Efficient Segmentation Research Articles

Semantic-Region Aware Model Predictive Trajectory Tracking in Automated Guided Vehicles

Autonomous routing through curved path for point-to-point mobile robot is a well-established challenging problem in the area of intelligent path navigation. Point-to-point collision-free locomotion of AGV (Automated Guided Vehicle) requires precise differentiation of movable path from other environmental visual noise. As these path navigating depend on various visual cues and precepts, naturally the semantic meaning of path in contrast to other closely available objects on the visual window requires significant amount of understanding of the input from precepts. In this paper, it is experimentally established that semantic segmentation has proved to be a concise method in making comparative better segregation of paths from midway structured obstacles that are with high computational cost. The claims are also evident from surveyed works. The challenge of reducing high computational performance with efficient segmentation of movable area has been addressed in this research work with a focus on deriving better filtered accessible paths with a degree of algorithmic confidence. Further, this segmented result is taken for curved trajectory tracking by the AGV. A systematic percept mediated deep based Semantic-region Aware Model Predictive Trajectory Tracking(SAMP-TT)Algorithm has been proposed to solve the problem of precise obstacle detection on curved path trajectories. RGB (Red, Green Blue) image of outdoor multi-sectioned area has been collected by Intel Realsense D455 which worked as input feed to the respective neural network models. The performance of the proposed technique has been benchmarked with existing segmentation models including ENET (Efficient Neural Network), U-NET to confirm the considerable reliability and accuracy of the presented algorithm. It has been followed by the state-of-art comparative visual result analysis of different taken models with the proposed architecture.

Fractional and B-COSFIRE filter based approach for efficient segmentation of retinal blood vessels

The morphological structure of retinal blood vessels plays an important role in diagnosing ophthalmic diseases such as glaucoma and diabetic retinopathy. Diabetic retinopathy is one of the leading causes of blindness worldwide. Because of the need to examine a large number of individuals on a daily basis, it is indeed challenging for ophthalmologists to analyze the complex retinal vasculature of every outpatient. Automated segmentation of retinal blood vessels can be of significant aid in this labor-intensive process. This work proposes an unsupervised approach for retinal blood vessel segmentation. Here, we enhance the performance of the B-COSFIRE filters for segmentation of the retinal vasculature by denoising a retinal image using a fractional filter derived from a left/forward weighted fractional integral prior to the vascular enhancement by B-COSFIRE filters. Also, we utilize hysteresis thresholding rather than a single global threshold to obtain the final segmented vessels enhanced by the B-COSFIRE filters. This helps to avoid the problem of nonuniform illumination and poor contrast in retinal images.

Feasibility of Encord Artificial Intelligence Annotation of Arterial Duplex Ultrasound Images.

DUS measurements for popliteal artery aneurysms (PAAs) specifically can be time-consuming, error-prone, and operator-dependent. To eliminate this subjectivity and provide efficient segmentation, we applied artificial intelligence (AI) to accurately delineate inner and outer lumen on DUS. DUS images were selected from a cohort of patients with PAAs from a multi-institutional platform. Encord is an easy-to-use, readily available online AI platform that was used to segment both the inner lumen and outer lumen of the PAA on DUS images. A model trained on 20 images and tested on 80 images had a mean Average Precision of 0.85 for the outer polygon and 0.23 for the inner polygon. The outer polygon had a higher recall score than precision score at 0.90 and 0.85, respectively. The inner polygon had a score of 0.25 for both precision and recall. The outer polygon false-negative rate was the lowest in images with the least amount of blur. This study demonstrates the feasibility of using the widely available Encord AI platform to identify standard features of PAAs that are critical for operative decision making.

