Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech.

Several attempts for speech brain-computer interfacing (BCI) have been made to decode phonemes, sub-words, words, or sentences using invasive measurements, such as the electrocorticogram (ECoG), during auditory speech perception, overt speech, or imagined (covert) speech. Decoding sentences from covert speech is a challenging task. Sixteen epilepsy patients with intracranially implanted electrodes participated in this study, and ECoGs were recorded during overt speech and covert speech of eight Japanese sentences, each consisting of three tokens. In particular, Transformer neural network model was applied to decode text sentences from covert speech, which was trained using ECoGs obtained during overt speech. We first examined the proposed Transformer model using the same task for training and testing, and then evaluated the model's performance when trained with overt task for decoding covert speech. The Transformer model trained on covert speech achieved an average token error rate (TER) of 46.6% for decoding covert speech, whereas the model trained on overt speech achieved a TER of 46.3% ( p > 0.05 ; d = 0.07 ) . Therefore, the challenge of collecting training data for covert speech can be addressed using overt speech. The performance of covert speech can improve by employing several overt speeches.

The project for objective measures using computational psychiatry technology (PROMPT): Rationale, design, and methodology.

INTRODUCTION: Depressive and neurocognitive disorders are debilitating conditions that account for the leading causes of years lived with disability worldwide. However, there are no biomarkers that are objective or easy-to-obtain in daily clinical practice, which leads to difficulties in assessing treatment response and developing new drugs. New technology allows quantification of features that clinicians perceive as reflective of disorder severity, such as facial expressions, phonic/speech information, body motion, daily activity, and sleep. METHODS: Major depressive disorder, bipolar disorder, and major and minor neurocognitive disorders as well as healthy controls are recruited for the study. A psychiatrist/psychologist conducts conversational 10-min interviews with participants ≤10 times within up to five years of follow-up. Interviews are recorded using RGB and infrared cameras, and an array microphone. As an option, participants are asked to wear wrist-band type devices during the observational period. Various software is used to process the raw video, voice, infrared, and wearable device data. A machine learning approach is used to predict the presence of symptoms, severity, and the improvement/deterioration of symptoms. DISCUSSION: The overall goal of this proposed study, the Project for Objective Measures Using Computational Psychiatry Technology (PROMPT), is to develop objective, noninvasive, and easy-to-use biomarkers for assessing the severity of depressive and neurocognitive disorders in the hopes of guiding decision-making in clinical settings as well as reducing the risk of clinical trial failure. Challenges may include the large variability of samples, which makes it difficult to extract the features that commonly reflect disorder severity. TRIAL REGISTRATION: UMIN000021396, University Hospital Medical Information Network (UMIN).

Importance of over-reading ambulatory ECG-based microvolt T-wave alternans to eliminate three main sources of measurement error.

BACKGROUND: Ambulatory electrocardiogram (ECG)-based microvolt T-wave alternans values measured by the modified moving average method (MMA-TWA) can be disrupted by T-wave changes that mimic true repolarization alternans. METHODS: We investigated potential sources of measurement error by studying 19 healthy subjects (12 men; median age, 25) free of known heart disease with 36-month follow-up to establish freedom from significant arrhythmia or syncope. All participants underwent 24-hr continuous 12-lead ECG monitoring. Causes of automated MMA-TWA ≥42 µV episodes were classified based on visual inspection. RESULTS: A total of 2,189 episodes of automated MMA-TWA episodes ≥42 µV were observed in all subjects (peak MMA-TWA: median, 94 µV; interquartile range, 81-112 µV). All episodes included one or more beats with T-wave deformation which lacked "repeating ABAB pattern" and therefore were identified as TWA measurement error. Causes of such error were categorized as: (a) artifact [72.6% (1,589/2,189), observed in 19 (100%) subjects], more frequently in limb than precordial leads; (b) T-wave changes due to changes in heart/body position [25.5% (559/2,189), observed in 14 (73.7%) subjects], frequently observed in leads V1-2; and (c) postextrasystolic T-wave changes [1.9% (41/2,189), observed in 2 (10.5%) subjects]. CONCLUSIONS: Relying only on automated MMA-TWA values obtained during ambulatory ECG monitoring can lead to incorrect measurement of TWA. Our findings offer the potential to reduce false-positive TWA results and to achieve more accurate detection of true repolarization alternans.

