Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of medical labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the medical labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Preliminary heat map visualization data can be generated for transmission to a client device based on the probability matrix data. Heat map visualization data can be generated via a post-processing of the preliminary heat map visualization data to mitigate heat map artifacts.

Abstract: A multi-model medical scan analysis system is operable to generate a plurality of training sets from a plurality of medical scans. Each of a set of sub-models can be generated by performing a training step on a corresponding one of the plurality of training sets. A subset of the set of sub-models is selected for a new medical scan. A set of abnormality data is generated by applying a subset of a set of inference functions on the new medical scan, where the subset of the set of inference functions utilize the subset of the set of sub-models. Final abnormality data is generated by performing a final inference function on the set of abnormality data. The final abnormality data can be to a client device for display via a display device.

Abstract: A lesion tracking system is operable to receive a first medical scan and second medical scan associated with a patient ID. A lesion area calculation is performed on a first subset of image slices determined to include a lesion detected in the first medical to generate a first set of lesion area measurements. The lesion area calculation is performed on a second subset of image slices determined to include the lesion in the second medical scan to generate a second set of lesion area measurements. A lesion volume calculation is performed on the first set of lesion area measurements and the second set of lesion area measurements to generate a first lesion volume measurement and a second lesion volume measurement, respectively, and the first and second lesion volume measurements are utilized to calculate a lesion volume change for transmission to a client device for display via a display device.

Abstract: A contrast parameter learning system is operable to generate contrast significance data for a computer vision model, where the computer vision model was generated by performing a training step on a training set of medical scans. Significant contrast parameters are identified based on the contrast significance data. A re-contrasted training set is generated by performing an intensity transformation function that utilizes the significant contrast parameters on the training set of medical scans. A re-trained model is generated by performing the training step on the first re-contrasted training set. Re-contrasted image data of a new medical scan is generated by performing the intensity transformation function. Inference data is generated by performing an inference function that utilizes the first re-trained model on the re-contrasted image data. The inference data is transmitted via the transmitter to a client device for display via a display device.

Abstract: A longitudinal data quality assurance system is operable to receive a set of medical scans corresponding to a same first patient. A first chronologically ordered list of the set of medical scans is generated based on a corresponding first set of dates, where each of the corresponding first set of dates are extracted from a headers of the set of medical scans. Quality assurance data is generated for the first chronologically ordered list by performing at least one quality assurance function on at least one of the set of medical scans. A second chronologically ordered list that includes a first subset of the first set of medical scans is generated to rectify at least one continuity error of the first chronologically ordered list, indicated in the quality assurance data. The second chronologically ordered list is transmitted to a client device for display via a display device.

Abstract: A medical scan header standardization system is operable to determine a set of standard DICOM headers based on determining a standard set of fields and based on further determining a standard set of entries for each of the standard set of fields. A DICOM image is received via a network, and a header of the DICOM image is determined to be incorrect. A selected one of the set of standard DICOM headers to replace the header of the DICOM image is determined. The selected one of the set of standard DICOM headers is transmitted, via the network, to a medical scan database for storage in conjunction with the DICOM image.

Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of global labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the global labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Heat map visualization data can be generated for transmission to a client device based on the probability matrix data that indicates, for each of the set of abnormality classes, a color value for each pixel of the new medical scan.

Abstract: A multi-label heat map generating system is operable to receive a plurality of medical scans and a corresponding plurality of medical labels that each correspond to one of a set of abnormality classes. A computer vision model is generated by training on the medical scans and the medical labels. Probability matrix data, which includes a set of image patch probability values that each indicate a probability that a corresponding one of the set of abnormality classes is present in each of a set of image patches, is generated by performing an inference function that utilizes the computer vision model on a new medical scan. Preliminary heat map visualization data can be generated for transmission to a client device based on the probability matrix data. Heat map visualization data can be generated via a post-processing of the preliminary heat map visualization data to mitigate heat map artifacts.

Abstract: A medical scan triaging system is operable to train a computer vision model and to generate abnormality data indicating abnormality probabilities for medical scans via the computer vision model. A first subset of medical scans is determined by identifying medical scans with abnormality probabilities greater than a first probability value of a triage probability threshold. A second subset of medical scans is determined by identifying medical scans with abnormality probabilities less than the first probability value. An updated first subset of medical scans is determined by identifying medical scans with abnormality probabilities greater than a second probability value of an updated triage probability threshold. An updated second subset of the plurality of medical scans is determined by identifying medical scans with a abnormality probabilities less than the second probability value. The updated first subset of medical scans is transmitted to client devices.

Abstract: A medical scan system is operable to receive a set of labeling data corresponding to a set of medical scans from each of a set of client devices corresponding to a set of users. The set of medical scans and each set of labeling data is transmitted to an expert client device associated with an expert user, and a set of golden labeling data and a plurality of sets of correction data are received from the expert client device. A set of performance score data is generated based on the plurality of sets of correction data, and each performance score data of the set of performance score data is assigned to a corresponding one of the set of users. An updated training set that includes the set of golden labeling data is generated, and a medical scan analysis function is retrained based on the updated training set.

