External Imaging Research Articles

Detection of damage caused by Nezara viridula on soybean using novel imaging approaches based on computed tomography and image color analysis.

Soybean (Glycine max L.) is an important leguminous plant, in which pests trigger significant damage every year. Important members of this community are insects with piercing-sucking mouthpart, especially the southern green stinkbug, Nezara viridula L.. This insect with its extraoral digestion causes visible alterations (morphological and color changes) in the seeds. We aimed to obtain precise information about the extent and nature of damage in soybeans caused by N. viridula using nondestructive imaging methods. Two infestation conditions were applied: one with controlled numbers of pests (six insects/15 pods) and another with naturally occurring pests (samples collected from the apical part of the plant and samples from whole plants). An intact control group was also included, resulting in four treatment groups. Seed samples were analyzed by computed tomography (CT) and image color analysis under laboratory conditions. According to our CT findings, the damage caused by N. viridula changed the radiodensity, volume, and shape (Solidity) of the soybean seeds during the pod-filling and maturing period. Radiodensity was significantly reduced in all three damaged categories compared to the intact sample; the mean radiodensity reduction range was 49-412 HU. The seed volume also decreased significantly (25%-80% decrease), with a threefold reduction for samples exposed to regulated damage compared to natural ones. The samples exposed to natural damage showed significant but minor reduction in solidity, while samples exposed to regulated damage showed a prominent decrease (~12%). Image color analysis showed that the damaged samples were well distinguishable, and the differences were statistically verifiable. The achieved data derived from our external and internal imaging approaches contribute to a better understanding of the internal chemical processes, and CT analysis helps to understand the alteration trends of the hidden structure of seeds caused by a pest. Our results can contribute to the development of a practically applicable system based on image analysis, which can identify lots damaged by insects.

DC-UNet: Looking for follicles in the ovarian ultrasound images

The auspicious initiation of human reproduction starts by releasing the ovum through ovulation within the ovary. Ceaseless monitoring of the female reproductive organs has now become essential for combating fertility-related issues and for successful assisted reproduction. Cases of infertility and demands for assisted reproduction in our modern liberated society are rapidly increasing. External or Transvaginal ultrasound imaging of the ovary provides us with vital information about the number, size, and position of the follicles in the ovary and their cumulative response to biological stimuli. Manual screening of thousands of USG images having lacs of follicles is an extremely strenuous job and prone to humane error. This paper propounded a new deep-learning architecture named Double Contraction-UNet (DC-UNet) which makes follicle segmentation fully automatic. This model restructured the U-Net architecture by introducing two contracting paths to segment the follicular object with higher accuracy. The model was trained and tested on approximately forty two thousand annotated ovarian 2D ultrasonography images extracted from USOVA3D Training Set 1. The proposed model outperforms the other U-Net-based state-of-the-art models when trained and tested on the same dataset. The proposed model has achieved an accuracy rate of 97.82%, a precision rate of 97.54%, a Recall value of 94.34%, an F1 Score of 95.91%, a Dice Score of 0.76, and a Jaccard Similarity Index of 0.59.

Rapid, low-cost exploration of nucleation rates in l-glutamic acid crystallization in pure media and the presence of polymers through novel parallel experimentation

Crystal nucleation is crucial in various fields of science and technology, ranging from materials synthesis to pharmaceutical production. Our research aims to determine the nucleation rates from parallel induction time measurement experiments followed by low-cost external bulk video imaging. Stirred conditions are applied, making our results industry-relevant where the crystallizers are also mixed. The L-Glutamic Acid-water system (L-GA/water) is used as a surrogate. The study is conducted through a series of parallel, small-scale stirred experiments that explore the effects of supersaturation, temperature, and polymer additives on nucleation rates. The methodology involves careful data collection through controlled experimental setup and analysis of induction time distributions that the stochastic nature of nucleation explains the induction time distribution. The discussion section interprets the findings within the context of the research question, highlighting the implications of varying temperature and supersaturation levels as two experimental parameters and polymers on crystal nucleation rates. The specific parameters of supersaturation and temperature dependencies are in the range of those reported in the literature, which validated the developed rapid nucleation rate measurement platform. Stepping outside of these established measurements, analyzing the influence of polymers with high potential in controlling particle size, shape, and polymorphism was touched as well. As an unexpected result, the nucleation rates appeared to depend not only on the chemical structure and amount of the polymer but also on the polymer solution preparation method. The remarkable influence of polymers on nucleation rates was shown that cannot be explained with the solubility altering effect of the polymers alone.

Conditional Knockouts of Interphotoreceptor Retinoid Binding Protein Suggest Two Independent Mechanisms for Retinal Degeneration and Myopia.

