Computers in biology and medicine最新文献_第5页

Handwritten character classification from EEG through continuous kinematic decoding 通过连续运动解码从脑电图进行手写字符分类

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-26 DOI: 10.1016/j.compbiomed.2024.109132

The classification of handwritten letters from invasive neural signals has lately been subject of research to restore communication abilities in people with limited movement capacities. This study explores the classification of ten letters (a,d,e,f,j,n,o,s,t,v) from non-invasive neural signals of 20 participants, offering new insights into the neural correlates of handwriting. Letters were classified with two methods: the direct classification from low-frequency and broadband electroencephalogram (EEG) and a two-step approach comprising the continuous decoding of hand kinematics and the application of those in subsequent classification. The two-step approach poses a novel application of continuous movement decoding for the classification of letters from EEG. When using low-frequency EEG, results show moderate accuracies of 23.1% for ten letters and 39.0% for a subset of five letters with highest discriminability of the trajectories. The two-step approach yielded significantly higher performances of 26.2% for ten letters and 46.7% for the subset of five letters. Hand kinematics could be reconstructed with a correlation of 0.10 to 0.57 (average chance level: 0.04) between the decoded and original kinematic. The study shows the general feasibility of extracting handwritten letters from non-invasively recorded neural signals and indicates that the proposed two-step approach can improve performances. As an exploratory investigation of the neural mechanisms of handwriting in EEG, we found significant influence of the written letter on the low-frequency components of neural signals. Differences between letters occurred mostly in central and occipital channels. Further, our results suggest movement speed as the most informative kinematic for the decoding of short hand movements.

从侵入性神经信号对手写字母进行分类是近来为恢复运动能力受限者的交流能力而开展的研究课题。本研究探讨了从 20 名参与者的非侵入性神经信号中对 10 个字母（a,d,e,f,j,n,o,s,t,v）进行分类，为手写的神经相关性提供了新的见解。字母分类有两种方法：一种是直接从低频和宽带脑电图（EEG）进行分类，另一种是分两步进行的方法，包括手部运动学的连续解码和在后续分类中的应用。两步法是连续运动解码在脑电图字母分类中的新应用。在使用低频脑电图时，结果显示十个字母的准确率为 23.1%，五个字母子集的准确率为 39.0%，轨迹的可辨别性最高。两步法的准确率明显更高，十个字母的准确率为 26.2%，五个字母子集的准确率为 46.7%。解码后的手部运动轨迹与原始运动轨迹之间的相关性为 0.10 至 0.57（平均概率水平：0.04）。这项研究表明，从非侵入式记录的神经信号中提取手写字母具有普遍可行性，并表明所建议的两步法可以提高性能。作为对脑电图中手写神经机制的探索性研究，我们发现书写字母对神经信号的低频成分有显著影响。不同字母之间的差异主要出现在中央和枕叶通道。此外，我们的研究结果表明，运动速度是手部短小动作解码中信息量最大的运动学因素。

{"title":"Handwritten character classification from EEG through continuous kinematic decoding","authors":"","doi":"10.1016/j.compbiomed.2024.109132","DOIUrl":"10.1016/j.compbiomed.2024.109132","url":null,"abstract":"<div><div>The classification of handwritten letters from invasive neural signals has lately been subject of research to restore communication abilities in people with limited movement capacities. This study explores the classification of ten letters (<em>a</em>,<em>d</em>,<em>e</em>,<em>f</em>,<em>j</em>,<em>n</em>,<em>o</em>,<em>s</em>,<em>t</em>,<em>v</em>) from non-invasive neural signals of 20 participants, offering new insights into the neural correlates of handwriting. Letters were classified with two methods: the direct classification from low-frequency and broadband electroencephalogram (EEG) and a two-step approach comprising the continuous decoding of hand kinematics and the application of those in subsequent classification. The two-step approach poses a novel application of continuous movement decoding for the classification of letters from EEG. When using low-frequency EEG, results show moderate accuracies of 23.1% for ten letters and 39.0% for a subset of five letters with highest discriminability of the trajectories. The two-step approach yielded significantly higher performances of 26.2% for ten letters and 46.7% for the subset of five letters. Hand kinematics could be reconstructed with a correlation of 0.10 to 0.57 (average chance level: 0.04) between the decoded and original kinematic. The study shows the general feasibility of extracting handwritten letters from non-invasively recorded neural signals and indicates that the proposed two-step approach can improve performances. As an exploratory investigation of the neural mechanisms of handwriting in EEG, we found significant influence of the written letter on the low-frequency components of neural signals. Differences between letters occurred mostly in central and occipital channels. Further, our results suggest movement speed as the most informative kinematic for the decoding of short hand movements.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322593","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

Deep learning enabled in vitro predicting biological tissue thickness using force measurement device 利用测力装置进行深度学习，体外预测生物组织厚度

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-25 DOI: 10.1016/j.compbiomed.2024.109181

Accurate perception of biological tissues (BT) thickness is essential for preliminary evaluation of medical diagnosis and animal nutrition. However, traditional thickness measuring approaches of BT require complex operation, high-cost, and trigger biological stress response. Herein this study, an novel in vitro BT thickness measuring approach integrated with force test system (FST) and the discrete multiwavelet transform convolutional neural network (DMWA-CNN) prediction model based on deep learning are proposed. Simultaneously, several comprehensive experiments and model comparisons are conducted to demonstrate the superiority of the proposed approach. By establishing a DMWA-CNN demonstrates higher estimation accuracy than other traditional algorithm, achieving 100 % accuracy for artificial BT. Moreover, the experimental results indicate that proposed approach is robust to elastic modulus variation (E), external load variation (F), and small thickness differences (T_s). In addition, four kinds of the pork’ thickness are experimentally measured, and the accuracy value is not less than 98.2 %. The thickness of BT determined using the FST and DMWA-CNN algorithm demonstrate potential application in the biomechanical parameter prediction.

