Deep semantic segmentation of natural and medical images: a review

An efficient segment anything model for the segmentation of medical images

This paper introduces the efficient medical-images-aimed segment anything model (EMedSAM), addressing the high computational demands and limited adaptability of using SAM for medical image segmentation tasks. We present a novel, compact image encoder, DD-TinyViT, designed to enhance segmentation efficiency through an innovative parameter tuning method called med-adapter. The lightweight DD-TinyViT encoder is derived from the well-known ViT-H using a decoupled distillation approach.The segmentation and recognition capabilities of EMedSAM for specific structures are improved by med-adapter, which dynamically adjusts the model parameters specifically for medical imaging. We conducted extensive testing on EMedSAM using the public FLARE 2022 dataset and datasets from the First Hospital of Zhejiang University School of Medicine. The results demonstrate that our model outperforms existing state-of-the-art models in both multi-organ and lung segmentation tasks.

Pan-cancer image segmentation based on feature pyramids and Mask R-CNN framework

BACKGROUND

Cancer, a disease with a high mortality rate, poses a great threat to patients' physical and mental health and can lead to huge medical costs and emotional damage. With the continuous development of artificial intelligence technologies, deep learning-based cancer image segmentation techniques are becoming increasingly important in cancer detection and accurate diagnosis. However, in segmentation tasks, there are differences in efficiency between large and small objects and limited segmentation effects on objects of individual sizes. The previous segmentation frameworks still have room for improvement in multi-scale collaboration when segmenting objects.

PURPOSE

This paper proposes a method to train a deep learning segmentation framework using a feature pyramid processing dataset to improve the average precision (AP) index, and realizes multi-scale cooperation in target segmentation.

OBJECTIVE

Pan-Cancer Histology Dataset for Nuclei Instance Segmentation and Classification (PanNuke) dataset was selected to include approximately 7500 pathology images with cells from 19 different types of tissues, including five classifications of cancer, non-cancer, inflammation, death, and connective tissue.

METHODS

First, the method uses whole-slide images in the pan-cancer histology dataset for nuclei instance segmentation and classification (PanNuke) dataset, combined with the mask region convolutional neural network (Mask R-CNN) segmentation framework and improved loss function to segment and detect each cellular tissue in cancerous sections. Second, to address the problem of non-synergistic object segmentation at different scales in cancerous tissue segmentation, a scheme using feature pyramids to process the dataset was adopted as part of the feature extraction module.

RESULTS

Extensive experimental results on this dataset show that the method in this paper yields 0.269 AP and a boost of about 4% compared to the original Mask R-CNN framework.

CONCLUSIONS

It is effective and feasible to use feature pyramid to process data set to improve the effect of medical image segmentation.

FCSU-Net: A novel full-scale Cross-dimension Self-attention U-Net with collaborative fusion of multi-scale feature for medical image segmentation

Recently, ViT and CNNs based on encoder-decoder architecture have become the dominant model in the field of medical image segmentation. However, there are some deficiencies for each of them: (1) It is difficult for CNNs to capture the interaction between two locations with consideration of the longer distance. (2) ViT cannot acquire the interaction of local context information and carries high computational complexity. To optimize the above deficiencies, we propose a new network for medical image segmentation, which is called FCSU-Net. FCSU-Net uses the proposed collaborative fusion of multi-scale feature block that enables the network to obtain more abundant and more accurate features. In addition, FCSU-Net fuses full-scale feature information through the FFF (Full-scale Feature Fusion) structure instead of simple skip connections, and establishes long-range dependencies on multiple dimensions through the CS (Cross-dimension Self-attention) mechanism. Meantime, every dimension is complementary to each other. Also, CS mechanism has the advantage of convolutions capturing local contextual weights. Finally, FCSU-Net is validated on several datasets, and the results show that FCSU-Net not only has a relatively small number of parameters, but also has a leading segmentation performance.

From CNN to Transformer: A Review of Medical Image Segmentation Models

Medical image segmentation is an important step in medical image analysis, especially as a crucial prerequisite for efficient disease diagnosis and treatment. The use of deep learning for image segmentation has become a prevalent trend. The widely adopted approach currently is U-Net and its variants. Moreover, with the remarkable success of pre-trained models in natural language processing tasks, transformer-based models like TransUNet have achieved desirable performance on multiple medical image segmentation datasets. Recently, the Segment Anything Model (SAM) and its variants have also been attempted for medical image segmentation. In this paper, we conduct a survey of the most representative seven medical image segmentation models in recent years. We theoretically analyze the characteristics of these models and quantitatively evaluate their performance on Tuberculosis Chest X-rays, Ovarian Tumors, and Liver Segmentation datasets. Finally, we discuss the main challenges and future trends in medical image segmentation. Our work can assist researchers in the related field to quickly establish medical segmentation models tailored to specific regions.

Deep learning empowered breast cancer diagnosis: Advancements in detection and classification

Recent advancements in AI, driven by big data technologies, have reshaped various industries, with a strong focus on data-driven approaches. This has resulted in remarkable progress in fields like computer vision, e-commerce, cybersecurity, and healthcare, primarily fueled by the integration of machine learning and deep learning models. Notably, the intersection of oncology and computer science has given rise to Computer-Aided Diagnosis (CAD) systems, offering vital tools to aid medical professionals in tumor detection, classification, recurrence tracking, and prognosis prediction. Breast cancer, a significant global health concern, is particularly prevalent in Asia due to diverse factors like lifestyle, genetics, environmental exposures, and healthcare accessibility. Early detection through mammography screening is critical, but the accuracy of mammograms can vary due to factors like breast composition and tumor characteristics, leading to potential misdiagnoses. To address this, an innovative CAD system leveraging deep learning and computer vision techniques was introduced. This system enhances breast cancer diagnosis by independently identifying and categorizing breast lesions, segmenting mass lesions, and classifying them based on pathology. Thorough validation using the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) demonstrated the CAD system's exceptional performance, with a 99% success rate in detecting and classifying breast masses. While the accuracy of detection is 98.5%, when segmenting breast masses into separate groups for examination, the method's performance was approximately 95.39%. Upon completing all the analysis, the system's classification phase yielded an overall accuracy of 99.16% for classification. The potential for this integrated framework to outperform current deep learning techniques is proposed, despite potential challenges related to the high number of trainable parameters. Ultimately, this recommended framework offers valuable support to researchers and physicians in breast cancer diagnosis by harnessing cutting-edge AI and image processing technologies, extending recent advances in deep learning to the medical domain.

DermSynth3D: Synthesis of in-the-wild annotated dermatology images

In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis. However, existing datasets in this domain have significant limitations, including a small number of image samples, limited disease conditions, insufficient annotations, and non-standardized image acquisitions. To address these shortcomings, we propose a novel framework called DermSynth3D. DermSynth3D blends skin disease patterns onto 3D textured meshes of human subjects using a differentiable renderer and generates 2D images from various camera viewpoints under chosen lighting conditions in diverse background scenes. Our method adheres to top-down rules that constrain the blending and rendering process to create 2D images with skin conditions that mimic in-the-wild acquisitions, ensuring more meaningful results. The framework generates photo-realistic 2D dermatological images and the corresponding dense annotations for semantic segmentation of the skin, skin conditions, body parts, bounding boxes around lesions, depth maps, and other 3D scene parameters, such as camera position and lighting conditions. DermSynth3D allows for the creation of custom datasets for various dermatology tasks. We demonstrate the effectiveness of data generated using DermSynth3D by training DL models on synthetic data and evaluating them on various dermatology tasks using real 2D dermatological images. We make our code publicly available at https://github.com/sfu-mial/DermSynth3D.

