Assessment of changes in vessel area during needle manipulation in microvascular anastomosis using a deep learning-based semantic segmentation algorithm: A pilot study.

Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety.

Non-signing children's assessment of telicity in sign language.

Adults with no knowledge of sign languages can perceive distinctive markers that signal event boundedness (telicity), suggesting that telicity is a cognitively natural semantic feature that can be marked iconically (Strickland et al., 2015). This study asks if non-signing children (5-year-olds) can also link telicity to iconic markers in sign. Experiment 1 attempted three close replications of Strickland et al. (2015) and found only limited success. However, Experiment 2 showed that children can both perceive the relevant visual feature and can succeed at linking the visual property to telicity semantics when allowed to filter their answer through their own linguistic choices. Children's performance demonstrates the cognitive naturalness and early availability of the semantics of telicity, supporting the idea that telicity helps guide the language acquisition process.

It Costs To Exist: Acceptability Judgments of the Temporal Concord of the Auxiliary Verbs You and Hui in Taiwan Mandarin.

The mechanisms underlying the processing of the temporal reference of a sentence are still unexplored. Most of the previous psycholinguistic studies used the temporal concord violation between deictic time adverbs and tense marking on the verb to investigate this issue. They found that processing past tense marking is more difficult than non-past tense, indicated by lower accuracy rates and/or longer reaction time. However, it is not clear whether this complexity is due to tense marking or the temporal reference it denotes. This paper examines this issue with a judgment acceptability experiment in Taiwan Mandarin, which is analyzed as a tenseless language. The two modal auxiliary verbs you and hui were placed after deictic past time adverbs (grammatical with you but not with hui) and deictic future time adverbs (grammatical with hui but not with you). The temporal concord violation of the auxiliary verb you led to higher acceptability rates but longer reaction time than hui, reflecting higher processing difficulties. This paper argues that these complexities are due to the existential-assertive meaning of you, which interplays with the meaning of the event described by the verb rendering the situation more or less likely to occur in the future. The computation of the temporal concord of hui, displaying a future sense meaning, is more straightforward and therefore easier to process. This suggests that the mechanisms responsible for temporal reference processing are of different nature depending on the semantics of the temporal marker in the sentence.

Developing an Ontology Representing Fall Risk Management Domain Knowledge.

Ontologies serve as comprehensive frameworks for organizing domain-specific knowledge, offering significant benefits for managing clinical data. This study presents the development of the Fall Risk Management Ontology (FRMO), designed to enhance clinical text mining, facilitate integration and interoperability between disparate data sources, and streamline clinical data analysis. By representing major entities within the fall risk management domain, the FRMO supports the unification of clinical language and decision-making processes, ultimately contributing to the prevention of falls among older adults. We used Ontology Web Language (OWL) to build the FRMO in Protégé. Of the seven steps of the Stanford approach, six steps were utilized in the development of the FRMO: (1) defining the domain and scope of the ontology, (2) reusing existing ontologies when possible, (3) enumerating ontology terms, (4) specifying the classes and their hierarchy, (5) defining the properties of the classes, and (6) defining the facets of the properties. We evaluated the FRMO using four main criteria: consistency, completeness, accuracy, and clarity. The developed ontology comprises 890 classes arranged in a hierarchical structure, including six top-level classes with a total of 43 object properties and 28 data properties. FRMO is the first comprehensively described semantic ontology for fall risk management. Healthcare providers can use the ontology as the basis of clinical decision technology for managing falls among older adults.

Using Monte-Carlo simulation to test predictions about the time-course of semantic and lexical access in reading.

