Search

The ongoing COVID-19 pandemic caused by the SARS-CoV-2 virus has already resulted in 6.6 million deaths with more than 637 million people infected after only 30 months since the first occurrences of the disease in December 2019. Hence, rapid and accurate detection and diagnosis of the disease is the first priority all over the world. Researchers have been working on various methods for COVID-19 detection and as the disease infects lungs, lung image analysis has become a popular research area for detecting the presence of the disease. Medical images from chest X-rays (CXR), computed tomography (CT) images, and lung ultrasound images have been used by automated image analysis systems in artificial intelligence (AI)- and machine learning (ML)-based approaches. Various existing and novel ML, deep learning (DL), transfer learning (TL), and hybrid models have been applied for detecting and classifying COVID-19, segmentation of infected regions, assessing the severity, and tracking patient progress from medical images of COVID-19 patients. In this paper, a comprehensive review of some recent approaches on COVID-19-based image analyses is provided surveying the contributions of existing research efforts, the available image datasets, and the performance metrics used in recent works. The challenges and future research scopes to address the progress of the fight against COVID-19 from the AI perspective are also discussed. The main objective of this paper is therefore to provide a summary of the research works done in COVID detection and analysis from medical image datasets using ML, DL, and TL models by analyzing their novelty and efficiency while mentioning other COVID-19-based review/survey researches to deliver a brief overview on the maximum amount of information on COVID-19-based existing researches. [ABSTRACT FROM AUTHOR]

Advancements in clinical treatment are increasingly constrained by the limitations of supervised learning techniques, which depend heavily on large volumes of annotated data. The annotation process is not only costly but also demands substantial time from clinical specialists. Addressing this issue, we introduce the S4MI (Self-Supervision and Semi-Supervision for Medical Imaging) pipeline, a novel approach that leverages advancements in self-supervised and semi-supervised learning. These techniques engage in auxiliary tasks that do not require labeling, thus simplifying the scaling of machine supervision compared to fully-supervised methods. Our study benchmarks these techniques on three distinct medical imaging datasets to evaluate their effectiveness in classification and segmentation tasks. Notably, we observed that self-supervised learning significantly surpassed the performance of supervised methods in the classification of all evaluated datasets. Remarkably, the semi-supervised approach demonstrated superior outcomes in segmentation, outperforming fully-supervised methods while using 50% fewer labels across all datasets. In line with our commitment to contributing to the scientific community, we have made the S4MI code openly accessible, allowing for broader application and further development of these methods. The code can be accessed at https://github.com/pranavsinghps1/S4MI. [ABSTRACT FROM AUTHOR]

Early intervention in tumors can greatly improve human survival rates. With the development of deep learning technology, automatic image segmentation has taken a prominent role in the field of medical image analysis. Manually segmenting kidneys on CT images is a tedious task, and due to the diversity of these images and varying technical skills of professionals, segmentation results can be inconsistent. To address this problem, a novel ASD-Net network is proposed in this paper for kidney and kidney tumor segmentation tasks. First, the proposed network employs newly designed Adaptive Spatial-channel Convolution Optimization (ASCO) blocks to capture anisotropic information in the images. Then, other newly designed blocks, i.e., Dense Dilated Enhancement Convolution (DDEC) blocks, are utilized to enhance feature propagation and reuse it across the network, thereby improving its segmentation accuracy. To allow the network to segment complex and small kidney tumors more effectively, the Atrous Spatial Pyramid Pooling (ASPP) module is incorporated in its middle layer. With its generalized pyramid feature, this module enables the network to better capture and understand context information at various scales within the images. In addition to this, the concurrent spatial and channel squeeze & excitation (scSE) attention mechanism is adopted to better comprehend and manage context information in the images. Additional encoding layers are also added to the base (U-Net) and connected to the original encoding layer through skip connections. The resultant enhanced U-Net structure allows for better extraction and merging of high-level and low-level features, further boosting the network's ability to restore segmentation details. In addition, the combined Binary Cross Entropy (BCE)-Dice loss is utilized as the network's loss function. Experiments, conducted on the KiTS19 dataset, demonstrate that the proposed ASD-Net network outperforms the existing segmentation networks according to all evaluation metrics used, except for recall in the case of kidney tumor segmentation, where it takes the second place after Attention-UNet. [ABSTRACT FROM AUTHOR]

One of the most important areas in medical image analysis is segmentation, in which raw image data is partitioned into structured and meaningful regions to gain further insights. By using Deep Neural Networks (DNN), AI-based automated segmentation algorithms can potentially assist physicians with more effective imaging-based diagnoses. However, since it is difficult to acquire high-quality ground truths for medical images and DNN hyperparameters require significant manual tuning, the results by DNN-based medical models might be limited. A potential solution is to combine multiple DNN models using ensemble learning. We propose a two-layer ensemble of deep learning models in which the prediction of each training image pixel made by each model in the first layer is used as the augmented data of the training image for the second layer of the ensemble. The prediction of the second layer is then combined by using a weight-based scheme which is found by solving linear regression problems. To the best of our knowledge, our paper is the first work which proposes a two-layer ensemble of deep learning models with an augmented data technique in medical image segmentation. Experiments conducted on five different medical image datasets for diverse segmentation tasks show that proposed method achieves better results in terms of several performance metrics compared to some well-known benchmark algorithms. Our proposed two-layer ensemble of deep learning models for segmentation of medical images shows effectiveness compared to several benchmark algorithms. The research can be expanded in several directions like image classification. [ABSTRACT FROM AUTHOR]

Medical image segmentation is a crucial task in many clinical applications, such as tumor detection and surgical planning. However, the annotation process for medical images is often both time-consuming and expensive, which requires professional knowledge and experience. This study aims to develop a medical image segmentation method based on semi-supervised learning, which can improve the performance of segmentation by effectively using labeled data and unlabeled data. We proposed a novel multi-task semi-supervised method based on multi-branch cross pseudo supervision, called MS2MPS, which can efficiently utilize unlabeled data for semi-supervised medical image segmentation. The proposed method consists of two multi-task backbone networks with multiple output branches, which were used to simultaneously generate segmentation probability maps (SPM) and signed distance maps (SDM) to get more constraints and information. Moreover, a multi-branch cross pseudo supervised (MPS) approach was proposed to promote the high similarity between predictions of the same input image by multiple perturbation networks. Experiments on the public medical image segmentation dataset Automated Cardiac Diagnosis Challenge (ACDC) and Left Atrium (LA) dataset demonstrate that our approach is superior to existing some semi-supervised segmentation methods in terms of Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and Jaccard Similarity Coefficient (JSC). When trained with 10% labeled data, compared to the best results in all compared methods, our approach improved the DSC by 2.63% and 1.54% on the ACDC and LA datasets, increased the JSC by 23.15% and 0.79%, and simultaneously reduced the HD95 by 12.57% and 7.77% on the respective datasets. Our proposed semi-supervised medical image segmentation approach is an effective and practical solution for medical image analysis, particularly in scenarios where labeled data is limited or expensive. [ABSTRACT FROM AUTHOR]

