Background: The ability to accurately detect ischemic stroke and predict its neurological recovery is of great clinical value. This study intended to evaluate the performance of whole-brain dynamic radiomics features (DRF) for ischemic stroke detection, neurological impairment assessment, and outcome prediction. Methods: The supervised feature selection (Lasso) and unsupervised feature-selection methods (five-feature dimension-reduction algorithms) were used to generate four experimental groups with DRF in different combinations. Ten machine learning models were used to evaluate their performance by ten-fold cross-validation. Results: In experimental group_A, the best AUCs (0.873 for stroke detection, 0.795 for NIHSS assessment, and 0.818 for outcome prediction) were obtained by outstanding DRF selected by Lasso, and the performance of significant DRF was better than the five-feature dimension-reduction algorithms. The selected outstanding dimension-reduction DRF in experimental group_C obtained a better AUC than dimension-reduction DRF in experimental group_A but were inferior to the outstanding DRF in experimental group_A. When combining the outstanding DRF with each dimension-reduction DRF (experimental group_B), the performance can be improved in ischemic stroke detection (best AUC = 0.899) and NIHSS assessment (best AUC = 0.835) but failed in outcome prediction (best AUC = 0.806). The performance can be further improved when combining outstanding DRF with outstanding dimension-reduction DRF (experimental group_D), achieving the highest AUC scores in all three evaluation items (0.925 for stroke detection, 0.853 for NIHSS assessment, and 0.828 for outcome prediction). By the method in this study, comparing the best AUC of F_t-test in experimental group_A and the best_AUC in experimental group_D, the AUC in stroke detection increased by 19.4% (from 0.731 to 0.925), the AUC in NIHSS assessment increased by 20.1% (from 0.652 to 0.853), and the AUC in prognosis prediction increased by 14.9% (from 0.679 to 0.828). This study provided a potential clinical tool for detailed clinical diagnosis and outcome prediction before treatment.

Deep learning (DL) has emerged as a powerful image processing technique that learns the features of the data and produces state-of-the-art prediction results. The decade from 2010 to 2020 is a real revival of DL, which has come to a turning point in history. In image classification, many deep learning networks have been proposed by scholars, and each of them has its own strengthness. It is very important and efficient for the researchers and the developers to know the performance of these networks, especially for the beginners, so as to give them a transplant instruction by an objective evaluation index. In this paper, we constructed different data sets from three aspects, texture, shape, and measurement scale to test the performance of nine mainstream image classification networks. Cross-contrast experiments were performed to analyze the sensitivity of factors which influence the stability of image classification networks. Experimental results shown that in the 27 image datasets generated by the three image factors, the classification performance of AlexNet, GoogleNet, VggNet, and DenseNet is better. The perfomance comparison of these networks are showed and discussed in details. Code and pretrained models are available at https://github.com/liqiang12689/image-classification-finall .

Objectives: This study proposed an outcome prediction method to improve the accuracy and efficacy of ischemic stroke outcome prediction based on the diversity of whole brain features, without using basic information about patients and image features in lesions.Design: In this study, we directly extracted dynamic radiomics features (DRFs) from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) and further extracted static radiomics features (SRFs) and static encoding features (SEFs) from the minimum intensity projection (MinIP) map, which was generated from the time dimension of DSC-PWI images. After selecting whole brain features F_fuse from the combinations of DRFs, SRFs, and SEFs by the Lasso algorithm, various machine and deep learning models were used to evaluate the role of F_fuse in predicting stroke outcomes.Results: The experimental results show that the feature F_fuse generated from DRFs, SRFs, and SEFs (Resnet 18) outperformed other single and combination features and achieved the best mean score of 0.971 both on machine learning models and deep learning models and the 95% CI were (0.703, 0.877) and (0.92, 0.983), respectively. Besides, the deep learning models generally performed better than the machine learning models.Conclusion: The method used in our study can achieve an accurate assessment of stroke outcomes without segmentation of ischemic lesions, which is of great significance for rapid, efficient, and accurate clinical stroke treatment.

Introduction: In neurological diagnostics, accurate detection and segmentation of brain lesions is crucial. Identifying these lesions is challenging due to its complex morphology, especially when using traditional methods. Conventional methods are either computationally demanding with a marginal impact/enhancement or sacrifice fine details for computational efficiency. Therefore, balancing performance and precision in compute-intensive medical imaging remains a hot research topic.Methods: We introduce a novel encoder-decoder network architecture named the Adaptive Feature Medical Segmentation Network (AFMS-Net) with two encoder variants: the Single Adaptive Encoder Block (SAEB) and the Dual Adaptive Encoder Block (DAEB). A squeeze-and-excite mechanism is employed in SAEB to identify significant data while disregarding peripheral details. This approach is best suited for scenarios requiring quick and efficient segmentation, with an emphasis on identifying key lesion areas. In contrast, the DAEB utilizes an advanced channel spatial attention strategy for fine-grained delineation and multiple-class classifications. Additionally, both architectures incorporate a Segmentation Path (SegPath) module between the encoder and decoder, refining segmentation, enhancing feature extraction, and improving model performance and stability.Results: AFMS-Net demonstrates exceptional performance across several notable datasets, including BRATs 2021, ATLAS 2021, and ISLES 2022. Its design aims to construct a lightweight architecture capable of handling complex segmentation challenges with high precision.Discussion: The proposed AFMS-Net addresses the critical balance issue between performance and computational efficiency in the segmentation of brain lesions. By introducing two tailored encoder variants, the network adapts to varying requirements of speed and feature. This approach not only advances the state-of-the-art in lesion segmentation but also provides a scalable framework for future research in medical image processing.

Chronic obstructive pulmonary disease (COPD) is a preventable, treatable, progressive chronic disease characterized by persistent airflow limitation. Patients with COPD deserve special consideration regarding treatment in this fragile population for preclinical health management. Therefore, this paper proposes a novel lung radiomics combination vector generated by a generalized linear model (GLM) and Lasso algorithm for COPD stage classification based on an auto-metric graph neural network (AMGNN) with a meta-learning strategy. Firstly, the parenchyma images were segmented from chest high-resolution computed tomography (HRCT) images by ResU-Net. Second, lung radiomics features are extracted from the parenchyma images by PyRadiomics. Third, a novel lung radiomics combination vector (3 + 106) is constructed by the GLM and Lasso algorithm for determining the radiomics risk factors (K = 3) and radiomics node features (d = 106). Last, the COPD stage is classified based on the AMGNN. The results show that compared with the convolutional neural networks and machine learning models, the AMGNN based on constructed novel lung radiomics combination vector performs best, achieving an accuracy of 0.943, precision of 0.946, recall of 0.943, F1-score of 0.943, and ACU of 0.984. Furthermore, it is found that our method is effective for COPD stage classification.