The Irony of Iron: The Element with Diverse Influence on Neurodegenerative Diseases

Iron accumulation in the brain is a common feature of many neurodegenerative diseases. Its involvement spans across the main proteinopathies involving tau, amyloid-beta, alpha-synuclein, and TDP-43. Accumulating evidence supports the contribution of iron in disease pathologies, but the delineation of its pathogenic role is yet challenged by the complex involvement of iron in multiple neurotoxicity mechanisms and evidence supporting a reciprocal influence between accumulation of iron and protein pathology. Here, we review the major proteinopathy-specific observations supporting four distinct hypotheses: (1) iron deposition is a consequence of protein pathology; (2) iron promotes protein pathology; (3) iron protects from or hinders protein pathology; and (4) deposition of iron and protein pathology contribute parallelly to pathogenesis. Iron is an essential element for physiological brain function, requiring a fine balance of its levels. Understanding of disease-related iron accumulation at a more intricate and systemic level is critical for advancements in iron chelation therapies.

EEG analysis in patients with schizophrenia based on microstate semantic modeling method

Introduction

Microstate analysis enables the characterization of quasi-stable scalp potential fields on a sub-second timescale, preserving the temporal dynamics of EEG and spatial information of scalp potential distributions. Owing to its capacity to provide comprehensive pathological insights, it has been widely applied in the investigation of schizophrenia (SCZ). Nevertheless, previous research has primarily concentrated on differences in individual microstate temporal characteristics, neglecting potential distinctions in microstate semantic sequences and not fully considering the issue of the universality of microstate templates between SCZ patients and healthy individuals.

Methods

This study introduced a microstate semantic modeling analysis method aimed at schizophrenia recognition. Firstly, microstate templates corresponding to both SCZ patients and healthy individuals were extracted from resting-state EEG data. The introduction of a dual-template strategy makes a difference in the quality of microstate sequences. Quality features of microstate sequences were then extracted from four dimensions: Correlation, Explanation, Residual, and Dispersion. Subsequently, the concept of microstate semantic features was proposed, decomposing the microstate sequence into continuous sub-sequences. Specific semantic sub-sequences were identified by comparing the time parameters of sub-sequences.

Results

The SCZ recognition test was performed on the public dataset for both the quality features and semantic features of microstate sequences, yielding an impressive accuracy of 97.2%. Furthermore, cross-subject experimental validation was conducted, demonstrating that the method proposed in this paper achieves a recognition rate of 96.4% between different subjects.

Discussion

This research offers valuable insights for the clinical diagnosis of schizophrenia. In the future, further studies will seek to augment the sample size to enhance the effectiveness and reliability of this method.

Characterization of Age-Related and Sex-Related Differences of Relaxation Parameters in the Intervertebral Disc Using MR-Fingerprinting

BACKGROUND

Multiparameter characterization using MR fingerprinting (MRF) can quantify multiple relaxation parameters of intervertebral disc (IVD) simultaneously. These parameters may vary by age and sex.

PURPOSE

To investigate age- and sex-related differences in the relaxation parameters of the IVD of the lumbar spine using a multiparameter MRF technique.

STUDY TYPE

Prospective.

SUBJECTS

17 healthy subjects (8 male; mean age = 34 ± 10 years, range 20-60 years).

FIELD STRENGTH/SEQUENCE

3D-MRF sequence for simultaneous acquisition of proton density, T1 , T2 , and T1ρ maps at 3.0T.

ASSESSMENT

Global mean T1 , T2 , and T1ρ of all lumbar IVDs and mean T1 , T2 , and T1ρ of each individual IVD (L1-L5) were measured. Gray level co-occurrence matrix was used to quantify textural features (median, contrast, correlation, energy, and homogeneity) from T1 , T2 , and T1ρ maps.

STATISTICAL TESTS

Spearman rank correlations (R) evaluated the association between age and T1 , T2 , and T1ρ of IVD. Mann-Whitney U-tests evaluated differences between males and females in T1 , T2 , and T1ρ of IVD. Statistical significance was defined as P-value <0.05.

RESULTS

There was a significant negative correlation between age and global mean values of all IVDs for T1 (R = -0.637), T2 (R = -0.509), and T1ρ (R = -0.726). For individual IVDs, there was a significant negative correlation between age and mean T1 at all IVD segments (R range = -0.530 to -0.708), between age and mean T2 at L2-L3, L3-L4, and L4-L5 (R range = -0.493 to 0.640), and between age and mean T1ρ at all segments except L1-L2 (R range = -0.632 to -0.763). There were no significant differences between sexes in global mean T1 , T2, and T1ρ (P-value = 0.23-0.76) The texture features with the highest significant correlations with age for all IVDs were global T1ρ mean (R = -0.726), T1 energy (R = -0.681), and T1 contrast (R = 0.709).

CONCLUSION

This study showed that the 3D-MRF technique has potential to characterize age-related differences in T1 , T2, or T1ρ of IVD in healthy subjects.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 1.

Targeting the organelle for radiosensitization in cancer radiotherapy

Radiotherapy is a well-established cytotoxic therapy for local solid cancers, utilizing high-energy ionizing radiation to destroy cancer cells. However, this method has several limitations, including low radiation energy deposition, severe damage to surrounding normal cells, and high tumor resistance to radiation. Among various radiotherapy methods, boron neutron capture therapy (BNCT) has emerged as a principal approach to improve the therapeutic ratio of malignancies and reduce lethality to surrounding normal tissue, but it remains deficient in terms of insufficient boron accumulation as well as short retention time, which limits the curative effect. Recently, a series of radiosensitizers that can selectively accumulate in specific organelles of cancer cells have been developed to precisely target radiotherapy, thereby reducing side effects of normal tissue damage, overcoming radioresistance, and improving radiosensitivity. In this review, we mainly focus on the field of nanomedicine-based cancer radiotherapy and discuss the organelle-targeted radiosensitizers, specifically including nucleus, mitochondria, endoplasmic reticulum and lysosomes. Furthermore, the organelle-targeted boron carriers used in BNCT are particularly presented. Through demonstrating recent developments in organelle-targeted radiosensitization, we hope to provide insight into the design of organelle-targeted radiosensitizers for clinical cancer treatment.

Weighting the structural connectome: Exploring its impact on network properties and predicting cognitive performance in the human brain

Brain function does not emerge from isolated activity, but rather from the interactions and exchanges between neural elements that form a network known as the connectome. The human connectome consists of structural and functional aspects. The structural connectome (SC) represents the anatomical connections, and the functional connectome represents the resulting dynamics that emerge from this arrangement of structures. As there are different ways of weighting these connections, it is important to consider how such different approaches impact study conclusions. Here, we propose that different weighted connectomes result in varied network properties, and while neither superior the other, selection might affect interpretation and conclusions in different study cases. We present three different weighting models, namely, number of streamlines (NOS), fractional anisotropy (FA), and axon diameter distribution (ADD), to demonstrate these differences. The later, is extracted using recently published AxSI method and is first compared to commonly used weighting methods. Moreover, we explore the functional relevance of each weighted SC, using the Human Connectome Project (HCP) database. By analyzing intelligence-related data, we develop a predictive model for cognitive performance based on graph properties and the National Institutes of Health (NIH) toolbox. Results demonstrate that the ADD SC, combined with a functional subnetwork model, outperforms other models in estimating cognitive performance.

Evaluation of brain iron deposition in different cerebral arteries of acute ischaemic stroke patients using quantitative susceptibility mapping

AIM

To investigate differences in iron deposition between infarct and normal cerebral arterial regions in acute ischaemic stroke (AIS) patients using quantitative susceptibility mapping (QSM).

MATERIALS AND METHODS

Forty healthy controls and 40 AIS patients were recruited, and their QSM images were obtained. There were seven regions of interest (ROIs) in AIS patients, including the infarct regions of responsible arteries (R1), the non-infarct regions of responsible arteries (R2), the contralateral symmetrical sites of lesions (R3), and the non-responsible cerebral arterial regions (R4, R5, R6, R7). For the healthy controls, the cerebral arterial regions corresponding to the AIS patient group were selected as ROIs. The differences in corresponding ROI susceptibilities between AIS patients and healthy controls and the differences in susceptibilities between infarcted and non-infarct regions in AIS patients were compared.

RESULTS

The susceptibilities of infarct regions in AIS patients were significantly higher than those in healthy controls (p<0.0001). There was no significant difference in non-infarct regions between the two groups (p>0.05). The susceptibility of the infarct regions in AIS patients was significantly higher than those of the non-infarct region of responsible artery and non-responsible cerebral arterial regions (p<0.01).

CONCLUSIONS

Abnormal iron deposition detected by QSM in the infarct regions of AIS patients may not affect iron levels in the non-infarct regions of responsible arteries and normal cerebral arteries, which may open the door for potential new diagnostic and treatment strategies.

Individualized prediction of anxiety and depressive symptoms using gray matter volume in a non-clinical population

Machine learning is an emerging tool in clinical psychology and neuroscience for the individualized prediction of psychiatric symptoms. However, its application in non-clinical populations is still in its infancy. Given the widespread morphological changes observed in psychiatric disorders, our study applies five supervised machine learning regression algorithms-ridge regression, support vector regression, partial least squares regression, least absolute shrinkage and selection operator regression, and Elastic-Net regression-to predict anxiety and depressive symptom scores. We base these predictions on the whole-brain gray matter volume in a large non-clinical sample (n = 425). Our results demonstrate that machine learning algorithms can effectively predict individual variability in anxiety and depressive symptoms, as measured by the Mood and Anxiety Symptoms Questionnaire. The most discriminative features contributing to the prediction models were primarily located in the prefrontal-parietal, temporal, visual, and sub-cortical regions (e.g. amygdala, hippocampus, and putamen). These regions showed distinct patterns for anxious arousal and high positive affect in three of the five models (partial least squares regression, support vector regression, and ridge regression). Importantly, these predictions were consistent across genders and robust to demographic variability (e.g. age, parental education, etc.). Our findings offer critical insights into the distinct brain morphological patterns underlying specific components of anxiety and depressive symptoms, supporting the existing tripartite theory from a neuroimaging perspective.