Nuclei-level prior knowledge constrained multiple instance learning for breast histopathology whole slide image classification

New breast cancer cases have surpassed lung cancer, becoming the world's most prevalent cancer. Despite advancing medical image analysis, deep learning's lack of interpretability limits its adoption among pathologists. Hence, a nuclei-level prior knowledge constrained multiple instance learning (MIL) (NPKC-MIL) for breast whole slide image (WSI) classification is proposed. NPKC-MIL primarily involves the following steps: Initially, employing the transfer learning to extract patch-level features and aggregate them into slide-level features through attention pooling. Subsequently, abstract the extracted nuclei as nodes, establish nucleus topology using the K-NN (K-Nearest Neighbors, K-NN) algorithm, and create handcrafted features for nodes. Finally, combine patch-level deep learning features with nuclei-level handcrafted features to fine-tune classification results generated by slide-level deep learning features. The experimental results demonstrate that NPKC-MIL outperforms current comparable deep learning models. NPKC-MIL expands the analytical dimension of WSI classification tasks and integrates prior knowledge into deep learning models to improve interpretability.

Automated wound segmentation and classification of seven common injuries in forensic medicine

In forensic medical investigations, physical injuries are documented with photographs accompanied by written reports. Automatic segmentation and classification of wounds on these photographs could provide forensic pathologists with a tool to improve the assessment of injuries and accelerate the reporting process. In this pilot study, we trained and compared several preexisting deep learning architectures for image segmentation and wound classification on forensically relevant photographs in our database. The best scores were a mean pixel accuracy of 69.4% and a mean intersection over union (IoU) of 48.6% when evaluating the trained models on our test set. The models had difficulty distinguishing the background from wounded areas. As an example, image pixels showing subcutaneous hematomas or skin abrasions were assigned to the background class in 31% of cases. Stab wounds, on the other hand, were reliably classified with a pixel accuracy of 93%. These results can be partially attributed to undefined wound boundaries for some types of injuries, such as subcutaneous hematoma. However, despite the large class imbalance, we demonstrate that the best trained models could reliably distinguish among seven of the most common wounds encountered in forensic medical investigations.

Few-Shot Medical Image Segmentation via Generating Multiple Representative Descriptors

Automatic medical image segmentation has witnessed significant development with the success of large models on massive datasets. However, acquiring and annotating vast medical image datasets often proves to be impractical due to the time consumption, specialized expertise requirements, and compliance with patient privacy standards, etc. As a result, Few-shot Medical Image Segmentation (FSMIS) has become an increasingly compelling research direction. Conventional FSMIS methods usually learn prototypes from support images and apply nearest-neighbor searching to segment the query images. However, only a single prototype cannot well represent the distribution of each class, thus leading to restricted performance. To address this problem, we propose to Generate Multiple Representative Descriptors (GMRD), which can comprehensively represent the commonality within the corresponding class distribution. In addition, we design a Multiple Affinity Maps based Prediction (MAMP) module to fuse the multiple affinity maps generated by the aforementioned descriptors. Furthermore, to address intra-class variation and enhance the representativeness of descriptors, we introduce two novel losses. Notably, our model is structured as a dual-path design to achieve a balance between foreground and background differences in medical images. Extensive experiments on four publicly available medical image datasets demonstrate that our method outperforms the state-of-the-art methods, and the detailed analysis also verifies the effectiveness of our designed module.

Applying a deep learning pipeline to classify land cover from low-quality historical RGB imagery

Land use and land cover (LULC) classification is becoming faster and more accurate thanks to new deep learning algorithms. Moreover, new high spectral- and spatial-resolution datasets offer opportunities to classify land cover with greater accuracy and class specificity. However, deploying deep learning algorithms to characterize present-day, modern land cover based on state-of-the-art data is insufficient for understanding trends in land cover change and identifying changes in and drivers of ecological and social variables of interest. These identifications require characterizing past land cover, for which imagery is often lower-quality. We applied a deep learning pipeline to classify land cover from historical, low-quality RGB aerial imagery, using a case study of Vancouver, Canada. We deployed an atrous convolutional neural network from DeepLabv3+ (which has previously shown to outperform other networks) and trained it on modern Maxar satellite imagery using a modern land cover classification. We fine-tuned the resultant model using a small dataset of manually annotated and augmented historical imagery. This final model accurately predicted historical land cover classification at rates similar to other studies that used high-quality imagery. These predictions indicate that Vancouver has lost vegetative cover from 1995-2021, including a decrease in conifer cover, an increase in pavement cover, and an overall decrease in tree and grass cover. Our workflow may be harnessed to understand historical land cover and identify land cover change in other regions and at other times.

An Efficient and Rapid Medical Image Segmentation Network

Accurate medical image segmentation is an essential part of the medical image analysis process that provides detailed quantitative metrics. In recent years, extensions of classical networks such as UNet have achieved state-of-the-art performance on medical image segmentation tasks. However, the high model complexity of these networks limits their applicability to devices with constrained computational resources. To alleviate this problem, we propose a shallow hierarchical Transformer for medical image segmentation, called SHFormer. By decreasing the number of transformer blocks utilized, the model complexity of SHFormer can be reduced to an acceptable level. To improve the learned attention while keeping the structure lightweight, we propose a spatial-channel connection module. This module separately learns attention in the spatial and channel dimensions of the feature while interconnecting them to produce more focused attention. To keep the decoder lightweight, the MLP-D module is proposed to progressively fuse multi-scale features in which channels are aligned using Multi-Layer Perceptron (MLP) and spatial information is fused by convolutional blocks. We first validated the performance of SHFormer on the ISIC-2018 dataset. Compared to the latest network, SHFormer exhibits comparable performance with 15 times fewer parameters, 30 times lower computational complexity and 5 times higher inference efficiency. To test the generalizability of SHFormer, we introduced the polyp dataset for additional testing. SHFormer achieves comparable segmentation accuracy to the latest network while having lower computational overhead.

Intraretinal Hyper-Reflective Foci Are Almost Universally Present and Co-Localize With Intraretinal Fluid in Diabetic Macular Edema

Purpose

In diabetic macular edema (DME), hyper-reflective foci (HRF) has been linked to disease severity and progression. Using an automated approach, we aimed to investigate the baseline distribution of HRF in DME and their co-localization with cystoid intraretinal fluid (IRF).

Methods

Baseline spectral-domain optical coherence tomography (SD-OCT) volume scans (N = 1527) from phase III clinical trials YOSEMITE (NCT03622580) and RHINE (NCT03622593) were segmented using a deep-learning-based algorithm (developed using B-scans from BOULEVARD NCT02699450) to detect HRF. The HRF count and volume were assessed. HRF distributions were analyzed in relation to best-corrected visual acuity (BCVA), central subfield thickness (CST), and IRF volume in quartiles, and Diabetic Retinopathy Severity Scores (DRSS) in groups. Co-localization of HRF with IRF was calculated in the central 3-mm diameter using the en face projection.

Results

HRF were present in most patients (up to 99.7%). Median (interquartile range [IQR]) HRF volume within the 3-mm diameter Early Treatment Diabetic Retinopathy Study ring was 1964.3 (3325.2) pL, and median count was 64.0 (IQR = 96.0). Median HRF volumes were greater with decreasing BCVA (nominal P = 0.0109), and increasing CST (nominal P < 0.0001), IRF (nominal P < 0.0001), and DRSS up to very severe nonproliferative diabetic retinopathy (nominal P < 0.0001). HRF co-localized with IRF in the en face projection.

Conclusions

Using automated HRF segmentation of full SD-OCT volumes, we observed that HRF are a ubiquitous feature in DME and exhibit relationships with BCVA, CST, IRF, and DRSS, supporting a potential link to disease severity. The spatial distribution of HRF closely followed that of IRF.

