Automatic Sequence-Based Network for Lung Diseases Detection in Chest CT

ObjectiveTo develop an accurate and rapid computed tomography (CT)-based interpretable AI system for the diagnosis of lung diseases.BackgroundMost existing AI systems only focus on viral pneumonia (e.g., COVID-19), specifically, ignoring other similar lung diseases: e.g., bacterial pneumonia (BP), which should also be detected during CT screening. In this paper, we propose a unified sequence-based pneumonia classification network, called SLP-Net, which utilizes consecutiveness information for the differential diagnosis of viral pneumonia (VP), BP, and normal control cases from chest CT volumes.MethodsConsidering consecutive images of a CT volume as a time sequence input, compared with previous 2D slice-based or 3D volume-based methods, our SLP-Net can effectively use the spatial information and does not need a large amount of training data to avoid overfitting. Specifically, sequential convolutional neural networks (CNNs) with multi-scale receptive fields are first utilized to extract a set of higher-level representations, which are then fed into a convolutional long short-term memory (ConvLSTM) module to construct axial dimensional feature maps. A novel adaptive-weighted cross-entropy loss (ACE) is introduced to optimize the output of the SLP-Net with a view to ensuring that as many valid features from the previous images as possible are encoded into the later CT image. In addition, we employ sequence attention maps for auxiliary classification to enhance the confidence level of the results and produce a case-level prediction.ResultsFor evaluation, we constructed a dataset of 258 chest CT volumes with 153 VP, 42 BP, and 63 normal control cases, for a total of 43,421 slices. We implemented a comprehensive comparison between our SLP-Net and several state-of-the-art methods across the dataset. Our proposed method obtained significant performance without a large amount of data, outperformed other slice-based and volume-based approaches. The superior evaluation performance achieved in the classification experiments demonstrated the ability of our model in the differential diagnosis of VP, BP and normal cases.

Straintables: An application that extracts sequences from genome assemblies and generates dissimilarity matrices

Background and Objectives: The dissimilarity matrix (DM) is an important component of phylogenetic analysis, and many software packages exist to build and show DMs. However, as the common input for this type of software are sequences in FASTA file format, the process of extracting and aligning each set of sequences to produce a big number of matrices can be laborious. Additionally, existing software does not facilitate the comparison of clusters of similarity across several DMs built for the same group of individuals, using different genomic regions. To address our requirements of such a tool, we designed Straintables to extract specific genomic region sequences from a group of intraspecies genomic assemblies, using extracted sequences to build dissimilarity matrices. Methods: A Python module with executable scripts was developed for a study on genetic diversity across strains of Toxoplasma gondii, being a general purpose system for DM calculation and visualization for preliminary phylogenetic studies. For automatic region sequence extraction from genomic assemblies we assembled a system that designs virtual primers using reference sequences located at genomic annotations, then matches those primers on genome files by using regex patterns. Extracted sequences are then aligned using Clustal Omega and compared to generate matrices. Results: Using this software saves the user from manual preparation and alignment of the sequences, a process that can be laborious when a large number of assemblies or regions are involved. The automatic sequence extraction process can be checked against BLAST results using the extracted sequence as queries, where correct results were observed for same-species pools for various organisms. The package also contains a matrix visualization tool focused on cluster visualization, capable of drawing matrices into image files with custom settings, and features methods of reordering matrices to facilitate the comparison of clustering patterns across two or more matrices. Conclusion: Straintables may replace and extend the functionality of existing matrix-oriented phylogenetic software, featuring automatic region extraction from genomic assemblies and enhanced matrix visualization capabilities emphasizing cluster identification. This module is open source, available at GitHub (https://github.com/Gab0/straintables) under a MIT license and also as a PIPY package.

Collaborative Robotics: Enhance Maintenance Procedures on Primary Flight Control Servo-Actuators

Electro-Hydraulic Servo-Actuators (EHSAs) are mainly used to command primary flight control surfaces in military and commercial aircraft. Since these devices are crucial for vehicle stability and maneuverability, a correct assessment of their health status is mandatory. Within this framework, a joint research project (HyDiag), held by Politecnico di Torino and Lufthansa Technik AG (LHT), aims to provide a more efficient and reliable procedure to determine the operating conditions of the EHSA. A smart and automatic sequence, able to extract several health features of the Unit Under Test (UUT), has been developed and integrated. The present paper discusses the implementation of a collaborative robot, equipped with a vision system and customized tools, for both health features extraction, and maintenance tasks on unserviceable servo-actuators. The main challenges related to the automation of such complex tasks in a real working environment are highlighted, togetherwith the advantages brought by the proposed approach. The paper also presents the first results of an ongoing experimental campaign. Specifically, it reports the enhancements of the maintenance procedures using collaborative robotics and possible future developments.

