Immediate workup

Abstract

The present invention relates to deep learning implementations for medical imaging. More particularly, the present invention relates to a method and system for indicating whether additional medical tests are required after analysing an initial medical screening, in substantially real-time. Aspects and/or embodiments seek to provide a method and system for recommending additional medical tests, in substantially real-time, based on analysing an initial medical scan, with the use of deep learning.

Claims

1. A computer-aided method of analysing medical images, the method comprising: receiving one or more medical images; analysing said one or more medical images to determine characteristics using one or more trained machine learning models, wherein the characteristics include at least a tissue type and a density category; and generating output data based on the determined characteristics, wherein the output data is indicative of a requirement to obtain one or more additional medical tests, further wherein the output data is based on at least the determined tissue type and density category.

2. The method of claim 1 wherein the one or more additional medical tests comprises any or any combination of: a computerised tomography (CT) scan; an ultrasound scan; a magnetic resonance imaging (MRI) scan; a tomosynthesis scan; and/or a biopsy.

3. The method of claim 2 wherein the one or more additional medical tests are dependent upon the density category determined based on the one or more medical images.

4. The method of claim 1 wherein the one or more medical images comprises one or more mammographic or X-ray scans.

5. The method of claim 1 wherein the one or more trained machine learning models comprise convolutional neural networks.

6. The method of claim 1 wherein the step of analysing comprises segmenting one or more anatomical regions.

7. The method of claim 6 wherein the output data further comprises overlay data indicating a segmentation outline and/or probability masks showing one or more locations of one or more segmented regions.

8. The method of claim 1 wherein the step of analysing comprises automatically identifying one or more anomalous regions in the one or more medical images.

9. The method of claim 1 wherein the step of analysing comprises identifying and distinguishing between a malignant lesion and/or a benign lesion and/or typical lesion.

10. The method of claim 9 wherein the output data further comprises overlay data indicating a probability mask for the one or more lesions.

11. The method of claim 1 wherein the step of analysing comprises identifying architectural distortion.

12. The method of claim 1 wherein the one or more medical images comprise digital imaging and communications in medicine, (DICOM), files.

13. A system for analysing medical images, the system comprising: a medical imaging device; a picture archiving communication system (PACS); and a processing unit configured to analyse the one or more medical images on the PACS to identify at least a tissue type and a density category using one or more trained machine learning models, and generate output data based on at least the identified tissue type and density category, wherein the output data is indicative of a requirement to obtain one or more additional medical tests.

14. The system of claim 13 further comprising: an output viewer operable to display the output data.

15. The system of claim 13 wherein the processing unit is integrated with the medical imaging device.

16. The system of claim 13 wherein the processing unit is located remotely and is accessible via a communications channel.

17. The system of claim 16 wherein the processing unit is part of a computer system located within a remote cloud system.

18. The system of claim 13 wherein the medical imaging device includes x-ray equipment, mammography scanning equipment, or magnetic resonance imaging equipment.

19. The system of claim 13 wherein the one or more trained machine learning models comprise convolutional neural networks.

20. A non-transitory computer program product comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to claim 1.

Description

BRIEF DESCRIPTION OF DRAWINGS

(1) Embodiments will now be described, by way of example only and with reference to the accompanying drawings having like-reference numerals, in which:

(2) FIG. 1 shows a flow diagram of an embodiment;

(3) FIG. 2 depicts a first deployment (for example, within a medical scanning device);

(4) FIG. 3 depicts a second deployment (for example, on the premises of a medical facility); and

(5) FIG. 4 depicts a third deployment (for example, using a cloud system).

SPECIFIC DESCRIPTION

(6) Referring to FIGS. 1 to 4, an embodiment will now be described.

(7) As seen in FIG. 1, having performed a medical scan of a patient (such as a mammography) using a medical imaging scanner 101, the scanned images are collated in DICOM format, which is a file format commonly used to store medical images. The method uses pre-processed data that is stored on a Picture Archiving Communication Systems (PACS) 102 that radiology departments use in hospitals. The output of this method also enriches the PACS database to improve future applications of analysing mammographic images. Image data is extracted from the DICOM file and an image is generated.

