Abstract: For decision support in a medical therapy, machine learning provides a machine-learned generator for generating a prediction of outcome for therapy personalized to a patient. The outcome prediction may be used to determine dose. To assist in decision support, a regression analysis of the cohort used for machine training relates the outcome from the machine-learned generator to the dose and an actual control time (e.g., time-to-event). The dose that minimizes side effects while minimizing risk of failure to a time for any given patient is determined from the outcome for that patient and a calibration from the regression analysis.

Abstract: For decision support in a medical therapy, machine learning provides a machine-learned generator for generating a prediction of outcome for therapy personalized to a patient. The outcome prediction may be used to determine dose. To assist in decision support, a regression analysis of the cohort used for machine training relates the outcome from the machine-learned generator to the dose and an actual control time (e.g., time-to-event). The dose that minimizes side effects while minimizing risk of failure to a time for any given patient is determined from the outcome for that patient and a calibration from the regression analysis.

Abstract: Methods and systems for determining fractional regional ventilation are disclosed. A method includes obtaining first and second lung image data indicative of a first phase and a second phase of a respiratory cycle, respectively, determining an apparent mass ratio k based on the first lung image data and the second lung image data, determining first and second spatially matched lung image data, each including N voxels, based on the first lung image data and the second lung image data, and determining at least one fractional regional ventilation value (FRV value), in accordance with a first equation FRV(n)=(k·?2_n??1_n)/?1_n. The value of n is a voxel index, ?1_n is indicative of a density of a voxel n of the first spatially matched lung image data, and ?2_n is indicative of a density of a voxel n of the second spatially matched lung image data.

Abstract: An incubator for storing micro-plates or micro-tubes comprises a handling robot positioned between shelves or drawers containing micro-titer plates or other containers useful for biological based reactions. The advantages of this configuration are the ultimate compactness of the system and increased speed or reliability achieved with more than one robot being able to access the same plate or tube. Alternative embodiments standardize the spacing and configuration of a robot track and a shelf track such that a shelf and a robot are interchangeable in a track.

Abstract: An improved electroless process for metal-plating a substrate in a plating bath containing metal-plating ions, one or more reducing agents, one or more completing agents, one or more stabilizers and one or more pH adjusters. The improvement comprises adding to the bath an aging composition comprising reaction by-products generated and accumulated in the bath in the course of a plating cycle. The aging composition is present in the bath in a concentration corresponding to the concentration of by-products present in the bath at a desired bath age. The process also involves the continuous or intermittent discharging of a predetermined volume of the bath and the continuous or intermittent replenishment of the bath with one or more replenishing solutions comprising a source of the metal-plating ions, the reducing agents, the complexing agents, the stabilizers and the pH adjusters in a manner so as to maintain the concentration of consumable and non-consumable ingredients in the bath at a steady state.