Multimodal Imaging Research Articles

Multi-Modality Fusion and Tumor Sub-Component Relationship Ensemble Network for Brain Tumor Segmentation

Deep learning technology has been widely used in brain tumor segmentation with multi-modality magnetic resonance imaging, helping doctors achieve faster and more accurate diagnoses. Previous studies have demonstrated that the weighted fusion segmentation method effectively extracts modality importance, laying a solid foundation for multi-modality magnetic resonance imaging segmentation. However, the challenge of fusing multi-modality features with single-modality features remains unresolved, which motivated us to explore an effective fusion solution. We propose a multi-modality and single-modality feature recalibration network for magnetic resonance imaging brain tumor segmentation. Specifically, we designed a dual recalibration module that achieves accurate feature calibration by integrating the complementary features of multi-modality with the specific features of a single modality. Experimental results on the BraTS 2018 dataset showed that the proposed method outperformed existing multi-modal network methods across multiple evaluation metrics, with spatial recalibration significantly improving the results, including Dice score increases of 1.7%, 0.5%, and 1.6% for the enhanced tumor core, whole tumor, and tumor core regions, respectively.

Topography of Slowed Dark Adaptation in Pseudoxanthoma Elasticum: PROPXE Study Report 1.

To determine the prevalence and spatial pattern of rod and cone dysfunction in patients with pseudoxanthoma elasticum (PXE) and to correlate these with Bruch's membrane (BrM) calcification. PXE is a rare genetic disorder that causes calcification of Bruch's membrane, which eventually leads to loss of central vision. Understanding the functional implications of BrM calcification is crucial for developing effective treatments. In this prospective natural history study (PROPXE, ClinicalTrials.gov ID: NCT05662085), performed at a tertiary referral center, 26 patients with PXE (14 women, 12 men; median age, 55years; interquartile range, 43-59years), diagnosed according to the Plomp criteria, underwent comprehensive ophthalmic evaluations, including best-corrected visual acuity (BCVA), contrast sensitivity testing, and multimodal imaging. Dark adaptometry was tested following a 59% rhodopsin bleach at 8°, 15°, 30°, and 46° eccentricity from the fovea along the temporal retina. The eye without a history of exudative macular neovascularization (MNV) or the better-seeing eye was selected as the study eye. Of 26 participants, 12 had no history of exudative MNV in the study eye, while 14 had previous or current treatment for MNV with a median BCVA of -0.07 logMAR and 0.11 logMAR, respectively. In the macula at 8° eccentricity, rod intercept time (RIT) was prolonged in 83.3% of nonexudative and 92.9% of exudative eyes, while BCVA and cone thresholds at 8° eccentricity were affected in only 42.3% and 65.4% of eyes. The delay in RIT was most pronounced in regions at risk of calcification and increased markedly with age. In addition, prolonged cone recovery time constants were evident that correlated with RIT. Patients with PXE exhibit significant slowing of both cone- and rod-mediated dark adaptation, particularly in regions prone to BrM calcification. These findings suggest that dark adaptometry and assessment of BrM calcification can serve as clinical tools for evaluating disease severity and monitoring progression in PXE, enabling earlier interventions before the onset of exudative MNV or atrophy.

Imaging in clinical trials for psoriatic arthritis: a scoping review.

