Intraoperative ultrasound (ioUS) is a valuable tool in brain tumor surgery due to its versatility, affordability, and seamless integration into the surgical workflow. However, its adoption remains limited, primarily because of the challenges associated with image interpretation and the steep learning curve required for effective use. This study aimed to enhance the interpretability of ioUS images by developing a real-time brain tumor detection system deployable in the operating room. We collected 2D ioUS images from the BraTioUS and ReMIND datasets, annotated with expert-refined tumor labels. Using the YOLO11 architecture and its variants, we trained object detection models to identify brain tumors. The dataset included 1732 images from 192 patients, divided into training, validation, and test sets. Data augmentation expanded the training set to 11,570 images. In the test dataset, YOLO11s achieved the best balance of precision and computational efficiency, with a mAP@50 of 0.95, mAP@50-95 of 0.65, and a processing speed of 34.16 frames per second. The proposed solution was prospectively validated in a cohort of 20 consecutively operated patients diagnosed with brain tumors. Neurosurgeons confirmed its seamless integration into the surgical workflow, with real-time predictions accurately delineating tumor regions. These findings highlight the potential of real-time object detection algorithms to enhance ioUS-guided brain tumor surgery, addressing key challenges in interpretation and providing a foundation for future development of computer vision-based tools for neuro-oncological surgery.

This study aims to develop a deep learning framework that leverages modality imputation and subregion segmentation to improve grading accuracy in high-grade gliomas. A retrospective analysis was conducted using data from 1,251 patients in the BraTS2021 dataset as the main cohort and 181 clinical cases collected from a medical center between April 2013 and June 2018 (51 years ± 17; 104 males) as the external test set. We propose a PatchGAN-based modality imputation network with an Aggregated Residual Transformer (ART) module combining Transformer self-attention and CNN feature extraction via residual links, paired with a U-Net variant for segmentation. Generative accuracy used PSNR and SSIM for modality conversions, while segmentation performance was measured with DSC and HD95 across necrotic core (NCR), edema (ED), and enhancing tumor (ET) regions. Senior radiologists conducted a comprehensive Likert-based assessment, with diagnostic accuracy evaluated by AUC. Statistical analysis was performed using the Wilcoxon signed-rank test and the DeLong test. The best source-target modality pairs for imputation were T1 to T1ce and T1ce to T2 (p < 0.001). In subregion segmentation, the overall DSC was 0.878 and HD95 was 19.491, with the ET region showing the highest segmentation accuracy (DSC: 0.877, HD95: 12.149). Clinical validation revealed an improvement in grading accuracy by the senior radiologist, with the AUC increasing from 0.718 to 0.913 (P < 0.001) when using the combined imputation and segmentation models. The proposed deep learning framework improves high-grade glioma grading by modality imputation and segmentation, aiding the senior radiologist and offering potential to advance clinical decision-making.

This study aims to develop an imaging-based machine learning model for evaluating the severity of ischemic stroke in the middle cerebral artery (MCA) territory. This retrospective study included 173 patients diagnosed with acute ischemic stroke (AIS) in the MCA territory from two centers, with 114 in the training set and 59 in the test set. In the training set, spearman correlation coefficient and multiple linear regression were utilized to analyze the correlation between the CT imaging features of patients prior to treatment and the national institutes of health stroke scale (NIHSS) score. Subsequently, an optimal machine learning algorithm was determined by comparing seven different algorithms. This algorithm was then used to construct a imaging-based prediction model for stroke severity (severe and non-severe). Finally, the model was validated in the test set. After conducting correlation analysis, CT imaging features such as infarction side, basal ganglia area involvement, dense MCA sign, and infarction volume were found to be independently associated with NIHSS score (P < 0.05). The Logistic Regression algorithm was determined to be the optimal method for constructing the prediction model for stroke severity. The area under the receiver operating characteristic curve of the model in both the training set and test set were 0.815 (95% CI: 0.736-0.893) and 0.780 (95% CI: 0.646-0.914), respectively, with accuracies of 0.772 and 0.814. Imaging-based machine learning model can effectively evaluate the severity (severe or non-severe) of ischemic stroke in the MCA territory. Not applicable.

