CNN Based Segmentation of Infarcted Regions in Acute Cerebral Stroke Patients From Computed Tomography Perfusion Imaging

Tomasetti, L; Engan, Kjersti; Khanmohammadi, Mahdieh; Kurz, Kathinka D.

doi:10.1145/3388440.3412470

Cited by 5 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, relying on raw data (directly exploiting the temporal and spatial dimensions) is scarcely explored in the literature for AIS applications. To the best of our knowledge, few studies proposed DNN models with promising results, exploiting the temporal dimension to assess ischemic stroke lesions using CTP images [5,30,31,32,33]. Soltanpour et al [5] utilized 4D CTP images to create 2D matrices, in which each row is a voxel, and each column is a time point.…”

Section: Introductionmentioning

confidence: 99%

“…An understanding of the extension of the penumbra during the first stages of the ischemic stroke is crucial for treatment decision [35,36]. To the best of our knowledge, Tomasetti et al was the first research group to segment both core and penumbra regions using machine learning [36] or DNN approaches [32,37].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we present and investigate three novel models to segment the two ischemic regions (core and penumbra), where the input is the entire 4D CTP scans arranged in different ways to exploit the spatio-temporal nature of the data. We compare all models with previous work based on PMs [37] and slice-by-slice CTP [32], and two methods proposed by Amador et al [30,33].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting 4D CT Perfusion for segmenting infarcted areas in patients with suspected acute ischemic stroke

Tomasetti¹,

Engan²,

Høllesli³

et al. 2023

Preprint

View full text Add to dashboard Cite

Precise and fast prediction methods for ischemic areas (core and penumbra) in acute ischemic stroke (AIS) patients are of significant clinical interest: they play an essential role in improving diagnosis and treatment planning. Computed Tomography (CT) scan is one of the primary modalities for early assessment in patients with suspected AIS. CT Perfusion (CTP) is often used as a primary assessment to determine stroke location, severity, and volume of ischemic lesions. Current automatic segmentation methods for CTP mostly use already processed 3D color maps conventionally used for visual assessment by radiologists as input. Alternatively, the raw CTP data is used on a slice-by-slice basis as 2D+time input, where the spatial information over the volume is ignored. In this paper, we investigate different methods to utilize the entire 4D CTP as input to fully exploit the spatio-temporal information. This leads us to propose a novel 4D convolution layer. Our comprehensive experiments on a local dataset comprised of 152 patients divided into three groups show that our proposed models generate more precise results than other methods explored. A Dice Coefficient of 0.70 and 0.45 is achieved for All authors are with the BioMedical Data analysis group (https://www.uis.no/en/ bmdlab)

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting 4D CT Perfusion for segmenting infarcted areas in patients with suspected acute ischemic stroke

Tomasetti¹,

Engan²,

Høllesli³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, Machine Learning (ML) and neural network algorithms have achieved promising results in a large number of medical image analysis applications, and have also made their way into the stroke application [23]- [27]. Kemmling et al proposed a generalized linear model using the parametric maps as input and clinical data to quantify changes of tissue infarction [23].…”

Section: Introductionmentioning

confidence: 99%

“…Our research group was, to the best of our knowledge, the first using the entire 4D CTP data as input to a neural network to segment both penumbra and core simultaneously. A modified U-Net model was used in a small pilot study to segment both penumbra and core regions using the entire 4D CTP volume as input and with ground truth generated with manual expert assessment directly from the parametric maps [27]. The results were promising, but they were based on a very small pilot study and need to be validated on a larger sample size.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Algorithms Versus Thresholding to Segment Ischemic Regions in Patients With Acute Ischemic Stroke

Tomasetti

Høllesli

Engan

et al. 2022

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Objective: Computed tomography (CT) scan is a fast and widely used modality for early assessment in patients with symptoms of a cerebral ischemic stroke. CT perfusion (CTP) is often added to the protocol and is used by radiologists for assessing the severity of the stroke. Standard parametric maps are calculated from the CTP datasets. Based on parametric value combinations, ischemic regions are separated into presumed infarct core (irreversibly damaged tissue) and penumbra (tissue-at-risk). Different thresholding approaches have been suggested to segment the parametric maps into these areas. The purpose of this study is to compare fully-automated methods based on machine learning and thresholding approaches to segment the hypoperfused regions in patients with ischemic stroke. Methods: We test two different architectures with three mainstream machine learning algorithms. We use parametric maps as input features, and manual annotations made by two expert neuroradiologists as ground truth. Results: The best results are produced with random forest (RF) and Single-Step approach; we achieve an average Dice coefficient of 0.68 and 0.26, respectively for penumbra and core, for the three groups analysed. We also achieve an average in volume difference of 25.1ml for penumbra and 7.8ml for core. Conclusions: Our best RFbased method outperforms the classical thresholding approaches, to segment both the ischemic regions in a group of patients regardless of the severity of vessel occlusion. Significance: A correct visualization of the ischemic regions will guide treatment decisions better.

show abstract

CT Perfusion is All we Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Acute Ischemic Stroke

Tomasetti,

Engan,

Høllesli

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Stroke is the second leading cause of death worldwide, and around 87 % of strokes are ischemic strokes. Accurate and rapid prediction techniques for identifying ischemic regions, including dead tissue (core) and potentially salvageable tissue (penumbra), in patients with acute ischemic stroke (AIS) hold great clinical importance, as this can provide valuable information for diagnosis and treatment planning. Computed Tomography Perfusion (CTP) is often used as a primary tool for assessing stroke location, severity, and the volume of ischemic regions. Current automatic segmentation methods for CTP typically utilize preprocessed 3D parametric maps, traditionally used for clinical interpretation by radiologists. An alternative approach is to use the raw CTP data slice by slice as 2D+time input, where the spatial information over the volume is overlooked. Additionally, these methods primarily focus on segmenting core regions, yet predicting penumbra regions can be crucial for treatment planning. This paper investigates different methods to utilize the entire raw 4D CTP as input to fully exploit the spatio-temporal information, leading us to propose a 4D convolution layer in a 4D CNN network. Our comprehensive experiments on a local dataset of 152 patients divided into three groups show that our proposed models generate more precise results than other methods explored. Adopting the proposed 4D mJ-Net, a Dice Coefficient of 0.53 and 0.23 is achieved for segmenting penumbra and core areas, respectively. Using the entire 4D CTP data for AIS segmentation offers improved precision and potentially better treatment planning in patients suspected of this condition.

show abstract

CNN Based Segmentation of Infarcted Regions in Acute Cerebral Stroke Patients From Computed Tomography Perfusion Imaging

Abstract: Figure 1: A general overview of the various steps involved in the proposed approach (green panels) that bypasses the current methods used by the majority of the radiologists and state-of-the-art approaches based on thresholding and semi-automatic approaches (red panel).

Cited by 5 publications

References 24 publications

Exploiting 4D CT Perfusion for segmenting infarcted areas in patients with suspected acute ischemic stroke

Exploiting 4D CT Perfusion for segmenting infarcted areas in patients with suspected acute ischemic stroke

Machine Learning Algorithms Versus Thresholding to Segment Ischemic Regions in Patients With Acute Ischemic Stroke

CT Perfusion is All we Need: 4D CNN Segmentation of Penumbra and Core in Patients With Suspected Acute Ischemic Stroke

Contact Info

Product

Resources

About