# US 10,478,071 B2 · Medical imaging

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

- Number: US 10,478,071 B2
- Document ID: US10478071B2
- Status: Granted
- Kind: B2
- Application number: 15/102,398
- Filed: 2014-12-12
- Published: 2016-10-27
- Granted: 2019-11-19
- Earliest claimed: 2013-12-13
- Assignees: Revenio Research Oy
- Applicants: Revenio Research Oy
- Inventors: Noora Neittaanmäki-Perttu; Mari Grönroos; Pekka Neittaanmäki; Ilkka Pölönen; Hannu-Heikki Puupponen
- Web page: https://patentgrep.com/patent/US10478071B2

## CPC

- A61B 5/0075: {by spectroscopy, i.e. measuring spectra, e.g. Raman spectroscopy, infrared absorption spectroscopy (A61B5/0071 takes precedence)}
- A61B 5/0077: {Devices for viewing the surface of the body, e.g. camera, magnifying lens}
- A61B 5/444: {Evaluating skin marks, e.g. mole, nevi, tumour, scar}
- G01J 3/28: Investigating the spectrum (using colour filters G01J3/51)
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 5/70: Denoising; Smoothing
- G06T 7/00: Image analysis
- G06T 7/0012: {Biomedical image inspection}
- G16H 30/40: for processing medical images, e.g. editing
- A61B 2576/00: Medical imaging apparatus involving image processing or analysis (A61B1/00009, A61B6/52 and A61B8/52 take precedence)
- G01J 2003/2826: {Multispectral imaging, e.g. filter imaging}
- G06T 2207/10024: Color image
- G06T 2207/30088: Skin; Dermal
- G06T 2207/30096: Tumor; Lesion
- G06T 2210/22: Cropping
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G01J: MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY (light sources F21, H01J, H01K, H05B; investigating properties of materials by optical means G01N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A medical imaging method includes imaging a target with a hyperspectral imaging system in order to obtain imaging data. There is provided a method in medical imaging. In the method, a target is imaged with a hyperspectral imaging system in order to obtain imaging data. The obtained imaging data is pre-processed by spatial and spectral averaging. A number of endmembers to be determined from the pre-processed imaging data is selected. The endmembers are extracted from the pre-processed imaging data based on vertex component analysis on the pre-processed imaging data and the selected number of endmembers, said endmembers defining an extremity of projections of the pre-processed imaging data in a subspace spanned by the endmembers. At least one abundance map is generated of the selected number of endmembers in the pre-processed imaging data using a filter vector algorithm on the extracted endmembers and the imaging data.

## Claims

### Claim 1

A medical imaging method, comprising:
imaging a target with a hyperspectral imaging system in order to obtain imaging data;
pre-processing the obtained imaging data by spatial and spectral averaging;
selecting a number of endmembers to be determined from the pre-processed imaging data;
extracting the endmembers from the pre-processed imaging data based on vertex component analysis on the pre-processed imaging data and the selected number of endmembers, said endmembers defining an extremity of projections of the pre-processed imaging data in a subspace spanned by the endmembers; and
generating at least one abundance map of the selected number of endmembers in the pre-processed imaging data using a filter vector algorithm on the extracted endmembers and the imaging data.

### Claim 2 (depends on 1)

A medical imaging method according to claim 1, wherein the pre-processed imaging data is unmixed with respect to the selected number of endmembers.

### Claim 3 (depends on 1)

A medical imaging method according to claim 1, wherein the generated abundance maps are displayed.

### Claim 4 (depends on 1)

A medical imaging method according to claim 1, wherein the pre-processing comprises at least one of cropping the imaging data and blurring the imaging data.

### Claim 5 (depends on 1)

A medical imaging method according to claim 1, wherein the imaging data comprises a hyperspectral datacube, and wherein a pixel of the datacube comprises an intensity of light at a specific location on an imaged target for a specific wavelength of the spectrum.

### Claim 6 (depends on 1)

A medical imaging method according to claim 1, wherein the endmembers correspond to at least a healthy tissue and malignant tissue.

### Claim 7 (depends on 1)

A medical imaging method according to claim 1, wherein an abundance map defines borders of a specific tissue in the target.

### Claim 8 (depends on 1)

A medical imaging method according to claim 1, wherein the method further comprises determining borders of dermatological lesions.

### Claim 9 (depends on 8)

A medical imaging method according to claim 8, wherein the dermatological lesions comprise at least one of Lentigo Maligna (LM) or Lentigo Maligna Melanoma (LMM).

### Claim 10

A medical imaging apparatus comprising:
at least one processor and at least one memory including a computer program code, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to:
obtain imaging data of a target imaged by a hyperspectral imaging system;
pre-process the obtained imaging data by spatial and spectral averaging;
select a number of endmembers to be determined from the pre-processed imaging data;
extract the endmembers from the pre-processed imaging data based on vertex component analysis on the pre-processed imaging data and the selected number of endmembers, said endmembers defining an extremity of projections of the pre-processed imaging data in a subspace spanned by the endmembers; and
generate at least one abundance map of the selected number of endmembers in the pre-processed imaging data using a filter vector algorithm on the extracted endmembers and the imaging data.

### Claim 11 (depends on 10)

The medical imaging apparatus according to claim 10, wherein the at least one processor and at least one memory including the computer program code further cause the apparatus to display the generated abundance maps.

### Claim 12 (depends on 10)

The medical imaging apparatus according to claim 10, further comprising a handheld hyperspectral camera for obtaining hyperspectral imaging data, said hyperspectral camera comprising a handle, a camera lens for receiving light reflected from the target, wherein a light source is arranged around the camera lens for illuminating the target, when the camera lens is towards the target, and a cone arranged around the light source and to extend towards the target.

### Claim 13 (depends on 12)

The medical imaging apparatus according to claim 12, wherein a diffuse sheet is positioned between the light source and the target.

### Claim 14 (depends on 13)

The medical imaging apparatus according to claim 13, wherein the diffuse sheet is fitted to the size and shape of the cone and sealed to a position inside the cone.

### Claim 15 (depends on 12)

The medical imaging apparatus according to claim 12, wherein the light source is remote from the handheld camera unit and connected by a light fibre to a fiber-optic ring-light arranged around the camera lens.

### Claim 16 (depends on 12)

The medical imaging apparatus according to claim 12, wherein the hyperspectral camera comprises an interface to a remote data processing unit, whereby the imaging data is sent to the data processing unit for generating at least one abundance map.

### Claim 17 (depends on 10)

The medical imaging apparatus according to claim 10, wherein the preprocessing comprises at least one of cropping the imaging data and blurring the imaging data.

### Claim 18 (depends on 1)

A non-transitory computer readable storage medium having stored thereon a computer program product executable by a computer processor and comprising program instructions which, when executed by the computer processor causes the computer processor to, execute the method according to claim 1.

### Claim 19 (depends on 10)

The medical imaging apparatus according to claim 10, wherein the at least one processor and at least one memory including the computer program code further cause the apparatus to determine border of dermatological lesions.