To determine whether a machine learning model of voxel level [¹⁸f]fluorodeoxyglucose positron emission tomography (PET) data could predict progressive supranuclear palsy (PSP) pathology, as well as outperform currently available biomarkers. One hundred and thirty-seven autopsied patients with PSP (n = 42) and other neurodegenerative diseases (n = 95) who underwent antemortem [¹⁸f]fluorodeoxyglucose PET and 3.0 Tesla magnetic resonance imaging (MRI) scans were analyzed. A linear support vector machine was applied to differentiate pathological groups with sensitivity analyses performed to assess the influence of voxel size and region removal. A radial basis function was also prepared to create a secondary model using the most important voxels. The models were optimized on the main dataset (n = 104), and their performance was compared with the magnetic resonance parkinsonism index measured on MRI in the independent test dataset (n = 33). The model had the highest accuracy (0.91) and F-score (0.86) when voxel size was 6mm. In this optimized model, important voxels for differentiating the groups were observed in the thalamus, midbrain, and cerebellar dentate. The secondary models found the combination of thalamus and dentate to have the highest accuracy (0.89) and F-score (0.81). The optimized secondary model showed the highest accuracy (0.91) and F-scores (0.86) in the test dataset and outperformed the magnetic resonance parkinsonism index (0.81 and 0.70, respectively). The results suggest that glucose hypometabolism in the thalamus and cerebellar dentate have the highest potential for predicting PSP pathology. Our optimized machine learning model outperformed the best currently available biomarker to predict PSP pathology. ANN NEUROL 2025.

Periventricular white matter injury (PWMI) is the most frequent magnetic resonance imaging (MRI) finding in infants with Cerebral Palsy (CP). We aim to detect CP and identify subtle, sparse PWMI lesions in infants under two years of age with immature brain structures. Based on the characteristic that the responsible lesions are located within five target regions, we first construct a multi-modal dataset including 243 cases with the mask annotations of five target regions for delineating anatomical structures on T1-Weighted Imaging (T1WI) images, masks for lesions on T2-Weighted Imaging (T2WI) images, and categories (CP or Non-CP). Furthermore, we develop a bidirectional projection-based multi-modal fusion transformer (BiP-MFT), incorporating a Bidirectional Projection Fusion Module (BPFM) for integrating the features between five target regions on T1WI images and lesions on T2WI images. Our BiP-MFT achieves subject-level classification accuracy of 0.90, specificity of 0.87, and sensitivity of 0.94. It surpasses the best results of nine comparative methods, with 0.10, 0.08, and 0.09 improvements in classification accuracy, specificity and sensitivity respectively. Our BPFM outperforms eight compared feature fusion strategies using Transformer and U-Net backbones on our dataset. Ablation studies on the dataset annotations and model components justify the effectiveness of our annotation method and the model rationality. The proposed dataset and codes are available at https://github.com/Kai-Qi/BiP-MFT.

Basal ganglia intracranial hemorrhage (bgICH) morphology is associated with postoperative functional outcomes. We hypothesized that bgICH spatial representation modeling could be automated for functional outcome prediction after minimally invasive surgical (MIS) evacuation. A training set of 678 computed tomography head and computed tomography angiography images from 63 patients were used to train key-point detection and instance segmentation convolutional neural network-based models for anatomic landmark identification and bgICH segmentation. Anatomic landmarks included the bilateral orbital rims at the globe's maximum diameter and the posterior-most aspect of the tentorial incisura, which were used to define a universal stereotactic reference frame across patients. Convolutional neural network models were tested using volumetric computed tomography head/computed tomography angiography scans from 45 patients who underwent MIS bgICH evacuation with recorded modified Rankin Scales within one year after surgery. bgICH volumes were highly correlated (R2 = 0.95, P < .001) between manual (median 39-mL) and automatic (median 38-mL) segmentation methods. The absolute median difference between groups was 2-mL (IQR: 1-6 mL). Median localization accuracy (distance between automated and manually designated coordinate frames) was 4 mm (IQR: 3-6). Landmark coordinates were highly correlated in the x- (medial-lateral), y- (anterior-posterior), and z-axes (rostral-caudal) for all 3 landmarks (R2 range = 0.95-0.99, P < .001 for all). Functional outcome (modified Rankin Scale 4-6) was predicted with similar model performance using automated (area under the receiver operating characteristic curve = 0.81, 95% CI: 0.67-0.94) and manually (area under the receiver operating characteristic curve = 0.84, 95% CI: 0.72-0.96) constructed spatial representation models (P = .173). Computer vision models can accurately replicate bgICH manual segmentation, stereotactic localization, and prognosticate functional outcomes after MIS bgICH evacuation.

Medical image challenges have played a transformative role in advancing the field, catalyzing algorithmic innovation and establishing new performance standards across diverse clinical applications. Image registration, a foundational task in neuroimaging pipelines, has similarly benefited from the Learn2Reg initiative. Building on this foundation, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark designed to assess and advance unsupervised brain MRI registration. Distinct from prior challenges that leveraged anatomical label maps for supervision, LUMIR removes this dependency by providing over 4,000 preprocessed T1-weighted brain MRIs for training without any label maps, encouraging biologically plausible deformation modeling through self-supervision. In addition to evaluating performance on 590 held-out test subjects, LUMIR introduces a rigorous suite of zero-shot generalization tasks, spanning out-of-domain imaging modalities (e.g., FLAIR, T2-weighted, T2*-weighted), disease populations (e.g., Alzheimer's disease), acquisition protocols (e.g., 9.4T MRI), and species (e.g., macaque brains). A total of 1,158 subjects and over 4,000 image pairs were included for evaluation. Performance was assessed using both segmentation-based metrics (Dice coefficient, 95th percentile Hausdorff distance) and landmark-based registration accuracy (target registration error). Across both in-domain and zero-shot tasks, deep learning-based methods consistently achieved state-of-the-art accuracy while producing anatomically plausible deformation fields. The top-performing deep learning-based models demonstrated diffeomorphic properties and inverse consistency, outperforming several leading optimization-based methods, and showing strong robustness to most domain shifts, the exception being a drop in performance on out-of-domain contrasts.

