Data-Driven Personalized Breast CAD and Health-Tracking System
Systems and methods for risk-based breast cancer screening. The breast cancer screening techniques can identify and monitor women who may otherwise later be diagnosed with symptomatic and/or later-stage breast cancer. A personalized breast CAD and health-tracking system is provided that can differentiate pathological changes from normal changes in breast tomosynthesis images. A breast progression predictor can be a generative model that receives input breast images including past images captured at a past timepoint and current images captured at a current timepoint. The model uses the past images to generate predicted images for the current timepoint. Differences between the predicted images and the current images can be used to determine a likelihood of pathological change in the current images. When a pathological change is detected. The system can incorporate a broad spectrum of patient non-image information to further enhance and personalize the prediction of breast progression.
1 . A method for differentiating pathological change from normal aging in breast images, comprising:
receiving input breast images at a breast progression predictor, wherein the input breast images include first images captured at a first timepoint and second images captured at a second timepoint;
encoding the first images to a first latent vector;
generating a predicted latent vector at an age diffusion module, based on a healthy breast latent space, the first latent vector, and a time interval between the first timepoint and the second timepoint;
decoding the predicted latent vector to generate predicted images at the second timepoint;
identifying a difference between the second images and the predicted images; and
determining, based on the difference, a likelihood of pathology in the second images.
2 . The method of claim 1 , wherein generating the predicted latent vector at the age diffusion module comprises determining a number of diffusion cycles based on the time interval and performing the number of diffusion cycles on the first latent vector.
3 . The method of claim 1 , further comprising encoding the second images to a second latent vector.
4 . The method of claim 3 , further comprising determining a distance between the second latent vector and the predicted latent vector.
5 . The method of claim 4 , wherein determining the likelihood of pathology includes determining the likelihood based on the distance, wherein a greater distance value indicates a greater risk value.
6 . The method of claim 1 , wherein the likelihood of pathology in the second images includes a risk of cancer.
7 . The method of claim 1 , further comprising displaying the predicted images and the second images in a user interface.
8 . The method of claim 7 , further comprising identifying an area of pathological change in the second images and highlighting the area in the second images in the user interface.
9 . The method of claim 1 , further comprising receiving multimodality patient data at the breast progression predictor, and embedding the multimodality patient data in a third latent vector.
10 . The method of claim 9 , wherein generating the predicted latent vector further comprises generating the predicted latent vector based on the third latent vector.
11 . A system for differentiating pathological change from normal aging in breast images, comprising:
a breast progression predictor configured to receive input breast images, including first images captured at a first timepoint and second images captured at a second timepoint, the breast progression predictor including:
an encoder configured to encode the first images to a first latent vector,
a healthy breast latent manifold representing normal breast image latent space at various ages,
an age diffusion module configured to generate a predicted latent vector based on the healthy breast latent manifold, the first latent vector, and a time interval between the first timepoint and the second timepoint, and
a decoder configured to decode the predicted latent vector to generate predicted images at the second timepoint;
wherein the breast progression predictor is further configured to:
identify a difference between the second images and the predicted images, and
determine, based on the difference, a likelihood of pathology in the second images.
12 . The system of claim 11 , wherein the age diffusion module is further configured to:
determine a number of diffusion cycles based on the time interval, and
perform the number of diffusion cycles on the first latent vector to generate the predicted latent vector.
13 . The system of claim 11 , wherein the encoder is further configured to encode the second images to a second latent vector.
14 . The system of claim 13 , wherein the breast progression predictor is further configured to:
determine a distance between the second latent vector and the predicted latent vector, and
determine the likelihood of pathology based on the distance, wherein a greater distance value indicates a greater risk value.
15 . The system of claim 14 , wherein the breast progression predictor is further configured to determine a predicted speed of progression of the pathology.
16 . The system of claim 11 , wherein the breast progression predictor is further configured to identify an area of pathological change in the second images, and further comprising a user interface configured to display the predicted images and the second images, and to highlight the area of pathological change in the second images.
17 . The system of claim 11 , wherein the encoder is a first encoder and further comprising a second encoder, wherein the breast progression predictor is further configured to receive multimodality patient data, and the second encoder is configured to encode the multimodality patient data in a third latent vector.
18 . The system of claim 17 , wherein the breast progression predictor is further configured to generate the predicted latent vector based on the third latent vector.
19 . The system of claim 11 , wherein the breast progression predictor is further configured to receive multimodality patient data, and wherein the encoder is further configured to embed the multimodality patient data in a third latent vector.
20 . An apparatus, comprising:
a computer processor for executing computer program instructions; and
a non-transitory computer-readable memory storing computer program instructions executable by the computer processor to perform operations comprising:
receiving input breast images at a breast progression predictor, where the input breast images include first images captured at a first timepoint and second images captured at a second timepoint;
encoding the first images to a first latent vector;
generating a predicted latent vector at an age diffusion module, based on a healthy breast latent space, the first latent vector, and a time interval between the first timepoint and the second timepoint;
decoding the predicted latent vector to generate predicted images at the second timepoint;
identifying differences between the second images and the predicted images; and
determining, based on the differences, a likelihood of pathology in the second images.