Combining graph neural networks and computer vision methods for cell nuclei classification in lung tissue.

The detection of tumoural cells from whole slide images is an essential task in medical diagnosis and research. In this article, we propose and analyse a novel approach that combines computer vision-based models with graph neural networks to improve the accuracy of automated tumoural cell detection in lung tissue. Our proposal leverages the inherent structure and relationships between cells in the tissue. Experimental results on our own curated dataset show that modelling the problem with graphs gives the model a clear advantage over just working at pixel level. This change in perspective provides extra information that makes it possible to improve the performance. The reduction of dimensionality that comes from working with the graph also allows us to increase the field of view with low computational requirements. Code is available at https://github.com/Jerry-Master/lung-tumour-study, models are uploaded to https://huggingface.co/Jerry-Master/Hovernet-plus-Graphs, and the dataset is published on Zenodo https://zenodo.org/doi/10.5281/zenodo.8368122.

Stromal tissue segmentation in Ki67 histology images based on cytokeratin-19 stain translation.

Purpose: The 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. Approach: We 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. Results: The 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. Conclusions: An 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.

DigiPatICS: Digital Pathology Transformation of the Catalan Health Institute Network of 8 Hospitals-Planification, Implementation, and Preliminary Results.

Complete digital pathology transformation for primary histopathological diagnosis is a challenging yet rewarding endeavor. Its advantages are clear with more efficient workflows, but there are many technical and functional difficulties to be faced. The Catalan Health Institute (ICS) has started its DigiPatICS project, aiming to deploy digital pathology in an integrative, holistic, and comprehensive way within a network of 8 hospitals, over 168 pathologists, and over 1 million slides each year. We describe the bidding process and the careful planning that was required, followed by swift implementation in stages. The purpose of the DigiPatICS project is to increase patient safety and quality of care, improving diagnosis and the efficiency of processes in the pathological anatomy departments of the ICS through process improvement, digital pathology, and artificial intelligence tools.

Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation.

We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm. We then propose a high-performance hierarchical segmenter that makes effective use of multiscale information. Finally, we propose a grouping strategy that combines our multiscale regions into highly-accurate object proposals by exploring efficiently their combinatorial space. We also present Single-scale Combinatorial Grouping (SCG), a faster version of MCG that produces competitive proposals in under five seconds per image. We conduct an extensive and comprehensive empirical validation on the BSDS500, SegVOC12, SBD, and COCO datasets, showing that MCG produces state-of-the-art contours, hierarchical regions, and object proposals.

Supervised Evaluation of Image Segmentation and Object Proposal Techniques.

This paper tackles the supervised evaluation of image segmentation and object proposal algorithms. It surveys, structures, and deduplicates the measures used to compare both segmentation results and object proposals with a ground truth database; and proposes a new measure: the precision-recall for objects and parts. To compare the quality of these measures, eight state-of-the-art object proposal techniques are analyzed and two quantitative meta-measures involving nine state of the art segmentation methods are presented. The meta-measures consist in assuming some plausible hypotheses about the results and assessing how well each measure reflects these hypotheses. As a conclusion of the performed experiments, this paper proposes the tandem of precision-recall curves for boundaries and for objects-and-parts as the tool of choice for the supervised evaluation of image segmentation. We make the datasets and code of all the measures publicly available.

Correlation between a semiautomated method based on ultrasound texture analysis and standard ultrasound diagnosis using white matter damage in preterm neonates as a model.

OBJECTIVES: Diagnosis of white matter damage by cranial ultrasound imaging is still subject to interobserver variability and has limited sensitivity for predicting abnormal neurodevelopment later in life. In this study, we evaluated the ability of a semiautomated method based on ultrasound texture analysis to identify patterns that correlate with the ultrasound diagnosis of white matter damage. METHODS: The study included 44 very preterm neonates born at a median gestational age of 29 weeks 3 days (range, 26 weeks-31 weeks 6 days). Patients underwent cranial ultrasound scans within 1 week of birth and between 14 and 31 days of life. Periventricular leukomalacia was diagnosed by experienced clinicians on the 14- to 31-day scan according to standard criteria. To perform the texture analysis, 4 regions of interest were delineated in stored images: left and right periventricular areas and choroid plexuses. A classification algorithm was developed on the basis of the best combination of texture coefficients to correlate with the clinical diagnosis, and the ability of this algorithm to predict a later diagnosis of periventricular leukomalacia on the first scan was evaluated using a leave-one-out cross-validation. RESULTS: Periventricular leukomalacia was diagnosed by the standard procedure in 14 of 44 neonates. The texture classification algorithm performed on the first scan could identify cases with a later diagnosis of periventricular leukomalacia with sensitivity of 100% and accuracy of 97.7%. CONCLUSIONS: These data support the notion that semiautomated quantitative ultrasound analysis achieves early identification of changes in subclinical stages and warrant further investigation of the role of ultrasound texture analysis methods to improve early detection of neonatal brain damage.

