Transfer Learning for Image Segmentation by Combining Image Weighting and Kernel Learning

Cross-Anatomy Transfer Learning via Shape-Aware Adaptive Fine-Tuning for 3D Vessel Segmentation

Deep learning methods have recently achieved remarkable performance in vessel segmentation applications, yet require numerous labor-intensive labeled data. To alleviate the requirement of manual annotation, transfer learning methods can potentially be used to acquire the related knowledge of tubular structures from public large-scale labeled vessel datasets for target vessel segmentation in other anatomic sites of the human body. However, the cross-anatomy domain shift is a challenging task due to the formidable discrepancy among various vessel structures in different anatomies, resulting in the limited performance of transfer learning. Therefore, we propose a cross-anatomy transfer learning framework for 3D vessel segmentation, which first generates a pre-trained model on a public hepatic vessel dataset and then adaptively fine-tunes our target segmentation network initialized from the model for segmentation of other anatomic vessels. In the framework, the adaptive fine-tuning strategy is presented to dynamically decide on the frozen or fine-tuned filters of the target network for each input sample with a proxy network. Moreover, we develop a Gaussian-based signed distance map that explicitly encodes vessel-specific shape context. The prediction of the map is added as an auxiliary task in the segmentation network to capture geometry-aware knowledge in the fine-tuning. We demonstrate the effectiveness of our method through extensive experiments on two small-scale datasets of coronary artery and brain vessel. The results indicate the proposed method effectively overcomes the discrepancy of cross-anatomy domain shift to achieve accurate vessel segmentation for these two datasets.

Oral epithelial dysplasia detection and grading in oral leukoplakia using deep learning

BACKGROUND

The grading of oral epithelial dysplasia is often time-consuming for oral pathologists and the results are poorly reproducible between observers. In this study, we aimed to establish an objective, accurate and useful detection and grading system for oral epithelial dysplasia in the whole-slides of oral leukoplakia.

METHODS

Four convolutional neural networks were compared using the image patches from 56 whole-slide of oral leukoplakia labeled by pathologists as the gold standard. Sequentially, feature detection models were trained, validated and tested with 1,000 image patches using the optimal network. Lastly, a comprehensive system named E-MOD-plus was established by combining feature detection models and a multiclass logistic model.

RESULTS

EfficientNet-B0 was selected as the optimal network to build feature detection models. In the internal dataset of whole-slide images, the prediction accuracy of E-MOD-plus was 81.3% (95% confidence interval: 71.4-90.5%) and the area under the receiver operating characteristic curve was 0.793 (95% confidence interval: 0.650 to 0.925); in the external dataset of 229 tissue microarray images, the prediction accuracy was 86.5% (95% confidence interval: 82.4-90.0%) and the area under the receiver operating characteristic curve was 0.669 (95% confidence interval: 0.496 to 0.843).

CONCLUSIONS

E-MOD-plus was objective and accurate in the detection of pathological features as well as the grading of oral epithelial dysplasia, and had potential to assist pathologists in clinical practice.

Cell classification with worse-case boosting for intelligent cervical cancer screening

Cell classification underpins intelligent cervical cancer screening, a cytology examination that effectively decreases both the morbidity and mortality of cervical cancer. This task, however, is rather challenging, mainly due to the difficulty of collecting a training dataset representative sufficiently of the unseen test data, as there are wide variations of cells' appearance and shape at different cancerous statuses. This difficulty makes the classifier, though trained properly, often classify wrongly for cells that are underrepresented by the training dataset, eventually leading to a wrong screening result. To address it, we propose a new learning algorithm, called worse-case boosting, for classifiers effectively learning from under-representative datasets in cervical cell classification. The key idea is to learn more from worse-case data for which the classifier has a larger gradient norm compared to other training data, so these data are more likely to correspond to underrepresented data, by dynamically assigning them more training iterations and larger loss weights for boosting the generalizability of the classifier on underrepresented data. We achieve this idea by sampling worse-case data per the gradient norm information and then enhancing their loss values to update the classifier. We demonstrate the effectiveness of this new learning algorithm on two publicly available cervical cell classification datasets (the two largest ones to the best of our knowledge), and positive results (4% accuracy improvement) yield in the extensive experiments. The source codes are available at: https://github.com/YouyiSong/Worse-Case-Boosting.

Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans

The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.

