Discover imaging最新文献

{"title":"Adapting segment anything model for hematoma segmentation in traumatic brain injury.","authors":"Lingrui Cai, Craig Williamson, Andrew Nguyen, Emily Wittrup, Kayvan Najarian","doi":"10.1007/s44352-025-00011-4","DOIUrl":"10.1007/s44352-025-00011-4","url":null,"abstract":"<p><p>Hematoma segmentation in traumatic brain injury (TBI) is critical for accurate diagnosis and effective treatment planning. In this study, we evaluate various automated segmentation models, including stat-of-the-art architecture as benchmarks, and compare their performance with our proposed SAM-Adapter method for segmenting hematomas in brain CT scans. By incorporating the adapter into the vanilla SAM model, we address the challenges in medical imaging, which has very limited annotated datasets, enhancing model performance efficiency. We also find that domain-specific pre-processing, such as contrast adjustment, reduces the need for extensive pretraining, making the model more streamlined. And the model performance benefited with optimization and hyperparameter tuning. Our results demonstrate that the SAM-Adapter model achieved strong performance and reliability in identifying hematomas with Dice (72.34%), IoU (59.78%), 95% HD (5.57), sensitivity (75.39%) and specificity (99.73%). Inter-observer variability was assessed, revealing that the model's performance Dice (67.20%) was closely aligned with human expert agreement Dice (63.79%), suggesting its potential clinical utility. The external validation on the HemSeg-200 dataset, which contains 222 scans, demonstrates the robustness of our approach across diverse cases. These advancements in automatic segmentation hold promise for improving the accuracy and efficiency of TBI diagnosis, supporting clinical decision-making, and enhancing patient outcomes.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s44352-025-00011-4.</p>","PeriodicalId":520461,"journal":{"name":"Discover imaging","volume":"2 1","pages":"6"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12106135/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144176435","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":"Electron paramagnetic resonance detection of superoxide in a murine model of acute lung injury.","authors":"Hanan B Elajaili, Nathan Dee, Tanden Hovey, Autumn Canny, Georgina Amassah, Janelle Posey, George A Rinard, Joseph P Y Kao, Sandra S Eaton, Gareth R Eaton, Eva S Nozik","doi":"10.1007/s44352-025-00014-1","DOIUrl":"10.1007/s44352-025-00014-1","url":null,"abstract":"<p><p>Superoxide (O₂ ^·-) production in an acute lung injury (ALI) murine model was detected by electron paramagnetic resonance (EPR) spectroscopy and imaging. Lung injury was induced in wild-type (WT) mice and transgenic (Tg) mice with lung-specific EC-SOD overexpression by lipopolysaccharide (LPS) administered intraperitoneally (IP) at a dose of 10 mg/kg. At 24 h after LPS treatment, mice were treated intraperitoneally and subcutaneously with the cyclic hydroxylamine probe, CMH, for superoxide measurements in the blood, or via intratracheal delivery (IT) with the cyclic hydroxylamine probes, CPH or DCP-AM-H, for lung cellular and mitochondrial superoxide detection. Blood was drawn one hour after CMH probe administration, while lungs were harvested five minutes following the administration of CPH or DCP-AM-H. Superoxide measurements in the blood by EPR were performed at X-band (~ 9.5 GHz). EPR images of isolated lungs were obtained by rapid-scan EPR at L-band (1 GHz). Inflammatory cell count, protein, and cell count in bronchoalveolar lavage fluid (BALF) were used to evaluate systemic inflammation and lung injury, respectively. Increased circulating neutrophils and monocytes indicate LPS-induced systemic inflammation. LPS-induced ALI was evidenced by increased alveolar protein and inflammatory cell count. In WT mice LPS increased superoxide in blood and increased lung cellular and mitochondrial superoxide, measured by EPR. In Tg mice with increased lung EC-SOD, blood superoxide increased; however, lung cellular and mitochondrial superoxide did not increase with LPS. These results show that EPR spectroscopy and imaging of excised lungs can detect superoxide production in a model of ALI and differentiate between cellular and mitochondrial superoxide. This provides essential new information as we showed that changes in lung superoxide does not always correlate with changes in blood superoxide levels. This is a significant step toward the ultimate goal of establishing a protocol for real-time monitoring of lung redox status in vivo, enabling disease risk stratification and guiding clinical research.