Psoriatic arthritis (PsA) is a chronic inflammatory condition principally affecting the skin and musculoskeletal system, associated with comorbidities and decreased quality of life. Imaging is crucial for diagnosis, monitoring progression, and evaluating treatment efficacy; therefore, it plays an important role in PsA clinical trials. In this review, we aimed to characterize how imaging modalities and advances in imaging techniques are being used specifically in the PsA clinical trial literature. Following the Arksey and O'Malley framework for scoping reviews, we conducted a comprehensive search of multiple literature databases, from January 1, 2000, to June 27, 2024. We captured 1961 articles and after deduplication, title and abstract screening, and full-text review, 53 studies were included. Radiographs were the most used imaging modality (n = 32/53, 60%), and radiographic progression was frequently measured using the PsA-modified Sharp/van der Heijde score. MRI (n = 16/53, 30%) was used in evaluating peripheral and axial disease, with more recent adoption of validated scoring systems (PsAMRIS and SPARCC). Ultrasound (n = 11/53, 21%), including power Doppler, was used to assess soft tissue inflammation. Standardized scoring systems (e.g. GLOESS) were used in a minority of ultrasound-based studies. Multimodality imaging (n = 7/53, 13%) and CT (n = 2/53, 4%) was uncommon. The development of PsA-specific scoring systems for radiographs and MRI has been instrumental in advancing imaging assessment in PsA. However, their application remains limited, particularly in ultrasound, where further standardization is needed. Future clinical trials should focus on increasing the adoption of PsA-specific scoring systems, exploring advanced techniques (e.g. DCE-MRI), and multi-modal imaging to improve PsA disease monitoring.

A deep ensemble learning framework for glioma segmentation and grading prediction

The segmentation and risk grade prediction of gliomas based on preoperative multimodal magnetic resonance imaging (MRI) are crucial tasks in computer-aided diagnosis. Due to the significant heterogeneity between and within tumors, existing methods mainly rely on single-task approaches, overlooking the inherent correlation between segmentation and grading tasks. Furthermore, the limited availability of glioma grading data presents further challenges. To address these issues, we propose a deep-ensemble learning framework based on multimodal MRI and the U-Net model, which simultaneously performs glioma segmentation and risk grade prediction. We introduce asymmetric convolution and dual-domain attention in the encoder, fully integrating effective information from different modalities, enhancing the extraction of features from critical regions, and constructing a dual-branch decoder that combines spatial features and global semantic information for both segmentation and grading. In addition, we propose a weighted composite adaptive loss function to balance the optimization objectives of the two tasks. Our experimental results on the BraTS dataset demonstrate that our method outperforms state-of-the-art methods, yielding superior segmentation accuracy and precise risk grade prediction.

PROthrombotic States in Transcatheter HEart Valve Leaflet thromboSIS (PROSTHESIS): Rationale and Early Results of the Observational Cohort Study

Subclinical leaflet thrombosis is an imaging phenomenon observed after transcatheter aortic valve implantation (TAVI) and characterized by hypoattenuating leaflet thickening (HALT) on computed tomography angiography. The clinical implications and underlying causes remain uncertain. Hypercoagulability, a component of Virchow’s triad, may contribute to thrombus formation on bioprosthetic leaflets, but data on hypercoagulable disorders in TAVI patients and their impact on HALT are limited. The PROSTHESIS study (PROthrombotic States in Transcatheter HEart valve Subclinical leaflet thrombosIS) is a single-center observational cohort study aiming to include 130 TAVI patients. This pilot study aimed to (i) assess the effect of hypercoagulable disorders on HALT prevalence and (ii) evaluate their impact on the natural history of HALT. Patients were screened for common hypercoagulable disorders using genetic and functional assays and underwent multimodal imaging one year after TAVI to detect HALT. In patients with HALT, post-implant imaging was repeated after three months to assess its progression. Early results comparing 52 TAVI patients with 52 matched controls undergoing coronary angiography showed similar thrombophilia prevalence between the groups (16% vs. 12%, p = 0.565). HALT occurred in 15% of TAVI patients, more extensively in those with thrombophilia (712 mm3 vs. 135 mm3, p = 0.036). However, thrombophilia was not an independent predictor of HALT. One-year follow-up CTA revealed spontaneous HALT resolution in 63%, stability in 25%, and progression in 12%. This study aims to provide insights into HALT and its mechanisms, which may help prevent complications and improve bioprosthesis durability.