(8) The image then undergoes a pre-processing stage 103. The image is loaded onto a 4D tensor of size [1, width, height, 1]. The pre-processing stage may comprise windowing the image data to a predetermined windowing level. The windowing level defines the range of bit values considered in the image. Medical images are conventionally 16-bit images, wherein each pixel is represented as a 16-bit integer ranging from 0 to 2.sup.16−1, i.e. [0, 1, 2, . . . , 65535]. The information content is very high in these images, and generally comprises more information than what the human eye is capable of detecting. A set value for the windowing level is typically included within the DICOM file.

(9) In some cases, it can be important to maintain image resolution. Often, conventional graphics processing unit (GPU) constraints require that the image is divided into a plurality of patches in order to maintain resolution. Each patch can then be provided to a Fully Convolutional Network (FCN). The larger the patch, the more context that can be provided but some precision may be lost. For example, in the case of a large image comprising a small tumour, if the FCN is instructed that somewhere in this patch there is a tumour, the network would need to learn how to find it first before it can be classified. In this embodiment patch sizes of 300×300 pixels are used, although larger and smaller patch sizes may be used.

(10) A rescaling step may be included owing to above mentioned constraints of conventional hardware. Medical images are typically in the region of ˜3500×2500 pixels. An FCN applied to this image does not fit in conventional graphics processing unit (GPU) memory. The image can be rescaled to a larger or smaller size, or even not rescaled at all, and would allow the FCN to see a higher resolution and may pick up finer detail. However, this is unlikely to fit in GPU memory, and could cause the method to become considerably slower. By rescaling the image to a smaller size, it is more likely to be able to fit in a GPU memory, and allow the processes to run at a faster speed. The FCN may also generalise better owing to a smaller number of input parameters.

(11) The method may be used to identify and detect lesions in the mammograms. The lesions which may be segmented may comprise one or more cancerous growths, masses, abscesses, lacerations, calcifications, and/or other irregularities within biological tissue.

(12) The images are analysed by feeding them through a trained machine learning model 104, such as a Convolutional Neural Network. This embodiment utilises deep learning techniques to train and develop the convolution network. The model is trained on a dataset with known workups and, hence, directly establishes a relationship between the images received and the known workups to estimate a required workup. In particular, the output 105 of the machine learning model 104 is a binary vector, where the indices represent various types of workup. For example, the workups may be any, or any combination of need no further action, an Ultrasound scan, a Tomosynthesis scan, an MRI scan and/or taking a Biopsy.

(13) The dataset used for training the neural networks may also contain known density or tissue types. In that case, a multi-task learning approach can be taken to have the model also output density (A, B, C, D) or tissue type (1, 2, 3, 4, 5).

(14) There are different types of patterns in breast tissue that affect the detectability of breast cancers. Thus, it is important to know what kind of pattern is present. There are five mammography parenchymal patterns known as “Tabar patterns”, named after professor Laszlo Tabar who developed this classification.

(15) The Tabar patterns (or classifications types) are based on a histologic-mammographic correlation with a three-dimensional, subgross (thick-slice) technique, and on the relative proportion of four “building blocks” (nodular densities, linear densities, homogeneous fibrous tissue, radiolucent fat tissue). The five classifications are as follows: 1. Balanced proportion of all components of breast tissue with a slight predominance of fibrous tissue 2. Predominance of fat tissue 3. Predominance of fat tissue with retroareolar residual fibrous tissue 4. Predominantly nodular densities 5. Predominantly fibrous tissue (dense breast)

(16) Classes 4 and 5 are considered high risk, meaning that it is difficult to detect cancers in the breast with those patterns, whereas classes 1, 2 and 3 are considered lower risk as it is easier to spot cancerous regions.

(17) Some therapies may alter the pattern by increasing parenchymal density, as in hormone replacement therapy (HRT), or reducing it as in therapies with selective oestrogen-receptor modulators (SERM).

