Dual Imaging System Research Articles

Frugal engineering-inspired wearable augmented reality goggle system enables fluorescence-guided cancer surgery

Disparities in surgical outcomes often result from subjective decisions dictated by surgical training, experience, and available resources. To improve outcomes, surgeons have adopted advancements in robotics, endoscopy, and intra-operative imaging including fluorescence-guided surgery (FGS), which highlights tumors and anatomy in real-time. However, technical, economic, and logistic challenges hinder widespread adoption of FGS beyond high-resource centers. To overcome these impediments, we combined laser diodes, Raspberry Pi cameras and computers, off-the-shelf optical components, and 3D-printed parts to make a battery-powered, compact, dual white light and NIR imaging system that has comparable performance to existing bulkier, pricier, and wall-powered technologies. We combined these components with off-the-shelf augmented reality (AR) glasses to create a fully-wearable fluorescence imaging AR Raspberry Pi-based goggle system (FAR-Pi) and validated performance in a pre-clinical cancer surgery model. Novel device design ensures distance-independent coalignment between real and augmented views. As an open-source, affordable, and adaptable system, FAR-Pi is poised to democratize access to FGS and improve health outcomes worldwide.

An effective deep learning fusion method for predicting the TVB-N and TVC contents of chicken breasts using dual hyperspectral imaging systems

Total volatile basic nitrogen (TVB-N) and total viable count (TVC) are important freshness indicators of meat. Hyperspectral imaging combined with chemometrics has been proven to be effective in meat detection. However, a challenge with chemometrics is the lack of a universally applicable processing combination, requiring trial-and-error experiments with different datasets. This study proposes an end-to-end deep learning model, pyramid attention features fusion model (PAFFM), integrating CNN, attention mechanism and pyramid structure. PAFFM fuses the raw visible and near-infrared range (VNIR) and shortwave near-infrared range (SWIR) spectral data for predicting TVB-N and TVC in chicken breasts. Compared with the CNN and chemometric models, PAFFM obtains excellent results without a complicated processing combinatorial optimization process. Important wavelengths that contributed significantly to PAFFM performance are visualized and interpreted. This study offers valuable references and technical support for the market application of spectral detection, benefiting related research and practical fields.

Exploring natural genetic diversity in a bread wheat multi-founder population: Dual imaging of photosynthesis and stomatal kinetics.

A better understanding of crop phenotype under dynamic environmental conditions will help inform the development of new cultivars with superior adaptation to constantly changing field conditions. Recent research has shown that optimising photosynthetic and stomatal conductance traits holds promise for improved crop performance. However, standard phenotyping tools such as gas-exchange systems are limited by their throughput. In this work, a novel approach based on a bespoke gas-exchange chamber allowing combined measurement of the quantum yield of photosystem II (PSII) with an estimation of stomatal conductance via thermal imaging, was used to phenotype a range of bread wheat (Triticum aestivum L.) genotypes, that were a sub-set of a multi-founder experimental population. Datasets were further supplemented by measurement of photosynthetic capacity and stomatal density. First, we showed that measurement of stomatal traits using our dual imaging system compared to standard IRGA methods showed good agreement between the two methods (R2=0.86) for the rapidity of stomatal opening (Ki), with the dual-imager method resulting in less intra-genotype variation. Using the dual-imaging methods, and traditional approaches we found broad and significant variation in key traits, including photosynthetic CO2 uptake at saturating light and ambient CO2 concentration (Asat), photosynthetic CO2 uptake at saturating light and elevated CO2 concentration (Amax), the maximum velocity of Rubisco for carboxylation (Vcmax), time for stomatal opening (Ki), and leaf evaporative cooling. Anatomical analysis revealed significant variation in flag leaf adaxial stomatal density. Associations between traits highlighted significant relationships between leaf evaporative cooling, leaf stomatal conductance under low (gsmin) and high (gsmax) light intensity, and the operating efficiency of PSII (Fq'/Fm'), highlighting the importance of stomatal conductance and stomatal rapidity in maintaining optimal leaf temperature for photosynthesis in wheat. Additionally, gsmin and gsmax were positively associated, indicating that potential combination of preferable traits (i.e. inherently high gsmax, low Ki and maintained leaf evaporative cooling) are present in wheat. This work highlights for the first time the effectiveness of thermal imaging in screening dynamic stomatal conductance in a large panel of wheat genotypes. The wide phenotypic variation observed suggested the presence of exploitable genetic variability in bread wheat for dynamic stomatal conductance traits and photosynthetic capacity for targeted optimisation within future breeding programs.