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s44352-025-00014-1.</p>","PeriodicalId":520461,"journal":{"name":"Discover imaging","volume":"2 1","pages":"11"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12394321/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144985659","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":"Repeatability and reproducibility of quantitative ultrasound cervical measurements in women at risk for preterm birth.","authors":"Michelle Villegas-Downs, Ziyi Gao, Huizhu Jia, Aiguo Han, Barbara L McFarlin, William D O'Brien, Douglas G Simpson","doi":"10.1007/s44352-025-00020-3","DOIUrl":"10.1007/s44352-025-00020-3","url":null,"abstract":"<p><strong>Purpose: </strong>Transvaginal Quantitative Ultrasound (QUS) has the potential to enhance preterm birth risk monitoring during pregnancy but evidence on the reliability of commonly used QUS parameters in vivo is lacking. This study assesses intra-sonographer repeatability and inter-sonographer reproducibility of six different QUS measurements of the human cervix during pregnancy: Attenuation Coefficient (AC), Lizzi Feleppa (LF) Intercept, Midband and Slope, and Envelope Kappa and Mu.</p><p><strong>Methods: </strong>This prospective study was approved by the institutional review board at the University of Illinois, Chicago. Informed consent was obtained from all participants, who were selected from pregnant women enrolled in the single-center study, \"QUS Technology for Identifying At-Risk Women for Spontaneous Preterm Birth.\" They received a standard clinical transvaginal ultrasound scan followed by two research scans at 20 ± 2 and 24 ± 2 weeks of gestation. During one or both research scans, they underwent two independent examinations (same-sonographer or cross-sonographer). QUS measurements were computed from ultrasound radiofrequency (RF) data. Variation attributable to transducers, phantoms, and sonographers was evaluated by linear mixed model analysis. QUS parameters were averaged over four acquisitions from each examination. Repeatability and reproducibility were evaluated using the coefficient of variation (CoV), intraclass correlation coefficient (ICC), and Bland-Altman analysis.</p><p><strong>Results: </strong>Eighty-one participants (mean age, 27.12 years ± 5.81) were recruited for a total of 82 examination pairs, yielding 36 intra-sonographer and 46 inter-sonographer pairs of examinations. Transducer and reference phantom variances were not statistically significant (<i>p</i> > 0.05). AC, LF Midband, LF Slope, Kappa, and Mu displayed moderate re-examination (intra-sonographer) repeatability (CoV: 11.9%-12.9%, ICC: 0.62-0.69). LF Intercept had poor repeatability (CoV: 6.9%, ICC: 0.38). AC and LF Midband also displayed moderate inter-sonographer reproducibility (CoV: 10.4%-13.9%, ICC: 0.61-0.63). LF Intercept had marginal reproducibility (CoV: 7.6%, ICC: 0.51). Kappa and mu had poor reproducibility (CoV: 6.9%-14.5%, ICC 0.27-0.38).</p><p><strong>Conclusion: </strong>Averaged in vivo transvaginal QUS measurements of AC and LF Midband have potential for development as noninvasive clinical measurements with moderate reproducibility for auxiliary monitoring of the progress of pregnancy. The other QUS parameters evaluated in this study require further refinement before they can be recommended for clinical use.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s44352-025-00020-3.</p>","PeriodicalId":520461,"journal":{"name":"Discover imaging","volume":"2 1","pages":"16"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12627178/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145567046","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":"Multiplexed confocal FLIM for dynamic molecular imaging in live cells.","authors":"Morgan Richards, Nikolina Malic, Elizabeth J Osterlund, Andrea Rhikkaella Buendia, Laura Polga, Ray Truant, Qiyin Fang","doi":"10.1007/s44352-025-00010-5","DOIUrl":"10.1007/s44352-025-00010-5","url":null,"abstract":"<p><p>Quantitative measurements of the dynamics of biomolecular interactions allow biologists to develop a better understanding of biological processes that are critical to new diagnostic tools, drug discovery, and personalized treatments