Semantic segmentation using deep learning to extract total extraocular muscles and optic nerve from orbital computed tomography images

Brain Tumour Segmentation and Grading Using Local and Global Context-Aggregated Attention Network Architecture

Brain tumours (BTs) are among the most dangerous and life-threatening cancers in humans of all ages, and the early detection of BTs can make a huge difference to their treatment. However, grade recognition is a challenging issue for radiologists involved in automated diagnosis and healthcare monitoring. Recent research has been motivated by the search for deep learning-based mechanisms for segmentation and grading to assist radiologists in diagnostic analysis. Segmentation refers to the identification and delineation of tumour regions in medical images, while classification classifies based on tumour characteristics, such as the size, location and enhancement pattern. The main aim of this research is to design and develop an intelligent model that can detect and grade tumours more effectively. This research develops an aggregated architecture called LGCNet, which combines a local context attention network and a global context attention network. LGCNet makes use of information extracted through the task, dimension and scale. Specifically, a global context attention network is developed for capturing multiple-scale features, and a local context attention network is designed for specific tasks. Thereafter, both networks are aggregated, and the learning network is designed to balance all the tasks by combining the loss functions of the classification and segmentation. The main advantage of LGCNet is its dedicated network for a specific task. The proposed model is evaluated by considering the BraTS2019 dataset with different metrics, such as the Dice score, sensitivity, specificity and Hausdorff score. Comparative analysis with the existing model shows marginal improvement and provides scope for further research into BT segmentation and classification. The scope of this study focuses on the BraTS2019 dataset, with future work aiming to extend the applicability of the model to different clinical and imaging environments.

A novel clinical investigation using deep learning and human-in-the-loop approach in orbital volume measurement

Orbital volume assessment is crucial for surgical planning. Traditional methods lack efficiency and accuracy. Recent studies explore AI-driven techniques, but research on their clinical effectiveness is limited. This study included 349 patients aged 19 years and above, who underwent three-dimensional facial computed tomography (3DCT) without orbital trauma or congenital anomalies. To construct an AI training dataset, manual segmentation was performed on 178 patients' 3DCT using 3D Slicer. The remaining data of 171 patients underwent human-in-the-loop method, resulting in a dataset of 349 annotated samples. Comparative analysis of Dice coefficients and execution speeds was performed between manual and semi-automated segmentations. Comparing AI-assisted semi-automated segmentation with manual segmentation, all six annotators demonstrated lower average inference times without a significant difference in Dice coefficients (90.31% vs. 88.72%). For 178 patients' 3DCT, a high average Dice coefficient of 89.9% was observed, and a 38.42-ms inference time was recorded. For the full dataset, the AI model achieved a high average Dice coefficient of 94.1% and a fast average inference time of 32.55 ms per axial slice. This study demonstrates the potential of AI for maintaining high accuracy and time-efficiency in orbital region segmentation, with wide clinical applications.

Enhanced Cross-stage-attention U-Net for esophageal target volume segmentation

PURPOSE

The segmentation of target volume and organs at risk (OAR) was a significant part of radiotherapy. Specifically, determining the location and scale of the esophagus in simulated computed tomography images was difficult and time-consuming primarily due to its complex structure and low contrast with the surrounding tissues. In this study, an Enhanced Cross-stage-attention U-Net was proposed to solve the segmentation problem for the esophageal gross tumor volume (GTV) and clinical tumor volume (CTV) in CT images.

METHODS

First, a module based on principal component analysis theory was constructed to pre-extract the features of the input image. Then, a cross-stage based feature fusion model was designed to replace the skip concatenation of original UNet, which was composed of Wide Range Attention unit, Small-kernel Local Attention unit, and Inverted Bottleneck unit. WRA was employed to capture global attention, whose large convolution kernel was further decomposed to simplify the calculation. SLA was used to complement the local attention to WRA. IBN was structed to fuse the extracted features, where a global frequency response layer was built to redistribute the frequency response of the fused feature maps.

RESULTS

The proposed method was compared with relevant published esophageal segmentation methods. The prediction of the proposed network was MSD = 2.83(1.62, 4.76)mm, HD = 11.79 ± 6.02 mm, DC = 72.45 ± 19.18% in GTV; MSD = 5.26(2.18, 8.82)mm, HD = 16.22 ± 10.01 mm, DC = 71.06 ± 17.72% in CTV.