Phase coherence weighted multi-mode total focusing method imaging of multi-angle defects

ABSTRACT The multi-mode total focusing method (MTFM) enables a region of interest within a specimen to be imaged using different combinations of beam paths and wave-mode. For a crack, the diffraction response of the tip may be evident in certain modes and the specular reflection in others. Accurate characterisation of defects requires combining information from multiple modes. For MTFM images, not all modes have a high signal-to-noise ratio (SNR). In this work, multi-mode phase coherence imaging (MPCI) was proposed by combining MTFM and phase coherence imaging (PCI) method. The better data fusion is mainly the result of the selective use of information from the most appropriate mode(s) and fusion reduces the probability of misjudging defects. In this paper, full matrix data was acquired for aluminium alloy blocks containing notch defects at different angles and imaged using the both multi-mode methods. The signal-to-noise ratio results of the two multimodal methods show that MPCI is better than MTFM for multi-angle defect detection. In addition, the Sobol sensitivity analysis method was used to construct the signal-to-noise ratio sensitivity parameter for quantifying the imaging effect of each mode on defects at different angles, and the results can effectively guide the optimisation of the multi-mode fusion algorithm.

Real-time multimodal imaging of daptomycin action on the cell wall of adherent Staphylococcus aureus

ObjectivesThis study investigated the efficacy of daptomycin against adherent Staphylococcus aureus (S. aureus), a common colonizer of medical devices that leads to severe infections. For the first time, we evaluated the bactericidal effects of daptomycin on S. aureus immediately after adhesion, mimicking early-stage contamination of biomaterials. Time-kill curve assay and confocal laser scanning microscopy (CLSM) were used to analyze the process dynamics. In addition, atomic force microscopy (AFM) and scanning electron microscopy (SEM) were employed to elucidate daptomycin-induced structural changes in the bacterial cell wall.Results descriptionDaptomycin, at clinically relevant concentrations, rapidly eradicated adherent bacteria in the exponential growth phase, demonstrating an efficiency comparable to its action against planktonic cells. Prolonged exposure to the antibiotic caused marked alterations in the bacterial cell wall, including surface roughening and perforation, as revealed by multimodal imaging. However, daptomycin effectiveness diminished as biofilm formation progressed, underscoring the need for further exploration of optimized clinical strategies.

Acute and Chronic Cardiovascular Adverse Events in Patients with Acute Myeloid Leukemia: A Systematic Review

Background/Objectives: Patients with acute myeloid leukemia (AML) have a higher propensity for adverse cardiovascular outcomes, primarily due to the toxic effects of chemotherapeutic agents. The purpose of this systematic review is to explore the association of acute myeloid leukemia treatment with adverse cardiovascular events. Methods: We systematically screened the literature for studies providing comparative data on cardiovascular toxicities in patients treated for acute myeloid leukemia. After the initial search, 3649 papers were screened and a final total number of 46 were included for the review process. Results: Common chemotherapeutic agents used in AML may cause cardiovascular (CV) toxicities. A plethora of pathophysiological mechanisms are incriminated for these effects. Drug combinations may increase the risk in a synergistic way. In addition, common mutations of AML, personal history of previous cardiovascular disease and impaired heart function carry an increased complication risk. Biomarkers, as well as multimodality imaging, may be used for the early detection of cardiovascular toxicities. Conclusions: Increased risks of CV toxicity and comorbidities are observed among AML patients. With all the available diagnostic modalities, early detection and CV prevention strategies can improve the patient’s prognosis and quality of life.

Clinical characteristics and management outcomes of pediatric patients with Coats disease complicated with retinoschisis (retinal cyst)

PurposeTo present the clinical characteristics and management outcomes of Coats disease with retinoschisis (retinal cyst).MethodsThis was a retrospective review of 13 eyes from 13 consecutive Coats disease patients with retinal cyst. Clinical findings from multimodal ophthalmic imaging were recorded to characterize retinal cyst in Coats disease. All eyes were initially treated with endolaser photocoagulation combined with external drainage of cystic fluid and intravitreal ranibizumab injection. Patients were subsequently followed up to analyze anatomic and visual outcomes.ResultsAll retinal cysts were associated with extensive retinal exudation; 3 eyes (23.1%) presented with exudative retinal detachment. A total of 92.3% (12/13) of the retinal cysts were located in the inferotemporal quadrant. Fluorescein angiography demonstrated telangiectasia surrounding and/or at the edge of the retinal cyst. Eleven eyes (84.6%) underwent endolaser photocoagulation via a nonvitrectomy approach, and 2 eyes (15.4%) underwent endolaser photocoagulation after vitrectomy due to the presence of epiretinal membrane. An average of 1.5 additional laser photocoagulation sessions was performed per patient. After a median follow-up of 23 months (range, 11–33 months), all eyes demonstrated retinal cyst resolution and no active disease. Subretinal fibrosis was observed in 9 eyes (69.2%); of these, 8 had macular subretinal nodules. In total, 30.8% of the eyes had a final vision ≥20/200.ConclusionThe presence of retinoschisis (retinal cyst) in Coats disease is strongly associated with retinal telangiectasia and exudation and is indicative of active vascular disease requiring effective ablative treatment. We propose a novel approach, endolaser photocoagulation combined with external drainage of cystic fluid and intravitreal ranibizumab injection, which was effective in achieving final anatomic improvement with retinal cyst resolution.

