A difficulty-aware and task-augmentation method based on meta-learning model for few-shot diabetic retinopathy classification.

Background: Accurate classification techniques are essential for the early diagnosis and treatment of patients with diabetic retinopathy (DR). However, the limited amount of annotated DR data poses a challenge for existing deep-learning models. This article proposes a difficulty-aware and task-augmentation method based on meta-learning (DaTa-ML) model for few-shot DR classification with fundus images. Methods: The difficulty-aware (Da) method operates by dynamically modifying the cross-entropy loss function applied to learning tasks. This methodology has the ability to intelligently down-weight simpler tasks, while simultaneously prioritizing more challenging tasks. These adjustments occur automatically and aim to optimize the learning process. Additionally, the task-augmentation (Ta) method is used to enhance the meta-training process by augmenting the number of tasks through image rotation and improving the feature-extraction capability. To implement the expansion of the meta-training tasks, various task instances can be sampled during the meta-training stage. Ultimately, the proposed Ta method was introduced to optimize the initialization parameters and enhance the meta-generalization performance of the model. The DaTa-ML model showed promising results by effectively addressing the challenges associated with few-shot DR classification. Results: The Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 blindness detection data set was used to evaluate the DaTa-ML model. The results showed that with only 1% of the training data (5-way, 20-shot) and a single update step (training time reduced by 90%), the DaTa-ML model had an accuracy rate of 89.6% on the test data, which is a 1.7% improvement over the transfer-learning method [i.e., residual neural network (ResNet)50 pre-trained on ImageNet], and a 16.8% improvement over scratch-built models (i.e., ResNet50 without pre-trained weights), despite having fewer trainable parameters (the parameters used by the DaTa-ML model are only 0.47% of the ResNet50 parameters). Conclusions: The DaTa-ML model provides a more efficient DR classification solution with little annotated data and has significant advantages over state-of-the-art methods. Thus, it could be used to guide and assist ophthalmologists to determine the severity of DR.

Optimization of the cavity length and pulse characterization based on germanene as a saturable absorber in an Er-doped fiber laser.

In this study, germanene-nanosheets (NSs) were synthesized by liquid-phase exfoliation, followed by an experimental investigation into the nonlinear saturable absorption characteristics and morphological structure of germanene. The germanene-NSs were employed as saturable absorbers, exhibiting saturation intensity and modulation depth values of 22.64M W/c m 2 and 4.48%, respectively. This demonstrated the feasibility of utilizing germanene-NSs passively mode-locked in an erbium-doped fiber laser (EDFL). By optimizing the cavity length, improvements in the output of EDFL characteristics were achieved, resulting in 883 fs pulses with a maximum average output power of 19.74 mW. The aforementioned experimental outcomes underscore the significant potential of germanene in the realms of ultrafast photonics and nonlinear optics.

Dual contrast attention-guided multi-frequency fusion for multi-contrast MRI super-resolution.

Objective. Multi-contrast magnetic resonance (MR) imaging super-resolution (SR) reconstruction is an effective solution for acquiring high-resolution MR images. It utilizes anatomical information from auxiliary contrast images to improve the quality of the target contrast images. However, existing studies have simply explored the relationships between auxiliary contrast and target contrast images but did not fully consider different anatomical information contained in multi-contrast images, resulting in texture details and artifacts unrelated to the target contrast images.Approach. To address these issues, we propose a dual contrast attention-guided multi-frequency fusion (DCAMF) network to reconstruct SR MR images from low-resolution MR images, which adaptively captures relevant anatomical information and processes the texture details and low-frequency information from multi-contrast images in parallel. Specifically, after the feature extraction, a feature selection module based on a dual contrast attention mechanism is proposed to focus on the texture details of the auxiliary contrast images and the low-frequency features of the target contrast images. Then, based on the characteristics of the selected features, a high- and low-frequency fusion decoder is constructed to fuse these features. In addition, a texture-enhancing module is embedded in the high-frequency fusion decoder, to highlight and refine the texture details of the auxiliary contrast and target contrast images. Finally, the high- and low-frequency fusion process is constrained by integrating a deeply-supervised mechanism into the DCAMF network.Main results. The experimental results show that the DCAMF outperforms other state-of-the-art methods. The peak signal-to-noise ratio and structural similarity of DCAMF are 39.02 dB and 0.9771 on the IXI dataset and 37.59 dB and 0.9770 on the BraTS2018 dataset, respectively. The image recovery is further validated in segmentation tasks.Significance. Our proposed SR model can enhance the quality of MR images. The results of the SR study provide a reliable basis for clinical diagnosis and subsequent image-guided treatment.