准确感知生物组织（BT）的厚度对于医学诊断和动物营养的初步评估至关重要。然而，传统的生物组织厚度测量方法操作复杂、成本高，而且会引发生物应激反应。本研究提出了一种新型体外 BT 厚度测量方法，该方法集成了力测试系统（FST）和基于深度学习的离散多小波变换卷积神经网络（DMWA-CNN）预测模型。同时，还进行了多项综合实验和模型比较，以证明所提方法的优越性。与其他传统算法相比，DMWA-CNN 的估算精度更高，人工 BT 的估算精度达到了 100%。此外，实验结果表明，所提出的方法对弹性模量变化（E）、外部载荷变化（F）和小厚度差异（Ts）具有鲁棒性。此外，实验还测量了四种猪肉厚度，其精确度值不低于 98.2%。利用 FST 和 DMWA-CNN 算法测定的 BT 厚度在生物力学参数预测中具有潜在的应用价值。

{"title":"Deep learning enabled in vitro predicting biological tissue thickness using force measurement device","authors":"","doi":"10.1016/j.compbiomed.2024.109181","DOIUrl":"10.1016/j.compbiomed.2024.109181","url":null,"abstract":"<div><div>Accurate perception of biological tissues (BT) thickness is essential for preliminary evaluation of medical diagnosis and animal nutrition. However, traditional thickness measuring approaches of BT require complex operation, high-cost, and trigger biological stress response. Herein this study, an novel in vitro BT thickness measuring approach integrated with force test system (FST) and the discrete multiwavelet transform convolutional neural network (DMWA-CNN) prediction model based on deep learning are proposed. Simultaneously, several comprehensive experiments and model comparisons are conducted to demonstrate the superiority of the proposed approach. By establishing a DMWA-CNN demonstrates higher estimation accuracy than other traditional algorithm, achieving 100 % accuracy for artificial BT. Moreover, the experimental results indicate that proposed approach is robust to elastic modulus variation (<em>E</em>), external load variation (<em>F</em>), and small thickness differences (<em>T</em><sub><em>s</em></sub>). In addition, four kinds of the pork’ thickness are experimentally measured, and the accuracy value is not less than 98.2 %. The thickness of BT determined using the FST and DMWA-CNN algorithm demonstrate potential application in the biomechanical parameter prediction.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319682","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

Personalized food consumption detection with deep learning and Inertial Measurement Unit sensor 利用深度学习和惯性测量单元传感器进行个性化食物消费检测

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-25 DOI: 10.1016/j.compbiomed.2024.109167

For individuals diagnosed with diabetes mellitus, it is crucial to keep a record of the carbohydrates consumed during meals, as this should be done at least three times daily, amounting to an average of six meals. Unfortunately, many individuals tend to overlook this essential task. For those who use an artificial pancreas, carbohydrate intake proves to be a critical factor, as it can activate the insulin pump in the artificial pancreas to deliver insulin to the body. To address this need, we have developed personalized deep learning model that can accurately detect carbohydrate intake with a high degree of accuracy. Our study employed a publicly available dataset gathered by an Inertial Measurement Unit (IMU), which included accelerometer and gyroscope data. The data was sampled at a rate of 15 Hz, necessitating preprocessing. For our tailored to the patient model, we utilized a recurrent network comprising Long short-term memory (LSTM) layers. Our findings revealed a median F1 score of 0.99, indicating a high level of accuracy. Additionally, the confusion matrix displayed a difference of only 6 s, further validating the model’s accuracy. Therefore, we can confidently assert that our model architecture exhibits a high degree of accuracy. Our model performed well above 90% on the dataset, with most results between 98%–99%. The recurrent networks improved the problem-solving capabilities significantly, though some outliers remained. The model’s average prediction latency was 5.5 s, suggesting that later meal predictions result in extended meal progress predictions. The dataset’s limitation of mostly single-day data points raises questions about multi-day performance, which could be explored by collecting multi-day data, including night periods. Future enhancements might involve transformer networks and shorter time windows to improve model responsiveness and accuracy. Therefore, we can confidently assert that our model exhibits a high degree of accuracy.

对于确诊为糖尿病的患者来说，记录进餐时摄入的碳水化合物是至关重要的，因为每天至少要记录三次，平均六餐。遗憾的是，许多人往往忽视了这一重要任务。对于使用人工胰腺的人来说，碳水化合物的摄入量被证明是一个关键因素，因为它可以激活人工胰腺中的胰岛素泵向人体输送胰岛素。为了满足这一需求，我们开发了个性化的深度学习模型，该模型可以高精度地检测碳水化合物的摄入量。我们的研究采用了由惯性测量单元（IMU）收集的公开数据集，其中包括加速度计和陀螺仪数据。数据采样率为 15 Hz，因此需要进行预处理。在为患者量身定制的模型中，我们使用了由长短期记忆（LSTM）层组成的递归网络。我们的研究结果表明，中位 F1 得分为 0.99，表明准确度很高。此外，混淆矩阵显示的差异仅为 6 秒，进一步验证了模型的准确性。因此，我们可以自信地断言，我们的模型架构具有很高的准确性。我们的模型在数据集上的表现远高于 90%，大多数结果在 98%-99% 之间。尽管仍然存在一些异常值，但递归网络显著提高了解决问题的能力。模型的平均预测延迟时间为 5.5 秒，这表明较晚的用餐预测会导致用餐进度预测时间延长。数据集的局限性在于大部分数据点都是单日数据，这就对多日数据的性能提出了疑问，可以通过收集多日数据（包括夜间数据）来探索多日数据的性能。未来的改进可能涉及变压器网络和更短的时间窗口，以提高模型的响应速度和准确性。因此，我们可以肯定地说，我们的模型具有很高的准确性。

