Computer methods and programs in biomedicine最新文献

{"title":"A MPET²-mPBPK model for subcutaneous injection of biotherapeutics with different molecular weights: From local scale to whole-body scale.","authors":"Hao Wang, Mario de Lucio, Tianyi Hu, Yu Leng, Hector Gomez","doi":"10.1016/j.cmpb.2024.108543","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108543","url":null,"abstract":"<p><strong>Background and objective: </strong>Subcutaneous injection of biotherapeutics has attracted considerable attention in the pharmaceutical industry. However, there is limited understanding of the mechanisms underlying the absorption of drugs with different molecular weights and the delivery of drugs from the injection site to the targeted tissue.</p><p><strong>Methods: </strong>We propose the MPET²-mPBPK model to address this issue. This multiscale model couples the MPET² model, which describes subcutaneous injection at the local tissue scale from a biomechanical view, with a post-injection absorption model at injection site and a minimal physiologically-based pharmacokinetic (mPBPK) model at whole-body scale. Utilizing the principles of tissue biomechanics and fluid dynamics, the local MPET² model provides solutions that account for tissue deformation and drug absorption in local blood vessels and initial lymphatic vessels during injection. Additionally, we introduce a model accounting for the molecular weight effect on the absorption by blood vessels, and a nonlinear model accounting for the absorption in lymphatic vessels. The post-injection model predicts drug absorption in local blood vessels and initial lymphatic vessels, which are integrated into the whole-body mPBPK model to describe the pharmacokinetic behaviors of the absorbed drug in the circulatory and lymphatic system.</p><p><strong>Results: </strong>We establish a numerical model which links the biomechanical process of subcutaneous injection at local tissue scale and the pharmacokinetic behaviors of injected biotherapeutics at whole-body scale. With the help of the model, we propose an explicit relationship between the reflection coefficient and the molecular weight and predict the bioavalibility of biotherapeutics with varying molecular weights via subcutaneous injection.</p><p><strong>Conclusion: </strong>The considered drug absorption mechanisms enable us to study the differences in local drug absorption and whole-body drug distribution with varying molecular weights. This model enhances the understanding of drug absorption mechanisms and transport routes in the circulatory system for drugs of different molecular weights, and holds the potential to facilitate the application of computational modeling to drug formulation.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108543"},"PeriodicalIF":4.9,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821885","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}

{"title":"Transferable automatic hematological cell classification: Overcoming data limitations with self-supervised learning.","authors":"Laura Wenderoth, Anne-Marie Asemissen, Franziska Modemann, Maximilian Nielsen, René Werner","doi":"10.1016/j.cmpb.2024.108560","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108560","url":null,"abstract":"<p><strong>Background and objective: </strong>Classification of peripheral blood and bone marrow cells is critical in the diagnosis and monitoring of hematological disorders. The development of robust and reliable automatic classification systems is hampered by data scarcity and limited model generalizability across laboratories. The present study proposes the integration of self-supervised learning (SSL) into cell classification pipelines to address these challenges.</p><p><strong>Methods: </strong>The experiments are based on four public hematological single cell image datasets: one bone marrow and three peripheral blood datasets. The cell classification pipeline consists of two parts: (1) SSL-based image feature extraction without the use of image annotations, and (2) a lightweight machine learning classifier applied to the SSL features and trained on only a small number of annotated images.</p><p><strong>Results: </strong>Direct transfer of SSL models trained on bone marrow data to peripheral blood data resulted in higher balanced classification accuracy than the transfer of supervised deep learning counterparts for all blood datasets. After adaptation of the lightweight machine learning classifier with 50 labeled samples per class of the new dataset, the SSL pipeline surpasses supervised deep learning classification performance for one dataset and classes with rare or atypical cell types and performs similarly on the other datasets.</p><p><strong>Conclusions: </strong>The results demonstrate that SSL enables (1) extraction of meaningful cell image features without the use of cell class information; (2) efficient transfer of knowledge between bone marrow and peripheral blood cell domains; and (3) efficient model adaptation to new datasets using only a few labeled data samples.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108560"},"PeriodicalIF":4.9,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142853369","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}

