GB2531845A

GB2531845A - Apparatus and method

Info

Publication number: GB2531845A
Application number: GB1509886.6A
Authority: GB
Inventors: Tunstall Jonathon; Hamilton Peter; Wang Yinhai; Mccleary David; Diamond James
Original assignee: PathXL Ltd
Current assignee: Philips DCP Belfast Ltd
Priority date: 2013-05-10
Filing date: 2013-05-10
Publication date: 2016-05-04
Also published as: GB201509886D0

Abstract

A computer implemented image processing method of identifying a tissue boundary of a tumour region of a tissue sample 2, the tissue sample containing non-tumour regions and at least one tumour region, to enable excision of at least a portion of a tumour region from the tissue sample by cutting along the tissue boundary, the method comprises: obtaining an image of a tissue section of the tissue sample 4 such as an histology slide 10; identifying at least one image property of the image; comparing the image property with classification data; based on the comparison, classifying a region of the image as a tumour region representing a tumour region in the tissue sample or a non-tumour region representing a non-tumour region in the tissue sample; and if the region of the image is classified as a tumour region, identifying a boundary of the region of the image; and using the boundary to identify a tissue boundary of the tumour region of the tissue sample represented by the region of the image. Preferably a macrodissection system 60 has a computer 20 which receives data from an imager 50, which using a smoothing algorithm generates a result of the image which is then sent to a controller 30. The controller controls a cutting device 40 based on the result.

Description

Apparatus and method The present invention relates to image processing, in particular to systems, methods, apparatus, computer program products and servers for processing an image of a tissue 5 section of a tissue sample.

The accurate separation of tumour tissue from non-tumour tissue is a prerequisite for laboratory molecular analysis of many types of tumour tissues.

In standard laboratory practice, tumour tissue for analysis is obtained by cutting a thin tissue section from a formalin fixed, paraffin embedded (FFPE) tissue block known to contain tumour and non-tumour tissue, and preparing the tissue section on a glass histology slide. The tissue section will usually be cut with a thickness of approximately 5 pm or any other appropriate thickness to allow the outline of tissue structures to be made out by viewing the slide under a standard laboratory microscope.

In order to determine a boundary of a tumour region of a tissue section, it has been proposed to prepare a histology slide with the tissue section, comprising staining the tissue section with a laboratory dye and covering with a glass cover slip according to standard laboratory practice, for viewing and analysis by a trained pathologist. A method of marking tumour regions of the tissue section comprises the pathologist viewing the slide using a standard laboratory microscope and, based on subjective assessment, for example based on memory or on visual comparison with a look-up chart, identifying regions of the tissue section appearing to correspond to model tumour structures, and indicating boundaries of the regions via a manual annotation with a marker pen on the glass coverslip. Following annotation, a sequential tissue section, preferably having a thickness in the range indicated above, is cut from the tissue block and prepared on a second histology slide. Using the annotated slide as a template, tissue is manually scraped, using a scalpel, from a region of the sequential tissue section contained within an area corresponding to an annotated region.

The above process is manual in nature and relies upon subjective input from the pathologist to annotate the tumour area. Internal validation studies have indicated a high degree of both intra and inter-pathologist variation in this manual annotation process. -2 -

Aspects of the disclosure provide an automated method for tumour boundary indication which will accurately depict the tumour region for either manual dissection or for dissection using an automated instrument. This invention covers both of those applications and any other dissection methods which may be envisaged from the use of this technology, whether those be manual, automated or instrument controlled processes.

Aspects and examples of the invention are set out in the claims and aim to provide an improved image processing system, apparatus, method, computer program product and server for identifying a boundary of a tumour region of a tissue sample and for making data representing the boundary available to at least one user, and a macrodissection system, method and apparatus for identifying the same and for using data representing the boundary to perform macrodissection.

