Aphasia assessment plays a crucial role in rehabilitating people with aphasia (PWA), including classifying healthy individuals, identifying subtypes of aphasia, and assessing severity. This study explores unsupervised clustering methods in aphasic speech data, comparing five feature extraction approaches and four clustering algorithms. Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), Agglomerative clustering, K-means, and Gaussian Mixture Models. The focus is on distinguishing between fluent and non-fluent aphasia and subtypes such as Broca's, Wernicke's, and anomic aphasia. The feature extraction methods include Mel-Frequency Cepstral Coefficients (MFCCs), OpenL3 embeddings, their combination, and a fusion of MFCC with chroma features, spectral contrast, zero-crossing rate, and a novel deep convolutional autoencoder-based (CAE) model. These methods are evaluated for their ability to capture key characteristics of aphasic speech, with the clustering results assessed using intrinsic evaluation metrics. Our findings highlight the effectiveness of different feature extraction methods, with CAE emerging as the most effective approach in distinguishing aphasic speech categories and improving clustering performance. This research highlights the potential of unsupervised learning in aphasia research and offers insight into automated diagnosis and speech therapy tools, contributing to enhanced aphasia assessment and rehabilitation.

The convoluted network of myelinated fibers that supports behavior, cognition, and sensory processing in the human brain is the source of its extraordinary complexity. Advancements in tissue optical clearing, 3D fluorescence microscopy, and automated image analysis have enabled unprecedented insights into the architecture of these networks. Here, we investigate the multiscale organization of myelinated fibers in human brain tissue from the brainstem, Broca's area, hippocampus, and primary visual cortex by exploiting a specific fiber staining method, light-sheet fluorescence microscopy (LSFM), and an advanced spatial orientation analysis tool. Using an optimized protocol that integrates tissue clearing with the lipophilic DiD probe to achieve uniform and deep myelinated fiber labeling, we generate micrometer-resolution volumetric reconstructions of multiple brain regions through an inverted LSFM. Automated image processing, employing unsupervised 3D multiscale Frangi filters, provides orientation distribution functions and local orientation dispersion maps. This enables precise characterization of the directionality of white matter bundles, linking mesoscopic structural properties to orientation details computed at the native micrometric resolution of the LSFM apparatus. The presented workflow illustrates a robust platform for large-scale, high-resolution brain mapping, which may facilitate the investigation of pathological alterations with unparalleled spatial resolution and, furthermore, the validation of other neuroimaging modalities.

The convoluted network of myelinated fibers that supports behavior, cognition, and sensory processing in the human brain is the source of its extraordinary complexity. Advancements in tissue optical clearing, 3D fluorescence microscopy, and automated image analysis have enabled unprecedented insights into the architecture of these networks. Here, we investigate the multiscale organization of myelinated fibers in human brain tissue from the brainstem, Broca's area, hippocampus, and primary visual cortex by exploiting a specific fiber staining method, light-sheet fluorescence microscopy (LSFM), and an advanced spatial orientation analysis tool. Using an optimized protocol that integrates tissue clearing with the lipophilic DiD probe to achieve uniform and deep myelinated fiber labeling, we generate micrometerresolution volumetric reconstructions of multiple brain regions through an inverted LSFM. Automated image processing, employing unsupervised 3D multiscale Frangi filters, provides orientation distribution functions and local orientation dispersion maps. This enables precise characterization of the directionality of white matter bundles, linking mesoscopic structural properties to orientation details computed at the native micrometric resolution of the LSFM apparatus. The presented workflow illustrates a robust platform for large-scale, high-resolution brain mapping, which may facilitate the investigation of pathological alterations with unparalleled spatial resolution and, furthermore, the validation of other neuroimaging modalities.

With over 55 million people globally affected by dementia and nearly 10 million new cases reported annually, Alzheimer's disease is a prevalent and challenging neurodegenerative disorder. Despite significant advancements in machine learning techniques for Alzheimer's disease detection, the widespread adoption of deep learning models raises concerns about their explainability. The lack of explainability in deep learning models for online handwriting analysis is a critical gap in the literature in the context of Alzheimer's disease detection. This paper addresses this challenge by interpreting predictions from a Convolutional Neural Network applied to multivariate time series data, generated by online handwriting data associated with continuous loop series handwritten on a graphical tablet. Our explainability methods reveal distinct motor behavior characteristics for healthy individuals and those diagnosed with Alzheimer's. Healthy subjects exhibited consistent, smooth movements, while Alzheimer's patients demonstrated erratic patterns marked by abrupt stops and direction changes. This emphasizes the critical role of explainability in translating complex models into clinically relevant insights. Our research contributes to the enhancement of early diagnosis, providing significant and reliable insights to stakeholders involved in patient care and intervention strategies. Our work bridges the gap between machine learning predictions and clinical insights, fostering a more effective and understandable application of advanced models for Alzheimer's disease assessment.