SCIseg: Automatic Segmentation of T2-weighted Intramedullary Lesions in Spinal Cord Injury

Purpose

To develop a deep learning tool for the automatic segmentation of T2-weighted intramedullary lesions in spinal cord injury (SCI).

Material and Methods

This retrospective study included a cohort of SCI patients from three sites enrolled between July 2002 and February 2023. A deep learning model, SCIseg, was trained in a three-phase process involving active learning for the automatic segmentation of intramedullary SCI lesions and the spinal cord. The data consisted of T2-weighted MRI acquired using different scanner manufacturers with heterogeneous image resolutions (isotropic/anisotropic), orientations (axial/sagittal), lesion etiologies (traumatic/ischemic/hemorrhagic) and lesions spread across the cervical, thoracic and lumbar spine. The segmentations from the proposed model were visually and quantitatively compared with other open-source baselines. Wilcoxon signed-rank test was used to compare quantitative MRI biomarkers (lesion volume, lesion length, and maximal axial damage ratio) computed from manual lesion masks and those obtained automatically with SCIseg predictions.

Results

MRI data from 191 SCI patients (mean age, 48.1 years ± 17.9 [SD]; 142 males) were used for model training and evaluation. SCIseg achieved the best segmentation performance for both the cord and lesions. There was no statistically significant difference between lesion length and maximal axial damage ratio computed from manually annotated lesions and those obtained using SCIseg.

Conclusion

Automatic segmentation of intramedullary lesions commonly seen in SCI replaces the tedious manual annotation process and enables the extraction of relevant lesion morphometrics in large cohorts. The proposed model segments lesions across different etiologies, scanner manufacturers, and heterogeneous image resolutions. SCIseg is open-source and accessible through the Spinal Cord Toolbox.

A joint brain extraction and image quality assessment framework for fetal brain MRI slices

Brain extraction and image quality assessment are two fundamental steps in fetal brain magnetic resonance imaging (MRI) 3D reconstruction and quantification. However, the randomness of fetal position and orientation, the variability of fetal brain morphology, maternal organs around the fetus, and the scarcity of data samples, all add excessive noise and impose a great challenge to automated brain extraction and quality assessment of fetal MRI slices. Conventionally, brain extraction and quality assessment are typically performed independently. However, both of them focus on the brain image representation, so they can be jointly optimized to ensure the network learns more effective features and avoid overfitting. To this end, we propose a novel two-stage dual-task deep learning framework with a brain localization stage and a dual-task stage for joint brain extraction and quality assessment of fetal MRI slices. Specifically, the dual-task module compactly contains a feature extraction module, a quality assessment head and a segmentation head with feature fusion for simultaneous brain extraction and quality assessment. Besides, a transformer architecture is introduced into the feature extraction module and the segmentation head. We utilize a multi-step training strategy to guarantee a stable and successful training of all modules. Finally, we validate our method by a 5-fold cross-validation and ablation study on a dataset with fetal brain MRI slices in different qualities, and perform a cross-dataset validation in addition. Experiments show that the proposed framework achieves very promising performance.

SAA-SDM: Neural Networks Faster Learned to Segment Organ Images

In the field of medicine, rapidly and accurately segmenting organs in medical images is a crucial application of computer technology. This paper introduces a feature map module, Strength Attention Area Signed Distance Map (SAA-SDM), based on the principal component analysis (PCA) principle. The module is designed to accelerate neural networks' convergence speed in rapidly achieving high precision. SAA-SDM provides the neural network with confidence information regarding the target and background, similar to the signed distance map (SDM), thereby enhancing the network's understanding of semantic information related to the target. Furthermore, this paper presents a training scheme tailored for the module, aiming to achieve finer segmentation and improved generalization performance. Validation of our approach is carried out using TRUS and chest X-ray datasets. Experimental results demonstrate that our method significantly enhances neural networks' convergence speed and precision. For instance, the convergence speed of UNet and UNET +  + is improved by more than 30%. Moreover, Segformer achieves an increase of over 6% and 3% in mIoU (mean Intersection over Union) on two test datasets without requiring pre-trained parameters. Our approach reduces the time and resource costs associated with training neural networks for organ segmentation tasks while effectively guiding the network to achieve meaningful learning even without pre-trained parameters.

Multi-sample ζ-mixup: richer, more realistic synthetic samples from a p-series interpolant

Modern deep learning training procedures rely on model regularization techniques such as data augmentation methods, which generate training samples that increase the diversity of data and richness of label information. A popular recent method, mixup, uses convex combinations of pairs of original samples to generate new samples. However, as we show in our experiments, mixup  can produce undesirable synthetic samples, where the data is sampled off the manifold and can contain incorrect labels. We propose ζ -mixup, a generalization of mixup  with provably and demonstrably desirable properties that allows convex combinations of T ≥ 2 samples, leading to more realistic and diverse outputs that incorporate information from T original samples by using a p-series interpolant. We show that, compared to mixup, ζ -mixup  better preserves the intrinsic dimensionality of the original datasets, which is a desirable property for training generalizable models. Furthermore, we show that our implementation of ζ -mixup  is faster than mixup, and extensive evaluation on controlled synthetic and 26 diverse real-world natural and medical image classification datasets shows that ζ -mixup  outperforms mixup, CutMix, and traditional data augmentation techniques. The code will be released at https://github.com/kakumarabhishek/zeta-mixup.

Review of reinforcement learning applications in segmentation, chemotherapy, and radiotherapy of cancer

Owing to early diagnosis and treatment of cancer as a prerequisite in recent times, the role of machine learning has been increased substantially. The mathematically powerful and optimized solutions for the detection and cure of cancer are constantly being explored and novel models based upon standard algorithms are also being developed. Leveraging one such solution is Reinforcement Learning (RL), which is a semi-supervised type of learning. The paper presents a detailed discussion on the various RL techniques, algorithms, and open issues, in addition to the review of literature for diagnosis and treatment of cancer. A smaller number of publications for diagnosis and treatment of cancer have been reported before 2011 but now after the success of Deep Learning (DL) and the advent of Deep Reinforcement Learning (DRL), the publications have grown in number from 2017 onwards. The scope of RL for cancer diagnosis and treatment is also demystified and provides the research community with the insights of how to formulate RL problem as a Cancer diagnostic problem. RL has been found successful for landmark detection in medical images and optimal control of drugs and radiations.

Navigating the nuances: comparative analysis and hyperparameter optimisation of neural architectures on contrast-enhanced MRI for liver and liver tumour segmentation

In medical imaging, accurate segmentation is crucial to improving diagnosis, treatment, or both. However, navigating the multitude of available architectures for automatic segmentation can be overwhelming, making it challenging to determine the appropriate type of architecture and tune the most crucial parameters during dataset optimisation. To address this problem, we examined and refined seven distinct architectures for segmenting the liver, as well as liver tumours, with a restricted training collection of 60 3D contrast-enhanced magnetic resonance images (CE-MRI) from the ATLAS dataset. Included in these architectures are convolutional neural networks (CNNs), transformers, and hybrid CNN/transformer architectures. Bayesian search techniques were used for hyperparameter tuning to hasten convergence to the optimal parameter mixes while also minimising the number of trained models. It was unexpected that hybrid models, which typically exhibit superior performance on larger datasets, would exhibit comparable performance to CNNs. The optimisation of parameters contributed to better segmentations, resulting in an average increase of 1.7% and 5.0% in liver and tumour segmentation Dice coefficients, respectively. In conclusion, the findings of this study indicate that hybrid CNN/transformer architectures may serve as a practical substitute for CNNs even in small datasets. This underscores the significance of hyperparameter optimisation.