In an aspect there is provided a computer implemented image processing method of identifying a tissue boundary of a tumour region of a tissue sample, the tissue sample containing non-tumour regions and at least one tumour region, to enable excision of at least a portion of a tumour region from the tissue sample by cutting along the tissue boundary, the method comprising: obtaining an image of a tissue section of the tissue sample; identifying at least one image property of the image; comparing the image property with classification data; based on the comparison, classifying a region of the image as a tumour region representing a tumour region in the tissue sample or a non-tumour region representing a non-tumour region in the tissue sample; and if the region of the image is classified as a tumour region, identifying a boundary of the region of the image; and using the boundary to identify a tissue boundary of the tumour region of the tissue sample represented by the region of the image.

In an embodiment the at least one image property comprises one or any combination of image properties from the group comprising: a statistical moment, a moment invariant feature, a features derived from a grey level co-occurrence matrix, a spectral feature or a morphological feature.

In an embodiment the at least one image property comprises at least one image property of each of a plurality of different colour components of the image concatenated together to provide a feature vector. -3 -

In an embodiment the method comprises classifying the region of the image based on a comparison between the feature vector and the classification data.

In an embodiment the classification data comprises a subset of data sets selected from a set 5 of first model image data sets indicative of tumour tissue and from a set of second model image data sets indicative of non-tumour tissue.

In an embodiment the step of identifying a boundary of the region of the image comprises: generating a two-state map of the image by representing regions classified as tumour 10 regions using a first state and by representing regions classified as non-tumour regions using a second state.

In an embodiment the method comprises applying a smoothing algorithm to the boundary to provide a smoothed template for cutting along the tissue boundary.

In an embodiment applying the smoothing algorithm comprises applying a forward frequency-domain transform and an inverse frequency-domain transform.

In an embodiment applying the smoothing algorithm comprises representing the image 20 boundary as a sequence of transition indicators indicating the direction of a transition between pixels on the image boundary, and smoothing the sequence of transition indicators.

In an embodiment the method comprises displaying the two-state map combined with a probability data map indicating the probability that regions of the sample comprise tumour.

In an embodiment the method comprises updating the classification data using a supervised learning method.

In an embodiment the method comprises determining whether the sample comprises tumour 30 tissue, and only identifying the boundary in the event that it is determined that the sample comprises tumour.

In an aspect there is provided a computer implemented image processing method of identifying a tissue boundary of a tumour region of a tissue sample, the tissue sample 35 containing non-tumour regions and at least one tumour region, to enable excision of at least -4 -a portion of a tumour region from the tissue sample by cutting along the tissue boundary, the method comprising: identifying a background region in the image and removing the background region from the image using a thresholding method; dividing the image into tiles, and for each tile of at least a subset of the tiles: providing data representing a plurality of colour components of the tile, wherein a first of the colour component corresponds to a first indicator used to stain the tissue section, a second of the colour component corresponds to a second indicator used to stain the tissue section and a third of the colour component is a greyscale colour component; identifying an image property of each of the colour components and concatenating the image properties to generate a feature vector; comparing the feature vector with binary classification data, the binary classification data a set of first model image data sets indicative of tumour tissue and a set of second model image data sets indicative of non-tumour tissue; based on the comparison, classifying the feature vector as corresponding to tumour tissue or non-tumour tissue; based on having classified the feature vector of at least one tile as representing tumour tissue, classifying a region of the image as representing a tumour region; providing a binary colour map of the image by representing regions classified as 20 tumour regions in a first colour and regions classified as classified non-tumour regions in a second colour; identifying a boundary of a first colour region in the binary colour map; smoothing the boundary by applying a smoothing algorithm to provide a smoothed template for cutting along the corresponding tissue boundary; and scaling the relative colour intensity of first colour regions according to a probability of their correspondence with a tumour region of the tissue sample respectively.

In an embodiment the methods comprise cutting along the tissue boundary, wherein the step of cutting along the tissue boundary comprises cutting along a tissue boundary in the tissue 30 section or cutting along a tissue boundary in a subsequent tissue section of the tissue sample.

