Computerized Medical Imaging and Graphics最新文献

{"title":"AutoPromptSeg: Automated Decoupling of Uncertainty Prompts with SAM for semi-supervised medical image segmentation","authors":"Junan Zhu,&nbsp;Zhizhe Tang,&nbsp;Ping Ma,&nbsp;Zheng Liang,&nbsp;Chuanjian Wang","doi":"10.1016/j.compmedimag.2026.102708","DOIUrl":"10.1016/j.compmedimag.2026.102708","url":null,"abstract":"<div><div>The scarcity of high-quality annotated data limits the application of supervised learning in disease diagnosis. Semi-supervised learning (SSL) offers a promising solution to this challenge, utilizing both limited labeled data and large-scale unlabeled data to significantly boost segmentation accuracy. While existing SSL methods focus on model-centric regularization strategies, the emergence of promptable foundation models like Segment Anything (SAM) presents new opportunities for paradigmatic advancement. However, SAM requires datasets with additional prompt annotations to guide the segmentation process, yet most existing medical imaging datasets do not contain them. To address this limitation, we introduce a novel semi-supervised 3D medical image segmentation method called AutoPromptSeg, which generates effective prompts with the Decoupled Uncertainty Prompt Generator (DUPG) while maintaining superior segmentation performance in data-scarce scenarios. Concurrently, we employ the Channel Alignment and Fusion Architecture (CAFA) to align features obtained from different branches, thereby bolstering the representational capacity of unlabeled data. Our proposed approach achieves state-of-the-art performance on three benchmarks: the multi-modality abdominal multi-organ segmentation challenge 2022 dataset (Amos 2022), the left atrium dataset (LA), and the brain tumor segmentation challenge 2020 dataset (BraTS 2020). AutoPromptSeg achieves Dice Score of 68.78% on Amos 2022, 90.02% on LA, and 86.63% on BraTS 2020 under only 10% labeled data setting, demonstrating the excellent performance of our semi-supervised learning framework in limited annotated data.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102708"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023418","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":"ThyFusionNet: A CNN–transformer framework with spatial aware sparse attention for multi modal thyroid disease diagnosis","authors":"Bing Yang ,&nbsp;Jun Li ,&nbsp;Junyang Chen ,&nbsp;Yutong Huang ,&nbsp;Nanbo Xu ,&nbsp;Qiurui Liu ,&nbsp;Jiaxin Liu ,&nbsp;Yuheng Zhou","doi":"10.1016/j.compmedimag.2026.102706","DOIUrl":"10.1016/j.compmedimag.2026.102706","url":null,"abstract":"<div><div>In medical image analysis, accurately diagnosing complex lesions remains a formidable challenge, especially for thyroid disorders, which exhibit high incidence and intricate pathology. To enhance diagnostic precision and robustness, we assembled ThyM3, a large-scale multimodal dataset comprising thyroid computed tomography and ultrasound images. Building on this resource, we introduce ThyFusionNet, a novel deep-learning architecture that combines convolutional backbones with transformer modules and performs feature-level fusion to exploit complementary cues across modalities. To improve semantic alignment and spatial modeling, we incorporate head-wise positional encodings and an adaptive sparse attention scheme that suppresses redundant activations while highlighting key features. Skip connections are used to retain low-level details, and a gated-attention fusion block further enriches cross-modal interaction. We also propose an adaptive contrastive-entropy loss that preserves feature consistency and simultaneously enhances prediction discriminability and stability. Extensive experiments demonstrate that ThyFusionNet surpasses current leading methods in accuracy, robustness, and generalization, underscoring its strong potential for clinical deployment.