Automatic Quantification of Abnormal Lung Parenchymal Attenuation on Chest Computed Tomography Images Using Densitometry and Texture-based Analysis.

PURPOSE: To compare texture-based analysis using convolutional neural networks (CNNs) against lung densitometry in detecting chest computed tomography (CT) image abnormalities. MATERIAL AND METHODS: A U-NET was used for lung segmentation, and an ensemble of 7 CNN architectures was trained for the classification of low-attenuation areas (LAAs; emphysema, cysts), normal-attenuation areas (NAAs; normal parenchyma), and high-attenuation areas (HAAs; ground-glass opacities, crazy paving/linear opacity, consolidation). Lung densitometry also computes (LAAs, ≤-950 HU), NAAs (-949 to -700 HU), and HAAs (-699 to -250 HU). CNN-based and densitometry-based severity indices (CNN and Dens, respectively) were calculated as (LAA+HAA)/(LAA+NAA+HAA) in 812 CT scans from 176 normal subjects, 343 patients with emphysema, and 293 patients with interstitial lung disease (ILD). The correlation between CNN-derived and densitometry-derived indices was analyzed, alongside a comparison of severity indices among patient subgroups with emphysema and ILD, using the Spearman correlation and ANOVA with Bonferroni correction. RESULTS: CNN-derived and densitometry-derived severity indices (SIs) showed a strong correlation (ρ=0.90) and increased with disease severity. CNN-SIs differed from densitometry SIs, being lower for emphysema and higher for moderate to severe ILD cases. CNN estimations for normal attenuation areas were higher than those from densitometry across all groups, indicating a potential for more accurate characterization of lung abnormalities. CONCLUSIONS: CNN outputs align closely with densitometry in assessing lung abnormalities on CT scans, offering improved estimates of normal areas and better distinguishing similar abnormalities. However, this requires higher computing power.

Natural Language Processing for the Identification of Incidental Lung Nodules in Computed Tomography Reports: A Quality Control Tool.

PURPOSE: To evaluate the diagnostic performance of a natural language processing (NLP) model in detecting incidental lung nodules (ILNs) in unstructured chest computed tomography (CT) reports. METHODS: All unstructured consecutive reports of chest CT scans performed at a tertiary hospital between 2020 and 2021 were retrospectively reviewed (n = 21,542) to train the NLP tool. Internal validation was performed using reference readings by two radiologists of both CT scans and reports, using a different external cohort of 300 chest CT scans. Second, external validation was performed in a cohort of all random unstructured chest CT reports from 57 different hospitals conducted in May 2022. A review by the same thoracic radiologists was used as the gold standard. The sensitivity, specificity, and accuracy were calculated. RESULTS: Of 21,542 CT reports, 484 mentioned at least one ILN (mean age, 71 ± 17.6 [standard deviation] years; women, 52%) and were included in the training set. In the internal validation (n = 300), the NLP tool detected ILN with a sensitivity of 100.0% (95% CI, 97.6 to 100.0), a specificity of 95.9% (95% CI, 91.3 to 98.5), and an accuracy of 98.0% (95% CI, 95.7 to 99.3). In the external validation (n = 977), the NLP tool yielded a sensitivity of 98.4% (95% CI, 94.5 to 99.8), a specificity of 98.6% (95% CI, 97.5 to 99.3), and an accuracy of 98.6% (95% CI, 97.6 to 99.2). Twelve months after the initial reports, 8 (8.60%) patients had a final diagnosis of lung cancer, among which 2 (2.15%) would have been lost to follow-up without the NLP tool. CONCLUSION: NLP can be used to identify ILNs in unstructured reports with high accuracy, allowing a timely recall of patients and a potential diagnosis of early-stage lung cancer that might have been lost to follow-up.

Self-blame in major depression: a randomised pilot trial comparing fMRI neurofeedback with self-guided psychological strategies.