In an aspect there is provided a macrodissection apparatus, comprising: a receiver for receiving data representing a boundary in the image; and a controller for guiding a cutting of 35 the tissue sample along a path based on the data representing the boundary. -5 -

In an aspect there is provided an image server, accessible to a plurality of users, configured to; receive, from any of the plurality of users, image data of a tissue section of a tissue 5 sample containing tumour and non-tumour regions; access classification data for classifying regions of the image as tumour regions or non-tumour regions; implement a method according to claim 12 on the data to identify a boundary in the image; and make data representing the boundary available to at least one of the plurality of users.

In an embodiment the classification data comprises an association between stored feature vectors and a tumour tissue class, and a non-tumour tissue class. In an embodiment the feature vectors each comprise at least one image property derived from at least one of a plurality of colour components of the image. In an embodiment the image server is configured to update the classification data based on the received data and feedback from the user.

In an aspect there is provided an apparatus for guiding in vitro dissection of a tissue sample, the apparatus comprising: a processor configured to obtain an image of a tissue section of the tissue sample, to identify at least one image property of the image, to compare the image property with classification data, and, based on the comparison, to determine whether a region of the sample comprises tumour; wherein the processor is configured so, in the event that the sample comprises tumour, the processor identifies a boundary of the tumour region of the image; and provides the image boundary to guide dissection of tumour from the sample.

In an embodiment the apparatus comprises a display for displaying the boundary as a template to guide dissection of the sample. The apparatus may be configured to perform any of the methods described herein.

Apparatus features described herein may be provided as method features, and vice versa.

It should also be appreciated that particular combinations of the various features described -6 -and defined in any aspects of the invention can be implemented and/or supplied and/or used independently.

Embodiments of the invention will now be described, by way of example only, with reference 5 to the accompanying drawings in which: Figure 1 schematically shows a macrodissection system for excising tumour tissue from a tissue sample; Figure 2 shows a flow chart illustrating a method of using the macrodissection system of 10 Figure 1; and Figure 3 shows a flow chart illustrating a computer implemented method of processing an image to guide dissection of a tissue sample suspected of comprising tumour tissue.

Figure 1 shows a macrodissection system 60, comprising a tissue sample 2, a histology slide 10 carrying a tissue section 4 taken from the tissue sample 2, an imager 50, a computer 20, a controller 30, and a cutting device 40. The imager 50 is arranged to obtain a digital image of the tissue section 4 on the histology slide 10 and to provide data representing the image to the computer 20. The computer 20 is configured to receive the data from the imager 50, to run an algorithm on the data to generate a result, and to provide the result to the controller 30. The controller 30 is configured to control a cutting operation of the cutting device 40 based on the result.

The tissue sample 2 comprises tissue block suspected of containing at least one tumour region 6, and containing non-tumour regions 8.

The tissue section 4 is a section cut from the tissue sample 2, having a thickness in the range of approximately 5 pm, or 10 to 40 pm, although the skilled practitioner will understand that another thickness could be chosen as appropriate. A sequential tissue section (not shown) is a further slice cut from the tissue sample 2 at a location exposed by taking the first tissue section 4. The thickness of the sequential tissue section need not be the same as that of the first tissue section.

The histology slide 10 is a standard glass laboratory slide or any suitable equivalent for providing a flat transparent surface for receiving and displaying the tissue section 4. -7 -

The imager 50 is configured to generate an image of the tissue section 4 on the histology slide 10 and to provide data representing the image to computer 20.

The computer 20 comprises memory 24 and a processor 22. The memory 24 is configured to receive and store data from the imager 50. The processor 22 is coupled to access image data stored in the memory 24, to implement an image processing algorithm on the data to classify a region of the image as a tumour region and identify a boundary of the region (see, for example, Figure 3), to output data representing the boundary to the controller 30 and optionally to send a copy of the data to the memory 24 for later use.

Figure 2 shows a flow chart illustrating a method of operation of the system of Figure 1.