Parkinson's disease (PD) exhibits significant clinical heterogeneity, presenting challenges in the identification of reliable electroencephalogram (EEG) biomarkers. Machine learning techniques have been integrated with resting-state EEG for PD diagnosis, but their practicality is constrained by the interpretable features and the stochastic nature of resting-state EEG. The present study proposes a novel and interpretable deep learning model, graph signal processing-graph convolutional networks (GSP-GCNs), using event-related EEG data obtained from a specific task involving vocal pitch regulation for PD diagnosis. By incorporating both local and global information from single-hop and multi-hop networks, our proposed GSP-GCNs models achieved an averaged classification accuracy of 90.2%, exhibiting a significant improvement of 9.5% over other deep learning models. Moreover, the interpretability analysis revealed discriminative distributions of large-scale EEG networks and topographic map of microstate MS5 learned by our models, primarily located in the left ventral premotor cortex, superior temporal gyrus, and Broca's area that are implicated in PD-related speech disorders, reflecting our GSP-GCN models' ability to provide interpretable insights identifying distinctive EEG biomarkers from large-scale networks. These findings demonstrate the potential of interpretable deep learning models coupled with voice-related EEG signals for distinguishing PD patients from healthy controls with accuracy and elucidating the underlying neurobiological mechanisms.

Speech imagery recognition from electroencephalograms (EEGs) could potentially become a strong contender among non-invasive brain-computer interfaces (BCIs). In this report, first we extract language representations as the difference of line-spectra of phones by statistically analyzing many EEG signals from the Broca area. Then we extract vowels by using iterative search from hand-labeled short-syllable data. The iterative search process consists of principal component analysis (PCA) that visualizes linguistic representation of vowels through eigen-vectors φ(m), and subspace method (SM) that searches an optimum line-spectrum for redesigning φ(m). The extracted linguistic representation of Japanese vowels /i/ /e/ /a/ /o/ /u/ shows 2 distinguished spectral peaks (P1, P2) in the upper frequency range. The 5 vowels are aligned on the P1-P2 chart. A 5-vowel recognition experiment using a data set of 5 subjects and a convolutional neural network (CNN) classifier gave a mean accuracy rate of 72.6%.

In this study, we aimed to differentiate between euthymic bipolar disorder (BD) patients and healthy controls (HC) based on frontal activity measured by fNIRS that were converted to spectrograms with Convolutional Neural Networks (CNN). And also, we investigated brain regions that cause this distinction. In total, 29 BD patients and 28 HCs were recruited. Their brain cortical activities were measured using fNIRS while performing letter versions of VFT. Each one of the 24 fNIRS channels was converted to a 2D spectrogram on which a CNN architecture was designed and utilized for classification. We found that our CNN algorithm using fNIRS activity during a VFT is able to differentiate subjects with BD from healthy controls with 90% accuracy, 80% sensitivity, and 100% specificity. Moreover, validation performance reached an AUC of 94%. From our individual channel analyses, we observed channels corresponding to the left inferior frontal gyrus (left-IFC), medial frontal cortex (MFC), right dorsolateral prefrontal cortex (DLPFC), Broca area, and right premotor have considerable activity variation to distinguish patients from HC. fNIRS activity during VFT can be used as a potential marker to classify euthymic BD patients from HCs. Activity particularly in the MFC, left-IFC, Broca's area, and DLPFC have a considerable variation to distinguish patients from healthy controls.