BACKGROUND: Overgeneralised self-blame and worthlessness are key symptoms of major depressive disorder (MDD) and have previously been associated with self-blame-selective changes in connectivity between right superior anterior temporal lobe (rSATL) and subgenual frontal cortices. Another study showed that remitted MDD patients were able to modulate this neural signature using functional magnetic resonance imaging (fMRI) neurofeedback training, thereby increasing their self-esteem. The feasibility and potential of using this approach in symptomatic MDD were unknown. METHOD: This single-blind pre-registered randomised controlled pilot trial probed a novel self-guided psychological intervention with and without additional rSATL-posterior subgenual cortex (BA25) fMRI neurofeedback, targeting self-blaming emotions in people with insufficiently recovered MDD and early treatment-resistance (n = 43, n = 35 completers). Participants completed three weekly self-guided sessions to rebalance self-blaming biases. RESULTS: As predicted, neurofeedback led to a training-induced reduction in rSATL-BA25 connectivity for self-blame v. other-blame. Both interventions were safe and resulted in a 46% reduction on the Beck Depression Inventory-II, our primary outcome, with no group differences. Secondary analyses, however, revealed that patients without DSM-5-defined anxious distress showed a superior response to neurofeedback compared with the psychological intervention, and the opposite pattern in anxious MDD. As predicted, symptom remission was associated with increases in self-esteem and this correlated with the frequency with which participants employed the psychological strategies in daily life. CONCLUSIONS: These findings suggest that self-blame-rebalance neurofeedback may be superior over a solely psychological intervention in non-anxious MDD, although further confirmatory studies are needed. Simple self-guided strategies tackling self-blame were beneficial, but need to be compared against treatment-as-usual in further trials. https://doi.org/10.1186/ISRCTN10526888.

Increased Lung Immune Metabolic Activity in COVID-19 Survivors.

PURPOSE: We quantified lung glycolytic metabolic activity, clinical symptoms and inflammation, coagulation, and endothelial activation biomarkers in 2019 coronavirus disease (COVID-19) pneumonia survivors. METHODS: Adults previously hospitalized with moderate to severe COVID-19 pneumonia were prospectively included. Subjects filled out a questionnaire on clinical consequences, underwent chest CT and 18 F-FDG PET/CT, and provided blood samples on the same day. Forty-five volunteers served as control subjects. Analysis of CT images and quantitative voxel-based analysis of PET/CT images were performed for both groups. 18 F-FDG uptake in the whole-lung volume and in high- and low-attenuation areas was calculated and normalized to liver values. Quantification of plasma markers of inflammation (interleukin 6), d -dimer, and endothelial cell activation (angiopoietins 1 and 2, vascular cell adhesion molecule 1, and intercellular adhesion molecule 1) was also performed. RESULTS: We enrolled 53 COVID-19 survivors (62.3% were male; median age, 50 years). All survivors reported at least 1 persistent symptom, and 41.5% reported more than 6 symptoms. The mean lung density was greater in survivors than in control subjects, and more metabolic activity was observed in normal and dense lung areas, even months after symptom onset. Plasma proinflammatory, coagulation, and endothelial activation biomarker concentrations were also significantly higher in survivors. CONCLUSION: We observed more metabolic activity in areas of high and normal lung attenuation several months after moderate to severe COVID-19 pneumonia. In addition, plasma markers of thromboinflammation and endothelial activation persisted. These findings may have implications for our understanding of the in vivo pathogenesis and long-lasting effects of COVID-19 pneumonia.

Striatal and septo-hypothalamic responses to anticipation and outcome of affiliative rewards.

