PurposeThe diagnosis and prognosis of breast cancer relies on histopathology image analysis. In this context, proliferation markers, especially Ki67, are increasingly important. The diagnosis using these markers is based on the quantification of proliferation, which implies the counting of Ki67 positive and negative tumoral cells in epithelial regions, thus excluding stromal cells. However, stromal cells are often very difficult to distinguish from negative tumoral cells in Ki67 images and often lead to errors when automatic analysis is used.ApproachWe study the use of automatic semantic segmentation based on convolutional neural networks (CNNs) to separate stromal and epithelial areas on Ki67 stained images. CNNs need to be accurately trained with extensive databases with associated ground truth. As such databases are not publicly available, we propose a method to produce them with minimal manual labelling effort. Inspired by the procedure used by pathologists, we have produced the database relying on knowledge transfer from cytokeratin-19 images to Ki67 using an image-to-image (I2I) translation network.ResultsThe automatically produced stroma masks are manually corrected and used to train a CNN that predicts very accurate stroma masks for unseen Ki67 images. An F-score value of 0.87 is achieved. Examples of effect on the KI67 score show the importance of the stroma segmentation.ConclusionsAn I2I translation method has proved very useful for building ground-truth labeling in a task where manual labeling is unfeasible. With reduced correction effort, a dataset can be built to train neural networks for the difficult problem of separating epithelial regions from stroma in stained images where separation is very hard without additional information.
This paper deals with the joint use of connected operators and image inpainting for image filtering. Connected
operators filter the image by merging its flat zones while preserving contour information. Image inpainting
restores the values of an image for a destroyed or consciously masked subregion of the image domain. In the
present paper, it will be shown that image inpainting can be combined with connected operators to perform
an efficient geometrical filtering technique. First, connected operators are presented and their drawbacks for
certain applications are highlighted. Second, image inpainting methodology is introduced and a structural image
inpainting algorithm is described. Finally, a general filtering scheme is proposed to show how the drawbacks of
connected operators can be efficiently solved by structural image inpainting.
This paper deals with a class of morphological operators called connected operators. These operators interact with the signal by merging flat zones. As a results, they do not create any new contours and are very attractive for filtering tasks where the contour information has to be preserved. This paper focuses on a class of operators dealing with motion information. They remove from the original sequence the components that do not undergo a specific motion. They have a large number of applications including image sequence analysis with motion multiresolution decomposition and motion estimation.
This paper deals with the coding of the partition information resulting from the segmentation of video sequences. Motion compensation of partition sequences is described as an efficient inter-frame mode of coding. It involves the prediction of the partition, the computation of the partition compensation error, the simplification of the error and its transmission. The major issues and processing steps of a general motion compensation loop for partitions are presented and discussed.
This paper describes a coding-oriented segmentation technique for video schemes using an optimization strategy to address the problem of bit allocation. The optimization is based on the rate-distortion theory. Our purpose is to define a method to obtain an 'optimal' partition together with the best coding technique for each region of this partition so that the result is optimal in a rate-distortion sense.
This paper deals with the notion of connected operators. These operators are becoming popular in image processing because they have the fundamental property of simplifying the signal while preserving the contour information. In a first step, we recall the basic notions involved in binary and gray level connected operators. Then, we show how one can extend and generalize these operators. We focus on two important issues: the connectivity and the simplification criterion. We show in particular how to create connectivities that are either more or less strict than the usual ones and how to build new criteria.
This paper describes a texture coding technique mainly suitable for segmentation-based coding schemes. The main features of the proposed technique are its efficiency in terms of bits per pixel for homogeneous regions and its ability to deal with local inhomogeneities that may be present in the image. The basic idea of the coding strategy is to divide the image into blocks and to classify the blocks in two categories: Referable and Nonreferable. Referable means that the block can be approximated by one block of the already transmitted texture and nonreferable is defined by opposition. Nonreferable blocks are transmitted with a general purpose coding scheme (for example a DCT-based technique) and referable blocks are transmitted by means of a simple transition vector indicating which sample of the transmitted texture has to be translated. We show that this technique is suitable for texture but produces distortions for strong contours. As a result, we propose to use it within a segmentation-based coding scheme where contours are transmitted by another strategy. Finally, the application to sequence coding is discussed. It is shown that this technique is particularly attractive to code the prediction error within a motion compensated video coding scheme.