Semantic segmentation is a fundamental step in image understanding, playing a crucial role in the fields of automatic driving, medical image analysis, defect detection, etc. Despite significant progress in deep learning-based image segmentation, challenges in terms of accuracy and efficiency still exist, especially for small-scale objects. In this paper, we present a novel data augmentation method for small-scale objects in images, aiming to address the issue of class imbalance. Specifically, we extract small-scale objects from one image and then copy-scale-and-paste them to other images. Additionally, a novel multi-scale feature fusion module is proposed to effectively combine features from both deep and shallow neural network layers. Subsequently, the data augmentation method and multi-scale feature fusion module are utilized in the proposed Fast-SegNet architecture for semantic segmentation. Extensive experiments demonstrate that Fast-SegNet could improve segmentation performance, especially for small-scale objects with an acceptable computational cost. State-of-the-art performance has been achieved on CamVid, CityScapes, and MOST (Micro-optical sectioning tomography) datasets with respect to the tradeoff between accuracy and speed. Specifically, the CamVid dataset yields mean IoU (Intersection over Union) values of 45.7% and 38.6% for small-scale objects as Pedestrian and Bicyclist, respectively. The CityScapes dataset demonstrates mean IoU of 43.43% and 43.56% for small-scale objects as Traffic Light and Rider, respectively. The MOST dataset results in a segmentation mean IoU of 88.2% for vessels in the mouse brain. In conclusion, our approach achieves better results in terms of accuracy and efficiency on three datasets. Codes are available at https://github.com/apple1986/Fast-SegNet. [ABSTRACT FROM AUTHOR]

Due to the fast development of medical imaging technologies, medical image analysis has entered the period of big data for proper disease diagnosis. At the same time, intracerebral hemorrhage (ICH) becomes a serious disease which affects the injury of blood vessels in the brain regions. This paper presents an artificial intelligence and big data analytics-based ICH e-diagnosis (AIBDA-ICH) model using CT images. The presented model utilizes IoMT devices for data acquisition process. The presented AIBDA-ICH model involves graph cut-based segmentation model for identifying the affected regions in the CT images. To manage big data, Hadoop Ecosystem and its elements are mainly used. In addition, capsule network (CapsNet) model is applied as a feature extractor to derive a useful set of feature vectors. Finally, the presented AIBDA-ICH model makes use of the fuzzy deep neural network (FDNN) model to carry out classification process. For validating the superior performance of the AIBDA-ICH method, an extensive set of simulations were performed and the outcomes are examined under diverse aspects. The experimental values pointed out the improved e-diagnostic performance of the AIBDA-ICH model over the other compared methods with the precision and accuracy of 94.96% and 98.59%, respectively. [ABSTRACT FROM AUTHOR]

Artificial intelligence has captivated the healthcare industry as these techniques are efficient and accurate in medical image analysis. In recent years, several deep learning models have been proposed for the task of 2D or 3D bio-medical image segmentation. Liver tumour segmentation in Computed Tomography (CT) images remains an arduous problem due to the tumour's shape variance, its occurrence in multiple regions and the granular noise of the CT images. In this paper, a novel Convolutional Encoder-Decoder Residual Neural Network (CEDRNN) is proposed for automatic liver tumour segmentation from CT images. The feature accumulation using additive skip connections in the proposed model assures better learning of the model and faster convergence during training. A public dataset (3DIRCADb) was used to train and test the proposed model. The 3DIRCADb dataset is considered challenging to use because it contains a greater variety and complexity of livers and tumours. The CT slices were subjected to pre-processing steps such as Hounsfield windowing and Gaussian filtering. The proposed model has resulted in an average DICE score of 95.2% for liver tumour segmentation. The task of tumour segmentation is done precisely without the need for prior liver segmentation in the CT image. Despite having 85 layers in its architecture, CEDRNN outperforms comparable models with only 0.6 million network parameters. The experimental results proved that the proposed model is more efficient for liver tumour segmentation as compared to the related existing approaches. The automatic segmentation of the tumour is essential for the clinical interpretation and diagnosis of liver-related problems. [ABSTRACT FROM AUTHOR]

Optical Coherence Tomography (OCT) is a non-invasive and newly-developing technique to image human retina and choroid. Many ocular diseases such as pathological myopia and Age-related Macular Degeneration (AMD) are related to the morphological changes of the choroid. Consequently, the automatic choroid segmentation becomes an important step to the examination and diagnosis of those choroid-related diseases. However, there are still challenges such as the inseparability of the histogram between the choroid and sclera boundaries and the inconsistency of the choroid layer texture and intensity. To solve those challenges, we propose a Context Efficient Adaptive network (CEA-Net) that includes a module of Efficient Channel Attention (ECA), a novel block called adaptive morphological refinement (AMR) and a new loss function called Choroidal Convex Boundary (CCB) regularization. The Adaptive Morphological Refinement (AMR) block is designed to avoid the segmentation of discrete subtle objects in choroid. The new Choroidal Convex Boundary (CCB) loss is proposed to refine the segmented choroidal boundaries. The proposed method is applied to two OCT datasets acquired from two different manufacturers respectively in order to evaluate its effectiveness. The results show that the AMR block and CCB loss function enable the deep network to obtain more accurate choroid segmentations. In addition, for the first time in the field of medical image analysis, we construct a dedicated OCT choroid layer segmentation dataset (OCHID), which consists of 640 OCT images with choroidal boundaries annotations. This dataset is available for public use to assist community researchers in their research on related topics. [ABSTRACT FROM AUTHOR]

Image segmentation lays the foundation for many high-stakes vision applications such as autonomous driving and medical image analysis. It is, therefore, of great importance to not only improve the accuracy of segmentation models on well-established benchmarks, but also enhance their robustness in the real world so as to avoid sparse but fatal failures. In this paper, instead of chasing state-of-the-art performance on existing benchmarks, we turn our attention to a new challenging problem: how to efficiently expose failures of "top-performing" segmentation models in the real world and how to leverage such counterexamples to rectify the models. To achieve this with minimal human labelling effort, we first automatically sample a small set of images that are likely to falsify the target model from a large corpus of web images via the maximum discrepancy competition principle. We then propose a weakly labelling strategy to further reduce the number of false positives, before time-consuming pixel-level labelling by humans. Finally, we fine-tune the model to harness the identified failures, and repeat the whole process, resulting in an efficient and progressive framework for troubleshooting segmentation models. We demonstrate the feasibility of our framework using the semantic segmentation task in PASCAL VOC, and find that the fine-tuned model exhibits significantly improved generalization when applied to real-world images with greater content diversity. The code is available at https://github.com/VITA-Group/Troubleshooting_Image_Segmentation. [ABSTRACT FROM AUTHOR]

The research work intends to segregate the lungs area of interest, especially removing the ribs from the X-Ray images for future image analysis and interpretation. The storage and processing of medical data irrespective of the physical location of lab are explored in this research with Cloud computing. Extracting valid information from a medical image is of high importance in the medical arena. The information loss may lead to the misinterpretation of medical image analysis, which in turn can affect the treatment process to be prolonged or can be deviated from the real phase of examination. Evaluating the entropy from the medical images using the multi-level segmentation using the differential evolution technique on the fuzzy parameters applied on the chest X-ray images resulted in the extraction of the rib cages from the image, thus producing an image with the region of lung alone for the diagnostic purposes. The quality of the information obtained has been evaluated based upon the entropic value. The multi-level segmentation applied on the chest X-ray images using the differential evolution accelerated the optimum fuzzy parameters for the multi-level segmentation. The multi-level algorithmic approach with 4 threshold levels applied had resulted in four different thresholding, out of which the optimum threshold value has been chosen by the algorithm to provide the output. The results thus obtained, outperformed the conventional approach of Otsu segmentation and 3-level segmentation. The computational and storage power of cloud added strength to image data processing. The cloud computing facility by Matlab Cloud NVIDIA eased the processing rather than the conventional computing. [ABSTRACT FROM AUTHOR]