Abstract: A medical scan interface feature evaluator system is operable to receive a set of responses from each of a set of client devices, where each set of responses is generated based on a corresponding client device displaying each of the set of medical scans in conjunction with at least one interface feature indicated in an image-to-prompt mapping. Response score data is generated for each response of the set of responses received from each of the set of client devices by comparing each response to truth annotation data of a corresponding medical scan of the set of medical scans indicated by the image-to-prompt mapping. Interface feature score data corresponding to each user interface feature in the set of user interface features is generated based on aggregating corresponding response score data. A ranking of the set of user interface features is generated based on the interface feature score data.

Abstract: A risk assessment system is configured to receive patient history data for a patient. A set of risk assessment scores corresponding to the patient are generated for a set of risk assessment categories based on applying at least one risk assessment function to the patient history data. One of the set of risk assessment categories is identified as high risk for the patient based on a corresponding one of the set of risk assessment scores. A high risk protocol corresponding to the one of the set of risk assessment categories is identified, and performance of the high risk protocol is facilitated for the patient based on identification of the one of the set of risk assessment categories as high risk for the patient.

Abstract: A multi-model medical scan analysis system is operable to generate a generic model by performing a training step on image data of a plurality of medical scans and corresponding labeling data. A plurality of fine-tuned models are generated by performing a fine-tuning step on the generic model. Abnormality detection data is generated for a new medical scan by utilizing the generic model. A first one of the plurality of abnormality types that is detected in the new medical scan is determined based on a corresponding one of the plurality of probability values. Additional abnormality data is generated by performing a fine-tuned inference function on the image data of the new medical scan that utilizes one of the plurality of fine-tuned models that corresponds to the first one of the plurality of abnormality types. The additional abnormality data is transmitted for display.

Abstract: A model-assisted annotating system is operable to receive a first set of annotation data for a first set of medical scans from a set of client devices. A computer vision model is trained by utilizing first set of medical scans and the first set of annotation data. A second set of annotation data for a second set of medical scans is generated by utilizing the computer vision model. The second set of medical scans and the second set of annotation data is transmitted to the set of client devices, and a set of additional annotation data is received in response. An updated computer vision model is generated by utilizing the set of additional annotation data. A third set of annotation data is generated for a third set of medical scans by utilizing the updated computer vision model for transmission to the set of client devices for display.

Abstract: A report generating system is operable to generate inference data for a medical scan indicating a first subset of a plurality of anatomical features of the medical scan are normal. A set of default natural language text corresponding to the first subset of the plurality of anatomical features are identified based on report template data. Preliminary report data is generated to include the set of default natural language text corresponding to the first subset of the plurality of anatomical features based on the inference data. The preliminary report data is displayed an interactive user interface, and review data is received based on user input in response to at least one prompt displayed via the interactive user interface. Final report data that includes natural language text data for each of the plurality of report sections is generated based on the review data.

Abstract: An inference process visualization system is configured to generate inference process visualization data for a medical scan indicating an inference process flow of plurality of sub-models applied to the medical scan and further indicating a plurality of inference data for the medical scan generated by applying the plurality of sub-models in accordance with the inference process flow. The inference process visualization system is further configured to facilitate display of the inference process visualization data via an interactive interface.

Abstract: A peer-review flagging system is operable to train a computer vision model and to generate automated assessment data by performing an inference function on a first medical scan by utilizing the computer vision model. Human assessment data is generated based on a first medical report written by a medical professional in conjunction with review of the first medical scan. First consensus data is generated based on the automated assessment data, the human assessment data, and a first threshold, and the first medical scan is determined to be flagged based on the first consensus data. A second threshold is selected use in generating second consensus data for a second medical scan and a second medical report written by the medical professional in conjunction with review of the second medical scan, and is selected to be stricter than the first threshold based on determining to flag the first medical scan.

Abstract: A medical scan artifact detection system is operable to receive a medical scan of a patient. Artifact detection data is generated by executing an artifact detection function on the medical scan, where the artifact detection data indicates at least one artifact detected in the medical scan that includes a motion artifact or a nipple shadow. A notification is generated for display via a display device, where the notification indicates the at least one artifact.

Abstract: A medical report natural language model includes an artificial neural network implemented via the processor and is trained based a plurality of medical reports wherein each of the medical reports is mapped to at least one medical code of a plurality of medical codes and further based a plurality of medical condition terms from a plurality of alias mapping pairs, wherein each of the plurality of medical condition terms are unique, wherein each of the plurality of medical condition terms indicates a corresponding medical condition and wherein each of the plurality of alias mapping pairs includes a one of the plurality of medical condition terms and a corresponding single one of the plurality of medical codes that is a deterministic function of the one of the plurality of medical condition terms and wherein the plurality of alias mapping pairs includes two or more alias mapping pairs that map a corresponding two or more of the plurality of medical condition terms to a same one of the plurality of medical codes.

Abstract: A medical scan triaging system is operable to generate a global abnormality probability for each of a plurality of medical scans by utilizing a computer vision model trained on a training set of medical scans. A triage probability threshold is determined based on user input to a client device. A first subset of the plurality of medical scans, designated for human review, is determined by identifying medical scans with a corresponding global abnormality probability that compares favorably to the triage probability threshold. A second subset of the plurality of medical scans, designated as normal, is determined by identifying ones of the plurality of medical scans with a corresponding global abnormality probability that compares unfavorably to the triage probability threshold. Transmission of the first subset of the plurality of medical scans to a plurality of client devices associated with a plurality of users is facilitated.