A Point Cloud Segmentation Method for Dim and Cluttered Underground Tunnel Scenes Based on the Segment Anything Model

In recent years, point cloud segmentation technology has increasingly played a pivotal role in tunnel construction and maintenance. Currently, traditional methods for segmenting point clouds in tunnel scenes often rely on a multitude of attribute information, including spatial distribution, color, normal vectors, intensity, and density. However, the underground tunnel scenes show greater complexity than road tunnel scenes, such as dim light, indistinct boundaries of tunnel walls, and disordered pipelines. Furthermore, issues pertaining to data quality, such as the lack of color information and insufficient annotated data, contribute to the subpar performance of conventional point cloud segmentation algorithms. To address this issue, a 3D point cloud segmentation framework specifically for underground tunnels is proposed based on the Segment Anything Model (SAM). This framework effectively leverages the generalization capability of the visual foundation model to automatically adapt to various scenes and perform efficient segmentation of tunnel point clouds. Specifically, the tunnel is first sliced along its direction on the tunnel line. Then, each sliced point cloud is projected onto a two-dimensional plane. Various projection methods and point cloud coloring techniques are employed to enhance SAM’s segmentation performance in images. Finally, the semantic segmentation of the entire underground tunnel is achieved by a small set of manually annotated semantic labels used as prompts in a progressive and recursive manner. The key feature of this method lies in its independence from model training, as it directly and efficiently addresses tunnel point cloud segmentation challenges by capitalizing on the generalization capability of foundation model. Comparative experiments against classical region growing algorithms and PointNet++ deep learning algorithms demonstrate the superior performance of our proposed algorithm.

Efficient and accurate segmentation of adhesive lamellae in tri-modal microstructure of titanium alloy based on OpenCV

The adhesive characteristics of the tri-modal microstructure in titanium alloys, particularly the adhesion of the lamellar phase that constitutes over 50% of the microstructure, significantly hinder its quantitative characterization, further impeding the establishment of the quantitative relationships between the microstructure and mechanical properties. Addressing this challenge, this study utilized the OpenCV computer vision library to accomplish efficient and precise automated segmentation of the adhesive lamellae in tri-modal microstructure by enhancing the existing segmentation algorithm based on concave point matching. Specifically, by taking the number of the adhesive target after segmentation and Harris corner detection threshold as the optimization goal and variable respectively, and employing the genetic algorithm, the threshold, accounting for the segmentation effect, was adaptively determined to accurately identify the corner points of the adhesive lamellae. And then quick determination of the concave points within these corner points was achieved by substituting conventional pixel circle with equidistant pixels distributed along the circumference. Upon identifying the concave points, classification of the points was performed based on their spacing and location, and corresponding matching criteria were established and applied. Eventually, by introducing segmentation lines between the matched points, adhesive lamellae were segmented with an accuracy exceeding 85%, which will lay a robust foundation for the rapid and automated quantitative characterization of the tri-modal microstructure in titanium alloys.

Image Segmentation of Plant Leaves in Natural Environments Based on LinkNet

The conventional approach to plant leaf image segmentation for subsequent measurement of leaf geometric parameters, while reasonably accurate, exhibits lower efficiency. To address this challenge, a plant leaf image segmentation algorithm based on deep learning semantic segmentation models and transfer learning is proposed to achieve rapid and precise leaf segmentation. The presented method adopts LinkNet as its foundational network structure and introduces four key enhancements: leveraging ResNet18 as the backbone encoder network to expedite model fitting through transfer learning; reducing the number of encoding and decoding blocks to decrease network complexity; refining channel reduction strategies to minimize parameters in upsampling; and implementing subpixel convolution for upsampling to lower computational load. Integrated with the focal loss function, this improved LinkNet network is applied to a standard leaf dataset. Experimental outcomes indicate that the proposed algorithm achieves a segmentation accuracy of 97.27%, comparable to the original LinkNet; inference time is merely 7.82 ms, a 39.89% reduction compared to the original network; a substantial decrease in model parameters and floating-point operations; and a significantly faster inference speed of the improved network compared to FCN, U-Net, DeepLabV3+, and similar networks. This algorithm not only swiftly segments the main body of leaves but also effectively preserves details such as leaf edge serrations. It truly enables efficient and precise segmentation of plant leaves, offering a novel approach for rapidly measuring leaf area and other geometric parameters.