The segmentation and estimation of thyroid volume in 3D ultrasound images have attracted the research community's attention because of their great importance in clinical diagnosis. Usually, thyroid volume estimation is based on the segmentation of 3D ultrasound images, which is difficult due to various disorders, including non-homogeneous texture distribution within the thyroid region, artifacts, speckles, and the nature of the thyroid shape. This paper presents an approach to segmenting all individual slices and then reconstructing them into a 3D object to overcome these difficulties. The process involves four techniques. The VOI initialization encompasses the probable thyroid gland; it greatly affects the segmentation results. Multi-gene genetic programming determines the appropriate textural features. The block-matching technique estimates the thyroid gland's change in size and location from slice to slice. Finally, the ITKSNAP software reconstructs the 3D volume. The proposed method is compared with state-of-the-art methods to prove its effectiveness in medical image analysis. Sixteen 3D images from an ultrasound thyroid image dataset were used for the experiments. The analysis of the results based on performance evaluation metrics shows that the proposed method is more efficient than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image segmentation technology has made a remarkable effect in medical image analysis and processing, which is used to help physicians get a more accurate diagnosis. Manual segmentation of the medical image requires a lot of effort by professionals, which is also a subjective task. Therefore, developing an advanced segmentation method is an essential demand. We propose an end-to-end segmentation method for medical images, which mimics physicians delineating a region of interest (ROI) on the medical image in a multi-step manner. This multi-step operation improves the performance from a coarse result to a fine result progressively. In this paper, the segmentation process is formulated as a Markov decision process and solved by a deep reinforcement learning (DRL) algorithm, which trains an agent for segmenting ROI in images. The agent performs a serial action to delineate the ROI. We define the action as a set of continuous parameters. Then, we adopted a DRL algorithm called deep deterministic policy gradient to learn the segmentation model in continuous action space. The experimental result shows that the proposed method has 7.24% improved to the state-of-the-art method on three prostate MR data sets and has 3.52% improved on one retinal fundus image data set. [ABSTRACT FROM AUTHOR]

Generative adversarial networks (GAN) are widely used in medical image analysis tasks, such as medical image segmentation and synthesis. In these works, adversarial learning is directly applied to the original supervised segmentation (synthesis) networks. The usage of adversarial learning is effective in improving visual perception performance since adversarial learning works as realistic regularization for supervised generators. However, the quantitative performance often cannot improve as much as the qualitative performance, and it can even become worse in some cases. In this paper, we explore how we can take better advantage of adversarial learning in supervised segmentation (synthesis) models and propose an adversarial confidence learning framework to better model these problems. We analyze the roles of discriminator in the classic GANs and compare them with those in supervised adversarial systems. Based on this analysis, we propose adversarial confidence learning, i.e., besides the adversarial learning for emphasizing visual perception, we use the confidence information provided by the adversarial network to enhance the design of supervised segmentation (synthesis) network. In particular, we propose using a fully convolutional adversarial network for confidence learning to provide voxel-wise and region-wise confidence information for the segmentation (synthesis) network. With these settings, we propose a difficulty-aware attention mechanism to properly handle hard samples or regions by taking structural information into consideration so that we can better deal with the irregular distribution of medical data. Furthermore, we investigate the loss functions of various GANs and propose using the binary cross entropy loss to train the proposed adversarial system so that we can retain the unlimited modeling capacity of the discriminator. Experimental results on clinical and challenge datasets show that our proposed network can achieve state-of-the-art segmentation (synthesis) accuracy. Further analysis also indicates that adversarial confidence learning can both improve the visual perception performance and the quantitative performance. [ABSTRACT FROM AUTHOR]

Automatic brain tumor segmentation using several image processing techniques supports early diagnosis and provides useful information for treatment planning. However, due to the heterogeneous nature of brain tumor makes the segmentation process very challenging and exhaustive. Glioma is one type of the fast-growing brain tumors. Its shape, size, and location vary across the patients. Manual extraction of exact glioma from brain MRI (Magnetic Resonance Imaging) is very tricky and time-consuming task for the radiologists. U-Net model is one of the most popular deep learning models for biomedical image segmentation utilized by the researchers and scientists around the world. The up-sampling and down-sampling architecture of U-Net model deliver a remarkable result with small amount of data in various medical image analysis applications. This paper presents the effect of different learning parameters on the performance of the deep U-Net model for brain tumor segmentation. Here, we have compared the performance by tuning the different learning parameters such as the activation function, pooling strategies, kernel or filter size, dropout and batch normalization and measured the accuracy in terms of AUC (area under the curve) and F1score. The experiment was performed on two well-known freely data sets available, BraTs 2017 and BraTs 2018. The whole tumor along with its core and enhancing parts were segmented from FLAIR (Fluid Attenuated Inversion Recovery) MR scans and it is observed that the AUC is improved by 2% in whole tumor segmentation from base model with fine-tuned parameters. [ABSTRACT FROM AUTHOR]

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging–related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations. [ABSTRACT FROM AUTHOR]

Image segmentation is a basic problem in medical image analysis and useful for disease diagnosis. However, the complexity of medical images makes image segmentation difficult. In recent decades, fuzzy clustering algorithms have been preferred due to their simplicity and efficiency. However, they are sensitive to noise. To solve this problem, many algorithms using non-local information have been proposed, which perform well but are inefficient. This paper proposes an improved fuzzy clustering algorithm utilizing nonlocal self-similarity and a low-rank prior for image segmentation. Firstly, cluster centers are initialized based on peak detection. Then, a pixel correlation model between corresponding pixels is constructed, and similar pixel sets are retrieved. To improve efficiency and robustness, the proposed algorithm uses a novel objective function combining non-local information and a low-rank prior. Experiments on synthetic images and medical images illustrate that the algorithm can improve efficiency greatly while achieving satisfactory results. [ABSTRACT FROM AUTHOR]

Medical image segmentation of tissue abnormalities, key organs, or blood vascular system is of great significance for any computerized diagnostic system. However, automatic segmentation in medical image analysis is a challenging task since it requires sophisticated knowledge of the target organ anatomy. This paper develops an end-to-end deep learning segmentation method called Contextual Multi-Scale Multi-Level Network (CMM-Net). The main idea is to fuse the global contextual features of multiple spatial scales at every contracting convolutional network level in the U-Net. Also, we re-exploit the dilated convolution module that enables an expansion of the receptive field with different rates depending on the size of feature maps throughout the networks. In addition, an augmented testing scheme referred to as Inversion Recovery (IR) which uses logical "OR" and "AND" operators is developed. The proposed segmentation network is evaluated on three medical imaging datasets, namely ISIC 2017 for skin lesions segmentation from dermoscopy images, DRIVE for retinal blood vessels segmentation from fundus images, and BraTS 2018 for brain gliomas segmentation from MR scans. The experimental results showed superior state-of-the-art performance with overall dice similarity coefficients of 85.78%, 80.27%, and 88.96% on the segmentation of skin lesions, retinal blood vessels, and brain tumors, respectively. The proposed CMM-Net is inherently general and could be efficiently applied as a robust tool for various medical image segmentations. [ABSTRACT FROM AUTHOR]