The histology slide 10 is prepared 201 by cutting the tissue section 4 form the tissue sample 2 using a laboratory microtome. The tissue section 4 is placed in the slide 10, stained with 15 Haematoxylin and Eosin laboratory stain and covered with a glass cover slip.

An image of the tissue section 4 is obtained 202 by imaging the cover slide 10 with the imager 26. Data representing the image is provided to the memory 24 of the computer 20.

The processor 22 retrieves the image data from the memory 24 and analyses the data to classify 203 a region of the image as representing a tumour region of the tissue section. Classifying the region comprises comparing at least one property of the image data with classification data (see, for example Figure 3).

The processor 22 identifies 204 a boundary of the region to enable identification of a tumour boundary in a sequential tissue section. Data representing the identified boundary is output to the controller 30. The data may be displayed on a user interface.

Data representing the region and the boundary are stored to non-volatile memory for later 30 user reference and/or for updating the classification data using a learning method.

The controller 30 receives the data representing the boundary and guides the cutting device 40 to cut 205 in the sequential tissue section along a path based on the boundary, by using the boundary as a template. -8 -

Figure 3 shows a flow chart illustrating a computer implemented method of processing an image to guide dissection of a tissue sample suspected of comprising tumour.

The processor 22 obtains 1000 from memory 24 an image of a section through the tissue 5 sample. The section can be imaged from a microscope slide stained using Haemotoxylin and Eosin.

The processor obtains 1001 a first component of the image data corresponding to the Eosin stain.

The processor PPP then selects a threshold to apply to the first component of the image data that divides the eosin image data into two groups. The processor is configured to select a threshold that reduces, for example minimises, the variance of the data values within each group. The processor 1000 then applies the threshold value to the first component of the image data to generate a mask.

The processor then applies the mask generated from the first component to segment 1002 the image data into two groups. Image data in the first group is identified as tissue, and image data in the second group is identified as background.

The processor then partitions 1004 the first group of image data, relating to tissue, into tiles. The image data for each tile comprises image data relating to that tile at a series of different resolutions The data for the tile at each different resolution comprises a plurality of blocks each representing at least a portion of the tile at a different effective magnification. Different magnifications may be achieved by providing equivalent pixel numbers for different sized spatial regions, or a different number of pixels for equally sized spatial regions.

For each tile, at each resolution level, the processor obtains 1005 three components of the image data, a first component corresponding to the Eosin stain, a second component corresponding to the Haemotoxylin stain, and a third grey scale component. The first and second components may be obtained by applying a colour deconvolution method to the image data. The grey scale image data comprises a greyscale version of the image data in the tile.

For each colour component of the tile, the processor selects at least one property to be -9 -determined based on the colour component image data in the tile. The properties to be determined are selected based on the colour component so different properties can be determined for different colour components. The properties are selected from the list comprising texture, statistical moments, such as centroids, averages, variances, higher order moments, moment invariant, frequency domain features, features derived from the grey level co-occurrence matrix, and morphological features, such as average nuclear size and/or shape, nuclear concentration in a spatial region, and high level spatial relationships between image objects, which may be derived from Delaunay Triangulation, Voronoi diagram and/or a minimal expanding tree algorithm which treats each cell nucleus as a vertex.

The processor then determines 1006 the selected image properties for each of the three components of the tile, and concatenates the image properties together to provide a feature vector.

The processor then obtains from memory a subset of the stored classification data. The classification data comprises a first set of model image feature vectors associated with tumour tissues, and a second set of model image feature vectors associated with non-tumour tissue.

The processor selects from amongst the first plurality of feature vectors (tumour type) from the classification data, and the second plurality of feature vectors (non-tumour type) from the classification data to provide a subset (e.g. less than all of the set). This provides a subset of model feature vectors.

The processor then compares 1008 the concatenated feature vector from the tile with the selected subset of the classification data, and based on the comparison, the processor classify 1010 the tile as belonging to one of two states -tumour or non-tumour.