{"title":"MP-FocalUNet: Multiscale parallel focal self-attention U-Net for medical image segmentation.","authors":"Chuan Wang, Mingfeng Jiang, Yang Li, Bo Wei, Yongming Li, Pin Wang, Guang Yang","doi":"10.1016/j.cmpb.2024.108562","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108562","url":null,"abstract":"<p><strong>Background and objective: </strong>Medical image segmentation has been significantly improved in recent years with the progress of Convolutional Neural Networks (CNNs). Due to the inherent limitations of convolutional operations, CNNs perform poorly in learning the correlation information between global and long-range features. To solve this problem, some existing solutions rely on building deep encoders and down-sampling operations, but such methods are prone to produce redundant network structures and lose local details. Therefore, medical image segmentation tasks require better solutions to improve the modeling of the global context, while maintaining a strong grasp of the low-level details.</p><p><strong>Methods: </strong>We propose a novel multiscale parallel branch architecture (MP-FocalUNet). On the encoder side of MP-FocalUNet, dual-scale sub-networks are used to extract information of different scales. A cross-scale \"Feature Fusion\" (FF) module was proposed to explore the potential of dual branch networks and fully utilize feature representations at different scales. On the decoder side, combined with the traditional CNN in parallel, focal self-attention is used for long-distance modeling, which can effectively capture the global dependencies and underlying spatial details in a shallower way.</p><p><strong>Results: </strong>Our proposed method is evaluated on both abdominal organ segmentation datasets and automatic cardiac diagnosis challenge datasets. Our method consistently outperforms several state-of-the-art segmentation methods with an average Dice score of 82.45 % (2.68 % higher than HC-Net) and 91.44 % (0.35 % higher than HC-Net) on the abdominal organ datasets and the automatic cardiac diagnosis challenge datasets, respectively.</p><p><strong>Conclusions: </strong>Our MP-FocalUNet is a novel encoder-decoder based multiscale parallel branch Transformer network, which solves the problem of insufficient long-distance modeling in CNNs and fuses image information at different scales. Extensive experiments on abdominal and cardiac medical image segmentation tasks show that our MP-FocalUNet outperforms other state-of-the-art methods. In the future, our work will focus on designing more lightweight Transformer-based models and better learning pixel-level intrinsic structural features generated by patch division in visual Transformers.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108562"},"PeriodicalIF":4.9,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142827621","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}

{"title":"Time-hybrid OSAformer (THO): A hybrid temporal sequence transformer for accurate detection of obstructive sleep apnea via single-lead ECG signals.","authors":"Lingxuan Hou, Yan Zhuang, Heng Zhang, Gang Yang, Zhan Hua, Ke Chen, Lin Han, Jiangli Lin","doi":"10.1016/j.cmpb.2024.108558","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108558","url":null,"abstract":"<p><strong>Background and objective: </strong>Obstructive Sleep Apnea (OSA) is among the most sleep-related breathing disorders, capable of causing severe neurological and cardiovascular complications if left untreated. The conventional diagnosis of OSA relies on polysomnography, which involves multiple electrodes and expert supervision. A promising alternative is single-channel Electrocardiogram (ECG) based diagnosis due to its simplicity and relevance. However, extracting respiratory-related features from ECG is challenging since ECG signals do not directly reflect respiratory patterns. Consequently, the accuracy of most deep learning models that predict OSA using ECG data remains to be improved.</p><p><strong>Methods: </strong>In this study, we propose the Time-Hybrid OSA transformer (THO), a novel method that leverages single-lead ECG signals for accurate OSA detection. The THO enhances feature extraction using a hybrid architecture combining dilated convolution and Long Short-Term Memory (LSTM), along with a multi-scale feature fusion strategy. Additionally, THO integrates an embedded memory decay mechanism within a multi-head attention model to capture real-time characteristics of time series data. Finally, a voting mechanism is incorporated to enhance decision reliability.</p><p><strong>Results: </strong>Evaluation of the THO model demonstrates superior performance with prediction accuracy (ACC) and area under the receiver operating characteristic curve (AUC) values of 95.03 % and 96.85 %, respectively, representing improvements of 11 % and 8 % over comparative models. Moreover, the ACC shows a 5 % enhancement relative to state-of-the-art models.</p><p><strong>Conclusions: </strong>These results prove the THO model's efficacy in predicting OSA, offering a robust alternative to traditional diagnostic approaches.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108558"},"PeriodicalIF":4.9,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142812638","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}

