Discover imagingPub Date : 2025-01-01Epub Date: 2025-05-26DOI: 10.1007/s44352-025-00011-4
Lingrui Cai, Craig Williamson, Andrew Nguyen, Emily Wittrup, Kayvan Najarian
{"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}
Discover imagingPub Date : 2025-01-01Epub Date: 2025-05-26DOI: 10.1007/s44352-025-00010-5
Morgan Richards, Nikolina Malic, Elizabeth J Osterlund, Andrea Rhikkaella Buendia, Laura Polga, Ray Truant, Qiyin Fang
{"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}
Discover imagingPub Date : 2025-01-01Epub Date: 2025-03-10DOI: 10.1007/s44352-025-00006-1
Maysam Orouskhani, Sarwesh Rauniyar, Norma Morella, Daniel Lachance, Samuel S Minot, Neelendu Dey
{"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}