An efficient instance segmentation approach for studying fission gas bubbles in irradiated metallic nuclear fuel

Gaseous fission products from nuclear fission reactions tend to form fission gas bubbles of various shapes and sizes inside nuclear fuel. The behavior of fission gas bubbles dictates nuclear fuel performances, such as fission gas release, grain growth, swelling, and fuel cladding mechanical interaction. Although mechanical understanding of the overall evolution behavior of fission gas bubbles is well known, lacking the quantitative data and high-level correlation between burnup/temperature and microstructure evolution blocks the development of predictive models and reduces the possibility of accelerating the qualification for new fuel forms. Historical characterization of fission gas bubbles in irradiated nuclear fuel relied on a simple threshold method working on low-resolution optical microscopy images. Advanced characterization of fission gas bubbles using scanning electron microscopic images reveals unprecedented details and extensive morphological data, which strains the effectiveness of conventional methods. This paper proposes a hybrid framework, based on digital image processing and deep learning models, to efficiently detect and classify fission gas bubbles from scanning electron microscopic images. The developed bubble annotation tool used a multitask deep learning network that integrates U-Net and ResNet to accomplish instance-level bubble segmentation. With limited annotated data, the model achieves a recall ratio of more than 90%, a leap forward compared to the threshold method. The model has the capability to identify fission gas bubbles with and without lanthanides to better understand the movement of lanthanide fission products and fuel cladding chemical interaction. Lastly, the deep learning model is versatile and applicable to the micro-structure segmentation of similar materials.

An Efficient Point Cloud Semantic Segmentation Method Based on Bilateral Enhancement and Random Sampling

Point cloud semantic segmentation is of utmost importance in practical applications. However, most existing methods have evolved to be incredibly intricate, leading to a rise in complexity that has made them increasingly impractical for real-world utilization. The escalating complexity of these methods has resulted in a deterioration in their efficiency and ease of implementation, making them less suitable for use in time-sensitive and resource-constrained environments. Towards this issue, we propose an efficient and lightweight segmentation method, able to achieve a remarkable performance in terms of both segmentation accuracy, training speed, and space consumption. Specifically, we first propose to adopt random sampling to replace the original one to obtain more efficiency. Moreover, a lightweight decoding module and an improved bilateral enhancement (BAE) module are developed to further improve the performance. The proposed method achieved a 73.6% and 60.7% mIoU on the S3DIS and Semantickitti datasets, respectively. In the future, the random sampling and the proposed BAE module can be adopted in a more concise and lightweight network to achieve faster and more-accurate point cloud segmentation.

Railway Remote Sensing Image Segmentation Technology in Big Data-oriented Urban Rail Transit Safety Evaluation System

This paper discusses the application of satellite remote sensing images in urban rail transit safety evaluation. First of all, the article expounds the significance of satellite remote sensing images in the rail transit safety evaluation system, which can provide the overall information of the rail transit network, be used for traffic flow analysis, land use monitoring, etc., and provide a basis for planning decision-making. Then, the article introduces the application of artificial intelligence technology in the segmentation of railway remote sensing images. The deep learning model can realize automatic and efficient image segmentation and improve the segmentation accuracy. Then, the article designs a railway remote sensing image segmentation system based on PaddleSeg, and uses Google Earth remote sensing images for training and testing. Finally, the article analyzes the role of U-Net in the railway segmentation task, and the reflection of different evaluation indicators on the performance of the model. Research shows that artificial intelligence technology can greatly improve the segmentation efficiency and accuracy of railway remote sensing images, and provide strong support for rail transit safety evaluation.

Feature-enhanced fusion of U-NET-based improved brain tumor images segmentation

The field of medical image segmentation, particularly in the context of brain tumor delineation, plays an instrumental role in aiding healthcare professionals with diagnosis and accurate lesion quantification. Recently, Convolutional Neural Networks (CNNs) have demonstrated substantial efficacy in a range of computer vision tasks. However, a notable limitation of CNNs lies in their inadequate capability to encapsulate global and distal semantic information effectively. In contrast, the advent of Transformers, which has established their prowess in natural language processing and computer vision, offers a promising alternative. This is primarily attributed to their self-attention mechanisms that facilitate comprehensive modeling of global information. This research delineates an innovative methodology to augment brain tumor segmentation by synergizing UNET architecture with Transformer technology (denoted as UT), and integrating advanced feature enhancement (FE) techniques, specifically Modified Histogram Equalization (MHE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Modified Bi-histogram Equalization Based on Optimization (MBOBHE). This integration fosters the development of highly efficient image segmentation algorithms, namely FE1-UT, FE2-UT, and FE3-UT. The methodology is predicated on three pivotal components. Initially, the study underscores the criticality of feature enhancement in the image preprocessing phase. Herein, techniques such as MHE, CLAHE, and MBOBHE are employed to substantially ameliorate the visibility of salient details within the medical images. Subsequently, the UT model is meticulously engineered to refine segmentation outcomes through a customized configuration within the UNET framework. The integration of Transformers within this model is instrumental in imparting contextual comprehension and capturing long-range data dependencies, culminating in more precise and context-sensitive segmentation. Empirical evaluation of the model on two extensively acknowledged public datasets yielded accuracy rates exceeding 99%.

