Nuclear segmentation in digital microscopic tissue images can enable extraction of high-quality features for nuclear morphometrics and other analysis in computational pathology. Conventional image processing techniques, such as Otsu thresholding and watershed segmentation, do not work effectively on challenging cases, such as chromatin-sparse and crowded nuclei. In contrast, machine learning-based segmentation can generalize across various nuclear appearances. However, training machine learning algorithms requires data sets of images, in which a vast number of nuclei have been annotated. Publicly accessible and annotated data sets, along with widely agreed upon metrics to compare techniques, have catalyzed tremendous innovation and progress on other image classification problems, particularly in object recognition. Inspired by their success, we introduce a large publicly accessible data set of hematoxylin and eosin (H&E)-stained tissue images with more than 21000 painstakingly annotated nuclear boundaries, whose quality was validated by a medical doctor. Because our data set is taken from multiple hospitals and includes a diversity of nuclear appearances from several patients, disease states, and organs, techniques trained on it are likely to generalize well and work right out-of-the-box on other H&E-stained images. We also propose a new metric to evaluate nuclear segmentation results that penalizes object- and pixel-level errors in a unified manner, unlike previous metrics that penalize only one type of error. We also propose a segmentation technique based on deep learning that lays a special emphasis on identifying the nuclear boundaries, including those between the touching or overlapping nuclei, and works well on a diverse set of test images.

A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology

This paper presents a new supervised method for vessel segmentation in retinal images. This method remolds the task of segmentation as a problem of cross-modality data transformation from retinal image to vessel map. A wide and deep neural network with strong induction ability is proposed to model the transformation, and an efficient training strategy is presented. Instead of a single label of the center pixel, the network can output the label map of all pixels for a given image patch. Our approach outperforms reported state-of-the-art methods in terms of sensitivity, specificity and accuracy. The result of cross-training evaluation indicates its robustness to the training set. The approach needs no artificially designed feature and no preprocessing step, reducing the impact of subjective factors. The proposed method has the potential for application in image diagnosis of ophthalmologic diseases, and it may provide a new, general, high-performance computing framework for image segmentation.

A Cross-Modality Learning Approach for Vessel Segmentation in Retinal Images

Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels’ local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired by the recently introduced deformable convolutional networks, we integrate the deformable convolution into the proposed network. The DUNet, with upsampling operators to increase the output resolution, is designed to extract context information and enable precise localization by combining low-level features with high-level ones. Furthermore, DUNet captures the retinal vessels at various shapes and scales by adaptively adjusting the receptive fields according to vessels’ scales and shapes. Public datasets: DRIVE, STARE, CHASE_DB1 and HRF are used to test our models. Detailed comparisons between the proposed network and the deformable neural network, U-Net are provided in our study. Results show that more detailed vessels can be extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0.9566/0.9641/0.9610/0.9651 and AUC of 0.9802/0.9832/0.9804/0.9831 on DRIVE, STARE, CHASE_DB1 and HRF respectively. Moreover, to show the generalization ability of the DUNet, we use another two retinal vessel data sets, i.e., WIDE and SYNTHE, to qualitatively and quantitatively analyze and compare with other methods. Extensive cross-training evaluations are used to further assess the extendibility of DUNet. The proposed method has the potential to be applied to the early diagnosis of diseases.

DUNet: A deformable network for retinal vessel segmentation

Goal: In this work, we present an extensive description and evaluation of our method for blood vessel segmentation in fundus images based on a discriminatively trained fully connected conditional random field model. Methods: Standard segmentation priors such as a Potts model or total variation usually fail when dealing with thin and elongated structures. We overcome this difficulty by using a conditional random field model with more expressive potentials, taking advantage of recent results enabling inference of fully connected models almost in real time. Parameters of the method are learned automatically using a structured output support vector machine, a supervised technique widely used for structured prediction in a number of machine learning applications. Results: Our method, trained with state of the art features, is evaluated both quantitatively and qualitatively on four publicly available datasets: DRIVE, STARE, CHASEDB1, and HRF. Additionally, a quantitative comparison with respect to other strategies is included. Conclusion: The experimental results show that this approach outperforms other techniques when evaluated in terms of sensitivity, F1-score, G-mean, and Matthews correlation coefficient. Additionally, it was observed that the fully connected model is able to better distinguish the desired structures than the local neighborhood-based approach. Significance: Results suggest that this method is suitable for the task of segmenting elongated structures, a feature that can be exploited to contribute with other medical and biological applications.

