Journal of imaging informatics in medicine最新文献

{"title":"An Adaptive SCG-ECG Multimodal Gating Framework for Cardiac CTA.","authors":"Shambavi Ganesh, Mostafa Abozeed, Usman Aziz, Srini Tridandapani, Pamela T Bhatti","doi":"10.1007/s10278-024-01289-2","DOIUrl":"10.1007/s10278-024-01289-2","url":null,"abstract":"<p><p>Cardiovascular disease (CVD) is the leading cause of death worldwide. Coronary artery disease (CAD), a prevalent form of CVD, is typically assessed using catheter coronary angiography (CCA), an invasive, costly procedure with associated risks. While cardiac computed tomography angiography (CTA) presents a less invasive alternative, it suffers from limited temporal resolution, often resulting in motion artifacts that degrade diagnostic quality. Traditional ECG-based gating methods for CTA inadequately capture cardiac mechanical motion. To address this, we propose a novel multimodal approach that enhances CTA imaging by predicting cardiac quiescent periods using seismocardiogram (SCG) and ECG data, integrated through a weighted fusion (WF) approach and artificial neural networks (ANNs). We developed a regression-based ANN framework (r-ANN WF) designed to improve prediction accuracy and reduce computational complexity, which was compared with a classification-based framework (c-ANN WF), ECG gating, and US data. Our results demonstrate that the r-ANN WF approach improved overall diastolic and systolic cardiac quiescence prediction accuracy by 52.6% compared to ECG-based predictions, using ultrasound (US) as the ground truth, with an average prediction time of 4.83 ms. Comparative evaluations based on reconstructed CTA images show that both r-ANN WF and c-ANN WF offer diagnostic quality comparable to US-based gating, underscoring their clinical potential. Additionally, the lower computational complexity of r-ANN WF makes it suitable for real-time applications. This approach could enhance CTA's diagnostic quality, offering a more accurate and efficient method for CVD diagnosis and management.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1669-1680"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092878/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142485255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Discrimination of Left Atrial Strain Patterns in Hypertensive Heart Disease and Hypertrophic Cardiomyopathy: a Cardiac Magnetic Resonance Feature.","authors":"Huimin Xu, Wei Deng, Zixiang Pan, Kaixuan Yao, Jinxiu Yang, Zhen Wang, Hui Gao, Hongmin Shu, Ren Zhao, Yongqiang Yu, Yuchi Han, Xiaohu Li","doi":"10.1007/s10278-024-01293-6","DOIUrl":"10.1007/s10278-024-01293-6","url":null,"abstract":"<p><p>To assess left atrial (LA) strain parameters using cardiovascular magnetic resonance imaging feature tracking (cardiac MRI-FT) for differentiating hypertensive heart disease (HHD) from hypertrophic cardiomyopathy (HCM), which are two left ventricular hypertrophic diseases that could present with similar morphologies in early stage but differ in clinical symptoms and treatment strategies. 45 patients with HHD, 85 patients with HCM (non-obstructive hypertrophic cardiomyopathy [HNCM, n = 45] and obstructive hypertrophic cardiomyopathy [HOCM, n = 40]) and 30 healthy controls (HC) were retrospectively included. LA volumes, strain, and strain rate were determined by manually contouring on the two- and four-chamber views of the CMR-FT module using CVI 42 software. LA volume parameters including LA maximum, precontraction, and minimum volume index, and total, passive, and active emptying fractions were obtained using the biplane methods. The LA strain parameters, including total strain (εs), passive strain (εe), active strain (εa), peak positive strain rate (SRs), early peak negative strain rate (SRe), and late peak negative strain rate (SRa), were obtained from the LA strain curve. The LA strain and LA strain rate were impaired in both HHD group and HCM group, and they were the most severely impaired in the HOCM group. εs (AUC = 0.691, P = 0.006; the best cutoff value, 25.1%), εa (AUC = 0.654, P = 0.027; the best cutoff value, 10.5%), SRs (AUC = 0.710, P = 0.003; the best cutoff value, 0.81 1/s) and SRa (AUC = 0.667, P = 0.016; the best cutoff value, -1.30 1/s) showed significant differences in the identification between HHD and HNCM. All LA strain parameters were different in the identification between HHD and HOCM (all P < 0.05).LA strain parameters can be helpful for differentiating HHD from HCM, providing valuable insights for diagnosis.