Deep learning frameworks utilizing convolutional neural networks (CNNs) have frequently been used for brain age prediction and have achieved outstanding performance. Nevertheless, deep learning remains a black box as it is hard to interpret which brain parts contribute significantly to the predictions. To tackle this challenge, we first trained a lightweight, fully CNN model for brain age estimation on a large sample data set (N = 3054, age range = [8,80 years]) and tested it on an independent data set (N = 555, age range = [8,80 years]). We then developed an interpretable scheme combining network occlusion sensitivity analysis (NOSA) with a fine-grained human brain atlas to uncover the learned invariance of the model. Our findings show that the dorsolateral, dorsomedial frontal cortex, anterior cingulate cortex, and thalamus had the highest contributions to age prediction across the lifespan. More interestingly, we observed that different regions showed divergent patterns in their predictions for specific age groups and that the bilateral hemispheres contributed differently to the predictions. Regions in the frontal lobe were essential predictors in both the developmental and aging stages, with the thalamus remaining relatively stable and saliently correlated with other regional changes throughout the lifespan. The lateral and medial temporal brain regions gradually became involved during the aging phase. At the network level, the frontoparietal and the default mode networks show an inverted U-shape contribution from the developmental to the aging stages. The framework could identify regional contributions to the brain age prediction model, which could help increase the model interpretability when serving as an aging biomarker.

Breast cancer is one of the most prevalent cancers affecting women worldwide. Early detection and treatment are crucial in significantly reducing mortality rates Microcalcifications (MCs) are of particular importance among the various breast lesions. These tiny calcium deposits within breast tissue are present in approximately 30% of malignant tumors and can serve as critical indirect indicators of early-stage breast cancer. Three or more MCs within an area of 1 cm² are considered a Microcalcification Cluster (MCC) and assigned a BI-RADS category 4, indicating a suspicion of malignancy. Mammography is the most used technique for breast cancer detection. Approximately one in two mammograms showing MCCs is confirmed as cancerous through biopsy. MCCs are challenging to detect, even for experienced radiologists, underscoring the need for computer-aided detection tools such as Convolutional Neural Networks (CNNs). CNNs require large amounts of domain-specific data with consistent resolutions for effective training. However, most publicly available mammogram datasets either lack resolution information or are compiled from heterogeneous sources. Additionally, MCCs are often either unlabeled or sparsely represented in these datasets, limiting their utility for training CNNs. In this dataset, we present the MEXBreast, an annotated MCCs Mexican digital mammogram database, containing images from resolutions of 50, 70, and 100 microns. MEXBreast aims to support the training, validation, and testing of deep learning CNNs.

The existing assessment of adjacent segment degeneration (ASD) risk after lumbar fusion surgery focuses on a single type of clinical information or imaging manifestations. In the early stages, it is difficult to show obvious degeneration characteristics, and the patients' true risks cannot be fully revealed. The evaluation results based on imaging ignore the clinical symptoms and changes in quality of life of patients, limiting the understanding of the natural process of ASD and the comprehensive assessment of its risk factors, and hindering the development of effective prevention strategies. To improve the quality of postoperative management and effectively identify the characteristics of ASD, this paper studies the risk assessment of ASD after lumbar fusion surgery by combining the artificial intelligence (AI) medical image-aided diagnosis system. First, the collaborative attention mechanism is adopted to start with the extraction of single-modal features and fuse the multi-modal features of computed tomography (CT) and magnetic resonance imaging (MRI) images. Then, the similarity matrix is weighted to achieve the complementarity of multi-modal information, and the stability of feature extraction is improved through the residual network structure. Finally, the fully connected network (FCN) is combined with the multi-task learning framework to provide a more comprehensive assessment of the risk of ASD. The experimental analysis results show that compared with three advanced models, three dimensional-convolutional neural networks (3D-CNN), U-Net++, and deep residual networks (DRN), the accuracy of the model in this paper is 3.82 %, 6.17 %, and 6.68 % higher respectively; the precision is 0.56 %, 1.09 %, and 4.01 % higher respectively; the recall is 3.41 %, 4.85 %, and 5.79 % higher respectively. The conclusion shows that the AI medical image-aided diagnosis system can help to accurately identify the characteristics of ASD and effectively assess the risks after lumbar fusion surgery.

