StrokeNeXt: A Siamese-encoder Approach for Brain Stroke Classification in Computed Tomography Imagery

Leo Thomas Ramos; Angel D. Sappa

eess.IVFeb 16, 2026

StrokeNeXt: A Siamese-encoder Approach for Brain Stroke Classification in Computed Tomography Imagery

Authors: Leo Thomas Ramos, Angel D. Sappa

Organizations: Computer Vision Center · Universitat Aut`onoma de Barcelona · ESPOL Polytechnic University

Abstract

We present StrokeNeXt, a model for stroke classification in 2D Computed Tomography (CT) images. StrokeNeXt employs a dual-branch design with two ConvNeXt encoders, whose features are fused through a lightweight convolutional decoder based on stacked 1D operations, including a bottleneck projection and transformation layers, and a compact classification head. The model is evaluated on a curated dataset of 6,774 CT images, addressing both stroke detection and subtype classification between ischemic and hemorrhage cases. StrokeNeXt consistently outperforms convolutional and Transformer-based baselines, reaching accuracies and F1-scores of up to 0.988. Paired statistical tests confirm that the performance gains are statistically significant, while class-wise sensitivity and specificity demonstrate robust behavior across diagnostic categories. Calibration analysis shows reduced prediction error compared to competing methods, and confusion matrix results indicate low misclassification rates. In addition, the model exhibits low inference time and fast convergence.

Figures & tables

Figure 1: Overview of the proposed StrokeNeXt architecture. The model processes the input CT image through two parallel ConvNeXt encoders. Their outputs are fused via a custom convolutional decoder composed of a stack operation, a 1D convolutional fusion path with transformation layers, and a classification head.

Figure 2: Sample images from the used dataset in this work.

Figure 3: ConvNeXt architecture (tiny version). Source: [ 23 ]

Model	Channels (per stage)	Depths (per stage)	Params (M)	FLOPs (G)
ConvNeXt-tiny	[96, 192, 384, 768]	[3, 3, 9, 3]	28	4.5
ConvNeXt-small	[96, 192, 384, 768]	[3, 3, 27, 3]	50	8.7
ConvNeXt-base	[128, 256, 512, 1024]	[3, 3, 27, 3]	89	15.4
ConvNeXt-large	[192, 384, 768, 1536]	[3, 3, 27, 3]	198	34.4

Table 1: Details of ConvNeXt variants. Taken from: [ 24 ]

Figure 4: Structure of fusion decoder developed in this study.

Method	Accuracy	Precision	Recall	F1-score	AUROC	AUPRC	Balanced Acc.	MCC	Brier score	ECE	Latency (s)	Throughput (img/s)	Peak GPU (GB)	FLOPs (G)	Params (M)	Train. time (h)
StrokeNeXt-tiny	0.978	0.978	0.978	0.978	0.986	0.987	0.971	0.950	0.021	0.053	0.002	570	1.417	8.977	57.6	0.087
StrokeNeXt-small	0.980	0.981	0.981	0.980	0.976	0.981	0.972	0.957	0.019	0.047	0.003	349	1.747	17.474	100.8	0.126
StrokeNeXt-base	0.982	0.983	0.982	0.982	0.990	0.990	0.977	0.960	0.017	0.051	0.004	222	2.641	30.853	178.5	0.161
StrokeNeXt-large	0.987	0.987	0.987	0.987	0.995	0.995	0.983	0.970	0.013	0.059	0.009	113	4.950	68.940	399.9	0.245

Table 2: Performance of the different StrokeNeXt variants on stroke presence classification (non-stroke vs. stroke).

Method	Accuracy	Precision	Recall	F1-score	AUROC	AUPRC	Balanced Acc.	MCC	Brier score	ECE	Latency (s)	Throughput (img/s)	Peak GPU (GB)	FLOPs (G)	Params (M)	Train. time (h)
MobileNetv2 [ 26 ]	0.865	0.863	0.865	0.862	0.938	0.894	0.828	0.685	0.121	0.154	0.001	3374	0.868	0.319	2.2	0.040
VGG16 [ 16 ]	0.894	0.893	0.894	0.893	0.918	0.858	0.822	0.657	0.142	0.180	0.001	1750	4.020	15.519	134.2	0.041
ResNet50 [ 12 ]	0.875	0.879	0.875	0.870	0.926	0.893	0.827	0.711	0.125	0.164	0.001	2057	1.034	4.130	23.5	0.040
ResNet152 [ 12 ]	0.892	0.894	0.892	0.889	0.937	0.908	0.855	0.752	0.108	0.152	0.001	1213	1.298	11.601	58.2	0.046
Swin Transformer [ 17 ]	0.893	0.893	0.892	0.890	0.939	0.899	0.859	0.751	0.094	0.099	0.002	363	2.196	10.550	87.1	0.067
ConvNeXt-base [ 18 ]	0.879	0.878	0.879	0.879	0.937	0.891	0.857	0.723	0.123	0.174	0.002	444	1.947	15.425	87.5	0.049

Table 3: Performance of StrokeNeXt on stroke presence classification (non-stroke vs. stroke) compared with other methods.