One of the main theoretical distinctions between reading models is how and when they predict semantic processing occurs. Some models assume semantic activation occurs after word-form is retrieved. Other models assume there is no-word form, and that what people think of as word-form is actually just semantics. These models thus predict semantic effects should occur early in reading. Results showing words with inconsistent spelling-sound correspondences are faster to read aloud if they are imageable/concrete compared to if they are abstract have been used as evidence supporting this prediction, although null-effects have also been reported. To investigate this, I used Monte-Carlo simulation to create a large set of simulated experiments from RTs taken from different databases. The results showed significant main effects of concreteness and spelling-sound consistency, as well as age-of-acquisition, a variable that can potentially confound the results. Alternatively, simulations showing a significant interaction between spelling-sound consistency and concreteness did not occur above chance, even without controlling for age-of-acquisition. These results support models that use lexical form. In addition, they suggest significant interactions from previous experiments may have occurred due to idiosyncratic items affecting the results and random noise causing the occasional statistical error.

Development of a scoring system to quantify errors from semantic characteristics in incident reports.

OBJECTIVES: Incident reporting systems are widely used to identify risks and enable organisational learning. Free-text descriptions contain important information about factors associated with incidents. This study aimed to develop error scores by extracting information about the presence of error factors in incidents using an original decision-making model that partly relies on natural language processing techniques. METHODS: We retrospectively analysed free-text data from reports of incidents between January 2012 and December 2022 from Nagoya University Hospital, Japan. The sample data were randomly allocated to equal-sized training and validation datasets. We conducted morphological analysis on free text to segment terms from sentences in the training dataset. We calculated error scores for terms, individual reports and reports from staff groups according to report volume size and compared these with conventional classifications by patient safety experts. We also calculated accuracy, recall, precision and F-score values from the proposed 'report error score'. RESULTS: Overall, 114 013 reports were included. We calculated 36 131 'term error scores' from the 57 006 reports in the training dataset. There was a significant difference in error scores between reports of incidents categorised by experts as arising from errors (p<0.001, d=0.73 (large)) and other incidents. The accuracy, recall, precision and F-score values were 0.8, 0.82, 0.85 and 0.84, respectively. Group error scores were positively associated with expert ratings (correlation coefficient, 0.66; 95% CI 0.54 to 0.75, p<0.001) for all departments. CONCLUSION: Our error scoring system could provide insights to improve patient safety using aggregated incident report data.

Assessment of Language Function in Older Mandarin-Speaking Adults with Mild Cognitive Impairment using Multifaceted Language Tests.

BACKGROUND: Individuals with amnestic mild cognitive impairment (aMCI), especially for those with multidomain cognitive deficits, should be clinically examined for determining risk of developing Alzheimer's disease. English-speakers with aMCI exhibit language impairments mostly at the lexical-semantic level. Given that the language processing of Mandarin Chinese is different from that of alphabetic languages, whether previous findings for English-speakers with aMCI can be generalized to Mandarin Chinese speakers with aMCI remains unclear. OBJECTIVE: This study examined the multifaceted language functions of Mandarin Chinese speakers with aMCI and compared them with those without cognitive impairment by using a newly developed language test battery. METHODS: Twenty-three individuals with aMCI and 29 individuals without cognitive impairment were recruited. The new language test battery comprises five language domains (oral production, auditory and reading comprehension, reading aloud, repetition, and writing). RESULTS: Compared with the controls, the individuals with aMCI exhibited poorer performance in the oral production and auditory and reading comprehension domains, especially on tests involving effortful lexical and semantic processing. Moreover, the aMCI group made more semantic naming errors compared with their counterparts and tended to experience difficulty in processing items belonging to the categories of living objects. CONCLUSIONS: The pattern identified in the present study is similar to that of English-speaking individuals with aMCI across multiple language domains. Incorporating language tests involving lexical and semantic processing into clinical practice is essential and can help identify early language dysfunction in Mandarin Chinese speakers with aMCI.

Latent Graph Representations for Critical View of Safety Assessment.