{"title":"Personalized food consumption detection with deep learning and Inertial Measurement Unit sensor","authors":"","doi":"10.1016/j.compbiomed.2024.109167","DOIUrl":"10.1016/j.compbiomed.2024.109167","url":null,"abstract":"<div><div>For individuals diagnosed with diabetes mellitus, it is crucial to keep a record of the carbohydrates consumed during meals, as this should be done at least three times daily, amounting to an average of six meals. Unfortunately, many individuals tend to overlook this essential task. For those who use an artificial pancreas, carbohydrate intake proves to be a critical factor, as it can activate the insulin pump in the artificial pancreas to deliver insulin to the body. To address this need, we have developed personalized deep learning model that can accurately detect carbohydrate intake with a high degree of accuracy. Our study employed a publicly available dataset gathered by an Inertial Measurement Unit (IMU), which included accelerometer and gyroscope data. The data was sampled at a rate of 15 Hz, necessitating preprocessing. For our tailored to the patient model, we utilized a recurrent network comprising Long short-term memory (LSTM) layers. Our findings revealed a median F1 score of 0.99, indicating a high level of accuracy. Additionally, the confusion matrix displayed a difference of only 6 s, further validating the model’s accuracy. Therefore, we can confidently assert that our model architecture exhibits a high degree of accuracy. Our model performed well above 90% on the dataset, with most results between 98%–99%. The recurrent networks improved the problem-solving capabilities significantly, though some outliers remained. The model’s average prediction latency was 5.5 s, suggesting that later meal predictions result in extended meal progress predictions. The dataset’s limitation of mostly single-day data points raises questions about multi-day performance, which could be explored by collecting multi-day data, including night periods. Future enhancements might involve transformer networks and shorter time windows to improve model responsiveness and accuracy. Therefore, we can confidently assert that our model exhibits a high degree of accuracy.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319681","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 multi-task learning model for clinically interpretable sesamoiditis grading 用于临床可解释的芝麻骨膜炎分级的多任务学习模型

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-25 DOI: 10.1016/j.compbiomed.2024.109179

Sesamoiditis is a common equine disease with varying severity, leading to increased injury risks and performance degradation in horses. Accurate grading of sesamoiditis is crucial for effective treatment. Although deep learning-based approaches for grading sesamoiditis show promise, they remain underexplored and often lack clinical interpretability. To address this issue, we propose a novel, clinically interpretable multi-task learning model that integrates clinical knowledge with machine learning. The proposed model employs a dual-branch decoder to simultaneously perform sesamoiditis grading and vascular channel segmentation. Feature fusion is utilized to transfer knowledge between these tasks, enabling the identification of subtle radiographic variations. Additionally, our model generates a diagnostic report that, along with the vascular channel mask, serves as an explanation of the model’s grading decisions, thereby increasing the transparency of the decision-making process. We validate our model on two datasets, demonstrating its superior performance compared to state-of-the-art models in terms of accuracy and generalization. This study provides a foundational framework for the interpretable grading of similar diseases.

趾骨关节炎是一种常见的马病，严重程度不一，会导致马匹受伤的风险增加和性能下降。芝麻骨膜炎的准确分级对于有效治疗至关重要。虽然基于深度学习的芝麻骨炎分级方法前景广阔，但仍未得到充分探索，而且往往缺乏临床可解释性。为了解决这个问题，我们提出了一种新颖的、临床上可解释的多任务学习模型，该模型将临床知识与机器学习相结合。该模型采用双分支解码器，可同时进行芝麻炎分级和血管通道分割。利用特征融合在这些任务之间传递知识，从而能够识别细微的放射学变化。此外，我们的模型还能生成诊断报告，该报告与血管通道掩膜一起解释了模型的分级决定，从而提高了决策过程的透明度。我们在两个数据集上验证了我们的模型，证明其在准确性和概括性方面都优于最先进的模型。这项研究为类似疾病的可解释分级提供了一个基础框架。

{"title":"A multi-task learning model for clinically interpretable sesamoiditis grading","authors":"","doi":"10.1016/j.compbiomed.2024.109179","DOIUrl":"10.1016/j.compbiomed.2024.109179","url":null,"abstract":"<div><div>Sesamoiditis is a common equine disease with varying severity, leading to increased injury risks and performance degradation in horses. Accurate grading of sesamoiditis is crucial for effective treatment. Although deep learning-based approaches for grading sesamoiditis show promise, they remain underexplored and often lack clinical interpretability. To address this issue, we propose a novel, clinically interpretable multi-task learning model that integrates clinical knowledge with machine learning. The proposed model employs a dual-branch decoder to simultaneously perform sesamoiditis grading and vascular channel segmentation. Feature fusion is utilized to transfer knowledge between these tasks, enabling the identification of subtle radiographic variations. Additionally, our model generates a diagnostic report that, along with the vascular channel mask, serves as an explanation of the model’s grading decisions, thereby increasing the transparency of the decision-making process. We validate our model on two datasets, demonstrating its superior performance compared to state-of-the-art models in terms of accuracy and generalization. This study provides a foundational framework for the interpretable grading of similar diseases.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319680","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

ASCHOPLEX: A generalizable approach for the automatic segmentation of choroid plexus ASCHOPLEX：脉络丛自动分割的通用方法

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-25 DOI: 10.1016/j.compbiomed.2024.109164

Background:

The Choroid Plexus (ChP) plays a vital role in brain homeostasis, serving as part of the Blood-Cerebrospinal Fluid Barrier, contributing to brain clearance pathways and being the main source of cerebrospinal fluid. Since the involvement of ChP in neurological and psychiatric disorders is not entirely established and currently under investigation, accurate and reproducible segmentation of this brain structure on large cohorts remains challenging. This paper presents ASCHOPLEX, a deep-learning tool for the automated segmentation of human ChP from structural MRI data that integrates existing software architectures like 3D UNet, UNETR, and DynUNet to deliver accurate ChP volume estimates.