Effect of different loads on facet joint motion during lumbar lateral bending in sitting position

ObjectiveTo study the effect of weight-bearing on lumbar facet joint during lateral bending in sitting position.MethodsTen normal healthy people (5 males and 5 females) aged 25–39 years (mean 32 ± 4.29 years) were recruited. CT scanning was used to reconstruct the lumbar spine model, and then dual fluoroscopic image system (DFIS) was used to restore the lumbar facet joint movement in sitting position. Finally, the lumbar facet joint translation distance and rotation angle were measured.ResultsIn L3-4 level, the displacement of right facet joint in Y-axis was the smallest at 0.05 ± 0.40 mm, the displacement of 0 kg left facet joint in X-axis was the largest at 1.68 ± 0.85 mm, and the rotation angle was − 0.57 ± 1.43° to 5.66 ± 2.70° at 10 kg; in L4-5 level, the displacement of right facet joint in Y-axis was the smallest at 10 kg, − 0.13 ± 0.91 mm, and the displacement of left facet joint in Z-axis was the largest at − 2.11 ± 0.88 mm, and the rotation angle was 0.21 ± 2.14° to 7.89 ± 2.59° at 10 kg; in L5-S1 level, the displacement of right facet joint in Y-axis was the smallest at 10 kg, − 0.17 ± 1.10 mm, and the displacement of 0 kg left facet joint in X-axis was the largest at 2.19 ± 2.28 mm, and the rotation angle was 0.03 ± 2.02° to 3.98 ± 0.37°.ConclusionIn sitting position, weight-bearing has certain influence on the displacement of facet joints during lumbar lateral bending movement, and this influence occurs simultaneously in translation and rotation; the left and right facet joints are not symmetrical during lumbar lateral bending movement.

Temperature-related Variations of 1064 nm Surface Reflectance on Mercury: Implications for Space Weathering

It has been predicted that high equatorial temperatures on Mercury could promote thermal annealing by Ostwald ripening, where nanophase metal particles (a product of space weathering) coalesce and grow into larger, microphase particles, resulting in lower albedo. Here, we test this prediction by studying the correlation between albedo and temperature in 1° spatial bins using newly recalibrated 1064 nm reflectance data acquired by the Mercury Laser Altimeter (MLA), low incidence angle data from the Mercury Dual Imaging System (MDIS), and newly modeled maximum surface temperatures (MSTs). Accounting for local geology and latitude, we compare the reflectance values of surfaces with MSTs >675 K (where Ostwald ripening is predicted to be most effective) to surfaces with MSTs <473 K (where ripening is predicted not to be effective). Smooth plain surfaces >675 K are 10% and 12% darker than surfaces <473 K in MLA and MDIS data, respectively, and nonsmooth plain surfaces >675 K are 8% and 7% darker than surfaces <473 K. However, open questions remain regarding the causation of this darkening; statistical tests cannot distinguish whether the reflectance differences are systematic or the result of compositional variations that happen to correlate with MST. Along Mercury’s thermal longitudes, we find that reflectance is typically lower along hot poles than along the 90°E cold pole in the low-to-midlatitudes, especially in the smooth plains, consistent with previous work identifying a decrease in optical maturity along the 90°E cold pole. Longitudinal reflectance variations correlate with temperature variations, rather than variations in micrometeoroid or solar wind fluxes.