Structural Comparison between the Right and Left Atrial Appendages Using Multidetector Computed Tomography.

The three-dimensional (3D) structures of the right atrial appendage (RAA) and left atrial appendage (LAA) were compared to clarify why thrombus formation less frequently occurs in RAA than in LAA. Morphological differences between RAA and LAA of 34 formalin-preserved cadaver hearts were investigated. Molds of RAA and LAA specimens were made and the neck areas, volumes of the atrial appendages (AA), and amount of pectinate muscles (PMs) were analyzed using multidetector computed tomography. In RAA, most PMs were connected to one another and formed a "dendritic" appearance and the inner surface area was smaller than in LAA. RAA had smaller volumes and larger neck areas than LAA. The ratios of the neck area/volume were larger and the amounts of PMs were smaller in RAA than in LAA. The volumes, neck areas, and amount of PMs of RAA were significantly correlated with those of LAA. According to the 3D structure, RAA appears to be suited for a more favorable blood flow, which may explain why the thrombus formation is less common in RAA than in LAA. Examining not only LAA but also RAA by transesophageal echocardiography may be useful in high-risk patients of thrombus formation in LAA because the volume, neck area, and amount of PMs of LAA reflect the shape of RAA.

Sonographic Detection of Subcutaneous Foreign Bodies in 3 Cases.

Subcutaneous masses caused by foreign bodies are frequently encountered in daily practice. Although the majority of foreign bodies such as metals can be detected by radiography, substances such as vegetative materials or wood are difficult to detect. To our knowledge, only a few studies have described the sonographic characteristics of foreign bodies. Herein, we report 3 cases where we studied the sonographic characteristics of the foreign bodies in the dermis and subcutaneous tissue. Our results revealed the following 3 foreign bodies: (1) glass, (2) vegetative material, and (3) a pencil core. Thus, sonographic examination is useful for the detection of foreign bodies.

Fast Coding of Feature Vectors Using Neighbor-to-Neighbor Search.

Searching for matches to high-dimensional vectors using hard/soft vector quantization is the most computationally expensive part of various computer vision algorithms including the bag of visual word (BoW). This paper proposes a fast computation method, Neighbor-to-Neighbor (NTN) search [1] , which skips some calculations based on the similarity of input vectors. For example, in image classification using dense SIFT descriptors, the NTN search seeks similar descriptors from a point on a grid to an adjacent point. Applications of the NTN search to vector quantization, a Gaussian mixture model, sparse coding, and a kernel codebook for extracting image or video representation are presented in this paper. We evaluated the proposed method on image and video benchmarks: the PASCAL VOC 2007 Classification Challenge and the TRECVID 2010 Semantic Indexing Task. NTN-VQ reduced the coding cost by 77.4 percent, and NTN-GMM reduced it by 89.3 percent, without any significant degradation in classification performance.

Sonographic Findings of Subcutaneous Sarcoidosis in 3 Cases.

Subcutaneous sarcoidosis occurs infrequently among cases of cutaneous sarcoidosis. To our knowledge, few studies have described the sonographic characteristics of subcutaneous sarcoidosis. Here we report the sonographic characteristics of 3 cases of this condition. Our results revealed 4 features: (1) an irregular hypoechoic appearance, (2) heterogeneous echogenicity, (3) perilesional hyperechoic changes, and (4) abnormal Doppler signals. Sonography is a rapid, simple, and noninvasive procedure that is useful for initial evaluation of granulomatous lesions such as subcutaneous sarcoidosis.

[Diagnostic ability of ultrasonography for the rotator cuff tear: comparison with ultrasonography and MRI findings].

