1,721,089 research outputs found
Image biomarkers and explainable AI: handcrafted features versus deep learned features
No full textAbstract Feature extraction and selection from medical data are the basis of radiomics and image biomarker discovery for various architectures, including convolutional neural networks (CNNs). We herein describe the typical radiomics steps and the components of a CNN for both deep feature extraction and end-to-end approaches. We discuss the curse of dimensionality, along with dimensionality reduction techniques. Despite the outstanding performance of deep learning (DL) approaches, the use of handcrafted features instead of deep learned features needs to be considered for each specific study. Dataset size is a key factor: large-scale datasets with low sample diversity could lead to overfitting; limited sample sizes can provide unstable models. The dataset must be representative of all the “facets” of the clinical phenomenon/disease investigated. The access to high-performance computational resources from graphics processing units is another key factor, especially for the training phase of deep architectures. The advantages of multi-institutional federated/collaborative learning are described. When large language models are used, high stability is needed to avoid catastrophic forgetting in complex domain-specific tasks. We highlight that non-DL approaches provide model explainability superior to that provided by DL approaches. To implement explainability, the need for explainable AI arises, also through post hoc mechanisms. Relevance statement This work aims to provide the key concepts for processing the imaging features to extract reliable and robust image biomarkers. Key Points The key concepts for processing the imaging features to extract reliable and robust image biomarkers are provided. The main differences between radiomics and representation learning approaches are highlighted. The advantages and disadvantages of handcrafted versus learned features are given without losing sight of the clinical purpose of artificial intelligence models. Graphical Abstrac
Applications of imaging processing to MRgFUS treatment for fibroids: A review
No full textMagnetic resonance guided focused ultrasound (MRgFUS) is an innovative technology that can treat many oncological diseases. Among these, uterine fibroids are well suited to be treated by focused ultrasound, because the treatment, unlike traditional surgical resection, is non-invasive and thus preserves the desired reproductive capacity of patients. There are some methodological issues in MRgFUS treatment that should be addressed. First, there is operator dependence; this is related to the use of manual approaches for the segmentation of regions of interest (ROI) for treatment, both in the initial stages of treatment planning and in the post-treatment evaluation of the ablated area. From this scenario, we understand the need to integrate MRgFUS technology with methods for the automatic detection of the regions affected by the treatment. Temperature monitoring techniques, based on proton resonance shift (PRF), although not always able to provide correct measurements, are the most used in the treatments guided by magnetic resonance. The dependence on a reference image makes the thermal maps obtained through PRF subject to artefacts and, consequently, to temperature measurement errors. It is therefore crucial to develop new techniques, perhaps based on referenceless thermometry approaches, in order to avoid overheating in unwanted areas that could lead to patients suffering burns. Closely linked to the two above mentioned problems, there is the motion compensation that would improve the current method (this requires re-planning MRgFUS treatment in cases of patient movement) as well as temperature monitoring since it would overcome limitations related to a fixed baseline image, uncorrelated to the real patient position. This paper addresses these important issues, providing for each of them a high-level discussion able to give a brief overview. Specific technical details are provided about one of the approaches in the literature, in order to make the discussed problem more complete and easier to understand
Reply to a Letter to the Editor on Comparative performance of fully-automated and semi-automated artificial intelligence methods for the detection of clinically significant prostate cancer on MRI: a systematic review
No full textA Novel Bio-Inspired Approach for High-Performance Management in Service-Oriented Networks
No full textService-continuity in distributed computing can be enhanced by designing self-organized systems, with a non-fixed structure, able to modify their structure and organization, as well as adaptively react to internal and external environment changes. In this paper, an architecture exploiting a bio-inspired management approach, i.e., the functioning of cell metabolism, for specialized computing environments in Service-Oriented Networks (SONs) is proposed. Similar to the processes acting in metabolic networks, the nodes communicate to each other by means of stimulation or suppression chains giving rise to emergent behaviors to defend against foreign invaders, attacks, and malfunctioning. The main contribution of this work is a novel bio-inspired methodology for SON analysis to improve the network reliability and robustness for maintaining service-continuity. To show the effectiveness of the proposed computational framework, an embedded Field-Programmable Gate Array (FPGA) prototyped SON for a relevant healthcare imaging application is also outlined. In particular, our case study extracts and analyzes the Cerebral Vascular Tree from Magnetic Resonance Angiography series via a Maximum Intensity Projection algorithm; the proposed solution addresses and implements some basic issues of an interesting diagnosis tool for cerebral aneurysm detection. The prototyped system was tested and evaluated in terms of execution time and used resource analysis, by achieving a 4× speed-up factor compared to the software counterpart