Medical image segmentation as an earlier application field in image segmentation is the key technology of medical image analysis and is also a key point and difficulty in clinical application. This paper proposes an accurate and robust active contour model based on the four-phase level set for medical MR images. First we define a new energy functional by combining the data term and the length term, where the data term is defined by transforming the energy functional of the multiplicative intrinsic component optimization (MICO) model into the level set framework after adding an edge detector function. Then, when we minimize the energy functional, we use the split Bregman method to improve the convergence speed. To test the performance of our model, we do lots of experiments according to the different brain MR images, which show that even under the severe influence of bias field or shadows, our model can still segment these images well, and our model is robust to the initial contours and noise. Moreover, our model is compared with the MICO model by experimental results and the numerical values, concluding that our model is better than the MICO model no matter in segmentation accuracy or in correction effect. [ABSTRACT FROM AUTHOR]

The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class. This task is a part of the concept of scene understanding or better explaining the global context of an image. In the medical image analysis domain, image segmentation can be used for image-guided interventions, radiotherapy, or improved radiological diagnostics. In this review, we categorize the leading deep learning-based medical and non-medical image segmentation solutions into six main groups of deep architectural, data synthesis-based, loss function-based, sequenced models, weakly supervised, and multi-task methods and provide a comprehensive review of the contributions in each of these groups. Further, for each group, we analyze each variant of these groups and discuss the limitations of the current approaches and present potential future research directions for semantic image segmentation. [ABSTRACT FROM AUTHOR]

Purpose: In the field of medical image analysis, deep learning methods gained huge attention over the last years. This can be explained by their often improved performance compared to classic explicit algorithms. In order to work well, they need large amounts of annotated data for supervised learning, but these are often not available in the case of medical image data. One way to overcome this limitation is to generate synthetic training data, e.g., by performing simulations to artificially augment the dataset. However, simulations require domain knowledge and are limited by the complexity of the underlying physical model. Another method to perform data augmentation is the generation of images by means of neural networks. Methods: We developed a new algorithm for generation of synthetic medical images exhibiting speckle noise via generative adversarial networks (GANs). Key ingredient is a speckle layer, which can be incorporated into a neural network in order to add realistic and domain-dependent speckle. We call the resulting GAN architecture SpeckleGAN. Results: We compared our new approach to an equivalent GAN without speckle layer. SpeckleGAN was able to generate ultrasound images with very crisp speckle patterns in contrast to the baseline GAN, even for small datasets of 50 images. SpeckleGAN outperformed the baseline GAN by up to 165 % with respect to the Fréchet Inception distance. For artery layer and lumen segmentation, a performance improvement of up to 4 % was obtained for small datasets, when these were augmented with images by SpeckleGAN. Conclusion: SpeckleGAN facilitates the generation of realistic synthetic ultrasound images to augment small training sets for deep learning based image processing. Its application is not restricted to ultrasound images but could be used for every imaging methodology that produces images with speckle such as optical coherence tomography or radar. [ABSTRACT FROM AUTHOR]

Machine learning has considerably improved medical image analysis in the past years. Although data-driven approaches are intrinsically adaptive and thus, generic, they often do not perform the same way on data from different imaging modalities. In particular computed tomography (CT) data poses many challenges to medical image segmentation based on convolutional neural networks (CNNs), mostly due to the broad dynamic range of intensities and the varying number of recorded slices of CT volumes. In this paper, we address these issues with a framework that adds domain-specific data preprocessing and augmentation to state-of-the-art CNN architectures. Our major focus is to stabilise the prediction performance over samples as a mandatory requirement for use in automated and semi-automated workflows in the clinical environment. To validate the architecture-independent effects of our approach we compare a neural architecture based on dilated convolutions for parallel multi-scale processing (a modified Mixed-Scale Dense Network: MS-D Net) to traditional scaling operations (a modified U-Net). Finally, we show that an ensemble model combines the strengths across different individual methods. Our framework is simple to implement into existing deep learning pipelines for CT analysis. It performs well on a range of tasks such as liver and kidney segmentation, without significant differences in prediction performance on strongly differing volume sizes and varying slice thickness. Thus our framework is an essential step towards performing robust segmentation of unknown real-world samples. [ABSTRACT FROM AUTHOR]

Accurate pancreas segmentation from medical images is an important yet challenging problem for medical image analysis and medical surgery. Challenges relating to the pancreas image acquisition, the limited availability of image data and segmentation methodology hinder this segmentation task. This paper aims to present a systematic review of the different methodologies. Recently, a variety of segmentation methods have been proposed for automatic delineation of pancreas images. We intended to survey the methods proposed for image segmentation, outline those that have already been adopted for pancreas segmentation, perform a comparison between them using various indices and experimental data, and discuss their major contributions. Looking at the theoretical approach, different segmentation methods have been applied for delineating the pancreas and can be classified into those based on region, edge, atlas, neural network and other categories. Each segmentation method has its own advantages and disadvantages. Based on the previously performed analysis and discussion, and compared to other abdominal organs, improving the results of pancreas segmentation in the near future will require addressing several challenging issues. These issues include: (1) establishing publically available standardized datasets; (2) define clear metrics to evaluate the segmentation performance and (3) design new segmentation methods. [ABSTRACT FROM AUTHOR]

MRI image segmentation and classification is one of the important tasks in medical image analysis and visualization, despite occurrence of noise makes it tough to segment the region of interest. In this paper, the MRI images are pre-processed and segmentation is carried out using modified Level set method for the tumor segmentation. Also, it is important to extract the useful features to predict the image class accurately. The proposed method operates Multi-Level wavelet decomposition features and for the wavelet coefficients modified chief descriptions like Grey Level Co-Occurrence Matrix (GLCM), Gabor and moment invariant features are extracted. The classification is carried out using the Adaptive Artificial Neural Network (AANN) methodology. In the adaptive ANN, the layer neurons are optimized using Whale Optimization Algorithm (WOA). The adaptive neural network optimizes the network structure to increase the classification accuracy and thus gives better classification results of tumors based on the segmented images. The proposed method will be executed in the working platform of MATLAB and the results are compared with the previous state of the art techniques. Finally, the proposed method results in classification accuracy of 98%. [ABSTRACT FROM AUTHOR]

