# US 2021/0174497 A1 · Saliency mapping by feature reduction and perturbation modeling in medical imaging

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0174497 A1
- Document ID: US20210174497A1
- Status: Published application
- Kind: A1
- Application number: 16/707,209
- Filed: 2019-12-09
- Published: 2021-06-10
- Earliest claimed: 2019-12-09
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: Youngjin Yoo; Pascal Ceccaldi; Eli Gibson; Mariappan S. Nadar
- Web page: https://patentgrep.com/patent/US20210174497A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/24: Classification techniques
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06V 10/462: {Salient features, e.g. scale invariant feature transforms [SIFT]}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/10104: Positron emission tomography [PET]
- G06T 2207/10108: Single photon emission computed tomography [SPECT]
- G06T 2207/10116: X-ray image
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20164: Salient point detection; Corner detection
- G06T 2211/421: Filtered back projection [FBP]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

For saliency mapping, a machine-learned classifier is used to classify input data. A perturbation encoder is trained and/or applied for saliency mapping of the machine-learned classifier. The training and/or application (testing) of the perturbation encoder uses less than all feature maps of the machine-learned classifier, such as selecting different feature maps of different hidden layers in a multiscale approach. The subset used is selected based on gradients from back-projection. The training of the perturbation encoder may be unsupervised, such as using an entropy score, or semi-supervised, such as using the entropy score and a difference of a perturbation mask from a ground truth segmentation.

## Claims

### Claim 1

A method for saliency mapping in a medical imaging system, the method comprising:
generating, by the medical imaging system, an image of a patient;
classifying the image with a machine-learned classifier, the classifying with the machine-learned classifier determining values for a plurality of features of the machine-learned classifier in outputting a class membership of the image;
selecting only a subset of the features;
forming a saliency map of the image from input of the values for only the subset of the features to a machine-learned model; and
displaying the class membership and the saliency map.

### Claim 2 (depends on 1)

The method of claim 1 wherein selecting comprises performing back-propagation from the classifying by the machine-learned classifier and selecting the subset from results of the back-propagation.

### Claim 3 (depends on 2)

The method of claim 2 wherein selecting comprises selecting the features having a largest gradient from the back-propagation.

### Claim 4 (depends on 3)

The method of claim 3 wherein selecting comprises selecting with the largest gradient comprising a largest average gradient.

### Claim 5 (depends on 1)

The method of claim 1 wherein selecting comprises separately selecting for different hidden layers of the machine-learned classifier.

### Claim 6 (depends on 1)

The method of claim 1 wherein the machine-learned classifier comprises a convolutional neural network, and wherein selecting the subset comprises selecting convolutions of the convolutional neural network.

### Claim 7 (depends on 1)

The method of claim 1 wherein forming comprises outputting from the machine-learned model comprises a fully convolutional network.

### Claim 8 (depends on 1)

The method of claim 1 wherein forming comprises forming by the machine-learned model comprises a machine-trained perturbation encoder.

### Claim 9 (depends on 1)

The method of claim 1 wherein forming comprises forming by the machine-learned model, the machine-learned model having been trained in a semi-supervised manner with a score function based on a difference between a ground truth segmentation and an estimated perturbation.

### Claim 10 (depends on 1)

The method of claim 1 wherein selecting comprises selecting the subset as class sensitive features.

### Claim 11

A method for machine training saliency map prediction of a machine-learned classifier, the method comprising:
classifying an input image by the machine-learned classifier;
back-propagating from a class of the classifying, the back-propagating providing gradients with respect to feature maps of the machine-learned classifier;
selecting less than all of the feature maps based on sensitivities of the feature maps to the class;
generating a perturbation mask by input of the selected features maps to a perturbation encoder;
inputting a perturbed input formed by combining the perturbation mask with the input image to the machine-learned classifier, the inputting resulting in a distorted class prediction;
computing a score from the distorted class prediction; and
altering the perturbation encoder to minimize the score.

### Claim 12 (depends on 11)

The method of claim 11 wherein selecting comprises selecting separately for each of a plurality of hidden layers of the machine-learned classifier.

### Claim 13 (depends on 11)

The method of claim 11 wherein the combining of the inputting comprises combining as a Hadamard product.

### Claim 14 (depends on 11)

The method of claim 11 wherein selecting comprises selecting from averages of the gradients for the different feature maps.

### Claim 15 (depends on 11)

The method of claim 11 further comprising storing the perturbation encoder.

### Claim 16 (depends on 11)

The method of claim 11 wherein classifying comprises classifying by the machine-learned classifier comprises a convolutional neural network, the feature maps corresponding to convolution kernels, and wherein generating comprises generating by the perturbation encoder comprising a fully connected neural network.

### Claim 17 (depends on 11)

The method of claim 11 wherein computing the score comprises computing from the distorted class prediction and from a difference of the perturbation mask and a ground truth segmentation.

### Claim 18

A system for saliency map prediction, the system comprising:
a medical imaging scanner configured to generate data representing a patient;
an image processor configured to classify the data by application of a machine-learned model and to generate a saliency map for the classification by application of input based on gradients from back-propagation of the classification to a perturbation encoder, the perturbation encoder having been machine trained in a semi-supervised manner based on entropy and a difference of saliency from ground truth segmentations; and
a display configured to display the classification and the saliency map for the patient.

### Claim 19 (depends on 18)

The system of claim 18 wherein the image processor is configured to select a sub-set of feature maps using the gradients, and wherein the input is the selected feature maps.

### Claim 20 (depends on 18)

The system of claim 18 wherein the perturbation encoder was trained with a score function including the entropy and the difference.
