Towards Accurate Medical Image Segmentation With Gradient-Optimized Dice Loss

Accurate segmentation of medical images is crucial for disease diagnosis and understanding disease changes. Deep learning methods, utilizing encoder-decoder structures, have demonstrated cutting-edge performance in various medical image segmentation tasks. However, the pooling operation in the encoding stage results in feature loss, which makes the network lack the ability to fuse multi-scale information at different levels, hinders its effective perception of multi-scale information, and leads to poor segmentation performance. Drawing inspiration from the U-shaped network, this study introduces a multi-branch feature hybrid attention and adaptive receptive field network (MFHARFNet) for medical image segmentation. Building upon the encoder-decoder framework, we initially devise a multi-branch feature hybrid attention module (MFHAM) to seamlessly integrate feature maps of varying scales, capturing both fine-grained features and coarse-grained semantics across the entire scale. Furthermore, we redesign the skip connection to amalgamate feature information from different branches in the encoder stage and efficiently transmit it to the decoder, providing the decoder with global context feature maps at different levels. Finally, the adaptive receptive field (ARF) module is introduced in the decoder feature reconstruction stage to adapt and focus on related fields, ensuring the model’s adaptation to different segmentation target features, and achieving different weights for the output of different convolution kernels to improve segmentation performance. We comprehensively evaluate our method on medical image segmentation tasks, by using four public datasets across CT and MRI. Remarkably, MFHARFNet method consistently outperforms other state-of-the-art methods, exceeding UNet by 2.1%, 0.9%, 6.6% and 1.0% on Dice on ATLAS, LiTs, BraTs2019 and Spine and intervertebral disc datasets, respectively. In addition, MFHARFNet minimizes network parameters and computational complexity as much as possible. The source codes are in https://github.com/OneHundred99/MFHARFNet.

Introduction: Precise segmentation of the liver from computed tomography (CT) scans is an essential component in the diagnosis and treatment of liver diseases such as hepatocellular carcinoma. Manual segmentation can be time-consuming and subject to variability, spurring the application of automated systems based on deep learning. We introduce a 3D U-Net-based convolutional neural network for end-to-end segmentation of the liver from volumetric CT images. The model is trained and tested on the LiTS dataset using a standard preprocessing pipeline and an in-house composite loss function—AdvancedComboLoss—combining Dice Loss, Binary Cross-Entropy, and Focal Tversky Loss to balance class imbalance and boundary accuracy. The network handles entire 3D volumes with spatial context retained between anatomical planes and is trained on a GPU-enabled setup with the PyTorch environment. Objectives: To develop a highly accurate and computationally efficient 3D U-Net-based deep learning model for automated liver segmentation from volumetric CT scans, addressing challenges like class imbalance, anatomical variability, and low tissue contrast, using a custom loss function (AdvancedComboLoss) and a standardized preprocessing pipeline. Methods: The methodology adopted is volumetric liver segmentation from a specially designed 3D U-Net architecture specific to medical CT scans. The process entails preprocessing of raw CT scans into a common shape and intensity range and training a fully convolutional 3D neural network that learns the spatial relationships among all three anatomical planes. The model uses an encoder-decoder architecture with skip connections to maintain fine-grained structural information, allowing for accurate delineation of liver regions. A hybrid loss function—integrating Dice, Binary Cross-Entropy, and Focal Tversky losses—is used to direct the learning process to optimize overlap of regions, accuracy of classification, and class imbalance. Results: Experimental outcomes demonstrate that the model has a Dice score of 0.9604 and voxel-wise accuracy of 0.9979, indicating excellent performance in segmentation as well as strong agreement with expert annotations. The model presented in this paper presents a solid, scalable, and clinically valuable approach to automated liver segmentation with future potential to integrate into multi-stage liver and tumor analysis workflows. Conclusions: Herein, we built and tested a 3D U-Net deep learning architecture for unsupervised liver segmentation from abdominal CT volumes. Through utilization of volumetric convolutions as well as through a well-engineered composite loss function, the model was successful in capturing complicated liver anatomy as well as being able to hold high performance even on varied CT volumes. The power of the method is not just in its quantitative performance but also in its capability to generate anatomically consistent and visually plausible segmentations, making it extremely relevant to actual clinical workflows. Although there are some limitations—constrained batch size and absence of data augmentation—there is room for improvement, the findings affirm that deep learning can be an effective tool for automating key tasks in medical image analysis. As a whole, this paper adds a robust and effective segmentation model that would be potentially embedded in wider diagnostic workflows, ending up improving the accuracy, speed, and scalability of liver evaluation in clinical practice. In brief, this paper adds a high-fidelity, scalable, and computationally effective solution for computer-aided liver segmentation, pushing the application of artificial intelligence in clinical decision-making and medical image analysis.