Segmentation is fundamental to medical image analysis. Recent advances in fully convolutional networks has enabled automatic segmentation; however, high labeling efforts and difficulty in acquiring sufficient and high-quality training data is still a challenge. In this study, a cascaded 3D U-Net with active learning to increase training efficiency with exceedingly limited data and reduce labeling efforts is proposed. Abdominal computed tomography images of 50 kidneys were used for training. In stage I, 20 kidneys with renal cell carcinoma and four substructures were used for training by manually labelling ground truths. In stage II, 20 kidneys from the previous stage and 20 newly added kidneys were used with convolutional neural net (CNN)-corrected labelling for the newly added data. Similarly, in stage III, 50 kidneys were used. The Dice similarity coefficient was increased with the completion of each stage, and shows superior performance when compared with a recent segmentation network based on 3D U-Net. The labeling time for CNN-corrected segmentation was reduced by more than half compared to that in manual segmentation. Active learning was therefore concluded to be capable of reducing labeling efforts through CNN-corrected segmentation and increase training efficiency by iterative learning with limited data. [ABSTRACT FROM AUTHOR]

Neural network-based segmentation methods are an important advancement in medical image analysis. Issues with class imbalance pose a significant challenge in medical segmentation, with lesions often occupying a considerably smaller volume (hard objects) relative to the background (easy objects). Medical image segmentation tasks require the model to pay attention on specific parts of the image rather than the entire image. Models based on CNN and its variants like U-Net have shown promising results in this regard. However, they often suffer from unstable gradient during the training process. We propose an optimized deep focused U-Net (DF U-Net) model along with a novel learnable optimized focal loss (LOF) function. The DF U-Net is integrated with a novel block that comprises of five subblocks: efficient channel attention, squeeze and excitation, stochastic depth, residual block and dense block, collectively known as (ESSRD) in the decoder layers which helps to address the unstable gradient and overfitting issues. The proposed LOF loss optimizes itself during the training of the model and converges to optimal values within few epochs. We evaluated DF U-Net using four medical imaging data sets: DRIVE, BUS2017, CVC-Clinic and Kvasir-SEG. During the training process, DF U-Net significantly reduced the convergence time by sharply minimizing the loss to 0.001% and achieved an accuracy of 99.5%. The experimental results show that DF U-Net helps to mitigate the unstable gradient issue while focusing on both easy and hard objects equally. [ABSTRACT FROM AUTHOR]

The segmentation accuracy of the lung images is affected by the occlusion of the front background objects. To address this problem, we propose a full-scale lung image segmentation algorithm based on hybrid skip connection and attention mechanism (HAFS). The algorithm uses yolov8 as the underlying network and enhancement of multi-layer feature fusion by incorporating dense and sparse skip connections into the network structure, and increased weighting of important features through attention gates. Finally the proposed algorithm was applied to the lung datasets Montgomery County chest X-ray and Shenzhen chest X-ray. The experimental results show that the proposed algorithm improves the precision, recall, pixel accuracy, Dice, mIoU, mAP and GFLOPs metrics compared to the comparison algorithms, which proves the advancement and effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Colonoscopy is widely recognized as the most effective method for the detection of colon polyps, which is crucial for early screening of colorectal cancer. Polyp identification and segmentation in colonoscopy images require specialized medical knowledge and are often labor-intensive and expensive. Deep learning provides an intelligent and efficient approach for polyp segmentation. However, the variability in polyp size and the heterogeneity of polyp boundaries and interiors pose challenges for accurate segmentation. Currently, Transformer-based methods have become a mainstream trend for polyp segmentation. However, these methods tend to overlook local details due to the inherent characteristics of Transformer, leading to inferior results. Moreover, the computational burden brought by self-attention mechanisms hinders the practical application of these models. To address these issues, we propose a novel CNN-Transformer hybrid model for polyp segmentation (CTHP). CTHP combines the strengths of CNN, which excels at modeling local information, and Transformer, which excels at modeling global semantics, to enhance segmentation accuracy. We transform the self-attention computation over the entire feature map into the width and height directions, significantly improving computational efficiency. Additionally, we design a new information propagation module and introduce additional positional bias coefficients during the attention computation process, which reduces the dispersal of information introduced by deep and mixed feature fusion in the Transformer. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance on multiple benchmark datasets for polyp segmentation. Furthermore, cross-domain generalization experiments show that our model exhibits excellent generalization performance. [ABSTRACT FROM AUTHOR]

Skin disorders significantly impact quality of life, necessitating advanced diagnostic tools. Machine Learning (ML) and Deep Learning (DL), particularly Convolutional Neural Networks (CNNs), offer promising solutions. ML aids in image segmentation and lesion classification, while DL captures intricate features for improved accuracy. Challenges include limited annotated data, the 'black box' nature of AI decision-making, and seamless integration into clinical workflows. Recent advancements such as development of ML and DL algorithms and availability of publicly available datasets, hold promise for earlier diagnoses and improved outcomes in dermatology. Building ML and DL models robust to variations in image quality, lighting conditions, and patient demographics is hence, paramount to enhance the accuracy and efficiency of skin image analysis in clinical practice. In conclusion, while ML and DL techniques show promise, exploring hybrid approaches combining the strengths of both could lead to more robust diagnostic tools for dermatology, revolutionizing skin disorder diagnosis and treatment. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) examinations are a routine part of the cancer treatment process. In developing countries, disease diagnosis is often time-consuming and associated with serious prognostic problems. Moreover, MRI is characterized by high noise and low resolution. This creates difficulties in automatic segmentation of the lesion region, leading to a decrease in the segmentation performance of the model. This paper proposes a deep convolutional neural network osteosarcoma image segmentation system based on noise reduction and super-resolution reconstruction, which is the first time to introduce super-resolution methods in the task of osteosarcoma MRI image segmentation, effectively improving the Model generalization performance. We first refined the initial osteosarcoma dataset using a Differential Activation Filter, separating those image data that had little effect on model training. At the same time, we carry out rough initial denoising of the image. Then, an improved information multi-distillation network based on adaptive cropping is proposed to reconstruct the original image and improve the resolution of the image. Finally, a high-resolution network is used to segment the image, and the segmentation boundary is optimized to provide a reference for doctors. Experimental results show that this algorithm has a stronger segmentation effect and anti-noise ability than existing methods. Code: https://github.com/GFF1228/NSRDN. [ABSTRACT FROM AUTHOR]

This paper presents an improved genetic algorithm focused on multi-threshold optimization for image segmentation in digital pathology. By innovatively enhancing the selection mechanism and crossover operation, the limitations of traditional genetic algorithms are effectively addressed, significantly improving both segmentation accuracy and computational efficiency. Experimental results demonstrate that the improved genetic algorithm achieves the best balance between precision and recall within the threshold range of 0.02 to 0.05, and it significantly outperforms traditional methods in terms of segmentation performance. Segmentation quality is quantified using metrics such as precision, recall, and F1 score, and statistical tests confirm the superior performance of the algorithm, especially in its global search capabilities for complex optimization problems. Although the algorithm's computation time is relatively long, its notable advantages in segmentation quality, particularly in handling high-precision segmentation tasks for complex images, are highly pronounced. The experiments also show that the algorithm exhibits strong robustness and stability, maintaining reliable performance under different initial conditions. Compared to general segmentation models, this algorithm demonstrates significant advantages in specialized tasks, such as pathology image segmentation, especially in resource-constrained environments. Therefore, this improved genetic algorithm offers an efficient and precise multi-threshold optimization solution for image segmentation, providing valuable reference for practical applications. [ABSTRACT FROM AUTHOR]