Surface modification of Nd3+ activated gadolinium core-shell nanospheres for near-infrared and magnetic resonance dual functional bioimaging system

Visualization techniques are effective tools in diagnosis and therapy for biomedical applications. Due to the unavoidable shortcomings of single optical or magnetic resonance imaging, the introduction of dual functional imaging system is of great significance. Herein a new Gd1-xNdx(CO3)OH@SiO2 core–shell nanostructure were developed to fulfill the corresponding demands. Uniform nanospheres were acquired with surface modification and coated with thickness tunable silica shells. The samples presented strong luminescence penetrating biological tissue, due to the wide spectral region covering NIR I & II window of Nd3+ under 808 nm laser excitation. On the other hand, distinct contrast enhancement could be viewed for in vitro and in vivo MRI trials, which generates from high paramagnetic relaxation of Gd3+ and well dispersibility caused by silica shells. Along with the non-toxicity proved by the low concentration of leaching Gd3+ and nice biocompatibility of silica coated nanospheres, it is a superior candidate for NIR and MRI dual functional imaging platform in biological applications.

A hybrid geological map of Sibelius Crater on Mercury, and its associated ejecta and impact melt deposits

Abstract Using MESSENGER Mercury Dual Imaging System data, we produced three new maps of Sibelius Crater, Mercury. Geomorphological and spectral maps were combined into a single hybrid map containing units associated with ejecta deposits, crater floor landforms and impact melt ponding. Spatial measurement of these units shows that ∼50% of the mapped melt pond area lies within a large, degraded impact crater (crater B), beyond the significantly lower northern Sibelius rim, with a potential melt flow to a smaller, degraded impact structure further north (crater C). Freshly processed spectral data from the eight-colour Map Projected Multispectral Reduced Data Record data highlight the emplacement of multiple uplifted ejecta units with distinct spectral properties. A new, high-resolution digital elevation model was created to help define and analyse crater floor uplift features and disrupted crater rims and to create detailed cross-sections. These illustrate a proposed location of B's central uplift structure exposed in the northern wall slopes of Sibelius. Small features at the limit of visibility, such as a groove possibly associated with a rolling or sliding mega-boulder and lobate melt flow on the crater floor with accompanying channel opening, are highlighted for future investigations by BepiColombo's instruments once it reaches orbit.

Investigation of Characteristic Motion Patterns of the Knee Joint During a Weightbearing Flexion.

This study aimed to develop and validate a novel flexion axis concept by calculating the points on femoral condyles that could maintain constant heights during knee flexion. Twenty-two knees of 22 healthy subjects were investigated when performing a weightbearing single leg lunge. The knee positions were captured using a validated dual fluoroscopic image system. The points on sagittal planes of the femoral condyles that had minimal changes in heights from the tibial plane along the flexion path were calculated. It was found that the points do formulate a medial-lateral flexion axis that was defined as the iso-height axis (IHA). The six degrees of freedom (6DOF) kinematics data calculated using the IHA were compared with those calculated using the conventional transepicondylar axis and geometrical center axis. The IHA measured minimal changes in proximal-distal translations and varus-valgus rotations along the flexion path, indicating that the IHA may have interesting clinical implications. Therefore, identifying the IHA could provide an alternative physiological reference for improvement of contemporary knee surgeries, such as ligament reconstruction and knee replacement surgeries that are aimed to reproduce normal knee kinematics and medial/lateral soft tissue tensions during knee flexion.

Investigating the Stability and Distribution of Surface Ice in Mercury’s Northernmost Craters

Observations made by Earth-based radar telescopes and the MErcury Surface, Space ENvironment, GEochemistry, and Ranging (MESSENGER) spacecraft provided compelling evidence for water ice in Mercury's polar craters. In our investigation, we constructed higher-resolution (125 m pixel−1) digital elevation models (DEMs) for four of the largest northernmost craters, Kandinsky, Tolkien, Chesterton, and Tryggvadóttir. The DEMs were leveraged to model solar illumination and the thermal environment, products that were used to identify permanently shadowed regions and simulate surface temperatures. From these models, we predicted the regions of surface stability for ice and volatile organic compounds. These predictions were then compared against the Arecibo radar, Mercury Laser Altimeter (MLA), and Mercury Dual Imaging System (MDIS) data. Our radar analysis shows that areas of high radar backscatter are correlated with areas predicted to host surface ice. Additionally, we identify radar backscatter heterogeneities within the deposits that could be associated with variations in ice purity, mantling of the ice, or ice abundances. The MDIS analysis did not reveal conclusive evidence for ice or volatiles at the surface, while MLA results support the presence of water ice at the surface in these craters. However, evidence for boundaries between the surface ice and low-reflectance volatile organic compounds, as suggested could be present by our models, was inconclusive owing to the limited MESSENGER data in these regions. BepiColombo’s upcoming orbital mission at Mercury has the opportunity to obtain new measurements of these high-latitude craters and test our predictions for the distribution of surface volatiles in these environments.

