Deep learning on lateral flow immunoassay for the analysis of detection data

BackgroundVariability in the bony morphology of pathologic hips/knees is a challenge in automating preoperative computed tomography (CT) scan measurements. With the increasing prevalence of CT for advanced preoperative planning, processing this data represents a critical bottleneck in presurgical planning, research, and development. The purpose of this study was to demonstrate a reproducible and scalable methodology for analyzing CT-based anatomy to process hip and knee anatomy for perioperative planning and execution. MethodsOne hundred patients with preoperative CT scans undergoing total knee arthroplasty for osteoarthritis were processed. A two-step deep learning pipeline of classification and segmentation models was developed that identifies landmark images and then generates contour representations. We utilized an open-source computer vision library to compute measurements. Classification models were assessed by accuracy, precision, and recall. Segmentation models were evaluated using dice and mean Intersection over Union (IOU) metrics. Contour measurements were compared against manual measurements to validate posterior condylar axis angle, sulcus angle, trochlear groove-tibial tuberosity distance, acetabular anteversion, and femoral version. ResultsClassifiers identified landmark images with accuracy of 0.91 and 0.88 for hip and knee models, respectively. Segmentation models demonstrated mean IOU scores above 0.95 with the highest dice coefficient of 0.957 [0.954-0.961] (UNet3+) and the highest mean IOU of 0.965 [0.961-0.969] (Attention U-Net). There were no statistically significant differences for the measurements taken automatically vs manually (P > 0.05). Average time for the pipeline to preprocess (48.65 +/− 4.41 sec), classify/retrieve landmark images (8.36 +/− 3.40 sec), segment images (<1 sec), and obtain measurements was 2.58 (+/− 1.92) minutes. ConclusionsA fully automated three-stage deep learning and computer vision-based pipeline of classification and segmentation models accurately localized, segmented, and measured landmark hip and knee images for patients undergoing total knee arthroplasty. Incorporation of clinical parameters, like patient-reported outcome measures and instability risk, will be important considerations alongside anatomic parameters.

As the COVID-19 pandemic moves towards endemic status, testing strategies are being de-escalated. A rapid and effective point of care test (POCT) assessment of SARS-CoV-2 immune responses can inform clinical decision-making and epidemiological monitoring of the disease. This cross-sectional seroprevalence study of anti-SARS-CoV-2 antibodies in Irish healthcare workers assessed how rapid anti-SARS-CoV-2 antibody testing can be compared to a standard laboratory assay, discusses its effectiveness in neutralisation assessment and its uses into the future of the pandemic. A point of care lateral flow immunoassay (LFA) detecting anti-SARS-CoV-2 spike (S)-receptor binding domain (RBD) neutralising antibodies (Healgen SARS-CoV-2 neutralising Antibody Rapid Test Cassette) was compared to the Roche Elecsys/-S anti-SARS-CoV-2 antibody assays and an in vitro surrogate neutralisation assay. A correlation between anti-spike (S), anti-nucleocapsid (N) titres, and in vitro neutralisation was also assessed. 1,777 serology samples were tested using Roche Elecsys/-S anti-SARS-CoV-2 assays to detect total anti-N/S antibodies. 1,562 samples were tested using the POC LFA (including 50 negative controls), and 90 samples were tested using an in vitro ACE2-RBD binding inhibition surrogate neutralisation assay. The POCT demonstrated 97.7% sensitivity, 100% specificity, a positive predictive value (PPV) of 100%, and a negative predictive value (NPV) of 61% in comparison to the commercial assay. Anti-S antibody titres determined by the Roche assay stratified by the POC LFA result groups demonstrated statistically significant differences between the "Positive" and "Negative" LFA groups (p < 0.0001) and the "Weak Positive" and "Positive" LFA groups (p < 0.0001). No statistically significant difference in ACE2-RBD binding inhibition was demonstrated when stratified by the LFA POC results. A positive, statistically significant correlation was demonstrated between the in vitro pseudo-neutralisation assay results and anti-S antibody titres (rho 0.423, p < 0.001) and anti-N antibody titres (rho = 0.55, p < 0.0001). High sensitivity, specificity, and PPV were demonstrated for the POC LFA for the detection of anti-S-RBD antibodies in comparison to the commercial assay. The LFA was not a reliable determinant of the neutralisation capacity of identified antibodies. POC LFA are useful tools in sero-epidemiology settings, pandemic preparedness and may act as supportive tools in treatment decisions through the rapid identification of anti-Spike antibodies.

