首页 > 最新文献

Biocybernetics and Biomedical Engineering最新文献

英文 中文
Corrigendum to “Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images” [Biocybern. Biomed. Eng. 43(3) (2023) 586–602] 用于超声图像中前列腺精确分割的多级全卷积网络》[Biocybern. Biomed. Eng. 43(3) (2023) 586-602] 更正
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.10.003
Yujie Feng , Chukwuemeka Clinton Atabansi , Jing Nie , Haijun Liu , Hang Zhou , Huai Zhao , Ruixia Hong , Fang Li , Xichuan Zhou
{"title":"Corrigendum to “Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images” [Biocybern. Biomed. Eng. 43(3) (2023) 586–602]","authors":"Yujie Feng , Chukwuemeka Clinton Atabansi , Jing Nie , Haijun Liu , Hang Zhou , Huai Zhao , Ruixia Hong , Fang Li , Xichuan Zhou","doi":"10.1016/j.bbe.2023.10.003","DOIUrl":"10.1016/j.bbe.2023.10.003","url":null,"abstract":"","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 4","pages":"Page 776"},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0208521623000578/pdfft?md5=6a5fed5d9ac5219134f858f11ea0539f&pid=1-s2.0-S0208521623000578-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136127396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Automated detection of abnormal respiratory sound from electronic stethoscope and mobile phone using MobileNetV2 利用MobileNetV2自动检测来自电子听诊器和手机的异常呼吸声
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.11.001
Ximing Liao , Yin Wu , Nana Jiang , Jiaxing Sun , Wujian Xu , Shaoyong Gao , Jun Wang , Ting Li , Kun Wang , Qiang Li

Auscultation, a traditional clinical examination method using a stethoscope to quickly assess airway abnormalities, remains valuable due to its real-time, non-invasive, and easy-to-perform nature. Recent advancements in computerized respiratory sound analysis (CRSA) have provided a quantifiable approach for recording, editing, and comparing respiratory sounds, also enabling the training of artificial intelligence models to fully excavate the potential of auscultation. However, existing sound analysis models often require complex computations, leading to prolonged processing times and high calculation and memory requirements. Moreover, the limited diversity and scope of available databases limits reproducibility and robustness, mainly relying on small sample datasets primarily collected from Caucasians. In order to overcome these limitations, we developed a new Chinese adult respiratory sound database, LD-DF RSdb, using an electronic stethoscope and mobile phone. By enrolling 145 participants, 9,584 high quality recordings were collected, containing 6,435 normal sounds, 2,782 crackles, 208 wheezes, and 159 combined sounds. Subsequently, we utilized a lightweight neural network architecture, MobileNetV2, for automated categorization of the four types of respiratory sounds, achieving an appreciable overall performance with an AUC of 0.8923. This study demonstrates the feasibility and potential of using mobile phones, electronic stethoscopes, and MobileNetV2 in CRSA. The proposed method offers a convenient and promising approach to enhance overall respiratory disease management and may help address healthcare resource disparities.

听诊是一种传统的临床检查方法,使用听诊器快速评估气道异常,由于其实时性,无创性和易于操作的性质,仍然有价值。计算机呼吸音分析(CRSA)的最新进展为记录、编辑和比较呼吸音提供了可量化的方法,也使人工智能模型的训练能够充分挖掘听诊的潜力。然而,现有的声音分析模型往往需要复杂的计算,导致处理时间延长,计算和内存需求高。此外,可用数据库的有限多样性和范围限制了可重复性和稳健性,主要依赖于主要从高加索人收集的小样本数据集。为了克服这些限制,我们利用电子听诊器和手机开发了一个新的中国成人呼吸声数据库LD-DF RSdb。通过招募145名参与者,收集了9584个高质量的录音,其中包括6435个正常声音,2782个噼啪声,208个喘息声和159个混合声音。随后,我们利用轻量级的神经网络架构MobileNetV2对四种类型的呼吸声音进行自动分类,取得了令人满意的整体性能,AUC为0.8923。本研究证明了在CRSA中使用移动电话、电子听诊器和MobileNetV2的可行性和潜力。提出的方法提供了一种方便和有前途的方法,以加强整体呼吸系统疾病的管理,并可能有助于解决医疗资源差距。
{"title":"Automated detection of abnormal respiratory sound from electronic stethoscope and mobile phone using MobileNetV2","authors":"Ximing Liao ,&nbsp;Yin Wu ,&nbsp;Nana Jiang ,&nbsp;Jiaxing Sun ,&nbsp;Wujian Xu ,&nbsp;Shaoyong Gao ,&nbsp;Jun Wang ,&nbsp;Ting Li ,&nbsp;Kun Wang ,&nbsp;Qiang Li","doi":"10.1016/j.bbe.2023.11.001","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.11.001","url":null,"abstract":"<div><p>Auscultation, a traditional clinical examination method using a stethoscope to quickly assess airway abnormalities, remains valuable due to its real-time, non-invasive, and easy-to-perform nature. Recent advancements in computerized respiratory sound analysis (CRSA) have provided a quantifiable approach for recording, editing, and comparing respiratory sounds, also enabling the training of artificial intelligence models to fully excavate the potential of auscultation. However, existing sound analysis models often require complex computations, leading to prolonged processing times and high calculation and memory requirements. Moreover, the limited diversity and scope of available databases limits reproducibility and robustness, mainly relying on small sample datasets primarily collected from Caucasians. In order to overcome these limitations, we developed a new Chinese adult respiratory sound database, LD-DF RSdb, using an electronic stethoscope and mobile phone. By enrolling 145 participants, 9,584 high quality recordings were collected, containing 6,435 normal sounds, 2,782 crackles, 208 wheezes, and 159 combined sounds. Subsequently, we utilized a lightweight neural network architecture, MobileNetV2, for automated categorization of the four types of respiratory sounds, achieving an appreciable overall performance with an AUC of 0.8923. This study demonstrates the feasibility and potential of using mobile phones, electronic stethoscopes, and MobileNetV2 in CRSA. The proposed method offers a convenient and promising approach to enhance overall respiratory disease management and may help address healthcare resource disparities.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 4","pages":"Pages 763-775"},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0208521623000608/pdfft?md5=eb2d1ad12271a18266dc09d4d5b9b3c9&pid=1-s2.0-S0208521623000608-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138448149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A dual-stage transformer and MLP-based network for breast ultrasound image segmentation 基于双级变压器和mlp网络的乳腺超声图像分割
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.09.001
Guidi Lin , Mingzhi Chen , Minsheng Tan , Lingna Chen , Junxi Chen