Photoacoustic Spectral Analysis for Evaluating the Aggressiveness of Prostate Cancer Labeled by Methylene Blue Polyacrylamide Nanoparticles.

Evaluating the aggressiveness of prostate cancer (PCa) is crucial for PCa diagnosis and prognosis. Previously, studies have shown that photoacoustic spectral analysis (PASA) can assess prostate tissue microarchitecture for evaluating the aggressiveness of PCa. In this study, in a transgenic mouse (TRAMP) model of PCa, we utilized methylene blue polyacrylamide nanoparticles (MB PAA NPs) to label the cancer cells in prostate in vivo. MB PAA NPs can specifically target proliferating cancer cells as a contrast agent, allowing photoacoustic (PA) imaging to better detect PCa tumors, and also assessing prostate glandular architecture. With the PA signals from the prostates measured simultaneously by a needle hydrophone and a PA and ultrasound (US) dual-imaging system, we conducted PASA and correlated the quantified spectral parameter slopes with the cancer grading from histopathology. The PASA results from 18 mice showed significant differences between normal and cancer, and also between low-score cancer and high-score cancer. This study in the clinically relevant TRAMP model of PCa demonstrated that PA imaging and PASA, powered by MB PAA NPs that can label the PCa microarchitectures in vivo after systemic administration, can detect PCa and, more importantly, evaluate cancer aggressiveness.

Dual-wavelength real-time simultaneous phase imaging based on off-axis interferometry

Dual-wavelength interferometry is widely used in optical measurement, including the of great significance phase imaging of transparent samples. Here, we present a dual wavelength real-time phase imaging system based on off-axis interferometry with two cameras for recording complex fields transmitted through transparent samples in a wide-field and non-intrusive manner. The method of phase unwrapping based on combing dual wavelength with Fourier transform was derived in detail. The advantage of the proposed system is, compared with single-shot dual wavelength holograms methods, that it can easily extract the complex fields at both wavelengths without consideration of spectrum overlap or needing extra optic device to create lateral shearing. For phase noise, we calculated and removed the phase signal without sample in Fourier domain, which can also ensure the measured phase accurately. Experimental results on standard sample (polystyrene microspheres) demonstrated the efficiency of this imaging system. Implementation in quantitative imaging of living cells showed the time of single-shot acquisition of samples was only 0.025s, which indicated that the system can be applied to real-time and label-free identification of phase objects.

Developing thermal infrared de-ghost and multi-level nested conglutinated segmentation algorithm for detection of rice seed setting rate

The seed setting rate (SSR) of rice is not only a key component of yield, but also an important parameter in rice phenotypic analysis. Fast and accurate detection of SSR is of great significance for yield prediction. The purpose of this research was to detect the SSR of rice quickly and automatically. A thermal infrared–visible light dual imaging system was built to obtain thermal infrared images and RGB images of rice grains. This paper proposed image registration method, thermal infrared de-ghost method and multi-layer nested conglutinated segmentation algorithm to detect SSR. Compared with the detection accuracy of three deep learning models (Faster RCNN 96.43%, SSD 81.84%, YOLO V3 96.75%) and image registration methods (80.83%), the highest SSR detection accuracy (97.66%) was achieved by fusing thermal infrared de-ghost and multi-layer nested conglutinated segmentation algorithm. This method has the advantages of simple structure, high efficiency and competitive results, and has great potential in detecting seed setting rate.