Liver ultrasound is widely used in clinical practice due to its advantages of non-invasiveness, non-radiation, and real-time imaging. Accurate segmentation of the liver region in ultrasound images is essential for accelerating the auxiliary diagnosis of liver-related diseases. This paper proposes BACANet, a deep learning algorithm designed for real-time liver ultrasound segmentation. Our approach utilizes a lightweight network backbone for liver feature extraction and incorporates a convolutional attention mechanism to enhance the network's ability to capture global contextual information. To improve early localization of liver boundaries, we developed a selective large kernel convolution module for boundary feature extraction and introduced explicit liver boundary supervision. Additionally, we designed an enhanced attention gate to efficiently convey liver body and boundary features to the decoder to enhance the feature representation capability. Experimental results across multiple datasets demonstrate that BACANet effectively completes the task of liver ultrasound segmentation, achieving a balance between inference speed and segmentation accuracy. On a public dataset, BACANet achieved a DSC of 0.921 and an IOU of 0.854. On a private test dataset, BACANet achieved a DSC of 0.950 and an IOU of 0.907, with an inference time of approximately 0.32 s per image on a CPU processor. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is the most prevalent cause of preventable vision loss worldwide, imposing a significant economic and medical burden on society today, of which early identification is the cornerstones of the management. The diagnosis and severity grading of DR rely on scales based on clinical visualized features, but lack detailed quantitative parameters. Retinal non-perfusion area (NPA) is a pathogenic characteristic of DR that symbolizes retinal hypoxia conditions, and was found to be intimately associated with disease progression, prognosis, and management. However, the practical value of NPA is constrained since it appears on fundus fluorescein angiography (FFA) as distributed, irregularly shaped, darker plaques that are challenging to measure manually. In this study, we propose a deep learning-based method, NPA-Net, for accurate and automatic segmentation of NPAs from FFA images acquired in clinical practice. NPA-Net uses the U-net structure as the basic backbone, which has an encoder-decoder model structure. To enhance the recognition performance of the model for NPA, we adaptively incorporate multi-scale features and contextual information in feature learning and design three modules: Adaptive Encoder Feature Fusion (AEFF) module, Multilayer Deep Supervised Loss, and Atrous Spatial Pyramid Pooling (ASPP) module, which enhance the recognition ability of the model for NPAs of different sizes from different perspectives. We conducted extensive experiments on a clinical dataset with 163 eyes with NPAs manually annotated by ophthalmologists, and NPA-Net achieved better segmentation performance compared to other existing methods with an area under the receiver operating characteristic curve (AUC) of 0.9752, accuracy of 0.9431, sensitivity of 0.8794, specificity of 0.9459, IOU of 0.3876 and Dice of 0.5686. This new automatic segmentation model is useful for identifying NPA in clinical practice, generating quantitative parameters that can be useful for further research as well as guiding DR detection, grading severity, treatment planning, and prognosis. [ABSTRACT FROM AUTHOR]

Image segmentation of the liver is an important step in treatment planning for liver cancer. However, manual segmentation at a large scale is not practical, leading to increasing reliance on deep learning models to automatically segment the liver. This manuscript develops a generalizable deep learning model to segment the liver on T1-weighted MR images. In particular, three distinct deep learning architectures (nnUNet, PocketNet, Swin UNETR) were considered using data gathered from six geographically different institutions. A total of 819 T1-weighted MR images were gathered from both public and internal sources. Our experiments compared each architecture's testing performance when trained both intra-institutionally and inter-institutionally. Models trained using nnUNet and its PocketNet variant achieved mean Dice-Sorensen similarity coefficients>0.9 on both intra- and inter-institutional test set data. The performance of these models suggests that nnUNet and PocketNet liver segmentation models trained on a large and diverse collection of T1-weighted MR images would on average achieve good intra-institutional segmentation performance. [ABSTRACT FROM AUTHOR]

Tasks related to the automation of medical data processing are becoming more urgent. Particular attention is paid to systems for monitoring and analyzing human physiological parameters. Such systems often use specialized sensors to capture biomedical images, such as infrared cameras. This article describes our study of the problem of segmenting the eye pupil and iris in images obtained using an infrared camera. In our work, we propose a proprietary deep neural network architecture with a novel loss function for learning to segment human ocular structures. We also present a segmentation dataset and perform a comparative analysis of different eye structure segmentation methods. Our proposed model outperforms other considered approaches and has demonstrated state-of-the-art results in segmentation of human ocular structures. [ABSTRACT FROM AUTHOR]

As the rise in cancer cases, there is an increasing demand to develop accurate and rapid diagnostic tools for early intervention. Pathologists are looking to augment manual analysis with computer-based evaluation to develop more efficient cancer diagnostics reports. The processing of these reports from manual evaluation is time-consuming, where the pathologists focus on accurately segmenting individual cancer cells, a vital step in analysis. This paper describes the design and validation of an application which has been developed based on deep learning networks. The application includes a workflow of image pre-processing followed by synthetic image generation, which is crucial due to the lack of training data in pathology settings. The next steps are the segmentation of nuclei regions and overlapping nuclei splitting. An improved approach has been considered based on a cycle-consistent GAN network for synthetic image generation. The synthetic images were utilized in a modified U-net network. Accurately outlining the individual nucleus border assisted an automated system that split the nuclei cluster into the individual nucleus. The SSIM and PSNR values of synthetic images corresponding to original were 0.204 and 10.610. The DSC value of the network trained by the synthetic data was 0.984 which was higher than the network trained by original images (0.805). The developed application provided better individual nuclei segmentation performance, where the average accuracy of different group images was 0.97. This higher accuracy suggests the benefit of using synthetic images in a situation to avoid the scarcity of labeled histopathology images in deep networks. [ABSTRACT FROM AUTHOR]

Skin disease image segmentation faces two major challenges: the complex and varied lesion morphology and the presence of interfering image backgrounds. To address these difficulties in skin disease image segmentation, we propose a Residual U-Net architecture with Channel-Space Separate Attention based on depthwise separable convolutions. The multi-scale residual U-Net modules in the encoder efficiently capture multi-scale texture information in lesions and backgrounds within a single stage, overcoming the limitations of U-Net in extracting just local features. The introduction of ConvMixer Block for global contextual modeling contributes to suppress complex background interference and enhances the overall understanding of lesion morphology. Additionally, we employ a Channel-Space Separate Attention mechanism with depthwise separable convolutions(CSSA-DSC) for feature fusion, effectively addressing the limited expressiveness issue associated with U-Net’s direct skip-connection concatenation. Experimental results on the PH2, ISIC 2017, and ISIC 2018 datasets demonstrate our method’s strong multi-scale modeling and feature expression capabilities. [ABSTRACT FROM AUTHOR]