DFBU-Net: Double-branch flat bottom U-Net for efficient medical image segmentation

In the field of medical image processing, segmenting tissues and organs in CT/MRI and other medical sequence images is a vital yet challenging task. Analyzing the MICCAI competition, we have identified two problems in current methods for medical image organ segmentation: (1) There is a bottleneck in organ segmentation, with marginal room for improvement, as algorithmic capabilities have already surpassed the task’s inherent difficulty. (2) Most current research focuses on stacking and enhancing new modules for segmentation while overlooking the inherent characteristics of medical sequence images. To overcome these two problems, firstly, we have encapsulated the three characteristics of CT/MRI medical sequence image segmentation: semantic correctness, edge accuracy, and 3D structure. Secondly, we delved into the most information-rich downsampling stage in terms of detail and semantics. Subsequently, we designed a flat-bottom double-branch network (DFBU-Net) based on the U-Net architecture. The high-resolution flat bottom branch of this network maintained a 1/4 feature map size to ensure the preservation of rich detail information, while the low-resolution branch underwent progressive downsampling to capture more semantic information. To prevent information loss, cross-fusion was performed at each stage of the model’s two branches. Finally, DFBU-Net was evaluated on the MICCAI FLARE2021 dataset (DSC:93.61%, NSD:85.01%). Particularly, in the challenging task of pancreatic segmentation, our model outperformed the first-place model by 0.72% in DSC and 2.92% in NSD. Furthermore, in the MICCAI PARSE2022 competition, DFBU-Net ranked ninth with a DICE score of 79.28%, demonstrating its excellent segmentation performance and generalization ability.

An Efficient Breast Cancer Segmentation System based on Deep Learning Techniques

Breast cancer is one of the major threats that attack women around the world. Its detection and diagnosis in the early stages can greatly improve care efficiency and reduce mortality rate. Early detection of breast cancer allows medical professionals to use less intrusive treatments, such as lumpectomies or targeted medicines, improving survival rates and lowering morbidity. This study developed a breast cancer segmentation system based on an improved version of the U-Net 3+ neural network. Various optimizations were applied to this architecture to improve the localization and segmentation performance. An evaluation of different state-of-the-art networks was performed to improve the performance of the proposed breast cancer diagnosis system. Various experiments were carried out on the INbreast Full-Field Digital Mammographic dataset (INbreast FFDM). The results obtained demonstrated that the proposed model achieved a dice score of 98.47%, which is a new state-of-the-art segmentation finding, showcasing its efficiency in detecting breast cancer from mammography images with the possibility of implementation for real applications.

Research on water extraction from high resolution remote sensing images based on deep learning

Introduction: Monitoring surface water through the extraction of water bodies from high-resolution remote sensing images is of significant importance. With the advancements in deep learning, deep neural networks have been increasingly applied to high-resolution remote sensing image segmentation. However, conventional convolutional models face challenges in water body extraction, including issues like unclear water boundaries and a high number of training parameters.Methods: In this study, we employed the DeeplabV3+ network for water body extraction in high-resolution remote sensing images. However, the traditional DeeplabV3+ network exhibited limitations in segmentation accuracy for high-resolution remote sensing images and incurred high training costs due to a large number of parameters. To address these issues, we made several improvements to the traditional DeeplabV3+ network: Replaced the backbone network with MobileNetV2. Added a Channel Attention (CA) module to the MobileNetV2 feature extraction network. Introduced an Atrous Spatial Pyramid Pooling (ASPP) module. Implemented Focal loss for balanced loss computation.Results: Our proposed method yielded significant enhancements. It not only improved the segmentation accuracy of water bodies in high-resolution remote sensing images but also effectively reduced the number of network parameters and training time. Experimental results on the Water dataset demonstrated superior performance compared to other networks: Outperformed the U-Net network by 3.06% in terms of mean Intersection over Union (mIoU). Outperformed the MACU-Net network by 1.03%. Outperformed the traditional DeeplabV3+ network by 2.05%. The proposed method surpassed not only the traditional DeeplabV3+ but also U-Net, PSP-Net, and MACU-Net networks.Discussion: These results highlight the effectiveness of our modified DeeplabV3+ network with MobileNetV2 backbone, CA module, ASPP module, and Focal loss for water body extraction in high-resolution remote sensing images. The reduction in training time and parameters makes our approach a promising solution for accurate and efficient water body segmentation in remote sensing applications.