Research on anti-clogging of ore conveyor belt with static image based on improved Fast-SCNN and U-Net

This paper presents an improved Fast-Segmentation Convolutional Neural Network (Fast-SCNN) and U-Net networks based on the channel attention mechanism. While ensuring the speed of network detection, the accuracy of image segmentation is also considered. The experimental results show that the accuracy rate of improved Fast-SCNN based on the channel attention mechanism is greatly improved compared with the original Fast-SCNN, reaching 88.056%, and the mean intersection over union is also improved to a certain extent, reaching 81.087%, and the detection speed is better than the original Fast-SCNN network. The accuracy of improved U-Net network based on the channel attention mechanism is 0.91805, which is better than the original U-Net network. In terms of detection speed, the improved U-Net network based on channel attention mechanism has greatly improved compared with the original U-Net network, reaching 24.02 frames per second. In addition, a method of preventing clogging of ore conveyor belts based on static image detection is proposed in this paper. By judging and predicting the blockage of the ore conveyor belt. When the conveyor belt is about to be blocked or has been blocked, the fuzzy algorithm is used to control the ore conveyor belt to slow down and stop, to improve the safety and efficiency of the conveyor belt.

Fine scale hippocampus morphology variation cross 552 healthy subjects from age 20 to 80

The cerebral cortex varies over the course of a person's life span: at birth, the surface is smooth, before becoming more bumpy (deeper sulci and thicker gyri) in middle age, and thinner in senior years. In this work, a similar phenomenon was observed on the hippocampus. It was previously believed the fine-scale morphology of the hippocampus could only be extracted only with high field scanners (7T, 9.4T); however, recent studies show that regular 3T MR scanners can be sufficient for this purpose. This finding opens the door for the study of fine hippocampal morphometry for a large amount of clinical data. In particular, a characteristic bumpy and subtle feature on the inferior aspect of the hippocampus, which we refer to as hippocampal dentation, presents a dramatic degree of variability between individuals from very smooth to highly dentated. In this report, we propose a combined method joining deep learning and sub-pixel level set evolution to efficiently obtain fine-scale hippocampal segmentation on 552 healthy subjects. Through non-linear dentation extraction and fitting, we reveal that the bumpiness of the inferior surface of the human hippocampus has a clear temporal trend. It is bumpiest between 40 and 50 years old. This observation should be aligned with neurodevelopmental and aging stages.

Domain Adapted Multitask Learning for Segmenting Amoeboid Cells in Microscopy

The method proposed in this paper is a robust combination of multi-task learning and unsupervised domain adaptation for segmenting amoeboid cells in microscopy. A highlight of this work is the manner in which the model's hyperparameters are estimated. The detriments of ad-hoc parameter estimation are well known, but this issue remains largely unaddressed in the context of CNN-based segmentation. Using a novel min-max formulation of the segmentation cost function our proposed method analytically estimates the model's hyperparameters, while simultaneously learning the CNN weights during training. This end-to-end framework provides a consolidated mechanism to harness the potential of multi-task learning to isolate and segment clustered cells from low contrast brightfield images, and it simultaneously leverages deep domain adaptation to segment fluorescent cells without explicit pixel-level re- annotation of the data. Experimental validations on multi-cellular images strongly suggest the effectiveness of the proposed technique, and our quantitative results show at least 15% and 10% improvement in cell segmentation on brightfield and fluorescence images respectively compared to contemporary supervised segmentation methods.

Automated segmentation of whole-body CT images for body composition analysis in pediatric patients using a deep neural network

OBJECTIVES

To develop an automatic segmentation algorithm using a deep neural network with transfer learning applicable to whole-body PET-CT images in children.

METHODS

For model development, we utilized transfer learning with a pre-trained model based on adult patients. We used CT images of 31 pediatric patients under 19 years of age (mean age, 9.6 years) who underwent PET-CT from institution #1 for transfer learning. Two radiologists manually labeled the skin, bone, muscle, abdominal visceral fat, subcutaneous fat, internal organs, and central nervous system in each CT slice and used these as references. For external validation, we collected 14 pediatric PET/CT scans from institution #2 (mean age, 9.1 years). The Dice similarity coefficients (DSCs), sensitivities, and precision were compared between the algorithms before and after transfer learning. In addition, we evaluated segmentation performance according to sex, age (≤ 8 vs. > 8 years), and body mass index (BMI, ≤ 20 vs. > 20 kg/m²).