Schizophrenia (SCH) is a complex neurodevelopmental disorder, whose pathogenesis is not fully elucidated. This article aims to reveal disease-specific brain structural and functional changes and their potential genetic basis by analyzing the characteristics of brain magnetic resonance imaging (MRI) in SCH patients and related gene expression patterns. Differentially expressed genes (DEGs) between SCH and healthy control (NC) groups in the GSE48072 dataset were identified and functionally analyzed, and a protein-protein interaction (PPI) network was fabricated to screen for core genes (CGs). Meanwhile, MRI data from the COBRE, the Human Connectome Project (HCP), the 1000 Functional Connectomes Project (FCP), and the Consortium for Reliability and Reproducibility (CoRR) were utilized to explore differences in brain activity patterns between SCH patients and NC group using a 3D deep aggregation network (3D DANet) machine learning approach. A correlation analysis was performed between the identified CGs and MRI imaging characteristics. 82 DEGs were collected from the GSE48072 dataset, primarily involved in cytotoxic granules, growth factor binding, and graft-versus-host disease pathways. The construction of the PPI network revealed KLRD1, KLRF1, CD244, GZMH, GZMA, GZMB, PRF1, and SLAMF6 as CGs. SCH patients exhibited relatively enhanced activity patterns in the frontoparietal attention network (FAN) and default mode network (DMN) across four datasets, while showing a trend of weakening in most other networks. The 3D DANet demonstrated higher accuracy, specificity, and sensitivity in brain image classification. The correlation between enhancement of the DMN and genetic abnormalities was the strongest, followed by the enhancement of the frontal and parietal attention networks. In contrast, the correlation between the weakening of the sensory-motor network and occipital network and genetic abnormalities was relatively weak. The strongest correlation was observed between MRI characteristics and the KLRD1 and CD244 genes. The granzyme-mediated programmed cell death signaling pathway is related to pathogenesis of SCH, and CD244 may serve as potential biological markers for diagnosing SCH. The correlation between enhancement of the DMN and genetic abnormalities was the strongest, followed by the enhancement of the frontal and parietal attention networks. In contrast, the correlation between weakening of the sensory-motor network and occipital network and genetic abnormalities was relatively weak. Additionally, the strongest correlation was observed between MRI features and the KLRD1 and CD244 genes. The use of the 3D DANet method has improved the detection precision of brain structural and functional changes in SCH patients, providing a new perspective for understanding the biological basis of the disease.

Vision Transformers (ViTs) suffer from high parameter complexity because they rely on Multi-layer Perceptrons (MLPs) for nonlinear representation. This issue is particularly challenging in medical image analysis, where labeled data is limited, leading to inadequate feature representation. Existing methods have attempted to optimize either the patch embedding stage or the non-embedding stage of ViTs. Still, they have struggled to balance effective modeling, parameter complexity, and data availability. Recently, the Kolmogorov-Arnold Network (KAN) was introduced as an alternative to MLPs, offering a potential solution to the large parameter issue in ViTs. However, KAN cannot be directly integrated into ViT due to challenges such as handling 2D structured data and dimensionality catastrophe. To solve this problem, we propose MedKAFormer, the first ViT model to incorporate the Kolmogorov-Arnold (KA) theorem for medical image representation. It includes a Dynamic Kolmogorov-Arnold Convolution (DKAC) layer for flexible nonlinear modeling in the patch embedding stage. Additionally, it introduces a Nonlinear Sparse Token Mixer (NSTM) and a Nonlinear Dynamic Filter (NDF) in the non-embedding stage. These components provide comprehensive nonlinear representation while reducing model overfitting. MedKAFormer reduces parameter complexity by 85.61% compared to ViT-Base and achieves competitive results on 14 medical datasets across various imaging modalities and structures.

Prognostication of patients with acute disorders of consciousness is imprecise but more accurate technology-supported predictions, such as cognitive motor dissociation (CMD), are emerging. CMD refers to the detection of willful brain activation following motor commands using functional magnetic resonance imaging or machine learning-supported analysis of the electroencephalogram in clinically unresponsive patients. CMD is associated with long-term recovery, but acceptance by surrogates and health care professionals is uncertain. The objective of this study was to determine receptiveness for CMD to inform goals of care (GoC) decisions and research participation among health care professionals and surrogates of behaviorally unresponsive patients. This was a two-center study of surrogates of and health care professionals caring for unconscious patients with severe neurological injury who were enrolled in two prospective US-based studies. Participants completed a 13-item survey to assess demographics, religiosity, minimal acceptable level of recovery, enthusiasm for research participation, and receptiveness for CMD to support GoC decisions. Completed surveys were obtained from 196 participants (133 health care professionals and 63 surrogates). Across all respondents, 93% indicated that they would want their loved one or the patient they cared for to participate in a research study that supports recovery of consciousness if CMD were detected, compared to 58% if CMD were not detected. Health care professionals were more likely than surrogates to change GoC with a positive (78% vs. 59%, p = 0.005) or negative (83% vs. 59%, p = 0.0002) CMD result. Participants who reported religion was the most important part of their life were least likely to change GoC with or without CMD. Participants who identified as Black (odds ratio [OR] 0.12, 95% confidence interval [CI] 0.04-0.36) or Hispanic/Latino (OR 0.39, 95% CI 0.2-0.75) and those for whom religion was the most important part of their life (OR 0.18, 95% CI 0.05-0.64) were more likely to accept a lower minimum level of recovery. Technology-supported prognostication and enthusiasm for clinical trial participation was supported across a diverse spectrum of health care professionals and surrogate decision-makers. Education for surrogates and health care professionals should accompany integration of technology-supported prognostication.

