Decidual Vasculopathy Identification in Whole Slide Images Using Multiresolution Hierarchical Convolutional Neural Networks.

After a child is born, the examination of the placenta by a pathologist for abnormalities, such as infection or maternal vascular malperfusion, can provide important information about the immediate and long-term health of the infant. Detection of the pathologic placental blood vessel lesion decidual vasculopathy (DV) has been shown to predict adverse pregnancy outcomes, such as preeclampsia, which can lead to mother and neonatal morbidity in subsequent pregnancies. However, because of the high volume of deliveries at large hospitals and limited resources, currently a large proportion of delivered placentas are discarded without inspection. Furthermore, the correct diagnosis of DV often requires the expertise of an experienced perinatal pathologist. We introduce a hierarchical machine learning approach for the automated detection and classification of DV lesions in digitized placenta slides, along with a method of coupling learned image features with patient metadata to predict the presence of DV. Ultimately, the approach will allow many more placentas to be screened in a more standardized manner, providing feedback about which cases would benefit most from more in-depth pathologic inspection. Such computer-assisted examination of human placentas will enable real-time adjustment to infant and maternal care and possible chemoprevention (eg, aspirin therapy) to prevent preeclampsia, a disease that affects 2% to 8% of pregnancies worldwide, in women identified to be at risk with future pregnancies.

Robust mechanobiological behavior emerges in heterogeneous myosin systems.

Biological complexity presents challenges for understanding natural phenomenon and engineering new technologies, particularly in systems with molecular heterogeneity. Such complexity is present in myosin motor protein systems, and computational modeling is essential for determining how collective myosin interactions produce emergent system behavior. We develop a computational approach for altering myosin isoform parameters and their collective organization, and support predictions with in vitro experiments of motility assays with α-actinins as molecular force sensors. The computational approach models variations in single myosin molecular structure, system organization, and force stimuli to predict system behavior for filament velocity, energy consumption, and robustness. Robustness is the range of forces where a filament is expected to have continuous velocity and depends on used myosin system energy. Myosin systems are shown to have highly nonlinear behavior across force conditions that may be exploited at a systems level by combining slow and fast myosin isoforms heterogeneously. Results suggest some heterogeneous systems have lower energy use near stall conditions and greater energy consumption when unloaded, therefore promoting robustness. These heterogeneous system capabilities are unique in comparison with homogenous systems and potentially advantageous for high performance bionanotechnologies. Findings open doors at the intersections of mechanics and biology, particularly for understanding and treating myosin-related diseases and developing approaches for motor molecule-based technologies.

Interrupted: The roles of distributed effort and incubation in preventing fixation and generating problem solutions.

Fixation on inappropriate concepts is a key barrier to problem solving. Previous research has shown that continuous work is likely to cause repeated retrieval of those concepts, resulting in increased fixation. Accordingly, distributing effort across problems through multiple, brief, and interlaced sessions (distributed effort) should prevent such fixation and in turn enhance problem solving. This study examined whether distributed effort can provide an advantage for problem solving, particularly for problems that can induce fixation (Experiment 1), and whether and how incubation can be combined with distributed effort to further enhance performance (Experiment 2). Remote Associates Test (RAT) problems were used as the problem-solving tasks. Half of them (i.e., misleading RAT) were more likely to mislead individuals to fixate on incorrect associates than the other half. Experiments revealed a superiority of distributed over massed effort on misleading RAT performance and a differing time course of incubation for the massed and distributed groups. We conclude that distributed effort facilitates problem solving, most likely via overcoming fixation. Cognitive mechanisms other than the commonly posited forgetting of inappropriate ideas may occur during incubation to facilitate problem solving. The experiments in this article offer support for the occurrence of spreading activation during incubation.

Emergent systems energy laws for predicting myosin ensemble processivity.

In complex systems with stochastic components, systems laws often emerge that describe higher level behavior regardless of lower level component configurations. In this paper, emergent laws for describing mechanochemical systems are investigated for processive myosin-actin motility systems. On the basis of prior experimental evidence that longer processive lifetimes are enabled by larger myosin ensembles, it is hypothesized that emergent scaling laws could coincide with myosin-actin contact probability or system energy consumption. Because processivity is difficult to predict analytically and measure experimentally, agent-based computational techniques are developed to simulate processive myosin ensembles and produce novel processive lifetime measurements. It is demonstrated that only systems energy relationships hold regardless of isoform configurations or ensemble size, and a unified expression for predicting processive lifetime is revealed. The finding of such laws provides insight for how patterns emerge in stochastic mechanochemical systems, while also informing understanding and engineering of complex biological systems.

Data on human decision, feedback, and confidence during an artificial intelligence-assisted decision-making task.

