Search

Medical image synthesis has emerged as a promising solution to address the limited availability of annotated medical data needed for training machine learning algorithms in the context of image-based Clinical Decision Support (CDS) systems. To this end, Generative Adversarial Networks (GANs) have been mainly applied to support the algorithm training process by generating synthetic images for data augmentation. However, in the field of Wireless Capsule Endoscopy (WCE), the limited content diversity and size of existing publicly available annotated datasets adversely affect both the training stability and synthesis performance of GANs. In this paper a novel Variational Autoencoder (VAE) architecture is proposed for WCE image synthesis, namely ‘This Intestine Does not Exist’ (TIDE). This is the first VAE architecture comprising multiscale feature extraction convolutional blocks and residual connections. Its advantage is that it enables the generation of high-quality and diverse datasets even with a limited number of training images. Contrary to the current approaches, which are oriented towards the augmentation of the available datasets, this study demonstrates that using TIDE, real WCE datasets can be fully substituted by artificially generated ones, without compromising classification performance of CDS. It performs a spherical experimental evaluation study that covers both quantitative and qualitative aspects, including a user evaluation study performed by WCE specialists, which validate from a medical viewpoint that both the normal and abnormal WCE images synthesized by TIDE are sufficiently realistic. The quantitative results obtained by comparative experiments validate that the proposed architecture outperforms the state-of-the-art.

Abstract The adoption of convolutional neural network (CNN) models in high-stake domains is hindered by their inability to meet society’s demand for transparency in decision-making. So far, a growing number of methodologies have emerged for developing CNN models that are interpretable by design. However, such models are not capable of providing interpretations in accordance with human perception, while maintaining competent performance. In this paper, we tackle these challenges with a novel, general framework for instantiating inherently interpretable CNN models, named E pluribus unum interpretable CNN (EPU-CNN). An EPU-CNN model consists of CNN sub-networks, each of which receives a different representation of an input image expressing a perceptual feature, such as color or texture. The output of an EPU-CNN model consists of the classification prediction and its interpretation, in terms of relative contributions of perceptual features in different regions of the input image. EPU-CNN models have been extensively evaluated on various publicly available datasets, as well as a contributed benchmark dataset. Medical datasets are used to demonstrate the applicability of EPU-CNN for risk-sensitive decisions in medicine. The experimental results indicate that EPU-CNN models can achieve a comparable or better classification performance than other CNN architectures while providing humanly perceivable interpretations.

Machine Learning (ML) applications are growing in an unprecedented scale. The development of easy-to-use machine-learning application frameworks has enabled the development of advanced artificial intelligence (AI) applications with only a few lines of self-explanatory code. As a result, ML-based AI is becoming approachable by mainstream developers and small businesses. However, the deployment of ML algorithms for remote high throughput ML task execution, involving complex data-processing pipelines can still be challenging, especially with respect to production ML use cases. To cope with this issue, in this paper we propose a novel system architecture that enables Algorithm-agnostic, Scalable ML (ASML) task execution for high throughput applications. It aims to provide an answer to the research question of how to design and implement an abstraction framework, suitable for the deployment of end-to-end ML pipelines in a generic and standard way. The proposed ASML architecture manages horizontal scaling, task scheduling, reporting, monitoring and execution of multi-client ML tasks using modular, extensible components that abstract the execution details of the underlying algorithms. Experiments in the context of obstacle detection and recognition, as well as in the context of abnormality detection in medical image streams, demonstrate its capacity for parallel, mission critical, task execution.

Artificial intelligence (AI) is an integral part of clinical decision support systems (CDSS), offering methods to approximate human reasoning and computationally infer decisions. Such methods are generally based on medical knowledge, either directly encoded with rules or automatically extracted from medical data using machine learning (ML). ML techniques, such as Artificial Neural Networks (ANNs) and support vector machines (SVMs), are based on mathematical models with parameters that can be optimally tuned using appropriate algorithms. The ever-increasing computational capacity of today’s computer systems enables more complex ML systems with millions of parameters, bringing AI closer to human intelligence. With this objective, the term deep learning (DL) has been introduced to characterize ML based on deep ANN (DNN) architectures with multiple layers of artificial neurons. Despite all of these promises, the impact of AI in current clinical practice is still limited. However, this could change shortly, as the significantly increased papers in AI, machine learning and deep learning in cardiology show. We highlight the significant achievements of recent years in nearly all areas of cardiology and underscore the mounting evidence suggesting how AI will take a central stage in the field.

A novel accurate and robust metric called II-Learn for measuring the increase of intelligence of a system after a learning process is proposed. We define evolving learning systems, as systems that are able to make at least one measurable evolutionary step by learning. To prove the effectiveness of the metric we performed a case study, using a learning system. The universality of II-Learn is based on the fact that it does not depend on the architecture of the studied system.