Region merging techniques using information theory statistical measures.

The purpose of the current work is to propose, under a statistical framework, a family of unsupervised region merging techniques providing a set of the most relevant region-based explanations of an image at different levels of analysis. These techniques are characterized by general and nonparametric region models, with neither color nor texture homogeneity assumptions, and a set of innovative merging criteria, based on information theory statistical measures. The scale consistency of the partitions is assured through i) a size regularization term into the merging criteria and a classical merging order, or ii) using a novel scale-based merging order to avoid the region size homogeneity imposed by the use of a size regularization term. Moreover, a partition significance index is defined to automatically determine the subset of most representative partitions from the created hierarchy. Most significant automatically extracted partitions show the ability to represent the semantic content of the image from a human point of view. Finally, a complete and exhaustive evaluation of the proposed techniques is performed, using not only different databases for the two main addressed problems (object-oriented segmentation of generic images and texture image segmentation), but also specific evaluation features in each case: under- and oversegmentation error, and a large set of region-based, pixel-based and error consistency indicators, respectively. Results are promising, outperforming in most indicators both object-oriented and texture state-of-the-art segmentation techniques.

Binary partition trees for object detection.

This paper discusses the use of Binary Partition Trees (BPTs) for object detection. BPTs are hierarchical region-based representations of images. They define a reduced set of regions that covers the image support and that spans various levels of resolution. They are attractive for object detection as they tremendously reduce the search space. In this paper, several issues related to the use of BPT for object detection are studied. Concerning the tree construction, we analyze the compromise between computational complexity reduction and accuracy. This will lead us to define two parts in the BPT: one providing accuracy and one representing the search space for the object detection task. Then we analyze and objectively compare various similarity measures for the tree construction. We conclude that different similarity criteria should be used for the part providing accuracy in the BPT and for the part defining the search space and specific criteria are proposed for each case. Then we discuss the object detection strategy based on BPT. The notion of node extension is proposed and discussed. Finally, several object detection examples illustrating the generality of the approach and its efficiency are reported.

Prefetching and caching strategies for remote and interactive browsing of JPEG2000 images.

This paper considers the issues of scheduling and caching JPEG2000 data in client/server interactive browsing applications, under memory and channel bandwidth constraints. It analyzes how the conveyed data have to be selected at the server and managed within the client cache so as to maximize the reactivity of the browsing application. Formally, to render the dynamic nature of the browsing session, we assume the existence of a reaction model that defines when the user launches a novel command as a function of the image quality displayed at the client. As a main outcome, our work demonstrates that, due to the latency inherent to client/server exchanges, a priori expectation about future navigation commands may help to improve the overall reactivity of the system. In our study, the browsing session is defined by the evolution of a rectangular window of interest (WoI) along the time. At any given time, the WoI defines the position and the resolution of the image data to display at the client. The expectation about future navigation commands is then formalized based on a stochastic navigation model, which defines the probability that a given WoI is requested next, knowing previous WoI requests. Based on that knowledge, several scheduling scenarios are considered. The first scenario is conventional and transmits all the data corresponding to the current WoI before prefetching the most promising data outside the current WoI. Alternative scenarios are then proposed to anticipate prefetching, by scheduling data expected to be requested in the future before all the current WoI data have been sent out. Our results demonstrate that, for predictable navigation commands, anticipated prefetching improves the overall reactivity of the system by up to 30% compared to the conventional scheduling approach. They also reveal that an accurate knowledge of the reaction model is not required to get these significant improvements.