Noninvasive Assessment of HER2 Expression Status in Gastric Cancer Using 18F-FDG Positron Emission Tomography/Computed Tomography-Based Radiomics: A Pilot Study

Purpose: Immunohistochemistry (IHC) is the main method to detect human epidermal growth factor receptor 2 (HER2) expression levels. However, IHC is invasive and cannot reflect HER2 expression status in real time. The aim of this study was to construct and verify three types of radiomics models based on 18F-fuorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) imaging and to evaluate the predictive ability of these radiomics models for the expression status of HER2 in patients with gastric cancer (GC). Patients and Methods: A total of 118 patients with GC were enrolled in this study. 18F-FDG PET/CT imaging was performed prior to surgery. The LIFEx software package was applied to extract PET and CT radiomics features. The minimum absolute contraction and selection operator (least absolute shrinkage and selection operator [LASSO]) algorithm was used to select the best radiomics features. Three machine learning methods, logistic regression (LR), support vector machine (SVM), and random forest (RF) models, were constructed and verified. The Synthetic Minority Oversampling Technique (SMOTE) was applied to address data imbalance. Results: In the training and test sets, the area under the curve (AUC) values of the LR, SVM, and RF models were 0.809, 0.761, 0.861 and 0.628, 0.993, 0.717, respectively, and the Brier scores were 0.118, 0.214, and 0.143, respectively. Among the three models, the LR and RF models exhibited extremely good prediction performance. The AUC values of the three models significantly improved after SMOTE balanced the data. Conclusions: 18F-FDG PET/CT-based radiomics models, especially LR and RF models, demonstrate good performance in predicting HER2 expression status in patients with GC and can be used to preselect patients who may benefit from HER2-targeted therapy.

Uncertainty-aware refinement framework for ovarian tumor segmentation in CECT volume

BACKGROUND

Ovarian cancer is a highly lethal gynecological disease. Accurate and automated segmentation of ovarian tumors in contrast-enhanced computed tomography (CECT) images is crucial in the radiotherapy treatment of ovarian cancer, enabling radiologists to evaluate cancer progression and develop timely therapeutic plans. However, automatic ovarian tumor segmentation is challenging due to factors such as inhomogeneous background, ambiguous tumor boundaries, and imbalanced foreground-background, all of which contribute to high predictive uncertainty for a segmentation model.

PURPOSE

To tackle these challenges, we propose an uncertainty-aware refinement framework that aims to estimate and refine regions with high predictive uncertainty for accurate ovarian tumor segmentation in CECT images.

METHODS

To this end, we first employ an approximate Bayesian network to detect coarse regions of interest (ROIs) of both ovarian tumors and uncertain regions. These ROIs allow a subsequent segmentation network to narrow down the search area for tumors and prioritize uncertain regions, resulting in precise segmentation of ovarian tumors. Meanwhile, the framework integrates two guidance modules that learn two implicit functions capable of mapping query features sampled according to their uncertainty to organ or boundary manifolds, guiding the segmentation network to facilitate information encoding of uncertain regions.

RESULTS

Firstly, 367 CECT images are collected from the same hospital for experiments. Dice score, Jaccard, Recall, Positive predictive value (PPV), 95% Hausdorff distance (HD95) and Average symmetric surface distance (ASSD) for the testing group of 77 cases are 86.31%, 73.93%, 83.95%, 86.03%, 15.17  mm and 2.57  mm, all of which are significantly better than that of the other state-of-the-art models. And results of visual comparison shows that the compared methods have more mis-segmentation than our method. Furthermore, our method achieves a Dice score that is at least 20% higher than the Dice scores of other compared methods when tumor volumes are less than 20 cm3 $^3$ , indicating better recognition ability to small regions by our method. And then, 38 CECT images are collected from another hospital to form an external testing group. Our approach consistently outperform the compared methods significantly, with the external testing group exhibiting substantial improvements across key evaluation metrics: Dice score (83.74%), Jaccard (69.55%), Recall (82.12%), PPV (81.61%), HD95 (12.31 mm), and ASSD (2.32 mm), robustly establishing its superior performance.

CONCLUSIONS

Experimental results demonstrate that the framework significantly outperforms the compared state-of-the-art methods, with decreased under- or over-segmentation and better small tumor identification. It has the potential for clinical application.

EGR3 Polymorphism Is a Potential Susceptibility Factor of Schizophrenia Risk in a Chinese Population

Objective: The purpose of this study was to evaluate the association between the single nucleotide polymorphisms (SNPs) (EGR3 rs1996147; EGR4 rs3813226, rs6747506; ERBB3 rs2292238; and ERBB4 rs707284, rs7560730) and the risk of schizophrenia (SZ) in a Chinese population. Materials and Methods: We conducted a case-control study, including 248 patients with SZ and 236 healthy controls matched for age and sex. The Mass-array platform was used to detect all the genotypes of the SNPs. Results: The results revealed that the EGR3 rs1996147 AA genotype was associated with borderline decreased SZ risk (AA vs. GG: adjusted OR = 0.43, 95% CI: 0.18-1.02, p = 0.06). However, no significant correlation was found between the other SNPs and overall SZ risk. Subgroup analysis also failed to show any significant association between all SNPs and the risk of SZ. Conclusion: In summary, this study revealed that the EGR3 rs1996147 AA genotype was associated with a borderline risk for SZ.

SwinPA-Net: Swin Transformer-Based Multiscale Feature Pyramid Aggregation Network for Medical Image Segmentation

The precise segmentation of medical images is one of the key challenges in pathology research and clinical practice. However, many medical image segmentation tasks have problems such as large differences between different types of lesions and similar shapes as well as colors between lesions and surrounding tissues, which seriously affects the improvement of segmentation accuracy. In this article, a novel method called Swin Pyramid Aggregation network (SwinPA-Net) is proposed by combining two designed modules with Swin Transformer to learn more powerful and robust features. The two modules, named dense multiplicative connection (DMC) module and local pyramid attention (LPA) module, are proposed to aggregate the multiscale context information of medical images. The DMC module cascades the multiscale semantic feature information through dense multiplicative feature fusion, which minimizes the interference of shallow background noise to improve the feature expression and solves the problem of excessive variation in lesion size and type. Moreover, the LPA module guides the network to focus on the region of interest by merging the global attention and the local attention, which helps to solve similar problems. The proposed network is evaluated on two public benchmark datasets for polyp segmentation task and skin lesion segmentation task as well as a clinical private dataset for laparoscopic image segmentation task. Compared with existing state-of-the-art (SOTA) methods, the SwinPA-Net achieves the most advanced performance and can outperform the second-best method on the mean Dice score by 1.68%, 0.8%, and 1.2% on the three tasks, respectively.

Anomaly guided segmentation: Introducing semantic context for lesion segmentation in retinal OCT using weak context supervision from anomaly detection

Automated lesion detection in retinal optical coherence tomography (OCT) scans has shown promise for several clinical applications, including diagnosis, monitoring and guidance of treatment decisions. However, segmentation models still struggle to achieve the desired results for some complex lesions or datasets that commonly occur in real-world, e.g. due to variability of lesion phenotypes, image quality or disease appearance. While several techniques have been proposed to improve them, one line of research that has not yet been investigated is the incorporation of additional semantic context through the application of anomaly detection models. In this study we experimentally show that incorporating weak anomaly labels to standard segmentation models consistently improves lesion segmentation results. This can be done relatively easy by detecting anomalies with a separate model and then adding these output masks as an extra class for training the segmentation model. This provides additional semantic context without requiring extra manual labels. We empirically validated this strategy using two in-house and two publicly available retinal OCT datasets for multiple lesion targets, demonstrating the potential of this generic anomaly guided segmentation approach to be used as an extra tool for improving lesion detection models.

Differential predictability of cognitive profiles from brain structure in older males and females

Structural brain imaging parameters may successfully predict cognitive performance in neurodegenerative diseases but mostly fail to predict cognitive abilities in healthy older adults. One important aspect contributing to this might be sex differences. Behaviorally, older males and females have been found to differ in terms of cognitive profiles, which cannot be captured by examining them as one homogenous group. In the current study, we examined whether the prediction of cognitive performance from brain structure, i.e. region-wise grey matter volume (GMV), would benefit from the investigation of sex-specific cognitive profiles in a large sample of older adults (1000BRAINS; N = 634; age range 55-85 years). Prediction performance was assessed using a machine learning (ML) approach. Targets represented a) a whole-sample cognitive component solution extracted from males and females, and b) sex-specific cognitive components. Results revealed a generally low predictability of cognitive profiles from region-wise GMV. In males, low predictability was observed across both, the whole sample as well as sex-specific cognitive components. In females, however, predictability differences across sex-specific cognitive components were observed, i.e. visual working memory (WM) and executive functions showed higher predictability than fluency and verbal WM. Hence, results accentuated that addressing sex-specific cognitive profiles allowed a more fine-grained investigation of predictability differences, which may not be observable in the prediction of the whole-sample solution. The current findings not only emphasize the need to further investigate the predictive power of each cognitive component, but they also emphasize the importance of sex-specific analyses in older adults.