MARS-GAN: Multilevel-Feature-Learning Attention-Aware Based Generative Adversarial Network for Removing Surgical Smoke.

Surgical smoke caused poor visibility during laparoscopic surgery, the smoke removal is important to improve the safety and efficiency of the surgery. We propose the Multilevel-feature-learning Attention-aware based Generative Adversarial Network for Removing Surgical Smoke (MARS-GAN) in this work. MARS-GAN incorporates multilevel smoke feature learning, smoke attention learning, and multi-task learning together. Specifically, the multilevel smoke feature learning adopts the multilevel strategy to adaptively learn non-homogeneity smoke intensity and area features with specific branches and integrates comprehensive features to preserve both semantic and textural information with pyramidal connections. The smoke attention learning extends the smoke segmentation module with the dark channel prior module to provide the pixel-wise measurement for focusing on the smoke features while preserving the smokeless details. And the multi-task learning strategy fuses the adversarial loss, cyclic consistency loss, smoke perception loss, dark channel prior loss, and contrast enhancement loss to help the model optimization. Furthermore, a paired smokeless/smoky dataset is synthesized for elevating smoke recognition ability. The experimental results show that MARS-GAN outperforms the comparative methods for removing surgical smoke on both synthetic/real laparoscopic surgical images, with the potential to be embedded in laparoscopic devices for smoke removal.

Low-Threshold, Multiple High-Order Harmonics Fiber Laser Employing Cr2Si2Te6 Saturable Absorber.

Abundant research findings have proved the value of two-dimensional (2D) materials in the study of nonlinear optics in fiber lasers. However, there remains two problems: how to reduce the start-up threshold, and how to improve the damage threshold, of fiber lasers based on 2D materials. A 15.1 mW low-threshold mode-locked fiber laser, based on a Cr2Si2Te6 saturable absorber (SA) prepared by the liquid-phase exfoliation method, is demonstrated successfully in this work. This provides a useful and economical method to produce SAs with low insertion loss and low saturation intensity. Besides, multiple high-order harmonics, from the fundamental frequency (12.6 MHz) to the 49th-order harmonic (617.6 MHz), mode-locked operations are recorded. The experimental results indicate the excellent potential of Cr2Si2Te6 as an optical modulator in exploring the soliton dynamics, harmonic mode locking, and other nonlinear effects in fiber lasers.

Image-based scatter correction for cone-beam CT using flip swin transformer U-shape network.

BACKGROUND: Cone beam computed tomography (CBCT) plays an increasingly important role in image-guided radiation therapy. However, the image quality of CBCT is severely degraded by excessive scatter contamination, especially in the abdominal region, hindering its further applications in radiation therapy. PURPOSE: To restore low-quality CBCT images contaminated by scatter signals, a scatter correction algorithm combining the advantages of convolutional neural networks (CNN) and Swin Transformer is proposed. METHODS: In this paper a scatter correction model for CBCT image, the Flip Swin Transformer U-shape network (FSTUNet) model, is proposed. In this model, the advantages of CNN in texture detail and Swin Transformer in global correlation are used to accurately extract shallow and deep features, respectively. Instead of using the original Swin Transformer tandem structure, we build the Flip Swin Transformer Block to achieve a more powerful inter-window association extraction. The validity and clinical relevance of the method is demonstrated through extensive experiments on a Monte Carlo (MC) simulation dataset and frequency split dataset generated by a validated method, respectively. RESULT: Experimental results on the MC simulated dataset show that the root mean square error of images corrected by the method is reduced from over 100 HU to about 7 HU. Both the structural similarity index measure (SSIM) and the universal quality index (UQI) are close to 1. Experimental results on the frequency split dataset demonstrate that the method not only corrects shading artifacts but also exhibits a high degree of structural consistency. In addition, comparison experiments show that FSTUNet outperforms UNet, Deep Residual Convolutional Neural Network (DRCNN), DSENet, Pix2pixGAN, and 3DUnet methods in both qualitative and quantitative metrics. CONCLUSIONS: Accurately capturing the features at different levels is greatly beneficial for reconstructing high-quality scatter-free images. The proposed FSTUNet method is an effective solution to CBCT scatter correction and has the potential to improve the accuracy of CBCT image-guided radiation therapy.