of diseases. Such measurements require multidimensional (spatial, spectral, and temporal) imaging with a high frame rate. Conventional single point confocal microscopy can produce 3D images at video rate but faces difficulties in accurately measuring fluorescence lifetime images (FLIM) while maintaining low excitation power to avoid phototoxicity and photobleaching in live cells. Multipoint confocal fluorescence lifetime imaging offers access to microscopic dynamics at the subcellular resolution. We have designed a 32 × 32 point multiplexing time-resolved confocal microscope to address these problems and demonstrated the power of this system to measure live cell FLIM of Förester resonance energy transfer (FRET). Using a pinhole array simplifies the optical system design, allowing improved optical efficiency for imaging at faster frame rates with a temporally calibrated single photon avalanche detector (SPAD) array. These efficiency improvements are leveraged by redesigning the optomechanical system and software processing to achieve a frame rate 12 times faster than previously demonstrated. Through dilution series measurements, we demonstrate that a concentration as low as 10 µM Coumarin6 can be measured accurately at 4 Hz frame rates. The performance is also demonstrated with fixed, stained samples and FLIM-FRET constructs in live cells at a maximum imaging rate of 4 Hz with an image dimension of 960 × 960 pixels.</p>","PeriodicalId":520461,"journal":{"name":"Discover imaging","volume":"2 1","pages":"7"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12106160/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144176392","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":"Deep learning imaging analysis to identify bacterial metabolic states associated with carcinogen production.","authors":"Maysam Orouskhani, Sarwesh Rauniyar, Norma Morella, Daniel Lachance, Samuel S Minot, Neelendu Dey","doi":"10.1007/s44352-025-00006-1","DOIUrl":"10.1007/s44352-025-00006-1","url":null,"abstract":"<p><strong>Background: </strong>Colorectal cancer (CRC) is a globally prevalent cancer. Emerging research implicates the gut microbiome in CRC pathogenesis. Bacteria such as <i>Clostridium scindens</i> can produce the carcinogenic bile acid deoxycholic acid (DCA). It is unknown whether imaging methods can differentiate DCA-producing and DCA-non-producing <i>C. scindens</i> cells.</p><p><strong>Methods: </strong>Light microscopy images of anaerobically cultured <i>C. scindens</i> in four conditions were acquired at 100× magnification using the Tissue FAX system: <i>C. scindens</i> in media alone (DCA-non-producing state), <i>C. scindens</i> in media with cholic acid (DCA-producing state), or <i>C. scindens</i> in co-culture with one of two <i>Bacteroides</i> species (intermediate DCA production states). We evaluated three approaches: whole-image classification, per-cell classification, and image segmentation-based classification. For whole-image classification, we used a custom Convolutional Neural Network (CNN), pre-trained DenseNet, pre-trained ResNet, and ResNet enhanced by integrating the Digital Images of Bacterial Species (DIBaS) dataset. For cell detection and classification, we applied thresholding (OTSU or adaptive thresholding) followed by a ResNet model. Finally, image segmentation-based classification was performed using nnU-Net.</p><p><strong>Results: </strong>For whole-image analysis, DIBaS-enhanced ResNet models achieved the best performance in distinguishing <i>C. scindens</i> states in monoculture (accuracy 0.89 ± 0.006) and in co-cultures (accuracy 0.86 ± 0.004). Per-cell analysis was optimal at a C constant value of 3, with the ResNet model achieving 62-74% accuracy for <i>C. scindens</i> states in monoculture. Segmentation-based analysis using nnU-Net resulted in Dice coefficients of 87% for <i>C. scindens</i> and 74-76% for the <i>Bacteroides</i> species.</p><p><strong>Conclusions: </strong>This study demonstrates feasibility of image-based deep learning models in identifying health-relevant gut bacterial metabolic states.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at 10.1007/s44352-025-00006-1.</p>","PeriodicalId":520461,"journal":{"name":"Discover imaging","volume":"2 1","pages":"2"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11912549/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143653271","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}