Recent trends and advances in novel formulations as an armament in Bcl-2/Bax targeted breast cancer

Breast cancer (BC) remains a significant health burden worldwide, necessitating the development of innovative therapeutic strategies. The B-cell lymphoma 2 (Bcl-2) family proteins, Bcl-2 and Bax, play a crucial role in regulating apoptosis and thus are promising targets for BC therapy. We focus on the recent advancements in novel formulations that specifically target Bcl-2/Bax pathway to combat BC. It provides an overview on biological functions of Bcl-2/Bax in apoptosis regulation, emphasizing their significance in pathogenesis and progression of the disease while covering the numerous therapeutic approaches aimed at modulating the Bcl-2/Bax pathway, including small-molecule inhibitors, peptides, gene-based therapies and other repurposed drugs harboured onto cutting-edge technologies and nanocarrier systems employed to enhance the targeted delivery of Bcl-2/Bax inhibitors tumor cells. These advanced formulations aim to improve therapeutic efficacy, minimize off-target effects, and overcome drug resistance, offering promising prospects in its treatment. In conclusion, it illuminates the diverse and evolving landscape of novel formulations as an essential armament in targeting these proteins while bridging and unravelling the obscurity of Bcl-2/Bax pathway-targeted drug delivery systems which are presently in their nascent stages of exploration for BC therapy which can benefit researchers, clinicians, and pharmaceutical scientists.

Dural arteriovenous fistula of the craniocervical junction

Dural arteriovenous (AV) fistulas of the craniocervical junction can be challenging to diagnose. We describe a 70-year-old man with subacute progressive myelopathy whose MR scan of cervical spine showed serpiginous dorsal vessels, suggesting a dural AV fistula. However, a detailed diagnostic angiogram was normal, prompting additional work-up and a wider differential, which was non-revealing. His symptoms progressed over months, but the evolution of the lesion characteristics on repeat spinal imaging still suggested a dural AV fistula. Repeat angiogram identified an infratentorial dural AV fistula arising from the meningohypophyseal artery. He improved following retrosigmoid craniotomy and clipping. Initial angiography does not always demonstrate a dural AV fistula; if there is clinical and radiographic evolution, repeat angiography might identify a fistula with a rare arterial feeder.

Quantitative transport mapping of multi-delay arterial spin labeling MRI detects early blood perfusion alteration in Alzheimer's disease

Background

Quantitative transport mapping (QTM) of blood velocity, based on the transport equation has been demonstrated higher accuracy and sensitivity of perfusion quantification than the traditional Kety's method-based blood flow (Kety flow). This study aimed to investigate the associations between QTM velocity and cognitive function in Alzheimer's disease (AD) using multiple post-labeling delay arterial spin labeling (ASL) MRI.

Methods

A total of 128 subjects (21 normal controls (NC), 80 patients with mild cognitive impairment (MCI), and 27 AD) were recruited prospectively. All participants underwent MRI examination and neuropsychological evaluation. QTM velocity and traditional Kety flow maps were computed from multiple delay ASL. Regional quantitative perfusion measurements were performed and compared to study group differences. We tested the hypothesis that cognition declines with reduced cerebral blood flow with consideration of age and gender effects.

Results

In cortical gray matter (GM) and the hippocampus, QTM velocity and Kety flow showed decreased values in AD group compared to NC and MCI groups; QTM velocity, but not Kety flow, showed a significant difference between MCI and NC groups. QTM velocity and Kety flow showed values decreasing with age; QTM velocity, but not Kety flow, showed a significant gender difference between male and female. QTM velocity and Kety flow in the hippocampus were positively correlated with cognition, including global cognition, memory, executive function, and language function.

Conclusion

This study demonstrated an increased sensitivity of QTM velocity as compared with the traditional Kety flow. Specifically, we observed only in QTM velocity, reduced perfusion velocity in GM and the hippocampus in MCI compared with NC. Both QTM velocity and Kety flow demonstrated reduction in AD vs controls. Decreased QTM velocity and Kety flow in the hippocampus were correlated with cognitive measures. These findings suggest QTM velocity as an improved biomarker for early AD blood flow alterations.

Clinical and radiomics integrated nomogram for preoperative prediction of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer

Objectives

The present study aimed to develop a radiomics nomogram based on conventional ultrasound (CUS) to preoperatively distinguish high tumor-infiltrating lymphocytes (TILs) and low TILs in triple-negative breast cancer (TNBC) patients.

Methods

In the present study, 145 TNBC patients were retrospectively included. Pathological evaluation of TILs in the hematoxylin and eosin sections was set as the gold standard. The patients were randomly allocated into training dataset and validation dataset with a ratio of 7:3. Clinical features (age and CUS features) and radiomics features were collected. Then, the Rad-score model was constructed after the radiomics feature selection. The clinical features model and clinical features plus Rad-score (Clin+RS) model were built using logistic regression analysis. Furthermore, the performance of the models was evaluated by analyzing the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

Results

Univariate analysis and LASSO regression were employed to identify a subset of 25 radiomics features from a pool of 837 radiomics features, followed by the calculation of Rad-score. The Clin+RS integrated model, which combined posterior echo and Rad-score, demonstrated better predictive performance compared to both the Rad-score model and clinical model, achieving AUC values of 0.848 in the training dataset and 0.847 in the validation dataset.

Conclusion

The Clin+RS integrated model, incorporating posterior echo and Rad-score, demonstrated an acceptable preoperative evaluation of the TIL level. The Clin+RS integrated nomogram holds tremendous potential for preoperative individualized prediction of the TIL level in TNBC.

Spatial and temporal pattern of structure-function coupling of human brain connectome with development

Brain structural circuitry shapes a richly patterned functional synchronization, supporting for complex cognitive and behavioural abilities. However, how coupling of structural connectome (SC) and functional connectome (FC) develops and its relationships with cognitive functions and transcriptomic architecture remain unclear. We used multimodal magnetic resonance imaging data from 439 participants aged 5.7 to 21.9 years to predict functional connectivity by incorporating intracortical and extracortical structural connectivity, characterizing SC-FC coupling. Our findings revealed that SC-FC coupling was strongest in the visual and somatomotor networks, consistent with evolutionary expansion, myelin content, and functional principal gradient. As development progressed, SC-FC coupling exhibited heterogeneous alterations dominated by an increase in cortical regions, broadly distributed across the somatomotor, frontoparietal, dorsal attention, and default mode networks. Moreover, we discovered that SC-FC coupling significantly predicted individual variability in general intelligence, mainly influencing frontoparietal and default mode networks. Finally, our results demonstrated that the heterogeneous development of SC-FC coupling is positively associated with genes in oligodendrocyte-related pathways and negatively associated with astrocyte-related genes. This study offers insight into the maturational principles of SC-FC coupling in typical development.

Coherent activity within and between hemispheres: cortico-cortical connectivity revealed by rTMS of the right posterior parietal cortex

Introduction

Low frequency (1 Hz) repetitive transcranial stimulation (rTMS) applied over right posterior parietal cortex (rPPC) has been shown to reduce cortical excitability both of the stimulated area and of the interconnected contralateral homologous areas. In the present study, we investigated the whole pattern of intra- and inter-hemispheric cortico-cortical connectivity changes induced by rTMS over rPPC.

Methods

To do so, 14 healthy participants underwent resting state EEG recording before and after 30 min of rTMS at 1 Hz or sham stimulation over the rPPC (electrode position P6). Real stimulation was applied at 90% of motor threshold. Coherence values were computed on the electrodes nearby the stimulated site (i.e., P4, P8, and CP6) considering all possible inter- and intra-hemispheric combinations for the following frequency bands: delta (0.5-4 Hz), theta (4-8 Hz), alpha (8-12Hz), low beta (12-20 Hz), high beta (20-30 Hz), and gamma (30-50 Hz).

Results and discussion

Results revealed a significant increase in coherence in delta, theta, alpha and beta frequency bands between rPPC and the contralateral homologous sites. Moreover, an increase in coherence in theta, alpha, beta and gamma frequency bands was found between rPPC and right frontal sites, reflecting the activation of the fronto-parietal network within the right hemisphere. Summarizing, subthreshold rTMS over rPPC revealed cortico-cortical inter- and intra-hemispheric connectivity as measured by the increase in coherence among these areas. Moreover, the present results further confirm previous evidence indicating that the increase of coherence values is related to intra- and inter-hemispheric inhibitory effects of rTMS. These results can have implications for devising evidence-based rehabilitation protocols after stroke.

Case report: Rapidly progressive neurocognitive disorder with a fatal outcome in a patient with PU.1 mutated agammaglobulinemia

Introduction

PU.1-mutated agammaglobulinemia (PU.MA) represents a recently described autosomal-dominant form of agammaglobulinemia caused by mutation of the SPI1 gene. This gene codes for PU.1 pioneer transcription factor important for the maturation of monocytes, B lymphocytes, and conventional dendritic cells. Only six cases with PU.MA, presenting with chronic sinopulmonary and systemic enteroviral infections, have been previously described. Accumulating literature evidence suggests a possible relationship between SPI1 mutation, microglial phagocytic dysfunction, and the development of Alzheimer's disease (AD).

Case description

We present a Caucasian female patient born from a non-consanguineous marriage, who was diagnosed with agammaglobulinemia at the age of 15 years when the immunoglobulin replacement therapy was started. During the following seventeen years, she was treated for recurrent respiratory and intestinal infections. At the age of 33 years, the diagnosis of celiac-like disease was established. Five years later progressive cognitive deterioration, unstable gait, speech disturbances, and behavioral changes developed. Comprehensive microbiological investigations were negative, excluding possible infective etiology. Brain MRI, 18FDG-PET-CT, and neuropsychological testing were suggestive for a diagnosis of a frontal variant of AD. Clinical exome sequencing revealed the presence of a novel frameshift heterozygous variant c.441dup in exon 4 of the SPI1 gene. Despite intensive therapy, the patient passed away a few months after the onset of the first neurological symptoms.