{"title":"Bio-K-Transformer: A pre-trained transformer-based sequence-to-sequence model for adverse drug reactions prediction.","authors":"Xihe Qiu, Siyue Shao, Haoyu Wang, Xiaoyu Tan","doi":"10.1016/j.cmpb.2024.108524","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108524","url":null,"abstract":"<p><strong>Background and objective: </strong>Adverse drug reactions (ADRs) pose a serious threat to patient health, potentially resulting in severe consequences, including mortality. Accurate prediction of ADRs before drug market release is crucial for early prevention. Traditional ADR detection, relying on clinical trials and voluntary reporting, has inherent limitations. Clinical trials face challenges in capturing rare and long-term reactions due to scale and time constraints, while voluntary reporting tends to neglect mild and common reactions. Consequently, drugs on the market may carry unknown risks, leading to an increasing demand for more accurate predictions of ADRs before their commercial release. This study aims to develop a more accurate prediction model for ADRs prior to drug market release.</p><p><strong>Methods: </strong>We frame the ADR prediction task as a sequence-to-sequence problem and propose the Bio-K-Transformer, which integrates the transformer model with pre-trained models (i.e., Bio_ClinicalBERT and K-bert), to forecast potential ADRs. We enhance the attention mechanism of the Transformer encoder structure and adjust embedding layers to model diverse relationships between drug adverse reactions. Additionally, we employ a masking technique to handle target data. Experimental findings demonstrate a notable improvement in predicting potential adverse reactions, achieving a predictive accuracy of 90.08%. It significantly exceeds current state-of-the-art baseline models and even the fine-tuned Llama-3.1-8B and Llama3-Aloe-8B-Alpha model, while being cost-effective. The results highlight the model's efficacy in identifying potential adverse reactions with high precision, sensitivity, and specificity.</p><p><strong>Conclusion: </strong>The Bio-K-Transformer significantly enhances the prediction of ADRs, offering a cost-effective method with strong potential for improving pre-market safety evaluations of pharmaceuticals.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108524"},"PeriodicalIF":4.9,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142817251","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}

{"title":"Adaptive multilevel thresholding for SVD-based clutter filtering in ultrafast transthoracic coronary flow imaging.","authors":"Yizhou Huang, Ruud van Sloun, Massimo Mischi","doi":"10.1016/j.cmpb.2024.108542","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108542","url":null,"abstract":"<p><strong>Background and objective: </strong>The integration of ultrafast Doppler imaging with singular value decomposition clutter filtering has demonstrated notable enhancements in flow measurement and Doppler sensitivity, surpassing conventional Doppler techniques. However, in the context of transthoracic coronary flow imaging, additional challenges arise due to factors such as the utilization of unfocused diverging waves, constraints in spatial and temporal resolution for achieving deep penetration, and rapid tissue motion. These challenges pose difficulties for ultrafast Doppler imaging and singular value decomposition in determining optimal tissue-blood (TB) and blood-noise (BN) thresholds, thereby limiting their ability to deliver high-contrast Doppler images.</p><p><strong>Methods: </strong>This study introduces a novel local blood subspace detection method that utilizes multilevel thresholding by the valley-emphasized Otsu's method to estimate the TB and BN thresholds on a pixel-based level, operating under the assumption that the magnitude of the spatial singular vector curve of each pixel resembles the shape of a trimodal Gaussian. Upon obtaining the local TB and BN thresholds, a weighted mask (WM) is generated to assess the blood content in each pixel. To enhance the computational efficiency of this pixel-based algorithm, a dedicated tree-structure k-means clustering approach, further enhanced by noise rejection (NR) at each singular vector order, is proposed to group pixels with similar spatial singular vector curves, subsequently applying local thresholding (LT) on a cluster-based (CB) level.</p><p><strong>Results: </strong>The effectiveness of the proposed method was evaluated using an ex-vivo setup featuring a Langendorff swine heart. Comparative analysis with power Doppler images filtered using the conventional global thresholding method, which uniformly applies TB and BN thresholds to all pixels, revealed noteworthy enhancements. Specifically, our proposed CBLT+NR+WM approach demonstrated an average 10.8-dB and 11.2-dB increase in Contrast-to-Noise ratio and Contrast in suppressing the tissue signal, paralleled by an average 5-dB (Contrast-to-Noise ratio) and 9-dB (Contrast) increase in suppressing the noise signal.</p><p><strong>Conclusions: </strong>These results clearly indicate the capability of our method to attenuate residual tissue and noise signals compared to the global thresholding method, suggesting its promising utility in challenging transthoracic settings for coronary flow measurement.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108542"},"PeriodicalIF":4.9,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142799520","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}