(18) Similarly, breast density categories are classified by radiologists using the BI-RADS system. Again, this classification is used for quality control purposes. For example, it is very difficult to spot an anomaly in dense breasts. There are four categories in the BI-RADS system: A. The breasts are almost entirely fatty B. There are scattered areas of fibroglandular density C. The breasts are heterogeneously dense, which may obscure small masses D. The breasts are extremely dense, which lowers the sensitivity of mammography

(19) Importantly, breast densities and tissue patterns are also known to have a mutual correlation to breast cancer development.

(20) In some cases, the method can produce two types of output data. Whilst output data can relate to a suggested workup or additional medical tests 105a, the output data may also indicate the density or tissue classification 105b. The output data can indicate a binary output as to the requirement for further tests. Optionally, the output data can include data relating to how the binary output was reached, including any of; Tabar pattern; tissue classification types; breast density; nodular densities; linear densities; homogenous fibrous tissue; radiolucent fat tissue; BI-RADS category; a measure of superimposed features within the images; probability and/or confidence rating.

(21) Mammography is a medical imaging modality widely used for breast cancer detection. Mammography makes use of “soft” X-rays to produce detailed images of the internal structure of the human breast—these images are called mammograms and this method is considered to be the gold standard in early detection of breast abnormalities which provide a valid diagnosis of a cancer in a curable phase.

(22) Unfortunately, the procedure of analysing mammograms is often challenging. The density and tissue type of the breasts are highly varied and in turn present a high variety of visual features due to patient genetics. These background visual patterns can obscure the often tiny signs of malignancies which may then be easily overlooked by the human eye. Thus, the analyses of mammograms often lead to false-positive or false-negative diagnostic results which may cause missed treatment (in the case of false negatives) as well as unwanted psychological and sub-optimal downstream diagnostic and treatment consequences (in the case of false positives).

(23) Most developed countries maintain a population-wide screening program, comprising a comprehensive system for calling in women of a certain age group (even if free of symptoms) to have regular breast screening. These screening programs require highly standardized protocols to be followed by experienced specialist trained doctors who can reliably analyse a large number of mammograms routinely. Most professional guidelines strongly suggest reading of each mammogram by two equally expert radiologists (also referred to as double-reading). Nowadays, when the number of available radiologists is insufficient and decreasing, the double-reading requirement is often impractical or impossible.

(24) When analysing mammograms, the reliable identification of anatomical structures is important for visual evaluation and especially for analytic assessment of visual features based on their anatomic location and their relation to anatomic structures, which may have profound implications on the final diagnostic results. In the case that anatomic structures appear distorted they may also indicate the presence of possible malignancies.

(25) Conventional X-ray is a medical imaging modality widely used for the detection of structural abnormalities related to the air containing structures and bones, as well as those diseases which have an impact on them. Conventional X-ray is the most widely used imaging method and makes use of “hard” X-rays to produce detailed images of the internal structure of the lungs and the skeleton. These images are called roentgenograms or simply X-rays.

(26) Unfortunately, the procedure of analysing X-rays is often challenging, especially when analysing lung X-rays in order to detect infectious disease (e.g. TB) or lung cancer in early stage.

(27) Cross-sectional medical imaging modalities are widely used for detection of structural or functional abnormalities and diseases which have a visually identifiable structural impact on the human internal organs. Generally, the images demonstrate the internal structures in multiple cross-sections of the body. The essence of the most widely used cross-sectional techniques are described below.

(28) Computed tomography (CT) is a widely used imaging method and makes use of “hard” X-rays produced and detected by a specially rotating instrument and the resulted attenuation data (also referred to as raw data) are presented by a computed analytic software producing detailed images of the internal structure of the internal organs. The produced sets of images are called CT-scans which may constitute multiple series with different settings and different contrast agent phases to present the internal anatomical structures in cross sections perpendicular to the axis of the human body (or synthesized sections in other angles).

(29) Magnetic Resonance Imaging (MRI) is an advanced diagnostic technique which makes use of the effect magnetic field impacts on movements of protons which are the utmost tiniest essential elements of every living tissue. In MRI machines the detectors are antennas and the signals are analysed by a computer creating detailed images if the internal structures in any section of the human body. MRI can add useful functional information based on signal intensity of generated by the moving protons.