Assessing the critical view of safety in laparoscopic cholecystectomy requires accurate identification and localization of key anatomical structures, reasoning about their geometric relationships to one another, and determining the quality of their exposure. Prior works have approached this task by including semantic segmentation as an intermediate step, using predicted segmentation masks to then predict the CVS. While these methods are effective, they rely on extremely expensive ground-truth segmentation annotations and tend to fail when the predicted segmentation is incorrect, limiting generalization. In this work, we propose a method for CVS prediction wherein we first represent a surgical image using a disentangled latent scene graph, then process this representation using a graph neural network. Our graph representations explicitly encode semantic information - object location, class information, geometric relations - to improve anatomy-driven reasoning, as well as visual features to retain differentiability and thereby provide robustness to semantic errors. Finally, to address annotation cost, we propose to train our method using only bounding box annotations, incorporating an auxiliary image reconstruction objective to learn fine-grained object boundaries. We show that our method not only outperforms several baseline methods when trained with bounding box annotations, but also scales effectively when trained with segmentation masks, maintaining state-of-the-art performance.

A semantic fidelity interpretable-assisted decision model for lung nodule classification.

PURPOSE: Early diagnosis of lung nodules is important for the treatment of lung cancer patients, existing capsule network-based assisted diagnostic models for lung nodule classification have shown promising prospects in terms of interpretability. However, these models lack the ability to draw features robustly at shallow networks, which in turn limits the performance of the models. Therefore, we propose a semantic fidelity capsule encoding and interpretable (SFCEI)-assisted decision model for lung nodule multi-class classification. METHODS: First, we propose multilevel receptive field feature encoding block to capture multi-scale features of lung nodules of different sizes. Second, we embed multilevel receptive field feature encoding blocks in the residual code-and-decode attention layer to extract fine-grained context features. Integrating multi-scale features and contextual features to form semantic fidelity lung nodule attribute capsule representations, which consequently enhances the performance of the model. RESULTS: We implemented comprehensive experiments on the dataset (LIDC-IDRI) to validate the superiority of the model. The stratified fivefold cross-validation results show that the accuracy (94.17%) of our method exceeds existing advanced approaches in the multi-class classification of malignancy scores for lung nodules. CONCLUSION: The experiments confirm that the methodology proposed can effectively capture the multi-scale features and contextual features of lung nodules. It enhances the capability of shallow structure drawing features in capsule networks, which in turn improves the classification performance of malignancy scores. The interpretable model can support the physicians' confidence in clinical decision-making.

Does pain hurt more in Spanish? The neurobiology of pain among Spanish-English bilingual adults.

We previously found Spanish-English bilingual adults reported higher pain intensity when exposed to painful heat in the language of their stronger cultural orientation. Here, we elucidate brain systems involved in language-driven alterations in pain responses. During separate English- and Spanish-speaking fMRI scanning runs, 39 (21 female) bilingual adults rated painful heat intermixed between culturally evocative images and completed sentence reading tasks. Surveys of cultural identity and language use measured relative preference for US-American vs Hispanic culture (cultural orientation). Participants produced higher intensity ratings in Spanish compared to English. Group-level whole-brain differences in pain-evoked activity between languages emerged in somatosensory, cingulate, precuneus and cerebellar cortex. Regions of interest associated with semantic, attention and somatosensory processing showed higher average pain-evoked responses in participants' culturally preferred language, as did expression of a multivariate pain-predictive pattern. Follow-up moderated mediation analyses showed somatosensory activity mediated language effects on pain intensity, particularly for Hispanic oriented participants. These findings relate to distinct ('meddler', 'spotlight' and 'inducer') hypotheses about the nature of language effects on perception and cognition. Knowledge of language influences on pain could improve efficacy of culturally sensitive treatment approaches across the diversity of Hispanic adults to mitigate documented health disparities in this population.

A full-document analysis of the semantic relation between European Public Assessment Reports and EMA guidelines using a BERT language model.