Automatic segmentation of breast lesions from ultrasound images plays an important role in computer-aided breast cancer diagnosis. Many deep learning methods based on convolutional neural networks (CNNs) have been proposed for breast ultrasound image segmentation. However, breast ultrasound image segmentation is still challenging due to ambiguous lesion boundaries. We propose a novel dual-stage framework based on Transformer and Multi-layer perceptron (MLP) for the segmentation of breast lesions. We combine the Swin Transformer block with an efficient pyramid squeezed attention block in a parallel design and introduce bi-directional interactions across branches, which can efficiently extract multi-scale long-range dependencies to improve the segmentation performance and robustness of the model. Furthermore, we introduce tokenized MLP block in the MLP stage to extract global contextual information while retaining fine-grained information to segment more complex breast lesions. We have conducted extensive experiments with state-of-the-art methods on three breast ultrasound datasets, including BUSI, BUL, and MT_BUS datasets. The dice coefficient reached 0.8127 ± 0.2178, and the intersection over union reached 0.7269 ± 0.2370 on benign lesions when the Hausdorff distance was maintained at 3.75 ± 1.83. The dice coefficient of malignant lesions is improved by 3.09% for BUSI dataset. The segmentation results on the BUL and MT_BUS datasets also show that our proposed model achieves better segmentation results than other methods. Moreover, the external experiments indicate that the proposed model provides better generalization capability for breast lesion segmentation. The dual-stage scheme and the proposed Transformer module achieve the fine-grained local information and long-range dependencies to relieve the burden of radiologists.

超声图像中乳腺病变的自动分割在癌症计算机辅助诊断中起着重要作用。已经提出了许多基于卷积神经网络(CNNs)的深度学习方法用于乳腺超声图像分割。然而,由于病变边界不明确,乳腺超声图像分割仍然具有挑战性。我们提出了一种新的基于Transformer和多层感知器(MLP)的双阶段框架来分割乳腺病变。我们在并行设计中将Swin-Transformer块与高效的金字塔压缩注意力块相结合,并引入跨分支的双向交互,可以有效地提取多尺度长程依赖关系,以提高模型的分割性能和鲁棒性。此外,我们在MLP阶段引入了标记化MLP块来提取全局上下文信息,同时保留细粒度信息来分割更复杂的乳腺病变。我们使用最先进的方法在三个乳腺超声数据集上进行了广泛的实验,包括BUSI、BUL和MT_BUS数据集。骰子系数达到0.8127 ± 0.2178,并集上的交点达到0.7269 ± 当Hausdorff距离保持在3.75时,良性病变为0.2370 ± 1.83.BUSI数据集的恶性病变骰子系数提高了3.09%。在BUL和MT_BUS数据集上的分割结果也表明,我们提出的模型比其他方法获得了更好的分割结果。此外,外部实验表明,该模型为乳腺病变分割提供了更好的泛化能力。双阶段方案和所提出的Transformer模块实现了细粒度的局部信息和长程依赖性,减轻了放射科医生的负担。
{"title":"A dual-stage transformer and MLP-based network for breast ultrasound image segmentation","authors":"Guidi Lin ,&nbsp;Mingzhi Chen ,&nbsp;Minsheng Tan ,&nbsp;Lingna Chen ,&nbsp;Junxi Chen","doi":"10.1016/j.bbe.2023.09.001","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.09.001","url":null,"abstract":"<div><p><span>Automatic segmentation of breast lesions from ultrasound images plays an important role in computer-aided breast cancer diagnosis. Many deep learning<span> methods based on convolutional neural networks (CNNs) have been proposed for </span></span>breast ultrasound<span> image segmentation. However, breast ultrasound image segmentation is still challenging due to ambiguous lesion boundaries. We propose a novel dual-stage framework based on Transformer and Multi-layer perceptron<span><span><span> (MLP) for the segmentation of breast lesions. We combine the Swin Transformer block with an efficient pyramid squeezed attention block in a parallel design and introduce bi-directional interactions across branches, which can efficiently extract multi-scale long-range dependencies to improve the segmentation performance and robustness of the model. Furthermore, we introduce tokenized MLP block in the MLP stage to extract global contextual information while retaining fine-grained information to segment more complex breast lesions. We have conducted extensive experiments with state-of-the-art methods on three breast ultrasound datasets, including BUSI, BUL, and MT_BUS datasets. The dice coefficient reached 0.8127 ± 0.2178, and the intersection over union reached 0.7269 ± 0.2370 on </span>benign lesions<span> when the Hausdorff distance was maintained at 3.75 ± 1.83. The dice coefficient of malignant lesions is improved by 3.09% for BUSI dataset. The segmentation results on the BUL and MT_BUS datasets also show that our proposed model achieves better segmentation results than other methods. Moreover, the external experiments indicate that the proposed model provides better generalization capability for breast lesion segmentation. The dual-stage scheme and the proposed Transformer module achieve the fine-grained local information and long-range dependencies to relieve the burden of </span></span>radiologists.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 4","pages":"Pages 656-671"},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Automated detection of multi-class urinary sediment particles: An accurate deep learning approach 多类尿液沉淀物颗粒的自动检测:一种精确的深度学习方法
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-10-01 DOI: 10.1016/j.bbe.2023.09.003
He Lyu , Fanxin Xu , Tao Jin , Siyi Zheng , Chenchen Zhou , Yang Cao , Bin Luo , Qinzhen Huang , Wei Xiang , Dong Li

Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images.

尿液显微镜是肾脏和泌尿道疾病的重要诊断工具,尿液沉积物颗粒的自动分析提高了诊断效率。然而,由于个体差异、边界模糊和样本不平衡,一些尿沉渣颗粒仍然难以识别。本研究旨在减轻尿液沉积物颗粒的不良影响,同时提高多类检测性能。我们提出了一种基于改进YOLOX的尿沉渣颗粒检测创新模型(YUS-Net)。尿沉渣数据增强和整体预训练权重的结合增强了模型优化的潜力。此外,我们将注意力模块纳入关键特征转移路径,并使用一种新的损失函数Varifocur损失来促进判别特征的提取,这有助于识别密集分布的小物体。基于USE数据集,YUS-Net的平均准确度(mAP)为96.07%,平均准确度为99.35%,平均召回率为96.77%,延迟为26.13 ms每幅图像。每个类别的具体指标如下:铸造:99.66%的AP;晶体:100%AP;表位:92.31%AP;表位:100%AP;红斑:92.31%的AP;白细胞:99.90%AP;霉菌:99.96%的AP。YUS Net采用实用的网络结构,实现了高效、准确、端到端的尿沉渣颗粒检测。该模型采用本地高分辨率图像作为输入,无需额外步骤。最后,建立了一种适用于尿液显微图像领域的数据增强策略,为在尿液显微图像中应用其他方法提供了一种新的方法。
{"title":"Automated detection of multi-class urinary sediment particles: An accurate deep learning approach","authors":"He Lyu ,&nbsp;Fanxin Xu ,&nbsp;Tao Jin ,&nbsp;Siyi Zheng ,&nbsp;Chenchen Zhou ,&nbsp;Yang Cao ,&nbsp;Bin Luo ,&nbsp;Qinzhen Huang ,&nbsp;Wei Xiang ,&nbsp;Dong Li","doi":"10.1016/j.bbe.2023.09.003","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.09.003","url":null,"abstract":"<div><p>Urine microscopy is an essential diagnostic tool for kidney and urinary tract diseases, with automated analysis of urinary sediment particles improving diagnostic efficiency. However, some urinary sediment particles remain challenging to identify due to individual variations, blurred boundaries, and unbalanced samples. This research aims to mitigate the adverse effects of urine sediment particles while improving multi-class detection performance. We proposed an innovative model based on improved YOLOX for detecting urine sediment particles (YUS-Net). The combination of urine sediment data augmentation and overall pre-trained weights enhances model optimization potential. Furthermore, we incorporate the attention module into the critical feature transfer path and employ a novel loss function, Varifocal loss, to facilitate the extraction of discriminative features, which assists in the identification of densely distributed small objects. Based on the USE dataset, YUS-Net achieves the mean Average Precision (mAP) of 96.07%, 99.35% average precision, and 96.77% average recall, with a latency of 26.13 ms per image. The specific metrics for each category are as follows: cast: 99.66% AP; cryst: 100% AP; epith: 92.31% AP; epithn: 100% AP; eryth: 92.31% AP; leuko: 99.90% AP; mycete: 99.96% AP. With a practical network structure, YUS-Net achieved efficient, accurate, end-to-end urinary sediment particle detection. The model takes native high-resolution images as input without additional steps. Finally, a data augmentation strategy appropriate for the urinary microscopic image domain is established, which provides a novel approach for applying other methods in urine microscopic images.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 4","pages":"Pages 672-683"},"PeriodicalIF":6.4,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images 超声图像中前列腺精确分割的多阶段全卷积网络
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.08.002
Yujie Feng , Chukwuemeka Clinton Atabansi , Jing Nie , Haijun Liu , Hang Zhou , Huai Zhao , Ruixia Hong , Fang Li , Xichuan Zhou