CONCLUSION

The reconstruction of the skip concatenation in UNet showed an improvement of performance for esophageal segmentation. The results showed the proposed network had better effect on esophageal GTV and CTV segmentation.

A method of nucleus image segmentation and counting based on TC-UNet++ and distance watershed

Nucleus segmentation and counting play a crucial role in many cell analysis applications. However, the dense distribution and blurry boundaries of nucleus make nucleus segmentation tasks challenging. This paper proposes a novel segmentation and counting method. Firstly, TC-UNet++ is proposed to achieve a global segmentation. Then, the distance watershed method is used to finish local segmentation, which separate the adhesion and overlap part of the image. Finally, counting method is performed to obtain information on the counting number, area and center of mass of nucleus. TC-UNet++ achieved a Dice coefficient of 89.95% for cell instance segmentation on the Data Science Bowl dataset, surpassing the original U-Net++ by 0.23%. It also showed a 5.09% improvement in counting results compared to other methods. On the ALL-IDB dataset, TC-UNet++ reached a Dice coefficient of 83.97%, a 7.93% increase over the original U-Net++. Additionally, its counting results improved by 16.82% compared to other approaches. These results indicate that our method has a more complete and reasonable nucleus segmentation and counting scheme compared to other methods.

Extraocular muscle enlargement in dysthyroid optic neuropathy

OBJECTIVE

To investigate extraocular muscle volumes in thyroid eye disease (TED) patients with and without dysthyroid optic neuropathy (DON).

DESIGN

Retrospective cohort study.

PARTICIPANTS

TED patients who had computed tomography of the orbits.

METHODS

The extraocular muscles were manually segmented in consecutive axial and coronal slices, and the volume was calculated by summing the areas in each slice and multiplying by the slice thickness. Data were collected on patient demographics, disease presentation, thyroid function tests, and antibody levels.

RESULTS

Imaging from 200 orbits was evaluated. The medial rectus, lateral rectus, superior muscle group, inferior rectus, and superior oblique volumes were significantly greater in orbits with DON compared with TED orbits without DON (p < 0.01 for all). There was no significant difference in the inferior oblique muscle volume (p = 0.19). Increase in volume of the superior oblique muscle showed the highest odds for DON. Each 100 mm3 increase in superior oblique, lateral rectus, inferior rectus, medial rectus, and superior muscle group volume was associated with 1.58, 1.25, 1.20, 1.16, and 1.14 times increased odds of DON.

CONCLUSION

All extraocular muscle volumes except for the inferior oblique were significantly greater in DON patients. Superior oblique enlargement was associated with the highest odds of DON, suggesting superior oblique enlargement to be a novel marker of DON.

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

BACKGROUND

Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Traditional invasive methods are inconvenient and not suitable for rapid, point-of-care testing. Moreover, current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. This study aims to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to accurately estimate hemoglobin levels, thereby facilitating rapid and accessible medical assessments.

METHODS

The study employed a smartphone application to capture images of the eye, which were subsequently analyzed by a deep neural network trained on data from invasive blood test data. Specifically, the EGE-Unet model was utilized for eyelid segmentation, while the DHA(C3AE) model was employed for hemoglobin level prediction. The performance of the EGE-Unet was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. The DHA(C3AE) model's performance was assessed using mean absolute error (MAE), mean-square error (MSE), root mean square error (RMSE), and R^2.

RESULTS

The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving an MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with an MAE of 1.34, an MSE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08 M, with a computational complexity of 0.12 FLOPs (G).

CONCLUSIONS

This system presents a groundbreaking approach that eliminates the need for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings.

TRIAL REGISTRATION

The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on 20/02/2021.

