Abstract: To plan tumor treating fields (TTFields) therapy, a model of a patient's head is often used to determine where to position the transducer arrays during treatment, and the accuracy of this model depends in large part on an accurate segmentation of MRI images. The quality of a segmentation can be improved by presenting the segmentation to a previously-trained machine learning system. The machine learning system generates a quality score for the segmentation. Revisions to the segmentation are accepted, and the machine learning system scores the revised segmentation. The quality scores are used to determine which segmentation provides better results, optionally by running simulations for models that correspond to each segmentation for a plurality of different transducer array layouts.

Abstract: Characteristics of alternating electric fields that will be applied to a target region in a subject’s body can be selected by applying different sets of pulses between electrode elements positioned on opposite sides of the target region. Thermal responses to the different sets of pulses are determined. Based on these thermal responses, the system selects a set of characteristics for output pulses of alternating current that will (a) maximize peak current amplitude and (b) keep temperatures at the electrode elements below a threshold value.

Abstract: To plan tumor treating fields (TTFields) therapy, a model of a patient's head is often used to determine where to position the transducer arrays during treatment, and the accuracy of this model depends in large part on an accurate segmentation of MRI images. The quality of a segmentation can be improved by presenting the segmentation to a previously-trained machine learning system. The machine learning system generates a quality score for the segmentation. Revisions to the segmentation are accepted, and the machine learning system scores the revised segmentation. The quality scores are used to determine which segmentation provides better results, optionally by running simulations for models that correspond to each segmentation for a plurality of different transducer array layouts.

Abstract: Treatment resistance to Tumor Treating Fields (TTFields) has been observed in some subjects after those subjects were treated with TTFields for extended periods of time. Treatment resistance can be ameliorated by varying the treatment parameters of the TTFields over time. This can be accomplished by applying TTFields to cancer cells during a course of treatment, and varying a set of parameters of the TTFields during the course of treatment. Examples of parameters that can be varied during the course of treatment include the time of day at which the TTFields are applied, the frequency of the TTFields, the waveform used to generate the TTFields, the envelope shape of the waveform used to generate the TTFields, and the direction-switching rate of the TTFields.

Abstract: To plan tumor treating fields (TTFields) therapy, a model of a patient's head is often used to determine where to position the transducer arrays during treatment, and the accuracy of this model depends in large part on an accurate segmentation of MRI images. The quality of a segmentation can be improved by presenting the segmentation to a previously-trained machine learning system. The machine learning system generates a quality score for the segmentation. Revisions to the segmentation are accepted, and the machine learning system scores the revised segmentation. The quality scores are used to determine which segmentation provides better results, optionally by running simulations for models that correspond to each segmentation for a plurality of different transducer array layouts.

Abstract: To plan tumor treating fields (TTFields) therapy, a model of a patient's head is often used to determine where to position the transducer arrays during treatment, and the accuracy of this model depends in large part on an accurate segmentation of MRI images. The quality of a segmentation can be improved by presenting the segmentation to a previously-trained machine learning system. The machine learning system generates a quality score for the segmentation. Revisions to the segmentation are accepted, and the machine learning system scores the revised segmentation. The quality scores are used to determine which segmentation provides better results, optionally by running simulations for models that correspond to each segmentation for a plurality of different transducer array layouts.