In the European Union, the Committee for Medicinal Products for Human Use of the European Medicines Agency (EMA) develop guidelines to guide drug development, supporting development of efficacious and safe medicines. A European Public Assessment Report (EPAR) is published for every medicine application that has been granted or refused marketing authorisation within the EU. In this work, we study the use of text embeddings and similarity metrics to investigate the semantic similarity between EPARs and EMA guidelines. All 1024 EPARs for initial marketing authorisations from 2008 to 2022 was compared to the 669 current EMA scientific guidelines. Documents were converted to plain text and split into overlapping chunks, generating 265,757 EPAR and 27,649 guideline text chunks. Using a Sentence BERT language model, the chunks were transformed into embeddings and fed into an in-house piecewise matching algorithm to estimate the full-document semantic distance. In an analysis of the document distance scores and product characteristics using a linear regression model, EPARs of anti-virals for systemic use (ATC code J05) and antihemorrhagic medicines (B02) present with statistically significant lower overall semantic distance to guidelines compared to other therapeutic areas, also when adjusting for product age and EPAR length. In conclusion, we believe our approach provides meaningful insight into the interplay between EMA scientific guidelines and the assessment made during regulatory review, and could potentially be used to answer more specific questions such as which therapeutic areas could benefit from additional regulatory guidance.

Tracking diachronic sentiment change of economic terms in times of crisis: Connotative fluctuations of 'inflation' in the news discourse.

The present study focuses on the fluctuation of sentiment in economic terminology to observe semantic changes in restricted diachrony. Our study examines the evolution of the target term 'inflation' in the business section of quality news and the impact of the Great Recession. This is carried out through the application of quantitative and qualitative methods: Sentiment Analysis, Usage Fluctuation Analysis, Corpus Linguistics, and Discourse Analysis. From the diachronic Great Recession News Corpus that covers the 2007-2015 period, we extracted sentences containing the term 'inflation'. Several facts are evidenced: (i) terms become event words given the increase in their frequency of use due to the unfolding of relevant crisis events, and (ii) there are statistically significant culturally motivated changes in the form of emergent collocations with sentiment-laden words with a lower level of domain-specificity.

A new method for safety helmet detection based on convolutional neural network.

Considering practical issues such as cost control of hardware facilities in engineering projects, it is a challenge to design a robust safety helmet detection method, which can be implemented on mobile or embedded devices with limited computing power. This paper presents an approach to optimize the BottleneckCSP structure in the YOLOv5 backbone network, which can greatly reduce the complexity of the model without changing the size of the network input and output. To eliminate the information loss caused by upsampling and enhance the semantic information of the feature map on the reverse path, this paper designs an upsampling feature enhancement module. Besides, To avoid the negative impact of redundant information generated by feature fusion on the detection results, this paper introduces a self-attention mechanism. That is, using the designed channel attention module and location attention module, adjacent shallow feature maps and upsampled feature maps are adaptively fused to generate new feature maps with strong semantics and precise location information. Compared with the existing methods with the fastest inference speed, under the same compute capability, the proposed method not only has faster inference speed, the FPS can reach 416, but also has better performance with mAP of 94.2%.

Occupational health assessment summary designed for semantic interoperability.

BACKGROUND: Geopolitical and economic crises force a growing number of people to leave their countries and search better employment opportunities abroad. Meanwhile, the highly competitive labor market provides opportunities for employees to change workplaces and job positions. Health assessment data collected during the occupational history is an essential resource for developing efficient occupational disease prevention strategies as well as for ensuring the physical and psychological well-being of newly appointed workers. The diversity in data representation is source for interoperability problems that are insufficiently explored in the existing literature. OBJECTIVES: This research aims to design a worker's occupational health assessment summary (OHAS) dataset that satisfies the requirements of an international standard for semantic interoperability in the use case for exchanging extracts of such data. The focus is on the need for a common OHAS standard at EU level allowing seamless exchange of OHAS at both cross-border and at the worker's country of origin level. RESULTS: This paper proposes a novelty systematic approach ensuring semantic interoperability in the exchange of OHAS. Two use cases are explored in terms of UML sequence diagram. The OHAS dataset reflects common data requirements established in the national legislation of EU countries. Finally, an EN 13606 archetype of OHAS is designed by satisfying the requirements for semantic interoperability in the exchange of clinical data. Semantic interoperability of OHAS is demonstrated with realistic use case data. CONCLUSIONS: The designed static, non-volatile and reusable information model of OHAS developed in this paper allows to create EN 13606 archetype instances that are valid with respect to the Reference model and the datatypes of this standard. Thus, basic activities in the OHAS use case can be implemented in software, for example, by means of a native XML database as well as integrated into existing information systems.