RETRACTED ARTICLE: Features fusion based novel approach for efficient blood vessel segmentation from fundus images

RETRACTED ARTICLE: Features fusion based novel approach for efficient blood vessel segmentation from fundus images

Efficient hand segmentation for rehabilitation tasks using a convolution neural network with attention

Efficient hand segmentation for rehabilitation tasks using a convolution neural network with attention

EdgeMedNet: Lightweight and Accurate U-Net for Implementing Efficient Medical Image Segmentation on Edge Devices

EdgeMedNet: Lightweight and Accurate U-Net for Implementing Efficient Medical Image Segmentation on Edge Devices

Deep learning-based clinical-radiomics nomogram for preoperative prediction of lymph node metastasis in patients with rectal cancer: a two-center study.

Precise preoperative evaluation of lymph node metastasis (LNM) is crucial for ensuring effective treatment for rectal cancer (RC). This research aims to develop a clinical-radiomics nomogram based on deep learning techniques, preoperative magnetic resonance imaging (MRI) and clinical characteristics, enabling the accurate prediction of LNM in RC. Between January 2017 and May 2023, a total of 519 rectal cancer cases confirmed by pathological examination were retrospectively recruited from two tertiary hospitals. A total of 253 consecutive individuals were selected from Center I to create an automated MRI segmentation technique utilizing deep learning algorithms. The performance of the model was evaluated using the dice similarity coefficient (DSC), the 95th percentile Hausdorff distance (HD95), and the average surface distance (ASD). Subsequently, two external validation cohorts were established: one comprising 178 patients from center I (EVC1) and another consisting of 88 patients from center II (EVC2). The automatic segmentation provided radiomics features, which were then used to create a Radscore. A predictive nomogram integrating the Radscore and clinical parameters was constructed using multivariate logistic regression. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were employed to evaluate the discrimination capabilities of the Radscore, nomogram, and subjective evaluation model, respectively. The mean DSC, HD95 and ASD were 0.857 ± 0.041, 2.186 ± 0.956, and 0.562 ± 0.194 mm, respectively. The nomogram, which incorporates MR T-stage, CEA, CA19-9, and Radscore, exhibited a higher area under the ROC curve (AUC) compared to the Radscore and subjective evaluation in the training set (0.921 vs. 0.903 vs. 0.662). Similarly, in both external validation sets, the nomogram demonstrated a higher AUC than the Radscore and subjective evaluation (0.908 vs. 0.735 vs. 0.640, and 0.884 vs. 0.802 vs. 0.734). The application of the deep learning method enables efficient automatic segmentation. The clinical-radiomics nomogram, utilizing preoperative MRI and automatic segmentation, proves to be an accurate method for assessing LNM in RC. This approach has the potential to enhance clinical decision-making and improve patient care. Research registry, identifier 9158, https://www.researchregistry.com/browse-the-registry#home/registrationdetails/648e813efffa4e0028022796/.

UNesT: Local spatial representation learning with hierarchical transformer for efficient medical segmentation.

Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis. Transformer reformats the image into separate patches and realizes global communication via the self-attention mechanism. However, positional information between patches is hard to preserve in such 1D sequences, and loss of it can lead to sub-optimal performance when dealing with large amounts of heterogeneous tissues of various sizes in 3D medical image segmentation. Additionally, current methods are not robust and efficient for heavy-duty medical segmentation tasks such as predicting a large number of tissue classes or modeling globally inter-connected tissue structures. To address such challenges and inspired by the nested hierarchical structures in vision transformer, we proposed a novel 3D medical image segmentation method (UNesT), employing a simplified and faster-converging transformer encoder design that achieves local communication among spatially adjacent patch sequences by aggregating them hierarchically. We extensively validate our method on multiple challenging datasets, consisting of multiple modalities, anatomies, and a wide range of tissue classes, including 133 structures in the brain, 14 organs in the abdomen, 4 hierarchical components in the kidneys, inter-connected kidney tumors and brain tumors. We show that UNesT consistently achieves state-of-the-art performance and evaluate its generalizability and data efficiency. Particularly, the model achieves whole brain segmentation task complete ROI with 133 tissue classes in a single network, outperforming prior state-of-the-art method SLANT27 ensembled with 27 networks. Our model performance increases the mean DSC score of the publicly available Colin and CANDI dataset from 0.7264 to 0.7444 and from 0.6968 to 0.7025, respectively. Code, pre-trained models, and use case pipeline are available at: https://github.com/MASILab/UNesT.