Ultrasonography (US) is a non-invasive method which can assess not only solid tissue organs but also soft tissues such as tendons and nerves. However, it has not been fully understood that US is a useful tool for the depiction of periarticular structure. We compared the diagnostic accuracies between US and magnetic resonance imaging (MRI) in the patients with rotator cuff tear (RCT). Seventy patients, who underwent arthroscopic surgery, preoperative US and MRI examinations at Gifu University Hospital from January 2010 to April 2013 (49 male, 21 female, mean age 59.7 +/- 15.9) were included in this study. The diagnostic accuracy, sensitivity and specificity of US and MRI were 94.3% and 94.3%, 95.8% and 97.9%, 90.9% and 84.6%, respectively, when the intraoperative finding was regarded as a gold standard. These results suggest that US is useful for the diagnosis of RCT as equal as MRI.

Covalent anthocyanin-flavonol complexes from the violet-blue flowers of Allium 'Blue Perfume'.

Three covalent anthocyanin-flavonol complexes (pigments 1-3) were extracted from the violet-blue flower of Allium 'Blue Perfume' with 5% acetic acid-MeOH solution, in which pigment 1 was the dominant pigment. These three pigments are based on delphinidin 3-glucoside as their deacylanthocyanin and were acylated with malonyl kaempferol 3-sophoroside-7-glucosiduronic acid or malonyl-kaempferol 3-p-coumaroyl-tetraglycoside-7-glucosiduronic acid in addition to acylation with acetic acid. By spectroscopic and chemical methods, the structures of these three pigments 1-3 were determined to be: pigment 1, (6(I)-O-(delphinidin 3-O-(3(I)-O-(acetyl)-ß-glucopyranoside(I))))(2(VI)-O-(kaempferol 3-O-(2(II)-O-(3(III)-O-(ß-glucopyranosyl(V))-ß-glucopyranosyl(III))-4(II)-O-(trans-p-coumaroyl)-6(II)-O-(ß-glucopyranosyl(IV))-ß-glucopyranoside(II))-7-O-(ß-glucosiduronic acid(VI)))) malonate; pigment 2, (6(I)-O-(delphinidin 3-O-(3(I)-O-(acetyl)-ß-glucopyranoside(I))))(2(VI)-O-(kaempferol 3-O-(2(II)-O-ß-glucopyranosyl(III))-ß-glucopyranoside(II))-7-O-(ß-glucosiduronic acid(VI)))); and pigment 3, (6(I)-O-(delphinidin 3-O-(3(I)-O-(acetyl)-ß-glucopyranoside(I))))(2(VI)-O-(kaempferol 3-O-(2(II)-O-(3(III)-O-(ß-glucopyranosyl(V))-ß-glucopyranosyl(III))-4(II)-O-(cis-p-coumaroyl)-6(II)-O-(ß-glucopyranosyl(IV))-ß-glucopyranoside(II))-7-O-(ß-glucosiduronic acid(VI)))) malonate. The structure of pigment 2 was analogous to that of a covalent anthocyanin-flavonol complex isolated from Allium schoenoprasum where delphinidin was observed in place of cyanidin. The three covalent anthocyanin-flavonol complexes (pigment 1-3) had a stable violet-blue color with three characteristic absorption maxima at 540, 547 and 618nm in pH 5-6 buffer solution. From circular dichroism measurement of pigment 1 in the pH 6.0 buffer solution, cotton effects were observed at 533 (+), 604 (-) and 638 (-) nm. Based on these results, these covalent anthocyanin-flavonol complexes were presumed to maintain a stable intramolecular association between delphinidin and kaempferol units closely related to that observed between anthocyanin and hydroxycinnamic acid residues in polyacylated anthocyanins. Additionally, an acylated kaempferol glycoside (pigment 4) was isolated from the same flower extract, and its structure was determined to be kaempferol 3-O-sophoroside-7-O-(3-O-(malonyl)-ß-glucopyranosiduronic acid).

The blue anthocyanin pigments from the blue flowers of Heliophila coronopifolia L. (Brassicaceae).