Methods:

Here we trained ASCHOPLEX on 128 T1-w MRI images comprising both controls and patients with Multiple Sclerosis. ASCHOPLEX’s performances were evaluated using traditional segmentation metrics; manual segmentation by experts served as ground truth. To overcome the generalizability problem that affects data-driven approaches, an additional fine-tuning procedure (ASCHOPLEX_tune) was implemented on 77 T1-w PET/MRI images of both controls and depressed patients.

Results:

ASCHOPLEX showed superior performance compared to commonly used methods like FreeSurfer and Gaussian Mixture Model both in terms of Dice Coefficient (ASCHOPLEX 0.80, ASCHOPLEX_tune 0.78) and estimated ChP volume error (ASCHOPLEX 9.22%, ASCHOPLEX_tune 9.23%).

Conclusion:

These results highlight the high accuracy, reliability, and reproducibility of ASCHOPLEX ChP segmentations.

背景：脉络丛（Choroid Plexus，ChP）是血-脑脊液屏障（Blood-Cerebrospinal Fluid Barrier）的一部分，是脑清除途径的一部分，也是脑脊液的主要来源，在脑平衡中起着至关重要的作用。由于 ChP 与神经和精神疾病的关系尚未完全确定，目前仍在研究中，因此在大样本中对这一大脑结构进行准确和可重复的分割仍具有挑战性。本文介绍的 ASCHOPLEX 是一种深度学习工具，用于从结构性 MRI 数据中自动分割人类 ChP，它集成了现有的软件架构，如 3D UNet、UNETR 和 DynUNet，以提供准确的 ChP 体积估计。ASCHOPLEX 的性能使用传统的分割指标进行评估；专家的手动分割作为基本事实。为了克服影响数据驱动方法的通用性问题，对 77 张对照组和抑郁症患者的 T1-w PET/MRI 图像实施了额外的微调程序（ASCHOPLEXtune）。结果：与FreeSurfer和高斯混合模型等常用方法相比，ASCHOPLEX在Dice系数（ASCHOPLEX为0.80，ASCHOPLEXtune为0.78）和估计ChP体积误差（ASCHOPLEX为9.22%，ASCHOPLEXtune为9.23%）方面都表现出更优越的性能。

{"title":"ASCHOPLEX: A generalizable approach for the automatic segmentation of choroid plexus","authors":"","doi":"10.1016/j.compbiomed.2024.109164","DOIUrl":"10.1016/j.compbiomed.2024.109164","url":null,"abstract":"<div><h3>Background:</h3><div>The Choroid Plexus (ChP) plays a vital role in brain homeostasis, serving as part of the Blood-Cerebrospinal Fluid Barrier, contributing to brain clearance pathways and being the main source of cerebrospinal fluid. Since the involvement of ChP in neurological and psychiatric disorders is not entirely established and currently under investigation, accurate and reproducible segmentation of this brain structure on large cohorts remains challenging. This paper presents ASCHOPLEX, a deep-learning tool for the automated segmentation of human ChP from structural MRI data that integrates existing software architectures like 3D UNet, UNETR, and DynUNet to deliver accurate ChP volume estimates.</div></div><div><h3>Methods:</h3><div>Here we trained ASCHOPLEX on 128 T1-w MRI images comprising both controls and patients with Multiple Sclerosis. ASCHOPLEX’s performances were evaluated using traditional segmentation metrics; manual segmentation by experts served as ground truth. To overcome the generalizability problem that affects data-driven approaches, an additional fine-tuning procedure (ASCHOPLEX<sub>tune</sub>) was implemented on 77 T1-w PET/MRI images of both controls and depressed patients.</div></div><div><h3>Results:</h3><div>ASCHOPLEX showed superior performance compared to commonly used methods like FreeSurfer and Gaussian Mixture Model both in terms of Dice Coefficient (ASCHOPLEX 0.80, ASCHOPLEX<sub>tune</sub> 0.78) and estimated ChP volume error (ASCHOPLEX 9.22%, ASCHOPLEX<sub>tune</sub> 9.23%).</div></div><div><h3>Conclusion:</h3><div>These results highlight the high accuracy, reliability, and reproducibility of ASCHOPLEX ChP segmentations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319679","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

DetSegDiff: A joint periodontal landmark detection and segmentation in intraoral ultrasound using edge-enhanced diffusion-based network DetSegDiff：利用边缘增强扩散网络在口内超声中联合检测和分割牙周地标

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-24 DOI: 10.1016/j.compbiomed.2024.109174