Reinforcement learning for bluff body active flow control in experiments and simulations

We have demonstrated the effectiveness of reinforcement learning (RL) in bluff body flow control problems both in experiments and simulations by automatically discovering active control strategies for drag reduction in turbulent flow. Specifically, we aimed to maximize the power gain efficiency by properly selecting the rotational speed of two small cylinders, located parallel to and downstream of the main cylinder. By properly defining rewards and designing noise reduction techniques, and after an automatic sequence of tens of towing experiments, the RL agent was shown to discover a control strategy that is comparable to the optimal strategy found through lengthy systematically planned control experiments. Subsequently, these results were verified by simulations that enabled us to gain insight into the physical mechanisms of the drag reduction process. While RL has been used effectively previously in idealized computer flow simulation studies, this study demonstrates its effectiveness in experimental fluid mechanics and verifies it by simulations, potentially paving the way for efficient exploration of additional active flow control strategies in other complex fluid mechanics applications.

On the automaticity of sequences defined by the Thue–Morse and period-doubling Stieltjes continued fractions

Continued fraction expansions of automatic numbers have been extensively studied during the last few decades. The research interests are, on one hand, in the degree or automaticity of the partial quotients following the seminal paper of Baum and Sweet in 1976, and on the other hand, in calculating the Hankel determinants and irrationality exponents, as one can find in the works of Allouche–Peyrière–Wen–Wen, Bugeaud, and the first author. This paper is motivated by the converse problem: to study Stieltjes continued fractions whose coefficients form an automatic sequence. We consider two such continued fractions defined by the Thue–Morse and period-doubling sequences, respectively, and prove that they are congruent to algebraic series in [Formula: see text] modulo [Formula: see text]. Consequently, the sequences of the coefficients of the power series expansions of the two continued fractions modulo [Formula: see text] are [Formula: see text]-automatic.

3D Point Cloud Analysis for Damage Detection on Hyperboloid Cooling Tower Shells

The safe operation and maintenance of the appropriate strength of hyperboloid cooling towers require special supervision and a maintenance plan that takes into consideration the condition of the structure. With three series of terrestrial laser scanning data, the paper presents an automatic inspection system for reinforced concrete cooling tower shells that ensures detection and measurement of damage together with the verification of the quality and durability of surface repairs as required by industry standards. The proposed solution provides an automatic sequence of algorithm steps with low computational requirements. The novel method is based on the analysis of values of the local surface curvature determined for each point in the cloud using principal component analysis and transformed using the square root function. Data segmentation into cloud points representing a uniform shell and identified defects was carried out using the region growing algorithm. The extent of extracted defects was defined through vectorisation with a convex hull. The proposed diagnostics strategy of reinforced concrete hyperboloid cooling towers was drafted and validated using an object currently under repair but in continuous service for fifty years. The results of detection and measurement of defects and verification of surface continuity at repaired sites were compared with traditional diagnostics results. It was shown that the sequence of algorithm steps successfully identified all cavities, scaling, and blisters in the shell recorded in the expert report (recognition rate—100%). Cartometric vectorisation of defects determined the scope of necessary shell repairs offering higher performance and detail level than direct contact measurement from suspended platforms. Analysis of local geometric features of repaired surfaces provided a reliable baseline for the evaluation of the repairs aimed at restoring the protective properties of the concrete surround, desirable especially in the warranty period.

From Controlled to Automatic Processes and Back Again: The Role of Contextual Features

In cognitive psychology, classical approaches categorize automatic and controlled processes from a dichotomous point of view. Automatic processes are believed to be rigid, whereas controlled processes are thought to be flexible. New theories have softened this dichotomous view. The aim of the present study is to examine the possibility of implementing flexibility in automatic processing through reliance on contextual features. One hundred and twenty subjects (mean age 22.4, SD = 4.2), 60 male and 60 female, participated in this study. An automatic sequence task (with and without contextual features) was used to test flexibility in automatic processing. Results showed that the use of contextual cues can increase flexibility in automatic processes. The results are discussed in light of new theories on softened automaticity.

Cobham’s Theorem and Automaticity

We make certain bounds in Krebs’ proof of Cobham’s theorem explicit and obtain corresponding upper bounds on the length of a common prefix of an aperiodic [Formula: see text]-automatic sequence and an aperiodic [Formula: see text]-automatic sequence, where [Formula: see text] and [Formula: see text] are multiplicatively independent. We also show that an automatic sequence cannot have arbitrarily large factors in common with a Sturmian sequence.

Communiqué: a planning-based sequence diagrams generator

During the software system development lifecycle, different types of Unified Modeling Language model are developed to represent different views of the system. Sequence diagrams represent one of the most important types of model. They show how objects in the system interact to offer the functionality manifested in the form of use cases. As the complexity of the system being modeled increases, creating the sequence diagrams manually becomes harder. However, the problem of automatic sequence diagrams generation has not caught enough researchers yet. This paper presents an approach and a tool to automatically generate sequence diagrams from use cases and class diagrams. The problem of determining the sequence of message passing is treated as an Artificial Intelligence action planning problem and solved as such. In doing so, Design by Contract concepts are enforced in the specification of the given use cases and class diagrams. A special message-passing planner, Communiqué, was developed and implemented accordingly. The overall approach was empirically evaluated against sets of manually created sequence diagrams available in the literature. Communiqué was able to create sequence diagrams comparable to the manually developed ones. The paper also sheds the light on some directions for future work to advance the applicability of the approach.