In medical clinical scenarios for reasons such as patient privacy, information protection and data migration, when domain adaptation is needed for real scenarios, the source-domain data is often inaccessible and only the pre-trained source model on the source-domain is available. Existing solutions for this type of problem tend to forget the rich task experience previously learned on the source domain after adapting, which means that the model simply overfits the target-domain data when adapting and does not learn robust features that facilitate real task decisions. We address this problem by exploring the particular application of source-free domain adaptation in medical image segmentation and propose a two-stage additive source-free adaptation framework. We generalize the domain-invariant features by constraining the core pathological structure and semantic consistency between different perspectives. And we reduce the segmentation generated by locating and filtering elements that may have errors through Monte-Carlo uncertainty estimation. We conduct comparison experiments with some other methods on a cross-device polyp segmentation and a cross-modal brain tumor segmentation dataset, the results in both the target and source domains verify that the proposed method can effectively solve the domain offset problem and the model retains its dominance on the source domain after learning new knowledge of the target domain.This work provides valuable exploration for achieving additive learning on the target and source domains in the absence of source data and offers new ideas and methods for adaptation research in the field of medical image segmentation. [ABSTRACT FROM AUTHOR]

U-net, a fully convolutional network-based image segmentation method, has demonstrated widespread adaptability in the crack segmentation task. The combination of the semantically dissimilar features of the encoder (shallow layers) and the decoder (deep layers) in the skip connections leads to blurry features map and leads to undesirable over- or under-segmentation of target regions. Additionally, the shallow architecture of the U-Net model prevents the extraction of more discriminatory information from input images. This paper proposes a Residual Sharp U-Net (RS-Net) architecture for crack segmentation and severity assessment in pavement surfaces to address these limitations. The proposed architecture uses residual block in the U-Net model to extract a more insightful representation of features. In addition to that, a sharpening kernel filter is used instead of plain skip connections to generate a fine-tuned encoder features map before combining it with decoder features maps to reduce the dissimilarity between them and smoothes artifacts in the network layers during early training. The proposed architecture is also integrated with various morphological operations to assess the severity of cracks and categorize them into hairline, medium, and severe labels. Experiments results demonstrated that the RS-Net model has promising segmentation performance, outperforming earlier U-Net variations on testing data for crack segmentation and severity assessment, with a promising accuracy (>0.97) [ABSTRACT FROM AUTHOR]

Malignant tumors are a common cytopathologic disease. Pathological tissue examination is a key tool for diagnosing malignant tumors. Doctors need to manually analyze the images of pathological tissue sections, which is not only time-consuming but also highly subjective, easily leading to misdiagnosis. Most of the existing computer-aided diagnostic techniques focus too much on accuracy when processing pathological tissue images, and do not take into account the problems of insufficient resources in developing countries to meet the training of large models and the difficulty of obtaining medical annotation data. Based on this, this study proposes an artificial intelligence multiprocessing scheme (MSPInet) for digital pathology images of malignant tumors. We use techniques such as data expansion and noise reduction to enhance the dataset. Then we design a coarse segmentation method for cell nuclei of pathology images based on Transformer for Semantic Segmentation and further optimize the segmentation of tumor edges using conditional random fields. Finally, we improve the training strategy for knowledge distillation. As a medical assistive system, the method can quantify and convert complex pathology images into analyzable image information. Experimental results show that our method performs well in terms of segmentation accuracy and also has advantages in terms of time and space efficiency. This makes our technology available to developing countries that are not as well resourced, and equipped in terms of medical care. The teacher model and lightweight student model included in our method achieve 71.6% and 66.1% Intersection over Union (IoU) in cell segmentation respectively, outperforming Swin-unet and CSWin Transformer. [ABSTRACT FROM AUTHOR]

Anomaly detection poses a significant challenge in the industry and knowledge distillation constructed using a frozen teacher network and a trainable student network is the prevailing approach for detecting suspicious regions. Forward and reverse distillation are the main ways to achieve anomaly detection. To design an effective model and aggregate detection results, we propose a dual-student knowledge distillation (DSKD) based on forward and reverse distillation. Taking advantage of the priority of reverse distillation to obtain high-level representation, we combine a skip connection and an attention module to build a reverse distillation student network that simultaneously focuses on high-level representation and low-level features. DSKD uses a forward distillation network as an auxiliary to allow the student network to preferentially obtain the query image. For different anomaly score maps obtained by the dual-student network, we use synthetic noise enhancement in combination with image segmentation loss to adaptively learn the weight scores of individual maps. Empirical experiments conducted on the MVTec dataset show that the proposed DSKD method achieves good performance on texture images as well as competitive results on object images compared with other state-of-the-art methods. Meanwhile, ablation experiments and a visualization analysis validate the contributions of each of the model's components. [ABSTRACT FROM AUTHOR]

Semantic image segmentation is extensively used for automatic concrete crack detection. In previous studies on semantic image segmentation, concrete images were usually labeled as crack and noncrack zones, and recognition models were then trained using artificial neural networks. However, there is not enough edge information in concrete images for the trained model to identify effectively fine concrete cracks (widths < 0.1 mm). Furthermore, complex backgrounds in concrete images can cause false detections. To improve efficiency and reduce false detections, this study develops a three-stage automatic crack-width identification method for fine concrete cracks. First, a full crack skeleton information identification based on image segmentation is proposed. The performance of the mainstream image segmentation architectures, PSP-Net, Seg-Net, U-Net, and Res-Unet, are compared and analyzed, demonstrating that the Res-Unet-based crack skeleton segmentation is the most accurate at fine-crack detection and able to solve the information loss problem that occurs when learning the imbalanced data of fine concrete cracks. Second, a fractal dimension (FD)-based false detection removal process is applied to discriminate true cracks and false detections. The results show that false detections (line-like curves, shadows, and surface stains) can be removed, increasing the matching rate from 0.6476 to 0.8351. Finally, the FD features of the crack skeleton with maximum widths < 0.1 mm, crack widths in the range of 0.1–0.2 mm, and crack widths > 0.2 mm are calculated. Findings illustrate that the values of the FD feature for the three crack-width ranges are suitable for quantitative characterization of identified crack widths. [ABSTRACT FROM AUTHOR]

Melanoma is the deadliest form of skin cancer, and its incidence level is increasing. It is important to obtain a diagnosis at an early stage to increase the patient survival rate. Skin lesion segmentation is a difficult problem in medical image analysis. To address this problem, we propose end-to-end object scale-oriented fully convolutional networks (OSO–FCNs) for skin lesion segmentation. Given a single skin lesion image, the proposed method produces a pixel-level mask for skin lesion areas. We found that the scale of the lesions in the training dataset affects a large number of the segmentation results of the lesions in the testing phase, and thus, a training strategy called object scale-oriented (OSO) training is proposed. First, the pre-trained network of VGG-16 is adapted and is transformed into fully convolutional networks (FCNs). Second, after very simple preprocessing, skin lesion images with boundary-level annotations are fed into the FCNs for fine-tuning training based on the pre-trained model using OSO training. During the OSO training, the training dataset is divided into 2 subsets according to an index called the object occupation ratio, and then the whole training dataset and the 2 subsets are used to train 3 different scale-oriented FCNs. A dataset provided by the International Skin Imaging Collaboration (ISIC), ISIC2016, is used for training and testing. Our algorithm is compared with the state-of-the-art algorithms, and the experimental results demonstrate that the segmentation accuracy of our algorithm is higher or very close to the performances of the other algorithms. [ABSTRACT FROM AUTHOR]