Individuals with malocclusion require an orthodontic diagnosis and treatment plan based on the severity of their condition. Assessing and monitoring changes in periodontal structures before, during, and after orthodontic procedures is crucial, and intraoral ultrasound (US) imaging has been shown a promising diagnostic tool in imaging periodontium. However, accurately delineating and analyzing periodontal structures in US videos is a challenging task for clinicians, as it is time-consuming and subject to interpretation errors. This paper introduces DetSegDiff, an edge-enhanced diffusion-based network developed to simultaneously detect the cementoenamel junction (CEJ) and segment alveolar bone structure in intraoral US videos. An edge feature encoder is designed to enhance edge and texture information for precise delineation of periodontal structures. Additionally, we employed the spatial squeeze-attention module (SSAM) to extract more representative features to perform both detection and segmentation tasks at global and local levels. This study used 169 videos from 17 orthodontic patients for training purposes and was subsequently tested on 41 videos from 4 additional patients. The proposed method achieved a mean distance difference of 0.17 ± 0.19 mm for the CEJ and an average Dice score of 90.1% for alveolar bone structure. As there is a lack of multi-task benchmark networks, thorough experiments were undertaken to assess and benchmark the proposed method against state-of-the-art (SOTA) detection and segmentation individual networks. The experimental results demonstrated that DetSegDiff outperformed SOTA approaches, confirming the feasibility of using automated diagnostic systems for orthodontists.

错颌畸形患者需要根据病情的严重程度进行正畸诊断并制定治疗计划。在正畸治疗之前、期间和之后，评估和监测牙周结构的变化至关重要，而口内超声波（US）成像已被证明是牙周成像中一种很有前途的诊断工具。然而，对于临床医生来说，在 US 视频中准确划分和分析牙周结构是一项极具挑战性的任务，因为它既耗时又容易出现解读错误。本文介绍的 DetSegDiff 是一种基于边缘增强扩散的网络，可同时检测口内 US 视频中的牙釉质连接点（CEJ）和牙槽骨结构。边缘特征编码器旨在增强边缘和纹理信息，以精确划分牙周结构。此外，我们还采用了空间挤压注意模块（SSAM）来提取更具代表性的特征，以便在全局和局部层面执行检测和分割任务。这项研究使用了 17 名正畸患者的 169 个视频作为训练，随后又对另外 4 名患者的 41 个视频进行了测试。所提出的方法在 CEJ 方面的平均距离差为 0.17 ± 0.19 mm，在牙槽骨结构方面的平均 Dice 分数为 90.1%。由于缺乏多任务基准网络，我们进行了全面的实验，以评估所提出的方法，并将其与最先进的（SOTA）检测和分割单个网络进行比较。实验结果表明，DetSegDiff 的表现优于 SOTA 方法，证实了为正畸医师使用自动诊断系统的可行性。

{"title":"DetSegDiff: A joint periodontal landmark detection and segmentation in intraoral ultrasound using edge-enhanced diffusion-based network","authors":"","doi":"10.1016/j.compbiomed.2024.109174","DOIUrl":"10.1016/j.compbiomed.2024.109174","url":null,"abstract":"<div><div>Individuals with malocclusion require an orthodontic diagnosis and treatment plan based on the severity of their condition. Assessing and monitoring changes in periodontal structures before, during, and after orthodontic procedures is crucial, and intraoral ultrasound (US) imaging has been shown a promising diagnostic tool in imaging periodontium. However, accurately delineating and analyzing periodontal structures in US videos is a challenging task for clinicians, as it is time-consuming and subject to interpretation errors. This paper introduces DetSegDiff, an edge-enhanced diffusion-based network developed to simultaneously detect the cementoenamel junction (CEJ) and segment alveolar bone structure in intraoral US videos. An edge feature encoder is designed to enhance edge and texture information for precise delineation of periodontal structures. Additionally, we employed the spatial squeeze-attention module (SSAM) to extract more representative features to perform both detection and segmentation tasks at global and local levels. This study used 169 videos from 17 orthodontic patients for training purposes and was subsequently tested on 41 videos from 4 additional patients. The proposed method achieved a mean distance difference of 0.17 ± 0.19 mm for the CEJ and an average Dice score of 90.1% for alveolar bone structure. As there is a lack of multi-task benchmark networks, thorough experiments were undertaken to assess and benchmark the proposed method against state-of-the-art (SOTA) detection and segmentation individual networks. The experimental results demonstrated that DetSegDiff outperformed SOTA approaches, confirming the feasibility of using automated diagnostic systems for orthodontists.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315351","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

MV-GNN: Generation of continuous geometric representations of mitral valve motion from 3D+t echocardiography MV-GNN：从三维+t 超声心动图生成二尖瓣运动的连续几何表征

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-24 DOI: 10.1016/j.compbiomed.2024.109154

We present a geometric deep-learning method for reconstructing a temporally continuous mitral valve surface mesh from 3D transesophageal echocardiography sequences. Our approach features a supervised end-to-end deep learning architecture that combines a convolutional neural network-based voxel encoder and decoder with a graph neural network-based multi-resolution mesh decoder, all trained on sparse landmark annotations. Key elements of our methodology include a tube-shaped prototype mesh with labeled vertices, a specialized loss function to preserve the known inlet and outlet, and a rigid alignment system for anatomical landmarks. A custom term in the loss function prevents self-intersecting geometries within the valve mesh, promoting point correspondence and facilitating a continuous representation of valve anatomy over time. An ablation study evaluates the impact of different loss term configurations on model performance, highlighting the effectiveness of each individual loss term. Our Mitral Valve Graph Neural Network (MV-GNN) outperforms existing deep-learning methods on most distance metrics for the annulus and leaflets. The continuous valve motion representations generated by our approach (3D+t) exhibit distance measures comparable to our 3D solution, demonstrating its potential for analyzing mitral valve dynamics and enhancing personalized simulations for hemodynamic assessment and therapy planning.