Six acylated delphinidin glycosides (pigments 1-6) and one acylated kaempferol glycoside (pigment 9) were isolated from the blue flowers of cape stock (Heliophila coronopifolia) in Brassicaceae along with two known acylated cyanidin glycosides (pigments 7 and 8). Pigments 1-8, based on 3-sambubioside-5-glucosides of delphinidin and cyanidin, were acylated with hydroxycinnamic acids at 3-glycosyl residues of anthocyanidins. Using spectroscopic and chemical methods, the structures of pigments 1, 2, 5, and 6 were determined to be: delphinidin 3-O-[2-O-(ß-xylopyranosyl)-6-O-(acyl)-ß-glucopyranoside]-5-O-[6-O-(malonyl)-ß-glucopyranoside], in which acyl moieties were, respectively, cis-p-coumaric acid for pigment 1, trans-caffeic acid for pigment 2, trans-p-coumaric acid for pigment 5 (a main pigment) and trans-ferulic acid for pigment 6, respectively. Moreover, the structure of pigments 3 and 4 were elucidated, respectively, as a demalonyl pigment 5 and a demalonyl pigment 6. Two known anthocyanins (pigments 7 and 8) were identified to be cyanidin 3-(6-p-coumaroyl-sambubioside)-5-(6-malonyl-glucoside) for pigment 7 and cyanidin 3-(6-feruloyl-sambubioside)-5-(6-malonyl-glucoside) for pigment 8 as minor anthocyanin pigments. A flavonol pigment (pigment 9) was isolated from its flowers and determined to be kaempferol 3-O-[6-O-(trans-feruloyl)-ß-glucopyranoside]-7-O-cellobioside-4'-O-glucopyranoside as the main flavonol pigment. On the visible absorption spectral curve of the fresh blue petals of this plant and its petal pressed juice in the pH 5.0 buffer solution, three characteristic absorption maxima were observed at 546, 583 and 635 nm. However, the absorption curve of pigment 5 (a main anthocyanin in its flower) exhibited only one maximum at 569 nm in the pH 5.0 buffer solution, and violet color. The color of pigment 5 was observed to be very unstable in the pH 5.0 solution and soon decayed. In the pH 5.0 solution, the violet color of pigment 5 was restored as pure blue color by addition of pigment 9 (a main flavonol in this flower) like its fresh flower, and its blue solution exhibited the same three maxima at 546, 583 and 635 nm. On the other hand, the violet color of pigment 5 in the pH 5.0 buffer solution was not restored as pure blue color by addition of deacyl pigment 9 or rutin (a typical flower copigment). It is particularly interesting that, a blue anthocyanin-flavonol complex was extracted from the blue flowers of this plant with H(2)O or 5% HOAc solution as a dark blue powder. This complex exhibited the same absorption maxima at 546, 583 and 635 nm in the pH 5.0 buffer solution. Analysis of FAB mass measurement established that this blue anthocyanin-flavonol complex was composed of one molecule each of pigment 5 and pigment 9, exhibiting a molecular ion [M+1] (+) at 2102 m/z (C(93)H(105)O(55) calc. 2101.542). However, this blue complex is extremely unstable in acid solution. It really dissociates into pigment 5 and pigment 9.

An unusual acylated malvidin 3-glucoside from flowers of Impatiens textori Miq. (Balsaminaceae).

Acylated malvidin 3-glucoside was isolated from the purple flowers of Impatiens textori Miq. as a major anthocyanin component along with malvidin 3-(6''-malonyl-glucoside). Its structure was elucidated to be malvidin 3-O-[6-O-(3-hydroxy-3-methylglutaryl)-beta-glucopyranoside] by chemical and spectroscopic methods.

Tetra-acylated cyanidin 3-sophoroside-5-glucosides from the flowers of Iberis umbellata L. (Cruciferae).

