Abstract: An air conditioned enclosure can include an electronics enclosure with an internal electronics area and an air-conditioner opening into the internal electronics area and an air conditioner. The air conditioner can include an ambient-exchange housing that defines an exchange cavity including a first heat exchanger, a cooling enclosure including a mating surface and first walls that define a cooling cavity having a second heat exchanger, and the mating surface mounted to the electronics enclosure to provide a sealed perimeter around the air-condition opening with cooling cavity aligned for air exchange with the internal electronics area. The cooling enclosure can define a fluid connection between the ambient air exchange cavity and the cooling cavity including a fluid trap extending from the second heat exchanger along a trap height to capture and retain condensate from the second heat exchanger as a barrier to ingress from the exchange cavity into the cooling cavity.

Abstract: A shroud assembly can include a support frame with a locking slot and a hinge slot, and a shroud with a first pin and a second pin. The locking slot can receive the first pin to secure the shroud in a closed configuration. The hinge slot can receive the second pin to support the shroud in the closed configuration, in an open configuration, and during hinging of the shroud between the closed and open configurations. A tab can engage a notch to support the shroud at a predetermined angle relative to the support frame when the shroud is in the open configuration.

Abstract: An air conditioner for an enclosure that can include a housing that partly defines an ambient air exchange cavity and a tub that further defines the ambient air exchange cavity and partly defines a cooling cavity. The tub can support a first heat exchanger within the ambient air exchange cavity, and a second heat exchanger and a fan within the cooling cavity. The second heat exchanger can be included in a coolant flow loop with the first heat exchanger and the fan can move air across the second heat exchanger and into the inlet of the enclosure. The second heat exchanger can be located above the fan. A fluid trap can be provided below the second heat exchanger and adjacent the fan to capture condensate from the second heat exchanger and can direct the condensate into the ambient air exchange cavity for disposal.

Abstract: A method to process a laboratory carrier in a laboratory system based on a feature of a test liquid in the laboratory carrier is presented. The laboratory system comprises the laboratory carrier comprising the test liquid, a terahertz wave source, a terahertz detector, a laboratory carrier processing device, and a control unit. Using terahertz technology and data analysis, the feature of the test liquid in the laboratory carrier can be determined. In addition, the control unit controls the laboratory carrier processing device based on the determined feature of the test liquid.

Abstract: A method is for training an artificial neural network, for classifying sensor data, as a function of a first loss function and a second loss function. The first loss function is calculated as a function of an output of the artificial neural network. The second loss function is configured such that the output of the artificial neural network is essentially normalized.

Abstract: A method for operating an artificial neural network (ANN) on a hardware platform. The ANN is designed to ascertain confidences with which input data are to be assigned to N discrete classes. The hardware platform includes a dedicated unit which forms from a list of M>N confidences expanded confidences by encoding into each confidence an identification number of its place in the list, and numerically sorts the expanded confidences. The unit is fed confidences 1, . . . , M?N, which have the minimal representable value, and confidences M?N+1, . . . , M, which correspond to the N discrete classes, and/or it is ensured that those confidences fed to the unit that correspond to one of the N discrete classes have a value higher than the minimal representable value. A ranking of the classes ordered according to confidences, to which the input data are to be assigned, is ascertained from the first N of the numerically sorted expanded confidences.

Abstract: A cover is provided for an air conditioner of an enclosure. The cover can include a top wall and first and second side walls that at least partly define an interior compartment of the cover. The cover can further include a tab extending from the top wall into the interior compartment, a first side clip extending obliquely from the first side wall into the interior compartment, and a second side clip extending obliquely from the second side wall to the interior compartment. The tab and side clips can be configured to engage the air conditioner to retain the cover on the air conditioner.

Abstract: An encoder, connectable to a data-memory, for storing numerical values in the data-memory, which lie in a value range between a predefined-minimum-value and a predefined-maximum-value, the encoder including an assignment instruction, according to which the value range is subdivided into multiple discrete intervals, and the encoder being configured to classify a numerical value to be stored in exactly one interval and to output an identifier of this interval, the intervals varying in width on the scale of the numerical values. A decoder for numerical values, which are stored in a data-memory using an encoder, to assign according to one assignment instruction an identifier of a discrete interval retrieved from the data-memory a fixed numerical value belonging to this interval and to output it. Also described are an AI module including an ANN, an encoder and a decoder, and a method for manufacturing the AI module, and an associated computer program.

Abstract: The present disclosure relates to operating an MR system in which MR signals of an object under examination are acquired in an examining region using a multi echo imaging sequence, in which an RF excitation pulse and a plurality of RF refocusing pulses are applied. The techniques include determining a first accumulated phase of a magnetization in the object under examination. Then, a second accumulated phase of the magnetization in the object under examination is determined due to concomitant magnetic fields occurring between a second pair of consecutive RF pulses. Finally, it is determined whether a deviation from the predefined relationship is larger than a threshold and, if this is the case, a measure is applied in view of the fact that the deviation is larger than the threshold.

Abstract: An air conditioner for an enclosure that can include a housing that partly defines an ambient air exchange cavity and a tub that further defines the ambient air exchange cavity and partly defines a cooling cavity. The tub can support a first heat exchanger within the ambient air exchange cavity, and a second heat exchanger and a fan within the cooling cavity. The second heat exchanger can be included in a coolant flow loop with the first heat exchanger and the fan can move air across the second heat exchanger and into the inlet of the enclosure. The second heat exchanger can be located above the fan. A fluid trap can be provided below the second heat exchanger and adjacent the fan to capture condensate from the second heat exchanger and can direct the condensate into the ambient air exchange cavity for disposal.

