Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Learning from positive and unlabeled data or PU learning is the setting where a learner only has access to positive examples and unlabeled data. The assumption is that the unlabeled data can contain both positive and negative examples. This setting has attracted increasing interest within the machine learning literature as this type of data naturally arises in applications such as medical diagnosis and knowledge base completion. This article provides a survey of the current state of the art in PU learning. It proposes seven key research questions that commonly arise in this field and provides a broad overview of how the field has tried to address them.

/pdf/learning-from-positive-and-unlabeled-data-a-survey-4o60ux0esd.pdf

Learning from positive and unlabeled data: a survey

Matlab (the language of technical computing): using matlab graphics ver.5

Untethered micron-scale mobile robots can navigate and non-invasively perform specific tasks inside unprecedented and hard-to-reach inner human body sites and inside enclosed organ-on-a-chip microfluidic devices with live cells. They are aimed to operate robustly and safely in complex physiological environments where they will have a transforming impact in bioengineering and healthcare. Research along this line has already demonstrated significant progress, increasing attention, and high promise over the past several years. The first-generation microrobots, which could deliver therapeutics and other cargo to targeted specific body sites, have just been started to be tested inside small animals toward clinical use. Here, we review frontline advances in design, fabrication, and testing of untethered mobile microrobots for bioengineering applications. We convey the most impactful and recent strategies in actuation, mobility, sensing, and other functional capabilities of mobile microrobots, and discuss their potential advantages and drawbacks to operate inside complex, enclosed and physiologically relevant environments. We lastly draw an outlook to provide directions in the veins of more sophisticated designs and applications, considering biodegradability, immunogenicity, mobility, sensing, and possible medical interventions in complex microenvironments.

/pdf/mobile-microrobots-for-bioengineering-applications-5fh7v0t7qr.pdf

Mobile microrobots for bioengineering applications

Systemic chemotherapy remains the backbone of many cancer treatments. Due to its untargeted nature and the severe side effects it can cause, numerous nanomedicine approaches have been developed to overcome these issues. However, targeted delivery of therapeutics remains challenging. Engineering microrobots is increasingly receiving attention in this regard. Their functionalities, particularly their motility, allow microrobots to penetrate tissues and reach cancers more efficiently. Here, we highlight how different microrobots, ranging from tailor-made motile bacteria and tiny bubble-propelled microengines to hybrid spermbots, can be engineered to integrate sophisticated features optimised for precision-targeting of a wide range of cancers. Towards this, we highlight the importance of integrating clinicians, the public and cancer patients early on in the development of these novel technologies.

/pdf/engineering-microrobots-for-targeted-cancer-therapies-from-a-imodv8s6jv.pdf

Engineering microrobots for targeted cancer therapies from a medical perspective

To achieve the effective navigation of microscale agents in the vascular network, a high magnetic field strength with high directional magnetic gradients are required. So far, the methods that have been investigated support only one of these specifications but not both. Here, we propose a new method dubbed dipole field navigation (DFN) that provides high field strength to bring magnetic agents at saturation magnetization with gradients exceeding 300 mT/m at any depth within the human body. For DFN, the high field strength is achieved by placing the patient in the tunnel of a clinical MRI scanner, while high gradients are generated by the distortions of the scanner's homogeneous field from larger ferromagnetic cores placed at specific locations outside the patient. The main challenge of DFN lies in the methods that are required to adequately place the cores in the tunnel. Here, a first method is presented to solve the inverse magnetic problem of positioning such a set of cores so that microscale agents could be guided through a desired path in the vascular network. As a first proof of concept, magnetic particles were steered successfully in three consecutive bifurcations in a 3-D in vitro network.

Dipole Field Navigation: Theory and Proof of Concept

The magnetic navigation of drugs in the vascular network promises to increase the efficacy and reduce the secondary toxicity of cancer treatments by targeting tumors directly. Recently, dipole field navigation (DFN) was proposed as the first method achieving both high field and high navigation gradient strengths for whole-body interventions in deep tissues. This is achieved by introducing large ferromagnetic cores around the patient inside a magnetic resonance imaging (MRI) scanner. However, doing so distorts the static field inside the scanner, which prevents imaging during the intervention. This limitation constrains DFN to open-loop navigation, thus exposing the risk of a harmful toxicity in case of a navigation failure. Here, we are interested in periodically assessing drug targeting efficiency using MRI even in the presence of a core. We demonstrate, using a clinical scanner, that it is in fact possible to acquire, in specific regions around a core, images of sufficient quality to perform this task. ...