Efficient and accurate microplastics identification and segmentation in urban waters using convolutional neural networks

Microplastics (MPs), measuring less than 5 mm, pose threats to ecological security and human health in urban waters. Additionally, they act as carriers, transporting pollutants from terrestrial systems into oceanic circulation, contributing to global pollution. Recognizing the significance of identifying MPs in urban waters, one potential solution to the time-consuming and labor-intensive manual identification process is the application of a convolutional neural network (CNN). Therefore, having a reliable CNN model that efficiently and accurately identifies MPs is essential for extensive research on MPs pollution in urban waters. In this work, an MPs dataset with complex background was acquired from urban waters in southern China. The dataset was used to train and validate CNN models, including UNet, UNet2plus, and UNet3plus. Subsequently, the computational and inference performance of the three models was evaluated using a newly collected MPs dataset. The results showed that UNet, UNet2plus, UNet3plus, after being trained for 120 epochs, provided efficient inferences within less than 1 s, 2 s, and 3 s for 100 MPs images, respectively. Accurate segmentation with mIoU of 91.45 ± 5.93 % and 91.08 ± 6.18 % was achieved using UNet and UNet2plus, respectively, while UNet3plus exhibited a lower performance with only 82.21 ± 10.33 % mIoU. This work demonstrated that UNet and UNet2plus deliver efficient and accurate identification of MPs in urban waters. Developing CNN models that efficiently and accurately identify MPs is crucial for reducing manual time, especially in large-scale investigations of MPs pollution in urban waters.

Image-Compression Techniques: Classical and "Region-of-Interest-Based" Approaches Presented in Recent Papers

Image compression is a vital component for domains in which the computational resources are usually scarce such as automotive or telemedicine fields. Also, when discussing real-time systems, the large amount of data that must flow through the system can represent a bottleneck. Therefore, the storage of images, alongside the compression, transmission, and decompression procedures, becomes vital. In recent years, many compression techniques that only preserve the quality of the region of interest of an image have been developed, the other parts being either discarded or compressed with major quality loss. This paper proposes a study of relevant papers from the last decade which are focused on the selection of a region of interest of an image and on the compression techniques that can be applied to that area. To better highlight the novelty of the hybrid methods, classical state-of-the-art approaches are also analyzed. The current work will provide an overview of classical and hybrid compression methods alongside a categorization based on compression ratio and other quality factors such as mean-square error and peak signal-to-noise ratio, structural similarity index measure, and so on. This overview can help researchers to develop a better idea of what compression algorithms are used in certain domains and to find out if the presented performance parameters are of interest for the intended purpose.

Automatic segmentation of brain glioma based on XY-Net

Glioma is a malignant primary brain tumor, which can easily lead to death if it is not detected in time. Magnetic resonance imaging is the most commonly used technique to diagnose gliomas, and precise outlining of tumor areas from magnetic resonance images (MRIs) is an important aid to physicians in understanding the patient's condition and formulating treatment plans. However, relying on radiologists to manually depict tumors is a tedious and laborious task, so it is clinically important to investigate an automated method for outlining glioma regions in MRIs. To liberate radiologists from the heavy task of outlining tumors, we propose a fully convolutional network, XY-Net, based on the most popular U-Net symmetric encoder-decoder structure to perform automatic segmentation of gliomas. We construct two symmetric sub-encoders for XY-Net and build interconnected X-shaped feature map transmission paths between the sub-encoders, while maintaining the feature map concatenation between each sub-encoder and the decoder. Moreover, a loss function composed of the balanced cross-entropy loss function and the dice loss function is used in the training task of XY-Net to solve the class unevenness problem of the medical image segmentation task. The experimental results show that the proposed XY-Net has a 2.16% improvement in dice coefficient (DC) compared to the network model with a single encoder structure, and compare with some state-of-the-art image segmentation methods, XY-Net achieves the best performance. The DC, HD, recall, and precision of our method on the test set are 74.49%, 10.89 mm, 78.06%, and 76.30%, respectively. The combination of sub-encoders and cross-transmission paths enables the model to perform better; based on this combination, the XY-Net achieves an end-to-end automatic segmentation of gliomas on 2D slices of MRIs, which can play a certain auxiliary role for doctors in grasping the state of illness.

A multi-branched semantic segmentation network based on twisted information sharing pattern for medical images

BACKGROUND

Semantic segmentation plays an indispensable role in clinical diagnosis support, intelligent surgical assistance, personalized treatment planning, and drug development, making it a core area of research in smart healthcare. However, the main challenge in medical image semantic segmentation lies in the accuracy bottleneck, primarily due to the low interactivity of feature information and the lack of deep exploration of local features during feature fusion.

METHODS

To address this issue, a novel approach called Twisted Information-sharing Pattern for Multi-branched Network (TP-MNet) has been proposed. This architecture facilitates the mutual transfer of features among neighboring branches at the next level, breaking the barrier of semantic isolation and achieving the goal of semantic fusion. Additionally, performing a secondary feature mining during the transfer process effectively enhances the detection accuracy. Building upon the Twisted Pattern transmission in the encoding and decoding stages, enhanced and refined modules for feature fusion have been developed. These modules aim to capture key features of lesions by acquiring contextual semantic information in a broader context.

RESULTS

The experiments extensively and objectively validated the TP-MNet on 5 medical datasets and compared it with 21 other semantic segmentation models using 7 metrics. Through metric analysis, image comparisons, process examination, and ablation tests, the superiority of TP-MNet was convincingly demonstrated. Additionally, further investigations were conducted to explore the limitations of TP-MNet, thereby clarifying the practical utility of the Twisted Information-sharing Pattern.

CONCLUSIONS

TP-MNet adopts the Twisted Information-sharing Pattern, leading to a substantial improvement in the semantic fusion effect and directly contributing to enhanced segmentation performance on medical images. Additionally, this semantic broadcasting mode not only underscores the importance of semantic fusion but also highlights a pivotal direction for the advancement of multi-branched architectures.

ReFs: A hybrid pre-training paradigm for 3D medical image segmentation

Self-supervised learning (SSL) has achieved remarkable progress in medical image segmentation. The application of an SSL algorithm often follows a two-stage training process: using unlabeled data to perform label-free representation learning and fine-tuning the pre-trained model on the downstream tasks. One issue of this paradigm is that the SSL step is unaware of the downstream task, which may lead to sub-optimal feature representation for a target task. In this paper, we propose a hybrid pre-training paradigm that is driven by both self-supervised and supervised objectives. To achieve this, a supervised reference task is involved in self-supervised learning, aiming to improve the representation quality. Specifically, we employ the off-the-shelf medical image segmentation task as reference, and encourage learning a representation that (1) incurs low prediction loss on both SSL and reference tasks and (2) leads to a similar gradient when updating the feature extractor from either task. In this way, the reference task pilots SSL in the direction beneficial for the downstream segmentation. To this end, we propose a simple but effective gradient matching method to optimize the model towards a consistent direction, thus improving the compatibility of both SSL and supervised reference tasks. We call this hybrid pre-training paradigm reference-guided self-supervised learning (ReFs), and perform it on a large-scale unlabeled dataset and an additional reference dataset. The experimental results demonstrate its effectiveness on seven downstream medical image segmentation benchmarks.

CVII: Enhancing Interpretability in Intelligent Sensor Systems via Computer Vision Interpretability Index

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies.

Real-time semantic segmentation and anomaly detection of functional images for cell therapy manufacturing

BACKGROUND AIMS

Cell therapy is a promising treatment method that uses living cells to address a variety of diseases and conditions, including cardiovascular diseases, neurologic disorders and certain cancers. As interest in cell therapy grows, there is a need to shift to a more efficient, scalable and automated manufacturing process that can produce high-quality products at a lower cost.

METHODS

One way to achieve this is using non-invasive imaging and real-time image analysis techniques to monitor and control the manufacturing process. This work presents a machine learning-based image analysis pipeline that includes semantic segmentation and anomaly detection capabilities.