High-fidelity image reconstruction in multimode fiber imaging through the MITM-Unet framework

Using a single multimode fiber for both illumination and imaging offers notable advantages in developing ultra-thin imaging probes. However, uneven speckle illumination introduces additional noise, complicating high-precision reconstruction of complex grayscale images, which remains challenging for traditional methods. In this study, we first optimize the image reconstruction framework by combining the inverse transmission matrix approach with deep neural networks, enhancing interpretability and delivering exceptional performance in reconstructing complex images. To address the noise introduced by uneven speckle illumination, we increase the target exposure and effectively integrate information from multiple illumination conditions. Results show that our proposed Multi-speckle Illumination type Inverse Transmission Matrix-Unet (MITM-Unet) method significantly outperforms the Single-speckle illumination type (SITM-Unet). Specifically, images reconstructed with MITM-Unet achieve a structural similarity index of 0.59 and a Pearson correlation coefficient of 0.91, compared to SITM-Unet’s 0.38 and 0.77. These findings underscore the effectiveness of the MITM-Unet method in achieving high-quality imaging of complex grayscale targets, providing valuable insights into the imaging capabilities of single multimode fiber systems. This work holds promise for advancing simpler, more compact wide-field endomicroscopic imaging using multimode fibers.

Design and Characterization of an Optical Phantom for Mesoscopic Multimodal Fluorescence Lifetime Imaging and Optical Coherence Elastography

Design and Characterization of an Optical Phantom for Mesoscopic Multimodal Fluorescence Lifetime Imaging and Optical Coherence Elastography

Brainstem and cerebellar radiological findings in progressive supranuclear palsy

Abstract Progressive supranuclear palsy (PSP) is a sporadic neurodegenerative 4-repeat (4R) tauopathy associated with significant morbidity. Heterogeneity of symptom expression among this group is increasingly recognized, reflecting variable tau spread and neurodegeneration. Clinical manifestations consist of debilitating and rapidly progressive motor, oculomotor, speech, cognitive and affective impairments. Core pathological changes are noted with a predominance in the midbrain and basal ganglia, however spread to the more caudal brainstem and cerebellar regions is reported at various stages. Accordingly, whilst midbrain atrophy is the best recognized supportive imaging finding, quantitative neuroimaging studies using MRI and PET approaches have revealed a wider profile of brain abnormalities in cohorts of individuals with PSP. This expanded neurobiological scope of disease may account for individual heterogeneity and may highlight additional biological markers that are relevant to diagnosing and tracking the illness. Additionally, there is increasing understanding of the diverse cognitive, affective and speech functions of the cerebellum, which may be implicated in PSP beyond current recognition. In this review, we undertake a systematic literature search and summary of in vivo structural and functional neuroimaging findings in the brainstem and cerebellum in PSP to date. Novel and multimodal imaging techniques have emerged over recent years, which reveal several infratentorial alterations beyond midbrain atrophy in PSP. Most saliently, there is evidence for volume loss and microstructural damage in the pons, middle cerebellar peduncles and cerebellar cortex and deep nuclei, reported alongside recognised midbrain and superior cerebellar peduncle changes. Whilst the literature supporting the presence of these features is not unanimous, the evidence base is compelling, including correlations with disease progression, severity, or variant differences. A smaller number of studies report on abnormalities in MRI measures of iron deposition, neuromelanin, viscoelasticity, and the glymphatic system involving the infratentorial regions. Molecular imaging studies have also shown increased uptake of tau tracer in the midbrain and cerebellar dentate nucleus, although concern remains regarding possible off-target binding. Imaging of other molecular targets has been sparse, but reports of neurotransmitter, inflammatory and synaptic density alterations in cerebellar and brainstem regions are available. Taken together, there is an established evidence base of in vivo imaging alterations in the brainstem and cerebellum which highlight that midbrain atrophy is often accompanied by other infratentorial alterations in people with PSP. Further research examining the contribution of these features to clinical morbidity and inter-individual variability in symptom expression is warranted.