Conclusion

We describe the first case of PU.MA patient presenting with a rapidly progressive neurocognitive deterioration. The possible role of microglial dysfunction in patients with SPI1 mutation could explain their susceptibility to neurodegenerative diseases thus highlighting the importance of genetic testing in patients with inborn errors of immunity. Since PU.MA represents a newly described form of agammaglobulinemia, our case expands the spectrum of manifestations associated with SPI1 mutation.

Rethinking automatic segmentation of gross target volume from a decoupling perspective

Accurate and reliable segmentation of Gross Target Volume (GTV) is critical in cancer Radiation Therapy (RT) planning, but manual delineation is time-consuming and subject to inter-observer variations. Recently, deep learning methods have achieved remarkable success in medical image segmentation. However, due to the low image contrast and extreme pixel imbalance between GTV and adjacent tissues, most existing methods usually obtained limited performance on automatic GTV segmentation. In this paper, we propose a Heterogeneous Cascade Framework (HCF) from a decoupling perspective, which decomposes the GTV segmentation into independent recognition and segmentation subtasks. The former aims to screen out the abnormal slices containing GTV, while the latter performs pixel-wise segmentation of these slices. With the decoupled two-stage framework, we can efficiently filter normal slices to reduce false positives. To further improve the segmentation performance, we design a multi-level Spatial Alignment Network (SANet) based on the feature pyramid structure, which introduces a spatial alignment module into the decoder to compensate for the information loss caused by downsampling. Moreover, we propose a Combined Regularization (CR) loss and Balance-Sampling Strategy (BSS) to alleviate the pixel imbalance problem and improve network convergence. Extensive experiments on two public datasets of StructSeg2019 challenge demonstrate that our method outperforms state-of-the-art methods, especially with significant advantages in reducing false positives and accurately segmenting small objects. The code is available at https://github.com/shijun18/GTV_AutoSeg.

Magnetic and injectable Fe-doped liquid metals for controlled movement and photothermal/electromagnetic therapy

As a multifunctional material, gallium-based liquid metal (LM) mixtures with metal particles dispersed in the LM environment display many excellent and intriguing properties. In this study, biomaterials were prepared by mixing Fe particles with LM for easily manageable photothermal or electromagnetic therapy and evaluated. Clinically, the fabricated 5%Fe/LM sample was injectable and radiopaque, which allowed its smooth delivery through a syringe to the target tissues, where it could help achieve clear imaging under CT. Meanwhile, because of the loading of Fe particles, the 5%Fe/LM possessed a magnetic property, implying a high manipulation capability. According to the experiments, the capsule containing 5%Fe/LM when placed in an isolated pig large intestine could move as desired to the designated position through an external magnet. Further, the biosafety and low toxicity of the 5%Fe/LM were confirmed by cytotoxicity tests in vitro, and the temperature changes at the interface between the 5%Fe/LM and intestinal tissue after near-infrared (NIR) laser irradiation were determined through theoretical modeling and numerical simulation data analysis. Due to the excellent photothermal and magnetothermal effects of LM, the temperature of the 5%Fe/LM injected into the rabbit abdominal cavity could significantly increase under NIR laser or alternating magnetic field (AMF) administration. As a novel functional biomaterial, the 5%Fe/LM exhibited promising potential for designated position movement and photothermal or magnetothermal therapy in the near future.

Clinical features, treatment strategies and outcomes of craniocervical junction arteriovenous fistulas: a cohort study of 193 patients

BACKGROUND

Craniocervical junction (CCJ) arteriovenous fistulas (AVFs) are rare. The current treatment strategies for AVFs with different angioarchitecture need to be clarified. The present study aimed to analyse the correlation between angioarchitecture and clinical characteristics, share our experience in treating this disease and identify risk factors associated with subarachnoid haemorrhage (SAH) and poor outcomes.

METHODS

A total of 198 consecutive patients with CCJ AVFs from our neurosurgical centre were retrospectively reviewed. The patients were grouped according to their clinical manifestations, and their baseline clinical characteristics, angioarchitecture, treatment strategies and outcomes were summarised.

RESULTS

The patients' median age was 56 years (IQR 47-62 years). The majority of patients were men with 166 (83.8%) patients. The most common clinical manifestation was SAH (52.0%), followed by venous hypertensive myelopathy (VHM) (45.5%). The most common CCJ AVFs type was dural AVF, with 132 (63.5%) fistulas. The most frequent fistula location was C-1 (68.7%) and dural branch of vertebral artery (70.2%) was the most involved arterial feeders for fistulas. The most common direction of venous drainage was descending intradural drainage (40.9%), followed by ascending intradural drainage (36.5%). Microsurgery was the most common treatment strategy applied for 151 (76.3%) patients, 15 (7.6%) patients were treated with interventional embolisation only, and 27 (13.6%) received both interventional embolisation and microsurgical treatment. The learning curve for microsurgery only was analysed by cumulative summation method, and the turning point was the 70th case, and blood loss in post-group was lower than that in pre-group (p=0.034). At the last follow-up, there were 155 (78.3%) patients with favourable outcomes (modified Rankin Scale(mRS)<3). Age≥56 (OR 2.038, 95% CI 1.039 to 3.998, p=0.038), VHM as the clinical manifestation (OR 4.102, 95% CI 2.108 to 7.982, p<0.001) and pretreatment mRS≥3 (OR 3.127, 95% CI 1.617 to 6.047, p<0.001) were significantly associated with poor outcomes.

CONCLUSION

The arterial feeders and direction of the venous drainage were important factors in the clinical presentations. The location of fistula and drainage vein was essential for choosing different treatment strategies. Older age, VHM onset and poor pretreatment functional status predicted poor outcomes.

Iron quantification in basal ganglia: quantitative susceptibility mapping as a potential biomarker for Alzheimer's disease - a systematic review and meta-analysis

Introduction

Alzheimer's disease (AD), characterized by distinctive pathologies such as amyloid-β plaques and tau tangles, also involves deregulation of iron homeostasis, which may accelerate neurodegeneration. This meta-analysis evaluated the use of quantitative susceptibility mapping (QSM) to detect iron accumulation in the deep gray matter (DGM) of the basal ganglia in AD, contributing to a better understanding of AD progression, and potentially leading to new diagnostic and therapeutic approaches.

Methods

Using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically searched the PubMed, Scopus, Web of Sciences, and Google Scholar databases up to October 2023 for studies employing QSM in AD research. Eligibility criteria were based on the PECO framework, and we included studies assessing alterations in magnetic susceptibility indicative of iron accumulation in the DGM of patients with AD. After initial screening and quality assessment using the Newcastle-Ottawa Scale, a meta-analysis was conducted to compare iron levels between patients with AD and healthy controls (HCs) using a random-effects model.

Results

The meta-analysis included nine studies comprising 267 patients with AD and 272 HCs. There were significantly higher QSM values, indicating greater iron deposition, in the putamen (standardized mean difference (SMD) = 1.23; 95% CI: 0.62 to 1.84; p = 0.00), globus pallidus (SMD = 0.79; 95% CI: 0.07 to 1.52; p = 0.03), and caudate nucleus (SMD = 0.72; 95% CI: 0.39 to 1.06; p = 0.00) of AD patients compared to HCs. However, no significant differences were found in the thalamus (SMD = 1.00; 95% CI: -0.42 to 2.43; p = 0.17). The sensitivity analysis indicated that no single study impacted the overall results. Age was identified as a major contributor to heterogeneity across all basal ganglia nuclei in subgroup analysis. Older age (>69 years) and lower male percentage (≤30%) were associated with greater putamen iron increase in patients with AD.

Conclusion

The study suggests that excessive iron deposition is linked to the basal ganglia in AD, especially the putamen. The study underscores the complex nature of AD pathology and the accumulation of iron, influenced by age, sex, and regional differences, necessitating further research for a comprehensive understanding.

Increased iron in the substantia nigra pars compacta identifies patients with early Parkinson'sdisease: A 3T and 7T MRI study

Degeneration in the substantia nigra (SN) pars compacta (SNc) underlies motor symptoms in Parkinson's disease (PD). Currently, there are no neuroimaging biomarkers that are sufficiently sensitive, specific, reproducible, and accessible for routine diagnosis or staging of PD. Although iron is essential for cellular processes, it also mediates neurodegeneration. MRI can localize and quantify brain iron using magnetic susceptibility, which could potentially provide biomarkers of PD. We measured iron in the SNc, SN pars reticulata (SNr), total SN, and ventral tegmental area (VTA), using quantitative susceptibility mapping (QSM) and R2* relaxometry, in PD patients and age-matched healthy controls (HCs). PD patients, diagnosed within five years of participation and HCs were scanned at 3T (22 PD and 23 HCs) and 7T (17 PD and 21 HCs) MRI. Midbrain nuclei were segmented using a probabilistic subcortical atlas. QSM and R2* values were measured in midbrain subregions. For each measure, groups were contrasted, with Age and Sex as covariates, and receiver operating characteristic (ROC) curve analyses were performed with repeated k-fold cross-validation to test the potential of our measures to classify PD patients and HCs. Statistical differences of area under the curves (AUCs) were compared using the Hanley-MacNeil method (QSM versus R2*; 3T versus 7T MRI). PD patients had higher QSM values in the SNc at both 3T (padj = 0.001) and 7T (padj = 0.01), but not in SNr, total SN, or VTA, at either field strength. No significant group differences were revealed using R2* in any midbrain region at 3T, though increased R2* values in SNc at 7T MRI were marginally significant in PDs compared to HCs (padj = 0.052). ROC curve analyses showed that SNc iron measured with QSM, distinguished early PD patients from HCs at the single-subject level with good diagnostic accuracy, using 3T (mean AUC = 0.83, 95 % CI = 0.82-0.84) and 7T (mean AUC = 0.80, 95 % CI = 0.79-0.81) MRI. Mean AUCs reported here are from averages of tests in the hold-out fold of cross-validated samples. The Hanley-MacNeil method demonstrated that QSM outperforms R2* in discriminating PD patients from HCs at 3T, but not 7T. There were no significant differences between 3T and 7T in diagnostic accuracy of QSM values in SNc. This study highlights the importance of segmenting midbrain subregions, performed here using a standardized atlas, and demonstrates high accuracy of SNc iron measured with QSM at 3T MRI in identifying early PD patients. QSM measures of SNc show potential for inclusion in neuroimaging diagnostic biomarkers of early PD. An MRI diagnostic biomarker of PD would represent a significant clinical advance.