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1518-1530"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142485258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing a Reproducible Radiomics Model for Diagnosis of Active Crohn's Disease on CT Enterography Across Annotation Variations and Acquisition Differences.","authors":"Prathyush V Chirra, Pavithran Giriprakash, Alain G Rizk, Jacob A Kurowski, Satish E Viswanath, Namita S Gandhi","doi":"10.1007/s10278-024-01303-7","DOIUrl":"10.1007/s10278-024-01303-7","url":null,"abstract":"<p><p>To systematically identify radiomics features on CT enterography (CTE) scans which can accurately diagnose active Crohn's disease across multiple sources of variation. Retrospective study of CTE scans curated between 2013 and 2015, comprising 164 subjects (65 male, 99 female; all patients were over the age of 18) with endoscopic confirmation for the presence or absence of active Crohn's disease. All patients had three distinct sets of scans available (full and reduced dose, where the latter had been reconstructed via two different methods), acquired on a single scanner at a single institution. Radiomics descriptors from annotated terminal ileum regions were individually and systematically evaluated for resilience to different imaging variations (changes in dose/reconstruction, batch effects, and simulated annotation differences) via multiple reproducibility measures. Multiple radiomics models (by accounting for each source of variation) were evaluated in terms of classifier area under the ROC curve (AUC) for identifying patients with active Crohn's disease, across separate discovery and hold-out validation cohorts. Radiomics descriptors selected based on resiliency to multiple sources of imaging variation yielded the highest overall classification performance in the discovery cohort (AUC = 0.79 ± 0.04) which also best generalized in hold-out validation (AUC = 0.81). Performance was maintained across multiple doses and reconstructions while also being significantly better (p < 0.001) than non-resilient descriptors or descriptors only resilient to a single source of variation. Radiomics features can accurately diagnose active Crohn's disease on CTE scans across multiple sources of imaging variation via systematic analysis of reproducibility measures. Clinical utility and translatability of radiomics features for diagnosis and characterization of Crohn's disease on CTE scans will be contingent on their reproducibility across multiple types and sources of imaging variation.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1594-1605"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles.","authors":"William C Walton, Seung-Jun Kim","doi":"10.1007/s10278-024-01244-1","DOIUrl":"10.1007/s10278-024-01244-1","url":null,"abstract":"<p><p>Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1829-1845"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092884/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142309617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Lightweight Method for Breast Cancer Detection Using Thermography Images with Optimized CNN Feature and Efficient Classification.","authors":"Thanh Nguyen Chi, Hong Le Thi Thu, Tu Doan Quang, David Taniar","doi":"10.1007/s10278-024-01269-6","DOIUrl":"10.1007/s10278-024-01269-6","url":null,"abstract":"<p><p>Breast cancer is a prominent cause of death among women worldwide. Infrared thermography, due to its cost-effectiveness and non-ionizing radiation, has emerged as a promising tool for early breast cancer diagnosis. This article presents a hybrid model approach for breast cancer detection using thermography images, designed to process and classify these images into healthy or cancerous categories, thus supporting disease diagnosis. Multiple pre-trained convolutional neural networks are employed for image feature extraction, and feature filter methods are proposed for feature selection, with diverse classifiers utilized for image classification. Evaluating the DRM-IR test set revealed that the combination of ResNet34, Chi-square ( <math> <msup><mrow><mi>χ</mi></mrow> <mrow><mn>2</mn></mrow> </msup> </math> ) filter, and SVM classifier demonstrated superior performance, achieving the highest accuracy at <math><mrow><mn>99.62</mn> <mo>%</mo></mrow> </math> . Furthermore, the highest accuracy improvement obtained was <math><mrow><mn>18.3</mn> <mo>%</mo></mrow> </math> when using the SVM classifier and Chi-square filter compared to regular convolutional neural networks. The results confirmed that the proposed method, with its high accuracy and lightweight model, outperforms state-of-the-art breast cancer detection from thermography image methods, making it a good choice for computer-aided diagnosis.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1434-1451"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092891/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142362679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Application of ImageJ Software for Roughness Analysis of Dental Implants.","authors":"Giovanna Nascimento Mendes, Lara Góis Floresta, Wilton Mitsunari Takeshita, Bernardo Ferreira Brasileiro, Cleverson Luciano Trento","doi":"10.1007/s10278-024-01298-1","DOIUrl":"10.1007/s10278-024-01298-1","url":null,"abstract":"<p><p>ImageJ software is a versatile, open-source software for visualizing, processing, and analyzing images, which has contributed to its widespread adoption in the scientific community. A notable application of this software is its integration with scanning electron microscope images, where surface roughness can be quantified. This study aims to highlight the need for knowledge and standardization of the technique selected for analysis to ensure the viability of ImageJ software as a reliable alternative for evaluating the