The structures of 11 acylated cyanidin 3-sophoroside-5-glucosides (pigments 1-11), isolated from the flowers of Iberis umbellata cultivars (Cruciferae), were elucidated by chemical and spectroscopic methods. Pigments 1-11 were acylated with malonic acid, p-coumaric acid, ferulic acid, sinapic acid and/or glucosylhydroxycinnamic acids. Pigments 1-11 were classified into four groups by the substitution patterns of the linear acylated residues at the 3-position of the cyanidin. In the first group, pigments 1-3 were determined to be cyanidin 3-O-[2-O-(2-O-(acyl)-beta-glucopyranosyl)-6-O-(trans-p-coumaroyl)-beta-glucopyranoside]-5-O-[6-O-(malonyl)-beta-glucopyranoside], in which the acyl moiety varied with none for pigment 1, ferulic acid for pigment 2 and sinapic acid for pigment 3. In the second one, pigments 4-6 were cyanidin 3-O-[2-O-(2-O-(acyl)-beta-glucopyranosyl)-6-O-(4-O-(beta-glucopyranosyl)-trans-p-coumaroyl)-beta-glucopyranoside]-5-O-[6-O-(malonyl)-beta-glucopyranoside], in which the acyl moiety varied with none for pigment 4, ferulic acid for pigment 5 and sinapic acid for pigment 6. In the third one, pigments 7-9 were cyanidin 3-O-[2-O-(2-O-(acyl)-beta-glucopyranosyl)-6-O-(4-O-(6-O-(trans-feruloyl)-beta-glucopyranosyl)-trans-p-coumaroyl)-beta-glucopyranoside]-5-O-[6-O-(malonyl)-beta-glucopyranoside], in which the acyl moiety varied with none for pigment 7, ferulic acid for pigment 8, and sinapic acid for pigment 9. In the last one, pigments 10 and 11 were cyanidin 3-O-[2-O-(2-O-(acyl)-beta-glucopyranosyl)-6-O-(4-O-(6-O-(4-O-(beta-glucopyranosyl)-trans-feruloyl)-beta-glucopyranosyl)-trans-p-coumaroyl)-beta-glucopyranoside]-5-O-[6-O-(malonyl)-beta-glucopyranoside], in which acyl moieties were none for pigment 10 and ferulic acid for pigment 11. The distribution of these pigments was examined in the flowers of four cultivars of I. umbellata by HPLC analysis. Pigment 1 acylated with one molecule of p-coumaric acid was dominantly observed in purple-violet cultivars. On the other hand, pigments (9 and 11) acylated with three molecules of hydroxycinnamic acids were observed in lilac (purple-violet) cultivars as major anthocyanins. The bluing effect and stability on these anthocyanin colors were discussed in relation to the molecular number of hydroxycinnamic acids in these anthocyanin molecules.

Triacylated cyanidin 3-(3X-glucosylsambubioside)-5-glucosides from the flowers of Malcolmia maritima.

Three acylated cyanidin 3-(3(X)-glucosylsambubioside)-5-glucosides (1-3) and one non-acylated cyanidin 3-(3(X)-glucosylsambubioside)-5-glucoside (4) were isolated from the purple-violet or violet flowers and purple stems of Malcolmia maritima (L.) R. Br (the Cruciferae), and their structures were determined by chemical and spectroscopic methods. In the flowers of this plant, pigment 1 was determined to be cyanidin 3-O-[2-O-(2-O-(trans-sinapoyl)-3-O-(beta-D-glucopyranosyl)-beta-D-xylopyranosyl)-6-O-(trans-p-coumaroyl)-beta-D-glucopyranoside]-5-O-[6-O-(malonyl)-(beta-D-glucopyranoside) as a major pigment, and a minor pigment 2 was determined to be the cis-p-coumaroyl isomer of pigment 1. In the stems, pigment 3 was determined to be cyanidin 3-O-[2-O-(2-O-(trans-sinapoyl)-3-O-(beta-D-glucopyranosyl)-beta-D-xylopyranosyl)-6-O-(trans-p-coumaroyl)-beta-d-glucopyranoside]-5-O-(beta-D-glucopyranoside) as a major anthocyanin, and also a non-acylated anthocyanin, cyanidin 3-O-[2-O-(3-O-(beta-D-glucopyranosyl)-beta-D-xylopyranosyl)-beta-D-glucopyranoside]-5-O-(beta-D-glucopyranoside) was determined to be a minor pigment (pigment 4). In this study, it was established that the acylation-enzymes of malonic acid has important roles for the acylation of 5-glucose residues of these anthocyanins in the flower-tissues of M. maritima; however, the similar enzymatic reactions seemed to be inhibited or lacking in the stem-tissues.