Segmentation quality assessment by automated detection of erroneous surface regions in medical images.

Despite the advancement in deep learning-based semantic segmentation methods, which have achieved accuracy levels of field experts in many computer vision applications, the same general approaches may frequently fail in 3D medical image segmentation due to complex tissue structures, noisy acquisition, disease-related pathologies, as well as the lack of sufficiently large datasets with associated annotations. For expeditious diagnosis and quantitative image analysis in large-scale clinical trials, there is a compelling need to predict segmentation quality without ground truth. In this paper, we propose a deep learning framework to locate erroneous regions on the boundary surfaces of segmented objects for quality control and assessment of segmentation. A Convolutional Neural Network (CNN) is explored to learn the boundary related image features of multi-objects that can be used to identify location-specific inaccurate segmentation. The predicted error locations can facilitate efficient user interaction for interactive image segmentation (IIS). We evaluated the proposed method on two data sets: Osteoarthritis Initiative (OAI) 3D knee MRI and 3D calf muscle MRI. The average sensitivity scores of 0.95 and 0.92, and the average positive predictive values of 0.78 and 0.91 were achieved, respectively, for erroneous surface region detection of knee cartilage segmentation and calf muscle segmentation. Our experiment demonstrated promising performance of the proposed method for segmentation quality assessment by automated detection of erroneous surface regions in medical images.

Body composition assessment with limited field-of-view computed tomography: A semantic image extension perspective.

Field-of-view (FOV) tissue truncation beyond the lungs is common in routine lung screening computed tomography (CT). This poses limitations for opportunistic CT-based body composition (BC) assessment as key anatomical structures are missing. Traditionally, extending the FOV of CT is considered as a CT reconstruction problem using limited data. However, this approach relies on the projection domain data which might not be available in application. In this work, we formulate the problem from the semantic image extension perspective which only requires image data as inputs. The proposed two-stage method identifies a new FOV border based on the estimated extent of the complete body and imputes missing tissues in the truncated region. The training samples are simulated using CT slices with complete body in FOV, making the model development self-supervised. We evaluate the validity of the proposed method in automatic BC assessment using lung screening CT with limited FOV. The proposed method effectively restores the missing tissues and reduces BC assessment error introduced by FOV tissue truncation. In the BC assessment for large-scale lung screening CT datasets, this correction improves both the intra-subject consistency and the correlation with anthropometric approximations. The developed method is available at https://github.com/MASILab/S-EFOV.

Systematic design and data-driven evaluation of social determinants of health ontology (SDoHO).

OBJECTIVE: Social determinants of health (SDoH) play critical roles in health outcomes and well-being. Understanding the interplay of SDoH and health outcomes is critical to reducing healthcare inequalities and transforming a "sick care" system into a "health-promoting" system. To address the SDOH terminology gap and better embed relevant elements in advanced biomedical informatics, we propose an SDoH ontology (SDoHO), which represents fundamental SDoH factors and their relationships in a standardized and measurable way. MATERIAL AND METHODS: Drawing on the content of existing ontologies relevant to certain aspects of SDoH, we used a top-down approach to formally model classes, relationships, and constraints based on multiple SDoH-related resources. Expert review and coverage evaluation, using a bottom-up approach employing clinical notes data and a national survey, were performed. RESULTS: We constructed the SDoHO with 708 classes, 106 object properties, and 20 data properties, with 1,561 logical axioms and 976 declaration axioms in the current version. Three experts achieved 0.967 agreement in the semantic evaluation of the ontology. A comparison between the coverage of the ontology and SDOH concepts in 2 sets of clinical notes and a national survey instrument also showed satisfactory results. DISCUSSION: SDoHO could potentially play an essential role in providing a foundation for a comprehensive understanding of the associations between SDoH and health outcomes and paving the way for health equity across populations. CONCLUSION: SDoHO has well-designed hierarchies, practical objective properties, and versatile functionalities, and the comprehensive semantic and coverage evaluation achieved promising performance compared to the existing ontologies relevant to SDoH.

