Modern technology makes it possible to sequence individual cells and to identify which genes are currently being expressed in each cell. These methods are sensitive and consequently error prone. Devices, environment and biology itself can be responsible for failures and differences between measurements. Researchers at Helmholtz Zentrum München joined forces with colleagues from the Technical University of Munich (TUM) and the British Wellcome Sanger Institute and have developed algorithms that make it possible to predict and correct such sources of error. The work was published in'Nature Methods' and'Nature Communications'.
To improve evaluation efficiency, a team of researchers at Helmholtz Zentrum München and the University Hospital, LMU Munich, trained a deep neuronal network with almost 20,000 single cell images to classify them. Dr. med Karsten Spiekermann and Simone Schwarz from the Department of Medicine III, University Hospital, LMU Munich, used images which were extracted from blood smears of 100 patients suffering from the aggressive blood disease AML and 100 controls. The new AI-driven approach was then evaluated by comparing its performance with the accuracy of human experts. The result showed that the AI-driven solution is able to identify diagnostic blast cells at least as good as a trained cytologist expert. Deep learning algorithms for image processing require two things: first, an appropriate convolutional neural network architecture with hundreds of thousands of parameters; second, a sufficiently large amount of training data.
Two artificial intelligence companies are working on a pair of technology-imbued spectacles designed to track the severity of Parkinson's symptoms. UK start-up Emteq and Munich-based audEERING, both of which specialise in technology designed to track emotional responses, will collaborate on a device that will use facial tracking and vocal analysis to track "key physical indicators" of Parkinson's disease. Emteq designs sensor-laden wearable devices capable of tracking facial expression, which are interpreted by the company's AI platform to gauge emotional responses. AudEERING, meanwhile, is an audio analysis firm that uses machine intelligence and deep learning techniques to determine the emotional state of the speaker. The'smart' glasses will combine Emteq's hardware and emotion-tracking technology with an AI model developed by audEERING said to be capable of detecting vocal changes associated with Parkinson's Disease.
In this profile series, we interview AI innovators on the front-lines - those who have dedicated their life's work to improving the human condition through technology advancements. His background in electrical engineering, biomedical engineering, and computer science, helps him research different methods, including AI, to improve diagnostic imaging in the development of medical devices. In addition to OneProjects, Hennersperger also works with Trinity College in Dublin, Ireland and the Technical University of Munich in Germany. OneProjects is an innovative medical device start-up founded in 2017 in Dublin and Munich. For the past two years, OneProjects has been developing VERAFEYE, a new medical device treating cardiac arrhythmias.
--In this paper we present a generalized Deep Learning-based approach to solve ill-posed large-scale inverse problems occurring in medical imaging. Recently, Deep Learning methods using iterative neural networks and cascaded neural networks have been reported to achieve excellent image quality for the task of image reconstruction in different imaging modalities. However, the fact that these approaches employ the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by decoupling the regularization of the solution from ensuring consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained neural network which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative networks. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude. N inverse problems, the goal is to recover an object of interest from a set of indirect and possibly incomplete observations. M. Haltmeier is with the Department of Mathematics, University of Innsbruck, Innsbruck, Austria (email: email@example.com) T. Schaeffter is with the Physikalisch-Technische Bundesanstalt (PTB), Braunschweig and Berlin, Germany, King's College London, London, UK and the Department of Medical Engineering, Technical University of Berlin, Berlin, Germany (email: firstname.lastname@example.org) M. Dewey is with the Department of Radiology, Charit e - Univer-sit atsmedizin Berlin, Berlin, Germany and the Berlin Institute of Health, Berlin, Germany (email: email@example.com) C. Kolbitsch is with the Physikalisch-Technische Bundesanstalt (PTB), Braunschweig and Berlin, Germany and King's College London, London, UK (email: firstname.lastname@example.org)