Dual-Energy Computed Tomography in Detecting and Predicting Lymph Node Metastasis in Malignant Tumor Patients: A Comprehensive Review

The accurate and timely assessment of lymph node involvement is paramount in the management of patients with malignant tumors, owing to its direct correlation with cancer staging, therapeutic strategy formulation, and prognostication. Dual-energy computed tomography (DECT), as a burgeoning imaging modality, has shown promising results in the diagnosis and prediction of preoperative metastatic lymph nodes in recent years. This article aims to explore the application of DECT in identifying metastatic lymph nodes (LNs) across various cancer types, including but not limited to thyroid carcinoma (focusing on papillary thyroid carcinoma), lung cancer, and colorectal cancer. Through this narrative review, we aim to elucidate the clinical relevance and utility of DECT in the detection and predictive assessment of lymph node metastasis in malignant tumors, thereby contributing to the broader academic discourse in oncologic radiology and diagnostic precision.

Changes in iron load in specific brain areas lead to neurodegenerative diseases of the central nervous system

The causes of neurodegenerative diseases remain largely elusive, increasing their personal and societal impacts. To reveal the causal effects of iron load on Parkinson's disease (PD), Alzheimer's disease (AD), amyotrophic lateral sclerosis and multiple sclerosis, we used Mendelian randomisation and brain imaging data from a UK Biobank genome-wide association study of 39,691 brain imaging samples (predominantly of European origin). Using susceptibility-weighted images, which reflect iron load, we analysed genetically significant brain regions. Inverse variance weighting was used as the main estimate, while MR Egger and weighted median were used to detect heterogeneity and pleiotropy. Nine clear associations were obtained. For AD and PD, an increased iron load was causative: the right pallidum for AD and the right caudate, left caudate and right accumbens for PD. However, a reduced iron load was identified in the right and left caudate for multiple sclerosis, the bilateral hippocampus for mixed vascular dementia and the left thalamus and bilateral accumbens for subcortical vascular dementia. Thus, changes in iron load in different brain regions have causal effects on neurodegenerative diseases. Our results are crucial for understanding the pathogenesis and investigating the treatment of these diseases.

Prediction of cognitive performance differences in older age from multimodal neuroimaging data

Differences in brain structure and functional and structural network architecture have been found to partly explain cognitive performance differences in older ages. Thus, they may serve as potential markers for these differences. Initial unimodal studies, however, have reported mixed prediction results of selective cognitive variables based on these brain features using machine learning (ML). Thus, the aim of the current study was to investigate the general validity of cognitive performance prediction from imaging data in healthy older adults. In particular, the focus was with examining whether (1) multimodal information, i.e., region-wise grey matter volume (GMV), resting-state functional connectivity (RSFC), and structural connectivity (SC) estimates, may improve predictability of cognitive targets, (2) predictability differences arise for global cognition and distinct cognitive profiles, and (3) results generalize across different ML approaches in 594 healthy older adults (age range: 55-85 years) from the 1000BRAINS study. Prediction potential was examined for each modality and all multimodal combinations, with and without confound (i.e., age, education, and sex) regression across different analytic options, i.e., variations in algorithms, feature sets, and multimodal approaches (i.e., concatenation vs. stacking). Results showed that prediction performance differed considerably between deconfounding strategies. In the absence of demographic confounder control, successful prediction of cognitive performance could be observed across analytic choices. Combination of different modalities tended to marginally improve predictability of cognitive performance compared to single modalities. Importantly, all previously described effects vanished in the strict confounder control condition. Despite a small trend for a multimodal benefit, developing a biomarker for cognitive aging remains challenging.

Ligand Mediation for Tunable and Oxide Suppressed Surface Gold-Decorated Liquid Metal Nanoparticles

Gallium-based liquid metal systems hold vast potential in materials science. However, maximizing their possibilities is hindered by gallium's native oxide and interfacial functionalization. In this study, small-molecule ligands are adopted as surfactants to modify the surface of eutectic gallium indium (EGaIn) nanoparticles and suppress oxidation. Different p-aniline derivatives are explored. Next, the reduction of chloroanric acid (HAuCl4 ) onto these p-aniline ligand modified EGaIn nanoparticles is investigated to produce gold-decorated EGaIn nanosystems. It is found that by altering the concentrations of HAuCl4 or the p-aniline ligand, the formation of gold nanoparticles (AuNPs) on EGaIn can be manipulated. The reduction of interfacial oxidation and presence of AuNPs enhances electrical conductivity, plasmonic performance, wettability, stability, and photothermal performance of all the p-aniline derivative modified EGaIn. Of these, EGaIn nanoparticles covered with the ligand of p-aminobenzoic acid offer the most evenly distributed AuNPs decoration and perfect elimination of gallium oxides, resulting in the augmented electrical conductivity, and highest wettability suitable for patterning, enhanced aqueous stability, and favorable photothermal properties. The proof-of-concept application in photothermal therapy of cancer cells demonstrates significantly enhanced photothermal conversion performance along with good biocompatibility. Due to such unique characteristics, the developed gold-decorated EGaIn nanodroplets are expected to offer significant potential in precise medicine.

SaB-Net: Self-attention backward network for gastric tumor segmentation in CT images

Gastric cancer is a significant contributor to cancer-related fatalities globally. The automated segmentation of gastric tumors has the potential to analyze the medical condition of patients and enhance the likelihood of surgical treatment success. However, the development of an automatic solution is challenged by the heterogeneous intensity distribution of gastric tumors in computed tomography (CT) images, the low-intensity contrast between organs, and the high variability in the stomach shapes and gastric tumors in different patients. To address these challenges, we propose a self-attention backward network (SaB-Net) for gastric tumor segmentation (GTS) in CT images by introducing a self-attention backward layer (SaB-Layer) to feed the self-attention information learned at the deep layer back to the shallow layers. The SaB-Layer efficiently extracts tumor information from CT images and integrates the information into the network, thereby enhancing the network's tumor segmentation ability. We employed datasets from two centers, one for model training and testing and the other for external validation. The model achieved dice scores of 0.8456 on the test set and 0.8068 on the external verification set. Moreover, we validated the model's transfer learning ability on a publicly available liver cancer dataset, achieving results comparable to state-of-the-art liver cancer segmentation models recently developed. SaB-Net has strong potential for assisting in the clinical diagnosis of and therapy for gastric cancer. Our implementation is available at https://github.com/TyrionJ/SaB-Net.

Depth- and curvature-based quantitative susceptibility mapping analyses of cortical iron in Alzheimer's disease

In addition to amyloid beta plaques and neurofibrillary tangles, Alzheimer's disease (AD) has been associated with elevated iron in deep gray matter nuclei using quantitative susceptibility mapping (QSM). However, only a few studies have examined cortical iron, using more macroscopic approaches that cannot assess layer-specific differences. Here, we conducted column-based QSM analyses to assess whether AD-related increases in cortical iron vary in relation to layer-specific differences in the type and density of neurons. We obtained global and regional measures of positive (iron) and negative (myelin, protein aggregation) susceptibility from 22 adults with AD and 22 demographically matched healthy controls. Depth-wise analyses indicated that global susceptibility increased from the pial surface to the gray/white matter boundary, with a larger slope for positive susceptibility in the left hemisphere for adults with AD than controls. Curvature-based analyses indicated larger global susceptibility for adults with AD versus controls; the right hemisphere versus left; and gyri versus sulci. Region-of-interest analyses identified similar depth- and curvature-specific group differences, especially for temporo-parietal regions. Finding that iron accumulates in a topographically heterogenous manner across the cortical mantle may help explain the profound cognitive deterioration that differentiates AD from the slowing of general motor processes in healthy aging.

Reduced Oxygen Extraction Fraction in Deep Cerebral Veins Associated with Cognitive Impairment in Multiple Sclerosis

Studying the relationship between cerebral oxygen utilization and cognitive impairment is essential to understanding neuronal functional changes in the disease progression of multiple sclerosis (MS). This study explores the potential of using venous susceptibility in internal cerebral veins (ICVs) as an imaging biomarker for cognitive impairment in relapsing-remitting MS (RRMS) patients. Quantitative susceptibility mapping derived from fully flow-compensated MRI phase data was employed to directly measure venous blood oxygen saturation levels (SvO2) in the ICVs. Results revealed a significant reduction in the susceptibility of ICVs (212.4 ± 30.8 ppb vs 239.4 ± 25.9 ppb) and a significant increase of SvO2 (74.5 ± 1.89 % vs 72.4 ± 2.23 %) in patients with RRMS compared with age- and sex-matched healthy controls. Both the susceptibility of ICVs (r = 0.646, p = 0.004) and the SvO2 (r = -0.603, p = 0.008) exhibited a strong correlation with cognitive decline in these patients assessed by the Paced Auditory Serial Addition Test, while no significant correlation was observed with clinical disability measured by the Expanded Disability Status Scale. The findings suggest that venous susceptibility in ICVs has the potential to serve as a specific indicator of oxygen metabolism and cognitive function in RRMS.