The human cost of ethical artificial intelligence.

Foundational models such as ChatGPT critically depend on vast data scales the internet uniquely enables. This implies exposure to material varying widely in logical sense, factual fidelity, moral value, and even legal status. Whereas data scaling is a technical challenge, soluble with greater computational resource, complex semantic filtering cannot be performed reliably without human intervention: the self-supervision that makes foundational models possible at least in part presupposes the abilities they seek to acquire. This unavoidably introduces the need for large-scale human supervision-not just of training input but also model output-and imbues any model with subjectivity reflecting the beliefs of its creator. The pressure to minimize the cost of the former is in direct conflict with the pressure to maximise the quality of the latter. Moreover, it is unclear how complex semantics, especially in the realm of the moral, could ever be reduced to an objective function any machine could plausibly maximise. We suggest the development of foundational models necessitates urgent innovation in quantitative ethics and outline possible avenues for its realisation.

Assessment of encoder-decoder-based segmentation models for thyroid ultrasound images.

Encoder-decoder-based semantic segmentation models classify image pixels into the corresponding class, such as the ROI (region of interest) or background. In the present study, simple / dilated convolution / series / directed acyclic graph (DAG)-based encoder-decoder semantic segmentation models have been implemented, i.e., SegNet (VGG16), SegNet (VGG19), U-Net, mobileNetv2, ResNet18, ResNet50, Xception and Inception networks for the segment TTUS(Thyroid Tumor Ultrasound) images. Transfer learning has been used to train these segmentation networks using original and despeckled TTUS images. The performance of the networks has been calculated using mIoU and mDC metrics. Based on the exhaustive experiments, it has been observed that ResNet50-based segmentation model obtained the best results objectively with values 0.87 for mIoU, 0.94 for mDC, and also according to radiologist opinion on shape, margin, and echogenicity characteristics of segmented lesions. It is noted that the segmentation model, namely ResNet50, provides better segmentation based on objective and subjective assessment. It may be used in the healthcare system to identify thyroid nodules accurately in real time.

Slowdowns in scalar implicature processing: Isolating the intention-reading costs in the Bott & Noveck task.

An underinformative sentence, such as Some cats are mammals, is trivially true with a semantic (some and perhaps all) reading of the quantifier and false with a pragmatic (some but not all) one, with the latter reliably resulting in longer response times than the former in a truth evaluation task (Bott & Noveck, 2004). Most analyses attribute these prolonged reaction times, or costs, to the steps associated with the derivation of the scalar implicature. In the present work we investigate, across three experiments, whether such slowdowns can be attributed (at least partly) to the participant's need to adjust to the speaker's informative intention. In Experiment 1, we designed a web-based version of Bott & Noveck's (2004) laboratory task that would most reliably provide its classic results. In Experiment 2 we found that over the course of an experimental session, participants' pragmatic responses to underinformative sentences are initially reliably long and ultimately comparable to response times of logical interpretations to the same sentences. Such results cannot readily be explained by assuming that implicature derivation is a consistent source of processing effort. In Experiment 3, we further tested our account by examining how response times change as a function of the number of people said to produce the critical utterances. When participants are introduced (via a photo and description) to a single 'speaker', the results are similar to those found in Experiment 2. However, when they are introduced to two 'speakers', with the second 'speaker' appearing midway (after five encounters with underinformative items), we found a significant uptick in pragmatic response latencies to the underinformative item right after participants' meet their second speaker (i.e. at their sixth encounter with an underinformative item). Overall, we interpret these results as suggesting that at least part of the cost typically attributed to the derivation of a scalar implicature is actually a consequence of how participants think about the informative intentions of the person producing the underinformative sentences.