DRA-Net: Medical image segmentation based on adaptive feature extraction and region-level information fusion

Medical image segmentation is a key task in computer aided diagnosis. In recent years, convolutional neural network (CNN) has made some achievements in medical image segmentation. However, the convolution operation can only extract features in a fixed size region at a time, which leads to the loss of some key features. The recently popular Transformer has global modeling capabilities, but it does not pay enough attention to local information and cannot accurately segment the edge details of the target area. Given these issues, we proposed dynamic regional attention network (DRA-Net). Different from the above methods, it first measures the similarity of features and concentrates attention on different dynamic regions. In this way, the network can adaptively select different modeling scopes for feature extraction, reducing information loss. Then, regional feature interaction is carried out to better learn local edge details. At the same time, we also design ordered shift multilayer perceptron (MLP) blocks to enhance communication within different regions, further enhancing the network's ability to learn local edge details. After several experiments, the results indicate that our network produces more accurate segmentation performance compared to other CNN and Transformer based networks.

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Image segmentation is a fundamental task in deep learning, which is able to analyse the essence of the images for further development. However, for the supervised learning segmentation method, collecting pixel-level labels is very time-consuming and labour-intensive. In the medical image processing area for optic disc and cup segmentation, we consider there are two challenging problems that remain unsolved. One is how to design an efficient network to capture the global field of the medical image and execute fast in real applications. The other is how to train the deep segmentation network using a few training data due to some medical privacy issues. In this paper, to conquer such issues, we first design a novel attention-aware segmentation model equipped with the multi-scale attention module in the pyramid structure-like encoder-decoder network, which can efficiently learn the global semantics and the long-range dependencies of the input images. Furthermore, we also inject the prior knowledge that the optic cup lies inside the optic disc by a novel loss function. Then, we propose a self-supervised contrastive learning method for optic disc and cup segmentation. The unsupervised feature representation is learned by matching an encoded query to a dictionary of encoded keys using a contrastive technique. Finetuning the pre-trained model using the proposed loss function can help achieve good performance for the task. To validate the effectiveness of the proposed method, extensive systemic evaluations on different public challenging optic disc and cup benchmarks, including DRISHTI-GS and REFUGE datasets demonstrate the superiority of the proposed method, which can achieve new state-of-the-art performance approaching 0.9801 and 0.9087 F1 score respectively while gaining 0.9657 D C disc and 0.8976 D C cup . The code will be made publicly available.

Biomedical image segmentation algorithm based on dense atrous convolution

Biomedical images have complex tissue structures, and there are great differences between images of the same part of different individuals. Although deep learning methods have made some progress in automatic segmentation of biomedical images, the segmentation accuracy is relatively low for biomedical images with significant changes in segmentation targets, and there are also problems of missegmentation and missed segmentation. To address these challenges, we proposed a biomedical image segmentation method based on dense atrous convolution. First, we added a dense atrous convolution module (DAC) between the encoding and decoding paths of the U-Net network. This module was based on the inception structure and atrous convolution design, which can effectively capture multi-scale features of images. Second, we introduced a dense residual pooling module to detect multi-scale features in images by connecting residual pooling blocks of different sizes. Finally, in the decoding part of the network, we adopted an attention mechanism to suppress background interference by enhancing the weight of the target area. These modules work together to improve the accuracy and robustness of biomedical image segmentation. The experimental results showed that compared to mainstream segmentation networks, our segmentation model exhibited stronger segmentation ability when processing biomedical images with multiple-shaped targets. At the same time, this model can significantly reduce the phenomenon of missed segmentation and missegmentation, improve segmentation accuracy, and make the segmentation results closer to the real situation.

UNet based on dynamic convolution decomposition and triplet attention

The robustness and generalization of medical image segmentation models are being challenged by the differences between different disease types, different image types, and different cases.Deep learning based semantic segmentation methods have been providing state-of-the-art performance in the last few years. One deep learning technique, U-Net, has become the most popular architecture in the medical imaging segmentation. Despite outstanding overall performance in segmenting medical images, it still has the problems of limited feature expression ability and inaccurate segmentation. To this end, we propose a DTA-UNet based on Dynamic Convolution Decomposition (DCD) and Triple Attention (TA). Firstly, the model with Attention U-Net as the baseline network uses DCD to replace all the conventional convolution in the encoding-decoding process to enhance its feature extraction capability. Secondly, we combine TA with Attention Gate (AG) to be used for skip connection in order to highlight lesion regions by removing redundant information in both spatial and channel dimensions. The proposed model are tested on the two public datasets and actual clinical dataset such as the public COVID-SemiSeg dataset, the ISIC 2018 dataset, and the cooperative hospital stroke segmentation dataset. Ablation experiments on the clinical stroke segmentation dataset show the effectiveness of DCD and TA with only a 0.7628 M increase in the number of parameters compared to the baseline model. The proposed DTA-UNet is further evaluated on the three datasets of different types of images to verify its universality. Extensive experimental results show superior performance on different segmentation metrics compared to eight state-of-art methods.The GitHub URL of our code is https://github.com/shuaihou1234/DTA-UNet .

