Logotyp: till Uppsala universitets webbplats

Volumetric quantification of tumors is usually done manually by radiologists requiring precious medical time and suffering from inter-observer variability. An automatic tool for accurate volume quantification of post-operative glioblastoma would reduce the workload of radiologists and improve the quality of follow-up monitoring and patient care. This paper deals with the 3-D segmentation of post-operative glioblastoma using channel squeeze and excitation based attention gated network (ASE-Net). The proposed deep neural network has a 3-D encoder and decoder based architecture with channel squeeze and excitation (CSE) blocks and attention blocks. The CSE block reduces the dependency on space information and put more emphasize on the channel information. The attention block suppresses the feature maps of irrelevant background and helps highlighting the relevant feature maps. The Uppsala university data set used has post-operative follow-up MRI scans for fifteen patients. A patient specific fine-tuning approach is used to improve the segmentation results for each patient. ASE-Net is also cross-validated with BraTS-2021 data set. The mean dice score of five-fold cross validation results with BraTS-2021 data set for enhanced tumor is 0.8244. The proposed network outperforms the competing networks like U-Net, Attention U-Net and Res U-Net. On the Uppsala University glioblastoma data set, the mean Dice score obtained with the proposed network is 0.7084, Hausdorff Distance-95 is 7.14 and the mean volumetric similarity achieved is 0.8579. With fine-tuning the pre-trained network, the mean dice score improved to 0.7368, Hausdorff Distance-95 decreased to 6.10 and volumetric similarity improved to 0.8736. ASE-Net outperforms the competing networks and can be used for volumetric quantification of post-operative glioblastoma from follow-up MRI scans. The network significantly reduces the probability of over segmentation.

Radiological imaging to examine intracranial blood vessels is critical for preoperative planning and postoperative follow-up. Automated segmentation of cerebrovascular anatomy from Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) can provide radiologists with a more detailed and precise view of these vessels. This paper introduces a domain generalized artificial intelligence (AI) solution for volumetric monitoring of cerebrovascular structures from multi-center MRAs. Our approach utilizes a multi-task deep convolutional neural network (CNN) with a topology-aware loss function to learn voxel-wise segmentation of the cerebrovascular tree. We use Decorrelation Loss to achieve domain regularization for the encoder network and auxiliary tasks to provide additional regularization and enable the encoder to learn higher-level intermediate representations for improved performance. We compare our method to six state-of-the-art 3D vessel segmentation methods using retrospective TOF-MRA datasets from multiple private and public data sources scanned at six hospitals, with and without vascular pathologies. The proposed model achieved the best scores in all the qualitative performance measures. Furthermore, we have developed an AI-assisted Graphical User Interface (GUI) based on our research to assist radiologists in their daily work and establish a more efficient work process that saves time.

Accurate localization and volumetric quantification of postoperative glioblastoma are of profound importance for clinical applications like post-surgery treatment planning, monitoring of tumor regrowth, and radiotherapy map planning. Manual delineation consumes more time and error prone thus automated 3-D quantification of brain tumors using deep learning algorithms from MRI scans has been used in recent years. The shortcoming with automated segmentation is that it often over-segments or under-segments the tumor regions. An interactive deep-learning tool will enable radiologists to correct the over-segmented and under-segmented voxels. In this paper, we proposed a network named Attention-SEV-Net which outperforms state-of-the-art network architectures. We also developed an interactive graphical user interface, where the initial 3-D segmentation of contrast-enhanced tumor can be interactively corrected to remove falsely detected isolated tumor regions. Attention-SEV-Net is trained with BraTS-2021 training data set and tested on Uppsala University post-operative glioblastoma dataset. The methodology outperformed state-of-the-art networks like U-Net, VNet, Attention U-Net and Residual U-Net. The mean dice score achieved is 0.6682 and the mean Hausdorff distance-95 got is 8.96mm for the Uppsala University dataset.

This paper presents a weakly supervised deep convolutional neural network-based approach to perform voxel-level3D registration between subsequent follow-up MRI scans of the same patient. To handle the large deformation inthe surrounding brain tissues due to the tumor’s mass effect we proposed curriculum learning-based training forthe network. Weak supervision helps the network to concentrate more focus on the tumor region and resectioncavity through a saliency detection network. Qualitative and quantitative experimental results show the proposedregistration network outperformed two popular state-of-the-art methods.

This paper presents a novel solution for catastrophic forgetting in lifelong learning (LL) using Dynamic Convolution Neural Network (Dy-CNN). The proposed dynamic convolution layer can adapt convolution filters by learning kernel coefficients or weights based on the input image. The suitability of the proposed Dy-CNN in a lifelong sequential learning-based scenario with multi-modal MR images is experimentally demonstrated for the segmentation of Glioma tumors from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.

This paper presents a novel solution for catastrophic forgetting in life long learning (LL) using Dynamic ConvolutionNeural Network (Dy-CNN). The proposed dynamic convolution layer, can adapt convolution filters bylearning kernel coefficients or weights based on the input image. Suitability of the proposed Dy-CNN in a lifelongsequential learning-based scenario with multi-modal MR images is experimentally demonstrated for segmentation of Glioma tumor from multi-modal MR images. Experimental results demonstrated the superiority of the Dy-CNN-based segmenting network in terms of learning through multi-modal MRI images and better convergence of lifelong learning-based training.

Arterial cerebral vessel assessment is critical for thediagnosis of patients with cerebrovascular disease e.g., hypertension, Intracranial aneurysms, and dementia. Magnetic resonance angiography is a primary imaging technique for diagnosing cerebrovascular diseases. There are many Convolutional neuralnetworks (CNN) based methods for cerebral vessel segmentation but lack to identify the target vessels and understand the arterial tree structure for diagnosis and endovascular surgical planning.In the present study, we generated annotations for major vesselsegmentation and analyzed fully automatic segmentation of major vessels using state-of-the-art U-Net based deep learning models. Computer-aided major cerebral vessel segmentation incorporatedinto clinical practice may help speed up the diagnosis of time-critical vessel anomalies and help find important bio-markers for neurological dysfunction. We validated and compared U-Net based models for volumetric segmentation and predictionof cerebral arteries and it could be done in real-time withoutany image pre-processing.

This paper presents a topology-aware learning strategy for volumetric segmentation of intracranial cerebrovascular structures. We propose a multi-task deep CNN along with a topology-aware loss function for this purpose. Along with the main task (i.e. segmentation), we train the model to learn two related auxiliary tasks viz. learning the distance transform for the voxels on the surface of the vascular tree and learning the vessel centerline. This provides additional regularization and allows the encoder to learn higher-level intermediate representations to boost the performance of the main task. We compare the proposed method with six state-of-the-art deep learning-based 3D vessel segmentation methods, by using a public Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) dataset. Experimental results demonstrate that the proposed method has the best performance in this particular context.