Method A	Method B	A✓B✗	B✓A✗	$\chi^{2}$	p-value
StrokeNeXt-large	VGG16 [ 16 ]	94	2	82.260	$<$ 0.0001
StrokeNeXt-large	MobileNetv2 [ 26 ]	87	4	73.890	$<$ 0.0001
StrokeNeXt-large	ResNet50 [ 12 ]	79	3	68.597	$<$ 0.0001
StrokeNeXt-large	ResNet152 [ 12 ]	67	3	56.700	$<$ 0.0001
StrokeNeXt-large	ConvNeXt-base [ 18 ]	76	3	65.620	$<$ 0.0001
StrokeNeXt-large	Swin Transformer [ 17 ]	69	5	53.635	$<$ 0.0001

Table 4: Results of the McNemar test comparing our best model with other methods on stroke presence classification (non-stroke vs. stroke).

Method	Non-stroke		Stroke
	Sensitivity	Specificity	Sensitivity	Specificity
MobileNetv2 [ 26 ]	0.934	0.722	0.722	0.934
VGG16 [ 16 ]	0.908	0.735	0.735	0.908
ResNet50 [ 12 ]	0.967	0.686	0.686	0.967
ResNet152 [ 12 ]	0.965	0.744	0.744	0.965
Swin Transformer [ 17 ]	0.956	0.762	0.762	0.956

Table 5: Per-class performance of StrokeNeXt on stroke presence classification (non-stroke vs. stroke) compared to other methods.

Figure 5: Confusion matrices comparison between StrokeNeXt and other models on stroke presence classification (non-stroke vs. stroke).

Method	Accuracy	Precision	Recall	F1-score
StrokeViT [ 21 ]	0.870	0.870	0.870	0.870
OzNet [ 20 ]	0.984	0.983	0.986	0.984
CNN [ 14 ]	0.951	0.953	0.936	0.944
ElasticNet [ 8 ]	0.760	0.790	0.710	0.750
CAD [ 28 ]	0.810	0.760	0.820	0.730
MobileNetv2 [ 29 ]	0.975	0.977	0.972	0.974

Table 6: Comparison of StrokeNeXt on stroke presence classification (non-stroke vs. stroke) with other methods from the literature.

Method	Accuracy	Precision	Recall	F1-score	AUROC	AUPRC	Balanced Acc.	MCC	Brier score	ECE	Latency (s)	Throughput (img/s)	Peak GPU (GB)	FLOPs (G)	Params (M)	Train. time (h)
StrokeNeXt-tiny	0.986	0.985	0.986	0.986	1.000	1.000	0.986	0.973	0.011	0.058	0.002	571	1.417	8.977	57.6	0.041
StrokeNeXt-small	0.987	0.987	0.987	0.987	0.999	0.999	0.986	0.973	0.013	0.049	0.003	349	1.747	17.474	100.8	0.096
StrokeNeXt-base	0.988	0.988	0.988	0.988	1.000	1.000	0.986	0.973	0.011	0.054	0.005	219	2.641	30.853	178.5	0.101
StrokeNeXt-large	0.987	0.987	0.985	0.986	0.999	0.999	0.986	0.973	0.015	0.061	0.009	114	4.950	68.940	399.9	0.122

Table 7: Performance of the different StrokeNeXt variants on stroke type classification (ischemia vs. hemorrhage).

Method	Accuracy	Precision	Recall	F1-score	AUROC	AUPRC	Balanced Acc.	MCC	Brier score	ECE	Latency (s)	Throughput (img/s)	Peak GPU (GB)	FLOPs (G)	Params (M)	Train. time (h)
MobileNetv2 [ 26 ]	0.812	0.813	0.811	0.811	0.919	0.919	0.811	0.624	0.122	0.083	0.001	2341	0.868	0.319	2.2	0.020
VGG16 [ 16 ]	0.879	0.879	0.879	0.879	0.951	0.956	0.879	0.758	0.104	0.124	0.001	1434	4.020	15.519	134.3	0.020
ResNet50 [ 12 ]	0.852	0.854	0.852	0.852	0.918	0.924	0.851	0.706	0.133	0.136	0.001	1900	1.034	4.130	23.5	0.024
ResNet152 [ 12 ]	0.865	0.873	0.865	0.865	0.949	0.936	0.864	0.738	0.101	0.130	0.001	1217	1.298	11.601	58.2	0.025
Swin Transformer [ 17 ]	0.825	0.825	0.825	0.825	0.905	0.911	0.825	0.650	0.132	0.084	0.003	335	2.196	10.550	87.1	0.029
ConvNeXt-base [ 18 ]	0.848	0.848	0.848	0.848	0.926	0.930	0.848	0.695	0.130	0.142	0.002	441	1.947	15.425	87.6	0.026

Table 8: Performance of StrokeNeXt on stroke type classification (ischemia vs. hemorrhage) compared with other methods.