IMoVR-Net: A robust interpretable network for multi-ocular lesion recognition from TAO facial images

Thyroid-associated ophthalmopathy (TAO) is an organ-specific autoimmune disease that seriously affects patient's life and health. However, the early diagnosis of TAO is highly dependent on the physician's subjective experience. Moreover, the currently proposed deep learning networks for eye diseases do not provide robust interpretability concerning feature learning paradigm, model structure, and the number of neurons. But the mentioned components are very important for model interpretability and are key factors that severely affect the transparency of the model. Therefore, a robust interpretable multi-orientation visual recognition network (IMoVR-Net) for TAO multi-ocular lesion recognition is proposed in this paper. Firstly, a multi-orientation visual cascaded encoder composed of the DenseGabor module and the dilated Gabor convolution group is proposed to achieve the fine extraction of multi-directional TAO lesion features by using a novel feature learning paradigm called alternating filtering. Besides, combining information theory and topology tool, an optimization rule based on topological energy entropy is proposed to provide a solid interpretable theory for determining the model structure. Finally, a clustering correlation analysis method is developed to accomplish the determination of the number of convolutional hidden neurons, providing robust interpretability for the selection of the number of neurons. Compared to other advanced models, the IMoVR-Net achieved state-of-the-art performance on different TAO ocular datasets with an average accuracy, sensitivity, precision, and F1 score of 0.878, 87.27 %, 0.875, and 87.39 %, respectively. The IMoVR-Net has good clinical application prospects due to its strong recognition ability and robust interpretability in feature extraction paradigm, model structure, and number of convolutional neurons.

A multimodal screening system for elderly neurological diseases based on deep learning

In this paper, we propose a deep-learning-based algorithm for screening neurological diseases. We proposed various examination protocols for screening neurological diseases and collected data by video-recording persons performing these protocols. We converted video data into human landmarks that capture action information with a much smaller data dimension. We also used voice data which are also effective indicators of neurological disorders. We designed a subnetwork for each protocol to extract features from landmarks or voice and a feature aggregator that combines all the information extracted from the protocols to make a final decision. Multitask learning was applied to screen two neurological diseases. To capture meaningful information about these human landmarks and voices, we applied various pre-trained models to extract preliminary features. The spatiotemporal characteristics of landmarks are extracted using a pre-trained graph neural network, and voice features are extracted using a pre-trained time-delay neural network. These extracted high-level features are then passed onto the subnetworks and an additional feature aggregator that are simultaneously trained. We also used various data augmentation techniques to overcome the shortage of data. Using a frame-length staticizer that considers the characteristics of the data, we can capture momentary tremors without wasting information. Finally, we examine the effectiveness of different protocols and different modalities (different body parts and voice) through extensive experiments. The proposed method achieves AUC scores of 0.802 for stroke and 0.780 for Parkinson's disease, which is effective for a screening system.

Deep learning-based diagnosis of disease activity in patients with Graves' orbitopathy using orbital SPECT/CT

PURPOSE

Orbital [99mTc]TcDTPA orbital single-photon emission computed tomography (SPECT)/CT is an important method for assessing inflammatory activity in patients with Graves' orbitopathy (GO). However, interpreting the results requires substantial physician workload. We aim to propose an automated method called GO-Net to detect inflammatory activity in patients with GO.