(30) However, the procedure of analysing any kind of cross-sectional images is often challenging, especially in the case of oncologic disease as the initial signs are often hidden and appearance of the affected areas are only minimally differed from the normal.

(31) When analysing cross sectional scans, diagnosis is based on visual evaluation of anatomical structures. The reliable assessment, especially for analytic assessment, of visual appearance based on their anatomic location and their relation to anatomic structures, may have profound implications on final diagnostic results. In the case that anatomic structures appear distorted they may also indicate the presence of possible malignancies.

(32) Generally, in the case of all diagnostic radiology methods (which include mammography, conventional X-ray, CT, MRI), the identification, localisation (registration), segmentation and classification of abnormalities and/or findings are important interlinked steps in the diagnostic workflow.

(33) In the case of ordinary diagnostic workflows carried out by human radiologists, these steps may only be partially or sub-consciously performed but in the case of computer-based or computer-aided diagnoses and analyses the steps often need to be performed in a clear, concrete, descriptive and accurate manner.

(34) Locality and classification may define and significantly influence diagnoses. Both locality and classification may be informed by segmentation in terms of the exact shape and extent of visual features (i.e. size and location of boundaries, distance from and relation to other features and/or anatomy). Segmentation may also provide important information regarding the change in status of disease (e.g. progression or recession).

(35) Machine learning is the field of study where a computer or computers learn to perform classes of tasks using the feedback generated from the experience or data gathered that the machine learning process acquires during computer performance of those tasks.

(36) Typically, machine learning can be broadly classed as supervised and unsupervised approaches, although there are particular approaches such as reinforcement learning and semi-supervised learning which have special rules, techniques and/or approaches. Supervised machine learning is concerned with a computer learning one or more rules or functions to map between example inputs and desired outputs as predetermined by an operator or programmer, usually where a data set containing the inputs is labelled.

(37) Unsupervised learning is concerned with determining a structure for input data, for example when performing pattern recognition, and typically uses unlabelled data sets. Reinforcement learning is concerned with enabling a computer or computers to interact with a dynamic environment, for example when playing a game or driving a vehicle.

(38) Various hybrids of these categories are possible, such as “semi-supervised” machine learning where a training data set has only been partially labelled. For unsupervised machine learning, there is a range of possible applications such as, for example, the application of computer vision techniques to image processing or video enhancement. Unsupervised machine learning is typically applied to solve problems where an unknown data structure might be present in the data. As the data is unlabelled, the machine learning process is required to operate to identify implicit relationships between the data for example by deriving a clustering metric based on internally derived information. For example, an unsupervised learning technique can be used to reduce the dimensionality of a data set and attempt to identify and model relationships between clusters in the data set, and can for example generate measures of cluster membership or identify hubs or nodes in or between clusters (for example using a technique referred to as weighted correlation network analysis, which can be applied to high-dimensional data sets, or using k-means clustering to cluster data by a measure of the Euclidean distance between each datum).

(39) Semi-supervised learning is typically applied to solve problems where there is a partially labelled data set, for example where only a subset of the data is labelled. Semi-supervised machine learning makes use of externally provided labels and objective functions as well as any implicit data relationships. When initially configuring a machine learning system, particularly when using a supervised machine learning approach, the machine learning algorithm can be provided with some training data or a set of training examples, in which each example is typically a pair of an input signal/vector and a desired output value, label (or classification) or signal. The machine learning algorithm analyses the training data and produces a generalised function that can be used with unseen data sets to produce desired output values or signals for the unseen input vectors/signals. The user needs to decide what type of data is to be used as the training data, and to prepare a representative real-world set of data. The user must however take care to ensure that the training data contains enough information to accurately predict desired output values without providing too many features (which can result in too many dimensions being considered by the machine learning process during training and could also mean that the machine learning process does not converge to good solutions for all or specific examples). The user must also determine the desired structure of the learned or generalised function, for example whether to use support vector machines or decision trees.