Humans are intrinsically motivated to bond with others. The ability to experience affiliative emotions (such as affection/tenderness, sexual attraction, and admiration/awe) may incentivize and promote these affiliative bonds. Here, we interrogate the role of the critical reward circuitry, especially the Nucleus Accumbens (NAcc) and the septo-hypothalamic region, in the anticipation of and response to affiliative rewards using a novel incentive delay task. During Functional Magnetic Resonance Imaging (FMRI), participants (n = 23 healthy humans; 14 female) anticipated and watched videos involving affiliative (tenderness, erotic desire, and awe) and nonaffiliative (i.e., food) rewards, as well as neutral scenes. On the one hand, anticipation of both affiliative and nonaffiliative rewards increased activity in the NAcc, anterior insula, and supplementary motor cortex, but activity in the amygdala and the ventromedial prefrontal cortex (vmPFC) increased in response to reward outcomes. On the other hand, affiliative rewards more specifically increased activity in the septo-hypothalamic area. Moreover, NAcc activity during anticipation correlated with positive arousal for all rewards, whereas septo-hypothalamic activity during the outcome correlated with positive arousal and motivation for subsequent re-exposure only for affiliative rewards. Together, these findings implicate a general appetitive response in the NAcc to different types of rewards but suggests a more specific response in the septo-hypothalamic region in response to affiliative rewards outcomes. This work also presents a new task for distinguishing between neural responses to affiliative and non-affiliative rewards.

Blame-rebalance fMRI neurofeedback in major depressive disorder: A randomised proof-of-concept trial.

Previously, using fMRI, we demonstrated lower connectivity between right anterior superior temporal (ATL) and anterior subgenual cingulate (SCC) regions while patients with major depressive disorder (MDD) experience guilt. This neural signature was detected despite symptomatic remission which suggested a putative role in vulnerability. This randomised controlled double-blind parallel group clinical trial investigated whether patients with MDD are able to voluntarily modulate this neural signature. To this end, we developed a fMRI neurofeedback software (FRIEND), which measures ATL-SCC coupling and displays its levels in real time. Twenty-eight patients with remitted MDD were randomised to two groups, each receiving one session of fMRI neurofeedback whilst retrieving guilt and indignation/anger-related autobiographical memories. They were instructed to feel the emotion whilst trying to increase the level of a thermometer-like display on a screen. Active intervention group: The thermometer levels increased with increasing levels of ATL-SCC correlations in the guilt condition. Control intervention group: The thermometer levels decreased when correlation levels deviated from the previous baseline level in the guilt condition, thus reinforcing stable correlations. Both groups also received feedback during the indignation condition reinforcing stable correlations. We confirmed our predictions that patients in the active intervention group were indeed able to increase levels of ATL-SCC correlations for guilt vs. indignation and their self-esteem after training compared to before training and that this differed significantly from the control intervention group. These data provide proof-of-concept for a novel treatment target for MDD patients and are in keeping with the hypothesis that ATL-SCC connectivity plays a key role in self-worth. https://clinicaltrials.gov/ct2/show/results/NCT01920490.

Emotion Regulation Using Virtual Environments and Real-Time fMRI Neurofeedback.