Prostate cancer is one of the most commonly diagnosed non-cutaneous malignant tumors and the sixth major cause of cancer-related death generally found in men globally. Automatic segmentation of prostate regions has a wide range of applications in prostate cancer diagnosis and treatment. It is challenging to extract powerful spatial features for precise prostate segmentation methods due to the wide variation in prostate size, shape, and histopathologic heterogeneity among patients. Most of the existing CNN-based architectures often produce unsatisfactory results and inaccurate boundaries in prostate segmentation, which are caused by inadequate discriminative feature maps and the limited amount of spatial information. To address these issues, we propose a novel deep learning technique called Multi-Stage FCN architecture for 2D prostate segmentation that captures more precise spatial information and accurate prostate boundaries. In addition, a new prostate ultrasound image dataset known as CCH-TRUSPS was collected from Chongqing University Cancer Hospital, including prostate ultrasound images of various prostate cancer architectures. We evaluate our method on the CCH-TRUSPS dataset and the publicly available Multi-site T2-weighted MRI dataset using five commonly used metrics for medical image analysis. When compared to other CNN-based methods on the CCH-TRUSPS test set, our Multi-Stage FCN achieves the highest and best binary accuracy of 99.15%, the DSC score of 94.90%, the IoU score of 89.80%, the precision of 94.67%, and the recall of 96.49%. The statistical and visual results demonstrate that our approach outperforms previous CNN-based techniques in all ramifications and can be used for the clinical diagnosis of prostate cancer.

前列腺癌是最常见的非皮肤恶性肿瘤之一,也是全球男性癌症相关死亡的第六大原因。前列腺区域自动分割在前列腺癌的诊断和治疗中有着广泛的应用。由于前列腺大小、形状和组织病理异质性的广泛差异,为精确的前列腺分割方法提取强大的空间特征是具有挑战性的。现有的大多数基于cnn的架构在前列腺分割中往往产生不理想的结果和不准确的边界,这是由不充分的判别特征映射和有限的空间信息造成的。为了解决这些问题,我们提出了一种新的深度学习技术,称为多阶段FCN架构,用于二维前列腺分割,可以捕获更精确的空间信息和准确的前列腺边界。此外,从重庆大学肿瘤医院收集了一个新的前列腺超声图像数据集CCH-TRUSPS,包括各种前列腺癌结构的前列腺超声图像。我们在CCH-TRUSPS数据集和公开可用的多站点t2加权MRI数据集上使用五种常用的医学图像分析指标来评估我们的方法。在CCH-TRUSPS测试集上,与其他基于cnn的方法相比,我们的多阶段FCN的最高和最佳二值准确率为99.15%,DSC评分为94.90%,IoU评分为89.80%,精密度为94.67%,召回率为96.49%。统计和视觉结果表明,我们的方法在所有分支中都优于以前基于cnn的技术,可用于前列腺癌的临床诊断。
{"title":"Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images","authors":"Yujie Feng ,&nbsp;Chukwuemeka Clinton Atabansi ,&nbsp;Jing Nie ,&nbsp;Haijun Liu ,&nbsp;Hang Zhou ,&nbsp;Huai Zhao ,&nbsp;Ruixia Hong ,&nbsp;Fang Li ,&nbsp;Xichuan Zhou","doi":"10.1016/j.bbe.2023.08.002","DOIUrl":"10.1016/j.bbe.2023.08.002","url":null,"abstract":"<div><p><span><span>Prostate cancer is one of the most commonly diagnosed non-cutaneous malignant tumors and the sixth major cause of cancer-related death generally found in men globally. Automatic segmentation of prostate regions has a wide range of applications in prostate cancer diagnosis and treatment. It is challenging to extract powerful spatial features for precise prostate </span>segmentation methods due to the wide variation in prostate size, shape, and histopathologic heterogeneity among patients. Most of the existing CNN-based architectures often produce unsatisfactory results and inaccurate boundaries in prostate segmentation, which are caused by inadequate discriminative feature maps and the limited amount of spatial information. To address these issues, we propose a novel </span>deep learning<span> technique called Multi-Stage FCN architecture for 2D prostate segmentation that captures more precise spatial information and accurate prostate boundaries. In addition, a new prostate ultrasound image dataset known as CCH-TRUSPS was collected from Chongqing University Cancer Hospital, including prostate ultrasound images of various prostate cancer architectures. We evaluate our method on the CCH-TRUSPS dataset and the publicly available Multi-site T2-weighted MRI dataset using five commonly used metrics for medical image analysis. When compared to other CNN-based methods on the CCH-TRUSPS test set, our Multi-Stage FCN achieves the highest and best binary accuracy of 99.15%, the DSC score of 94.90%, the IoU score of 89.80%, the precision of 94.67%, and the recall of 96.49%. The statistical and visual results demonstrate that our approach outperforms previous CNN-based techniques in all ramifications and can be used for the clinical diagnosis of prostate cancer.</span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 586-602"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43556776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Attention-guided multiple instance learning for COPD identification: To combine the intensity and morphology 注意引导多实例学习识别COPD:将强度与形态学相结合
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.06.004
Yanan Wu , Shouliang Qi , Jie Feng , Runsheng Chang , Haowen Pang , Jie Hou , Mengqi Li , Yingxi Wang , Shuyue Xia , Wei Qian