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102706"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023420","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":"An interpretable machine learning framework with data-informed imaging biomarkers for diagnosis and prediction of Alzheimer’s disease","authors":"Wenjie Kang ,&nbsp;Bo Li ,&nbsp;Lize C. Jiskoot ,&nbsp;Peter Paul De Deyn ,&nbsp;Geert Jan Biessels ,&nbsp;Huiberdina L. Koek ,&nbsp;Jurgen A.H.R. Claassen ,&nbsp;Huub A.M. Middelkoop ,&nbsp;Wiesje M. van der Flier ,&nbsp;Willemijn J. Jansen ,&nbsp;Stefan Klein ,&nbsp;Esther E. Bron ,&nbsp;Alzheimer’s Disease Neuroimaging Initiative ,&nbsp;on behalf of the Parelsnoer Neurodegenerative Diseases study group","doi":"10.1016/j.compmedimag.2026.102722","DOIUrl":"10.1016/j.compmedimag.2026.102722","url":null,"abstract":"<div><div>Machine learning methods based on imaging and other clinical data have shown great potential for improving the early and accurate diagnosis of Alzheimer’s disease (AD). However, for most deep learning models, especially those including high-dimensional imaging data, the decision-making process remains largely opaque which limits clinical applicability. Explainable Boosting Machines (EBMs) are inherently interpretable machine learning models, but are typically applied to low-dimensional data. In this study, we propose an interpretable machine learning framework that integrates data-driven feature extraction based on Convolutional Neural Networks (CNNs) with the intrinsic transparency of EBMs for AD diagnosis and prediction. The framework enables interpretation at both the group-level and individual-level by identifying imaging biomarkers contributing to predictions. We validated the framework on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort, achieving an area-under-the-curve (AUC) of 0.969 for AD vs. control classification and 0.750 for MCI conversion prediction. External validation was performed on an independent cohort, yielding AUCs of 0.871 for AD vs. subjective cognitive decline (SCD) classification and 0.666 for MCI conversion prediction. The proposed framework achieves performance comparable to state-of-the-art black-box models while offering transparent decision-making, a critical requirement for clinical translation. Our code is available at: <span><span>https://gitlab.com/radiology/neuro/interpretable_ad_classification</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102722"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146144513","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":"SGAFNet: Robust brain tumor segmentation via learnable sequence-guided adaptive fusion in available MRI acquisitions","authors":"Zhuoneng Zhang ,&nbsp;Luyi Han ,&nbsp;Dengqiang Jia ,&nbsp;Tianyu Zhang ,&nbsp;Zehui Lin ,&nbsp;Kahou Chan ,&nbsp;Jiaju Huang ,&nbsp;Shaobin Chen ,&nbsp;Xiangyu Xiong ,&nbsp;Sio-Kei Im ,&nbsp;Tao Tan ,&nbsp;Yue Sun","doi":"10.1016/j.compmedimag.2026.102703","DOIUrl":"10.1016/j.compmedimag.2026.102703","url":null,"abstract":"<div><div>Automatic and accurate segmentation of brain tumors from Magnetic Resonance Imaging (MRI) data holds significant promise for advancing clinical applicability. However, substantial challenges persist in algorithm development, particularly in scenarios where MRI sequences are incomplete or missing. Although recent automatic segmentation methods have demonstrated notable progress in addressing incomplete sequence scenarios, they often overlook the varying contributions of different MRI sequences to the final segmentation. To address this limitation, we propose a Learnable Sequence-Guided Adaptive Fusion Network (SGAFNet) for robust brain tumor segmentation under incomplete sequence scenarios. Our architecture features parallel encoder–decoders for sequence-specific feature extraction, enhanced by two novel components: (1) a Learned Sequence-Guided Weighted Average (SGWA) module, which adaptively fuses different sequence features by learning sequence-specific contribution factors based on embedded priors, and (2) a Sequence-Specific Attention (SSA) module, which establishes cross-sequence dependencies between available sequences feature and the fused features generated by the SGWA. Comprehensive experiments on the BraTS2018 and BraTS2020 datasets demonstrate that our framework achieves state-of-the-art performance in handling incomplete sequences scenarios compared to existing approaches, with ablation studies confirming the critical role of the proposed SGWA and SSA modules. Increased robustness to incomplete MRI acquisitions enhances clinical applicability, facilitating more consistent diagnostic workflows.