Cross-layer connected network with adaptive attention mechanism for 3D multi-organ and tumor segmentations from CT

3D medical image segmentation is one of the most important and challenging tasks for medical image analysis. To enhance the feature extraction ability of 3D convolutional neural networks (CNN) and improve the segmentation accuracy on small tumors, this paper presents a cross-layer connected network with an adaptive attention mechanism to achieve efficient segmentations for 3D multi-organ and tumor from CT. A cross layer connection is proposed to utilize features more effectively by reusing multiple layers of semantic information while recovering spatial information. The pre-activation Residual Block and Squeeze-and-Excitation (SE) block are introduced to enhance the feature extraction ability. Due to the serious class imbalance problem caused by small tumors, the training process of the 3D CNN model is unstable and small targets are difficult to segment. To relieve the training instability problem, Anti-Aliased Pooling (AAP) is introduced to replace the original maxpooling. Moreover, a region of interest (ROI) adaptive attention mechanism based on the auxiliary loss function is developed to improve the segmentation accuracy on small target tumors by combining the target detection method with semantic segmentation models. Extensive experiments show that the dice coefficient of 3D liver tumor segmentation on the LiTS dataset reaches 0.668 by using our designed network, and the experiments on the BRATS dataset for 3D brain tumor segmentation yield average dice coefficient, sensitivity, and Hausdorff distance of 0.706, 0.730, and 5.972 mm, respectively, which are obviously superior to some existing methods.

Segmentation of hard exudate lesions in color fundus image using two-stage CNN-based methods

The presence of hard exudate (EX) lesions is an early clinical symptom of Diabetic Retinopathy (DR); its accurate segmentation is essential for diagnosis and treatment. Automatic segmentation of EX lesions is challenging because they have a wide range of sizes, shapes, and brightness, and can be confused with soft exudate lesions. In this paper, we present and assess an efficient segmentation method for interactively segmenting EX lesions in fundus images from DR patients. Our approach consisted of two main stages: (1) the first stage generates an automatic segmentation using a CNN-based method. (2) If the obtained segmentation is suboptimal, the second stage is used to refine each inaccurately segmented region using a CNN-based interactive segmentation method. To train and evaluate method performance, we used two public datasets (IDRiD and DDR) and two local datasets from two medical centers (EHos and EWT) containing a wide range of EX lesions. Several state-of-the art CNN-based models and the proposed method were trained and evaluated on IDRiD, DDR and EHos datasets using the area under the precision–recall curve (AUPR), the dice similarity coefficient (Dice) and the intersection over union (IoU). In addition, EWT dataset was used to evaluate the methods without retraining the CNN models. The evaluation results using IDRiD dataset showed that the proposed method achieved AUPR, mean Dice and mean IoU scores of 0.893, 76.6% and 62.4%, respectively, which are comparable to the state-of-the-art method on EX segmentation. When evaluated on the DDR dataset with large portion of small EX lesions, the proposed method achieved AUPR, mean Dice and mean IoU scores of 0.693, 60.8% and 45.5%, yielding state-of-the-art performance. Furthermore, with the main evaluation metric being AUPR, the evaluation results on two datasets, EHos and ETW, with scores of 0.689 and 0.667 demonstrated superiority of the proposed method over the other segmentation methods. The proposed two-stage CNN-based segmentation method is an useful approach for accurately segmenting EX lesions in color fundus images, enabling lesion quantification to aid experts in treating patients with DR. The source code, the trained CNN models and the data are publicly available at: https://github.com/dvquang2000/Interactive_HardExudates_Segmentation.