RESULTS

The algorithm after transfer learning showed better performance than the algorithm before transfer learning for all body compositions (p < 0.001). The average DSC, sensitivity, and precision of each algorithm before and after transfer learning were 98.23% and 99.28%, 98.16% and 99.28%, and 98.29% and 99.28%, respectively. The segmentation performance of the algorithm was generally not affected by age, sex, or BMI, except for precision in the body muscle compartment.

CONCLUSION

The developed model with transfer learning enabled accurate and fully automated segmentation of multiple tissues on whole-body CT scans in children.

KEY POINTS

• We utilized transfer learning with a pre-trained segmentation algorithm for adult to develop an algorithm for automated segmentation of pediatric whole-body CT. • This algorithm showed excellent performance and was not affected by sex, age, or body mass index, except for precision in body muscle.

Medical Image Segmentation Algorithm for Three-Dimensional Multimodal Using Deep Reinforcement Learning and Big Data Analytics

To avoid the problems of relative overlap and low signal-to-noise ratio (SNR) of segmented three-dimensional (3D) multimodal medical images, which limit the effect of medical image diagnosis, a 3D multimodal medical image segmentation algorithm using reinforcement learning and big data analytics is proposed. Bayesian maximum a posteriori estimation method and improved wavelet threshold function are used to design wavelet shrinkage algorithm to remove high-frequency signal component noise in wavelet domain. The low-frequency signal component is processed by bilateral filtering and the inverse wavelet transform is used to denoise the 3D multimodal medical image. An end-to-end DRD U-Net model based on deep reinforcement learning is constructed. The feature extraction capacity of denoised image segmentation is increased by changing the convolution layer in the traditional reinforcement learning model to the residual module and introducing the multiscale context feature extraction module. The 3D multimodal medical image segmentation is done using the reward and punishment mechanism in the deep learning reinforcement algorithm. In order to verify the effectiveness of 3D multimodal medical image segmentation algorithm, the LIDC-IDRI data set, the SCR data set, and the DeepLesion data set are selected as the experimental data set of this article. The results demonstrate that the algorithm's segmentation effect is effective. When the number of iterations is increased to 250, the structural similarity reaches 98%, the SNR is always maintained between 55 and 60 dB, the training loss is modest, relative overlap and accuracy all exceed 95%, and the overall segmentation performance is superior. Readers will understand how deep reinforcement learning and big data analytics test the effectiveness of 3D multimodal medical image segmentation algorithm.

Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review

Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging was the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.

A New Method of Deep Convolutional Neural Network Image Classification Based on Knowledge Transfer in Small Label Sample Environment

The problem of deep learning network image classification when a large number of image samples are obtained in life and with only a small amount of knowledge annotation, is preliminarily solved in this paper. First, a support vector machine expert labeling system is constructed by using a bag-of-words model to extract image features from a small number of labeled samples. The labels of a large number of unlabeled image samples are automatically annotated by using the constructed SVM expert labeling system. Second, a small number of labeled samples and automatically labeled image samples are combined to form an augmented training set. A deep convolutional neural network model is created by using an augmented training set. Knowledge transfer from SVMs trained with a small number of image samples annotated by artificial knowledge to deep neural network classifiers is implemented in this paper. The problem of overfitting in neural network training with small samples is solved. Finally, the public dataset caltech256 is used for experimental verification and mechanism analysis of the performance of the new method.

Flood Detection Using Real-Time Image Segmentation from Unmanned Aerial Vehicles on Edge-Computing Platform

With the proliferation of unmanned aerial vehicles (UAVs) in different contexts and application areas, efforts are being made to endow these devices with enough intelligence so as to allow them to perform complex tasks with full autonomy. In particular, covering scenarios such as disaster areas may become particularly difficult due to infrastructure shortage in some areas, often impeding a cloud-based analysis of the data in near-real time. Enabling AI techniques at the edge is therefore fundamental so that UAVs themselves can both capture and process information to gain an understanding of their context, and determine the appropriate course of action in an independent manner. Towards this goal, in this paper, we take determined steps towards UAV autonomy in a disaster scenario such as a flood. In particular, we use a dataset of UAV images relative to different floods taking place in Spain, and then use an AI-based approach that relies on three widely used deep neural networks (DNNs) for semantic segmentation of images, to automatically determine the regions more affected by rains (flooded areas). The targeted algorithms are optimized for GPU-based edge computing platforms, so that the classification can be carried out on the UAVs themselves, and only the algorithm output is uploaded to the cloud for real-time tracking of the flooded areas. This way, we are able to reduce dependency on infrastructure, and to reduce network resource consumption, making the overall process greener and more robust to connection disruptions. Experimental results using different types of hardware and different architectures show that it is feasible to perform advanced real-time processing of UAV images using sophisticated DNN-based solutions.