{"title":"MDMNet: Multi-dimensional multi-modal network to identify organ system limitation in cardiopulmonary exercise testing.","authors":"Qin Wang, Wei Fan, Mingshan Li, Yuanyuan Wang, Yi Guo","doi":"10.1016/j.cmpb.2024.108557","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108557","url":null,"abstract":"<p><strong>Background and objective: </strong>Cardiopulmonary exercise testing (CPET) serves as an integrative and comprehensive assessment tool for cardiorespiratory fitness. In this paper, we present a novel multi-dimensional multi-modal network (MDMNet) to identify functional limitation of organ systems via CPET, which is of great importance in clinical practice and yet a challenging task due to (1) the intricate intra-variable associations, and (2) the significant inter-individual variability.</p><p><strong>Methods: </strong>The proposed model has three compelling characteristics. First, we employ a dedicated embedding strategy for CPET data to map raw inputs into the learned embedding space, facilitating the detection of latent features of physiological variables. Second, we devise a novel multi-dimensional feature extraction module to capture rich features of physiological inputs at different dimensions, which consists of a one-dimensional feature extraction branch unfolding both temporal and spatial patterns of the entire data, and a two-dimensional feature extraction branch based on Gramian Angular Field (GAF) encoding to reveal the complicated temporal correlation relationships between time points within a variable. Third, we integrate these techniques with clinically significant demographic information to establish our MDMNet incorporating multi-dimensional with multi-modal learning, thereby further addressing the issues of complex intra-variable associations and inter-individual variability simultaneously.</p><p><strong>Results: </strong>We evaluated the proposed method on the publicly available CPET dataset, achieving AUC scores of 0.948, 0.949 and 0.931 for three tasks respectively.</p><p><strong>Conclusions: </strong>The superiority of our method in discerning inter-individual differences was further demonstrated through partial least squares discriminant analysis, which holds significant potential for automated clinical application of CPET.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108557"},"PeriodicalIF":4.9,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821886","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}

{"title":"Predicting vulnerable coronary arteries: A combined radiomics-biomechanics approach.","authors":"Anna Corti, Marco Stefanati, Matteo Leccardi, Ovidio De Filippo, Alessandro Depaoli, Pietro Cerveri, Francesco Migliavacca, Valentina D A Corino, José F Rodriguez Matas, Luca Mainardi, Gabriele Dubini","doi":"10.1016/j.cmpb.2024.108552","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108552","url":null,"abstract":"<p><strong>Background and objective: </strong>Nowadays, vulnerable coronary plaque detection from coronary computed tomography angiography (CCTA) is suboptimal, although being crucial for preventing major adverse cardiac events. Moreover, despite the suggestion of various vulnerability biomarkers, encompassing image and biomechanical factors, accurate patient stratification remains elusive, and a comprehensive approach integrating multiple markers is lacking. To this aim, this study introduces an innovative approach for assessing vulnerable coronary arteries and patients by integrating radiomics and biomechanical markers through machine learning methods.</p><p><strong>Methods: </strong>The study included 40 patients (7 high-risk and 33 low-risk) who underwent both CCTA and coronary optical coherence tomography (OCT). The dataset comprised 49 arteries (with 167 plaques), 7 of which (with 28 plaques) identified as vulnerable by OCT. Following image preprocessing and segmentation, CCTA-based radiomic features were extracted and a finite element analysis was performed to compute the biomechanical features. A novel machine learning pipeline was implemented to stratify coronary arteries and patients. For each stratification task, three independent predictive models were developed: a radiomic, a biomechanical and a combined radiomic-biomechanical model. Both k-nearest neighbors (KNN) and decision tree (DT) classifiers were considered.</p><p><strong>Results: </strong>The best radiomic model (KNN) detected all 7 vulnerable arteries and patients and was associated with a balanced accuracy of 0.86 (sensitivity=1, specificity=0.71) for the artery model and of 0.83 (sensitivity=1, specificity=0.67) for the patient model. The best biomechanical model (DT) detected 6 over 7 vulnerable arteries and patients and remarkably increased the specificity, resulting in a balanced accuracy of 0.89 (sensitivity=0.86, specificity=0.93) for the artery model and of 0.88 (sensitivity=0.86, specificity=0.91) for the patient model. Notably, the combined approach optimized the performance, with an increase in the balance accuracy up to 0.94 for the artery model and up to 0.92 for the patient model, being associated with sensitivity=1 and high specificity (0.88 and 0.85 for artery and patient models, respectively).</p><p><strong>Conclusion: </strong>This investigation highlights the promise of radio-mechanical coronary artery phenotyping for patient stratification. If confirmed from larger studies, our approach enables a more personalized management of the disease, with the early identification of high-risk individuals and the reduction of unnecessary interventions for low-risk individuals.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108552"},"PeriodicalIF":4.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142812637","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}