Chronic obstructive pulmonary disease (COPD) is a complex and multi-component respiratory disease. Computed tomography (CT) images can characterize lesions in COPD patients, but the image intensity and morphology of lung components have not been fully exploited. Two datasets (Dataset 1 and 2) comprising a total of 561 subjects were obtained from two centers. A multiple instance learning (MIL) method is proposed for COPD identification. First, randomly selected slices (instances) from CT scans and multi-view 2D snapshots of the 3D airway tree and lung field extracted from CT images are acquired. Then, three attention-guided MIL models (slice-CT, snapshot-airway, and snapshot-lung-field models) are trained. In these models, a deep convolution neural network (CNN) is utilized for feature extraction. Finally, the outputs of the above three MIL models are combined using logistic regression to produce the final prediction. For Dataset 1, the accuracy of the slice-CT MIL model with 20 instances was 88.1%. The backbone of VGG-16 outperformed Alexnet, Resnet18, Resnet26, and Mobilenet_v2 in feature extraction. The snapshot-airway and snapshot-lung-field MIL models achieved accuracies of 89.4% and 90.0%, respectively. After the three models were combined, the accuracy reached 95.8%. The proposed model outperformed several state-of-the-art methods and afforded an accuracy of 83.1% for the external dataset (Dataset 2). The proposed weakly supervised MIL method is feasible for COPD identification. The effective CNN module and attention-guided MIL pooling module contribute to performance enhancement. The morphology information of the airway and lung field is beneficial for identifying COPD.

慢性阻塞性肺疾病(COPD)是一种复杂的多组分呼吸系统疾病。计算机断层扫描(CT)图像可以表征慢性阻塞性肺病患者的病变,但图像强度和肺成分的形态尚未得到充分利用。两个数据集(数据集1和数据集2)共561名受试者,来自两个中心。提出了一种基于多实例学习(MIL)的慢阻肺识别方法。首先,从CT扫描中随机选择切片(实例),并从CT图像中提取三维气道树和肺场的多视图二维快照。然后,训练了三种注意力引导的MIL模型(切片- ct,快照-气道和快照-肺场模型)。在这些模型中,使用深度卷积神经网络(CNN)进行特征提取。最后,使用逻辑回归将上述三种MIL模型的输出组合以产生最终预测。对于数据集1,包含20个实例的切片ct MIL模型的准确率为88.1%。VGG-16的主干在特征提取方面优于Alexnet、Resnet18、Resnet26和Mobilenet_v2。快照气道和快照长场MIL模型的准确率分别为89.4%和90.0%。三种模型组合后,准确率达到95.8%。所提出的模型优于几种最先进的方法,并为外部数据集(数据集2)提供83.1%的准确率。所提出的弱监督MIL方法对于COPD识别是可行的。有效的CNN模块和注意引导的MIL池模块有助于提高性能。气道和肺野的形态学信息有利于COPD的鉴别。
{"title":"Attention-guided multiple instance learning for COPD identification: To combine the intensity and morphology","authors":"Yanan Wu ,&nbsp;Shouliang Qi ,&nbsp;Jie Feng ,&nbsp;Runsheng Chang ,&nbsp;Haowen Pang ,&nbsp;Jie Hou ,&nbsp;Mengqi Li ,&nbsp;Yingxi Wang ,&nbsp;Shuyue Xia ,&nbsp;Wei Qian","doi":"10.1016/j.bbe.2023.06.004","DOIUrl":"10.1016/j.bbe.2023.06.004","url":null,"abstract":"<div><p><span>Chronic obstructive pulmonary disease<span> (COPD) is a complex and multi-component respiratory disease. Computed tomography (CT) images can characterize lesions in COPD patients, but the image intensity and morphology of lung components have not been fully exploited. Two datasets (Dataset 1 and 2) comprising a total of 561 subjects were obtained from two centers. A multiple instance learning (MIL) method is proposed for COPD identification. First, randomly selected slices (instances) from CT scans and multi-view 2D snapshots of the 3D </span></span>airway tree<span><span> and lung field extracted from CT images are acquired. Then, three attention-guided MIL models (slice-CT, snapshot-airway, and snapshot-lung-field models) are trained. In these models, a deep convolution<span> neural network (CNN) is utilized for feature extraction. Finally, the outputs of the above three MIL models are combined using </span></span>logistic regression to produce the final prediction. For Dataset 1, the accuracy of the slice-CT MIL model with 20 instances was 88.1%. The backbone of VGG-16 outperformed Alexnet, Resnet18, Resnet26, and Mobilenet_v2 in feature extraction. The snapshot-airway and snapshot-lung-field MIL models achieved accuracies of 89.4% and 90.0%, respectively. After the three models were combined, the accuracy reached 95.8%. The proposed model outperformed several state-of-the-art methods and afforded an accuracy of 83.1% for the external dataset (Dataset 2). The proposed weakly supervised MIL method is feasible for COPD identification. The effective CNN module and attention-guided MIL pooling module contribute to performance enhancement. The morphology information of the airway and lung field is beneficial for identifying COPD.</span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 568-585"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42298880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficient simultaneous segmentation and classification of brain tumors from MRI scans using deep learning 利用深度学习对MRI扫描中的脑肿瘤进行有效的同时分割和分类
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.08.003
Akshya Kumar Sahoo , Priyadarsan Parida , K. Muralibabu , Sonali Dash

Brain tumors can be difficult to diagnose, as they may have similar radiographic characteristics, and a thorough examination may take a considerable amount of time. To address these challenges, we propose an intelligent system for the automatic extraction and identification of brain tumors from 2D CE MRI images. Our approach comprises two stages. In the first stage, we use an encoder-decoder based U-net with residual network as the backbone to detect different types of brain tumors, including glioma, meningioma, and pituitary tumors. Our method achieved an accuracy of 99.60%, a sensitivity of 90.20%, a specificity of 99.80%, a dice similarity coefficient of 90.11%, and a precision of 90.50% for tumor extraction. In the second stage, we employ a YOLO2 (you only look once) based transfer learning approach to classify the extracted tumors, achieving a classification accuracy of 97%. Our proposed approach outperforms state-of-the-art methods found in the literature. The results demonstrate the potential of our method to aid in the diagnosis and treatment of brain tumors.