Automated delineation of orbital abscess depicted on CT scan using deep learning

OBJECTIVES

To develop and validate a deep learning algorithm to automatically detect and segment an orbital abscess depicted on computed tomography (CT).

METHODS

We retrospectively collected orbital CT scans acquired on 67 pediatric subjects with a confirmed orbital abscess in the setting of infectious orbital cellulitis. A context-aware convolutional neural network (CA-CNN) was developed and trained to automatically segment orbital abscess. To reduce the requirement for a large dataset, transfer learning was used by leveraging a pre-trained model for CT-based lung segmentation. An ophthalmologist manually delineated orbital abscesses depicted on the CT images. The classical U-Net and the CA-CNN models with and without transfer learning were trained and tested on the collected dataset using the 10-fold cross-validation method. Dice coefficient, Jaccard index, and Hausdorff distance were used as performance metrics to assess the agreement between the computerized and manual segmentations.

RESULTS

The context-aware U-Net with transfer learning achieved an average Dice coefficient and Jaccard index of 0.78 ± 0.12 and 0.65 ± 0.13, which were consistently higher than the classical U-Net or the context-aware U-Net without transfer learning (P < 0.01). The average differences of the abscess between the computerized results and the experts in terms of volume and Hausdorff distance were 0.10 ± 0.11 mL and 1.94 ± 1.21 mm, respectively. The context-aware U-Net detected all orbital abscess without false positives.

CONCLUSIONS

The deep learning solution demonstrated promising performance in detecting and segmenting orbital abscesses on CT images in strong agreement with a human observer.

Automated cardiac segmentation of cross-modal medical images using unsupervised multi-domain adaptation and spatial neural attention structure

Accurate cardiac segmentation of multimodal images, e.g., magnetic resonance (MR), computed tomography (CT) images, plays a pivot role in auxiliary diagnoses, treatments and postoperative assessments of cardiovascular diseases. However, training a well-behaved segmentation model for the cross-modal cardiac image analysis is challenging, due to their diverse appearances/distributions from different devices and acquisition conditions. For instance, a well-trained segmentation model based on the source domain of MR images is often failed in the segmentation of CT images. In this work, a cross-modal images-oriented cardiac segmentation scheme is proposed using a symmetric full convolutional neural network (SFCNN) with the unsupervised multi-domain adaptation (UMDA) and a spatial neural attention (SNA) structure, termed UMDA-SNA-SFCNN, having the merits of without the requirement of any annotation on the test domain. Specifically, UMDA-SNA-SFCNN incorporates SNA to the classic adversarial domain adaptation network to highlight the relevant regions, while restraining the irrelevant areas in the cross-modal images, so as to suppress the negative transfer in the process of unsupervised domain adaptation. In addition, the multi-layer feature discriminators and a predictive segmentation-mask discriminator are established to connect the multi-layer features and segmentation mask of the backbone network, SFCNN, to realize the fine-grained alignment of unsupervised cross-modal feature domains. Extensive confirmative and comparative experiments on the benchmark Multi-Modality Whole Heart Challenge dataset show that the proposed model is superior to the state-of-the-art cross-modal segmentation methods.