RESULTS/CONCLUSIONS

This method can be easily implemented even when given a limited dataset of annotated images, is able to segment cells and debris and can identify anomalies such as contamination or hardware failure.

Evaluation of an artificial intelligence-based system for echocardiographic estimation of right atrial pressure

Current noninvasive estimation of right atrial pressure (RAP) by inferior vena cava (IVC) measurement during echocardiography may have significant inter-rater variability due to different levels of observers' experience. Therefore, there is a need to develop new approaches to decrease the variability of IVC analysis and RAP estimation. This study aims to develop a fully automated artificial intelligence (AI)-based system for automated IVC analysis and RAP estimation. We presented a multi-stage AI system to identify the IVC view, select good quality images, delineate the IVC region and quantify its thickness, enabling temporal tracking of its diameter and collapsibility changes. The automated system was trained and tested on expert manual IVC and RAP reference measurements obtained from 255 patients during routine clinical workflow. The performance was evaluated using Pearson correlation and Bland-Altman analysis for IVC values, as well as macro accuracy and chi-square test for RAP values. Our results show an excellent agreement (r=0.96) between automatically computed versus manually measured IVC values, and Bland-Altman analysis showed a small bias of [Formula: see text]0.33 mm. Further, there is an excellent agreement ([Formula: see text]) between automatically estimated versus manually derived RAP values with a macro accuracy of 0.85. The proposed AI-based system accurately quantified IVC diameter, collapsibility index, both are used for RAP estimation. This automated system could serve as a paradigm to perform IVC analysis in routine echocardiography and support various cardiac diagnostic applications.

GCLR: A self-supervised representation learning pretext task for glomerular filtration barrier segmentation in TEM images

Automatic segmentation of the three substructures of glomerular filtration barrier (GFB) in transmission electron microscopy (TEM) images holds immense potential for aiding pathologists in renal disease diagnosis. However, the labor-intensive nature of manual annotations limits the training data for a fully-supervised deep learning model. Addressing this, our study harnesses self-supervised representation learning (SSRL) to utilize vast unlabeled data and mitigate annotation scarcity. Our innovation, GCLR, is a hybrid pixel-level pretext task tailored for GFB segmentation, integrating two subtasks: global clustering (GC) and local restoration (LR). GC captures the overall GFB by learning global context representations, while LR refines three substructures by learning local detail representations. Experiments on 18,928 unlabeled glomerular TEM images for self-supervised pre-training and 311 labeled ones for fine-tuning demonstrate that our proposed GCLR obtains the state-of-the-art segmentation results for all three substructures of GFB with the Dice similarity coefficient of 86.56 ± 0.16%, 75.56 ± 0.36%, and 79.41 ± 0.16%, respectively, compared with other representative self-supervised pretext tasks. Our proposed GCLR also outperforms the fully-supervised pre-training methods based on the three large-scale public datasets - MitoEM, COCO, and ImageNet - with less training data and time.

Domain adaptive Sim-to-Real segmentation of oropharyngeal organs

Video-assisted transoral tracheal intubation (TI) necessitates using an endoscope that helps the physician insert a tracheal tube into the glottis instead of the esophagus. The growing trend of robotic-assisted TI would require a medical robot to distinguish anatomical features like an experienced physician which can be imitated by utilizing supervised deep-learning techniques. However, the real datasets of oropharyngeal organs are often inaccessible due to limited open-source data and patient privacy. In this work, we propose a domain adaptive Sim-to-Real framework called IoU-Ranking Blend-ArtFlow (IRB-AF) for image segmentation of oropharyngeal organs. The framework includes an image blending strategy called IoU-Ranking Blend (IRB) and style-transfer method ArtFlow. Here, IRB alleviates the problem of poor segmentation performance caused by significant datasets domain differences, while ArtFlow is introduced to reduce the discrepancies between datasets further. A virtual oropharynx image dataset generated by the SOFA framework is used as the learning subject for semantic segmentation to deal with the limited availability of actual endoscopic images. We adapted IRB-AF with the state-of-the-art domain adaptive segmentation models. The results demonstrate the superior performance of our approach in further improving the segmentation accuracy and training stability.

DeepNet model empowered cuckoo search algorithm for the effective identification of lung cancer nodules

Introduction

Globally, lung cancer is a highly harmful type of cancer. An efficient diagnosis system can enable pathologists to recognize the type and nature of lung nodules and the mode of therapy to increase the patient's chance of survival. Hence, implementing an automatic and reliable system to segment lung nodules from a computed tomography (CT) image is useful in the medical industry.

Methods

This study develops a novel fully convolutional deep neural network (hereafter called DeepNet) model for segmenting lung nodules from CT scans. This model includes an encoder/decoder network that achieves pixel-wise image segmentation. The encoder network exploits a Visual Geometry Group (VGG-19) model as a base architecture, while the decoder network exploits 16 upsampling and deconvolution modules. The encoder used in this model has a very flexible structural design that can be modified and trained for any resolution based on the size of input scans. The decoder network upsamples and maps the low-resolution attributes of the encoder. Thus, there is a considerable drop in the number of variables used for the learning process as the network recycles the pooling indices of the encoder for segmentation. The Thresholding method and the cuckoo search algorithm determines the most useful features when categorizing cancer nodules.

Results and discussion

The effectiveness of the intended DeepNet model is cautiously assessed on the real-world database known as The Cancer Imaging Archive (TCIA) dataset and its effectiveness is demonstrated by comparing its representation with some other modern segmentation models in terms of selected performance measures. The empirical analysis reveals that DeepNet significantly outperforms other prevalent segmentation algorithms with 0.962 ± 0.023% of volume error, 0.968 ± 0.011 of dice similarity coefficient, 0.856 ± 0.011 of Jaccard similarity index, and 0.045 ± 0.005s average processing time.

Image Augmentation based on Variational Autoencoder for Breast Tumor Segmentation

RATIONALE AND OBJECTIVES

Breast tumor segmentation based on Dynamic Contrast-Enhanced Magnetic Resonance Imaging is significant step for computable radiomics analysis of breast cancer. Manual tumor annotation is time-consuming process and involves medical acquaintance, biased, inclined to error, and inter-user discrepancy. A number of modern trainings have revealed the capability of deep learning representations in image segmentation.

MATERIALS AND METHODS

Here, we describe a 3D Connected-UNets for tumor segmentation from 3D Magnetic Resonance Imagings based on encoder-decoder architecture. Due to a restricted training dataset size, a variational auto-encoder outlet is supplementary to renovate the input image itself in order to identify the shared decoder and execute additional controls on its layers. Based on initial segmentation of Connected-UNets, fully connected 3D provisional unsystematic domain is used to enhance segmentation outcomes by discovering 2D neighbor areas and 3D volume statistics. Moreover, 3D connected modules evaluation is used to endure around large modules and decrease segmentation noise.

RESULTS

The proposed method has been assessed on two widely offered datasets, explicitly INbreast and the curated breast imaging subset of digital database for screening mammography The proposed model has also been estimated using a private dataset.

CONCLUSION

The experimental results show that the proposed model outperforms the state-of-the-art methods for breast tumor segmentation.

Segmentation of Arm Ultrasound Images in Breast Cancer-Related Lymphedema: A Database and Deep Learning Algorithm

OBJECTIVE

Breast cancer treatment often causes the removal of or damage to lymph nodes of the patient's lymphatic drainage system. This side effect is the origin of Breast Cancer-Related Lymphedema (BCRL), referring to a noticeable increase in excess arm volume. Ultrasound imaging is a preferred modality for the diagnosis and progression monitoring of BCRL because of its low cost, safety, and portability. As the affected and unaffected arms look similar in B-mode ultrasound images, the thickness of the skin, subcutaneous fat, and muscle have been shown to be important biomarkers for this task. The segmentation masks are also helpful in monitoring the longitudinal changes in morphology and mechanical properties of tissue layers.