我们提出了一种几何深度学习方法，用于从三维经食道超声心动图序列中重建时间上连续的二尖瓣表面网格。我们的方法采用有监督的端到端深度学习架构，将基于卷积神经网络的体素编码器和解码器与基于图神经网络的多分辨率网格解码器结合在一起，所有这些都是在稀疏的地标注释上进行训练的。我们方法的关键要素包括一个带有标记顶点的管状原型网格、一个用于保留已知入口和出口的专门损失函数，以及一个用于解剖地标的刚性对齐系统。损耗函数中的一个自定义项可以防止瓣膜网格内的自交几何形状，促进点对应，并有利于随着时间的推移连续表示瓣膜解剖结构。一项消融研究评估了不同损失项配置对模型性能的影响，突出了每个损失项的有效性。我们的二尖瓣图神经网络（MV-GNN）在瓣环和瓣叶的大多数距离指标上都优于现有的深度学习方法。我们的方法（3D+t）生成的连续瓣膜运动表示的距离度量与我们的 3D 解决方案相当，这证明了它在分析二尖瓣动态以及增强血液动力学评估和治疗规划的个性化模拟方面的潜力。

{"title":"MV-GNN: Generation of continuous geometric representations of mitral valve motion from 3D+t echocardiography","authors":"","doi":"10.1016/j.compbiomed.2024.109154","DOIUrl":"10.1016/j.compbiomed.2024.109154","url":null,"abstract":"<div><div>We present a geometric deep-learning method for reconstructing a temporally continuous mitral valve surface mesh from 3D transesophageal echocardiography sequences. Our approach features a supervised end-to-end deep learning architecture that combines a convolutional neural network-based voxel encoder and decoder with a graph neural network-based multi-resolution mesh decoder, all trained on sparse landmark annotations. Key elements of our methodology include a tube-shaped prototype mesh with labeled vertices, a specialized loss function to preserve the known inlet and outlet, and a rigid alignment system for anatomical landmarks. A custom term in the loss function prevents self-intersecting geometries within the valve mesh, promoting point correspondence and facilitating a continuous representation of valve anatomy over time. An ablation study evaluates the impact of different loss term configurations on model performance, highlighting the effectiveness of each individual loss term. Our Mitral Valve Graph Neural Network (MV-GNN) outperforms existing deep-learning methods on most distance metrics for the annulus and leaflets. The continuous valve motion representations generated by our approach (3D+t) exhibit distance measures comparable to our 3D solution, demonstrating its potential for analyzing mitral valve dynamics and enhancing personalized simulations for hemodynamic assessment and therapy planning.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012393/pdfft?md5=4bc6eedd0ac8002d3434fafeaf193c7d&pid=1-s2.0-S0010482524012393-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315353","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

Simulation-informed learning for time-resolved angiographic contrast agent concentration reconstruction 针对时间分辨血管造影剂浓度重建的模拟知情学习

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-24 DOI: 10.1016/j.compbiomed.2024.109178

Three-dimensional Digital Subtraction Angiography (3D-DSA) is a well-established X-ray-based technique for visualizing vascular anatomy. Recently, four-dimensional DSA (4D-DSA) reconstruction algorithms have been developed to enable the visualization of volumetric contrast flow dynamics through time-series of volumes. This reconstruction problem is ill-posed mainly due to vessel overlap in the projection direction and geometric vessel foreshortening, which leads to information loss in the recorded projection images. However, knowledge about the underlying fluid dynamics can be leveraged to constrain the solution space. In our work, we implicitly include this information in a neural network-based model that is trained on a dataset of image-based blood flow simulations. The model predicts the spatially averaged contrast agent concentration for each centerline point of the vasculature over time, lowering the overall computational demand. The trained network enables the reconstruction of relative contrast agent concentrations with a mean absolute error of 0.02±0.02 and a mean absolute percentage error of 5.31±9.25 %. Moreover, the network is robust to varying degrees of vessel overlap and vessel foreshortening. Our approach demonstrates the potential of the integration of machine learning and blood flow simulations in time-resolved angiographic contrast agent concentration reconstruction.

三维数字减影血管造影术（3D-DSA）是一种成熟的基于 X 射线的血管解剖可视化技术。最近，人们开发了四维数字减影血管造影（4D-DSA）重建算法，以便通过时间序列的体积来观察体积造影剂的流动动态。由于投影方向上的血管重叠和几何上的血管前缩，导致记录的投影图像中信息丢失，因此这一重建问题存在困难。不过，可以利用有关基本流体动力学的知识来限制求解空间。在我们的工作中，我们在基于图像的血流模拟数据集上训练的神经网络模型中隐含了这一信息。该模型可预测血管每个中心线点随时间变化的空间平均造影剂浓度，从而降低整体计算需求。训练有素的网络能重建相对造影剂浓度，平均绝对误差为 0.02±0.02，平均绝对百分比误差为 5.31±9.25%。此外，该网络对不同程度的血管重叠和血管前缩具有鲁棒性。我们的方法证明了机器学习和血流模拟在时间分辨血管造影剂浓度重建中的整合潜力。