/pdf/a-discriminatively-trained-fully-connected-conditional-29gv5ppedb.pdf

A Discriminatively Trained Fully Connected Conditional Random Field Model for Blood Vessel Segmentation in Fundus Images

One of the most common modalities to examine the human eye is the eye-fundus photograph. The evaluation of fundus photographs is carried out by medical experts during time-consuming visual inspection. Our aim is to accelerate this process using computer aided diagnosis. As a first step, it is necessary to segment structures in the images for tissue differentiation. As the eye is the only organ, where the vasculature can be imaged in an in vivo and noninterventional way without using expensive scanners, the vessel tree is one of the most interesting and important structures to analyze. The quality and resolution of fundus images are rapidly increasing. Thus, segmentation methods need to be adapted to the new challenges of high resolutions. In this paper, we present a method to reduce calculation time, achieve high accuracy, and increase sensitivity compared to the original Frangi method. This method contains approaches to avoid potential problems like specular reflexes of thick vessels. The proposed method is evaluated using the STARE and DRIVE databases and we propose a new high resolution fundus database to compare it to the state-of-the-art algorithms. The results show an average accuracy above 94% and low computational needs. This outperforms state-of-the-art methods.

/pdf/robust-vessel-segmentation-in-fundus-images-257cdoka2b.pdf

Robust Vessel Segmentation in Fundus Images

Automatic assessment of retinal vessels plays an important role in the diagnosis of various eye, as well as systemic diseases. A public screening is highly desirable for prompt and effective treatment, since such diseases need to be diagnosed at an early stage. Automated and accurate segmentation of the retinal blood vessel tree is one of the challenging tasks in the computer-aided analysis of fundus images today. We improve the concept of matched filtering, and propose a novel and accurate method for segmenting retinal vessels. Our goal is to be able to segment blood vessels with varying vessel diameters in high-resolution colour fundus images. All recent authors compare their vessel segmentation results to each other using only low-resolution retinal image databases. Consequently, we provide a new publicly available high-resolution fundus image database of healthy and pathological retinas. Our performance evaluation shows that the proposed blood vessel segmentation approach is at least comparable with recent state-of-the-art methods. It outperforms most of them with an accuracy of 95% evaluated on the new database.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-ipr.2012.0455

Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database

A method for segmentation of vessel structure in colour retinal fundus images is presented, based on 2D matched filtering correlating the local image areas with 2D masks obtained via averaging of brightness profiles of vessels for several different vessel widths.Each of the basic masks is rotated in twelve different directions; this way, 60 masks for 5 different widths, each with 12 orientations are produced and used as 2D convolution kernels of the matched filters. The maximum response of all the filter responses for a concrete local area thus carries - if there is a vessel present - the information both on the width and orientation of the vessel segment. Compared to the previously published results [6], the segmentation has been improved primarily in two directions: the width resolution has been increased from 3 to 5 classes with a better approximation of the brightness profiles, and the orientation information is now utilized to provide vessel direction maps that are further used in the following phase of complementing the missing vessel segments. The parametric maps representing the maximum responses of the filters are then combined and finally tresholded thus obtaining binary vessel maps to be morphologically cleaned in order to remove the artefacts due to noise and also to complement the obviously missing parts of vessels. The method was designed and tested using the high-resolution fundus camera images provided by a cooperating ophthalmological clinic, and also statistically tested based on the standard public image database DRIVE.

Improvement of Vessel Segmentation by Matched Filtering in Colour Retinal Images

Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration.

Thickness related textural properties of retinal nerve fiber layer in color fundus images.

The texture analysis of the retinal nerve fiber layer (RNFL) in colour fundus images is a promising tool for early glaucoma diagnosis. This paper describes model-based method for detection of changes in the RNFL. The method utilizes Gaussian Markov random fields (GMRF) and the least-square error (LSE) estimate for the local RNFL texture modelling. The model parameters are used as a texture features and non-linear classifier based on the Bayesian rule is used for classification of healthy and glaucomatous RNFL tissue. The proposed features are tested in the sense of classification errors and also they are applied for segmentation of RNFL defects in a high-resolution colour fundus-camera images. The results are also compared with the Optical Coherence Tomography images regarded as a gold standard for our application due to the possibility of quantitative RNFL thickness measurement.

Jiri Gazarek

Papers

Retinal vessel segmentation by improved matched filtering: evaluation on a new high-resolution fundus image database

Improvement of Vessel Segmentation by Matched Filtering in Colour Retinal Images

Retinal image analysis aimed at blood vessel tree segmentation and early detection of neural-layer deterioration.

Thickness related textural properties of retinal nerve fiber layer in color fundus images.

Retinal nerve fiber layer analysis via Markov random fields texture modelling