(40) The use of unsupervised or semi-supervised machine learning approaches are sometimes used when labelled data is not readily available, or where the system generates new labelled data from unknown data given some initial seed labels.

(41) Machine learning may be performed through the use of one or more of: a non-linear hierarchical algorithm; neural network; convolutional neural network; recurrent neural network; long short-term memory network; multi-dimensional convolutional network; a memory network; fully convolutional network or a gated recurrent network allows a flexible approach when generating the predicted block of visual data. The use of an algorithm with a memory unit such as a long short-term memory network (LSTM), a memory network or a gated recurrent network can keep the state of the predicted blocks from motion compensation processes performed on the same original input frame. The use of these networks can improve computational efficiency and also improve temporal consistency in the motion compensation process across a number of frames, as the algorithm maintains some sort of state or memory of the changes in motion. This can additionally result in a reduction of error rates.

(42) Developing a machine learning system typically consists of two stages: (1) training and (2) production. During the training the parameters of the machine learning model are iteratively changed to optimise a particular learning objective, known as the objective function or the loss. Once the model is trained, it can be used in production, where the model takes in an input and produces an output using the trained parameters.

(43) During training stage of neural networks, verified inputs are provided, and hence it is possible to compare the neural network's calculated output to then the correct the network is need be. An error term or loss function for each node in neural network can be established, and the weights adjusted, so that future outputs are closer to an expected result. Backpropagation techniques can also be used in the training schedule for the or each neural network.

(44) The model can be trained using backpropagation and forward pass through the network. The loss function for dense training is the sum over spatial dimensions of the loss functions of the individual pixels.
L(x)=Σ.sub.i,jl′(x.sub.i,j)
here L(x) is the loss over the whole image and l′(x.sub.i,j) is the loss for the pixel at i,j. This enables the system to automatically identify one or more lesions from the image created by the system.

(45) The loss function may be the DICE loss, which is defined as

(46) $L_{\mathrm{DSC}}=\frac{2\underset{i}{\overset{N}{.Math.}}{s}_i{r}_i}{\underset{i}{\overset{N}{.Math.}}{s}_i+\underset{i}{\overset{N}{.Math.}}{r}_i}$
where s.sub.i and r.sub.i represent the continuous values of the prediction map ∈[0, . . . , 1] and the ground truth at each pixel i, respectively. Alternatively, a cross-entropy can be used. The cross-entropy loss for the pixel at i, j is defined as

(47) $L_{\mathrm{CE}}=-\underset{c=1}{\overset{C}{.Math.}}y*\log \left(s\right)$
where C is the number of classes, y∈{0,1} is the binary indicator for class c, and s is the score for class c. The loss for the full image, x, is defined as the sum over all the losses for the pixels:

(48) $L_{\mathrm{CE}}\left(x\right)=\underset{i,j}{.Math.}\left(-\underset{c=1}{\overset{C}{.Math.}}y*\log \left(s\right)\right)$

(49) Once an output is generated by the neural network, one or more patches from the output may be sampled. The sampling may be proportional to the probability of the presence of lesions, in particular the sampling may be taken from areas with a higher probability of being a lesion as defined by a predetermined threshold. Alternatively, Poisson sampling or uniform sampling may be used to sample patches. Poisson sampling may give a better coverage of all of the breast tissue. The CNN may also be trained using the results of a different process, for example a Random Forest based candidate selector or any similar lesion detection method.

(50) In the multitask learning setting, the loss will consist of multiple parts. A loss term for each task.
L(x)=λ.sub.1L.sub.1+λ.sub.2L.sub.2

(51) Where L.sub.1, L.sub.2 are the loss terms for two different tasks and λ.sub.1, λ.sub.2 are weighting terms.

(52) Any system features as described herein may also be provided as method features, and vice versa. As used herein, means plus function features may be expressed alternatively in terms of their corresponding structure.

(53) Any feature in one aspect may be applied to other aspects, in any appropriate combination. In particular, method aspects may be applied to system aspects, and vice versa. Furthermore, any, some and/or all features in one aspect can be applied to any, some and/or all features in any other aspect, in any appropriate combination.

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