Net performs better than five segmentation models which were trained in supervised manner on the Kvasir-Sessile dataset.Publicationtype: Conference Paper25 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Unsupervised anomaly detection in 3D brain MRI using deep learning with multi-task brain age predictionLesion detection in brain Magnetic Resonance Images (MRIs) remains a challenging task. MRIs are typically read and interpreted by domain experts, which is a tedious and time-consuming process. Recently, unsupervised anomaly detection (UAD) in brain MRI with deep learning has shown promising results to provide a quick, initial assessment. So far, these methods only rely on the visual appearance of healthy brain anatomy for anomaly detection. Another biomarker for abnormal brain development is the deviation between the brain age and the chronological age, which is unexplored in combination with UAD. We propose deep learning for UAD in 3D brain MRI considering additional age information. We analyze the value of age information during training, as an additional anomaly score, and systematically study several architecture concepts. Based on our analysis, we propose a novel deep learning approach for UAD with multi-task age prediction. We use clinical T1-weighted MRIs of 1735 healthy subjects and the publicly available BraTs 2019 data set for our study. Our novel approach significantly improves UAD performance with an AUC of 92.60% compared to an AUC-score of 84.37% using previous approaches without age information.Publicationtype: Conference Paper34