{"title":"EpiBrCan-Lite: A lightweight deep learning model for breast cancer subtype classification using epigenomic data.","authors":"Punam Bedi, Surbhi Rani, Bhavna Gupta, Veenu Bhasin, Pushkar Gole","doi":"10.1016/j.cmpb.2024.108553","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108553","url":null,"abstract":"<p><strong>Background and objectives: </strong>Early breast cancer subtypes classification improves the survival rate as it facilitates prognosis of the patient. In literature this problem was prominently solved by various Machine Learning and Deep Learning techniques. However, these studies have three major shortcomings: huge Trainable Weight Parameters (TWP), suffer from low performance and class imbalance problem.</p><p><strong>Methods: </strong>This paper proposes a lightweight model named EpiBrCan-Lite for classifying breast cancer subtypes using DNA methylation data. This model encompasses three blocks namely Data Encoding, TransGRU, and Classification blocks. In Data Encoding block, the input features are encoded into equal sized chunks and then passed down to TransGRU block which is a modified version of traditional Transformer Encoder (TE). In TransGRU block, MLP module of traditional TE is replaced by GRU module, consisting of two GRU layers to reduce TWP and capture the long-range dependencies of input feature data. Furthermore, output of TransGRU block is passed to Classification block for classifying breast cancer into their subtypes.</p><p><strong>Results: </strong>The proposed model is validated using Accuracy, Precision, Recall, F1-score, FPR, and FNR metrics on TCGA breast cancer dataset. This dataset suffers from the class imbalance problem which is mitigated using Synthetic Minority Oversampling Technique (SMOTE). Experimentation results demonstrate that EpiBrCan-Lite model attained 95.85 % accuracy, 95.96 % recall, 95.85 % precision, 95.90 % F1-score, 1.03 % FPR, and 4.12 % FNR despite of utilizing only 1/1500 of TWP than other state-of-the-art models.</p><p><strong>Conclusion: </strong>EpiBrCan-Lite model is efficiently classifying breast cancer subtypes, and being lightweight, it is suitable to be deployed on low computational powered devices.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108553"},"PeriodicalIF":4.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142817256","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}

{"title":"A multi-task framework for breast cancer segmentation and classification in ultrasound imaging.","authors":"Carlos Aumente-Maestro, Jorge Díez, Beatriz Remeseiro","doi":"10.1016/j.cmpb.2024.108540","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108540","url":null,"abstract":"<p><strong>Background: </strong>Ultrasound (US) is a medical imaging modality that plays a crucial role in the early detection of breast cancer. The emergence of numerous deep learning systems has offered promising avenues for the segmentation and classification of breast cancer tumors in US images. However, challenges such as the absence of data standardization, the exclusion of non-tumor images during training, and the narrow view of single-task methodologies have hindered the practical applicability of these systems, often resulting in biased outcomes. This study aims to explore the potential of multi-task systems in enhancing the detection of breast cancer lesions.</p><p><strong>Methods: </strong>To address these limitations, our research introduces an end-to-end multi-task framework designed to leverage the inherent correlations between breast cancer lesion classification and segmentation tasks. Additionally, a comprehensive analysis of a widely utilized public breast cancer ultrasound dataset named BUSI was carried out, identifying its irregularities and devising an algorithm tailored for detecting duplicated images in it.</p><p><strong>Results: </strong>Experiments are conducted utilizing the curated dataset to minimize potential biases in outcomes. Our multi-task framework exhibits superior performance in breast cancer respecting single-task approaches, achieving improvements close to 15% in segmentation and classification. Moreover, a comparative analysis against the state-of-the-art reveals statistically significant enhancements across both tasks.</p><p><strong>Conclusion: </strong>The experimental findings underscore the efficacy of multi-task techniques, showcasing better generalization capabilities when considering all image types: benign, malignant, and non-tumor images. Consequently, our methodology represents an advance towards more general architectures with real clinical applications in the breast cancer field.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108540"},"PeriodicalIF":4.9,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142794448","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}