The imperative development of point-of-care diagnosis for accurate and rapid medical image segmentation, has become increasingly urgent in recent years. Although some pioneering work has applied complex modules to improve segmentation performance, resulting models are often heavy, which is not practical for the modern clinical setting of point-of-care diagnosis. To address these challenges, we propose UltraNet, a state-of-the-art lightweight model that achieves competitive performance in segmenting multiple parts of medical images with the lowest parameters and computational complexity. To extract a sufficient amount of feature information and replace cumbersome modules, the Shallow Focus Float Block (ShalFoFo) and the Dual-stream Synergy Feature Extraction (DuSem) are respectively proposed at both shallow and deep levels. ShalFoFo is designed to capture finer-grained features containing more pixels, while DuSem is capable of extracting distinct deep semantic features from two different perspectives. By jointly utilizing them, the accuracy and stability of UltraNet segmentation results are enhanced. To evaluate performance, UltraNet's generalization ability was assessed on five datasets with different tasks. Compared to UNet, UltraNet reduces the parameters and computational complexity by 46 times and 26 times, respectively. Experimental results demonstrate that UltraNet achieves a state-of-the-art balance among parameters, computational complexity, and segmentation performance. Codes are available at https://github.com/Ziii1/UltraNet .

A novel method for tackling the problem of imbalanced data in medical image segmentation is proposed in this work. In Balanced Cross Entropy (BCE) loss, which is a type of weighted CE loss, the weight assigned to each class is the inverse of the class frequency. These balancing weights are expected to equalize the effect of each class on the overall loss and prevent the model from being biased towards the majority class. But, as it has been shown in previous studies, this method degrades the performance by a large margin. Therefore, Balanced CE is not a popular loss in medical segmentation tasks, and usually a region-based loss, like the Dice loss, is used to address the class imbalance problem. Existing weighting CE loss approaches, like Balanced CE, are usually adapted from classification tasks. In this study we propose a weighting method which is designed for segmentation and takes advantage of spatial and geometrical properties of the labels. In the proposed method, the weighting of cross entropy loss for each class is based on a dilated area of each class mask, and balancing weights are assigned to each class together with its surrounding pixels. The goal of this study is to show that the performance of Balanced CE loss can be greatly improved my modifying its weighting strategy. Experiments on different datasets show that the proposed Dilated Balanced CE (DBCE) loss outperforms the Balanced CE loss by a large margin and produces superior results compared to CE loss, and its performance is similar or better compared to the performance of the combination of Dice and CE loss. Also, the performance of different combination losses can be improved by replacing the CE loss with the proposed DBCE loss. This study shows that a weighted cross entropy loss with the right weighing strategy can be as effective as a region-based loss in handling the class imbalance problem.