Long afterglow nanoprobes labeled image enhancement using deep learning in rapid and sensitive lateral flow immunoassay

Accurate intracranial artery segmentation from digital subtraction angiography (DSA) is critical for neurovascular diagnosis and intervention planning. Vascular extraction, which combines preprocessing methods and deep learning models, yields a high level of results, but limited preprocessing results constrain the improvement of results. We propose a texture-based contrast enhancement preprocessing framework integrated with the nnU-Net model to improve vessel segmentation in time-sequential DSA images. The method generates a combined feature mask by fusing local contrast, local entropy, and brightness threshold maps, which is then used as input for deep learning–based segmentation. Segmentation performance was evaluated using the DIAS dataset with various standard quantitative metrics. The proposed preprocessing significantly improved segmentation across all metrics compared to both the baseline and contrast-limited adaptive histogram equalization (CLAHE). Using nnU-Net, the method achieved a Dice Similarity Coefficient (DICE) of 0.83 ± 0.20 and an Intersection over Union (IoU) of 0.72 ± 0.14, outperforming CLAHE (DICE 0.79 ± 0.41, IoU 0.70 ± 0.23) and the baseline (DICE 0.65 ± 0.15, IoU 0.47 ± 0.20). Most notably, vessel connectivity (VC) dropped by over 65% relative to unprocessed images, indicating marked improvements in VC and topological accuracy. This study demonstrates that combining texture-based preprocessing with nnU-Net delivers robust, noise-tolerant, and clinically interpretable segmentation of intracranial arteries from DSA.

To date, a specific point-of-care test (POCT) for 3,4-methylenedioxymethamphetamine (MDMA, ecstasy, 'E') in latent fingerprints (LFPs) has not been explored. Other POCTs identify MDMA in sweat by detecting the drug as a cross-reactant rather than target analyte, thus decreasing the test's sensitivity. The study's aim was to design a sensitive POCT for the detection of MDMA in LFPs using surface plasmon resonance (SPR) and lateral flow immunoassay (LFA) technology. A high-affinity antibody binding pair was identified using the former technique, deeming the pair suitable for a LFA. Titrations of fluorescently labelled antibody and antigen concentrations were tested to identify a sharp drop-in signal upon the addition of MDMA to allow a clear distinction between negative and positive outcomes. We trialled the LFA by producing dose response curves with MDMA and a group of drugs that share a similar chemical structure to MDMA. These were generated through spiking the LFA with increasing levels of drug (0-400 pg/10μl of MDMA; 0-10,000 pg/10μl of cross-reactant). Fluorescent test signals were measured using a cartridge reader. The cut-off (threshold) 60 pg/10μl calculated better cartridge performance (1.00 sensitivity, 0.95 specificity and 0.98 accuracy), when compared with 40 pg/10μl. The biggest cross-reactant was PMMA (250%), followed by MDEA (183%), MBDB (167%), MDA (16%) and methamphetamine (16%). A sensitive LFP screening tool requiring no sample preparation was successfully designed.

This study evaluated the performance of a multi-stage Segmentation Residual Network (SegResNet)-based deep learning (DL) model for the automatic segmentation of cone-beam computed tomography (CBCT) images of patients with stage III and IV periodontitis. Seventy pre-processed CBCT scans from patients undergoing periodontal rehabilitation were used for training and validation. The model was tested on 10 CBCT scans independent from the training dataset by comparing results with semi-automatic (SA) segmentations. Segmentation accuracy was assessed using the Dice similarity coefficient (DSC), Intersection over Union (IoU), and Hausdorff distance 95th percentile (HD95). Linear periodontal measurements were performed on four tooth surfaces to assess the validity of the DL segmentation in the periodontal region. The DL model achieved a mean DSC of 0.9650 ± 0.0097, with an IoU of 0.9340 ± 0.0180 and HD95 of 0.4820 mm ± 0.1269 mm, showing strong agreement with SA segmentation. Linear measurements revealed high statistical correlations between the mesial, distal, and lingual surfaces, with intraclass correlation coefficients (ICC) of 0.9442 (p < 0.0001), 0.9232 (p < 0.0001), and 0.9598(p < 0.0001), respectively, while buccal measurements revealed lower consistency, with an ICC of 0.7481 (p < 0.0001). The DL method reduced the segmentation time by 47 times compared to the SA method. Acquired 3D models may enable precise treatment planning in cases where conventional diagnostic modalities are insufficient. However, the robustness of the model must be increased to improve its general reliability and consistency at the buccal aspect of the periodontal region. This study presents a DL model for the CBCT-based segmentation of periodontal defects, demonstrating high accuracy and a 47-fold time reduction compared to SA methods, thus improving the feasibility of 3D diagnostics for advanced periodontitis.