Characterization of Syphilitic Chorioretinitis as a White Dot Syndrome with Multimodal Imaging: Case Series

Background/Objectives: To investigate the role of multimodal imaging, including ultra-widefield fundus autofluorescence (UWFAF), in diagnosing and monitoring syphilitic chorioretinitis, focusing on the detection of placoid appearance and white dots/spots. We aim to classify syphilitic chorioretinitis as a white dot syndrome, given evident features in the context of recent case reports and previously unavailable multimodal imaging. Methods: This single-institution study was conducted as a consecutive, observational case series. Five eyes from three patients were diagnosed with syphilitic chorioretinitis using multimodal imaging, including ultra-widefield pseudocolor fundus photography and intravenous fluorescein angiography, UWFAF, and swept-source optical coherence tomography, upon laboratory results. Results: In all five eyes with serologically confirmed syphilitic chorioretinitis, UWFAF revealed hyperautofluorescent white dots and spots scattered in the fundus, a finding minimally apparent with fluorescein angiography. Two eyes did not show evidence of classic placoid lesions. The hyperautofluorescence resolved after standard neurosyphilis treatment with intravenous course of penicillin. Conclusions: The presence of dots and spots identified through UWFAF may indicate syphilitic chorioretinitis and support its classification as a white dot syndrome. Based on the presence of hyperautofluorescent placoid lesions in some but not all cases with dots and spots, this study highlights the utility of multimodal imaging, including the more recent availability of UWFAF, in diagnosing syphilitic chorioretinitis. Future research is needed to determine whether the dots and spots in syphilitic chorioretinitis represent direct spirochete infiltration or a secondary inflammatory response.

The role of cardiovascular multimodality imaging in the evaluation of Anderson-Fabry disease: from early diagnosis to therapy monitoring A clinical consensus statement of the ESC Working Group on Myocardial & Pericardial Diseases and the European Association of Cardiovascular Imaging of the ESC.

Anderson-Fabry disease (AFD) is a rare genetic disease with X-linked transmission characterized by a defect in the enzyme alpha-galactosidase A (alpha-GAL), which impairs glycosphingolipid metabolism and leads to an excessive storage of globotriaosylceramide (Gb3) within lysosomes. AFD involves renal, cardiac, vascular, and nervous systems and is mainly observed in male patients with onset in childhood, although cardiac manifestation is often shown in adults. AFD cardiomyopathy is caused by the accumulation of Gb3 within myocytes first showed by left ventricular (LV) hypertrophy and diastolic dysfunction, leading to restrictive cardiomyopathy and systolic heart failure with biventricular involvement. The diagnosis of AFD cardiomyopathy may be insidious in the first stages and requires accurate differential diagnosis with other cardiomyopathies with hypertrophic phenotype. However, it is fundamental to promptly initiate specific therapies that have shown promising results, particularly for early treatment. A careful integration between clinical evaluation, genetic tests, and cardiac imaging is required to diagnose AFD with cardiac involvement. Basic and advanced echocardiography, cardiac magnetic resonance, and nuclear imaging may offer pivotal information for early diagnosis (Central illustration) and the management of these patients is often limited to centres with high expertise in the field. This clinical consensus statement, developed by experts from the European Society of Cardiology (ESC) Working Group on Myocardial & Pericardial Diseases and the European Association of Cardiovascular Imaging of the ESC, aims to provide practical advice for all clinicians regarding the use of multimodality imaging to simplify the diagnostic evaluation, prognostic stratification, and management of cardiac involvement in AFD.