Automatic and accurate segmentation of medical images plays an essential role in disease diagnosis and treatment planning. Convolution neural networks have achieved remarkable results in medical image segmentation in the past decade. Meanwhile, deep learning models based on Transformer architecture also succeeded tremendously in this domain. However, due to the ambiguity of the medical image boundary and the high complexity of physical organization structures, implementing effective structure extraction and accurate segmentation remains a problem requiring a solution. In this paper, we propose a novel Dual Encoder Network named DECTNet to alleviate this problem. Specifically, the DECTNet embraces four components, which are a convolution-based encoder, a Transformer-based encoder, a feature fusion decoder, and a deep supervision module. The convolutional structure encoder can extract fine spatial contextual details in images. Meanwhile, the Transformer structure encoder is designed using a hierarchical Swin Transformer architecture to model global contextual information. The novel feature fusion decoder integrates the multi-scale representation from two encoders and selects features that focus on segmentation tasks by channel attention mechanism. Further, a deep supervision module is used to accelerate the convergence of the proposed method. Extensive experiments demonstrate that, compared to the other seven models, the proposed method achieves state-of-the-art results on four segmentation tasks: skin lesion segmentation, polyp segmentation, Covid-19 lesion segmentation, and MRI cardiac segmentation.

Objective. Although convolutional neural networks (CNN) and Transformers have performed well in many medical image segmentation tasks, they rely on large amounts of labeled data for training. The annotation of medical image data is expensive and time-consuming, so it is common to use semi-supervised learning methods that use a small amount of labeled data and a large amount of unlabeled data to improve the performance of medical imaging segmentation. Approach. This work aims to enhance the segmentation performance of medical images using a triple-teacher cross-learning semi-supervised medical image segmentation with shape perception and multi-scale consistency regularization. To effectively leverage the information from unlabeled data, we design a multi-scale semi-supervised method for three-teacher cross-learning based on shape perception, called Semi-TMS. The three teacher models engage in cross-learning with each other, where Teacher A and Teacher C utilize a CNN architecture, while Teacher B employs a transformer model. The cross-learning module consisting of Teacher A and Teacher C captures local and global information, generates pseudo-labels, and performs cross-learning using prediction results. Multi-scale consistency regularization is applied separately to the CNN and Transformer to improve accuracy. Furthermore, the low uncertainty output probabilities from Teacher A or Teacher C are utilized as input to Teacher B, enhancing the utilization of prior knowledge and overall segmentation robustness. Main results. Experimental evaluations on two public datasets demonstrate that the proposed method outperforms some existing semi-segmentation models, implicitly capturing shape information and effectively improving the utilization and accuracy of unlabeled data through multi-scale consistency. Significance. With the widespread utilization of medical imaging in clinical diagnosis, our method is expected to be a potential auxiliary tool, assisting clinicians and medical researchers in their diagnoses.

Medical image segmentation is a fundamental task in medical image analysis, playing a crucial role in disease diagnosis, treatment planning, and clinical decision-making. Accurate segmentation of anatomical structures, such as blood vessels, organs, and lesions, is essential for reliable medical interpretations. However, existing segmentation models often face challenges in effectively capturing both local and global features within medical images. Traditional convolutional neural networks (CNNs) excel at extracting fine-grained local features but struggle to model long-range dependencies due to their limited receptive fields. Conversely, transformer-based models can capture global contextual relationships but often fail to preserve detailed local structures, leading to suboptimal segmentation performance. The purpose of this study is to develop SEFormer, a novel hybrid network that integrates SENet, ResNet, and Transformer to enhance medical image segmentation. SEFormer aims to effectively capture both local and global features, addressing the limitations of traditional CNNs and transformer-based models.SENet is incorporated to recalibrate feature maps by adaptively emphasizing informative features, thereby compensating for the global representation limitations of CNNs. Meanwhile, the ResNet backbone ensures deep feature extraction while maintaining computational efficiency. Additionally, the Transformer module is introduced to capture long-range dependencies and enhance contextual awareness, complementing the local feature extraction capabilities of CNNs. This hybrid approach allows SEFormer to balance fine-grained spatial details with broader contextual information, leading to more precise segmentation results.Furthermore, to mitigate information loss during feature extraction and ensure a more complete and hierarchical representation of image information, we introduce a feature pyramid structure inspired by multi-scale image pyramid models. By progressively increasing the receptive field across different scales and employing skip connections, SEFormer effectively fuses multi-scale local and global features at each stage of the pyramid. This hierarchical fusion mechanism ensures a richer and more robust feature representation, which is particularly beneficial for segmenting complex medical structures such as blood vessels. We evaluate SEFormer on the CHASE_DB1 dataset, a widely used benchmark for retinal vessel segmentation. Experimental results demonstrate that SEFormer outperforms existing state-of-the-art segmentation methods, achieving a 3.25% improvement in segmentation accuracy. Additionally, we conduct ablation studies to verify the contributions of different components within SEFormer. The results show that incorporating SENet enhances feature recalibration and channel attention, while the Transformer module significantly improves global context awareness. The feature pyramid structure further contributes to performance gains by ensuring a multi-scale representation of vascular structures. Compared to conventional CNN-based methods, our approach achieves better segmentation accuracy with improved robustness to variations in vessel thickness, noise, and image contrast. Furthermore, SEFormer maintains computational efficiency, making it suitable for real-world clinical applications where both accuracy and processing speed are critical. SEFormer provides an efficient and accurate approach for medical image segmentation by leveraging the complementary strengths of CNNs, SENet, and Transformers while integrating a feature pyramid structure to maximize feature representation. Future research directions include extending SEFormer to other medical imaging modalities, such as CT and MRI scans, as well as exploring further optimization techniques to reduce computational costs while maintaining high segmentation performance. Additionally, integrating SEFormer with active learning frameworks could further improve segmentation performance by leveraging expert-annotated data more efficiently.