The data are collected from a human subjects study in which 100 participants solve chess puzzle problems with artificial intelligence (AI) assistance. The participants are assigned to one of the two experimental conditions determined by the direction of the change in AI performance at problem 20: 1) high- to low-performing and 2) low- to high-performing. The dataset contains information about the participants' move before an AI suggestion, the goodness evaluation score of these moves, AI suggestion, feedback, and the participants' confidence in AI and self-confidence during three initial practice problems and 30 experimental problems. The dataset contains 100 CSV files, one per participant. There is opportunity for this dataset to be utilized in various domains that research human-AI collaboration scenarios such as human-computer interaction, psychology, computer science, and team management in engineering/business. Not only can the dataset enable further cognitive and behavioral analysis in human-AI collaboration contexts but also provide an experimental platform to develop and test future confidence calibration methods.

Inducing Vascular Grammars for Anomaly Classification in Brain Angiograms.

As machine learning is used to make strides in medical diagnostics, few methods provide heuristics from which human doctors can learn directly. This work introduces a method for leveraging human observable structures, such as macroscale vascular formations, for producing assessments of medical conditions with relatively few training cases, and uncovering patterns that are potential diagnostic aids. The approach draws on shape grammars, a rule-based technique, pioneered in design and architecture, and accelerated through a recursive subgraph mining algorithm. The distribution of rule instances in the data from which they are induced is then used as an intermediary representation enabling common classification and anomaly detection approaches to identify indicative rules with relatively small data sets. The method is applied to seven-tesla time-of-flight angiography MRI (n = 54) of human brain vasculature. The data were segmented and induced to generate representative grammar rules. Ensembles of rules were isolated to implicate vascular conditions reliably. This application demonstrates the power of automated structured intermediary representations for assessing nuanced biological form relationships, and the strength of shape grammars, in particular for identifying indicative patterns in complex vascular networks.

Data on the Human Versus artificial intelligence process management experiment.

Human subject experiments are performed to evaluate the influence of artificial intelligence (AI) process management on human design teams solving a complex engineering problem and compare that to the influence of human process management. Participants are grouped into teams of five individuals and asked to generate a drone fleet and plan routes to deliver parcels to a given customer market. The teams are placed under the guidance of either a human or an AI external process manager. Halfway through the experiment, the customer market is changed unexpectedly, requiring teams to adjust their strategy. During the experiment, participants can create, evaluate, share their drone designs and delivery routes, and communicate with their team through a text chat tool using a collaborative research platform called HyForm. The research platform collects step-by-step logs of the actions made by and communication amongst participants in both the design team's roles and the process managers. This article presents the data sets collected for 171 participants assigned to 31 design teams, 15 teams under the guidance of an AI agent (5 participants), and 16 teams under the guidance of a human manager (6 participants). These data sets can be used for data-driven design, behavioral analyses, sequence-based analyses, and natural language processing.

Attention affordances: Applying attention theory to the design of complex visual interfaces.

The design of visual interfaces plays a crucial role in ensuring swift and accurate information search for operators, who use procedures and information tables to cope with problems arising during emergencies. The primary cognitive mechanism involved in information search is visual attention. However, design of interfaces is seldom done through applying predictions of theories of attention. Conversely, theories of attention are seldom tested in applied contexts. Combining application and attention research thus stands to benefit both fields. Therefore, this study tested three theories of visual attention that are especially relevant for information processing in emergencies-Load Theory, Feature Integration Theory, and Dilution Theory-as well as predictions about attentional guidance and capture of color in a complex visual interface. Evidence was found for several predictions from theory, especially from Feature Integration Theory. Implications for design practice and attention research are discussed. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Data on the design and operation of drones by both individuals and teams.

Human subject experiments are performed to assess the impact of artificial intelligence (AI) agents on distributed human design teams and individual human designers. In the team experiment, participants in teams of six develop and operate a drone fleet to deliver parcels routed to multiple locations of a target market. Among the design teams in the experiment, half of the design teams are human-only teams with no available AI agent. The other half of the design teams, designated as hybrid teams, have drone design and operation AI agents to advise them. Halfway through the team experiment, team structure is changed unexpectedly, requiring participants to adapt to the change. In the individual experiment, participants develop drones based on given design specifications, either on their own or with the availability of a drone design AI agent to advise them. During these experiments, participants configure, test, and share their designs and communicate with their teammates through an online research platform. The platform collects a step-by-step log of the actions made by participants. This article contains data sets collected from 44 teams (264 participants) in the team experiment and 73 participants in the individual experiment. These data sets can be used for behavioral analysis, sequence-based analysis, and natural language processing.

Written in Blood: Applying Shape Grammars to Retinal Vasculatures.

Purpose: Blood vessel networks within the retina are crucial for maintaining tissue perfusion and therefore good vision. Their complexity and unique patterns often require a steep learning curve for humans to identify trends and changes in the shape and topology of the networks, even though there exists much information important to identifying disease within them. Methods: Through image processing, the vasculature is isolated from other features of the fundus images, forcing the viewer to focus on the complex vascular feature. This article explores an approach using a grammar based on shape to describe retinal vasculature and to generate realistic and increasingly unrealistic artificial vascular networks that are then reviewed by ophthalmologists via digital survey. The ophthalmologists are asked whether these artificial vascular networks appeared realistic or unrealistic. Results: With only three rules (initiate, branch, and curve), the grammar accomplishes these goals. Networks are generated by adding noise to rule parameters present in existing networks. Via the survey of synthetic networks generated with different noise parameters, a correlation between noise in the branch rule and realistic association is revealed. Conclusions: By creating a language to describe retinal vasculature, this article allows for the potential of new insight into such an important but less understood feature of the retina, which in the future may play a role in diagnosing or helping to predict types of ocular disease. Translational Relevance: Applying shape grammar to describe retinal vasculature permits new understanding, which in turn provides the potential for new diagnostic tools.