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102703"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928058","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":"SPARSE data, rich results: Few-shot semi-supervised learning via class-conditioned image translation","authors":"Guido Manni ,&nbsp;Clemente Lauretti ,&nbsp;Loredana Zollo ,&nbsp;Paolo Soda","doi":"10.1016/j.compmedimag.2026.102705","DOIUrl":"10.1016/j.compmedimag.2026.102705","url":null,"abstract":"<div><div>Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low labeled-data regimes, evaluated across settings with 5 to 50 labeled samples per class. Our approach integrates three specialized neural networks: a generator for class-conditioned image translation, a discriminator for authenticity assessment and classification, and a dedicated classifier, within a three-phase training framework. The method alternates between supervised training on limited labeled data and unsupervised learning that leverages abundant unlabeled images through image-to-image translation rather than generation from noise. We employ ensemble-based pseudo-labeling that combines confidence-weighted predictions from the discriminator and classifier with temporal consistency through exponential moving averaging, enabling reliable label estimation for unlabeled data. Comprehensive evaluation across eleven MedMNIST datasets demonstrates that our approach achieves statistically significant improvements over six state-of-the-art GAN-based semi-supervised methods, with particularly strong performance in the extreme 5-shot setting where the scarcity of labeled data is most challenging. The framework maintains its superiority across all evaluated settings (5, 10, 20, and 50 shots per class). Our approach offers a practical solution for medical imaging applications where annotation costs are prohibitive, enabling robust classification performance even with minimal labeled data. Code is available at <span><span>https://github.com/GuidoManni/SPARSE</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102705"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928060","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":"TA-MedSAM: Text-augmented improved MedSAM for pulmonary lesion segmentation","authors":"Siyuan Tang ,&nbsp;Siriguleng Wang ,&nbsp;Gang Xiang ,&nbsp;Jinliang Zhao ,&nbsp;Yuxin Wang","doi":"10.1016/j.compmedimag.2026.102698","DOIUrl":"10.1016/j.compmedimag.2026.102698","url":null,"abstract":"<div><div>Accurate segmentation of lung lesions is critical for clinical diagnosis. Traditional methods rely solely on unimodal visual data, which limits the performance of existing medical image segmentation models. This paper introduces a novel approach, Text-Augmented Medical Segment Anything Module(TA-MedSAM), which enhances cross-modal representation capabilities through a vision-language fusion paradigm. This method significantly improves segmentation accuracy for pulmonary lesions with challenging characteristics including low contrast, blurred boundaries, complex morphology, and small size. Firstly, we introduce a lightweight Medical Segment Anything Model (MedSAM) image encoder and a pre-trained ClinicalBERT text encoder to extract visual and textual features, This design preserves segmentation performance while reducing model parameters and computational costs, thereby enhancing inference speed. Secondly, a Reconstruction Text Module is proposed to focus the model on lesion-centric textual cues, strengthening semantic guidance for segmentation. Thirdly, we develop an effective Multimodal Feature Fusion Module that integrates visual and textual features using attention mechanisms, and introduce a feature alignment coordination mechanism to mutually enhance heterogeneous information across modalities, and a Dynamic Perception Learning Mechanism is proposed to quantitatively evaluate fusion effectiveness, enabling optimal fused feature selection for improved segmentation accuracy. Finally, a Multi-scale Feature Fusion Module combined with a Multi-task Loss Function enhances segmentation performance for complex regions. Comparative experiments demonstrate that TA-MedSAM outperforms state-of-the-art unimodal and multimodal methods on QaTa-COV19, MosMedData+ , and private dataset. Extensive ablation studies validate the efficacy of our proposed components and optimal hyperparameter combinations.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102698"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979339","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":"HF-VLP: A multimodal vision-language pre-trained model for diagnosing heart failure","authors":"Huiting Ma ,&nbsp;Dengao Li ,&nbsp;Guiji Zhao ,&nbsp;Li Liu ,&nbsp;Jian Fu ,&nbsp;Xiaole Fan ,&nbsp;Zhe Zhang ,&nbsp;Yuchen Liang","doi":"10.1016/j.compmedimag.2026.102719","DOIUrl":"10.1016/j.compmedimag.2026.102719","url":null,"abstract":"<div><div>A considerable increase in the incidence of heart failure (HF) has recently posed major challenges to the medical field, underscoring the urgent need for early detection and intervention. Medical vision-and-language