We propose a generalized focal loss function based on the Tversky index to address the issue of data imbalance in medical image segmentation. Compared to the commonly used Dice loss, our loss function achieves a better trade off between precision and recall when training on small structures such as lesions. To evaluate our loss function, we improve the attention U-Net model by incorporating an image pyramid to preserve contextual features. We experiment on the BUS 2017 dataset and ISIC 2018 dataset where lesions occupy 4.84% and 21.4% of the images area and improve segmentation accuracy when compared to the standard U-Net by 25.7% and 3.6%, respectively.

Improving domain generalization performance for medical image segmentation via random feature augmentation.

The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, the existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD directly. We propose three methods to estimate HD from the segmentation probability map produced by a CNN. One method makes use of the distance transform of the segmentation boundary. Another method is based on applying morphological erosion on the difference between the true and estimated segmentation maps. The third method works by applying circular/spherical convolution kernels of different radii on the segmentation probability maps. Based on these three methods for estimating HD, we suggest three loss functions that can be used for training to reduce HD. We use these loss functions to train CNNs for segmentation of the prostate, liver, and pancreas in ultrasound, magnetic resonance, and computed tomography images and compare the results with commonly-used loss functions. Our results show that the proposed loss functions can lead to approximately 18-45% reduction in HD without degrading other segmentation performance criteria such as the Dice similarity coefficient. The proposed loss functions can be used for training medical image segmentation methods in order to reduce the large segmentation errors.

Medical image segmentation is a critical application of computer vision in the analysis of medical images. Its primary objective is to isolate regions of interest in medical images from the background, thereby assisting clinicians in accurately identifying lesions, their sizes, locations, and their relationships with surrounding tissues. However, compared to natural images, medical images present unique challenges, such as low resolution, poor contrast, inconsistency, and scattered target regions. Furthermore, the accuracy and stability of segmentation results are subject to more stringent requirements. In recent years, with the widespread application of Convolutional Neural Networks (CNNs) in computer vision, deep learning-based methods for medical image segmentation have become a focal point of research. This paper categorizes, reviews, and summarizes the current representative methods and research status in the field of medical image segmentation. A comparative analysis of relevant experiments is presented, along with an introduction to commonly used public datasets, performance evaluation metrics, and loss functions in medical image segmentation. Finally, potential future research directions and development trends in this field are predicted and analyzed.

Internet of Things (IoT) brings telemedicine a new chance. This enables the specialist to consult the patient’s condition despite the fact that they are in different places. Medical image segmentation is needed for analysis, storage, and protection of medical image in telemedicine. Therefore, a variety of methods have been researched for fast and accurate medical image segmentation. Performing segmentation in various organs, the accurate judgment of the region is needed in medical image. However, the removal of region occurs by the lack of information to determine the region in a small region. In this paper, we researched how to reconstruct segmentation region in a small region in order to improve the segmentation results. We generated predicted segmentation of slices using volume data with linear equation and proposed improvement method for small regions using the predicted segmentation. In order to verify the performance of the proposed method, lung region by chest CT images was segmented. As a result of experiments, volume data segmentation accuracy rose from 0.978 to 0.981 and from 0.281 to 0.187 with a standard deviation improvement confirmed.