Highly Resolved Topography and Illumination at Mercury’s South Pole from MESSENGER MDIS NAC

Mercury’s south polar region is of particular interest since Arecibo radar measurements show many high-reflectance regions consistent with ice deposits. However, current elevation information in Mercury’s southern hemisphere is not sufficient to perform detailed modeling of the illumination and thermal conditions at these radar-bright locations and to constrain properties of the volatiles potentially residing there. In this work, we leverage previously existing elevation maps of Mercury’s surface from stereo-photogrammetry at 665 m pix−1, Mercury Dual Imaging System Narrow Angle Camera images, and Shape-from-Shading tools from the Ames Stereo Pipeline, to provide the first high-resolution topographic maps of the south pole with a resolution of 250 m pix−1 poleward of 75°S. We show that the increased resolution and level of detail provided by our new elevation model allow for a more realistic recovery of illumination conditions in Mercury’s south polar region, thus opening the way to future thermal analyses and for the characterization of potential ice and volatile deposits. We compare both the old and new topographic models to the Mercury Dual Imaging System Narrow Angle Camera images to show the higher level of fidelity with our products, and we assess the improved consistency of derived permanently shadowed regions with reflectance measurements by Arecibo’s antennas.

Preparation and quality control of a new porphyrin complex labeled with 45Ti for PET imaging

This study aims to produce and quality control of a new porphyrin complex labeled with 45Ti for PET imaging, so at the first step, the cross-section of 45Sc(p,n)45Ti was investigated by TALYS-1.6 and the optimal target thickness and theoretical yield were calculated by SRIM code. The purified 45Ti was labeled with the anticancer agent of tetrakis (pentafluorophenyl) porphyrin (TFPP). The radiochemical purity and the percentage of labeling were evaluated by radiation layer chromatography then the division coefficient of [45Ti]-TFPP was calculated. The dual coincidence imaging system was used for imaging 1 and 2 h after injection [45Ti]-TFPP to rats. Immediately after imaging, the mean percent injected dose per gram and specific activity of different tissues including blood, heart, lungs, stomach, liver, bone, kidney, spleen, intestine, muscle, feces, and skin were measured. The yield of 45Ti production was measured 468 MBq/μAh and the labeling rate was observed more than 98%. The highest activity was observed in the liver (%ID/g = 2.27%, 1 h) and spleen (2.2%, 1 h), respectively, because of the high lipophilic of 45Ti-TFPP. SPECT images showed a significant uptake of radiopharmaceuticals in the abdomen. The labeling rate of 45Ti-TFPP was high and this compound has the potential for clinical application in different ways than PSMA, it can be joined with photodynamic therapy (Severin et al., 2015).

Real-time mixed reality display of dual particle radiation detector data

Radiation source localization and characterization are challenging tasks that currently require complex analyses for interpretation. Mixed reality (MR) technologies are at the verge of wide scale adoption and can assist in the visualization of complex data. Herein, we demonstrate real-time visualization of gamma ray and neutron radiation detector data in MR using the Microsoft HoloLens 2 smart glasses, significantly reducing user interpretation burden. Radiation imaging systems typically use double-scatter events of gamma rays or fast neutrons to reconstruct the incidence directional information, thus enabling source localization. The calculated images and estimated ’hot spots’ are then often displayed in 2D angular space projections on screens. By combining a state-of-the-art dual particle imaging system with HoloLens 2, we propose to display the data directly to the user via the head-mounted MR smart glasses, presenting the directional information as an overlay to the user’s 3D visual experience. We describe an open source implementation using efficient data transfer, image calculation, and 3D engine. We thereby demonstrate for the first time a real-time user experience to display fast neutron or gamma ray images from various radioactive sources set around the detector. We also introduce an alternative source search mode for situations of low event rates using a neural network and simulation based training data to provide a fast estimation of the source’s angular direction. Using MR for radiation detection provides a more intuitive perception of radioactivity and can be applied in routine radiation monitoring, education & training, emergency scenarios, or inspections.

Intensity Modulated Radiotherapy on a Novel Ring Gantry-Based Linac with Integrated Dual PET-CT Imaging Systems: Dosimetric Plan Comparison and Initial Clinical Delivery Experience

