Importance Application of deep learning algorithms to whole-slide pathology images can potentially improve diagnostic accuracy and efficiency. Objective Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists’ diagnoses in a diagnostic setting. Design, Setting, and Participants Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). Exposures Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. Main Outcomes and Measures The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. Results The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884];P  Conclusions and Relevance In the setting of a challenge competition, some deep learning algorithms achieved better diagnostic performance than a panel of 11 pathologists participating in a simulation exercise designed to mimic routine pathology workflow; algorithm performance was comparable with an expert pathologist interpreting whole-slide images without time constraints. Whether this approach has clinical utility will require evaluation in a clinical setting.

/pdf/diagnostic-assessment-of-deep-learning-algorithms-for-13rg5habe2.pdf

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer.

Two different formal definitions of gray-scale reconstruction are presented. The use of gray-scale reconstruction in various image processing applications discussed to illustrate the usefulness of this transformation for image filtering and segmentation tasks. The standard parallel and sequential approaches to reconstruction are reviewed. It is shown that their common drawback is their inefficiency on conventional computers. To improve this situation, an algorithm that is based on the notion of regional maxima and makes use of breadth-first image scannings implemented using a queue of pixels is introduced. Its combination with the sequential technique results in a hybrid gray-scale reconstruction algorithm which is an order of magnitude faster than any previously known algorithm. >

/pdf/morphological-grayscale-reconstruction-in-image-analysis-nh3wqbbs21.pdf

Morphological grayscale reconstruction in image analysis: applications and efficient algorithms

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

https://pubs.rsna.org/doi/pdf/10.1148/radiol.2020191145

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

The watershed transform is the method of choice for image segmentation in the field of mathematical morphology. We present a critical review of several definitions of the watershed transform and the associated sequential algorithms, and discuss various issues which often cause confusion in the literature. The need to distinguish between definition, algorithm specification and algorithm implementation is pointed out. Various examples are given which illustrate differences between watershed transforms based on different definitions and/or implementations. The second part of the paper surveys approaches for parallel implementation of sequential watershed algorithms.

/pdf/the-watershed-transform-definitions-algorithms-and-19vbswqg8k.pdf

The watershed transform: definitions, algorithms and parallelization strategies

Mass cytometry enables high-dimensional, single-cell analysis of cell type and state. In mass cytometry, rare earth metals are used as reporters on antibodies. Analysis of metal abundances using the mass cytometer allows determination of marker expression in individual cells. Mass cytometry has previously been applied only to cell suspensions. To gain spatial information, we have coupled immunohistochemical and immunocytochemical methods with high-resolution laser ablation to CyTOF mass cytometry. This approach enables the simultaneous imaging of 32 proteins and protein modifications at subcellular resolution; with the availability of additional isotopes, measurement of over 100 markers will be possible. We applied imaging mass cytometry to human breast cancer samples, allowing delineation of cell subpopulations and cell-cell interactions and highlighting tumor heterogeneity. Imaging mass cytometry complements existing imaging approaches. It will enable basic studies of tissue heterogeneity and function and support the transition of medicine toward individualized molecularly targeted diagnosis and therapies.

Highly multiplexed imaging of tumor tissues with subcellular resolution by mass cytometry

In image compression, object-based approaches are adapted to high compression rates, since they take into account the geometry of the objects and the human eye characteristics. Mathematical Morphology, dealing with geometrical features is a well suited technique for segmentation purposes. This paper presents a method to segment image sequences, first step of an object-oriented compression system, based on Mathematical Morphology.

Morphological Segmentation of Image Sequences

works on an adequate class of functions, it is possible to define a subset ofremarkable points of the digital skeleton, called crest points. They form anover set of the centers of maximal disks. Crest points and their upstream formthe digital skeleton.The skeleton of a binary set is then made in three steps : 1) construct thedistance function, 2) detect the crest points, 3) construct their upstream.The quality of the skeleton depends on the quality of the distance function.The balls associated with the digital distance based on the connectivity ofthe grid are in fact polygons : hexagons for the hexagonal grid, squares or

Digital Euclidean skeletons

In most operators of mathematical morphology source and destina- tion are the same: from pixels to pixels. In this paper we present adjunctions where source and destination are not the same. In ad- dition to the pixels of a grid, we also consider the centers of edges linking neighboring pixels. Interesting filters may be constructed using such operators, in particular bi-levelings, where the introduc- tion of some degree of viscosity permits to obtain higher levels of simplifications as with ordinary levelings.

Micro-viscous morphological operators

If one considers only local neighborhoods for segmenting an image, one gets contours whose strength is often poorly estimated. A method for reevaluating the contour strength by taking into account non local features is presented: one generates a fixed number of random germs which serve as markers for the watershed segmentation. For each new population of markers, another set of contours is generated. "Important" contours are selected more often. The present paper shows that the probability that a contour is selected can be estimated without performing the effective simulations.

/pdf/a-stochastic-evaluation-of-the-contour-strength-3rskmns5pb.pdf

A stochastic evaluation of the contour strength

The transformation applies to images defined by pixels each presenting a characteristic, such as a brightness, defined by a digital value, with the pixels being distributed according to a matrix and their relations and distances established by a neighborhood graph. All or part of the image is explored according to a predetermined exploration mode and the value of each pixel is modified as a function of the values of a set of associated pixels, assuming their value in at least the image and being located inside a sliding window related to the pixel to be transformed, identical for all pixels and constituting a structuring element. The transformed version of each pixel is immediately substituted for the preceding value in an image memory. To implement the process, a device can be utilized having a morphological opening processor, an image memory and a morphological processor with rewrite processing.

Fernand Meyer

Papers

Morphological Segmentation of Image Sequences

Digital Euclidean skeletons

Micro-viscous morphological operators

A stochastic evaluation of the contour strength

Process and device for sequential image transformation