Method A	Method B	A✓B✗	B✓A✗	$\chi^{2}$	p-value
StrokeNeXt-base	VGG16 [ 16 ]	25	1	20.346	$<$ 0.0001
StrokeNeXt-base	MobileNetv2 [ 26 ]	40	1	35.219	$<$ 0.0001
StrokeNeXt-base	ResNet50 [ 12 ]	31	1	26.281	$<$ 0.0001
StrokeNeXt-base	ResNet152 [ 12 ]	29	2	21.807	$<$ 0.0003
StrokeNeXt-base	ConvNeXt-base [ 18 ]	32	1	27.272	$<$ 0.0001
StrokeNeXt-base	Swin Transformer [ 17 ]	37	1	32.236	$<$ 0.0001

Table 9: Results of the McNemar test comparing our best model with other methods on stroke type classification (ischemia vs. hemorrhage).

Method	Ischemia		Hemorrhage
	Sensitivity	Specificity	Sensitivity	Specificity
MobileNetv2 [ 26 ]	0.773	0.850	0.850	0.772
VGG16 [ 16 ]	0.873	0.885	0.885	0.873
ResNet50 [ 12 ]	0.809	0.894	0.894	0.809
ResNet152 [ 12 ]	0.790	0.938	0.938	0.790
Swin Transformer [ 17 ]	0.818	0.832	0.832	0.818

Table 10: Per-class performance of StrokeNeXt on troke type classification (ischemia vs. hemorrhage) compared to other methods.

Figure 6: Confusion matrices comparison between StrokeNeXt and other models on stroke type classification (ischemia vs. hemorrhage).

Method	Accuracy	Precision	Recall	F1-score
P-CNN-W [ 11 ]	0.975	0.975	0.975	0.975
Random Forest [ 4 ]	0.959	0.944	0.961	0.954
Enhanced-CNN [ 27 ]	0.952	0.949	0.972	0.960
P-CNN [ 11 ]	0.983	0.983	0.983	0.983
3D-CNN [ 19 ]	0.920	0.940	0.840	0.880
D-UNet [ 29 ]	0.985	0.986	0.985	0.985

Table 11: Comparison of StrokeNeXt on stroke type classification (ischemia vs. hemorrhage) with other methods from the literature.

Explore similar work

Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder
Feb 28, 2026Adam Marcus, Paul Bentley, Daniel RueckertClinical Outcome Prediction Clinical Prediction
Imperial College London, London, UK · Technische Universität München, München, Germany
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy
Aug 25, 2026Md Shahriar SajidClinical Prediction Clinical Risk Prediction
Department of Electrical & Computer Engineering Rajshahi University of Engineering & Technology
FSB-Net: Frequency-Spatial Boundary Network for Brain Stroke Lesion Segmentation in Non-Contrast CT
Jul 23, 2026Linke Fan, Xianglong Li, Huixin Huang +1Image Segmentation Medical Image Segmentation
Tongji University · Shanghai, China · University of Malaya +5

Feb 28, 2026J/K move · Enter open · S save

Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

Adam Marcus, Paul Bentley, Daniel Rueckert

Imperial College London, London, UK · Technische Universität München, München, Germany

Clinical Outcome Prediction Clinical Prediction Medical Image Representation Learning Diffusion Models Longitudinal Medical Image Analysis

Open paper AskPDF arXiv

Stroke is a major cause of death and disability worldwide. Accurate outcome and evolution prediction has the potential to revolutionize stroke care by individualizing clinical decision-making leading to better outcomes. However, despite a plethora of attempts and the rich data provided by neuroimaging, modelling the ultimate fate of brain tissue remains a challenging task. In this work, we apply recent ideas in the field of diffusion probabilistic models to generate a self-supervised semantically meaningful stroke representation from Computed Tomography (CT) images. We then improve this representation by extending the method to accommodate longitudinal images and the time from stroke onset. The effectiveness of our approach is evaluated on a dataset consisting of 5,824 CT images from 3,573 patients across two medical centers with minimal labels. Comparative experiments show that our method achieves the best performance for predicting next-day severity and functional outcome at discharge.

Abstract

Explore similar work

Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnostic Accuracy

FSB-Net: Frequency-Spatial Boundary Network for Brain Stroke Lesion Segmentation in Non-Contrast CT