Neurofeedback (NFB) enables the voluntary regulation of brain activity, with promising applications to enhance and recover emotion and cognitive processes, and their underlying neurobiology. It remains unclear whether NFB can be used to aid and sustain complex emotions, with ecological validity implications. We provide a technical proof of concept of a novel real-time functional magnetic resonance imaging (rtfMRI) NFB procedure. Using rtfMRI-NFB, we enabled participants to voluntarily enhance their own neural activity while they experienced complex emotions. The rtfMRI-NFB software (FRIEND Engine) was adapted to provide a virtual environment as brain computer interface (BCI) and musical excerpts to induce two emotions (tenderness and anguish), aided by participants' preferred personalized strategies to maximize the intensity of these emotions. Eight participants from two experimental sites performed rtfMRI-NFB on two consecutive days in a counterbalanced design. On one day, rtfMRI-NFB was delivered to participants using a region of interest (ROI) method, while on the other day using a support vector machine (SVM) classifier. Our multimodal VR/NFB approach was technically feasible and robust as a method for real-time measurement of the neural correlates of complex emotional states and their voluntary modulation. Guided by the color changes of the virtual environment BCI during rtfMRI-NFB, participants successfully increased in real time, the activity of the septo-hypothalamic area and the amygdala during the ROI based rtfMRI-NFB, and successfully evoked distributed patterns of brain activity classified as tenderness and anguish during SVM-based rtfMRI-NFB. Offline fMRI analyses confirmed that during tenderness rtfMRI-NFB conditions, participants recruited the septo-hypothalamic area and other regions ascribed to social affiliative emotions (medial frontal / temporal pole and precuneus). During anguish rtfMRI-NFB conditions, participants recruited the amygdala and other dorsolateral prefrontal and additional regions associated with negative affect. These findings were robust and were demonstrable at the individual subject level, and were reflected in self-reported emotion intensity during rtfMRI-NFB, being observed with both ROI and SVM methods and across the two sites. Our multimodal VR/rtfMRI-NFB protocol provides an engaging tool for brain-based interventions to enhance emotional states in healthy subjects and may find applications in clinical conditions associated with anxiety, stress and impaired empathy among others.

Altruistic decisions following penetrating traumatic brain injury.

The cerebral correlates of altruistic decisions have increasingly attracted the interest of neuroscientists. To date, investigations on the neural underpinnings of altruistic decisions have primarily been conducted in healthy adults undergoing functional neuroimaging as they engaged in decisions to punish third parties. The chief purpose of the present study was to investigate altruistic decisions following focal brain damage with a novel altruistic decision task. In contrast to studies that have focused either on altruistic punishment or donation, the Altruistic Decision Task allows players to anonymously punish or donate to 30 charitable organizations involved with salient societal issues such as abortion, nuclear energy and civil rights. Ninety-four Vietnam War veterans with variable patterns of penetrating traumatic brain injury and 28 healthy veterans who also served in combat participated in the study as normal controls. Participants were asked to invest $1 to punish or reward real societal organizations, or keep the money for themselves. Associations between lesion distribution and performance on the task were analysed with multivariate support vector regression, which enables the assessment of the joint contribution of multiple regions in the determination of a given behaviour of interest. Our main findings were: (i) bilateral dorsomedial prefrontal lesions increased altruistic punishment, whereas lesions of the right perisylvian region and left temporo-insular cortex decreased punishment; (ii) altruistic donations were increased by bilateral lesions of the dorsomedial parietal cortex, whereas lesions of the right posterior superior temporal sulcus and middle temporal gyri decreased donations; (iii) altruistic punishment and donation were only weakly correlated, emphasizing their dissociable neuroanatomical associations; and (iv) altruistic decisions were not related to post-traumatic personality changes. These findings indicate that altruistic punishment and donation are determined by largely non-overlapping cerebral regions, which have previously been implicated in social cognition and moral experience such as evaluations of intentionality and intuitions of justice and morality.10.1093/brain/awy064_video1awy064media15758316955001.

Identifying musical pieces from fMRI data using encoding and decoding models.

Encoding models can reveal and decode neural representations in the visual and semantic domains. However, a thorough understanding of how distributed information in auditory cortices and temporal evolution of music contribute to model performance is still lacking in the musical domain. We measured fMRI responses during naturalistic music listening and constructed a two-stage approach that first mapped musical features in auditory cortices and then decoded novel musical pieces. We then probed the influence of stimuli duration (number of time points) and spatial extent (number of voxels) on decoding accuracy. Our approach revealed a linear increase in accuracy with duration and a point of optimal model performance for the spatial extent. We further showed that Shannon entropy is a driving factor, boosting accuracy up to 95% for music with highest information content. These findings provide key insights for future decoding and reconstruction algorithms and open new venues for possible clinical applications.

FRIEND Engine Framework: a real time neurofeedback client-server system for neuroimaging studies.