Fingerprint classification based on deep learning approaches: Experimental findings and comparisons
Full text linkBiometric classification plays a key role in fingerprint characterization, especially in the identification process. In fact, reducing the number of comparisons in biometric recognition systems is essential when dealing with large-scale databases. The classification of fingerprints aims to achieve this target by splitting fingerprints into different categories. The general approach of fingerprint classification requires pre-processing techniques that are usually computationally expensive. Deep Learning is emerging as the leading field that has been successfully applied to many areas, such as image processing. This work shows the performance of pre-trained Convolutional Neural Networks (CNNs), tested on two fingerprint databases—namely, PolyU and NIST—and comparisons to other results presented in the literature in order to establish the type of classification that allows us to obtain the best performance in terms of precision and model efficiency, among approaches under examination, namely: AlexNet, GoogLeNet, and ResNet. We present the first study that extensively compares the most used CNN architectures by classifying the fingerprints into four, five, and eight classes. From the experimental results, the best performance was obtained in the classification of the PolyU database by all the tested CNN architectures due to the higher quality of its samples. To confirm the reliability of our study and the results obtained, a statistical analysis based on the McNemar test was performed
Proactive Particles in Swarm Optimization: A settings-free algorithm for real-parameter single objective optimization problems
No full textParticle Swarm Optimization (PSO) is an effective Swarm Intelligence technique for the optimization of non-linear and complex high-dimensional problems. Since PSO's performance is strongly dependent on the choice of its functioning settings, in this work we consider a self-tuning version of PSO, called Proactive Particles in Swarm Optimization (PPSO). PPSO leverages Fuzzy Logic to dynamically determine the best settings for the inertia weight, cognitive factor and social factor. The PPSO algorithm significantly differs from other versions of PSO relying on Fuzzy Logic, because specific settings are assigned to each particle according to its history, instead of being globally assigned to the whole swarm. In such a way, PPSO's particles gain a limited autonomous and proactive intelligence with respect to the reactive agents proposed by PSO. Our results show that PPSO achieves overall good optimization performances on the benchmark functions proposed in the CEC 2017 test suite, with the exception of those based on the Schwefel function, whose fitness landscape seems to mislead the fuzzy reasoning. Moreover, with many benchmark functions, PPSO is characterized by a higher speed of convergence than PSO in the case of high-dimensional problems
Advanced computational methods for oncological image analysis
Full text link: The Special Issue "Advanced Computational Methods for Oncological Image Analysis", published for the Journal of Imaging, covered original research papers about state-of-the-art and novel algorithms and methodologies, as well as applications of computational methods for oncological image analysis, ranging from radiogenomics to deep learning [...]
Recent advances of HCI in decision-making tasks for optimized clinical workflows and precision medicine
Full text linkThe ever-increasing amount of biomedical data is enabling new large-scale studies, even though ad hoc computational solutions are required. The most recent Machine Learning (ML) and Artificial Intelligence (AI) techniques have been achieving outstanding performance and an important impact in clinical research, aiming at precision medicine, as well as improving healthcare workflows. However, the inherent heterogeneity and uncertainty in the healthcare information sources pose new compelling challenges for clinicians in their decision-making tasks. Only the proper combination of AI and human intelligence capabilities, by explicitly taking into account effective and safe interaction paradigms, can permit the delivery of care that outperforms what either can do separately. Therefore, Human-Computer Interaction (HCI) plays a crucial role in the design of software oriented to decision-making in medicine. In this work, we systematically review and discuss several research fields strictly linked to HCI and clinical decision-making, by subdividing the articles into six themes, namely: Interfaces, Visualization, Electronic Health Records, Devices, Usability, and Clinical Decision Support Systems. However, these articles typically present overlaps among the themes, revealing that HCI inter-connects multiple topics. With the goal of focusing on HCI and design aspects, the articles under consideration were grouped into four clusters. The advances in AI can effectively support the physicians’ cognitive processes, which certainly play a central role in decision-making tasks because the human mental behavior cannot be completely emulated and captured; the human mind might solve a complex problem even without a statistically significant amount of data by relying upon domain knowledge. For this reason, technology must focus on interactive solutions for supporting the physicians effectively in their daily activities, by exploiting their unique knowledge and evidence-based reasoning, as well as improving the various aspects highlighted in this review
- …