Silence is golden: The effect of verbalization on group performance.

Contrary to the popular belief that collaboration brings better problem solutions, empirical studies have revealed that interacting groups often performed worse than noninteracting "nominal" groups. Past studies mainly examined how overhearing others' ideas impacts group performance. This study investigated the impact of another essential but overlooked group communicative process-verbalizing ideas to others-on group performance. Participants (N = 156) solved 20 verbal puzzles either alone quietly, alone thinking-aloud, or in verbalizing pairs. Participants in the same working-alone condition were randomly paired to form nominal pairs and their pooled performance was treated as nominal group performance. Relative to the quiet nominal group, the performance of the thinking-aloud nominal and interacting groups were impaired to similar extents. These two groups also demonstrated a similar limited capacity to expand the search scope. The equivalency of the interacting and thinking-aloud nominal group results suggest that verbalization is a key factor in groups' inferior performance. (PsycINFO Database Record

Data on the design of truss structures by teams of engineering students.

This experiment was conducted in order to compare different approaches that human teams use to solve design problems that change dynamically during solving. Specifically, study participants were given the task of designing a truss structure (similar to a bridge spanning a chasm) in teams of three. At two points during design, the problem statement was changed unexpectedly, requiring participants to adapt. Two conditions were given different initial problem representations. During the study, every participant had access to a computer interface that allowed them to construct, test, and share solutions. The interface also made it possible to collect a step-by-step log of the actions made by participants during the study. This article contains data collected from 48 participants (16 teams). This data has been used previously in behavioral analyses, sequence-based analysis, and development of computational models.

The influence of open goals on the acquisition of problem-relevant information.

There have been a number of recent findings indicating that unsolved problems, or open goals more generally, influence cognition even when the current task has no relation to the task in which the goal was originally set. It was hypothesized that open goals would influence what information entered the problem-solving process. Three studies were conducted to establish the effect of open goals on the acquisition of problem-relevant information. It was found that problem-relevant information, or hints, presented implicitly in a 2nd task in between attempts at solving problems aided problem solving. This effect cannot be attributed to strategic behavior after participants caught on to the manipulation, as most participants were not aware of the relationship. The implications of this research are discussed, including potential contributions to our understanding of insight, incubation, transfer, and creativity.

Data on the configuration design of internet-connected home cooling systems by engineering students.

This experiment was carried out to record the step-by-step actions that humans take in solving a configuration design problem, either in small teams or individually. Specifically, study participants were tasked with configuring an internet-connected system of products to maintain temperature within a home, subject to cost constraints. Every participant was given access to a computer-based design interface that allowed them to construct and assess solutions. The interface was also used to record the data that is presented here. In total, data was collected for 68 participants, and each participant was allowed to perform 50 design actions in solving the configuration design problem. Major results based on the data presented here have been reported separately, including initial behavioral analysis (McComb et al.) [1], [2] and design pattern assessments via Markovian modeling (McComb et al., 2017; McComb et al., 2017) [3], [4].

The role of functionality in the mental representations of engineering students: some differences in the early stages of expertise.

As engineers gain experience and become experts in their domain, the structure and content of their knowledge changes. Two studies are presented that examine differences in knowledge representation among freshman and senior engineering students. The first study examines recall of mechanical devices and chunking of components, and the second examines whether seniors represent devices in a more abstract functional manner than do freshmen. The most prominent differences between these 2 groups involve their representation of the functioning of groups of electromechanical components and how these groups of components interact to produce device behavior. Seniors are better able to construct coherent representations of devices by focusing on the function of sets of components in the device. The findings from these studies highlight some ways in which the structure and content of mental representations of design knowledge differ during the early stages of expertise acquisition.

The effect of incidental hints when problems are suspended before, during, or after an impasse.

Two studies examine how the time at which problem solving is suspended relative to an impasse affects the impact of incidental hints. An impasse is a point in problem solving at which a problem solver is not making progress and does not know how to proceed. In both studies, work on remote associates problems was suspended before an impasse was reached, at the time an impasse was reached, or after a period of continued work during an impasse. After problem solving was suspended on a set of problems, participants completed a lexical decision task before resuming work on the set of unsolved problems. For half of the problems suspended during each impasse state, solution words were presented as incidental hints in the lexical decision task. The proportion of initially unsolved problems that were solved after the intervening lexical decision task was greater when problem solving was suspended at the point an impasse was reached than when problem solving was suspended before an impasse or after a period of continued work during an impasse. These results suggest that suspending problem solving at the point of impasse may increase susceptibility to incidentally presented hints. The point of impasse may be an opportune time for hints because the problem has been explored but there has not been a large increase in fixation on failed solution attempts.