In this methods article, we present a new implementation of a recently reported FSL-integrated neurofeedback tool, the standalone version of "Functional Real-time Interactive Endogenous Neuromodulation and Decoding" (FRIEND). We will refer to this new implementation as the FRIEND Engine Framework. The framework comprises a client-server cross-platform solution for real time fMRI and fMRI/EEG neurofeedback studies, enabling flexible customization or integration of graphical interfaces, devices, and data processing. This implementation allows a fast setup of novel plug-ins and frontends, which can be shared with the user community at large. The FRIEND Engine Framework is freely distributed for non-commercial, research purposes.

Enhancing Motor Network Activity Using Real-Time Functional MRI Neurofeedback of Left Premotor Cortex.

Neurofeedback by functional magnetic resonance imaging (fMRI) is a technique of potential therapeutic relevance that allows individuals to be aware of their own neurophysiological responses and to voluntarily modulate the activity of specific brain regions, such as the premotor cortex (PMC), important for motor recovery after brain injury. We investigated (i) whether healthy human volunteers are able to up-regulate the activity of the left PMC during a right hand finger tapping motor imagery (MI) task while receiving continuous fMRI-neurofeedback, and (ii) whether successful modulation of brain activity influenced non-targeted motor control regions. During the MI task, participants of the neurofeedback group (NFB) received ongoing visual feedback representing the level of fMRI responses within their left PMC. Control (CTL) group participants were shown similar visual stimuli, but these were non-contingent on brain activity. Both groups showed equivalent levels of behavioral ratings on arousal and MI, before and during the fMRI protocol. In the NFB, but not in CLT group, brain activation during the last run compared to the first run revealed increased activation in the left PMC. In addition, the NFB group showed increased activation in motor control regions extending beyond the left PMC target area, including the supplementary motor area, basal ganglia and cerebellum. Moreover, in the last run, the NFB group showed stronger activation in the left PMC/inferior frontal gyrus when compared to the CTL group. Our results indicate that modulation of PMC and associated motor control areas can be achieved during a single neurofeedback-fMRI session. These results contribute to a better understanding of the underlying mechanisms of MI-based neurofeedback training, with direct implications for rehabilitation strategies in severe brain disorders, such as stroke.

Functional dissociation of ventral frontal and dorsomedial default mode network components during resting state and emotional autobiographical recall.

Humans spend a substantial share of their lives mind-wandering. This spontaneous thinking activity usually comprises autobiographical recall, emotional, and self-referential components. While neuroimaging studies have demonstrated that a specific brain "default mode network" (DMN) is consistently engaged by the "resting state" of the mind, the relative contribution of key cognitive components to DMN activity is still poorly understood. Here we used fMRI to investigate whether activity in neural components of the DMN can be differentially explained by active recall of relevant emotional autobiographical memories as compared with the resting state. Our study design combined emotional autobiographical memory, neutral memory and resting state conditions, separated by a serial subtraction control task. Shared patterns of activation in the DMN were observed in both emotional autobiographical and resting conditions, when compared with serial subtraction. Directly contrasting autobiographical and resting conditions demonstrated a striking dissociation within the DMN in that emotional autobiographical retrieval led to stronger activation of the dorsomedial core regions (medial prefrontal cortex, posterior cingulate cortex), whereas the resting state condition engaged a ventral frontal network (ventral striatum, subgenual and ventral anterior cingulate cortices) in addition to the IPL. Our results reveal an as yet unreported dissociation within the DMN. Whereas the dorsomedial component can be explained by emotional autobiographical memory, the ventral frontal one is predominantly associated with the resting state proper, possibly underlying fundamental motivational mechanisms engaged during spontaneous unconstrained ideation.

Voluntary enhancement of neural signatures of affiliative emotion using FMRI neurofeedback.