<h3>Purpose/Objective(s)</h3> This study aims to report our initial clinical experience on using a new external-beam radiotherapy delivery system on a ring gantry with dual PET-CT imaging capabilities for IMRT treatments at different anatomical sites. The study also evaluates the system's plan quality compared to an existing ring gantry-based Linac. This new external-beam radiotherapy delivery system has the potential to be used for biology-guided radiotherapy. <h3>Materials/Methods</h3> We performed a single-institution retrospective review of patients treated on the machine since commissioning. The initial five patients treated to a thoracic site and five patients treated to a pelvic site were included in this study. The dose per fraction ranged from 1.8 to 3.0 Gy. The treatment plans for the machine used a 2-cm jaw size along the longitudinal direction and used the IMRT delivery mode. A 64-leaf binary MLC was used to modulate a flattening filter free 6-MV photon beam. A helical tomotherapy plan (HT plan) using a 2.5-cm jaw size was generated for each RFX plan to serve as the backup plan in clinical treatments. Dosimetric parameters used in institutional treatment protocols were compared between RFX plans and HT plans. Daily delivery records were reviewed, and actual beam-on time was compared between the two machine types. <h3>Results</h3> On average, 12 dosimetric parameters (range: 7 – 14) for critical organs and the primary PTV were used in each treatment plan as clinically relevant planning optimization parameters and were analyzed in this study. Among the critical organ dose parameters, 19 (22.4%) dosimetric parameters were lower by more than 10% in the study's plans compared to the HT plans, while 11 (12.9%) dosimetric parameters were higher by more than 10% in the study's plans compared to the HT plans. The other dosimetric parameters had less than 10% or no clinically relevant difference between the two plans. There was no statistically significant difference in integrated dose between the new machine and HT plans. All the plans were normalized so that the prescription dose covered 95% of the primary planning target volume (PTV). The average D_mean of the primary PTV were 103.5±1.1% and 102.6±0.8% of the prescription dose in the new external-beam radiotherapy delivery system and HT plans, respectively, and the average D(1%) of the primary PTV (dose covering the hottest 1% of the PTV) were 107.1±2.0% and 105.2%±1.6% in the new external-beam radiotherapy delivery system and HT plans, respectively (two-tailed p-value = 0.06 in the paired t-test). The beam-on time was not significantly different between the two machines. The average daily beam-on time was 438.8±151.2 seconds and 427.6±183.1 seconds with the new external-beam radiotherapy delivery system and HT systems, respectively (two-tailed p-value = 0.76 in the paired t-test). <h3>Conclusion</h3> Our initial clinical experience with the external-beam radiotherapy delivery system showed that image guided IMRT could be delivered to different anatomical sites with adequate clinical workflow efficiency. The new machine achieved clinically comparable treatment plan quality compared to helical tomotherapy. The beam-on time was comparable to that on helical tomotherapy.

Repeatability and Reproducibility of Radiomic Features Produced over Time by the Fan-Beam kV-CT on a Novel Ring Gantry-Based PET/CT Linear

<h3>Purpose/Objective(s)</h3> The RefleXion® X1 is a new external-beam radiotherapy delivery system on a ring gantry with dual imaging systems fan-beam kV-CT and PET. The imaging system has the potential to be used for cancer prognosis and treatment response assessment using the radiomic features obtained from daily treatment images. The scanning variability in radiomics features and the differences between scanning protocols must be evaluated to warrant the accuracy of the prediction model. This study aims to establish the technical validation of the repeatability and reproducibility of radiomic features produced by the X1 kV-CT. <h3>Materials/Methods</h3> The Credence Cartridge Radiomics phantom was scanned 10 times on the X1 system over a 3-month time frame using the two most frequently used scanning protocols: head/medium dose/fast couch and body/medium dose/slow couch. A cylindrical region of interest of 8.0cm in diameter x 1.5cm in thickness was contoured for each of the 6 cartridges. The 6 cartridges are each comprised of different materials using acrylonitrile butadiene styrene, acrylic beads, polyvinyl chloride, hemp seeds encased in polyurethane, shredded rubber and dense cork. These materials were chosen to produce a range of radiomics feature values. 66 radiomic features were extracted using a widely available, IBSI-compliant radiomics software package. Linear regression analysis was performed to evaluate the repeatability and reproducibility over time. T-test for the difference in the mean and F-test for the difference in standard deviation was used to compare the radiomics features between scanning techniques. <h3>Results</h3> There was no significant variation of radiomic features over time. Based on linear regression analysis between the radiomic features and number of elapsed days since the initial scan, the fitted coefficient was less than 0.05 for all the radiomic features (scaled so that the mean value was unity). There was no strong linear relationship between radiomic features and elapsed days (R2 <= 0.02 in all regression analysis results). As reported in other studies, a comparison of radiomic features within each of the six cartridges demonstrated that up to 38 of the 66 radiomic features showed statistically significant differences between the fast scan and the slow scan protocols (two-tailed p value < 0.05 in paired t-tests) and up to 25 radiomic features had statistically significant differences in standard deviations between the fast and slow scan protocols (p value < 0.05 in F-tests), indicating the necessity of using consistent scan protocols to monitor radiomic features throughout the treatment course accurately. <h3>Conclusion</h3> The clinically useful CT radiomic features produced by the X1 are reproducible over time, demonstrating its utility as a quantitative imaging platform. The CT radiomic features produced by the X1 vary significantly with the scanning protocols. Evaluating radiomics feature changes over time requires image acquisition using the same scanning protocol.