MP-FocalUNet: Multiscale parallel focal self-attention U-Net for medical image segmentation.

Aim: Brain tumors are among the most fatal cancers worldwide. Diagnosing and manually segmenting tumors are time-consuming clinical tasks, and success strongly depends on the doctor's experience. Automatic quantitative analysis and accurate segmentation of brain tumors are greatly needed for cancer diagnosis.Methods:This paper presents an advanced three-dimensional multimodal segmentation algorithm called nested dilation networks (NDNs). It is inspired by the U-Net architecture, a convolutional neural network (CNN) developed for biomedical image segmentation and is modified to achieve better performance for brain tumor segmentation. Thus, we propose residual blocks nested with dilations (RnD) in the encoding part to enrich the low-level features and use squeeze-and-excitation (SE) blocks in both the encoding and decoding parts to boost significant features. To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks. Different loss functions are considered to cope with class imbalance problems to maximize the brain tumor segmentation results. A cascade training strategy is employed to run NDNs for coarse-to-fine tumor segmentation. This strategy decomposes the multiclass segmentation problem into three binary segmentation problems and trains each task sequentially. Various augmentation techniques are utilized to increase the diversity of the data to avoid overfitting.Results: This approach achieves Dice similarity scores of 0.6652, 0.5880, and 0.6682 for edema, non-enhancing tumors, and enhancing tumors, respectively, in which the Dice loss is used for single-pass training. After cascade training, the Dice similarity scores rise to 0.7043, 0.5889, and 0.7206, respectively.Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation. Moreover, applying cascade training to NDNs facilitates better performance than other methods. The findings of this study provide considerable insight into the automatic and accurate segmentation of brain tumors.

Medical image segmentation is crucial for improving healthcare outcomes. Convolutional neural networks (CNNs) have been widely applied in medical image analysis; however, their inherent inductive biases limit their ability to capture global contextual information. Vision transformer (ViT) architectures address this limitation by leveraging attention mechanisms to model global relationships; however, they typically require large-scale datasets for effective training, which is challenging in the field of medical imaging due to limited data availability. This study aimed to integrate the advantages of CNN and ViT architectures to improve segmentation performance on small-scale medical image datasets. In this study, we established a U-shaped network architecture based on a Transformer-assisted convolutional neural network (TAC-UNet). The TAC-UNet is primarily composed of a hybrid structure integrating CNN and Transformer components. Specifically, the hybrid architecture follows a dual-path design in which the Transformer branch continuously conveys global contextual information to the CNN backbone. This allows the CNN backbone to enhance its global perception while building on the local features it extracts, thereby improving its ability to comprehend complex image structures. A channel cross-attention (CCA) module is also incorporated as a bridge between the encoder and decoder to better reconcile the semantic discrepancies between them. Detailed experiments on three public datasets were conducted. Specifically, our model was trained on 30 images from the Multi-organ Nucleus Segmentation (MoNuSeg) training dataset, 85 images from the Gland Segmentation (GlaS) training dataset, and 551 images from the Computer Vision Center Colorectal Cancer-Clinic Database (CVC-ClinicDB) dataset. We evaluated the performance of our model on the corresponding test sets. Our TAC-UNet achieved the best Dice scores (80.36%, 90.70%, and 91.81% on the MoNuSeg, GlaS, and CVC-ClinicDB datasets, respectively) of all the models. Compared to other CNN-based, Transformer-based, and hybrid methods, the TAC-UNet demonstrated significantly superior segmentation performance. Our TAC-UNet model showed advanced segmentation performance on small-scale medical image datasets. The detailed experimental results showed the effectiveness of the method. Our model's code is available at: https://github.com/hejlhello/TAC-UNet.