1. |
- Banerjee, Subhashis, et al.
(författare)
-
Streamlining neuroradiology workflow with AI for improved cerebrovascular structure monitoring
- 2024
-
Ingår i: Scientific Reports. - : Nature Publishing Group. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
2. |
- Kahraman, Ali Teymur, et al.
(författare)
-
A Simple End-to-End Computer-Aided Detection Pipeline for Trained Deep Learning Models
- 2024
-
Ingår i: Engineering of Computer-Based Systems : 8th International Conference, ECBS 2023, Proceedings - 8th International Conference, ECBS 2023, Proceedings. - 0302-9743 .- 1611-3349. - 9783031492518 ; 14390 LNCS, s. 259-262
-
Konferensbidrag (refereegranskat)abstract
- Recently, there has been a significant rise in research and development focused on deep learning (DL) models within healthcare. This trend arises from the availability of extensive medical imaging data and notable advances in graphics processing unit (GPU) computational capabilities. Trained DL models show promise in supporting clinicians with tasks like image segmentation and classification. However, advancement of these models into clinical validation remains limited due to two key factors. Firstly, DL models are trained on off-premises environments by DL experts using Unix-like operating systems (OS). These systems rely on multiple libraries and third-party components, demanding complex installations. Secondly, the absence of a user-friendly graphical interface for model outputs complicates validation by clinicians. Here, we introduce a conceptual Computer-Aided Detection (CAD) pipeline designed to address these two issues and enable non-AI experts, such as clinicians, to use trained DL models offline in Windows OS. The pipeline divides tasks between DL experts and clinicians, where experts handle model development, training, inference mechanisms, Grayscale Softcopy Presentation State (GSPS) objects creation, and containerization for deployment. The clinicians execute a simple script to install necessary software and dependencies. Hence, they can use a universal image viewer to analyze results generated by the models. This paper illustrates the pipeline's effectiveness through a case study on pulmonary embolism detection, showcasing successful deployment on a local workstation by an in-house radiologist. By simplifying model deployment and making it accessible to non-AI experts, this CAD pipeline bridges the gap between technical development and practical application, promising broader healthcare applications.
|
|
3. |
- Kundu, Swagata, et al.
(författare)
-
ASE-Net for Segmentation of Post-operative Glioblastoma and Patient-specific Fine-tuning for Segmentation Refinement of Follow-up MRI Scans
- 2024
-
Ingår i: SN computer science. - : Springer. - 2661-8907. ; 5:106
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
4. |
- Pal, Subhash Chandra, et al.
(författare)
-
Multi-level Residual Dual Attention Network for Major Cerebral Arteries Segmentation in MRA towards Diagnosis of Cerebrovascular Disorders
- 2024
-
Ingår i: IEEE Transactions on Nanobioscience. - : IEEE. - 1536-1241 .- 1558-2639. ; 23:1, s. 167-175
-
Tidskriftsartikel (refereegranskat)abstract
- Segmentation of major brain vessels is very important for the diagnosis of cerebrovascular disorders and subsequent surgical planning. Vessel segmentation is an important pre-processing step for a wide range of algorithms for the automatic diagnosis or treatment of several vascular pathologies and as such, it is valuable to have a well-performing vascular segmentation pipeline. In this article, we propose an end-to-end multiscale residual dual attention deep neural network for resilient major brain vessel segmentation. In the proposed network, the encoder and decoder blocks of the U-Net are replaced with the multi-level atrous residual blocks to enhance the learning capability by increasing the receptive field to extract the various semantic coarse- and fine- grained features. Dual attention block is incorporated in the bottleneck to perform effective multiscale information fusion to obtain detailed structure of blood vessels. The methods were evaluated on the publicly available TubeTK data set. The proposed method outperforms the state-of-the-art techniques with dice of 0.79 on the whole-brain prediction. The statistical and visual assessments indicate that proposed network is robust to outliers and maintains higher consistency in vessel continuity than the traditional U-Net and its variations.
|
|