Automatic segmentation is a fundamental task in computer-assisted medical image analysis. Convolutional neural networks (CNNs) have been widely used for medical image segmentation tasks. Currently, most deep learning-based methods output a probability map and use a hand-crafted threshold to generate the final segmentation result, while how confident the network is of the probability map remains unclear. The segmentation result can be quite unreliable even though the probability is much higher than the threshold since the uncertainty of the probability can also be high. Moreover, boundary information loss caused by consecutive pooling layers and convolution strides makes the object’s boundary in segmentation even more unreliable. In this paper, we propose an uncertainty guided network referred to as UG-Net for automatic medical image segmentation. Different from previous methods, our UG-Net can learn from and contend with uncertainty by itself in an end-to-end manner. Specifically, UG-Net consists of three parts: a coarse segmentation module (CSM) to obtain the coarse segmentation and the uncertainty map, an uncertainty guided module (UGM) to leverage the obtained uncertainty map in an end-to-end manner, and a feature refinement module (FRM) embedded with several dual attention (DAT) blocks to generate the final segmentations. In addition, to formulate a unified segmentation network and extract richer context information, a multi-scale feature extractor (MFE) is inserted between the encoder and decoder of the CSM. Experimental results show that the proposed UG-Net outperforms the state-of-the-art methods on nasopharyngeal carcinoma (NPC) segmentation, lung segmentation, optic disc segmentation and retinal vessel detection. • A deep learning-based network named UG-Net is proposed for medical image segmentation. • An uncertainty guided module is proposed to learn from uncertainty in an end-to-end manner. • A feature refinement module with dual attention mechanism is designed for further performance promotion. • A multi-scale feature extractor is devised to fit into different segmentation tasks. 

Unified medical image segmentation by learning from uncertainty in an end-to-end manner

In a fundus image, Vessel local characteristics like direction, illumination and noise vary considerably, making vessel segmentation a challenging task. Methods based upon deep convolutional networks have consistently yield state of the art performance. Despite effective, of the drawbacks of these methods is their computational complexity, whereby testing and training of these networks require substantial computational resources and can be time consuming. Here we present a multi-scale kernel based on fully convolutional layers that is quite lightweight and can effectively segment large, medium, and thin vessels over a wide variations of contrast, position and size of the optic disk. Moreover, the architecture presented here makes use of these multi-scale kernels, reduced application of pooling operations and skip connections to achieve faster training. We illustrate the utility of our method for retinal vessel segmentation on the DRIVE, CHASE_DB and STARE data sets. We also compare the results delivered by our method with a number of alternatives elsewhere in the literature. In our experiments, our method always provides a margin of improvement on specificity, accuracy, AUC and sensitivity with respect to the alternative.

Residual Multiscale Full Convolutional Network (RM-FCN) for High Resolution Semantic Segmentation of Retinal Vasculature

Recent trends and advances in fundus image analysis: A review

Retinal vessels are considered important biomarkers for the detection of retinal diseases, like diabetic retinopathy (caused by diabetes) and hypertensive retinopathy (caused by hypertension). The manual finding from this retinal vasculature is time-consuming and costly. The image quality of the fundus image directly affects the accurate segmentation of these vessels in the automatic methods. With such inferior quality images, deep-learning-based methods are better for dealing with segmentation. Conventional deep-learning-based vessel segmentation methods deal the segmentation task with deeper convolutional neural networks and many trainable parameters. Minor changes in the retinal vasculature, such as those that result from the creation of new smaller vessels, is crucial for the keen analysis of diseases (e.g., diabetic retinopathy). The small vessels are crucial to segment, owing to continuous max-pooling operations and deeper networks. We herein present a pool-less residual segmentation network that is capable of segmenting even smaller vessels using a shallower network with a low number of trainable parameters. Our proposed pool-less residual segmentation network (PLRS-Net) is a vessel segmentation network that provides the pooling effect with strided convolution for better segmentation sensitivity. The final PLRS-Net is an advanced form of a pool-less segmentation network (PLS-Net) wherein semantic segmentation was performed with a few layers, and the residual connection fulfilled the feature enhancement strategy to construct PLRS-Net. PLS-Net and PLRS-Net are two separate networks that can perform vessel segmentation without prior preprocessing and postprocessing. To evaluate our proposed method, the experiments include three publicly available datasets: Digital retinal images for vessel extraction (DRIVE), child heart health study in England database (CHASE-DB1), and structured analysis of retina (STARE). The results demonstrate that our proposed method provides a high segmentation performance, achieving an average sensitivity (Sen) of 82.69, specificity (Spe) of 98.17, accuracy (Acc) 96.82, and area under the curve (AUC) of 98.35 for the DRIVE dataset, Sen of 83.01, Spe of 98.39, Acc of 97.31, and AUC of 98.63 for the CHASE-DB1 dataset, and a Sen of 86.35, Spe of 98.03, Acc of 97.15, and AUC of 98.99 for the STARE dataset. These accuracies show exceptional segmentation performance of the proposed method compared to state-of-the-art approaches for automatic vessel detection for diagnosis purposes. 

Detecting retinal vasculature as a key biomarker for deep Learning-based intelligent screening and analysis of diabetic and hypertensive retinopathy

Achieving accurate retinal vessel segmentation is critical in the progression and diagnosis of vision-threatening diseases such as diabetic retinopathy and age-related macular degeneration. Existing vessel segmentation methods are based on encoder-decoder architectures, which frequently fail to take into account the retinal vessel structure's context in their analysis. As a result, such methods have difficulty bridging the semantic gap between encoder and decoder characteristics. This paper proposes a Prompt Deep Light-weight Vessel Segmentation Network (PLVS-Net) to address these issues by using prompt blocks. Each prompt block use combination of asymmetric kernel convolutions, depth-wise separable convolutions, and ordinary convolutions to extract useful features. This novel strategy improves the performance of the segmentation network while simultaneously decreasing the number of trainable parameters. Our method outperformed competing approaches in the literature on three benchmark datasets, including DRIVE, STARE, and CHASE.

Prompt Deep Light-Weight Vessel Segmentation Network (PLVS-Net)

Accurate automatic segmentation of the retinal vessels is crucial for early detection and diagnosis of vision-threatening retinal diseases. A new supervised method using a variant of the fully convolutional neural network is pro-posed with the advantages of reduced hyper-parameters, reduced computational/memory requirements, and robust performance in capturing tiny vessel information. The fully convolutional architectures previously employed for vessel segmentation have multiple tunable hyperparameters and difficulty in end-to-end training due to their decoder structure. We resolve this problem by sharing information from the encoder for upsampling at the decoder stage, resulting in a significantly smaller number of tunable parameters and low computational overhead at the train and test stages. Moreover, the need for pre- and post-processing steps are eradicated. Consequently, the detection accuracy is significantly improved with scores of 0.9620, 0.9623, and 0.9620 on DRIVE, STARE, and CHASE_DB1 datasets respectively.

Syed S. Naqvi

Papers

Exploiting Residual Edge Information in Deep Fully Convolutional Neural Networks For Retinal Vessel Segmentation