METHODS

For the first time, a publicly available ultrasound dataset containing the Radio-Frequency (RF) data of 39 subjects and manual segmentation masks by two experts, are provided. Inter- and intra-observer reproducibility studies performed on the segmentation maps show a high Dice Score Coefficient (DSC) of 0.94±0.08 and 0.92±0.06, respectively. Gated Shape Convolutional Neural Network (GSCNN) is modified for precise automatic segmentation of tissue layers, and its generalization performance is improved by the CutMix augmentation strategy.

RESULTS

We got an average DSC of 0.87±0.11 on the test set, which confirms the high performance of the method.

CONCLUSION

Automatic segmentation can pave the way for convenient and accessible staging of BCRL, and our dataset can facilitate development and validation of those methods.

SIGNIFICANCE

Timely diagnosis and treatment of BCRL have crucial importance in preventing irreversible damage.

Skin lesion image segmentation based on lightweight multi-scale U-shaped network

UNet, and more recently medical image segmentation methods, utilize many parameters and computational quantities to achieve higher performance. However, due to the increasing demand for real-time medical image segmentation tasks, it is important to trade between accuracy rates and computational complexity. To this end, we propose a lightweight multi-scale U-shaped network (LMUNet), a multi-scale inverted residual and an asymmetric atrous spatial pyramid pooling-based network for skin lesion image segmentation. We test LMUNet on multiple medical image segmentation datasets, which show that it reduces the number of parameters by 67X and decreases the computational complexity by 48X while obtaining better performance over the partial lightweight networks.

M-CSAFN: Multi-Color Space Adaptive Fusion Network for Automated Port-Wine Stains Segmentation

Automatic segmentation of port-wine stains (PWS) from clinical images is critical for accurate diagnosis and objective assessment of PWS. However, this is a challenging task due to the color heterogeneity, low contrast, and indistinguishable appearance of PWS lesions. To address such challenges, we propose a novel multi-color space adaptive fusion network (M-CSAFN) for PWS segmentation. First, a multi-branch detection model is constructed based on six typical color spaces, which utilizes rich color texture information to highlight the difference between lesions and surrounding tissues. Second, an adaptive fusion strategy is used to fuse complementary predictions, which address the significant differences within the lesions caused by color heterogeneity. Third, a structural similarity loss with color information is proposed to measure the detail error between predicted lesions and truth lesions. Additionally, a PWS clinical dataset consisting of 1413 image pairs was established for the development and evaluation of PWS segmentation algorithms. To verify the effectiveness and superiority of the proposed method, we compared it with other state-of-the-art methods on our collected dataset and four publicly available skin lesion datasets (ISIC 2016, ISIC 2017, ISIC 2018, and PH2). The experimental results show that our method achieves remarkable performance in comparison with other state-of-the-art methods on our collected dataset, achieving 92.29% and 86.14% on Dice and Jaccard metrics, respectively. Comparative experiments on other datasets also confirmed the reliability and potential capability of M-CSAFN in skin lesion segmentation.

Weak Localization of Radiographic Manifestations in Pulmonary Tuberculosis from Chest X-ray: A Systematic Review

Pulmonary tuberculosis (PTB) is a bacterial infection that affects the lung. PTB remains one of the infectious diseases with the highest global mortalities. Chest radiography is a technique that is often employed in the diagnosis of PTB. Radiologists identify the severity and stage of PTB by inspecting radiographic features in the patient's chest X-ray (CXR). The most common radiographic features seen on CXRs include cavitation, consolidation, masses, pleural effusion, calcification, and nodules. Identifying these CXR features will help physicians in diagnosing a patient. However, identifying these radiographic features for intricate disorders is challenging, and the accuracy depends on the radiologist's experience and level of expertise. So, researchers have proposed deep learning (DL) techniques to detect and mark areas of tuberculosis infection in CXRs. DL models have been proposed in the literature because of their inherent capacity to detect diseases and segment the manifestation regions from medical images. However, fully supervised semantic segmentation requires several pixel-by-pixel labeled images. The annotation of such a large amount of data by trained physicians has some challenges. First, the annotation requires a significant amount of time. Second, the cost of hiring trained physicians is expensive. In addition, the subjectivity of medical data poses a difficulty in having standardized annotation. As a result, there is increasing interest in weak localization techniques. Therefore, in this review, we identify methods employed in the weakly supervised segmentation and localization of radiographic manifestations of pulmonary tuberculosis from chest X-rays. First, we identify the most commonly used public chest X-ray datasets for tuberculosis identification. Following that, we discuss the approaches for weakly localizing tuberculosis radiographic manifestations in chest X-rays. The weakly supervised localization of PTB can highlight the region of the chest X-ray image that contributed the most to the DL model's classification output and help pinpoint the diseased area. Finally, we discuss the limitations and challenges of weakly supervised techniques in localizing TB manifestations regions in chest X-ray images.

Label-efficient deep semantic segmentation of intracranial hemorrhages in CT-scans

Intracranial hemorrhage (ICH) is a common finding in traumatic brain injury (TBI) and computed tomography (CT) is considered the gold standard for diagnosis. Automated detection of ICH provides clinical value in diagnostics and in the ability to feed robust quantification measures into future prediction models. Several studies have explored ICH detection and segmentation but the research process is somewhat hindered due to a lack of open large and labeled datasets, making validation and comparison almost impossible. The complexity of the task is further challenged by the heterogeneity of ICH patterns, requiring a large number of labeled data to train robust and reliable models. Consequently, due to the labeling cost, there is a need for label-efficient algorithms that can exploit easily available unlabeled or weakly-labeled data. Our aims for this study were to evaluate whether transfer learning can improve ICH segmentation performance and to compare a variety of transfer learning approaches that harness unlabeled and weakly-labeled data. Three self-supervised and three weakly-supervised transfer learning approaches were explored. To be used in our comparisons, we also manually labeled a dataset of 51 CT scans. We demonstrate that transfer learning improves ICH segmentation performance on both datasets. Unlike most studies on ICH segmentation our work relies exclusively on publicly available datasets, allowing for easy comparison of performances in future studies. To further promote comparison between studies, we also present a new public dataset of ICH-labeled CT scans, Seq-CQ500.

A Real-Time Semantic Segmentation Method Based on STDC-CT for Recognizing UAV Emergency Landing Zones

With the accelerated growth of the UAV industry, researchers are paying close attention to the flight safety of UAVs. When a UAV loses its GPS signal or encounters unusual conditions, it must perform an emergency landing. Therefore, real-time recognition of emergency landing zones on the ground is an important research topic. This paper employs a semantic segmentation approach for recognizing emergency landing zones. First, we created a dataset of UAV aerial images, denoted as UAV-City. A total of 600 UAV aerial images were densely annotated with 12 semantic categories. Given the complex backgrounds, diverse categories, and small UAV aerial image targets, we propose the STDC-CT real-time semantic segmentation network for UAV recognition of emergency landing zones. The STDC-CT network is composed of three branches: detail guidance, small object attention extractor, and multi-scale contextual information. The fusion of detailed and contextual information branches is guided by small object attention. We conducted extensive experiments on the UAV-City, Cityscapes, and UAVid datasets to demonstrate that the STDC-CT method is superior for attaining a balance between segmentation accuracy and inference speed. Our method improves the segmentation accuracy of small objects and achieves 76.5% mIoU on the Cityscapes test set at 122.6 FPS, 68.4% mIoU on the UAVid test set, and 67.3% mIoU on the UAV-City dataset at 196.8 FPS on an NVIDIA RTX 2080Ti GPU. Finally, we deployed the STDC-CT model on Jetson TX2 for testing in a real-world environment, attaining real-time semantic segmentation with an average inference speed of 58.32 ms per image.

MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images

Aim

The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that uses a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesion contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results.

Patients

The X-ray dataset from Qatar University which contains 3379 cases for light, normal and heavy COVID-19 lung infection. The CT dataset contains the scans of 10 patient cases with COVID-19, a total of 1562 CT axial slices. The BAA dataset is obtained from the hospital and includes 387 original images. The ISIC 2018 dataset is from the International Skin Imaging Collaborative (ISIC) containing 2594 original images.

Results

The proposed MS-DCANet achieved evaluation metrics (MIOU) of 73.86, 97.26, 89.54, and 79.54 on the four datasets, respectively, far exceeding other current state-of-the art baselines.

Conclusion

The proposed MS-DCANet can help clinicians to automate the diagnosis of COVID-19 patients with different symptoms.

Deep learning for histopathological segmentation of smooth muscle in the urinary bladder

BACKGROUND

Histological assessment of smooth muscle is a critical step particularly in staging malignant tumors in various internal organs including  the urinary bladder. Nonetheless, manual segmentation and classification of muscular tissues by pathologists is often challenging. Therefore, a fully automated and reliable smooth muscle image segmentation system is in high demand.

METHODS

To characterize muscle fibers in the urinary bladder, including muscularis mucosa (MM) and muscularis propria (MP), we assessed 277 histological images from surgical specimens, using two well-known deep learning (DL) model groups, one including VGG16, ResNet18, SqueezeNet, and MobileNetV2, considered as a patch-based approach, and the other including U-Net, MA-Net, DeepLabv3 + , and FPN, considered as a pixel-based approach. All the trained models in both the groups were evaluated at pixel-level for their performance.

RESULTS

For segmenting MP and non-MP (including MM) regions, MobileNetV2, in the patch-based approach and U-Net, in the pixel-based approach outperformed their peers in the groups with mean Jaccard Index equal to 0.74 and 0.79, and mean Dice co-efficient equal to 0.82 and 0.88, respectively. We also demonstrated the strengths and weaknesses of the models in terms of speed and prediction accuracy.

CONCLUSIONS

This work not only creates a benchmark for future development of tools for the histological segmentation of smooth muscle but also provides an effective DL-based diagnostic system for accurate pathological staging of bladder cancer.

Deep Learning for Medical Image-Based Cancer Diagnosis

(1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images.

Semi-Supervised 3D Medical Image Segmentation Based on Dual-Task Consistent Joint Learning and Task-Level Regularization

Semi-supervised learning has attracted wide attention from many researchers since its ability to utilize a few data with labels and relatively more data without labels to learn information. Some existing semi-supervised methods for medical image segmentation enforce the regularization of training by implicitly perturbing data or networks to perform the consistency. Most consistency regularization methods focus on data level or network structure level, and rarely of them focus on the task level. It may not directly lead to an improvement in task accuracy. To overcome the problem, this work proposes a semi-supervised dual-task consistent joint learning framework with task-level regularization for 3D medical image segmentation. Two branches are utilized to simultaneously predict the segmented and signed distance maps, and they can learn useful information from each other by constructing a consistency loss function between the two tasks. The segmentation branch learns rich information from both labeled and unlabeled data to strengthen the constraints on the geometric structure of the target. Experimental results on two benchmark datasets show that the proposed method can achieve better performance compared with other state-of-the-art works. It illustrates our method improves segmentation performance by utilizing unlabeled data and consistent regularization.

A survey on deep learning for skin lesion segmentation

Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. However, the presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. In this survey, we cross-examine 177 research papers that deal with deep learning-based segmentation of skin lesions. We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions both from the viewpoint of select seminal works, and from a systematic viewpoint, examining how those choices have influenced current trends, and how their limitations should be addressed. To facilitate comparisons, we summarize all examined works in a comprehensive table as well as an interactive table available online³.

AI-Based Automated Lipomatous Tumor Segmentation in MR Images: Ensemble Solution to Heterogeneous Data

Deep learning (DL) has been proposed to automate image segmentation and provide accuracy, consistency, and efficiency. Accurate segmentation of lipomatous tumors (LTs) is critical for correct tumor radiomics analysis and localization. The major challenge of this task is data heterogeneity, including tumor morphological characteristics and multicenter scanning protocols. To mitigate the issue, we aimed to develop a DL-based Super Learner (SL) ensemble framework with different data correction and normalization methods. Pathologically proven LTs on pre-operative T1-weighted/proton-density MR images of 185 patients were manually segmented. The LTs were categorized by tumor locations as distal upper limb (DUL), distal lower limb (DLL), proximal upper limb (PUL), proximal lower limb (PLL), or Trunk (T) and grouped by 80%/9%/11% for training, validation and testing. Six configurations of correction/normalization were applied to data for fivefold-cross-validation trainings, resulting in 30 base learners (BLs). A SL was obtained from the BLs by optimizing SL weights. The performance was evaluated by dice-similarity-coefficient (DSC), sensitivity, specificity, and Hausdorff distance (HD95). For predictions of the BLs, the average DSC, sensitivity, and specificity from the testing data were 0.72 [Formula: see text] 0.16, 0.73 [Formula: see text] 0.168, and 0.99 [Formula: see text] 0.012, respectively, while for SL predictions were 0.80 [Formula: see text] 0.184, 0.78 [Formula: see text] 0.193, and 1.00 [Formula: see text] 0.010. The average HD95 of the BLs were 11.5 (DUL), 23.2 (DLL), 25.9 (PUL), 32.1 (PLL), and 47.9 (T) mm, whereas of SL were 1.7, 8.4, 15.9, 2.2, and 36.6 mm, respectively. The proposed method could improve the segmentation accuracy and mitigate the performance instability and data heterogeneity aiding the differential diagnosis of LTs in real clinical situations.

Preserved blood-brain barrier and neurovascular coupling in female 5xFAD model of Alzheimer's disease

Introduction

Dysfunction of the cerebral vasculature is considered one of the key components of Alzheimer's disease (AD), but the mechanisms affecting individual brain vessels are poorly understood.

Methods

Here, using in vivo two-photon microscopy in superficial cortical layers and ex vivo imaging across brain regions, we characterized blood-brain barrier (BBB) function and neurovascular coupling (NVC) at the level of individual brain vessels in adult female 5xFAD mice, an aggressive amyloid-β (Aβ) model of AD.

Results

We report a lack of abnormal increase in adsorptive-mediated transcytosis of albumin and preserved paracellular barrier for fibrinogen and small molecules despite an extensive load of Aβ. Likewise, the NVC responses to somatosensory stimulation were preserved at all regulatory segments of the microvasculature: penetrating arterioles, precapillary sphincters, and capillaries. Lastly, the Aβ plaques did not affect the density of capillary pericytes.

Conclusion

Our findings provide direct evidence of preserved microvascular function in the 5xFAD mice and highlight the critical dependence of the experimental outcomes on the choice of preclinical models of AD. We propose that the presence of parenchymal Aβ does not warrant BBB and NVC dysfunction and that the generalized view that microvascular impairment is inherent to Aβ aggregation may need to be revised.

LASSNet: A Four Steps Deep Neural Network for Left Atrial Segmentation and Scar Quantification

Accurate quantification of left atrium (LA) scar in patients with atrial fibrillation is essential to guide successful ablation strategies. Prior to LA scar quantification, a proper LA cavity segmentation is required to ensure exact location of scar. Both tasks can be extremely time-consuming and are subject to inter-observer disagreements when done manually. We developed and validated a deep neural network to automatically segment the LA cavity and the LA scar. The global architecture uses a multi-network sequential approach in two stages which segment the LA cavity and the LA Scar. Each stage has two steps: a region of interest Neural Network and a refined segmentation network. We analysed the performances of our network according to different parameters and applied data triaging. 200+ late gadolinium enhancement magnetic resonance images were provided by the LAScarQS 2022 Challenge. Finally, we compared our performances for scar quantification to the literature and demonstrated improved performances.