The objective of the paper is to present a new object based image coding technique using morphological segmentation. These are the first results of a final objective of proposing a completely new coding/decoding scheme for storage and transmission applications based on Mathematical Morphology. The paper presents a new object based image coding algorithm that involves three main processing steps: segmentation, coding of contours and coding of the inside. The three fundamental coding steps of our approach work on a multiscale representation of the data. The coding of contours represents the shape and location of the region and is based on techniques relying on chain codes. The coding of inside consists in modeling the gray level function of the image and in filling each region with this model. Orthogonal polynomials are used for inside coding and bit allocation techniques are developed such that efficient compression rates are obtained. Several computer generated images are presented that show good visual results for a variety of different compression ratios. The techniques can also be applied to image sequences. Current research is under way to propose new coding techniques for both the contour and the inside coding using Mathematical Morphology.
This paper deals with the notion of connected operators in the context of mathematical morphology. In the case of gray level functions, the flat zones over a space E are defined as the largest connected components of E on which the function is constant (a flat zone may be reduced to a single point). Hence, the flat zones of every function make a partition of the space. A connected operator acting on a function is a mapping which enlarges the partition of the space created by the flat zones of the functions. In this paper, it is shown that, from any connected operator acting on sets, one can construct a connected operator for functions. Then, the concept of pyramid is introduced and one of the most important results of this study is that, if a pyramid is based on connected operators, the flat zones of the functions increase with the level of the pyramid. In other words, the flat zones are nested. Then, a very important class of connected filter called `filter by reconstruction' is defined and its properties are stated and discussed. Rules to create pyramids relying on filters by reconstruction are proposed.
This paper deals with a morphological approach to the problem of unsupervised image segmentation. The proposed technique relies on a multiscale approach which allows a hierarchical processing of the data ranging from the most global scale to the most detailed one. At each scale, the algorithm relies on four steps: preprocessing, feature extraction, decision and quality estimation. The goal of the preprocessing step is to simplify the original signal which is too complex to be processed at once. Morphological filters by reconstruction are very attractive for this purpose because they simplify without corrupting the contour information. The feature extraction intends to extract the pertinent parameters for assessing the degree of homogeneity of the regions. To this goal, morphological techniques extracting flat or contrasted regions are very efficient. The decision step defines precisely the contours of the regions. This decision is achieved by a watershed algorithm. Finally, the quality estimation is used to compute the information that has to be further processed by the next scale to improve the segmentation result. The estimation is based on a region modeling procedure. The resulting segmentation is very robust and can deal with very different types of images. Moreover, the first levels give segmentation results with a few regions; but precisely located contours.
This paper deals with size-sensitive multiresolution decomposition using adaptive morphological filters with a flat structuring element. This type of decomposition generates a set of images, each containing elements of the original image with a specific size. The authors propose to extract a set of dominant shapes contained in the original image and to assess the size of a particular element by comparison with this set of dominant shapes. This approach is particularly suitable for texture images where dominant shapes are actually present. In a first step, it is shown how a flat structuring element of a morphological filter can be adapted to optimize a statistical criterion such as the mean square error. The approach is suitable for any morphological filters and the proposed algorithms are simple. Moreover, they can be easily modified to achieve a size-constrained optimization of the structuring element, which is an attractive solution for the extraction of dominant shapes. Finally,adaptive morphological filters are used in a multiresolution decomposition scheme which sorts the various components as a function of their size while taking into account the presence of dominant shapes. Two particular applications are presented. They address the problems of noise removal and texture defect detection.
This paper deals with surface defect detection. The approach investigated here attempts to detect grey level as well as texture defects. The defects are regarded as being characterized by abrupt, local and unpredictable changes in an image. On the other hand, a defect-free surface is assumed to be regular and homogeneous, possibly with smooth and slow variation in its features.
The detection is based on adaptive image modeling. It is shown that a classical autoregressive model is not really suitable for this detection problem. Then, two modified models are proposed. Their advantage lies in their taking into account the grey level value as well as the texture information.The model adaptation can be stated as a joint optimization problem with constraint. Two different algorithms are defined and tested.
The first algorithm performs the adaptation in a recursive way while enforcing the
constraint at each step, whereas the second one imposes the constraint only at optimum.
The performance of each algorithms is assessed with a statistical test using synthetic images. Finally, it is shown how this adaptive modeling technique can be applied to practical defect detection problems. Several cases are presented and discussed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.