CT synthesis from MR in the pelvic area using Residual Transformer Conditional GAN.

Magnetic resonance (MR) image-guided radiation therapy is a hot topic in current radiation therapy research, which relies on MR to generate synthetic computed tomography (SCT) images for radiation therapy. Convolution-based generative adversarial networks (GAN) have achieved promising results in synthesizing CT from MR since the introduction of deep learning techniques. However, due to the local limitations of pure convolutional neural networks (CNN) structure and the local mismatch between paired MR and CT images, particularly in pelvic soft tissue, the performance of GAN in synthesizing CT from MR requires further improvement. In this paper, we propose a new GAN called Residual Transformer Conditional GAN (RTCGAN), which exploits the advantages of CNN in local texture details and Transformer in global correlation to extract multi-level features from MR and CT images. Furthermore, the feature reconstruction loss is used to further constrain the image potential features, reducing over-smoothing and local distortion of the SCT. The experiments show that RTCGAN is visually closer to the reference CT (RCT) image and achieves desirable results on local mismatch tissues. In the quantitative evaluation, the MAE, SSIM, and PSNR of RTCGAN are 45.05 HU, 0.9105, and 28.31 dB, respectively. All of them outperform other comparison methods, such as deep convolutional neural networks (DCNN), Pix2Pix, Attention-UNet, WPD-DAGAN, and HDL.

Temperature guided network for 3D joint segmentation of the pancreas and tumors.

Accurate and automatic segmentation of pancreatic tumors and organs from medical images is important for clinical diagnoses and making treatment plans for patients with pancreatic cancer. Although deep learning methods have been widely adopted for this task, the segmentation accuracy, especially for pancreatic tumors, still needs to be further improved because (1) phenotypic differences, such as volumes, tend to make the models focus on pancreatic learning, resulting in insufficient tumor feature selection; (2) deep learning models may fall into local optima, leading to unsatisfactory segmentation results for tumors and pancreas. To alleviate the above issues, in this paper, we propose a 3D fully convolutional neural network with three temperature guided modules, namely, balance temperature loss, rigid temperature optimizer and soft temperature indictor, to realize joint segmentation of the pancreas and tumors. Specifically, balance temperature loss is designed to dynamically adjust the learning points between tumors and the pancreas to balance the selected features, and it is aimed at improving the accuracy of tumor segmentation without losing pancreas information. Rigid temperature optimizer is proposed to accept nonimproving moves probabilistically to adaptively avoid local optima. To further refine the segmentation results, we propose the soft temperature indictor to guide the network into a fine-tuning state automatically when the model tends to stability. Our experimental results are more accurate than the fourteen top-ranking methods in pancreas and tumors segmentation on the MSD pancreas dataset and six top-ranking methods in brain tumors segmentation. Ablation studies verify the effectiveness of the three temperature guided modules.

Third-order harmonic mode-locked and Q-switched Er-doped fiber laser based on a Cr2Ge2Te6 saturable absorber.

This paper reports the generation of fundamental solitons and third-order solitons in an erbium-doped fiber laser (EDFL) by a Cr2Ge2Te6-polyvinyl alcohol (CGT-PVA) saturable absorber (SA). Stable fundamental solitons at 1559.09 nm at a repetition frequency of 5.1 MHz were detected, and third-order solitons with a maximum output power of 6.807 mW and narrowest monopulse duration of 615.2 fs were obtained under a repetition frequency of 15.3 MHz by changing pump power. To the best of our knowledge, it is the first time to achieve a Q-switched pulse with a minimum pulse duration of 2.2 µs and maximum single pulse energy of 12.11 nJ in EDFL based on CGT-PVA SA after reducing the cavity length. Its repetition rate monotonically increased from 18.8 kHz to 61.8 kHz with a tuning range of about 43 kHz. The experimental results sufficiently demonstrate that CGT has enormous potential as an ultrafast photonics device.