pretraining learns general representation from medical images and texts and shows great prospects in multimodal data-based diagnosis. During model pretraining, patient images may contain multiple symptoms simultaneously and medical research faces a considerable challenge from noisy labels owing to factors such as differences among experts and machine-extracted labels. Furthermore, parameter-efficient fine-tuning (PEFT) is important for promoting model development. To address these challenges, we developed a multimodal vision–language pretrained model for HF, called HF-VLP. In particular, label calibration loss is adopted to solve the labeling noise problem of multisource pretraining data. During pretraining, the data labels are calibrated in real time using the correlation between the labels and prediction confidence. Considering the efficient migratability of the pretrained model, a PEFT method called decomposed singular value weight-decomposed low-rank adaptation is developed. It can learn the downstream data distribution quickly by fine-tuning &lt;1% of the parameters to obtain a better diagnosis rate than zero-shot. Simultaneously, the developed model fuses chest X-ray image features and radiology report features through the dynamic fusion graph module, enhancing the interaction and expression ability of multimodal information. The validity of the model is verified on multiple medical datasets. The average AUC of multisymptom prediction in the Open-I dataset and the hospital dataset PPL-CXR reached 83.67% and 91.28%, respectively. The developed model can accurately classify the symptoms of patients, thereby assisting doctors in diagnosis.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"128 ","pages":"Article 102719"},"PeriodicalIF":4.9,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146144561","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":"UltraBoneUDF: Self-supervised bone surface reconstruction from ultrasound based on neural unsigned distance functions","authors":"Luohong Wu ,&nbsp;Matthias Seibold ,&nbsp;Nicola A. Cavalcanti ,&nbsp;Giuseppe Loggia ,&nbsp;Lisa Reissner ,&nbsp;Bastian Sigrist ,&nbsp;Jonas Hein ,&nbsp;Lilian Calvet ,&nbsp;Arnd Viehöfer ,&nbsp;Philipp Fürnstahl","doi":"10.1016/j.compmedimag.2025.102690","DOIUrl":"10.1016/j.compmedimag.2025.102690","url":null,"abstract":"<div><h3>Background:</h3><div>Bone surface reconstruction is an essential component of computer-assisted orthopedic surgery (CAOS), forming the foundation for both preoperative planning and intraoperative guidance. Compared to traditional imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI), ultrasound, an emerging CAOS technology, provides a radiation-free, cost-effective, and portable alternative. While ultrasound offers new opportunities in CAOS, technical shortcomings continue to hinder its translation into surgery. In particular, due to the inherent limitations of ultrasound imaging, B-mode ultrasound typically captures only partial bone surfaces. The inter- and intra-operator variability in ultrasound scanning further increases the complexity of the data. Existing reconstruction methods struggle with such challenging data, leading to increased reconstruction errors and artifacts, such as holes and inflated structures. Effective techniques for accurately reconstructing open bone surfaces from real-world 3D ultrasound volumes remain lacking.</div></div><div><h3>Methods:</h3><div>We propose UltraBoneUDF, a self-supervised framework specifically designed for reconstructing open bone surfaces from ultrasound data. It learns unsigned distance functions (UDFs) from 3D ultrasound data. In addition, we present a novel loss function based on local tangent plane optimization that substantially improves surface reconstruction quality. UltraBoneUDF and competing models are benchmarked on three open-source datasets and further evaluated through ablation studies.</div></div><div><h3>Results:</h3><div>Qualitative results demonstrate the limitations of the state-of-the-art methods. Quantitatively, UltraBoneUDF achieves comparable or lower bi-directional Chamfer distance across three datasets with fewer parameters: 1.60 mm on the UltraBones100k dataset (<span><math><mrow><mo>≈</mo><mn>25</mn><mo>.</mo><mn>5</mn><mtext>%</mtext></mrow></math></span> improvement), 0.21 mm on the OpenBoneCT dataset, and 0.18 mm on the ClosedBoneCT dataset.</div></div><div><h3>Conclusion:</h3><div>UltraBoneUDF represents a promising solution for open bone surface reconstruction from 3D ultrasound volumes, with the potential to advance downstream applications in CAOS.