In medical imaging, the classification and segmentation of lesions have always been significant topics in clinical research. Different categories of lesions require different treatment strategies, and accurate segmentation helps to assist in improving the effect of the clinical treatment. The Segment anything model (SAM) is an image segmentation model trained on a large-scale dataset with strong prompt segmentation capability, but it cannot be directly applied to the classification and segmentation tasks of medical images due to insufficient training on medical image data. In this paper, we propose a deep learning method for the classification and segmentation of lesions, called GMM-based segment anything model (G-SAM). Prompt-tuning is utilized in the model with the LoRA strategy, and the lesion feature extraction (GFE) module based on the Gaussian mixture model (GMM), is designed to effectively improve the effect of lesion classification and segmentation on the basis of the SAM. Notably, G-SAM exhibits greater sensitivity to early stage of the lesions, aiding in tumor detection and prevention, which holds important clinical value. G-SAM overcomes the limitation that SAM is not suitable for the medical image classification and segmentation tasks due to insufficient training data with minimal cost. Moreover, it enhances classification accuracy and segmentation precision compared to traditional Gaussian model-based methods. The effectiveness of G-SAM in classifying and segmenting lesions is validated on the LIDC dataset, demonstrating advantages over state-of-the-art (SOTA) methods. The study further validates the applicability of G-SAM on large publicly available datasets across three different image modalities, achieving superior performance. [ABSTRACT FROM AUTHOR]

Medical imaging is essential in modern healthcare because it assists physicians in the diagnosis of cancer. Various tissues and features in medical imaging can be recognized using image segmentation algorithms. This feature makes it possible to pinpoint and define particular areas, which makes it easier to precisely locate and characterize anomalities or lesions for cancer diagnosis. Among cancers affecting women, breast cancer is particularly prevalent, underscoring the urgent need to improve the accuracy of image segmentation for breast cancer in order to assist medical practitioners. Multi-threshold image segmentation is widely acknowledged for its direct and effective characteristics. In this context, this paper suggests a refined whale optimization algorithm to improve the segmentation accuracy of breast cancer data. This algorithm optimizes performance by combining a quantum phase interference mechanism and an enhanced solution quality strategy. This work compares the method with classical, homogeneous, state-of-the-art algorithms and runs experiments on the IEEE CEC2017 benchmark to validate its practical optimization performance. Furthermore, a multi-threshold image segmentation algorithm-based image segmentation technique is presented in this study. The Berkeley segmentation dataset and the breast invasive ductal carcinomas segmentation dataset are segmented using the approach using a non-local means two-dimensional histogram and Renyi's entropy. Experimental results demonstrate the excellent performance of this segmentation method in image segmentation applications across both low and high threshold levels. As a result, it emerges as a valuable image segmentation technique with practical applications. [ABSTRACT FROM AUTHOR]

Image segmentation is the process of splitting a digital image into distinct segments or categories based on shared characteristics like texture, color, and intensity. Its primary aim is to simplify the image for easier analysis while preserving its important features. Each pixel in the image is assigned a label, grouped together by pixels with similar traits together. Segmentation helps to delineate boundaries and identify objects such as curves or lines within the image. The process generates a series of segmented images that cover the entire original image. This article reviews emerging applications of image segmentation in medical diagnostics, specifically employing nature-inspired optimization algorithms (NIOAs). It begins by outlining different segmentation methods and NIOAs types, then by examining relevant databases and medical imaging technologies. The study draws on a diverse range of research sources. Finally, this paper briefly discusses the challenges and future trends of medical image segmentation using NIOAs to detect different diseases. [ABSTRACT FROM AUTHOR]

Current mask processing operations rely on interpolation algorithms that do not produce extra pixels, such as nearest neighbor (NN) interpolation, as opposed to algorithms that do produce extra pixels, like bicubic (BIC) or bilinear (BIL) interpolation. In our previous study, the author proposed an alternative approach to NN-based mask processing and evaluated its effects on deep learning training outcomes. In this study, the author evaluated the effects of both BIC-based image and mask processing and BIC-and-NN-based image and mask processing versus NN-based image and mask processing. The evaluation revealed that the BIC-BIC model/network was an 8.9578% (with image size 256 × 256) and a 1.0496% (with image size 384 × 384) increase of the NN-NN network compared to the NN-BIC network which was an 8.3127% (with image size 256 × 256) and a 0.2887% (with image size 384 × 384) increase of the NN-NN network. [ABSTRACT FROM AUTHOR]

Supervoxel segmentation has become an essential tool to medical image analysis for three-dimension MR image. However, in no consideration of the intensity inhomogeneity in 2D/3D MR image, the state-of-the-art supervoxel segmentation methods do not satisfy the further analysis, such as tissue classification according to intensity feature. In order to overcome the above-mentioned issues, we propose a modified supervoxel segmentation method for three-dimension MR image, which integrates the bias field into the weighted distance metric to determine the nearest cluster center. The supervoxel segmentation and bias correction can be simultaneously completed in our method. Especially, the bias corrected image lays the foundation for the supervoxel classification in accordance with the intensity feature. The experimental results and quantitative evaluation showed that the supervoxels obtained by our method are adherence to the MR tissue boundaries, and the bias corrected image is positive for the intensity feature extraction. [ABSTRACT FROM AUTHOR]

AI-powered segmentation of hip and knee bony anatomy has revolutionized orthopedics, transforming pre-operative planning and post-operative assessment. Despite the remarkable advancements in AI algorithms for medical imaging, the potential for biases inherent within these models remains largely unexplored. This study tackles these concerns by thoroughly re-examining AI-driven segmentation for hip and knee bony anatomy. While advanced imaging modalities like CT and MRI offer comprehensive views, plain radiographs (X-rays) predominate the standard initial clinical assessment due to their widespread availability, low cost, and rapid acquisition. Hence, we focused on plain radiographs to ensure the utilization of our contribution in diverse healthcare settings, including those with limited access to advanced imaging technologies. This work provides insights into the underlying causes of biases in AI-based knee and hip image segmentation through an extensive evaluation, presenting targeted mitigation strategies to alleviate biases related to sex, race, and age, using an automatic segmentation that is fair, impartial, and safe in the context of AI. Our contribution can enhance inclusivity, ethical practices, equity, and an unbiased healthcare environment with advanced clinical outcomes, aiding decision-making and osteoarthritis research. Furthermore, we have made all the codes and datasets publicly and freely accessible to promote open scientific research. [ABSTRACT FROM AUTHOR]

Patients with congenital heart disease often have cardiac anatomy that deviates significantly from normal, frequently requiring multiple heart surgeries. Image segmentation from a preoperative cardiovascular magnetic resonance (CMR) scan would enable creation of patient-specific 3D surface models of the heart, which have potential to improve surgical planning, enable surgical simulation, and allow automatic computation of quantitative metrics of heart function. However, there is no publicly available CMR dataset for whole-heart segmentation in patients with congenital heart disease. Here, we release the HVSMR-2.0 dataset, comprising 60 CMR scans alongside manual segmentation masks of the 4 cardiac chambers and 4 great vessels. The images showcase a wide range of heart defects and prior surgical interventions. The dataset also includes masks of required and optional extents of the great vessels, enabling fairer comparisons across algorithms. Detailed diagnoses for each subject are also provided. By releasing HVSMR-2.0, we aim to encourage development of robust segmentation algorithms and clinically relevant tools for congenital heart disease. [ABSTRACT FROM AUTHOR]