The processor is configured to combine 1012 the tiles to provide a two state map (e.g. binary) identifying tumour, and non-tumour regions of the tissue with the tissue/non-tissue mask generated by the segmentation 1002 to provide a spatial map of the image data which classifies regions of the image into one of three states e.g. background, tumour tissue, and non-tumour tissue.

The processor is further configured to identify 1014 a boundary between regions in the three -10 -state map The processor is configured to identify an initial boundary based on an edge detection algorithm, encode the resulting boundary, and smooth the boundary by reducing the contribution of high spatial frequency components to the boundary.

The processor then obtains a probability estimate based on comparing the feature vectors of tiles in tissue regions of the image with the selected subset of model image data to assign a probability to each tile.

The processor then displays the resulting probability estimate as a colour map, overlaid with 10 the smoothed boundary data, to provide a user with an estimate of the location of tumour and non-tumour regions in the image.

It will be appreciated by the skilled addressee in the context of the present disclosure that the disclosure provides systems, methods, apparatus, computer program products and servers for processing an image of a tissue section of a tissue sample to analyse and identify a tumour region of a tissue sample for the purpose of macrodissection of the tissue sample. As already provided, a tumour may contain patterns of cell growth which contain, but are not limited to, any of dysplasia, neoplasia, carcinoma in-situ and cancerous tissue, or any combination thereof. It will be appreciated by the skilled addressee in the context of the present disclosure that the disclosure could equally apply to other diseases which are capable of morphological identification.

In Figure 1, the computer 20 is represented as a desk-top PC. It will be appreciated that any other type of computer or server could be used.

The processor 22 of Figure 1 may be a standard computer processor, but it will be understood that the processor could be implemented in hardware, software, film ware or any combination thereof as appropriate for implementing the image processing method described herein.

The memory 24 of the computer 20 of Figure 1 may be configured to store data received from the imager 50, results generated by the processor 22, and classification data for classifying tumour and non-tumour regions. Non-volatile memory may be provided for storing the classification data. Further non-volatile memory may be provided for storing the image data so that the image data for a plurality of tissue samples may be uploaded and stored in memory until such time as the processor 22 has capability or an instruction to process it. The memory 24 may comprise a buffer or an on-chip cache. Further non-volatile memory may be provided for storing results of the image processing method for later user reference and/or for updating the classification data using a learning method.

The controller 30 is configured to receive the output from the computer 20 and to control the cutting device 40 to cut tissue from a sequential tissue section based on the processor output. The controller 30 comprises any suitable means for guiding a cutting device along a predetermined path. For example, the controller could comprise a processor coupled to a machine driven scalpel or laser. In another example, the controller 30 is configured to provide and/or display a template based on the processor output to guide cutting, for example automated or manual cutting along a path corresponding to a boundary shown on the template or to scrape tissue with a spatula from inside the boundary.

Tumour regions, such as the tumour schematically illustrated by region 6 of Figure 1, are tissue regions containing abnormal patterns of growth, which may include, but are not limited to, any of dysplasia, neoplasia, carcinoma in-situ and cancerous tissue or any combination thereof. The non-tumour regions 8 may also contain tumour tissue, but in a lower concentration than present in their tumour regions 6, as will be understood by those skilled in the art. The tissue block may be a formalin fixed, paraffin embedded tissue block, or a tissue block prepared in any other suitable way.

The cutting device 40 may be a bladed instrument for cutting in a tissue section. In other examples the device could comprise a laser for dissecting tissue or a blunt instrument, such 25 as a spatula, for scraping tissue from the slide.

The imager 50 may comprise any suitable image generating means, including, but not limited to, an analogue or digital camera and a digital slide scanning system, in which an image is reconstructed following acquisition of image tiles or raster lines.

Obtaining the image data may comprise retrieving it from non-volatile memory, or from RAM, or from an on chip-cache, ADC or buffer. The image data in memory may be derived from data stored elsewhere in the apparatus, or received over a communications link such as a network, or obtained from an imager such as a microscope.