Mono+ algorithm assessment of the diagnostic value of dual-energy CT for high-risk factors for colorectal cancer: a preliminary study

Background

Risk factors for colorectal cancer (CRC) affect the way patients are subsequently treated and their prognosis. Dual-energy computerized tomography (DECT) is an advanced imaging technique that enables the quantitative evaluation of lesions. This study aimed to evaluate the quality of DECT images based on the Mono+ algorithm in CRC, and based on this, to assess the value of DECT in the diagnosis of CRC risk factors.

Methods

This prospective study was performed from 2021 to 2023. A dual-phase DECT protocol was established for consecutive patients with primary CRC. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), overall image quality, lesion delineation, and image noise of the dual-phase DECT images were assessed. Next, the optimal energy-level image was selected to analyze the iodine concentration (IC), normalized iodine concentration (NIC), effective atomic number, electron density, dual-energy index (DEI), and slope of the energy spectrum curve within the tumor for the high- and low-risk CRC groups. A multifactor binary logistic regression analysis was used to construct a differential diagnostic regression model for high- and low-risk CRC, receiver operating characteristic (ROC) curves were plotted, and the area under the curve (AUC) was calculated to assess the diagnostic value of the model.

Results

A total of 74 patients were enrolled in this study, of whom 41 had high-risk factors and 33 had low-risk factors. The SNR and CNR were best at 40 keV virtual monoenergetic imaging (VMI) based on the Mono+ algorithm (VMI+) (SNR 8.79±1.27, P<0.001; CNR 14.89±1.77, P=0.027). The overall image quality and lesion contours were best at 60 keV VMI+ and 40 keV VMI+, respectively (P=0.001). Among all the DECT parameters, the arterial phase (AP)-IC, NIC, DEI, energy spectrum curve, and venous phase-NIC differed significantly between the two groups. The AP-IC was the optimal DECT parameter for predicting high- and low-risk CRC with AUC, sensitivity, specificity, and cut-off values of 0.96, 97.06%, 87.80%, and 2.94, respectively, and the 95% confidence interval (CI) of the AUC was 0.88-0.99. Integrating the clinical factors and DECT parameters, the AUC, sensitivity, specificity, and predictive accuracy of the model were 0.99, 100.00%, 92.68%, and 94.67%, respectively, and the 95% CI of the AUC was 0.93-1.00.

Conclusions

The DECT parameters based on 40 keV noise-optimized VMI+ reconstruction images depicted the CRC tumors best, and the clinical DECT model may have significant implications for the preoperative prediction of high-risk factors in CRC patients.

Value of dual-layer spectral detector CT in predicting lymph node metastasis of non-small cell lung cancer

Background

The accurate assessment of lymph node metastasis (LNM) is crucial for the staging, treatment, and prognosis of lung cancer. In this study, we explored the potential value of dual-layer spectral detector computed tomography (SDCT) quantitative parameters in the prediction of LNM in non-small cell lung cancer (NSCLC).

Methods

In total, 91 patients presenting with solid solitary pulmonary nodules (8 mm < diameter ≤30 mm) with pathologically confirmed NSCLC (57 without LNM, and 34 with LNM) were enrolled in the study. The patients' basic clinical data and the SDCT morphological features were analyzed using the chi-square test or Fisher's exact test. The Mann-Whitney U-test and independent sample t-test were used to analyze the differences in multiple SDCT quantitative parameters between the non-LNM and LNM groups. The diagnostic efficacy of the corresponding parameters in predicting LNM in NSCLC was evaluated by plotting the receiver operating characteristic (ROC) curves. A multivariate logistic regression analysis was conducted to determine the independent predictive factors of LNM in NSCLC. Interobserver agreement was assessed using intraclass correlation coefficients (ICCs) and Bland-Altman plots.

Results

There were no significant differences between the non-LNM and LNM groups in terms of age, sex, and smoking history. Lesion size and vascular convergence sign differed significantly between the two groups (P<0.05), but there were no significant differences in the six tumor markers. The SDCT quantitative parameters [SAR40keV, SAR70keV, Δ40keV, Δ70keV, CER40keV, CER70keV, NEF40keV, NEF70keV, λ, normalized iodine concentration (NIC) and NZeff] were significantly higher in the non-LNM group than the LNM group (P<0.05). The ROC analysis showed that CER40keV, NIC, and CER70keV had higher diagnostic efficacy than other quantitative parameters in predicting LNM [areas under the curve (AUCs) =0.794, 0.791, and 0.783, respectively]. The multivariate logistic regression analysis showed that size, λ, and NIC were independent predictive factors of LNM. The combination of size, λ, and NIC had the highest diagnostic efficacy (AUC =0.892). The interobserver repeatability of the SDCT quantitative and derived quantitative parameters in the study was good (ICC: 0.801-0.935).

Conclusions

The SDCT quantitative parameters combined with the clinical data have potential value in predicting LNM in NSCLC. The size + λ + NIC combined parameter model could further improve the prediction efficacy of LNM.

Research progress of absorbable stents

Atherosclerosis, a chronic inflammation of blood vessel walls, is a progressive pathophysiological process characterized by lipid deposition and innate adaptive immune responses. Arteriosclerosis often leads to narrowing of blood vessels. At present, interventional stent therapy is the main treatment method for vascular stenosis, which has the advantages of less trauma, less risk and faster recovery. However, atherosclerosis occurs in a complex pathophysiological environment. Stenting inevitably causes local tissue damage, leading to complications such as inflammation, intimal hyperplasia, late thrombosis, stent restenosis and other complications. It is urgent to optimize interventional therapy program. This article summarizes the advantages and disadvantages of absorbable metal scaffolds and the research progress of absorbable polymer scaffolds. The optimization strategy of stent is proposed. The status quo of drug coating was summarized. The prospect of new stent. To improve the therapeutic effect of arteriosclerosis.

Effects of D-CAG chemotherapy regimen on cognitive function in patients with acute myeloid leukaemia: A resting-state functional magnetic resonance imaging study

Post-chemotherapy cognitive impairment, also known as 'chemobrain', is a common neurotoxic complication induced by chemotherapy, which has been reported in many cancer survivors who have undergone chemotherapy. In this study, we aimed to explore the effects of D-neneneba dicitabine, C-nenenebb cytarabine, A-aclamycin, G-granulocyte colony-stimulating factor (D-CAG) chemotherapy on cognitive function in patients with acute myeloid leukaemia (AML) and its possible central mechanisms. Twenty patients with AML and 25 matched healthy controls (HC) were enrolled in this study. The cognitive function of patients before and after D-CAG chemotherapy was evaluated by the Functional Assessment of Cancer Therapy-Cognitive Function (FACT-Cog). The resting-state functional magnetic resonance imaging data were collected from all patients before and after chemotherapy intervention, as well as HC. Then, resting-state functional magnetic resonance imaging data were preprocessed using DPABI software package and regional homogeneity (ReHo) values of brain regions were calculated. Finally, ReHo values between groups were compared by Resting-State fMRI Data Analysis software package with t-tests and Alphasim method was performed for multiple comparison correction. Moreover, associations between ReHo values of altered brain regions and the scores of FACT-Cog were analysed by Pearson correlation. The total FACT-Cog scores and four factor scores of AML patients increased significantly after treatment. ReHo values showed no significant changes in patients before treatment when compared with HC. Compared with HC, ReHo values of the right middle frontal gyrus, inferior frontal gyrus (opercular part), middle occipital gyrus, and left praecuneus decreased significantly, while ReHo values of the left inferior temporal gyrus, right middle temporal gyrus, and hippocampus increased significantly in patients after treatment. Compared with patients before treatment, ReHo values decreased significantly in the right middle frontal gyrus, inferior frontal gyrus (opercular part), and middle and inferior occipital gyri of patients after treatment. In addition, ReHo values of the right inferior frontal gyrus (opercular part) were negatively correlated with the total scores of FACT-Cog and factor scores of perceived cognitive impairment in patients after treatment. There were also negative correlations between ReHo values of the right middle frontal gyrus and perceived cognitive impairment scores. The present study confirmed that D-CAG chemotherapy might cause impaired subjective self-reported cognitive functioning in AML patients, which might be related to the decreased function of certain regions in the right prefrontal lobe. These findings provided further understanding of the mechanisms involved in post-chemotherapy cognitive impairment and would help develop new therapeutic strategies for 'chemobrain' in AML patients.

Preserving specificity in federated graph learning for fMRI-based neurological disorder identification

Resting-state functional magnetic resonance imaging (rs-fMRI) offers a non-invasive approach to examining abnormal brain connectivity associated with brain disorders. Graph neural network (GNN) gains popularity in fMRI representation learning and brain disorder analysis with powerful graph representation capabilities. Training a general GNN often necessitates a large-scale dataset from multiple imaging centers/sites, but centralizing multi-site data generally faces inherent challenges related to data privacy, security, and storage burden. Federated Learning (FL) enables collaborative model training without centralized multi-site fMRI data. Unfortunately, previous FL approaches for fMRI analysis often ignore site-specificity, including demographic factors such as age, gender, and education level. To this end, we propose a specificity-aware federated graph learning (SFGL) framework for rs-fMRI analysis and automated brain disorder identification, with a server and multiple clients/sites for federated model aggregation and prediction. At each client, our model consists of a shared and a personalized branch, where parameters of the shared branch are sent to the server while those of the personalized branch remain local. This can facilitate knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-temporal attention graph isomorphism network to learn dynamic fMRI representations. In the personalized branch, we integrate vectorized demographic information (i.e., age, gender, and education years) and functional connectivity networks to preserve site-specific characteristics. Representations generated by the two branches are then fused for classification. Experimental results on two fMRI datasets with a total of 1218 subjects suggest that SFGL outperforms several state-of-the-art approaches.