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102690"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840092","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":"Frequency-spatial synergistic network for accelerated multi-contrast MRI reconstruction","authors":"Ke Li ,&nbsp;Dong Liang ,&nbsp;Guoqing Chen ,&nbsp;Qiyu Jin ,&nbsp;Tieyong Zeng","doi":"10.1016/j.compmedimag.2025.102682","DOIUrl":"10.1016/j.compmedimag.2025.102682","url":null,"abstract":"<div><div>To accelerate the Magnetic Resonance Imaging (MRI) process, multi-contrast MRI reconstruction has emerged as a mainstream approach. This technique leverages readily available auxiliary modality information to guide the high-quality reconstruction of the target modality. The core challenge of this task lies in effectively capturing the global dependencies across different contrasts and efficiently integrating complementary information from multiple contrasts. To address these challenges, we propose the Multi-Contrast Dual-Domain (MCDD) network. It leverages frequency-domain information to capture global dependencies. Specifically, the network employs the Single-Contrast Learning (SCL) module as a prior to guide the Multi-Contrast Learning (MCL) module. Both modules extract complementary global and local features through Frequency (Fre) and Spatial (Spa) extraction blocks, which are fused via an Adaptive Fusion Mechanism (AFM). Experiments on BraTS, MRBrainS, and fastMRI demonstrate that MCDD outperforms state-of-the-art methods, achieving PSNR improvements of 2.42 dB (<span><math><mrow><mn>4</mn><mo>×</mo></mrow></math></span>), 2.11 dB (<span><math><mrow><mn>8</mn><mo>×</mo></mrow></math></span>), 1.63 dB (<span><math><mrow><mn>16</mn><mo>×</mo></mrow></math></span>), and 0.82 dB (<span><math><mrow><mn>32</mn><mo>×</mo></mrow></math></span>). Qualitative results further confirm enhanced structural fidelity and reduced artifacts, validating MCDD as an effective solution for accelerated MRI reconstruction.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102682"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685379","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":"Attention-aware network with lightness embedding and Hybrid Guided Embedding for laparoscopic image desmoking","authors":"Ziteng Liu ,&nbsp;Chenghong Zhang ,&nbsp;Dongdong He ,&nbsp;Chenyang Yang ,&nbsp;Hao Liu ,&nbsp;Wenpeng Gao ,&nbsp;Yili Fu","doi":"10.1016/j.compmedimag.2025.102691","DOIUrl":"10.1016/j.compmedimag.2025.102691","url":null,"abstract":"<div><div>Surgical smoke removal is crucial for enhancing laparoscopic image quality in computer-assisted surgery. While existing methods utilize estimated smoke distribution to address non-homogeneous characteristics, most treat this information merely as prior input and often suffer from over-desmoking artifacts. To address these limitations, this study introduces a desmoking network that reconstructs smoke-free images by explicitly utilizing smoke distribution information. The network comprises two key modules: the Smoke Attention Estimator (SAE) and the Hybrid Guided Embedding (HGE). The SAE generates a smoke attention map via a channel-aware position embedding with lightness prior to improve accuracy. The HGE takes the predicted smoke attention map from the SAE as input and employs convolutional layers along with a novel field transformation method to generate residual terms. By combining these residual terms with the original image, the HGE preserves fine details in smoke-free regions, thereby preventing over-desmoking. Experimental results reveal that the proposed method achieves improvements of at least 3.71% in Peak Signal-to-Noise Ratio (PSNR) and 18.75% in Learned Perceptual Image Patch Similarity compared to state-of-the-art methods on the synthetic dataset, while attaining the lowest Perception-based Image Quality Evaluator score (24.55) on the Cholec80 dataset. It operates at around 174 frames per second, indicating strong real-time processing capability. The network achieves over 40 dB in PSNR for smoke-free regions, excelling in both color restoration and detail preservation. This work is available at <span><span>https://homepage.hit.edu.cn/wpgao?lang=en</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50631,"journal":{"name":"Computerized Medical Imaging and Graphics","volume":"127 ","pages":"Article 102691"},"PeriodicalIF":4.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145866672","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}