Of all the nineteenth-century physicians whose names still resonate today, Armand Trousseau is perhaps the one most familiar, for his description of carpal spasm as a sign of hypocalcemia (Trousseau's sign) and his description of the hypercoagulable state associated with cancer (Trousseau's syndrome). In the last three years of his life, Trousseau turned his attention to aphasia, which he included in his 1864 and 1865 lectures given at Hôtel-Dieu Hospital in Paris and which he discussed in an address to the Imperial Academy of Medicine in 1865. Trousseau preceded Wernicke in describing aphasia as a symptom complex, in which he included Broca's aphemia, receptive aphasia, the inability to read with and without the inability to write (alexia with and without agraphia), the inability to name common objects (amnesic aphasia or anomia) and to recognize numbers (acalculia), and the inability to draw. Trousseau concluded that such a varied symptomatology could not arise from a single area, and he proposed that lesions of the posterior inferior frontal convolution identified by Broca, of the insula and corpus striatum and of the temporal and parietal lobes, could give rise to aphasia. The role of the posterior temporal lobe in receptive aphasia was confirmed by Wernicke in 1874, and the role of the inferior parietal lobule in agraphia and alexia was confirmed by Dejerine in 1891. Trousseau thought that aphasia resulted from the loss of the memory for words and for the synergistic actions of the movements of articulations learned in early childhood. Trousseau added inattention, lack of comprehension, and cognitive decline to amnesia as contributing factors to the verbal and nonverbal expression of thought. Trousseau constructed a comprehensive theory of aphasia that unified its semiology, localization, and pathophysiology. This construct had the virtue of being predictive and falsifiable by the clinico-pathological method. Through insight born of observation, Trousseau identified the issues that dominated aphasiology into the twenty-first century.

Background: Pre-surgical functional localization of eloquent cortex with task-based functional MRI (T-fMRI) is part of the current standard of care prior to resection of brain tumors. Resting state fMRI (RS-fMRI) is an alternative method currently under investigation. Here, we compare group level language localization using T-fMRI vs. RS-fMRI analyzed with 3D deep convolutional neural networks (3DCNN). Methods: We analyzed data obtained in 35 patients with brain tumors that had both language T-fMRI and RS-MRI scans during pre-surgical evaluation. The T-fMRI data were analyzed using conventional techniques. The language associated resting state network was mapped using a 3DCNN previously trained with data acquired in >2,700 normal subjects. Group level results obtained by both methods were evaluated using receiver operator characteristic analysis of probability maps of language associated regions, taking as ground truth meta-analytic maps of language T-fMRI responses generated on the Neurosynth platform. Results: Both fMRI methods localized major components of the language system (areas of Broca and Wernicke). Word-stem completion T-fMRI strongly activated Broca's area but also several task-general areas not specific to language. RS-fMRI provided a more specific representation of the language system. Conclusion: 3DCNN was able to accurately localize the language network. Additionally, 3DCNN performance was remarkably tolerant of a limited quantity of RS-fMRI data.

Artificial intelligence is a hot topic in medical imaging. The development of deep learning methods and in particular the use of convolutional neural networks (CNNs), have led to substantial performance gain over the classic machine learning techniques. Multiple usages are currently being evaluated, especially for thoracic imaging, such as such as lung nodule evaluation, tuberculosis or pneumonia detection or quantification of diffuse lung diseases. Chest radiography is a near perfect domain for the development of deep learning algorithms for automatic interpretation, requiring large annotated datasets, in view of the high number of procedures and increasing data availability. Current algorithms are able to detect up to 14 common anomalies, when present as isolated findings. Chest computed tomography is another major field of application for artificial intelligence, especially in the perspective of large scale lung cancer screening. It is important for radiologists to apprehend, contribute actively and lead this new era of radiology powered by artificial intelligence. Such a perspective requires understanding new terms and concepts associated with machine learning. The objective of this paper is to provide useful definitions for understanding the methods used and their possibilities, and report current and future developments for thoracic imaging. Prospective validation of AI tools will be required before reaching routine clinical implementation.