{"title":"Simulation-informed learning for time-resolved angiographic contrast agent concentration reconstruction","authors":"","doi":"10.1016/j.compbiomed.2024.109178","DOIUrl":"10.1016/j.compbiomed.2024.109178","url":null,"abstract":"<div><div>Three-dimensional Digital Subtraction Angiography (3D-DSA) is a well-established X-ray-based technique for visualizing vascular anatomy. Recently, four-dimensional DSA (4D-DSA) reconstruction algorithms have been developed to enable the visualization of volumetric contrast flow dynamics through time-series of volumes. This reconstruction problem is ill-posed mainly due to vessel overlap in the projection direction and geometric vessel foreshortening, which leads to information loss in the recorded projection images. However, knowledge about the underlying fluid dynamics can be leveraged to constrain the solution space. In our work, we implicitly include this information in a neural network-based model that is trained on a dataset of image-based blood flow simulations. The model predicts the spatially averaged contrast agent concentration for each centerline point of the vasculature over time, lowering the overall computational demand. The trained network enables the reconstruction of relative contrast agent concentrations with a mean absolute error of 0.02±0.02 and a mean absolute percentage error of 5.31±9.25 %. Moreover, the network is robust to varying degrees of vessel overlap and vessel foreshortening. Our approach demonstrates the potential of the integration of machine learning and blood flow simulations in time-resolved angiographic contrast agent concentration reconstruction.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012630/pdfft?md5=d402d6a132f3f9ced1d8f862d270edb5&pid=1-s2.0-S0010482524012630-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315348","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

Boosting medical diagnostics with a novel gradient-based sample selection method 利用基于梯度的新型样本选择方法提高医疗诊断水平

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-24 DOI: 10.1016/j.compbiomed.2024.109165

In the rapidly expanding landscape of medical data, the need for innovative approaches to maximize classification performance has become increasingly critical. As data volumes grow, ensuring that diagnostic systems work with accurate and relevant data is paramount for effective and generalizable classification. This study introduces a novel gradient-based sample selection method, the first of its kind in the literature, specifically designed to enhance classification accuracy by removing redundant and non-informative data. Unlike traditional methods that focus solely on feature selection, this approach integrates an advanced sample selection technique to optimize the input data, leading to more accurate and efficient diagnostics. The method is validated on multiple disease datasets, including the Wisconsin Diagnostic Breast Cancer (WDBC) dataset and the Cleveland Coronary Artery Disease (CAD) dataset, demonstrating its broad applicability and effectiveness. To address dataset imbalance, the Adaptive Synthetic Sampling (ADASYN) method is employed, followed by Particle Swarm Optimization (PSO) for feature selection. The refined datasets are then classified using a Support Vector Machine (SVM), showing that even traditional classifiers can achieve substantial improvements when enhanced with advanced sample selection. The results underscore the critical importance of precise sample selection in boosting classification performance, setting a new standard for computer-aided diagnostics and paving the way for future innovations in handling large and complex medical datasets.

在医疗数据迅速增长的形势下，采用创新方法最大限度地提高分类性能的需求变得越来越迫切。随着数据量的增长，确保诊断系统使用准确、相关的数据对于有效、可推广的分类至关重要。本研究介绍了一种新颖的基于梯度的样本选择方法，这在文献中尚属首次，专门用于通过去除冗余和非信息数据来提高分类准确性。与只关注特征选择的传统方法不同，这种方法整合了先进的样本选择技术，以优化输入数据，从而提高诊断的准确性和效率。该方法在多个疾病数据集上进行了验证，包括威斯康星诊断乳腺癌（WDBC）数据集和克利夫兰冠状动脉疾病（CAD）数据集，证明了其广泛的适用性和有效性。为解决数据集的不平衡问题，采用了自适应合成采样（ADASYN）方法，然后用粒子群优化（PSO）方法进行特征选择。然后使用支持向量机（SVM）对改进后的数据集进行分类，结果表明，即使是传统的分类器，在使用先进的样本选择技术后也能实现大幅改进。这些结果强调了精确样本选择在提高分类性能方面的极端重要性，为计算机辅助诊断设定了新标准，并为未来处理大型复杂医疗数据集的创新铺平了道路。

{"title":"Boosting medical diagnostics with a novel gradient-based sample selection method","authors":"","doi":"10.1016/j.compbiomed.2024.109165","DOIUrl":"10.1016/j.compbiomed.2024.109165","url":null,"abstract":"<div><div>In the rapidly expanding landscape of medical data, the need for innovative approaches to maximize classification performance has become increasingly critical. As data volumes grow, ensuring that diagnostic systems work with accurate and relevant data is paramount for effective and generalizable classification. This study introduces a novel gradient-based sample selection method, the first of its kind in the literature, specifically designed to enhance classification accuracy by removing redundant and non-informative data. Unlike traditional methods that focus solely on feature selection, this approach integrates an advanced sample selection technique to optimize the input data, leading to more accurate and efficient diagnostics. The method is validated on multiple disease datasets, including the Wisconsin Diagnostic Breast Cancer (WDBC) dataset and the Cleveland Coronary Artery Disease (CAD) dataset, demonstrating its broad applicability and effectiveness. To address dataset imbalance, the Adaptive Synthetic Sampling (ADASYN) method is employed, followed by Particle Swarm Optimization (PSO) for feature selection. The refined datasets are then classified using a Support Vector Machine (SVM), showing that even traditional classifiers can achieve substantial improvements when enhanced with advanced sample selection. The results underscore the critical importance of precise sample selection in boosting classification performance, setting a new standard for computer-aided diagnostics and paving the way for future innovations in handling large and complex medical datasets.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315350","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 bladder cancer diagnosis using an improved RIME algorithm with Orthogonal Learning 利用带正交学习的改进型 RIME 算法高效诊断膀胱癌

IF 7 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2024-09-24 DOI: 10.1016/j.compbiomed.2024.109175