/pdf/enabling-automated-magnetic-resonance-imaging-based-4rolfn63mt.pdf

Enabling automated magnetic resonance imaging-based targeting assessment during dipole field navigation

Cooperative localization is one of the fundamental techniques in GPS-denied environments, such as underwater, indoor, or on other planets, where teams of robots use each other to improve their pose estimation. In this paper, we present a novel schema for performing cooperative localization using bearing only measurements. These measurements correspond to the angles of pairs of landmarks located on each robot, extracted from camera images. Thus, the only exteroceptive measurements used are the camera images taken by each robot, under the condition that both cameras are mutually visible. An analytical solution is derived, together with an analysis of uncertainty as a function to the relative pose of the robots. A theoretical comparison with a standard stereo camera pose reconstruction is also provided. Finally, the feasibility and performance of the proposed method were validated, through simulations and experiments with a mobile robot setup.

/pdf/i-see-you-you-see-me-cooperative-localization-through-12clr1q4kb.pdf

I see you, you see me: Cooperative localization through bearing-only mutually observing robots

A new method for the navigation of therapeutic agents in the vascular network is introduced. This method, dubbed Dipole Field Navigation (DFN), is characterized by high directional gradients and a high magnetic field strength. The latter is used to bring magnetic therapeutic agents at saturation magnetization such that when combined with high directional gradients, effective navigation at any depths within the patient can be achieved. DFN does not have many of the constraints of gradient coil-based platforms, which include potential peripheral nerve stimulations, reduced directional changes and slew rates of the gradient fields, overheating of the coils, and high implementation cost. To achieve such specifications, soft ferromagnetic cores are positioned at specific locations inside the tunnel of a clinical MRI scanner providing a high uniform field of typically up to 3T, sufficient to bring both the cores and the therapeutic agents at full saturation magnetization. The field distortions created by the cores result in gradients exceeding 300 mT/m for whole body interventions. Hence, with such cores placed at specific locations, the resulting gradients would cause the therapeutic agents to follow a precise path in the vascular network towards the targeted region. In this paper, the fundamental theory of DFN with preliminary in vitro experimental results using one core in a 1.5T scanner confirms the potential of DFN for targeted drug delivery.

Dipole Field Navigation for targeted drug delivery

Magnetically guided agents in the vascular network are expected to enable the targeted delivery of therapeutics to localized regions while avoiding their systemic circulation. Due to the small size of the medically applicable superparamagnetic microscale agents required to reach the smaller arteries, high magnetic fields and gradients are required to reach saturation magnetization and generate sufficient directional forces, respectively, for their effective navigation in the vascular environment. Currently, the only method that provides both a high field and high magnetic gradient strengths in deep tissues at the human scale is known as dipole field navigation (DFN). This method relies on the controlled distortion of the field inside a magnetic resonance imaging scanner by precisely positioning ferromagnetic cores around the patient. This paper builds on previous works that have experimentally demonstrated the feasibility of the method and proposed optimization algorithms for placing the cores. The maximum gradient strengths that can be generated for single and multibifurcation vascular routes are investigated while considering the major constraints on core positions (limited space in the scanner, magnetic interactions). Using disc cores, which were previously shown particularly effective for the DFN, results show that gradient strengths exceeding 400 mT/m (a tenfold increase with respect to typical gradients generated by clinical MRI scanners) can be achieved at 10 cm inside the patient, but decrease as the complexity of the vascular route increases. The potential of the method is evaluated for targeting regions of a vascular model of a human liver, segmented from clinical data, with encouraging results showing strengths up to 150 mT/m for generating gradients at three consecutive bifurcations within 20° of average gradient direction error.

Evaluation of the Potential of Dipole Field Navigation for the Targeted Delivery of Therapeutic Agents in a Human Vascular Network

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Maxime Latulippe

Author Tools

Chat about Author