脑肿瘤很难诊断,因为它们可能具有相似的放射学特征,彻底的检查可能需要相当长的时间。为了解决这些挑战,我们提出了一种从二维CE MRI图像中自动提取和识别脑肿瘤的智能系统。我们的方法包括两个阶段。在第一阶段,我们使用基于编码器-解码器的U-net,以残馀网络为骨干来检测不同类型的脑肿瘤,包括胶质瘤、脑膜瘤和垂体瘤。该方法的肿瘤提取准确率为99.60%,灵敏度为90.20%,特异性为99.80%,骰子相似系数为90.11%,精密度为90.50%。在第二阶段,我们采用基于YOLO2(你只看一次)的迁移学习方法对提取的肿瘤进行分类,分类准确率达到97%。我们提出的方法优于文献中发现的最先进的方法。结果证明了我们的方法在脑肿瘤诊断和治疗方面的潜力。
{"title":"Efficient simultaneous segmentation and classification of brain tumors from MRI scans using deep learning","authors":"Akshya Kumar Sahoo ,&nbsp;Priyadarsan Parida ,&nbsp;K. Muralibabu ,&nbsp;Sonali Dash","doi":"10.1016/j.bbe.2023.08.003","DOIUrl":"10.1016/j.bbe.2023.08.003","url":null,"abstract":"<div><p><span>Brain tumors can be difficult to diagnose, as they may have similar radiographic characteristics, and a thorough examination may take a considerable amount of time. To address these challenges, we propose an intelligent system for the automatic extraction and identification of brain tumors from 2D CE MRI images. Our approach comprises two stages. In the first stage, we use an encoder-decoder based U-net with residual network<span><span><span> as the backbone to detect different types of brain tumors, including glioma, meningioma, and </span>pituitary tumors. Our method achieved an accuracy of 99.60%, a sensitivity of 90.20%, a specificity of 99.80%, a </span>dice similarity coefficient of 90.11%, and a precision of 90.50% for tumor extraction. In the second stage, we employ a YOLO2 (you only look once) based </span></span>transfer learning<span> approach to classify the extracted tumors, achieving a classification accuracy of 97%. Our proposed approach outperforms state-of-the-art methods found in the literature. The results demonstrate the potential of our method to aid in the diagnosis and treatment of brain tumors.</span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 616-633"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45686531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Non-invasive waveform analysis for emergency triage via simulated hemorrhage: An experimental study using novel dynamic lower body negative pressure model 模拟出血急诊分诊的无创波形分析:基于新型动态下体负压模型的实验研究
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.06.002
Naimahmed Nesaragi , Lars Øivind Høiseth , Hemin Ali Qadir , Leiv Arne Rosseland , Per Steinar Halvorsen , Ilangko Balasingham

The extent to which advanced waveform analysis of non-invasive physiological signals can diagnose levels of hypovolemia remains insufficiently explored. The present study explores the discriminative ability of a deep learning (DL) framework to classify levels of ongoing hypovolemia, simulated via novel dynamic lower body negative pressure (LBNP) model among healthy volunteers. We used a dynamic LBNP protocol as opposed to the traditional model, where LBNP is applied in a predictable step-wise, progressively descending manner. This dynamic LBNP version assists in circumventing the problem posed in terms of time dependency, as in real-life pre-hospital settings intravascular blood volume may fluctuate due to volume resuscitation. A supervised DL-based framework for ternary classification was realized by segmenting the underlying noninvasive signal and labeling segments with corresponding LBNP target levels. The proposed DL model with two inputs was trained with respective time–frequency representations extracted on waveform segments to classify each of them into blood volume loss: Class 1 (mild); Class 2 (moderate); or Class 3 (severe). At the outset, the latent space derived at the end of the DL model via late fusion among both inputs assists in enhanced classification performance. When evaluated in a 3-fold cross-validation setup with stratified subjects, the experimental findings demonstrated PPG to be a potential surrogate for variations in blood volume with average classification performance, AUROC: 0.8861, AUPRC: 0.8141, F1-score:72.16%, Sensitivity:79.06%, and Specificity:89.21%. Our proposed DL algorithm on PPG signal demonstrates the possibility to capture the complex interplay in physiological responses related to both bleeding and fluid resuscitation using this challenging LBNP setup.