In Ridley Scott's film "Blade Runner", empathy-detection devices are employed to measure affiliative emotions. Despite recent neurocomputational advances, it is unknown whether brain signatures of affiliative emotions, such as tenderness/affection, can be decoded and voluntarily modulated. Here, we employed multivariate voxel pattern analysis and real-time fMRI to address this question. We found that participants were able to use visual feedback based on decoded fMRI patterns as a neurofeedback signal to increase brain activation characteristic of tenderness/affection relative to pride, an equally complex control emotion. Such improvement was not observed in a control group performing the same fMRI task without neurofeedback. Furthermore, the neurofeedback-driven enhancement of tenderness/affection-related distributed patterns was associated with local fMRI responses in the septohypothalamic area and frontopolar cortex, regions previously implicated in affiliative emotion. This demonstrates that humans can voluntarily enhance brain signatures of tenderness/affection, unlocking new possibilities for promoting prosocial emotions and countering antisocial behavior.

Real-time fMRI pattern decoding and neurofeedback using FRIEND: an FSL-integrated BCI toolbox.

The demonstration that humans can learn to modulate their own brain activity based on feedback of neurophysiological signals opened up exciting opportunities for fundamental and applied neuroscience. Although EEG-based neurofeedback has been long employed both in experimental and clinical investigation, functional MRI (fMRI)-based neurofeedback emerged as a promising method, given its superior spatial resolution and ability to gauge deep cortical and subcortical brain regions. In combination with improved computational approaches, such as pattern recognition analysis (e.g., Support Vector Machines, SVM), fMRI neurofeedback and brain decoding represent key innovations in the field of neuromodulation and functional plasticity. Expansion in this field and its applications critically depend on the existence of freely available, integrated and user-friendly tools for the neuroimaging research community. Here, we introduce FRIEND, a graphic-oriented user-friendly interface package for fMRI neurofeedback and real-time multivoxel pattern decoding. The package integrates routines for image preprocessing in real-time, ROI-based feedback (single-ROI BOLD level and functional connectivity) and brain decoding-based feedback using SVM. FRIEND delivers an intuitive graphic interface with flexible processing pipelines involving optimized procedures embedding widely validated packages, such as FSL and libSVM. In addition, a user-defined visual neurofeedback module allows users to easily design and run fMRI neurofeedback experiments using ROI-based or multivariate classification approaches. FRIEND is open-source and free for non-commercial use. Processing tutorials and extensive documentation are available.

Identification of psychopathic individuals using pattern classification of MRI images.

BACKGROUND: Psychopathy is a disorder of personality characterized by severe impairments of social conduct, emotional experience, and interpersonal behavior. Psychopaths consistently violate social norms and bring considerable financial, emotional, or physical harm to others and to society as a whole. Recent developments in analysis methods of magnetic resonance imaging (MRI), such as voxel-based-morphometry (VBM), have become major tools to understand the anatomical correlates of this disorder. Nevertheless, the identification of psychopathy by neuroimaging or other neurobiological tools (e.g., genetic testing) remains elusive. METHODS/PRINCIPAL FINDINGS: The main aim of this study was to develop an approach to distinguish psychopaths from healthy controls, based on the integration between pattern recognition methods and gray matter quantification. We employed support vector machines (SVM) and maximum uncertainty linear discrimination analysis (MLDA), with a feature-selection algorithm. Imaging data from 15 healthy controls and 15 psychopathic individuals (7 women in each group) were analyzed with SPM2 and the optimized VBM preprocessing routines. Participants were scanned with a 1.5 Tesla MRI system. Both SVM and MLDA achieved an overall leave-one-out accuracy of 80%, but SVM mapping was sparser than using MLDA. The superior temporal sulcus/gyrus (bilaterally) was identified as a region containing the most relevant information to separate the two groups. CONCLUSION/SIGNIFICANCE: These results indicate that gray matter quantitative measures contain robust information to predict high psychopathy scores in individual subjects. The methods employed herein might prove useful as an adjunct to the established clinical and neuropsychological measures in patient screening and diagnostic accuracy.