Semi-supervised classification of fundus images combined with CNN and GCN.

PURPOSE: Diabetic retinopathy (DR) is one of the most serious complications of diabetes, which is a kind of fundus lesion with specific changes. Early diagnosis of DR can effectively reduce the visual damage caused by DR. Due to the variety and different morphology of DR lesions, automatic classification of fundus images in mass screening can greatly save clinicians' diagnosis time. To alleviate these problems, in this paper, we propose a novel framework-graph attentional convolutional neural network (GACNN). METHODS AND MATERIALS: The network consists of convolutional neural network (CNN) and graph convolutional network (GCN). The global and spatial features of fundus images are extracted by using CNN and GCN, and attention mechanism is introduced to enhance the adaptability of GCN to topology map. We adopt semi-supervised method for classification, which greatly improves the generalization ability of the network. RESULTS: In order to verify the effectiveness of the network, we conducted comparative experiments and ablation experiments. We use confusion matrix, precision, recall, kappa score, and accuracy as evaluation indexes. With the increase of the labeling rates, the classification accuracy is higher. Particularly, when the labeling rate is set to 100%, the classification accuracy of GACNN reaches 93.35%. Compared with DenseNet121, the accuracy rate is improved by 6.24%. CONCLUSIONS: Semi-supervised classification based on attention mechanism can effectively improve the classification performance of the model, and attain preferable results in classification indexes such as accuracy and recall. GACNN provides a feasible classification scheme for fundus images, which effectively reduces the screening human resources.

Common feature learning for brain tumor MRI synthesis by context-aware generative adversarial network.

Multi-modal structural Magnetic Resonance Image (MRI) provides complementary information and has been used widely for diagnosis and treatment planning of gliomas. While machine learning is popularly adopted to process and analyze MRI images, most existing tools are based on complete sets of multi-modality images that are costly and sometimes impossible to acquire in real clinical scenarios. In this work, we address the challenge of multi-modality glioma MRI synthesis often with incomplete MRI modalities. We propose 3D Common-feature learning-based Context-aware Generative Adversarial Network (CoCa-GAN) for this purpose. In particular, our proposed CoCa-GAN method adopts the encoder-decoder architecture to map the input modalities into a common feature space by the encoder, from which (1) the missing target modality(-ies) can be synthesized by the decoder, and also (2) the jointly conducted segmentation of the gliomas can help the synthesis task to better focus on the tumor regions. The synthesis and segmentation tasks share the same common feature space, while multi-task learning boosts both their performances. In particular, for the encoder to derive the common feature space, we propose and validate two different models, i.e., (1) early-fusion CoCa-GAN (eCoCa-GAN) and (2) intermediate-fusion CoCa-GAN (iCoCa-GAN). The experimental results demonstrate that the proposed iCoCa-GAN outperforms other state-of-the-art methods in synthesis of missing image modalities. Moreover, our method is flexible to handle the arbitrary combination of input/output image modalities, which makes it feasible to process brain tumor MRI data in real clinical circumstances.

Radiomics for Predicting Response of Neoadjuvant Chemotherapy in Nasopharyngeal Carcinoma: A Systematic Review and Meta-Analysis.

Purpose: This study examined the methodological quality of radiomics to predict the effectiveness of neoadjuvant chemotherapy in nasopharyngeal carcinoma (NPC). We performed a meta-analysis of radiomics studies evaluating the bias risk and treatment response estimation. Methods: Our study was conducted through a literature review as per the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We included radiomics-related papers, published prior to January 31, 2022, in our analysis to examine the effectiveness of neoadjuvant chemotherapy in NPC. The methodological quality was assessed using the radiomics quality score. The intra-class correlation coefficient (ICC) was employed to evaluate inter-reader reproducibility. The pooled area under the curve (AUC), pooled sensitivity, and pooled specificity were used to assess the ability of radiomics to predict response to neoadjuvant chemotherapy in NPC. Lastly, the Quality Assessment of Diagnostic Accuracy Studies technique was used to analyze the bias risk. Results: A total of 12 studies were eligible for our systematic review, and 6 papers were included in our meta-analysis. The radiomics quality score was set from 7 to 21 (maximum score: 36). There was satisfactory ICC (ICC = 0.987, 95% CI: 0.957-0.996). The pooled sensitivity and specificity were 0.88 (95% CI: 0.71-0.95) and 0.82 (95% CI: 0.68-0.91), respectively. The overall AUC was 0.91 (95% CI: 0.88-0.93). Conclusion: Prediction response of neoadjuvant chemotherapy in NPC using machine learning and radiomics is beneficial in improving standardization and methodological quality before applying it to clinical practice.