非侵入性生理信号的高级波形分析可以在多大程度上诊断低血容量水平,目前还没有得到充分的探索。本研究探讨了深度学习(DL)框架在健康志愿者中通过新型动态下半身负压(LBNP)模型模拟的持续低血容量水平分类的判别能力。与传统模型相反,我们使用了动态LBNP协议,在传统模型中,LBNP以可预测的逐步递减方式应用。这种动态LBNP版本有助于避免时间依赖性方面的问题,因为在现实生活中的院前环境中,血管内血容量可能会因容量复苏而波动。通过分割潜在的无创信号并用相应的LBNP靶水平标记片段,实现了基于监督DL的三元分类框架。所提出的具有两个输入的DL模型使用在波形段上提取的各自的时间-频率表示进行训练,以将每个波形段分类为血容量损失:1类(轻度);2级(中等);或3级(严重)。一开始,通过两个输入之间的后期融合在DL模型末尾导出的潜在空间有助于增强分类性能。当在分层受试者的3倍交叉验证设置中进行评估时,实验结果表明PPG是血容量变化的潜在替代品,具有平均分类性能,AUROC:0.861,AUPRC:0.8141,F1得分:72.16%,灵敏度:79.06%,特异性:89.21%。我们提出的PPG信号DL算法证明了使用这种具有挑战性的LBNP设置捕捉与出血和液体复苏相关的生理反应中复杂相互作用的可能性。
{"title":"Non-invasive waveform analysis for emergency triage via simulated hemorrhage: An experimental study using novel dynamic lower body negative pressure model","authors":"Naimahmed Nesaragi ,&nbsp;Lars Øivind Høiseth ,&nbsp;Hemin Ali Qadir ,&nbsp;Leiv Arne Rosseland ,&nbsp;Per Steinar Halvorsen ,&nbsp;Ilangko Balasingham","doi":"10.1016/j.bbe.2023.06.002","DOIUrl":"https://doi.org/10.1016/j.bbe.2023.06.002","url":null,"abstract":"<div><p>The extent to which advanced waveform analysis of non-invasive physiological signals can diagnose levels of hypovolemia remains insufficiently explored. The present study explores the discriminative ability of a deep learning (DL) framework to classify levels of ongoing hypovolemia, simulated via novel dynamic lower body negative pressure (LBNP) model among healthy volunteers. We used a dynamic LBNP protocol as opposed to the traditional model, where LBNP is applied in a predictable step-wise, progressively descending manner. This dynamic LBNP version assists in circumventing the problem posed in terms of time dependency, as in real-life pre-hospital settings intravascular blood volume may fluctuate due to volume resuscitation. A supervised DL-based framework for ternary classification was realized by segmenting the underlying noninvasive signal and labeling segments with corresponding LBNP target levels. The proposed DL model with two inputs was trained with respective time–frequency representations extracted on waveform segments to classify each of them into blood volume loss: Class 1 (mild); Class 2 (moderate); or Class 3 (severe). At the outset, the latent space derived at the end of the DL model via late fusion among both inputs assists in enhanced classification performance. When evaluated in a 3-fold cross-validation setup with stratified subjects, the experimental findings demonstrated PPG to be a potential surrogate for variations in blood volume with average classification performance, AUROC: 0.8861, AUPRC: 0.8141, <span><math><mrow><mi>F</mi><mn>1</mn></mrow></math></span>-score:72.16%, Sensitivity:79.06%, and Specificity:89.21%. Our proposed DL algorithm on PPG signal demonstrates the possibility to capture the complex interplay in physiological responses related to both bleeding and fluid resuscitation using this challenging LBNP setup.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 551-567"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49761293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
BA-Net: Brightness prior guided attention network for colonic polyp segmentation BA-Net:用于结肠息肉分割的亮度优先引导注意力网络
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.08.001
Haiying Xia , Yilin Qin , Yumei Tan , Shuxiang Song

Automatic polyp segmentation at colonoscopy plays an important role in the early diagnosis and surgery of colorectal cancer. However, the diversity of polyps in different images greatly increases the difficulty of accurately segmenting polyps. Manual segmentation of polyps in colonoscopic images is time-consuming and the rate of polyps missed remains high. In this paper, we propose a brightness prior guided attention network (BA-Net) for automatic polyp segmentation. Specifically, we first aggregate the high-level features of the last three layers of the encoder with an enhanced receptive field (ERF) module, which further fed to the decoder to obtain the initial prediction maps. Then, we introduce a brightness prior fusion (BF) module that fuses the brightness prior information into the multi-scale side-out high-level semantic features. The BF module aims to induce the network to localize salient regions, which may be potential polyps, to obtain better segmentation results. Finally, we propose a global reverse attention (GRA) module to combine the output of the BF module and the initial prediction map for obtaining long-range dependence and reverse refinement prediction results. With iterative refinement from higher-level semantics to lower-level semantics, our BA-Net can achieve more refined and accurate segmentation. Extensive experiments show that our BA-Net outperforms the state-of-the-art methods on six common polyp datasets.