Lateral flow immunoassay (LFIA) is widely utilized in a variety of point-of-care-test (POCT) applications. In this paper, we discuss the development of an ASIC based strip reader controller for LFIA. The control algorithm was proposed and implemented in Verilog HDL and fabricated into ASIC with 0.18 μm CMOS technology. Functional validation on both FPGA and ASIC implementations were presented. The ASIC controller occupied 0.946 mm2 area and drawn only 2710.39 μW running at the frequency of 50 MHz. High sensitivity was achieved in the quantitative LFIA detection experiments, indicating this ASIC chip has fulfilled the requirement of operating an integrated and portable LFIA strip reading system.

The lateral flow immunoassay (LFIA) is the most successful point-of-care testing (POCT) method to date. In the case of clinical biomarkers that require quantification, it remains a challenge to quantitate those biomarkers using the lateral flow immunoassay remains a challenge due to the cost of the reader and possibly the type of marker used. In the present work, a new concept of a platform LFIA device configuration is proposed in which different, aligned membrane components, some already existing in the classical lateral flow immunoassay, and the others created with special new functions in the present device. As the sample containing the target analyte passes through the aforementioned membranes, the target analyte will initially interact with a target-specific antibody-conjugated to horseradish peroxidase (HRP). Thereafter, the newly formed immunocomplex will diffuse through a proprietary capture membrane (that ensures that the nontarget-bound antibodies do not continue further and thus remain “captured” to that specific area). This is done by having the target molecules (or components thereof) immobilized onto the said capture layer. The target-bound immunocomplexes will then be allowed by the system configuration to continue further to the last layer, where the signal will be generated and quantified. Thus, in the absence of the target analyte in the sample, the free antibodies will be filtered at the capture layer by preimmobilized analyte molecules, thus preventing a false positive signal to occur. We validated the concept in the detection of dengue NS1 protein in view of making a triage test. The sample containing NS1 will first meet HRP-conjugated NS1-specific antibodies and become attached, thus producing an NS1-specific antibody–HRP immunocomplex. The sample then flows through the blocking layer, where the immunocomplex is unchallenged and thus allowed to reach the last “absorbent” pad, incorporating the substrate for the HRP marker. In the case of a positive test, a signal is generated, that is proportional to the amount of immunocomplexes (and therefore the NS1 concentration), and then analyzed and measured at the absorbent pad. Any unbound anti-NS1 antibody will be stopped at the blocking matrix by preimmobilized NS1, so there will be no false positive. As this study is the initial study of a novel configuration, much of the work comprised of optimization steps, such as determining the required NS1 membrane-immobilization concentration and the required target-specific capture antibody concentration. Our immunoassay was tested with spiked buffer and serum samples to mimic the clinical conditions, with a range of NS1 concentrations, and was found, at this time, to be fivefold more sensitive than a gold standard enzyme-linked immunosorbent assay (ELISA) test (5 ng mL–1) performed in our laboratory. This method shows another form of LFIA that has the potential to be quantitative (at least semiquantitative), albeit not solving the reader cost; however, unlike the regular LFIA, we do not use nanobeads but instead enzymes, allowing, in theory, greater sensitivity, while retaining the one-step procedure. The test is accurate and has low production costs.

To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos. A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos. A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos. SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement. III Laryngoscope, 134:2826-2834, 2024.

Segmentation of trabecular bone microdamage in Xray microCT images using a two-step deep learning method

BackgroundDespite recent advances in cancer immunotherapies, their efficacies vary significantly among patients. To better understand the mechanisms of drug resistance, it is essential to characterize immune responses to immunotherapies in...

Most bile duct (BDI) injuries during laparoscopic cholecystectomy (LC) occur due to visual misperception leading to the misinterpretation of anatomy. Deep learning (DL) models for surgical video analysis could, therefore, support visual tasks such as identifying critical view of safety (CVS). This study aims to develop a prediction model of CVS during LC. This aim is accomplished using a deep neural network integrated with a segmentation model that is capable of highlighting hepatocytic anatomy. Still images from LC videos were annotated with four hepatocystic landmarks of anatomy segmentation. A deep autoencoder neural network with U-Net to investigate accurate medical image segmentation was trained and tested using fivefold cross-validation. Accuracy, Loss, Intersection over Union (IoU), Precision, Recall, and Hausdorff Distance were computed to evaluate the model performance versus the annotated ground truth. A total of 1550 images from 200 LC videos were annotated. Mean IoU for segmentation was 74.65%. The proposed approach performed well for automatic hepatocytic landmarks identification with 92% accuracy and 93.9% precision and can segment challenging cases. DL, can potentially provide an intraoperative model for surgical video analysis and can be trained to guide surgeons toward reliable hepatocytic anatomy segmentation and produce selective video documentation of this safety step of LC.