Functional micro-/nanostructured gallium-based liquid metal for biochemical sensing and imaging applications

In recent years, liquid metals (LMs) have garnered increasing attention for their expanded applicability, and wide application potential in various research fields. Among them, gallium (Ga)-based LMs exhibit remarkable analytical performance in electrical and optical sensors, thanks to their excellent conductivity, large surface area, biocompatibility, small bandgap, and high elasticity. This review comprehensively summarizes the latest advancements in functional micro-/nanostructured Ga-based LMs for biochemical sensing and imaging applications. Firstly, the electrical, optical, and biocompatible features of Ga-based LM micro-/nanoparticles are briefly discussed, along with the manufacturing and functionalization processes. Subsequently, we demonstrate the utilization of Ga-based LMs in biochemical sensing techniques, encompassing electrochemistry, electrochemiluminescence, optical sensing techniques, and various biomedical imaging. Lastly, we present an insightful perspective on promising research directions and remaining challenges in LM-based biochemical sensing and imaging applications.

Preoperative CT Radiomics Nomogram for Predicting Microvascular Invasion in Stage I Non-Small Cell Lung Cancer

RATIONALE AND OBJECTIVES: This study aims to develop and validate a nomogram integrating clinical-CT and radiomic features for preoperative prediction of microvascular invasion (MVI) in patients with stage I non‑small cell lung cancer (NSCLC).

MATERIALS AND METHODS

This retrospective study analyzed 188 cases of stage I NSCLC (63 MVI positives and 125 negatives), which were randomly assigned to training (n = 133) and validation cohorts (n = 55) at a ratio of 7:3. Preoperative non-contrast and contrast-enhanced CT (CECT) images were used to analyze computed tomography (CT) features and extract radiomics features. The student's t-test, the Mann-Whitney-U test, the Pearson correlation, the least absolute shrinkage and selection operator, and multivariable logistic analysis were used to select the significant CT and radiomics features. Multivariable logistic regression analysis was performed to build the clinical-CT, radiomics, and integrated models. The predictive performances were evaluated through the receiver operating characteristic curve and compared with the DeLong test. The integrated nomogram was analyzed regarding discrimination, calibration, and clinical significance.

RESULTS

The rad-score was developed with one shape and four textural features. The integrated nomogram incorporating radiomics score, spiculation, and the number of tumor-related vessels (TVN) demonstrated better predictive efficacy than the radiomics and clinical-CT models in the training cohort (area under the curve [AUC], 0.893 vs 0.853 and 0.828, and p = 0.043 and 0.027, respectively) and validation cohort (AUC, 0.887 vs 0.878 and 0.786, and p = 0.761 and 0.043, respectively). The nomogram also demonstrated good calibration and clinical usefulness.

CONCLUSION

The radiomics nomogram integrating the radiomics with clinical-CT features demonstrated good performance in predicting MVI status in stage I NSCLC. The nomogram may be a useful tool for physicians in improving personalized management of stage I NSCLC.

Discriminative analysis of schizophrenia patients using an integrated model combining 3D CNN with 2D CNN: A multimodal MR image and connectomics analysis

OBJECTIVE

Few studies have applied deep learning to the discriminative analysis of schizophrenia (SZ) patients using the fusional features of multimodal MRI data. Here, we proposed an integrated model combining a 3D convolutional neural network (CNN) with a 2D CNN to classify SZ patients.

METHOD

Structural MRI (sMRI) and resting-state functional MRI (rs-fMRI) data were acquired for 140 SZ patients and 205 normal controls. We computed structural connectivity (SC) from the sMRI data as well as functional connectivity (FC), amplitude of low-frequency fluctuation (ALFF), and regional homogeneity (ReHo) from the rs-fMRI data. The 3D images of T1, ReHo, and ALFF were used as the inputs for the 3D CNN model, while the SC and FC matrices were used as the inputs for the 2D CNN model. Moreover, we added squeeze and excitation blocks (SE-blocks) to each layer of the integrated model and used a support vector machine (SVM) to replace the softmax classifier.

RESULTS

The integrated model proposed in this study, using the fusional features of the T1 images, and the matrices of FC, showed the best performance. The use of the SE-blocks and SVM classifiers significantly improved the performance of the integrated model, in which the accuracy, sensitivity, specificity, area under the curve, and F1-score were 89.86%, 86.21%, 92.50%, 89.35%, and 87.72%, respectively.

CONCLUSIONS

Our findings indicated that an integrated model combining 3D CNN with 2D CNN is a promising method to improve the classification performance of SZ patients and has potential for the clinical diagnosis of psychiatric diseases.

Prediction of the benign and malignant nature of masses in COPD background based on Habitat-based enhanced CT radiomics modeling: A preliminary study

BACKGROUND

It is difficult to differentiate between chronic obstructive pulmonary disease (COPD)-peripheral bronchogenic carcinoma (COPD-PBC) and inflammatory masses.

OBJECTIVE

This study aims to predict COPD-PBC based on clinical data and preoperative Habitat-based enhanced CT radiomics (HECT radiomics) modeling.

METHODS

A retrospective analysis was conducted on clinical imaging data of 232 cases of postoperative pathological confirmed PBC or inflammatory masses. The PBC group consisted of 82 cases, while the non-PBC group consisted of 150 cases. A training set and a testing set were established using a 7:3 ratio and a time cutoff point. In the training set, multiple models were established using clinical data and radiomics texture changes within different enhanced areas of the CT mass (HECT radiomics). The AUC values of each model were compared using Delong's test, and the clinical net benefit of the models was tested using decision curve analysis (DCA). The models were then externally validated in the testing set, and a nomogram of predicting COPD-PBC was created.

RESULTS

Univariate analysis confirmed that female gender, tumor morphology, CEA, Cyfra21-1, CT enhancement pattern, and Habitat-Radscore B/C were predictive factors for COPD-PBC (P< 0.05). The combination model based on these factors had significantly higher predictive performance [AUC: 0.894, 95% CI (0.836-0.936)] than the clinical data model [AUC: 0.758, 95% CI (0.685-0.822)] and radiomics model [AUC: 0.828, 95% CI (0.761-0.882)]. DCA also confirmed the higher clinical net benefit of the combination model, which was validated in the testing set. The nomogram developed based on the combination model helped predict COPD-PBC.

CONCLUSION

The combination model based on clinical data and Habitat-based enhanced CT radiomics can help differentiate COPD-PBC, providing a new non-invasive and efficient method for its diagnosis, treatment, and clinical decision-making.

Development and Validation of a Dual-Energy CT-Based Model for Predicting the Number of Central Lymph Node Metastases in Clinically Node-Negative Papillary Thyroid Carcinoma

RATIONALE AND OBJECTIVES

This study aimed to develop and validate a dual-energy CT (DECT)-based model for preoperative prediction of the number of central lymph node metastases (CLNMs) in clinically node-negative (cN0) papillary thyroid carcinoma (PTC) patients.

MATERIALS AND METHODS

Between January 2016 and January 2021, 490 patients who underwent lobectomy or thyroidectomy, CLN dissection, and preoperative DECT examinations were enrolled and randomly allocated into the training (N = 345) and validation cohorts (N = 145). The patients' clinical characteristics and quantitative DECT parameters obtained on primary tumors were collected. Independent predictors of> 5 CLNMs were identified and integrated to construct a DECT-based prediction model, for which the area under the curve (AUC), calibration, and clinical usefulness were assessed. Risk group stratification was performed to distinguish patients with different recurrence risks.

RESULTS

More than 5 CLNMs were found in 75 (15.3%) cN0 PTC patients. Age, tumor size, normalized iodine concentration (NIC), normalized effective atomic number (nZeff) and the slope of the spectral Hounsfield unit curve (λHu) in the arterial phase were independently associated with> 5 CLNMs. The DECT-based nomogram that incorporated predictors demonstrated favorable performance in both cohorts (AUC: 0.842 and 0.848) and significantly outperformed the clinical model (AUC: 0.688 and 0.694). The nomogram showed good calibration and added clinical benefit for predicting> 5 CLNMs. The KaplanMeier curves for recurrence-free survival showed that the high- and low-risk groups stratified by the nomogram were significantly different.

CONCLUSION

The nomogram based on DECT parameters and clinical factors could facilitate preoperative prediction of the number of CLNMs in cN0 PTC patients.

Sparse annotation learning for dense volumetric MR image segmentation with uncertainty estimation

Objective.Training neural networks for pixel-wise or voxel-wise image segmentation is a challenging task that requires a considerable amount of training samples with highly accurate and densely delineated ground truth maps. This challenge becomes especially prominent in the medical imaging domain, where obtaining reliable annotations for training samples is a difficult, time-consuming, and expert-dependent process. Therefore, developing models that can perform well under the conditions of limited annotated training data is desirable.Approach.In this study, we propose an innovative framework called the extremely sparse annotation neural network (ESA-Net) that learns with only the single central slice label for 3D volumetric segmentation which explores both intra-slice pixel dependencies and inter-slice image correlations with uncertainty estimation. Specifically, ESA-Net consists of four specially designed distinct components: (1) an intra-slice pixel dependency-guided pseudo-label generation module that exploits uncertainty in network predictions while generating pseudo-labels for unlabeled slices with temporal ensembling; (2) an inter-slice image correlation-constrained pseudo-label propagation module which propagates labels from the labeled central slice to unlabeled slices by self-supervised registration with rotation ensembling; (3) a pseudo-label fusion module that fuses the two sets of generated pseudo-labels with voxel-wise uncertainty guidance; and (4) a final segmentation network optimization module to make final predictions with scoring-based label quantification.Main results.Extensive experimental validations have been performed on two popular yet challenging magnetic resonance image segmentation tasks and compared to five state-of-the-art methods.Significance.Results demonstrate that our proposed ESA-Net can consistently achieve better segmentation performances even under the extremely sparse annotation setting, highlighting its effectiveness in exploiting information from unlabeled data.