结肠镜下息肉自动分割在结直肠癌的早期诊断和手术中具有重要作用。然而,不同图像中息肉的多样性大大增加了准确分割息肉的难度。人工分割结肠镜图像中的息肉是费时的,息肉漏报率仍然很高。本文提出了一种用于息肉自动分割的亮度优先引导注意网络(BA-Net)。具体来说,我们首先将编码器最后三层的高级特征与增强的接受场(ERF)模块聚合在一起,并将其进一步馈送到解码器以获得初始预测映射。然后,引入亮度先验融合(BF)模块,将亮度先验信息融合到多尺度侧出高级语义特征中;BF模块的目的是诱导网络定位可能是潜在息肉的显著区域,以获得更好的分割结果。最后,我们提出了一个全局反向关注(GRA)模块,将BF模块的输出与初始预测映射结合起来,获得远程依赖和反向细化预测结果。通过从高级语义到低级语义的迭代细化,我们的BA-Net可以实现更精细和准确的分割。大量的实验表明,我们的BA-Net在六个常见的息肉数据集上优于最先进的方法。
{"title":"BA-Net: Brightness prior guided attention network for colonic polyp segmentation","authors":"Haiying Xia ,&nbsp;Yilin Qin ,&nbsp;Yumei Tan ,&nbsp;Shuxiang Song","doi":"10.1016/j.bbe.2023.08.001","DOIUrl":"10.1016/j.bbe.2023.08.001","url":null,"abstract":"<div><p>Automatic polyp segmentation at colonoscopy plays an important role in the early diagnosis and surgery of colorectal cancer. However, the diversity of polyps in different images greatly increases the difficulty of accurately segmenting polyps. Manual segmentation of polyps in colonoscopic images is time-consuming and the rate of polyps missed remains high. In this paper, we propose a brightness prior guided attention network (BA-Net) for automatic polyp segmentation. Specifically, we first aggregate the high-level features of the last three layers of the encoder with an enhanced receptive field (ERF) module, which further fed to the decoder to obtain the initial prediction maps. Then, we introduce a brightness prior fusion (BF) module that fuses the brightness prior information into the multi-scale side-out high-level semantic features. The BF module aims to induce the network to localize salient regions, which may be potential polyps, to obtain better segmentation results. Finally, we propose a global reverse attention (GRA) module to combine the output of the BF module and the initial prediction map for obtaining long-range dependence and reverse refinement prediction results. With iterative refinement from higher-level semantics to lower-level semantics, our BA-Net can achieve more refined and accurate segmentation. Extensive experiments show that our BA-Net outperforms the state-of-the-art methods on six common polyp datasets.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 603-615"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44506676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Transformer-based cross-modal multi-contrast network for ophthalmic diseases diagnosis 基于变压器的跨模态多对比网络眼科疾病诊断
IF 6.4 2区 医学 Q1 ENGINEERING, BIOMEDICAL Pub Date : 2023-07-01 DOI: 10.1016/j.bbe.2023.06.001
Yang Yu, Hongqing Zhu

Automatic diagnosis of various ophthalmic diseases from ocular medical images is vital to support clinical decisions. Most current methods employ a single imaging modality, especially 2D fundus images. Considering that the diagnosis of ophthalmic diseases can greatly benefit from multiple imaging modalities, this paper further improves the accuracy of diagnosis by effectively utilizing cross-modal data. In this paper, we propose Transformer-based cross-modal multi-contrast network for efficiently fusing color fundus photograph (CFP) and optical coherence tomography (OCT) modality to diagnose ophthalmic diseases. We design multi-contrast learning strategy to extract discriminate features from cross-modal data for diagnosis. Then channel fusion head captures the semantically shared information across different modalities and the similarity features between patients of the same category. Meanwhile, we use a class-balanced training strategy to cope with the situation that medical datasets are usually class-imbalanced. Our method is evaluated on public benchmark datasets for cross-modal ophthalmic disease diagnosis. The experimental results demonstrate that our method outperforms other approaches. The codes and models are available at https://github.com/ecustyy/tcmn.

从眼部医学图像中自动诊断各种眼部疾病对支持临床决策至关重要。目前大多数方法采用单一成像方式,特别是二维眼底图像。考虑到多种成像模式对眼科疾病的诊断大有裨益,本文通过有效利用跨模式数据进一步提高了诊断的准确性。本文提出了一种基于transformer的跨模态多对比网络,用于有效融合彩色眼底照片(CFP)和光学相干断层扫描(OCT)模式来诊断眼科疾病。我们设计了多对比学习策略,从跨模态数据中提取判别特征进行诊断。然后,通道融合头捕获不同模式之间的语义共享信息和同一类别患者之间的相似特征。同时,我们采用类平衡训练策略来应对医疗数据集通常是类不平衡的情况。我们的方法在跨模态眼病诊断的公共基准数据集上进行了评估。实验结果表明,该方法优于其他方法。代码和模型可在https://github.com/ecustyy/tcmn上获得。
{"title":"Transformer-based cross-modal multi-contrast network for ophthalmic diseases diagnosis","authors":"Yang Yu,&nbsp;Hongqing Zhu","doi":"10.1016/j.bbe.2023.06.001","DOIUrl":"10.1016/j.bbe.2023.06.001","url":null,"abstract":"<div><p><span><span>Automatic diagnosis of various ophthalmic diseases from ocular medical images is vital to support clinical decisions. Most current methods employ a single </span>imaging modality<span>, especially 2D fundus images. Considering that the diagnosis of ophthalmic diseases can greatly benefit from multiple imaging modalities, this paper further improves the accuracy of diagnosis by effectively utilizing cross-modal data. In this paper, we propose Transformer-based cross-modal multi-contrast network for efficiently fusing color fundus photograph (CFP) and optical coherence tomography (OCT) modality to diagnose ophthalmic diseases. We design multi-contrast learning strategy to extract discriminate features from cross-modal data for diagnosis. Then channel fusion head captures the semantically shared information across different modalities and the similarity features between patients of the same category. Meanwhile, we use a class-balanced training strategy to cope with the situation that medical datasets are usually class-imbalanced. Our method is evaluated on public benchmark datasets for cross-modal ophthalmic disease diagnosis. The experimental results demonstrate that our method outperforms other approaches. The codes and models are available at </span></span><span>https://github.com/ecustyy/tcmn</span><svg><path></path></svg>.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":"43 3","pages":"Pages 507-527"},"PeriodicalIF":6.4,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43259056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Biocybernetics and Biomedical Engineering
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1