MATERIALS AND METHODS

GO-Net had two stages: (1) a semantic V-Net segmentation network (SV-Net) that extracts extraocular muscles (EOMs) in orbital CT images and (2) a convolutional neural network (CNN) that uses SPECT/CT images and the segmentation results to classify inflammatory activity. A total of 956 eyes from 478 patients with GO (active: 475; inactive: 481) at Xiangya Hospital of Central South University were investigated. For the segmentation task, five-fold cross-validation with 194 eyes was used for training and internal validation. For the classification task, 80% of the eye data were used for training and internal fivefold cross-validation, and the remaining 20% of the eye data were used for testing. The EOM regions of interest (ROIs) were manually drawn by two readers and reviewed by an experienced physician as ground truth for segmentation GO activity was diagnosed according to clinical activity scores (CASs) and the SPECT/CT images. Furthermore, results are interpreted and visualized using gradient-weighted class activation mapping (Grad-CAM).

RESULTS

The GO-Net model combining CT, SPECT, and EOM masks achieved a sensitivity of 84.63%, a specificity of 83.87%, and an area under the receiver operating curve (AUC) of 0.89 (p < 0.01) on the test set for distinguishing active and inactive GO. Compared with the CT-only model, the GO-Net model showed superior diagnostic performance. Moreover, Grad-CAM demonstrated that the GO-Net model placed focus on the GO-active regions. For EOM segmentation, our segmentation model achieved a mean intersection over union (IOU) of 0.82.

CONCLUSION

The proposed Go-Net model accurately detected GO activity and has great potential in the diagnosis of GO.

Improved graph neural network-based green anaconda optimization for segmenting and classifying the lung cancer

Normal lung cells incur genetic damage over time, which causes unchecked cell growth and ultimately leads to lung cancer. Nearly 85% of lung cancer cases are caused by smoking, but there exists factual evidence that beta-carotene supplements and arsenic in water may raise the risk of developing the illness. Asbestos, polycyclic aromatic hydrocarbons, arsenic, radon gas, nickel, chromium and hereditary factors represent various lung cancer-causing agents. Therefore, deep learning approaches are employed to quicken the crucial procedure of diagnosing lung cancer. The effectiveness of these methods has increased when used to examine cancer histopathology slides. Initially, the data is gathered from the standard benchmark dataset. Further, the pre-processing of the collected images is accomplished using the Gabor filter method. The segmentation of these pre-processed images is done through the modified expectation maximization (MEM) algorithm method. Next, using the histogram of oriented gradient (HOG) scheme, the features are extracted from these segmented images. Finally, the classification of lung cancer is performed by the improved graph neural network (IGNN), where the parameter optimization of graph neural network (GNN) is done by the green anaconda optimization (GAO) algorithm in order to derive the accuracy maximization as the major objective function. This IGNN classifies lung cancer into normal, adeno carcinoma and squamous cell carcinoma as the final output. On comparison with existing methods with respect to distinct performance measures, the simulation findings reveal the betterment of the introduced method.

Deep-Learning-Based Segmentation of Extraocular Muscles from Magnetic Resonance Images

In this study, we investigated the performance of four deep learning frameworks of U-Net, U-NeXt, DeepLabV3+, and ConResNet in multi-class pixel-based segmentation of the extraocular muscles (EOMs) from coronal MRI. Performances of the four models were evaluated and compared with the standard F-measure-based metrics of intersection over union (IoU) and Dice, where the U-Net achieved the highest overall IoU and Dice scores of 0.77 and 0.85, respectively. Centroid distance offset between identified and ground truth EOM centroids was measured where U-Net and DeepLabV3+ achieved low offsets (p > 0.05) of 0.33 mm and 0.35 mm, respectively. Our results also demonstrated that segmentation accuracy varies in spatially different image planes. This study systematically compared factors that impact the variability of segmentation and morphometric accuracy of the deep learning models when applied to segmenting EOMs from MRI.

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.

Automatic segmentation of thyroid with the assistance of the devised boundary improvement based on multicomponent small dataset

Deep learning has been widely considered in medical image segmentation. However, the difficulty of acquiring medical images and labels can affect the accuracy of the segmentation results for deep learning methods. In this paper, an automatic segmentation method is proposed by devising a multicomponent neighborhood extreme learning machine to improve the boundary attention region of the preliminary segmentation results. The neighborhood features are acquired by training U-Nets with the multicomponent small dataset, which consists of original thyroid ultrasound images, Sobel edge images and superpixel images. Afterward, the neighborhood features are selected by min-redundancy and max-relevance filter in the designed extreme learning machine, and the selected features are used to train the extreme learning machine to obtain supplementary segmentation results. Finally, the accuracy of the segmentation results is improved by adjusting the boundary attention region of the preliminary segmentation results with the supplementary segmentation results. This method combines the advantages of deep learning and traditional machine learning, boosting the accuracy of thyroid segmentation accuracy with a small dataset in a multigroup test.

Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks

Computed tomography (CT) imaging of the orbit with measurement of extraocular muscle size can be useful for diagnosing and monitoring conditions that affect extraocular muscles. However, the manual measurement of extraocular muscle size can be time-consuming and tedious. The purpose of this study is to evaluate the effectiveness of deep learning algorithms in segmenting extraocular muscles and measuring muscle sizes from CT images. Consecutive CT scans of orbits from 210 patients between 1 January 2010 and 31 December 2019 were used. Extraocular muscles were manually annotated in the studies, which were then used to train the deep learning algorithms. The proposed U-net algorithm can segment extraocular muscles on coronal slices of 32 test samples with an average dice score of 0.92. The thickness and area measurements from predicted segmentations had a mean absolute error (MAE) of 0.35 mm and 3.87 mm2, respectively, with a corresponding mean absolute percentage error (MAPE) of 7 and 9%, respectively. On qualitative analysis of 32 test samples, 30 predicted segmentations from the U-net algorithm were accepted while 2 were rejected. Based on the results from quantitative and qualitative evaluation, this study demonstrates that CNN-based deep learning algorithms are effective at segmenting extraocular muscles and measuring muscles sizes.

Residual based attention-Unet combing DAC and RMP modules for automatic liver tumor segmentation in CT

Purpose: Due to the complex distribution of liver tumors in the abdomen, the accuracy of liver tumor segmentation cannot meet the needs of clinical assistance yet. This paper aims to propose a new end-to-end network to improve the segmentation accuracy of liver tumors from CT. Method: We proposed a hybrid network, leveraging the residual block, the context encoder (CE), and the Attention-Unet, called ResCEAttUnet. The CE comprises a dense atrous convolution (DAC) module and a residual multi-kernel pooling (RMP) module. The DAC module ensures the network derives high-level semantic information and minimizes detailed information loss. The RMP module improves the ability of the network to extract multi-scale features. Moreover, a hybrid loss function based on cross-entropy and Tversky loss function is employed to distribute the weights of the two-loss parts through training iterations. Results: We evaluated the proposed method in LiTS17 and 3DIRCADb databases. It significantly improved the segmentation accuracy compared to state-of-the-art methods. Conclusions: Experimental results demonstrate the satisfying effects of the proposed method through both quantitative and qualitative analyses, thus proving a promising tool in liver tumor segmentation.

Nerve optic segmentation in CT images using a deep learning model and a texture descriptor

The increased intracranial pressure (ICP) can be described as an increase in pressure around the brain and can lead to serious health problems. The assessment of ultrasound images is commonly conducted by skilled experts which is a time-consuming approach, but advanced computer-aided diagnosis (CAD) systems can assist the physician to decrease the time of ICP diagnosis. The accurate detection of the nerve optic regions, with drawing a precise slope line behind the eyeball and calculating the diameter of nerve optic, are the main aims of this research. First, the Fuzzy C-mean (FCM) clustering is employed for segmenting the input CT screening images into the different parts. Second, a histogram equalization approach is used for region-based image quality enhancement. Then, the Local Directional Number method (LDN) is used for representing some key information in a new image. Finally, a cascade Convolutional Neural Network (CNN) is employed for nerve optic segmentation by two distinct input images. Comprehensive experiments on the CT screening dataset [The Cancer Imaging Archive (TCIA)] consisting of 1600 images show the competitive results of inaccurate extraction of the brain features. Also, the indexes such as Dice, Specificity, and Precision for the proposed approach are reported 87.7%, 91.3%, and 90.1%, respectively. The final classification results show that the proposed approach effectively and accurately detects the nerve optic and its diameter in comparison with the other methods. Therefore, this method can be used for early diagnose of ICP and preventing the occurrence of serious health problems in patients.