Multimodality MRI-based radiomics approach to predict the posttreatment response of lung cancer brain metastases to gamma knife radiosurgery.

OBJECTIVES: To develop and validate a multimodality MRI-based radiomics approach to predicting the posttreatment response of lung cancer brain metastases (LCBM) to gamma knife radiosurgery (GKRS). METHODS: We retrospectively analyzed 213 lesions from 137 patients with LCBM who received GKRS between January 2017 and November 2020. The data were divided into a primary cohort (102 patients with 173 lesions) and an independent validation cohort (35 patients with 40 lesions) according to the time of treatment. Benefit result was defined using pretreatment and 3-month follow-up MRI images based on the Response Assessment in Neuro-Oncology Brain Metastases criteria. Valuable radiomics features were extracted from pretreatment multimodality MRI images using random forests. Prediction performance among the radiomics features of tumor core (RFTC) and radiomics features of peritumoral edema (RFPE) together was evaluated separately. Then, the random forest radiomics score and nomogram were developed through the primary cohort and evaluated through an independent validation cohort. Prediction performance was evaluated by ROC curve, calibration curve, and decision curve. RESULTS: Gender (p = 0.018), histological subtype (p = 0.009), epidermal growth factor receptor mutation (p = 0.034), and targeted drug treatment (p = 0.021) were significantly associated with posttreatment response. Adding RFPE to RFTC showed improved prediction performance than RFTC alone in primary cohort (AUC = 0.848 versus AUC = 0.750; p < 0.001). Finally, the radiomics nomogram had an AUC of 0.930, a C-index of 0.930 (specificity of 83.1%, sensitivity of 87.3%) in primary cohort, and an AUC of 0.852, a C-index of 0.848 (specificity of 84.2%, sensitivity of 76.2%) in validation cohort. CONCLUSIONS: Multimodality MRI-based radiomics models can predict the posttreatment response of LCBM to GKRS. KEY POINTS: • Among the selected radiomics features, texture features basically contributed the dominant force in prediction tasks (80%), especially gray-level co-occurrence matrix features (40%). • Adding RFPE to RFTC showed improved prediction performance than RFTC alone in primary cohort (AUC = 0.848 versus AUC = 0.750; p < 0.001). • The multimodality MRI-based radiomics nomogram showed high accuracy for distinguishing the posttreatment response of LCBM to GKRS (AUC = 0.930, in primary cohort; AUC = 0.852, in validation cohort).

Soliton phenomena in normal and anomalous dispersion regions in Er-doped mode-locked fiber lasers based on Cr2Si2Te6 saturable absorbers.

Investigations of optical solitons have always been a hot topic due to their important scientific research value. In recent years, ultrafast lasers based on two-dimensional materials such as saturable absorbers (SAs) have become the focus of optical soliton research. In this work, various soliton operations are demonstrated in Er-doped fiber lasers (EDFLs) based on ${{\rm Cr}_2}{{\rm Si}_2}{{\rm Te}_6}$ SAs. First, a low-threshold passively mode-locked EDFL with traditional soliton output is constructed, and the pump threshold is as low as 10.1 mW. Second, by adjusting the net dispersion of the cavity, stable dissipative soliton operation can also be obtained. Traditional soliton mode-locked operation with controllable Kelly sidebands from first order to fourth order is realized by adjusting the pump power in a double-ended pumped structure, and the SNR is as high as 55 dB. All results prove that ${{\rm Cr}_2}{{\rm Si}_2}{{\rm Te}_6}$ used as SA material has great potential and wide application prospects in investigating optical soliton operations in mode-locked fiber lasers with both normal and anomalous dispersion.