Accurate segmentation of tumor-infected regions in retinal Optical Coherence Tomography (OCT) images is critical for early diagnosis and clinical decision-making. However, conventional deep learning and transformer-based models often struggle to delineate overlapping and inter-dependent pixel features, leading to reduced segmentation precision. This study proposes a novel Dependent Inter-Feature Segmentation Method (DIFSM) to improve the localization and segmentation of retinal tumor regions in OCT images. The proposed DIFSM framework integrates advanced image preprocessing, inter-feature dependency analysis, and a Vision Transformer (ViT) architecture to distinguish differentiable and non-differentiable features. Overlapping pixel regions are identified through inter-feature intensity and gradient analysis, which are indicative of tumor-affected areas. The Vision Transformer is trained using matched and unmatched inter-feature representations to enhance contextual learning and resolve feature ambiguities. Experiments were conducted on the OCTID dataset comprising high-resolution retinal OCT images, and performance was evaluated using Dice coefficient, Intersection over Union (IoU), precision, sensitivity, specificity, and Mean Square Matching Error (MSME). Comparative analysis was performed against state-of-the-art segmentation models. The proposed DIFSM model achieved a Dice coefficient of 96.2% and an IoU of 94.8%, demonstrating excellent spatial overlap with expert-validated tumor regions. Precision, sensitivity, and specificity reached 96.8%, 96.6%, and 96.7%, respectively, while MSME was reduced to 6.11%. Compared to existing methods, DIFSM improved segmentation accuracy by 14.39%, precision by 14.11%, and reduced MSME by 13.5%. The model consistently outperformed benchmark approaches in detecting macular hole and central serous retinopathy-associated tumor regions while maintaining robustness to noise and structural variability. The proposed DIFSM framework effectively addresses the limitations of existing OCT segmentation methods by explicitly modeling inter-feature dependencies and resolving overlapping pixel ambiguities using a Vision Transformer. The significant improvements in segmentation accuracy and error reduction highlight its potential as a reliable and clinically applicable tool for automated retinal tumor detection in ophthalmic imaging. DIFSM offers a promising direction for enhancing OCT-based diagnostic systems and supporting ophthalmologists in early disease identification and treatment planning.

Technology is changing the future of healthcare, technology-supported non-invasive medical procedures are more preferable in the medical diagnosis. Anemia is one of the widespread diseases affecting the wellbeing of individuals around the world especially childbearing age women and children and addressing this issue with the advanced technology will reduce the prevalence in large numbers. The objective of this work is to perform segmentation of the conjunctiva region for non-invasive anemia detection applications using deep learning. The proposed U-Net Based Conjunctiva Segmentation Model (UNBCSM) uses fine-tuned U-Net architecture for effective semantic segmentation of conjunctiva from the digital eye images captured by consumer-grade cameras in an uncontrolled environment. The ground truth for this supervised learning was given as Pascal masks obtained by manual selection of conjunctiva pixels. Image augmentation and pre-processing was performed to increase the data size and the performance of the model. UNBCSM showed good segmentation results and exhibited a comparable value of Intersection over Union (IoU) score between the ground truth and the segmented mask of 96% and 85.7% for training and validation, respectively.

Lateral flow immunoassay (LFIA) is a vital point-of-care testing (POCT) technique that is widely used for on-site detection and in vitro diagnosis. Many diseases, particularly cardiovascular diseases (CVDs), require the quantitative detection of multiple biomarkers across a broad dynamic range. Recurrent viral infections like COVID-19 elevate CVDs risk, necessitating early warning and prognostic monitoring, especially based on POCT of multiple blood biomarkers of D-dimer, NT-proBNP, and cTnI across a broad range from pg/mL to μg/mL. Traditional LFIAs lack ultrasensitivity and broad-range quantification. We design the surface chemistry-mediated template-free assembly of metal-aggregation-induced emission luminogens (AIEgen) framework@gold nanoparticles (MAF@AuNPs) for developing ultrasensitive and dynamic dual-quantitative LFIA (ddLFIA). The template-free self-assembled MAF@AuNPs have strong fluorescent and plasmonic properties, avoiding complicated synthesis, chemical modifications, and covalent conjugations, thus leading to highly convenient and versatile visual POCT. MAF@AuNPs ddLFIA achieves a normal detection at ng/mL using chromogenic AuNPs and ultrasensitive detection at pg/mL using fluorogenic MAFs, for which the fluorescence signal is 102-103 times more sensitive than the color signal. MAFs and AuNPs are functionally complementary to form a dynamic, broad-range quantification system covering over 5 orders of magnitude, at the same time having a naked eye sensitivity near 1 pg/mL. The visual POCT using MAF@AuNPs ddLFIA aligns well with clinical chemiluminescent assays. MAF@AuNPs ddLFIA perfectly matches ultrasensitive and broad-range multiple biomarker detections for clinical CVDs diagnosis.