Relevance and penetration of machine learning in clinical practice is a recent phenomenon with multiple applications being currently under development. Deep learning-and especially convolutional neural networks (CNNs)-is a subset of machine learning, which has recently entered the field of thoracic imaging. The structure of neural networks, organized in multiple layers, allows them to address complex tasks. For several clinical situations, CNNs have demonstrated superior performance as compared with classical machine learning algorithms and in some cases achieved comparable or better performance than clinical experts. Chest radiography, a high-volume procedure, is a natural application domain because of the large amount of stored images and reports facilitating the training of deep learning algorithms. Several algorithms for automated reporting have been developed. The training of deep learning algorithm CT images is more complex due to the dimension, variability, and complexity of the 3D signal. The role of these methods is likely to increase in clinical practice as a complement of the radiologist's expertise. The objective of this review is to provide definitions for understanding the methods and their potential applications for thoracic imaging. KEY POINTS: • Deep learning outperforms other machine learning techniques for number of tasks in radiology. • Convolutional neural network is the most popular deep learning architecture in medical imaging. • Numerous deep learning algorithms are being currently developed; some of them may become part of clinical routine in the near future.

The localization of articulate language (speech) to the posterior third of the third left frontal convolution-Broca's area-did not occur to Broca as he reported the case of his first aphasic patient in 1861. Initially Broca localized articulate language to both frontal lobes, a position that he maintained for 4 years after publishing his first case. In the interval, the Academy of Medicine in Paris had received a copy of a paper authored in 1836 by Marc Dax, in which Dax claimed that the ability to speak resides within the left hemisphere alone. The Academy of Medicine convened in the spring of 1865 to adjudicate the issue. All of the distinguished speakers argued against Dax's contention by citing the prevailing paradigm, that bilaterally symmetrical organs, such as the eyes and ears, and the hemispheres of the brain, must perform the same function. The lone dissenting voice was that of Jules Baillarger, the discoverer of the laminar organization of the cerebral cortex, whose argument in favor of what he called "Dax's law" was so lucid that it carried the day. During his address to the Academy, Baillarger not only supported left-hemisphere dominance for speech, but for the first time described two forms of aphasia, fluent and nonfluent, now referred to as Wernicke's and Broca's aphasias, respectively, as well as the ability of aphasics to speak during emotional outbursts, to which we now refer as Baillarger-Jackson aphasia. It was 9 days after Baillarger's address that Broca, for the first time, unequivocally localized speech to the left frontal lobe.This paper is based on the author's reading of Dax's and Broca's original texts and of the texts read before the Academy of Medicine meeting held at the National Library of France between April 4, 1865, and June 13, 1865. From these primary sources it is concluded that the Academy of Medicine's debate was the last serious challenge to left-hemisphere dominance for speech and to the localization of articulate language to the left frontal lobe-and that Jules Baillarger played a pivotal role in what was a defining moment in neurobiology.

Each brain hemisphere is dominant for certain functions such as speech. The determination of speech laterality prior to surgery is of paramount importance for accurate risk prediction. In this study, we aimed to determine speech laterality via EEG signals by using noninvasive machine learning techniques. The retrospective study included 67 subjects aged 18-65 years who had no chronic diseases and were diagnosed as healthy based on EEG examination. The subjects comprised 35 right-hand dominant (speech center located in the left hemisphere) and 32 left-hand dominant individuals (speech center located in the right hemisphere). A spectrogram was created for each of the 18 EEG channels by using various Convolutional Neural Networks (CNN) architectures including VGG16, VGG19, ResNet, MobileNet, NasNet, and DenseNet. These architectures were used to extract features from the spectrograms. The extracted features were classified using Support Vector Machines (SVM) and the classification performances of the CNN models were evaluated using Area Under the Curve (AUC). Of all the CNN models used in the study, VGG16 had a higher AUC value (0.83 ± 0.05) in the determination of speech laterality compared to all other models. The present study is a pioneer investigation into the determination of speech laterality via EEG signals with machine learning techniques, which, to our knowledge, has never been reported in the literature. Moreover, the classification results obtained in the study are promising and lead the way for subsequent studies though not practically feasible.

The ability to speak is a unique human capacity, but where is it located in our brains? This question is closely connected to the pioneering work of Pierre Paul Broca in the 1860s. Based on post-mortem observations of aphasic patients' brains, Broca located language production in the 3rd convolution of the left frontal lobe and thus reinitiated the localizationist view of brain functions. However, contemporary neuroscience has partially rejected this view in favor of a network-based perspective. This leads to the question, whether Broca's findings are still relevant today. In this mini-review, we discuss current and historical implications of Broca's work by focusing on his original contribution and contrasting it with contemporary knowledge. Borrowing from Broca's famous quote, our review shows that humans indeed "speak with the left hemisphere"- but Broca's area is not the sole "seat of articulatory language".