surface roughness of dental implants. Images obtained by scanning electron microscopy, depending on the plugin used or the researcher's standardization, yielded different surface roughness values, which were assessed via ImageJ. Thirty grade 4 titanium osseointegrated dental implants via all treated with similar surface treatment methods were studied. Two groups were formed for analysis via ImageJ: Group 1 assessed surface roughness using only the SurfCharJ plugin (n = 12), and Group 2 assessed surface roughness using both the roughness/waviness and SurfCharJ plugin (n = 18). The results showed that the use of different plugins can lead to different outcomes, potentially affecting the quality of the study. This study concluded that a standardized methodology is necessary to ensure consistency in results obtained via ImageJ.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1812-1819"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092845/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142485260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foundational Segmentation Models and Clinical Data Mining Enable Accurate Computer Vision for Lung Cancer.","authors":"Nathaniel C Swinburne, Christopher B Jackson, Andrew M Pagano, Joseph N Stember, Javin Schefflein, Brett Marinelli, Prashanth Kumar Panyam, Arthur Autz, Mohapar S Chopra, Andrei I Holodny, Michelle S Ginsberg","doi":"10.1007/s10278-024-01304-6","DOIUrl":"10.1007/s10278-024-01304-6","url":null,"abstract":"<p><p>This study aims to assess the effectiveness of integrating Segment Anything Model (SAM) and its variant MedSAM into the automated mining, object detection, and segmentation (MODS) methodology for developing robust lung cancer detection and segmentation models without post hoc labeling of training images. In a retrospective analysis, 10,000 chest computed tomography scans from patients with lung cancer were mined. Line measurement annotations were converted to bounding boxes, excluding boxes < 1 cm or > 7 cm. The You Only Look Once object detection architecture was used for teacher-student learning to label unannotated lesions on the training images. Subsequently, a final tumor detection model was trained and employed with SAM and MedSAM for tumor segmentation. Model performance was assessed on a manually annotated test dataset, with additional evaluations conducted on an external lung cancer dataset before and after detection model fine-tuning. Bootstrap resampling was used to calculate 95% confidence intervals. Data mining yielded 10,789 line annotations, resulting in 5403 training boxes. The baseline detection model achieved an internal F1 score of 0.847, improving to 0.860 after self-labeling. Tumor segmentation using the final detection model attained internal Dice similarity coefficients (DSCs) of 0.842 (SAM) and 0.822 (MedSAM). After fine-tuning, external validation showed an F1 of 0.832 and DSCs of 0.802 (SAM) and 0.804 (MedSAM). Integrating foundational segmentation models into the MODS framework results in high-performing lung cancer detection and segmentation models using only mined clinical data. Both SAM and MedSAM hold promise as foundational segmentation models for radiology images.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1552-1562"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142515945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultra-High-Resolution Photon-Counting Detector CT Benefits Visualization of Abdominal Arteries: A Comparison to Standard-Reconstruction.","authors":"Huan Zhang, Yue Xing, Lingyun Wang, Yangfan Hu, Zhihan Xu, Haoda Chen, Junjie Lu, Jiarui Yang, Bei Ding, Weiguo Hu, Jingyu Zhong","doi":"10.1007/s10278-024-01232-5","DOIUrl":"10.1007/s10278-024-01232-5","url":null,"abstract":"<p><p>This study aimed to investigate the potential benefit of ultra-high-resolution (UHR) photon-counting detector CT (PCD-CT) angiography in visualization of abdominal arteries in comparison to standard-reconstruction (SR) images of virtual monoenergetic images (VMI) at low kiloelectron volt (keV). We prospectively included 47 and 47 participants to undergo contrast-enhanced abdominal CT scans within UHR mode on a PCD-CT system using full-dose (FD) and low-dose (LD) protocols, respectively. The data were reconstructed into six series of images: FD_UHR_Br48, FD_UHR_Bv56, FD_UHR_Bv60, FD_SR_Bv40, LD_UHR_Bv48, and LD_SR_Bv40. The UHR reconstructions were performed with three kernels (Bv48, Bv56, and Bv60) within 0.2 mm. The SR were virtual monoenergetic imaging reconstruction with Bv40 kernel at 40-keV within 1 mm. Each series of axial images were reconstructed into coronal and volume-rendered images. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of seven arteries were measured. Three radiologists assessed the image quality, and visibility of nine arteries on all the images. SNR and CNR values of SR images were significantly higher than those of UHR images (P < 0.001). The SR images have higher ratings in image noise (P < 0.001), but the FD_UHR_Bv56 and FD_UHR_Bv60 images has higher rating in vessel sharpness (P < 0.001). The overall quality was not significantly different among FD_VMI_40keV, LD_VMI_40keV, FD_UHR_Bv48, and LD_UHR_Bv48 images (P > 0.05) but higher than those of FD_UHR_Bv56 and FD_UHR_Bv60 images (P < 0.001). There is no significant difference of nine abdominal arteries among six series of images of axial, coronal and volume-rendered images (P > 0.05). To conclude, 1-mm SR image of VMI at 40-keV is superior to 0.2-mm UHR regardless of which kernel is used to visualize abdominal arteries, while 0.2-mm UHR image using a relatively smooth kernel may allow similar image quality and artery visibility when thinner slice image is warranted.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1891-1903"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092866/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142515948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SDS-Net: A Synchronized Dual-Stage Network for Predicting Patients Within 4.5-h Thrombolytic Treatment Window Using MRI.","authors":"Xiaoyu Zhang, Ying Luan, Ying Cui, Yi Zhang, Chunqiang Lu, Yujie Zhou, Ying Zhang, Huiming Li, Shenghong Ju, Tianyu Tang","doi":"10.1007/s10278-024-01308-2","DOIUrl":"10.1007/s10278-024-01308-2","url":null,"abstract":"<p><p>Timely and precise identification of acute ischemic stroke (AIS) within 4.5 h is imperative for effective treatment decision-making. This study aims to construct a novel network that utilizes limited datasets to recognize AIS patients within this critical window. We conducted a retrospective analysis of 265 AIS patients who underwent both fluid attenuation inversion recovery (FLAIR) and diffusion-weighted imaging (DWI) within 24 h of symptom onset. Patients were categorized based on the time since stroke onset (TSS) into two groups: TSS ≤ 4.5 h and TSS > 4.5 h. The TSS was calculated as the time from stroke onset to MRI completion. We proposed a synchronized dual-stage network (SDS-Net) and a sequential dual-stage network (Dual-stage Net), which were comprised of infarct voxel identification and TSS classification stages. The models were trained on 181 patients and validated on an independent external cohort of 84 patients using metrics of area under the curve (AUC), sensitivity, specificity, and accuracy. A DeLong test was used to statistically compare the performance of the two models. SDS-Net achieved an accuracy of 0.844 with an AUC of 0.914 in the validation dataset, outperforming the Dual-stage Net, which had an accuracy of 0.822 and an AUC of 0.846. In the external test dataset, SDS-Net further demonstrated superior performance with an accuracy of 0.800 and an AUC of 0.879, compared to the accuracy of 0.694 and AUC of 0.744 of Dual-stage Net (P = 0.049). SDS-Net is a robust and reliable tool for identifying AIS patients within a 4.5-h treatment window using MRI. This model can assist clinicians in making timely treatment decisions, potentially improving patient outcomes.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1681-1689"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092910/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Self-Supervised Equivariant Refinement Classification Network for Diabetic Retinopathy Classification.","authors":"Jiacheng Fan, Tiejun Yang, Heng Wang, Huiyao Zhang, Wenjie Zhang, Mingzhu Ji, Jianyu Miao","doi":"10.1007/s10278-024-01270-z","DOIUrl":"10.1007/s10278-024-01270-z","url":null,"abstract":"<p><p>Diabetic retinopathy (DR) is a retinal disease caused by diabetes. If there is no intervention, it may even lead to blindness. Therefore, the detection of diabetic retinopathy is of great significance for preventing blindness in patients. Most of the existing DR detection methods use supervised methods, which usually require a large number of accurate pixel-level annotations. To solve this problem, we propose a self-supervised Equivariant Refinement Classification Network (ERCN) for DR classification. First, we use an unsupervised contrast pre-training network to learn a more generalized representation. Secondly, the class activation map (CAM) is refined by self-supervision learning. It first uses a spatial masking method to suppress low-confidence predictions, and then uses the feature similarity between pixels to encourage fine-grained activation to achieve more accurate positioning of the lesion. We propose a hybrid equivariant regularization loss to alleviate the degradation caused by the local minimum in the CAM refinement process. To further improve the classification accuracy, we propose an attention-based multi-instance learning (MIL), which weights each element of the feature map as an instance, which is more effective than the traditional patch-based instance extraction method. We evaluate our method on the EyePACS and DAVIS datasets and achieved 87.4% test accuracy in the EyePACS dataset and 88.7% test accuracy in the DAVIS dataset. It shows that the proposed method achieves better performance in DR detection compared with other state-of-the-art methods in self-supervised DR detection.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1796-1811"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092899/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142305696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}