Axial Attention Convolutional Neural Network for Brain Tumor Segmentation with Multi-Modality MRI Scans.

Accurately identifying tumors from MRI scans is of the utmost importance for clinical diagnostics and when making plans regarding brain tumor treatment. However, manual segmentation is a challenging and time-consuming process in practice and exhibits a high degree of variability between doctors. Therefore, an axial attention brain tumor segmentation network was established in this paper, automatically segmenting tumor subregions from multi-modality MRIs. The axial attention mechanism was employed to capture richer semantic information, which makes it easier for models to provide local-global contextual information by incorporating local and global feature representations while simplifying the computational complexity. The deep supervision mechanism is employed to avoid vanishing gradients and guide the AABTS-Net to generate better feature representations. The hybrid loss is employed in the model to handle the class imbalance of the dataset. Furthermore, we conduct comprehensive experiments on the BraTS 2019 and 2020 datasets. The proposed AABTS-Net shows greater robustness and accuracy, which signifies that the model can be employed in clinical practice and provides a new avenue for medical image segmentation systems.

The Impact of Different Uses of the Internet on Farmers' Adoption of Soil Testing and Formulated Fertilization Technology in Rural China.

Soil testing and formulated fertilization technology can effectively solve the problem of the excessive and inefficient use of chemical fertilizers. Previous studies have found that the use of the Internet can increase the adoption of soil testing and formulated fertilization technology among farmers. However, they do not distinguish between the effects of the different uses of the Internet (with or without productive use) on the adoption of soil testing and formulated fertilization technology. This study investigates the Internet use of 5341 professional farmers in rural China in 2019, finding that 18.97% of them still use the Internet for only communication and entertainment and do not use any agricultural productive services on the Internet. The adoption rate of soil testing and fertilization technology among these farmers is only 23.77%, which is approximately 10 percentage points lower than that of farmers who use the Internet for productive purposes. The double robust model shows that the probability of the adoption of soil testing and formulated fertilization technology by farmers with productive use of the Internet increases by six percentage points, which is both statistically and economically significant. In the future, China should train more farmers to use the Internet for productive purposes; this will help more farmers, particularly those with low skills and low educational attainment, to use the Internet and play a positive role in promoting the Internet for green agricultural production techniques.

Differentiation of Brain Abscess From Cystic Glioma Using Conventional MRI Based on Deep Transfer Learning Features and Hand-Crafted Radiomics Features.

Objectives: To develop and validate the model for distinguishing brain abscess from cystic glioma by combining deep transfer learning (DTL) features and hand-crafted radiomics (HCR) features in conventional T1-weighted imaging (T1WI) and T2-weighted imaging (T2WI). Methods: This single-center retrospective analysis involved 188 patients with pathologically proven brain abscess (102) or cystic glioma (86). One thousand DTL and 105 HCR features were extracted from the T1WI and T2WI of the patients. Three feature selection methods and four classifiers, such as k-nearest neighbors (KNN), random forest classifier (RFC), logistic regression (LR), and support vector machine (SVM), for distinguishing brain abscess from cystic glioma were compared. The best feature combination and classifier were chosen according to the quantitative metrics including area under the curve (AUC), Youden Index, and accuracy. Results: In most cases, deep learning-based radiomics (DLR) features, i.e., DTL features combined with HCR features, contributed to a higher accuracy than HCR and DTL features alone for distinguishing brain abscesses from cystic gliomas. The AUC values of the model established, based on the DLR features in T2WI, were 0.86 (95% CI: 0.81, 0.91) in the training cohort and 0.85 (95% CI: 0.75, 0.95) in the test cohort, respectively. Conclusions: The model established with the DLR features can distinguish brain abscess from cystic glioma efficiently, providing a useful, inexpensive, convenient, and non-invasive method for differential diagnosis. This is the first time that conventional MRI radiomics is applied to identify these diseases. Also, the combination of HCR and DTL features can lead to get impressive performance.

Generative adversarial networks in medical image segmentation: A review.