Bladder cancer (BC) diagnosis presents a critical challenge in biomedical research, necessitating accurate tumor classification from diverse datasets for effective treatment planning. This paper introduces a novel wrapper feature selection (FS) method that leverages a hybrid optimization algorithm combining Orthogonal Learning (OL) with a rime optimization algorithm (RIME), termed mRIME. The mRIME algorithm is designed to avoid local optima, streamline the search process, and select the most relevant features without compromising classifier performance. It also introduces mRIME-SVM, a novel hybrid model integrating modified mRIME for FS with Support Vector Machine (SVM) for classification. The mRIME algorithm is employed as an FS method and is also utilized to fine-tune the hyperparameters of it the It SVM, enhancing the overall classification accuracy. Specifically, mRIME navigates complex search spaces to optimize FS without compromising classifier performance. Evaluated on eight diverse BC datasets, mRIME-SVM outperforms popular metaheuristic algorithms, ensuring precise and reliable diagnostic outcomes. Moreover, the proposed mRIME was employed for tackling global optimization problems. It has been thoroughly assessed using the IEEE Congress on Evolutionary Computation 2022 (CEC’2022) test suite. Comparative analyzes with Gray wolf optimization (GWO), Whale optimization algorithm (WOA), Harris hawks optimization (HHO), Golden Jackal Optimization (GJO), Hunger Game optimization algorithm (HGS), Sinh Cosh Optimizer (SCHO), and the original RIME highlight mRIME’s competitiveness and efficacy across diverse optimization tasks. Leveraging mRIME’s success, mRIME-SVM achieves high classification accuracy on nine BC datasets, surpassing existing models. Results underscore mRIME’s competitiveness and applicability across diverse optimization tasks, extending its utility to enhance BC classification. This study contributes to advancing BC diagnostics with a robust computational framework, promising broader applications in bioinformatics and AI-driven medical research.

膀胱癌（BC）诊断是生物医学研究中的一项重要挑战，需要从不同的数据集中进行准确的肿瘤分类，以制定有效的治疗计划。本文介绍了一种新颖的包装特征选择（FS）方法，该方法利用了正交学习（OL）与 RIME 优化算法（RIME）相结合的混合优化算法，称为 mRIME。mRIME 算法旨在避免局部最优，简化搜索过程，并在不影响分类器性能的情况下选择最相关的特征。它还引入了 mRIME-SVM，这是一种新型混合模型，集成了用于 FS 的修正 mRIME 和用于分类的支持向量机（SVM）。mRIME 算法被用作一种 FS 方法，同时也用于微调 SVM 的超参数，从而提高整体分类准确率。具体来说，mRIME 可在复杂的搜索空间中导航，在不影响分类器性能的情况下优化 FS。通过对八个不同的 BC 数据集进行评估，mRIME-SVM 的表现优于流行的元启发式算法，确保了诊断结果的精确性和可靠性。此外，提出的 mRIME 还被用于解决全局优化问题。它通过 IEEE 2022 年进化计算大会（CEC'2022）测试套件进行了全面评估。与灰狼优化算法（GWO）、鲸鱼优化算法（WOA）、哈里斯鹰优化算法（HHO）、金豺优化算法（GJO）、饥饿游戏优化算法（HGS）、Sinh Cosh 优化算法（SCHO）和原始 RIME 的对比分析凸显了 mRIME 在不同优化任务中的竞争力和有效性。利用 mRIME 的成功经验，mRIME-SVM 在九个 BC 数据集上实现了很高的分类准确率，超越了现有模型。研究结果凸显了 mRIME 在不同优化任务中的竞争力和适用性，从而扩大了其在增强 BC 分类方面的实用性。这项研究通过一个稳健的计算框架推动了脑卒中诊断的发展，有望在生物信息学和人工智能驱动的医学研究中得到更广泛的应用。

{"title":"Efficient bladder cancer diagnosis using an improved RIME algorithm with Orthogonal Learning","authors":"","doi":"10.1016/j.compbiomed.2024.109175","DOIUrl":"10.1016/j.compbiomed.2024.109175","url":null,"abstract":"<div><div>Bladder cancer (BC) diagnosis presents a critical challenge in biomedical research, necessitating accurate tumor classification from diverse datasets for effective treatment planning. This paper introduces a novel wrapper feature selection (FS) method that leverages a hybrid optimization algorithm combining Orthogonal Learning (OL) with a rime optimization algorithm (RIME), termed mRIME. The mRIME algorithm is designed to avoid local optima, streamline the search process, and select the most relevant features without compromising classifier performance. It also introduces mRIME-SVM, a novel hybrid model integrating modified mRIME for FS with Support Vector Machine (SVM) for classification. The mRIME algorithm is employed as an FS method and is also utilized to fine-tune the hyperparameters of it the It SVM, enhancing the overall classification accuracy. Specifically, mRIME navigates complex search spaces to optimize FS without compromising classifier performance. Evaluated on eight diverse BC datasets, mRIME-SVM outperforms popular metaheuristic algorithms, ensuring precise and reliable diagnostic outcomes. Moreover, the proposed mRIME was employed for tackling global optimization problems. It has been thoroughly assessed using the IEEE Congress on Evolutionary Computation 2022 (CEC’2022) test suite. Comparative analyzes with Gray wolf optimization (GWO), Whale optimization algorithm (WOA), Harris hawks optimization (HHO), Golden Jackal Optimization (GJO), Hunger Game optimization algorithm (HGS), Sinh Cosh Optimizer (SCHO), and the original RIME highlight mRIME’s competitiveness and efficacy across diverse optimization tasks. Leveraging mRIME’s success, mRIME-SVM achieves high classification accuracy on nine BC datasets, surpassing existing models. Results underscore mRIME’s competitiveness and applicability across diverse optimization tasks, extending its utility to enhance BC classification. This study contributes to advancing BC diagnostics with a robust computational framework, promising broader applications in bioinformatics and AI-driven medical research.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142315349","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