Acylated cyanidin 3-sambubioside-5-glucosides in three garden plants of the Cruciferae.

Seven acylated cyanidin 3-sambubioside-5-glucosides were isolated from the flowers of three garden plants in the Cruciferae. Specifically, four pigments were isolated from Lobularia maritima (L.) Desv., together with a known pigment, as well as, three pigments from Lunaria annua L., and two known pigments from Cheiranthus cheiri L. These pigments were determined to be cyanidin 3-O-[2-O-((acyl-II)-(beta-d-xylopyranosyl))-6-O-(acyl-I)-beta-d-glucopyranoside]-5-O-[6-O-(acyl-III)-beta-d-glucopyranoside], in which the acyl-I group is represented by glucosyl-p-coumaric acid, p-coumaric acid and ferulic acid, acyl-II by caffeic acid and ferulic acid, and acyl-III by malonic acid, respectively. The distribution and biosynthesis of acylated cyanidin 3-sambubioside-5-glucosides are discussed according to the variations of acylation and glucosylation at their 3-sambubiose residues.

Isolation of individual egg cells and zygotes in Alstroemeria followed by manual selection with a microcapillary-connected micropump.

AIMS: To develop a procedure for isolating living egg cells and zygotes from Alstroemeria ovules. SCOPE: An attempt was made to isolate egg cells and zygotes from the ovules of Alstroemeria aurea. The ovules were histologically observed using a clearing procedure which revealed the localization and sizes of the embryo sacs and egg apparatus within the ovules. For the isolation of egg cells, ovules were cut into sections with a surgical blade and treated with an enzyme solution. Subsequently, these ovule sections were dissected using a glass needle under an inverted microscope. Egg cells successfully isolated by this procedure were collected using microcapillaries connected to a micropump. For zygote isolation, ovules were excised from ovaries 24 h after self-pollination. By treating excised ovules with an enzyme solution and subsequently dissecting them using a glass needle, zygotes were successfully isolated from the ovules and collected with a microcapillary. The isolated zygotes were associated with pollen tubes and one of the synergids. Egg cells and zygotes were viable for up to 2 h following isolation, as determined by fluorescein diacetate staining. CONCLUSIONS: The procedures for isolating egg cells and zygotes in Alstroemeria were established, and each egg cell and zygote was captured with a microcapillary.

Diacylated 8-C-glucosylcyanidin 3-glucoside from the flowers of Tricyrtis formosana.

A new diacylated 8-C-glucosylanthocyanin was isolated from the purple flowers of Tricyrtis formosana 'Fujimusume' as one of the major anthocyanins along with four known pigments. The structure of this pigment was determined to be 8-C-(6-O-trans-sinapoyl)-beta-glucopyranosylcyanidin 3-O-(6-O-malonyl-beta-glucopyranoside) by chemical and spectroscopic methods. In addition, four known pigments, 8-C-glucosylcyanidin 3-malonylglucoside, cyanidin 3-glucoside, cyanidin 3-rutinoside and cyanidin 3-malonylglucoside, were identified as the major anthocyanins in the flowers.

6-Hydroxypelargonidin glycosides in the orange-red flowers of Alstroemeria.

Two 6-hydroxypelargonidin glycosides were isolated from the orange-red flowers of Alstroemeria cultivars, and determined to be 6-hydroxypelargonidin 3-O-(beta-D-glucopyranoside) and 3-O-[6-O-(alpha-L-rhamnopyranosyl)-beta-D-glucopyranoside], respectively, by chemical and spectroscopic methods. In addition, five known anthocyanidin glycosides, 6-hydroxycyanidin 3-malonylglucoside, 6-hydroxycyanidin 3-rutinoside, cyanidin 3-malonylglucoside, cyanidin 3-rutinoside and pelargonidin 3-rutinoside were identified in the flowers.