Abstract: The present disclosure relates to a method of determining a prognostic outlook for patients having metastatic breast cancer. The method includes receiving imaging data from an image of a patient that is receiving or that is to receive cycline dependent kinase 4 and 6 (CDK 4/6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer. Radiomic heterogeneity features are extracted from imaging data associated with a metastasis within the imaging. A prognostic marker is determined from the radiomic heterogeneity features. The prognostic marker is indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.

Abstract: An oncological foundation model is trained with broad, multimodal data to make predictions concerning a variety of different types of cancers. For example, the foundation model may make use of medical images drawn from radiology and pathology, as well as immunohistochemistry data; the presence or absence of biomarkers for particular diagnoses; patient history data; patient demographic data; and other forms of medical data. When using medical images, whole medical images as well as feature sets derived from the medical images may be used. The foundation model may have both causal predictive abilities as well as generative abilities.

Abstract: In the disclosed systems and methods for characterizing a cancer condition of a tissue in a subject, a computer system inputs information into an ensemble model. The information includes, for each respective class of radiomics features in a plurality of classes of radiomics features, a corresponding value for each respective radiomic feature in a corresponding plurality of radiomics features of the respective class of radiomics features obtained from a medical imaging dataset. The ensemble model comprises a plurality of component models. The computer system obtains as output from each respective component model in the plurality of component models a corresponding component prediction for the cancer condition, thereby obtaining a plurality of component predictions for the cancer condition. The computer system combines the plurality of component predictions to obtain as output of the ensemble model a characterization of the cancer condition.

Abstract: The present disclosure relates to a method. The method may be performed by accessing data derived from one or more routine clinical medical imaging scans including a lesion in which the lesion and associated vasculature are segmented in a three-dimensional segmentation. At least two features are extracted from the three-dimensional segmentation of the associated vasculature. The at least two features include at least one feature indicative of a morphology of the associated vasculature or a portion thereof, and at least one feature indicative of a function of the associated vasculature or a portion thereof. The at least two features, and/or one or more statistics of the at least two features, are provided to a machine learning model trained to make a prediction concerning the lesion. The prediction concerning the lesion is received from the machine learning model.

Abstract: A system and method are provided for identifying a multimodal biomarker of a prognostic prediction, using a deep learning framework trained to analyze different modality data, including radiomic image data, pathology image data, and molecular image data to obtain unimodal embedding predictions from those modality data and generate multimodal embedding predictions, through application of a loss minimization and attention-based fusion processes.

Abstract: Machine learning models, such as machine learning classifiers, are trained to make medical predictions using loss functions that include at least one term derived from a confusion matrix, such as negative predictive value (NPV). The medical predictions are based on sets of features extracted from medical images. The medical images may be either radiology images, such as CT, MRI, or PET scans, or pathology images, such as whole-slide images of tissue. The loss functions may include terms that are designed to improve the overall accuracy of the machine learning model in addition to the confusion matrix term or terms. The loss function is typically constructed such that it is continuously differentiable.

Abstract: In the disclosed systems and methods for characterizing a cancer condition of a tissue in a subject, a computer system inputs information into an ensemble model. The information includes, for each respective class of radiomics features in a plurality of classes of radiomics features, a corresponding value for each respective radiomic feature in a corresponding plurality of radiomics features of the respective class of radiomics features obtained from a medical imaging dataset. The ensemble model comprises a plurality of component models. The computer system obtains as output from each respective component model in the plurality of component models a corresponding component prediction for the cancer condition, thereby obtaining a plurality of component predictions for the cancer condition. The computer system combines the plurality of component predictions to obtain as output of the ensemble model a characterization of the cancer condition.

Abstract: A machine learning system makes medical predictions based, at least in part, on pathomic features indicating collagen fiber organization extracted from pathology images that include lesions. The pathomic features are extracted from pathology images. The pathology images may be routine clinical images gathered in the course of diagnosis and treatment, such as hematoxylin and eosin (H&E)-stained whole slide images (WSIs) of tissue. The medical predictions may concern, e.g., the diagnosis, prognosis, genotype, or phenotype of a lesion, and may include disease-free survival (DFS) and overall survival (OS) of patients known or suspected of having malignant lesions. Methods for training a machine model to make, and for making, such predictions are also disclosed.

Abstract: The present disclosure relates to a method. The method includes accessing data having one or more segmented images identifying one or more lesions and/or a plurality of blood vessels associated with the lesions. Respective ones of the blood vessels correspond to one or more centerlines and one or more constituent branches associated with the one or more lesions. The one or more segmented images are derived from one or more radiological images of a patient having cancer. One or more vascular radiology features are extracted using the centerlines, the constituent branches, and the one or more lesions. The one or more vascular radiology features relate to a quantification of the plurality of blood vessels or a shape of the plurality of blood vessels. The one or more vascular radiology features are used to determine a medical prediction associated with an outcome of the patient to cyclin-dependent kinase (CDK) inhibitor therapy.

Abstract: Embodiments predict response to neoadjuvant chemotherapy (NAC) in breast cancer (BCa) from pre-treatment dynamic contrast enhanced magnetic resonance imaging (DCE-MRI).