Small-Object Sensitive Segmentation Using Across Feature Map Attention

Semantic segmentation is an important step in understanding the scene for many practical applications such as autonomous driving. Although Deep Convolutional Neural Networks-based methods have significantly improved segmentation accuracy, small/thin objects remain challenging to segment due to convolutional and pooling operations that result in information loss, especially for small objects. This article presents a novel attention-based method called Across Feature Map Attention (AFMA) to address this challenge. It quantifies the inner-relationship between small and large objects belonging to the same category by utilizing the different feature levels of the original image. The AFMA could compensate for the loss of high-level feature information of small objects and improve the small/thin object segmentation. Our method can be used as an efficient plug-in for a wide range of existing architectures and produces much more interpretable feature representation than former studies. Extensive experiments on eight widely used segmentation methods and other existing small-object segmentation models on CamVid and Cityscapes demonstrate that our method substantially and consistently improves the segmentation of small/thin objects.

Brain Tumor Segmentation Network with Multi-View Ensemble Discrimination and Kernel-Sharing Dilated Convolution

Accurate segmentation of brain tumors from magnetic resonance 3D images (MRI) is critical for clinical decisions and surgical planning. Radiologists usually separate and analyze brain tumors by combining images of axial, coronal, and sagittal views. However, traditional convolutional neural network (CNN) models tend to use information from only a single view or one by one. Moreover, the existing models adopt a multi-branch structure with different-size convolution kernels in parallel to adapt to various tumor sizes. However, the difference in the convolution kernels' parameters cannot precisely characterize the feature similarity of tumor lesion regions with various sizes, connectivity, and convexity. To address the above problems, we propose a hierarchical multi-view convolution method that decouples the standard 3D convolution into axial, coronal, and sagittal views to provide complementary-view features. Then, every pixel is classified by ensembling the discriminant results from the three views. Moreover, we propose a multi-branch kernel-sharing mechanism with a dilated rate to obtain parameter-consistent convolution kernels with different receptive fields. We use the BraTS2018 and BraTS2020 datasets for comparison experiments. The average Dice coefficients of the proposed network on the BraTS2020 dataset can reach 78.16%, 89.52%, and 83.05% for the enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively, while the number of parameters is only 0.5 M. Compared with the baseline network for brain tumor segmentation, the accuracy was improved by 1.74%, 0.5%, and 2.19%, respectively.

LUVS-Net: A Lightweight U-Net Vessel Segmentor for Retinal Vasculature Detection in Fundus Images

This paper presents LUVS-Net, which is a lightweight convolutional network for retinal vessel segmentation in fundus images that is designed for resource-constrained devices that are typically unable to meet the computational requirements of large neural networks. The computational challenges arise due to low-quality retinal images, wide variance in image acquisition conditions and disparities in intensity. Consequently, the training of existing segmentation methods requires a multitude of trainable parameters for the training of networks, resulting in computational complexity. The proposed Lightweight U-Net for Vessel Segmentation Network (LUVS-Net) can achieve high segmentation performance with only a few trainable parameters. This network uses an encoder–decoder framework in which edge data are transposed from the first layers of the encoder to the last layer of the decoder, massively improving the convergence latency. Additionally, LUVS-Net’s design allows for a dual-stream information flow both inside as well as outside of the encoder–decoder pair. The network width is enhanced using group convolutions, which allow the network to learn a larger number of low- and intermediate-level features. Spatial information loss is minimized using skip connections, and class imbalances are mitigated using dice loss for pixel-wise classification. The performance of the proposed network is evaluated on the publicly available retinal blood vessel datasets DRIVE, CHASE_DB1 and STARE. LUVS-Net proves to be quite competitive, outperforming alternative state-of-the-art segmentation methods and achieving comparable accuracy using trainable parameters that are reduced by two to three orders of magnitude compared with those of comparative state-of-the-art methods.

Localization of spleen and kidney organs from CT scans based on classification of slices in rotational views

This article presents a novel multiple organ localization and tracking technique applied to spleen and kidney regions in computed tomography images. The proposed solution is based on a unique approach to classify regions in different spatial projections (e.g., side projection) using convolutional neural networks. Our procedure merges classification results from different projection resulting in a 3D segmentation. The proposed system is able to recognize the contour of the organ with an accuracy of 88-89% depending on the body organ. Research has shown that the use of a single method can be useful for the detection of different organs: kidney and spleen. Our solution can compete with U-Net based solutions in terms of hardware requirements, as it has significantly lower demands. Additionally, it gives better results in small data sets. Another advantage of our solution is a significantly lower training time on an equally sized data set and more capabilities to parallelize calculations. The proposed system enables visualization, localization and tracking of organs and is therefore a valuable tool in medical diagnostic problems.

Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images

MOTIVATION

Morphological analyses with flatmount fluorescent images are essential to retinal pigment epithelial (RPE) aging studies and thus require accurate RPE cell segmentation. Although rapid technology advances in deep learning semantic segmentation have achieved great success in many biomedical research, the performance of these supervised learning methods for RPE cell segmentation is still limited by inadequate training data with high-quality annotations.

RESULTS

To address this problem, we develop a Self-Supervised Semantic Segmentation (S4) method that utilizes a self-supervised learning strategy to train a semantic segmentation network with an encoder-decoder architecture. We employ a reconstruction and a pairwise representation loss to make the encoder extract structural information, while we create a morphology loss to produce the segmentation map. In addition, we develop a novel image augmentation algorithm (AugCut) to produce multiple views for self-supervised learning and enhance the network training performance. To validate the efficacy of our method, we applied our developed S4 method for RPE cell segmentation to a large set of flatmount fluorescent microscopy images, we compare our developed method for RPE cell segmentation with other state-of-the-art deep learning approaches. Compared with other state-of-the-art deep learning approaches, our method demonstrates better performance in both qualitative and quantitative evaluations, suggesting its promising potential to support large-scale cell morphological analyses in RPE aging investigations.

AVAILABILITY AND IMPLEMENTATION

The codes and the documentation are available at: https://github.com/jkonglab/S4_RPE.

Deep-SAGA: a deep-learning-based system for automatic gaze annotation from eye-tracking data

With continued advancements in portable eye-tracker technology liberating experimenters from the restraints of artificial laboratory designs, research can now collect gaze data from real-world, natural navigation. However, the field lacks a robust method for achieving this, as past approaches relied upon the time-consuming manual annotation of eye-tracking data, while previous attempts at automation lack the necessary versatility for in-the-wild navigation trials consisting of complex and dynamic scenes. Here, we propose a system capable of informing researchers of where and what a user's gaze is focused upon at any one time. The system achieves this by first running footage recorded on a head-mounted camera through a deep-learning-based object detection algorithm called Masked Region-based Convolutional Neural Network (Mask R-CNN). The algorithm's output is combined with frame-by-frame gaze coordinates measured by an eye-tracking device synchronized with the head-mounted camera to detect and annotate, without any manual intervention, what a user looked at for each frame of the provided footage. The effectiveness of the presented methodology was legitimized by a comparison between the system output and that of manual coders. High levels of agreement between the two validated the system as a preferable data collection technique as it was capable of processing data at a significantly faster rate than its human counterpart. Support for the system's practicality was then further demonstrated via a case study exploring the mediatory effects of gaze behaviors on an environment-driven attentional bias.