The section of tissue can be stained using Haemotoxylin and Eosin, or with any other appropriate histological stain. The description above makes reference to separating the image data into components corresponding to the particular stains. As will be appreciated, other coloured stains may be used, and the image data may be separated into components corresponding to the stains used. The components may comprise colour channels, which may be separated using a colour deconvolution method. However, other types of colour component, separated by other kinds of methods may also be used.

Obtaining 1001 the first component corresponding to the eosin stain may comprise obtaining 10 the intensity of eosin stain using colour deconvolution method. The second component corresponding to the Haemotoxylin stain may be similarly obtained.

The segmentation by masking may be based on a single component of the image data, such as the first (eosin) component as described above, or from one of the other components, or 15 from the original image data, or from a combination of one or more of these. In some examples a predefined image mask may be used.

The threshold used to provide the mask can also be predefined rather than being based on the variance of the data values within each group. In some possibilities the threshold may be selected based on user input, for example the processor may be configured to determine the threshold (e.g. based on intra-group variances) and then to adjust the threshold based on input from a user.

Segmentation may be performed to provide a mask at each of a plurality of resolution levels, 25 or segmentation may be performed at one resolution (e.g. the native resolution of the images) and then up-sampled or down-sampled (e.g. by smoothing) to provide masks at different resolutions.

The image data for each tile may comprise image data relating to that tile at at least one resolution. Where different resolutions are used these may be provided by images collected at differing levels of magnification, for example as described in relation to Figure 3. In some possibilities, images at different resolutions for a given tile may be obtained by down-sampling, e.g. smoothing, or by image interpolation. This approach may be used in combination with differing magnification levels.

-13 -Image tiles of the same image region having different resolutions described above may comprise the same number of pixels, or a different number of pixels covering the same spatial region of the image. Different classification data may be applied to the image data relating to different resolutions.

In one possibility, for each tile, at each resolution level, the processor obtains 1005 three colour components, one corresponding to an eosin colour channel and another corresponding to a Haemotoxylin colour channel as obtained using a colour decomposition method, as well as one grey scale colour channel obtained directly from the original RGB coloured image. The processor then continues to step 1006 of the method as described above.

At or following the classification step 1010, tiles classified as representing tumour regions may be assigned a posterior probability of corresponding to a tumour region of the tissue 15 sample, based on a selected threshold level. For example, when classifying the tile as tumour or non-tumour, a threshold level of 0.5 (50%) may be applied.

The probability estimate used to generate the colour map be obtained by updating the posterior probability data.

The processor subset of the stored classification data may be selected at random, for example in a Monte-Carlo type approach. In some possibilities, selecting may comprise selecting a predefined, or user selected, subset of classification data. In one possibility the classification data comprises data (e.g. feature vectors) relating to known tissue types and/or known tumour types, and selecting the subset of classification data may comprise selecting classification data based on the tissue type of the sample from which the imaged section of tissue was derived.

The classification data may be derived from a supervised learning model in which the classification data comprises a feature vector derived from an image of a tissue sample, and an indication of whether that feature vector relates to tumour or non-tumour image data. The processor may be configured to obtain input from a user confirming whether a region of the image comprises tumour tissue and to store one or more feature vectors from that region of the image in memory with the classification data. This may enable the operation of the method to be adapted or tuned to operation in particular types of tissue.

-14 -The boundary may be encoded in the form of a sequence of transition indicators indicating the direction of a transition between two consecutive boundary pixels, e.g. a step to the right, a step diagonally right and up, a step up etc. Encoding the boundary in this way may provide as many transition indicator elements as there are boundary pixels. The position of the boundary in the image can then be encoded using the coordinates of the first pixel in the sequence. As will be appreciated by the skilled addressee in the context of the present disclosure, any other type of encoding of a line in a 2D plane may be used.