Abstract: The present disclosure relates to a method that provides a pre-treatment image of a region of tissue to a deep learning model. The pre-treatment image includes at least one lesion. The deep learning model has been trained to generate a first prediction as to whether the region of tissue will respond to medical treatment. A set of radiomic features are extracted from the pre-treatment image and are provided to a machine learning model. The machine learning model has been trained to generate a second prediction as to whether the region of tissue will respond to the medical treatment based on the set of radiomic features. The deep learning model is controlled to generate the first prediction and the machine learning model is controlled to generate the second prediction. A classification of the region of tissue as a responder or non-responder is generated based on the first and second prediction.

Abstract: The present disclosure relates to a method. The method may be performed by accessing data derived from one or more routine clinical medical imaging scans including a lesion in which the lesion and associated vasculature are segmented in a three-dimensional segmentation. At least two features are extracted from the three-dimensional segmentation of the associated vasculature. The at least two features include at least one feature indicative of a morphology of the associated vasculature or a portion thereof, and at least one feature indicative of a function of the associated vasculature or a portion thereof. The at least two features, and/or one or more statistics of the at least two features, are provided to a machine learning model trained to make a prediction concerning the lesion. The prediction concerning the lesion is received from the machine learning model.

Abstract: Embodiments discussed herein facilitate determination of a response to treatment and/or a prognosis for a tumor based at least in part on features of tumor-associated vasculature (TAV). One example embodiment is a method, comprising: accessing a medical imaging scan of a tumor, wherein the tumor is segmented on the medical imaging scan; segmenting tumor-associated vasculature (TAV) associated with the tumor based on the medical imaging scan; extracting one or more features from the TAV; providing the one or more features extracted from the TAV to a trained machine learning model; and receiving, from the machine learning model, one of a predicted response to a treatment for the tumor or a prognosis for the tumor.

Abstract: Embodiments discussed herein facilitate determination of whether lesions are benign or malignant. One example embodiment is a method, comprising: accessing medical imaging scan(s) that are each associated with distinct angle(s) and each comprise a segmented region of interest (ROI) of that medical imaging scan comprising a lesion associated with a first region and a second region; providing the first region(s) of the medical imaging scan(s) to trained first deep learning (DL) model(s) of an ensemble and the second region(s) of the medical imaging scan(s) to trained second DL model(s) of the ensemble; and receiving, from the ensemble of DL models, an indication of whether the lesion is a benign architectural distortion (AD) or a malignant AD.

Abstract: Embodiments discussed herein facilitate training and/or employing a combined model employing machine learning and deep learning outputs to generate prognoses for treatment of tumors. One example embodiment can extract radiomic features from a tumor and a peri-tumoral region; provide the intra-tumoral and peri-tumoral features to two separate machine learning models; provide the segmented tumor and peri-tumoral region to two separate deep learning models; receive predicted prognoses from each of the machine learning models and each of the deep learning models; provide the predicted prognoses to a combined machine learning model; and receive a combined predicted prognosis for the tumor from the combined machine learning model.

Abstract: The present disclosure relates to a method of determining a prognostic outlook for patients having metastatic breast cancer. The method includes receiving imaging data from an image of a patient that is receiving or that is to receive cycline dependent kinase 4 and 6 (CDK 4/6) inhibitor therapy for hormone receptor-positive (HR+) metastatic breast cancer. Radiomic heterogeneity features are extracted from imaging data associated with a metastasis within the imaging. A prognostic marker is determined from the radiomic heterogeneity features. The prognostic marker is indicative of a response of the patient to CDK 4/6 inhibitor therapy for HR+ metastatic breast cancer.

Abstract: A system and method are provided for identifying a multimodal biomarker of a prognostic prediction, using a deep learning framework trained to analyze different modality data, including radiomic image data, pathology image data, and molecular image data to obtain unimodal embedding predictions from those modality data and generate multimodal embedding predictions, through application of a loss minimization and attention-based fusion processes.

Abstract: Embodiments discussed herein facilitate determination of a response to treatment and/or a prognosis for a tumor based at least in part on features of tumor-associated vasculature (TAV). One example embodiment is a method, comprising: accessing a medical imaging scan of a tumor, wherein the tumor is segmented on the medical imaging scan; segmenting tumor-associated vasculature (TAV) associated with the tumor based on the medical imaging scan; extracting one or more features from the TAV; providing the one or more features extracted from the TAV to a trained machine learning model; and receiving, from the machine learning model, one of a predicted response to a treatment for the tumor or a prognosis for the tumor.

Abstract: Embodiments discussed herein facilitate determination of whether lesions are benign or malignant. One example embodiment is a method, comprising: accessing medical imaging scan(s) that are each associated with distinct angle(s) and each comprise a segmented region of interest (ROI) of that medical imaging scan comprising a lesion associated with a first region and a second region; providing the first region(s) of the medical imaging scan(s) to trained first deep learning (DL) model(s) of an ensemble and the second region(s) of the medical imaging scan(s) to trained second DL model(s) of the ensemble; and receiving, from the ensemble of DL models, an indication of whether the lesion is a benign architectural distortion (AD) or a malignant AD.

Abstract: Embodiments discussed herein facilitate training and/or employing a combined model employing machine learning and deep learning outputs to generate prognoses for treatment of tumors. One example embodiment can extract radiomic features from a tumor and a peri-tumoral region; provide the intra-tumoral and peri-tumoral features to two separate machine learning models; provide the segmented tumor and peri-tumoral region to two separate deep learning models; receive predicted prognoses from each of the machine learning models and each of the deep learning models; provide the predicted prognoses to a combined machine learning model; and receive a combined predicted prognosis for the tumor from the combined machine learning model.