Speech Vision: An End-to-End Deep Learning-Based Dysarthric Automatic Speech Recognition System

Dysarthria is a disorder that affects an individual's speech intelligibility due to the paralysis of muscles and organs involved in the articulation process. As the condition is often associated with physically debilitating disabilities, not only do such individuals face communication problems, but also interactions with digital devices can become a burden. For these individuals, automatic speech recognition (ASR) technologies can make a significant difference in their lives as computing and portable digital devices can become an interaction medium, enabling them to communicate with others and computers. However, ASR technologies have performed poorly in recognizing dysarthric speech, especially for severe dysarthria, due to multiple challenges facing dysarthric ASR systems. We identified these challenges are due to the alternation and inaccuracy of dysarthric phonemes, the scarcity of dysarthric speech data, and the phoneme labeling imprecision. This paper reports on our second dysarthric-specific ASR system, called Speech Vision (SV) that tackles these challenges by adopting a novel approach towards dysarthric ASR in which speech features are extracted visually, then SV learns to see the shape of the words pronounced by dysarthric individuals. This visual acoustic modeling feature of SV eliminates phoneme-related challenges. To address the data scarcity problem, SV adopts visual data augmentation techniques, generates synthetic dysarthric acoustic visuals, and leverages transfer learning. Benchmarking with other state-of-the-art dysarthric ASR considered in this study, SV outperformed them by improving recognition accuracies for 67% of UA-Speech speakers, where the biggest improvements were achieved for severe dysarthria.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

A Novel Negative-Transfer-Resistant Fuzzy Clustering Model With a Shared Cross-Domain Transfer Latent Space and its Application to Brain CT Image Segmentation

Traditional clustering algorithms for medical image segmentation can only achieve satisfactory clustering performance under relatively ideal conditions, in which there is adequate data from the same distribution, and the data is rarely disturbed by noise or outliers. However, a sufficient amount of medical images with representative manual labels are often not available, because medical images are frequently acquired with different scanners (or different scan protocols) or polluted by various noises. Transfer learning improves learning in the target domain by leveraging knowledge from related domains. Given some target data, the performance of transfer learning is determined by the degree of relevance between the source and target domains. To achieve positive transfer and avoid negative transfer, a negative-transfer-resistant mechanism is proposed by computing the weight of transferred knowledge. Extracting a negative-transfer-resistant fuzzy clustering model with a shared cross-domain transfer latent space (called NTR-FC-SCT) is proposed by integrating negative-transfer-resistant and maximum mean discrepancy (MMD) into the framework of fuzzy c-means clustering. Experimental results show that the proposed NTR-FC-SCT model outperformed several traditional non-transfer and related transfer clustering algorithms.

On-Line Multi-Class Segmentation of Side-Scan Sonar Imagery Using an Autonomous Underwater Vehicle

This paper proposes a method to perform on-line multi-class segmentation of Side-Scan Sonar acoustic images, thus being able to build a semantic map of the sea bottom usable to search loop candidates in a SLAM context. The proposal follows three main steps. First, the sonar data is pre-processed by means of acoustics based models. Second, the data is segmented thanks to a lightweight Convolutional Neural Network which is fed with acoustic swaths gathered within a temporal window. Third, the segmented swaths are fused into a consistent segmented image. The experiments, performed with real data gathered in coastal areas of Mallorca (Spain), explore all the possible configurations and show the validity of our proposal both in terms of segmentation quality, with per-class precisions and recalls surpassing the 90%, and in terms of computational speed, requiring less than a 7% of CPU time on a standard laptop computer. The fully documented source code, and some trained models and datasets are provided as part of this study.

Deep Learning-Based Development of Personalized Human Head Model With Non-Uniform Conductivity for Brain Stimulation

Electromagnetic stimulation of the human brain is a key tool for neurophysiological characterization and the diagnosis of several neurological disorders. Transcranial magnetic stimulation (TMS) is a commonly used clinical procedure. However, personalized TMS requires a pipeline for individual head model generation to provide target-specific stimulation. This process includes intensive segmentation of several head tissues based on magnetic resonance imaging (MRI), which has significant potential for segmentation error, especially for low-contrast tissues. Additionally, a uniform electrical conductivity is assigned to each tissue in the model, which is an unrealistic assumption based on conventional volume conductor modeling. This study proposes a novel approach for fast and automatic estimation of the electric conductivity in the human head for volume conductor models without anatomical segmentation. A convolutional neural network is designed to estimate personalized electrical conductivity values based on anatomical information obtained from T1- and T2-weighted MRI scans. This approach can avoid the time-consuming process of tissue segmentation and maximize the advantages of position-dependent conductivity assignment based on the water content values estimated from MRI intensity values. The computational results of the proposed approach provide similar but smoother electric field distributions of the brain than that provided by conventional approaches.