Sensor technologies are crucial in biomedicine, as the biomedical systems and devices used for screening and diagnosis rely on their efficiency and effectiveness [...]

Every day, visually challenged people (VCP) face mobility restrictions and accessibility limitations. A short walk to a nearby destination, which for other individuals is taken for granted, becomes a challenge. To tackle this problem, we propose a novel visual perception system for outdoor navigation that can be evolved into an everyday visual aid for VCP. The proposed methodology is integrated in a wearable visual perception system (VPS). The proposed approach efficiently incorporates deep learning, object recognition models, along with an obstacle detection methodology based on human eye fixation prediction using Generative Adversarial Networks. An uncertainty-aware modeling of the obstacle risk assessment and spatial localization has been employed, following a fuzzy logic approach, for robust obstacle detection. The above combination can translate the position and the type of detected obstacles into descriptive linguistic expressions, allowing the users to easily understand their location in the environment and avoid them. The performance and capabilities of the proposed method are investigated in the context of safe navigation of VCP in outdoor environments of cultural interest through obstacle recognition and detection. Additionally, a comparison between the proposed system and relevant state-of-the-art systems for the safe navigation of VCP, focused on design and user-requirements satisfaction, is performed.

Background and study aims Capsule endoscopy (CE) is invaluable for minimally invasive endoscopy of the gastrointestinal tract; however, several technological limitations remain including lack of reliable lesion localization. We present an approach to 3D reconstruction and localization using visual information from 2D CE images. Patients and methods Colored thumbtacks were secured in rows to the internal wall of a LifeLike bowel model. A PillCam SB3 was calibrated and navigated linearly through the lumen by a high-precision robotic arm. The motion estimation algorithm used data (light falling on the object, fraction of reflected light and surface geometry) from 2D CE images in the video sequence to achieve 3D reconstruction of the bowel model at various frames. The ORB-SLAM technique was used for 3D reconstruction and CE localization within the reconstructed model. This algorithm compared pairs of points between images for reconstruction and localization. Results As the capsule moved through the model bowel 42 to 66 video frames were obtained per pass. Mean absolute error in the estimated distance travelled by the CE was 4.1 ± 3.9 cm. Our algorithm was able to reconstruct the cylindrical shape of the model bowel with details of the attached thumbtacks. ORB-SLAM successfully reconstructed the bowel wall from simultaneous frames of the CE video. The “track” in the reconstruction corresponded well with the linear forwards-backwards movement of the capsule through the model lumen. Conclusion The reconstruction methods, detailed above, were able to achieve good quality reconstruction of the bowel model and localization of the capsule trajectory using information from the CE video and images alone.

Background and aims Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE. Methods Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers. Results The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %). Conclusion MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.

Hyperspectral/Multispectral imaging (HSI/MSI) technologies are able to sample from tens to hundreds of spectral channels within the electromagnetic spectrum, exceeding the capabilities of human vision. These spectral techniques are based on the principle that every material has a different response (reflection and absorption) to different wavelengths. Thereby, this technology facilitates the discrimination between different materials. HSI has demonstrated good discrimination capabilities for materials in fields, for instance, remote sensing, pollution monitoring, field surveillance, food quality, agriculture, astronomy, geological mapping, and currently, also in medicine. HSI technology allows tissue observation beyond the limitations of the human eye. Moreover, many researchers are using HSI as a new diagnosis tool to analyze optical properties of tissue. Recently, HSI has shown good performance in identifying human diseases in a non-invasive manner. In this paper, we show the potential use of these technologies in the medical domain, with emphasis in the current advances in gastroenterology. The main aim of this review is to provide an overview of contemporary concepts regarding HSI technology together with state-of-art systems and applications in gastroenterology. Finally, we discuss the current limitations and upcoming trends of HSI in gastroenterology.

The Symmetric Traveling Salesman Problem (sTSP) is an intensively studied NP-hard problem. It has many important real-life applications such as logistics, planning, manufacturing of microchips and DNA sequencing. In this paper we propose a cluster level incremental tour construction method called Intra-cluster Refinement Heuristic (IntraClusTSP). The proposed method can be used both to extend the tour with a new node and to improve the existing tour. The refinement step generates a local optimal tour for a cluster of neighbouring nodes and this local optimal tour is then merged into the global optimal tour. Based on the performed evaluation tests the proposed IntraClusTSP method provides an efficient incremental tour generation and it can improve the tour efficiency for every tested state-of-the-art methods including the most efficient Chained Lin-Kernighan refinement algorithm. As an application example, we apply IntraClusTSP to automatically determine the optimal number of clusters in a cluster analysis problem. The standard methods like Silhouette index, Elbow method or Gap statistic method, to estimate the number of clusters support only partitional (single level) clustering, while in many application areas, the hierarchical (multi-level) clustering provides a better clustering model. Our proposed method can discover hierarchical clustering structure and provides an outstanding performance both in accuracy and execution time.