PURPOSE: Since Generative Adversarial Network (GAN) was introduced into the field of deep learning in 2014, it has received extensive attention from academia and industry, and a lot of high-quality papers have been published. GAN effectively improves the accuracy of medical image segmentation because of its good generating ability and capability to capture data distribution. This paper introduces the origin, working principle, and extended variant of GAN, and it reviews the latest development of GAN-based medical image segmentation methods. METHOD: To find the papers, we searched on Google Scholar and PubMed with the keywords like "segmentation", "medical image", and "GAN (or generative adversarial network)". Also, additional searches were performed on Semantic Scholar, Springer, arXiv, and the top conferences in computer science with the above keywords related to GAN. RESULTS: We reviewed more than 120 GAN-based architectures for medical image segmentation that were published before September 2021. We categorized and summarized these papers according to the segmentation regions, imaging modality, and classification methods. Besides, we discussed the advantages, challenges, and future research directions of GAN in medical image segmentation. CONCLUSIONS: We discussed in detail the recent papers on medical image segmentation using GAN. The application of GAN and its extended variants has effectively improved the accuracy of medical image segmentation. Obtaining the recognition of clinicians and patients and overcoming the instability, low repeatability, and uninterpretability of GAN will be an important research direction in the future.

Red Blood Cell Classification Based on Attention Residual Feature Pyramid Network.

Clinically, red blood cell abnormalities are closely related to tumor diseases, red blood cell diseases, internal medicine, and other diseases. Red blood cell classification is the key to detecting red blood cell abnormalities. Traditional red blood cell classification is done manually by doctors, which requires a lot of manpower produces subjective results. This paper proposes an Attention-based Residual Feature Pyramid Network (ARFPN) to classify 14 types of red blood cells to assist the diagnosis of related diseases. The model performs classification directly on the entire red blood cell image. Meanwhile, a spatial attention mechanism and channel attention mechanism are combined with residual units to improve the expression of category-related features and achieve accurate extraction of features. Besides, the RoI align method is used to reduce the loss of spatial symmetry and improve classification accuracy. Five hundred and eighty eight red blood cell images are used to train and verify the effectiveness of the proposed method. The Channel Attention Residual Feature Pyramid Network (C-ARFPN) model achieves an mAP of 86%; the Channel and Spatial Attention Residual Feature Pyramid Network (CS-ARFPN) model achieves an mAP of 86.9%. The experimental results indicate that our method can classify more red blood cell types and better adapt to the needs of doctors, thus reducing the doctor's time and improving the diagnosis efficiency.

United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI.

Simultaneous segmentation and detection of liver tumors (hemangioma and hepatocellular carcinoma (HCC)) by using multi-modality non-contrast magnetic resonance imaging (NCMRI) are crucial for the clinical diagnosis. However, it is still a challenging task due to: (1) the HCC information on NCMRI is insufficient makes extraction of liver tumors feature difficult; (2) diverse imaging characteristics in multi-modality NCMRI causes feature fusion and selection difficult; (3) no specific information between hemangioma and HCC on NCMRI cause liver tumors detection difficult. In this study, we propose a united adversarial learning framework (UAL) for simultaneous liver tumors segmentation and detection using multi-modality NCMRI. The UAL first utilizes a multi-view aware encoder to extract multi-modality NCMRI information for liver tumor segmentation and detection. In this encoder, a novel edge dissimilarity feature pyramid module is designed to facilitate the complementary multi-modality feature extraction. Secondly, the newly designed fusion and selection channel is used to fuse the multi-modality feature and make the decision of the feature selection. Then, the proposed mechanism of coordinate sharing with padding integrates the multi-task of segmentation and detection so that it enables multi-task to perform united adversarial learning in one discriminator. Lastly, an innovative multi-phase radiomics guided discriminator exploits the clear and specific tumor information to improve the multi-task performance via the adversarial learning strategy. The UAL is validated in corresponding multi-modality NCMRI (i.e. T1FS pre-contrast MRI, T2FS MRI, and DWI) and three phases contrast-enhanced MRI of 255 clinical subjects. The experiments show that UAL gains high performance with the dice similarity coefficient of 83.63%, the pixel accuracy of 97.75%, the intersection-over-union of 81.30%, the sensitivity of 92.13%, the specificity of 93.75%, and the detection accuracy of 92.94%, which demonstrate that UAL has great potential in the clinical diagnosis of liver tumors.