Neuroprotective Action of Humanin and Humanin Analogues: Research Findings and Perspectives

Humanin is a 24-mer peptide first reported in the early 2000s as a new neuroprotective/cytoprotective factor rescuing neuronal cells from death induced by various Alzheimer's disease-associated insults. Nowadays it is known that humanin belongs to the novel class of the so-called mitochondrial-derived peptides (which are encoded by mitochondrial DNA) and has been shown to exert beneficial cytoprotective effects in a series of in vitro and/or in vivo experimental models of human diseases, including not only neurodegenerative disorders but other human diseases as well (e.g., age-related macular degeneration, cardiovascular diseases, or diabetes mellitus). This review article is focused on the presentation of recent in vitro and in vivo research results associated with the neuroprotective action of humanin as well as of various, mainly synthetic, analogues of the peptide; moreover, the main mode(s)/mechanism(s) through which humanin and humanin analogues may exert in vitro and in vivo regarding neuroprotection have been reported. The prospects of humanin and humanin analogues to be further investigated in the frame of future research endeavors against neurodegenerative/neural diseases have also been briefly discussed.

Longitudinal development of the human white matter structural connectome and its association with brain transcriptomic and cellular architecture

From childhood to adolescence, the spatiotemporal development pattern of the human brain white matter connectome and its underlying transcriptomic and cellular mechanisms remain largely unknown. With a longitudinal diffusion MRI cohort of 604 participants, we map the developmental trajectory of the white matter connectome from global to regional levels and identify that most brain network properties followed a linear developmental trajectory. Importantly, connectome-transcriptomic analysis reveals that the spatial development pattern of white matter connectome is potentially regulated by the transcriptomic architecture, with positively correlated genes involve in ion transport- and development-related pathways expressed in excitatory and inhibitory neurons, and negatively correlated genes enriches in synapse- and development-related pathways expressed in astrocytes, inhibitory neurons and microglia. Additionally, the macroscale developmental pattern is also associated with myelin content and thicknesses of specific laminas. These findings offer insights into the underlying genetics and neural mechanisms of macroscale white matter connectome development from childhood to adolescence.

Collaborative Multi-Metadata Fusion to Improve the Classification of Lumbar Disc Herniation

Computed tomography (CT) images are the most commonly used radiographic imaging modality for detecting and diagnosing lumbar diseases. Despite many outstanding advances, computer-aided diagnosis (CAD) of lumbar disc disease remains challenging due to the complexity of pathological abnormalities and poor discrimination between different lesions. Therefore, we propose a Collaborative Multi-Metadata Fusion classification network (CMMF-Net) to address these challenges. The network consists of a feature selection model and a classification model. We propose a novel Multi-scale Feature Fusion (MFF) module that can improve the edge learning ability of the network region of interest (ROI) by fusing features of different scales and dimensions. We also propose a new loss function to improve the convergence of the network to the internal and external edges of the intervertebral disc. Subsequently, we use the ROI bounding box from the feature selection model to crop the original image and calculate the distance features matrix. We then concatenate the cropped CT images, multiscale fusion features, and distance feature matrices and input them into the classification network. Next, the model outputs the classification results and the class activation map (CAM). Finally, the CAM of the original image size is returned to the feature selection network during the upsampling process to achieve collaborative model training. Extensive experiments demonstrate the effectiveness of our method. The model achieved 91.32% accuracy in the lumbar spine disease classification task. In the labelled lumbar disc segmentation task, the Dice coefficient reaches 94.39%. The classification accuracy in the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) reaches 91.82%.

Evaluation of tumor-infiltrating lymphocytes and mammographic density as predictors of response to neoadjuvant systemic therapy in breast cancer

BACKGROUND

Response rates vary among breast cancer patients treated with neoadjuvant systemic therapy (NAST). Thus, there is a need for reliable treatment predictors. Evidence suggests tumor-infiltrating lymphocytes (TILs) predict NAST response. Still, TILs are seldom used clinically as a treatment determinant. Mammographic density (MD) is another potential marker for NAST benefit and its relationship with TILs is unknown. Our aims were to investigate TILs and MD as predictors of NAST response and to study the unexplored relationship between TILs and MD.

MATERIAL AND METHODS

We studied 315 invasive breast carcinomas treated with NAST between 2013 and 2020. Clinicopathological data were retrieved from medical records. The endpoint was defined as pathological complete response (pCR) in the breast. TILs were evaluated in pre-treatment core biopsies and categorized as high (≥10%) or low (<10%). MD was scored (a-d) according to the breast imaging reporting and data system (BI-RADS) fifth edition. Binary logistic regression and Spearman's test of correlation were performed using SPSS.

RESULTS

Out of 315 carcinomas, 136 achieved pCR. 94 carcinomas had high TILs and 215 had low TILs. Six carcinomas had no available TIL data. The number of carcinomas in each BI-RADS category were 37, 122, 112, and 44 for a, b, c, and d, respectively. High TILs were independently associated with pCR (OR: 2.95; 95% CI: 1.59-5.46) compared to low TILs. In the univariable analysis, MD (BI-RADS d vs. a) showed a tendency of higher likelihood for pCR (OR: 2.43; 95% CI: 0.99-5.98). However, the association was non-significant, which is consistent with the result of the multivariable analysis (OR: 2.51; 95% CI: 0.78-8.04). We found no correlation between TILs and MD (0.02; p = .80).

CONCLUSION

TILs significantly predicted NAST response. We could not define MD as a significant predictor of NAST response. These findings should be further replicated.

A Review of AI-Based Radiomics and Computational Pathology Approaches in Triple-Negative Breast Cancer: Current Applications and Perspectives

Breast cancer is one of the most common and deadly cancers worldwide. Approximately, 20% of all breast cancers are characterized as triple negative (TNBC). TNBC typically is associated with a poorer prognosis relative to other breast cancer subtypes. Due to its aggressiveness and lack of response to hormonal therapy, conventional cytotoxic chemotherapy is the usual treatment; however, this treatment is not always effective, and an important percentage of patients develop recurrence. More recently, immunotherapy has started to be used on some populations with TNBC showing promising results. Unfortunately, immunotherapy is only applicable to a minority of patients and responses in metastatic TNBC have overall been modest in comparison to other cancer types. This situation evidences the need for developing effective biomarkers that help to stratify and personalize patient management. Thanks to recent advances in artificial intelligence (AI), there has been an increasing interest in its use for medical applications aiming at supporting clinical decision making. Several works have used AI in combination with diagnostic medical imaging, more specifically radiology and digitized histopathological tissue samples, aiming to extract disease-specific information that is difficult to quantify by the human eye. These works have demonstrated that analysis of such images in the context of TNBC has great potential for (1) risk-stratifying patients to identify those patients who are more likely to experience disease recurrence or die from the disease and (2) predicting pathologic complete response. In this manuscript, we present an overview on AI and its integration with radiology and histopathological images for developing prognostic and predictive approaches for TNBC. We present state of the art approaches in the literature and discuss the opportunities and challenges with developing AI algorithms regarding further development and clinical deployment, including identifying those patients who may benefit from certain treatments (e.g., adjuvant chemotherapy) from those who may not and thereby should be directed toward other therapies, discovering potential differences between populations, and identifying disease subtypes.

DC-AAE: Dual channel adversarial autoencoder with multitask learning for KL-grade classification in knee radiographs

Knee osteoarthritis (OA) is a frequent musculoskeletal disorder that leads to physical disability in older adults. Manual OA assessment is performed via visual inspection, which is highly subjective as it suffers from moderate to high inter-observer variability. Many deep learning-based techniques have been proposed to address this issue. However, owing to the limited amount of labelled data, all existing solutions have limitations in terms of performance or the number of classes. This paper proposes a novel fully automatic Kellgren and Lawrence (KL) grade classification scheme in knee radiographs. We developed a semi-supervised multi-task learning-based approach that enables the exploitation of additional unlabelled data in an unsupervised as well as supervised manner. Specifically, we propose a dual-channel adversarial autoencoder, which is first trained in an unsupervised manner for reconstruction tasks only. To exploit the additional data in a supervised way, we propose a multi-task learning framework by introducing an auxiliary task. In particular, we use leg side identification as an auxiliary task, which allows the use of more datasets, e.g., CHECK dataset. The work demonstrates that the utilization of additional data can improve the primary task of KL-grade classification for which only limited labelled data is available. This semi-supervised learning essentially helps to improve the feature learning ability of our framework, which leads to improved performance for KL-grade classification. We rigorously evaluated our proposed model on the two largest publicly available datasets for various aspects, i.e., overall performance, the effect of additional unlabelled samples and auxiliary tasks, robustness analysis, and ablation study. The proposed model achieved the accuracy, precision, recall, and F1 score of 75.53%, 74.1%, 78.51%, and 75.34%, respectively. Furthermore, the experimental results show that the suggested model not only achieves state-of-the-art performance on two publicly available datasets but also exhibits remarkable robustness.