DMCNN: A Deep Multiscale Convolutional Neural Network Model for Medical Image Segmentation

Medical image segmentation is one of the hot issues in the related area of image processing. Precise segmentation for medical images is a vital guarantee for follow-up treatment. At present, however, low gray contrast and blurred tissue boundaries are common in medical images, and the segmentation accuracy of medical images cannot be effectively improved. Especially, deep learning methods need more training samples, which lead to time-consuming process. Therefore, we propose a novelty model for medical image segmentation based on deep multiscale convolutional neural network (CNN) in this article. First, we extract the region of interest from the raw medical images. Then, data augmentation is operated to acquire more training datasets. Our proposed method contains three models: encoder, U-net, and decoder. Encoder is mainly responsible for feature extraction of 2D image slice. The U-net cascades the features of each block of the encoder with those obtained by deconvolution in the decoder under different scales. The decoding is mainly responsible for the upsampling of the feature graph after feature extraction of each group. Simulation results show that the new method can boost the segmentation accuracy. And, it has strong robustness compared with other segmentation methods.

StoolNet for Color Classification of Stool Medical Images

The color classification of stool medical images is commonly used to diagnose digestive system diseases, so it is important in clinical examination. In order to reduce laboratorians’ heavy burden, advanced digital image processing technologies and deep learning methods are employed for the automatic color classification of stool images in this paper. The region of interest (ROI) is segmented automatically and then classified with a shallow convolutional neural network (CNN) dubbed StoolNet. Thanks to its shallow structure and accurate segmentation, StoolNet can converge quickly. The sufficient experiments confirm the good performance of StoolNet and the impact of the different training sample numbers on StoolNet. The proposed method has several advantages, such as low cost, accurate automatic segmentation, and color classification. Therefore, it can be widely used in artificial intelligence (AI) healthcare.

Channel-Unet: A Spatial Channel-Wise Convolutional Neural Network for Liver and Tumors Segmentation

It is a challenge to automatically and accurately segment the liver and tumors in computed tomography (CT) images, as the problem of over-segmentation or under-segmentation often appears when the Hounsfield unit (Hu) of liver and tumors is close to the Hu of other tissues or background. In this paper, we propose the spatial channel-wise convolution, a convolutional operation along the direction of the channel of feature maps, to extract mapping relationship of spatial information between pixels, which facilitates learning the mapping relationship between pixels in the feature maps and distinguishing the tumors from the liver tissue. In addition, we put forward an iterative extending learning strategy, which optimizes the mapping relationship of spatial information between pixels at different scales and enables spatial channel-wise convolution to map the spatial information between pixels in high-level feature maps. Finally, we propose an end-to-end convolutional neural network called Channel-UNet, which takes UNet as the main structure of the network and adds spatial channel-wise convolution in each up-sampling and down-sampling module. The network can converge the optimized mapping relationship of spatial information between pixels extracted by spatial channel-wise convolution and information extracted by feature maps and realizes multi-scale information fusion. The proposed ChannelUNet is validated by the segmentation task on the 3Dircadb dataset. The Dice values of liver and tumors segmentation were 0.984 and 0.940, which is slightly superior to current best performance. Besides, compared with the current best method, the number of parameters of our method reduces by 25.7%, and the training time of our method reduces by 33.3%. The experimental results demonstrate the efficiency and high accuracy of Channel-UNet in liver and tumors segmentation in CT images.

3D Flow Entropy Contour Fitting Segmentation Algorithm Based on Multi-Scale Transform Contour Constraint

Image segmentation is a crucial topic in image analysis and understanding, and the foundation of target detection and recognition. Image segmentation, essentially, can be considered as classifying the image according to the consistency of the region and the inconsistency between regions, it is widely used in medical and criminal investigation, cultural relic identification, monitoring and so forth. There are two outstanding common problems in the existing segmentation algorithm, one is the lack of accuracy, and the other is that it is not widely applicable. The main contribution of this paper is to present a novel segmentation method based on the information entropy theory and multi-scale transform contour constraint. Firstly, the target contour is initially obtained by means of a multi-scale sample top-hat and bottom-hat transform and an improved watershed method. Subsequently, in terms of this initial contour, the interesting areas can be finely segmented out with an innovative 3D flow entropy method. Finally, the sufficient synthetic and real experiments proved that the proposed algorithm can greatly improve the segmentation effect. In addition, it is widely applicable.