Abstract: A shroud assembly can include a support frame with a locking slot and a hinge slot, and a shroud with a first pin and a second pin. The locking slot can receive the first pin to secure the shroud in a closed configuration. The hinge slot can receive the second pin to support the shroud in the closed configuration, in an open configuration, and during hinging of the shroud between the closed and open configurations. A tab can engage a notch to support the shroud at a predetermined angle relative to the support frame when the shroud is in the open configuration.

Abstract: A shroud assembly can include a support frame with a locking slot and a hinge slot, and a shroud with a first pin and a second pin. The locking slot can receive the first pin to secure the shroud in a closed configuration. The hinge slot can receive the second pin to support the shroud in the closed configuration, in an open configuration, and during hinging of the shroud between the closed and open configurations. A tab can engage a notch to support the shroud at a predetermined angle relative to the support frame when the shroud is in the open configuration.

Abstract: Techniques are disclosed for acquiring MR signals of an object under examination in an MR system using a multi echo imaging sequence. The method comprises the steps of applying an RF excitation pulse to the object to generate a transverse magnetization, applying at least two RF refocusing pulses for refocusing the transverse magnetization to generate at least two MR spin echoes for the RF excitation pulse, applying a first magnetic field gradient in a read out direction between the RF excitation pulse and the first of the at least two RF refocusing pulses, applying a second magnetic field gradient in the read out direction after each of the at least two RF refocusing pulses such that the zeroth and first gradient moment is substantially zero for the second magnetic field gradient, and acquiring the at least two MR spin echoes during the at least two second magnetic field gradients.

Abstract: In a method and magnetic resonance (MR) apparatus for acquiring MR data from a volume of an object in which first and second excitable spin types are present that differ in their Larmor frequencies by a chemical shift, an MR sequence with at least one radio-frequency pulse sequence selectively excites the first spin type or selectively suppresses MR signals of the second spin type. A B0 map describing the basic field distribution in a region of interest of the volume is established. First and second items of distribution information, which respectively describe the spectral distribution of Larmor frequencies of the first and second spin types, are derived from the B0 map. A pulse sequence parameter that describes the excitation spectrum of the radio-frequency pulse sequence is optimized based on the items of distribution information, with regard to a quality criterion that optimizes selective excitation and/or suppression.

Abstract: A method to process a laboratory carrier in a laboratory system based on a feature of a test liquid in the laboratory carrier is presented. The laboratory system comprises the laboratory carrier comprising the test liquid, a terahertz wave source, a terahertz detector, a laboratory carrier processing device, and a control unit. Using terahertz technology and data analysis, the feature of the test liquid in the laboratory carrier can be determined. In addition, the control unit controls the laboratory carrier processing device based on the determined feature of the test liquid.

Abstract: In a method for operating a magnetic resonance (MR) facility during recording of MR data by using a MR sequence including a saturation module for a spin type to be saturated, in which a high-frequency saturation pulse is emitted between first and second spoiler gradient pulses, and multiple further gradient pulses apart from the spoiler gradient pulses, eddy current data is determined. The eddy current data describes eddy currents existing during emission of the saturation pulse and resulting from the further gradient pulses. Further, a pulse parameter of the first spoiler gradient pulse is selected based on the eddy current data such that the eddy currents generated by the first spoiler gradient pulse compensate for at least part of the eddy currents described by the eddy current data during emission of the saturation pulse. The facility is controlled to emit the first spoiler gradient pulse with the selected pulse parameter.

Abstract: A method for operating an artificial neural network (ANN) on a hardware platform. The ANN is designed to ascertain confidences with which input data are to be assigned to N discrete classes. The hardware platform includes a dedicated unit which forms from a list of M>N confidences expanded confidences by encoding into each confidence an identification number of its place in the list, and numerically sorts the expanded confidences. The unit is fed confidences 1, . . . , M?N, which have the minimal representable value, and confidences M?N+1, . . . , M, which correspond to the N discrete classes, and/or it is ensured that those confidences fed to the unit that correspond to one of the N discrete classes have a value higher than the minimal representable value. A ranking of the classes ordered according to confidences, to which the input data are to be assigned, is ascertained from the first N of the numerically sorted expanded confidences.

Abstract: In a magnetic resonance tomography (MRT) apparatus and operating method, a field of view for imaging a target object is acquired. A relative position of this field of view in relation to a receiving space of the MRT scanner, in which the target object is received, is then automatically determined. A radio-frequency (RF) pulse to be used by the MRT scanner for imaging the target object is then automatically adjusted depending on this relative position. An excitation angle produced in the field of view by the RF pulse is changed compared to the use of the corresponding unadjusted RF pulse.

Abstract: In a method for providing setting parameter sets for at least one measuring protocol described by protocol parameters for acquiring magnetic resonance data with a magnetic resonance facility, setting parameter set is determined for each of at least two temperature status categories of the magnetic resonance facility using a temperature model describing a development of a temperature status of at least one component of the magnetic resonance facility. The method also includes preventing overheating of the at least one component due to the measurement with the measuring protocol being repeated a maximum number of times for a specified number of repetitions.

Abstract: A method for operating an artificial neural network is provided, including at least one convolution layer that is configured to convert an input matrix of the convolution layer into an output matrix, based on a convolution operation and a shift operation. The method includes ascertaining at least one first normalization value and one second normalization value based on inputs of the input matrix and/or based on a training data set, ascertaining a modified filter matrix based on an original filter matrix and based on at least one of the first normalization value and the second normalization value, and ascertaining a modified shift matrix based on an original shift matrix and based on at least one of the first normalization value and the second normalization value. The method further includes converting the input matrix into the output matrix by applying the modified filter matrix and the modified shift matrix.