In addition to, or as an alternative to displaying the probability estimate as a colour map, overlaid with the smoothed boundary data, the processor may be configured to control a cutting tool as described above with reference to Figure 1 and Figure 2 to dissect the tumour tissue from a sample (e.g the sample from which the tissue section was derived) based on the boundary. In some examples the functionality of the computer and/or the processor may be provided by digital logic, such as field programmable gate arrays, FPGA, application specific integrated circuits, ASIC, a digital signal processor, DSP, or by software loaded into a programmable processor.

In an aspect there is provided a computer implemented image processing method of identifying a tissue boundary of a first tissue type region of a tissue sample comprising at least one region of a first tissue type, and a second tissue type, to enable excision of at least a portion of the region of the first tissue type from the tissue sample by cutting along the tissue boundary, the method comprising: obtaining an image of a tissue section of the tissue sample; identifying at least one image property of the image; comparing the image property with classification data; based on the comparison, classifying a region of the image as the first tissue type or the first tissue type; and if the region of the image is classified as a first tissue type, identifying a boundary of the first tissue type in the image; using the boundary to identify a region of the first tissue type in the tissue sample.

Other examples and variations are within the scope of the disclosure, as set out in the appended claims.

Claims

-15 -Claims 1. A computer implemented image processing method of identifying a tissue boundary of a tumour region of a tissue sample, the tissue sample containing non-tumour regions and 5 at least one tumour region, to enable excision of at least a portion of a tumour region from the tissue sample by cutting along the tissue boundary, the method comprising: obtaining an image of a tissue section of the tissue sample; identifying at least one image property of the image; comparing the image property with classification data; based on the comparison, classifying a region of the image as a tumour region representing a tumour region in the tissue sample or a non-tumour region representing a non-tumour region in the tissue sample; and if the region of the image is classified as a tumour region, identifying a boundary of the region of the image; and using the boundary to identify a tissue boundary of the tumour region of the tissue sample represented by the region of the image.
2. The method of claim 1, wherein the at least one image property comprises one or any combination of image properties from the group comprising: a statistical moment, a moment 20 invariant feature, a features derived from a grey level co-occurrence matrix, a spectral feature or a morphological feature.
3. The method of claim 1 or 2, in which the at least one image property comprises at least one image property of each of a plurality of different colour components of the image 25 concatenated together to provide a feature vector.
4. The method of claim 3, comprising classifying the region of the image based on a comparison between the feature vector and the classification data.
5. The method of any preceding claim, wherein the classification data comprises a subset of data sets selected from a set of first model image data sets indicative of tumour tissue and from a set of second model image data sets indicative of non-tumour tissue.
6. The method of any preceding claim, wherein the step of identifying a boundary of the region of the image comprises: -16 -generating a two-state map of the image by representing regions classified as tumour regions using a first state and by representing regions classified as non-tumour regions using a second state.
7. The method of any preceding claim, comprising applying a smoothing algorithm to the boundary to provide a smoothed template for cutting along the tissue boundary.
8. The method of claim 7, wherein applying the smoothing algorithm comprises applying a forward frequency-domain transform and an inverse frequency-domain transform.
9. The method of claim 7 or 8, wherein applying the smoothing algorithm comprises representing the image boundary as a sequence of transition indicators indicating the direction of a transition between pixels on the image boundary, and smoothing the sequence of transition indicators.
10. The method of any of claims 6 to 9, comprising displaying the two-state map combined with a probability data map indicating the probability that regions of the sample comprise tumour.
11. The method of any preceding claim, comprising updating the classification data using a supervised learning method.
12. The method of claim 1 further comprising determining whether the sample comprises tumour tissue, and only identifying the boundary in the event that it is determined that the 25 sample comprises tumour.