The application of machine learning in medicine and healthcare has led to the creation of numerous diagnostic and prognostic models. However, despite their success, current approaches generally issue predictions using data from a single modality. This stands in stark contrast with clinician decision-making which employs diverse information from multiple sources. While several multimodal machine learning approaches exist, significant challenges in developing multimodal systems remain that are hindering clinical adoption. In this paper, we introduce a multimodal framework, AutoPrognosis-M, that enables the integration of structured clinical (tabular) data and medical imaging using automated machine learning. AutoPrognosis-M incorporates 17 imaging models, including convolutional neural networks and vision transformers, and three distinct multimodal fusion strategies. In an illustrative application using a multimodal skin lesion dataset, we highlight the importance of multimodal machine learning and the power of combining multiple fusion strategies using ensemble learning. We have open-sourced our framework as a tool for the community and hope it will accelerate the uptake of multimodal machine learning in healthcare and spur further innovation.

Identifying patients likely to regain consciousness early on is a challenge. The assessment of consciousness levels and the prediction of wakefulness probabilities are facilitated by ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET). This study aimed to develop a prognostic model for predicting 1-year postinjury outcomes in prolonged disorders of consciousness (DoC) using ¹⁸F-FDG PET alongside clinical behavioral scores. Eighty-seven patients with prolonged DoC newly diagnosed with behavioral Coma Recovery Scale-Revised (CRS-R) scores and ¹⁸F-FDG PET/computed tomography (18F-FDG PET/CT) scans were included. PET images were normalized by the cerebellum and extracerebral tissue, respectively. Images were divided into training and independent test sets at a ratio of 5:1. Image-based classification was conducted using the DenseNet121 network, whereas tabular-based deep learning was employed to train depth features extracted from imaging models and behavioral CRS-R scores. The performance of the models was assessed and compared using the McNemar test. Among the 87 patients with DoC who received routine treatments, 52 patients showed recovery of consciousness, whereas 35 did not. The classification of the standardized uptake value ratio by extracerebral tissue model demonstrated a higher specificity and lower sensitivity in predicting consciousness recovery than the classification of the standardized uptake value ratio by cerebellum model. With area under the curve values of 0.751 ± 0.093 and 0.412 ± 0.104 on the test sets, respectively, the difference is not statistically significant (P = 0.73). The combination of standardized uptake value ratio by extracerebral tissue and computed tomography depth features with behavioral CRS-R scores yielded the highest classification accuracy, with area under the curve values of 0.950 ± 0.027 and 0.933 ± 0.015 on the training and test sets, respectively, outperforming any individual mode. In this preliminary study, a multimodal prognostic model based on ¹⁸F-FDG PET extracerebral normalization and behavioral CRS-R scores facilitated the prediction of recovery in DoC.

Motion artifacts compromise the quality of magnetic resonance imaging (MRI) and pose challenges to achieving diagnostic outcomes and image-guided therapies. In recent years, supervised deep learning approaches have emerged as successful solutions for motion artifact reduction (MAR). One disadvantage of these methods is their dependency on acquiring paired sets of motion artifact-corrupted (MA-corrupted) and motion artifact-free (MA-free) MR images for training purposes. Obtaining such image pairs is difficult and therefore limits the application of supervised training. In this paper, we propose a novel UNsupervised Abnormality Extraction Network (UNAEN) to alleviate this problem. Our network is capable of working with unpaired MA-corrupted and MA-free images. It converts the MA-corrupted images to MA-reduced images by extracting abnormalities from the MA-corrupted images using a proposed artifact extractor, which intercepts the residual artifact maps from the MA-corrupted MR images explicitly, and a reconstructor to restore the original input from the MA-reduced images. The performance of UNAEN was assessed by experimenting with various publicly available MRI datasets and comparing them with state-of-the-art methods. The quantitative evaluation demonstrates the superiority of UNAEN over alternative MAR methods and visually exhibits fewer residual artifacts. Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies.

Breast cancer is a devastating disease that affects women worldwide, and computer-aided algorithms have shown potential in automating cancer diagnosis. Recently Generative Artificial Intelligence (GenAI) opens new possibilities for addressing the challenges of labeled data scarcity and accurate prediction in critical applications. However, a lack of diversity, as well as unrealistic and unreliable data, have a detrimental impact on performance. Therefore, this study proposes an augmentation scheme to address the scarcity of labeled data and data imbalance in medical datasets. This approach integrates the concepts of the Gaussian-Laplacian pyramid and pyramid blending with similarity measures. In order to maintain the structural properties of images and capture inter-variability of patient images of the same category similarity-metric-based intermixing has been introduced. It helps to maintain the overall quality and integrity of the dataset. Subsequently, deep learning approach with significant modification, that leverages transfer learning through the usage of concatenated pre-trained models is applied to classify breast cancer histopathological images. The effectiveness of the proposal, including the impact of data augmentation, is demonstrated through a detailed analysis of three different medical datasets, showing significant performance improvement over baseline models. The proposal has the potential to contribute to the development of more accurate and reliable approach for breast cancer diagnosis.