Facial recognition of reconstructed computed tomography (CT) scans poses patient privacy risks, necessitating reliable facial de-identification methods. Current methods obscure sinuses, turbinates, and other anatomy relevant for otolaryngology. We present a facial de-identification method that preserves these structures, along with two automated workflows for large-volume datasets. A total of 20 adult head CTs from the New Mexico Decedent Image Database were included. Using 3D Slicer, a seed-growing technique was performed to label the skin around the face. This label was dilated bidirectionally to form a 6-mm mask that obscures facial features. This technique was then automated using: (1) segmentation propagation that deforms an atlas head CT and corresponding mask to match other scans and (2) a deep learning model (nnU-Net). Accuracy of these methods against manually generated masks was evaluated with Dice scores and modified Hausdorff distances (mHDs). Manual de-identification resulted in facial match rates of 45.0% (zero-fill), 37.5% (deletion), and 32.5% (re-face). Dice scores for automated face masks using segmentation propagation and nnU-Net were 0.667 ± 0.109 and 0.860 ± 0.029, respectively, with mHDs of 4.31 ± 3.04 mm and 1.55 ± 0.71 mm. Match rates after de-identification using segmentation propagation (zero-fill: 42.5%; deletion: 40.0%; re-face: 35.0%) and nnU-Net (zero-fill: 42.5%; deletion: 35.0%; re-face: 30.0%) were comparable to manual masks. We present a simple facial de-identification approach for head CTs, as well as automated methods for large-scale implementation. These techniques show promise for preventing patient identification while preserving underlying sinonasal anatomy, but further studies using live patient photographs are necessary to fully validate its effectiveness.

Image enhancement of the Hypoxic-Ischemic Encephalopathy (HIE) lesion region in neonatal brain MR images is a challenging task due to the diffuse (i.e., multi-focal) nature, small size, and low contrast of the lesions. Classifying the stages of HIE is also difficult because of the unclear boundaries and edges of the lesions, which are dispersedthroughout the brain. Moreover, unclear boundaries and edges are due to chemical shifts, partial volume artifacts, and motion artifacts. Further, voxels may reflect signals from adjacent tissues. Existing algorithms perform poorly in HIE lesion enhancement due to artifacts, voxels, and the diffuse nature of the lesion. In this paper, we propose a Rough Neural Network and Anti-Homomorphic Filter (RNN-AHF) framework for the enhancement of the HIE lesion region. The RNN-AHF framework reduces the pixel dimensionality of the feature space, eliminates unnecessary pixels, and preserves essential pixels for lesion enhancement. The RNN efficiently learns and identifies pixel patterns and facilitates adaptive enhancement based on different weights in the neural network. The proposed RNN-AHF framework operates using optimized neural weights and an optimized training function. The hybridization of optimized weights and the training function enhances the lesion region with high contrast while preserving the boundaries and edges. The proposed RNN-AHF framework achieves a lesion image enhancement and classification accuracy of approximately 93.5%, which is better than traditional algorithms.

This study aimed to determine whether trigeminal neuralgia can be diagnosed using convolutional neural networks (CNNs) based on plain X-ray skull images. A labeled dataset of 166 skull images from patients aged over 16 years with trigeminal neuralgia was compiled, alongside a control dataset of 498 images from patients with unruptured intracranial aneurysms. The images were randomly partitioned into training, validation, and test datasets in a 6:2:2 ratio. Classifier performance was assessed using accuracy and the area under the receiver operating characteristic (AUROC) curve. Gradient-weighted class activation mapping was applied to identify regions of interest. External validation was conducted using a dataset obtained from another institution. The CNN achieved an overall accuracy of 87.2%, with sensitivity and specificity of 0.72 and 0.91, respectively, and an AUROC of 0.90 on the test dataset. In most cases, the sphenoid body and clivus were identified as key areas for predicting trigeminal neuralgia. Validation on the external dataset yielded an accuracy of 71.0%, highlighting the potential of deep learning-based models in distinguishing X-ray skull images of patients with trigeminal neuralgia from those of control individuals. Our preliminary results suggest that plain x-ray can be potentially used as an adjunct to conventional MRI, ideally with CISS sequences, to aid in the clinical diagnosis of TN. Further refinement could establish this approach as a valuable screening tool.