13. A computer implemented image processing method of identifying a tissue boundary of a tumour region of a tissue sample, the tissue sample containing non-tumour regions and at least one tumour region, to enable excision of at least a portion of a tumour region from 30 the tissue sample by cutting along the tissue boundary, the method comprising: identifying a background region in the image and removing the background region from the image using a thresholding method; dividing the image into tiles, and for each tile of at least a subset of the tiles: providing data representing a plurality of colour components of the tile, wherein a first 35 of the colour component corresponds to a first indicator used to stain the tissue section, a -17 -second of the colour component corresponds to a second indicator used to stain the tissue section and a third of the colour component is a greyscale colour component; identifying an image property of each of the colour components and concatenating the image properties to generate a feature vector; comparing the feature vector with binary classification data, the binary classification data a set of first model image data sets indicative of tumour tissue and a set of second model image data sets indicative of non-tumour tissue; based on the comparison, classifying the feature vector as corresponding to tumour tissue or non-tumour tissue; based on having classified the feature vector of at least one tile as representing tumour tissue, classifying a region of the image as representing a tumour region; providing a binary colour map of the image by representing regions classified as tumour regions in a first colour and regions classified as classified non-tumour regions in a second colour; identifying a boundary of a first colour region in the binary colour map; smoothing the boundary by applying a smoothing algorithm to provide a smoothed template for cutting along the corresponding tissue boundary; and scaling the relative colour intensity of first colour regions according to a probability of their correspondence with a tumour region of the tissue sample respectively.
14. The method of any preceding claim, comprising cutting along the tissue boundary, wherein the step of cutting along the tissue boundary comprises cutting along a tissue boundary in the tissue section or cutting along a tissue boundary in a subsequent tissue section of the tissue sample.
15. A computer program product comprising program instructions configured to program a processor to perform the method of any of claims 1 to 14.
16. Apparatus configured to carry out the method of any of claims 1 to 15. 30
17. A macrodissection apparatus, comprising: a receiver for receiving data representing the boundary in the image identified by the computer program product of claim 14 or the apparatus of claim 15; and a controller for guiding a cutting of the tissue sample along a path based on the data 35 representing the boundary.-18 -
18. A macrodissection system comprising the computer program product of claim 15 or the apparatus of claim 16 and the macrodissection apparatus of claim 17.
19. An image server, accessible to a plurality of users, configured to; receive, from any of the plurality of users, image data of a tissue section of a tissue sample containing tumour and non-tumour regions; access classification data for classifying regions of the image as tumour regions or non-tumour regions; implement a method according to any of claims 1 to 12 on the data to identify a boundary in the image; and make data representing the boundary available to at least one of the plurality of users
20. The image server of claim 19, wherein the classification data comprises an association between stored feature vectors and a tumour tissue class, and a non-tumour tissue class.
21. The image server of claim 19 wherein the feature vectors each comprise at least one 20 image property derived from at least one of a plurality of colour components of the image.
22. The image server of claim 19, wherein the image server is configured to update the classification data using a supervised learning method based on the received data and feedback from the user.
23. An apparatus for guiding in vitro dissection of a tissue sample, the apparatus comprising: a processor configured to obtain an image of a tissue section of the tissue sample, to identify at least one image property of the image, to compare the image property with classification data, and, based on the comparison, to determine whether a region of the sample comprises tumour; wherein the processor is configured so, in the event that the sample comprises tumour, the processor identifies a boundary of the tumour region of the image; and provides the image boundary to guide dissection of tumour from the sample.-19 -
24. The apparatus of claim 23 wherein the apparatus comprises a display for displaying the boundary as a template to guide dissection of the sample.
25. The apparatus of claim 23 or 24 configured to perform the method of any of claims 1 5 to 14.
26. A computer implemented image processing method, or computer program product, substantially as described herein with reference to the accompanying drawings.
27. Apparatus substantially as described herein with reference to the accompanying drawings.
28. A macrodissection system substantially as described herein with reference to the accompanying drawings.
29. An image server substantially as described herein with reference to the accompanying drawings.
30. The apparatus or method of any preceding claim wherein the image colour components comprise colour channels.