Diagnostic value and efficacy of multimodal magnetic resonance imaging in differentiating radiation necrosis from tumor recurrence in glioblastomas.

Distinguishing radiation necrosis (RN) from recurrent tumor (RT) in patients with gliomas treated with radiation therapy presents an important clinical dilemma. To evaluate the diagnostic performance of multiparametric magnetic resonance imaging (MRI) techniques in distinguishing RN from RT in patients with histologically confirmed glioma treated previously with radiotherapy and chemotherapy or without chemotherapy using a combination of dynamic susceptibility-weighted contrast-enhanced (DSC) perfusion MRI, diffusion tensor imaging (DTI), and MR spectroscopy (MRS). Patients with glioma who developed a new enhancing mass after standard treatment were retrospectively evaluated. Conventional MRI, DTI, DSC, and MRS were performed. The region of interest (ROI) was manually drawn in the enhancing lesions, peri-lesional white matter edema, and the contralateral normal-appearing white matter. Apparent diffusion coefficient (ADC), fractional anisotropy (FA), relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF), N-acetylaspartate (NAA), choline (Cho), creatine (Cr), NAA/Cr, Cho/NAA, and Cho/Cr were calculated. Two-tailed t-test and receiver operating characteristic (ROC) curve analysis were performed. In total, 34 patients with RT and 25 with RN met our inclusion criteria. FA, rCBF, rCBV, Cho/NAA, Cho/Cr were statistically significant between the two groups (P < 0.05). The sensitivity and specificity of FA, rCBF, rCBV, Cho/NAA, and Cho/Cr in the diagnosis of RT were 70.6%, 97.1%, 91.2%, 91.2%, and 82.4% and 64%, 100%, 100%, 96%, and 72% respectively. DTI, DSC, and MRS are of great value in the differential diagnosis of RN and RT of glioma. The diagnostic performance of DSC is better than DTI and MRS.

Signs of Cortical Inflammation in Migraine Measured with Quantitative Magnetic Resonance Imaging: A Registry for Migraine (REFORM) Study.

The involvement of cortical inflammation in migraine, particularly migraine with aura, has been a subject of considerable interest, but has proved challenging to demonstrate. We aimed to detect and characterize signs of cortical inflammation in adults with migraine using a novel, multimodal magnetic resonance imaging (MRI) technique. We used T2 mapping to measure water content/cellularity, T1 mapping to measure tissue microstructure integrity, and apparent diffusion coefficient (ADC) mapping to measure intra- or extracellular edema. We compared these values between participants with migraine (with and without aura) and healthy controls using general linear models adjusted for age and sex. Two hundred ninety-six adult participants with migraine and 155 age- and sex-matched healthy controls provided eligible imaging data. Among the participants with migraine, 103 had migraine with aura, 180 chronic migraine, and 88 were ictal during the scan. Participants with migraine had higher quantitative T2 (qT2) in the left occipital cortex than healthy controls (p < 0.0001). In migraine with aura, the higher qT2 was more widespread and located bilaterally in the occipital cortices, compared with controls (left, p < 0.0001; right p = 0.004). Post-hoc analysis revealed overlapping ADC elevations in migraine with aura compared with controls (p = 0.0069). Quantitative MRI changes compatible with cortical inflammation were detected in participants with migraine, and appeared driven by the subgroup with aura. Higher occipital qT2 in migraine with aura might represent either extracellular edema or accumulation of inflammatory microglia or astrocytes. These results support the importance of cortical inflammation in migraine pathophysiology, particularly in migraine with aura. ANN NEUROL 2025.

Understanding the Influence of Gd Deposition on the MPI and MRI Performance of Fe3O4 Nanoparticles for Multimodal Imaging Applications.