Quantitative tumor depth determination using dual wavelength excitation fluorescence.

Quantifying solid tumor margins with fluorescence-guided surgery approaches is a challenge, particularly when using near infrared (NIR) wavelengths due to increased penetration depths. An NIR dual wavelength excitation fluorescence (DWEF) approach was developed that capitalizes on the wavelength-dependent attenuation of light in tissue to determine fluorophore depth. A portable dual wavelength excitation fluorescence imaging system was built and tested in parallel with an NIR tumor-targeting fluorophore in tissue mimicking phantoms, chicken tissue, and in vivo mouse models of breast cancer. The system showed high accuracy in all experiments. The low cost and simplicity of this approach make it ideal for clinical use.

Damage detection of large concrete structure via dual imaging system and contrastive embedding

Regular surface damage detection of large concrete structures is one of the important measures to ensure their stableness and reliability. Recent advancements in computer vision and deep learning have been increasingly applied to the high-precision detection of concrete surface damage. However, most damage monitoring and localization methods are based on high-resolution images taken from close range, and the images usually contain tiny areas of actual structures. This paper proposes a contrastive embedding model to detect and localize damage on a wide range of concrete images. To achieve high-definition imaging of damage to the surface of large structures, a multifocus, and high-resolution imaging system is designed and employed. Furthermore, a concrete surface damage dataset containing 1006 detection areas and 45,375 images with seven types is constructed by manual annotation based on the obtained multiscale and multiresolution images. In addition, a contrastive embedding model based on a deep neural network is then modified, trained, and tested using the constructed dataset. To the best of our knowledge, this paper is the first to jointly use contrastive embedding to deal with damage monitoring and localization. Moreover, an evaluation framework based on sliding window iteration and nonmaximum suppression is proposed to verify the robustness and accuracy of the proposed contrastive embedding model. Experiments show that the best model achieves the classification accuracy of up to 94.84% and localization of 97.57%.

Field validation of deep learning based Point-of-Care device for early detection of oral malignant and potentially malignant disorders

Early detection of oral cancer in low-resource settings necessitates a Point-of-Care screening tool that empowers Frontline-Health-Workers (FHW). This study was conducted to validate the accuracy of Convolutional-Neural-Network (CNN) enabled m(mobile)-Health device deployed with FHWs for delineation of suspicious oral lesions (malignant/potentially-malignant disorders). The effectiveness of the device was tested in tertiary-care hospitals and low-resource settings in India. The subjects were screened independently, either by FHWs alone or along with specialists. All the subjects were also remotely evaluated by oral cancer specialist/s. The program screened 5025 subjects (Images: 32,128) with 95% (n = 4728) having telediagnosis. Among the 16% (n = 752) assessed by onsite specialists, 20% (n = 102) underwent biopsy. Simple and complex CNN were integrated into the mobile phone and cloud respectively. The onsite specialist diagnosis showed a high sensitivity (94%), when compared to histology, while telediagnosis showed high accuracy in comparison with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, however, when compared with telediagnosis, identified suspicious lesions with less sensitivity (60%). Phone integrated, CNN (MobileNet) accurately delineated lesions (n = 1416; sensitivity: 82%) and Cloud-based CNN (VGG19) had higher accuracy (sensitivity: 87%) with tele-diagnosis as reference standard. The results of the study suggest that an automated mHealth-enabled, dual-image system is a useful triaging tool and empowers FHWs for oral cancer screening in low-resource settings.