Fe3O4 core Gd shell nanoparticles are interesting candidates as multimodal MRI/MPI contrast agents/tracers that can potentially provide MPI signal from the magnetic iron component while still achieving positive MRI contrast from the Gd shell. However, a current challenge in synthesizing these NPs is controlling the uniformity of the Gd shell while maintaining the particle size. In this study, we show that by using thermal decomposition of mixed metal oleate precursors, the iron oxide nanoparticle core with Gd shell coating can be varied from 7% to 27% while maintaining a high level of control over the particle size, producing highly uniform particles of d = 13.5 nm. Iron oxide nanoparticles with moderate Gd coating have resulted in improved MPI signal and MRI relaxation compared with commercial tracers, indicating that iron oxide core Gd shell nanoparticles are effective materials for both MPI and MRI applications. These results demonstrate the ability to synthetically control both the amount of the Gd shell and the size of the core-shell iron oxide nanoparticles, which can be applied to other magnetic nanomaterials.

Super-resolution microscopy based on the inherent fluctuations of dye molecules

Fluorescence microscopy is a critical tool across various disciplines, from materials science to biomedical research, yet it is limited by the diffraction limit of resolution. Advanced super-resolution techniques such as localization microscopy and stimulated-emission-depletion microscopy often demand considerable resources. These methods depend heavily on elaborate sample-staining, complex optical systems, or prolonged acquisition periods, and their application in 3D and multicolor imaging presents significant experimental challenges. In the current work, we provide a complete demonstration of a widely accessible super-resolution imaging approach capable of 3D and multicolor imaging based on super-resolution optical fluctuation imaging (SOFI). We replace the confocal pinhole with an array of single-photon avalanche diodes and use the microsecond-scale fluctuations of dye molecules as a contrast mechanism. This contrast is transformed into a super-resolved image using a robust and deterministic algorithm. Our technique utilizes natural fluctuations inherent to organic dyes, thereby it does not require engineering of the blinking statistics. Our robust, versatile super-resolution method opens the way to next-generation multimodal imaging and facilitates on-demand super-resolution within a confocal architecture.

Application of Convolutional Neural Networks and Rolling Guidance Filter in Image Fusion for Detecting Brain Tumors

Medical image fusion is the technique of integrating images from several medical imaging modalities without causing any distortion or information loss. By preserving every feature in the fused image, it increases the value of medical imaging for the diagnosis and treatment of medical conditions. A novel fusion mechanism for multimodal image data sets is proposed in this paper. Each of the source image is smoothened using cross guided filter in the initial step. Guided filter output is further smoothened to remove fine structures using rolling guidance filter. Then details (high frequency) of each source image are extracted by subtracting the rolling guidance filter output from corresponding source image. These details are fed to convolutional neural networks to obtain decision maps. Finally the source images are fused based on decision map using maximum rule of combination. We assessed the performance of our suggested methodology using several pairs of medical imaging datasets that are accessible to the general public. According to the quantitative evaluation, the recommended fusion strategy for multimodal image fusion improves the average IE by 12.4%, MI by 41.8%, SF by 21.4%, SD by 22.81%, MSSIM by 31.1%, and by 39% when compared to existing methods, which makes it appropriate for use in the medical field for accurate diagnosis.

Functional Deficits Associated with Dark Without Pressure.

To describe a patient with progressive visual symptoms and reduced retinal sensitivity corresponding to dark without pressure (DWP). Retrospective chart review of a single patient. Comprehensive ophthalmic examinations and multimodal imaging techniques, including optical coherence tomography (OCT), OCT-angiography, and microperimetry, were analyzed. A 23-year-old male presented with progressive peripheral areas of blurred vision superiorly in his right eye and temporally in his left eye. These disturbances corresponded with dark areas of retina inferiorly in his right eye and nasally in his left eye having characteristic features of DWP on multimodal imaging. Although Humphrey visual field (HVF) 24-2 testing was normal, microperimetry showed decreased retinal sensitivity in areas of DWP relative to adjacent areas without DWP. Prior descriptions of DWP have described it as a benign retinal finding showing no functional deficits. We demonstrate that DWP can be associated with progressive visual complaints showing decreased retinal sensitivity on microperimetry and undetected with HVF 24-2 testing.