Interphotoreceptor retinoid-binding protein's (IRBP) role in eye growth and its involvement in cell homeostasis remain poorly understood. One hypothesis proposes early conditional deletion of the IRBP gene could lead to a myopic response with retinal degeneration, whereas late conditional deletion (after eye size is determined) could cause retinal degeneration without myopia. Here, we sought to understand if prior myopia was required for subsequent retinal degeneration in the absence of IRBP. This study investigates if any cell type or developmental stage is more important in myopia or retinal degeneration. IBRPfl/fl mice were bred with 5 Cre-driver lines: HRGP-Cre, Chx10-Cre, Rho-iCre75, HRGP-Cre Rho-iCre75, and Rx-Cre. Mice were analyzed for IRBP gene expression through digital droplet PCR (ddPCR). Young adult (P30) mice were tested for retinal degeneration and morphology using spectral-domain optical coherence tomography (SD-OCT) and hematoxylin and eosin (H&E) staining. Function was analyzed using electroretinograms (ERGs). Eye sizes and axial lengths were compared through external eye measurements and whole eye biometry. Across all outcome measures, when bred to IRBPfl/fl, HRGP-Cre and Chx10-Cre lines showed no differences from IRBPfl/fl alone. With the Rho-iCre75 line, small but significant reductions were seen in retinal thickness with SD-OCT imaging and postmortem H&E staining without increased axial length. Both the HRGP-Cre+Rho-iCre75 and the Rx-Cre lines showed significant decreases in retinal thickness and outer nuclear layer cell counts. Using external eye measurements and SD-OCT imaging, both lines showed an increase in eye size. Finally, function in both lines was roughly halved across scotopic, photopic, and flicker ERGs. Our studies support hypotheses that for both eye size determination and retinal homeostasis, there are two critical timing windows when IRBP must be expressed in rods or cones to prevent myopia (P7-P12) and degeneration (P21 and later). The rod-specific IRBP knockout (Rho-iCre75) showed significant retinal functional losses without myopia, indicating that the two phenotypes are independent. IRBP is needed for early development of photoreceptors and eye size, whereas Rho-iCre75 IRBPfl/fl knockout results in retinal degeneration without myopia.

A preliminary investigation of precise visualization, localization, and resection of pelvic lymph nodes in bladder cancer by using indocyanine green fluorescence-guided approach through intracutaneous dye injection into the lower limbs and perineum.

This study aimed to investigate the feasibility and effectiveness of using indocyanine green (ICG) injected intracutaneously through the lower limbs and perineum for visualized tracking, localization, and qualitative assessment of pelvic lymph nodes (LNs) in bladder cancer to achieve their accurate resection. First, ICG was injected into the LN metastasis model mice lower limbs, and real-time and dynamic in vivo and ex vivo imaging was conducted by using a near-infrared fluorescence imaging system. Additionally, 26 patients with bladder cancer were enrolled and divided into intracutaneous group and transurethral group. A near-infrared fluorescence imaging device with internal and external imaging probes was used to perform real-time tracking, localization, and resection of the pelvic LNs. The mice normal LNs and the metastatic LNs exhibited fluorescence. The metastatic LNs showed a significantly higher signal-to-background ratio than the normal LNs (3.9 ± 0.2 vs. 2.0 ± 0.1, p < 0.05). In the intracutaneous group, the accuracy rate of fluorescent-labeled LNs was 97.6%, with an average of 11.3 ± 2.4 LNs resected per patient. Six positive LNs were detected in three patients (18.8%). In the transurethral group, the accuracy rate of fluorescent-labeled LNs was 84.4%, with an average of 8.6 ± 2.3 LNs resected per patient. Two positive LNs were detected in one patient (12.5%). Following the intracutaneous injection of ICG into the lower limbs and perineum, the dye accumulates in pelvic LNs through lymphatic reflux. By using near-infrared fluorescence laparoscopic fusion imaging, physicians can perform real-time tracking, localization, and precise resection of pelvic LNs.

A novel hybrid-view technique for accurate mass estimation of kimchi cabbage using computer vision

This study addresses the accurate estimation of kimchi cabbage mass, as cabbage leaves exhibit size variability and complex leaf structures. Conventional mass estimation methods, which rely solely on external imaging, often overlook leaf gaps. To improve accuracy, we propose an innovative computer vision system utilizing hybrid-view images and detailed saturation analysis. Our system quantifies the impact of leaf gaps on mass using features from the saturation channel of images of bisected cabbage. Our proposed method can be easily integrated into existing workflows and has the potential to improve labor efficiency. Our approach outperforms the conventional method (R2 of 0.66 and relative error of 8.68%), achieving a 0.92 R2 value and lowering the relative error to 4.22%. This advancement offers a robust solution for the mass estimation of kimchi cabbage and suggests potential applications for other foods and crops with internal voids.

Continuous Shear Wave Elastography for Liver Using Frame-to-Frame Equalization of Complex Amplitude.

This study addresses a crucial necessity in the field of noninvasive liver fibrosis diagnosis by introducing the concept of continuous shear wave elastography (C-SWE), utilizing an external vibration source and color Doppler imaging. However, an application of C-SWE to assess liver elasticity, a deep region within the human body, arises an issue of signal instability in the obtained data. To tackle this challenge, this work proposes a method involving the acquisition of multiple frames of datasets, which are subsequently compressed. Furthermore, the proposed frame-to-frame equalization method compensates discrepancies in the initial phase that might exist among multiple-frame datasets, thereby significantly enhancing signal stability. The experimental validation of this approach encompasses both phantom tests and in vivo experiments. In the phantom tests, the proposed technique is validated through a comparison with the established shear wave elastography (SWE) technique. The results demonstrate a remarkable agreement, with an error in shear wave velocity of less than 4.2%. Additionally, the efficacy of the proposed method is confirmed through in vivo tests. As a result, the stabilization of observed shear waves using the frame-to-frame equalization technique exhibits promising potential for accurately assessing human liver elasticity. These findings collectively underscore the viability of C-SWE as a potential diagnostic instrument for liver fibrosis.

Radiomics and machine learning for renal tumor subtype assessment using multiphase computed tomography in a multicenter setting

ObjectivesTo distinguish histological subtypes of renal tumors using radiomic features and machine learning (ML) based on multiphase computed tomography (CT).Material and methodsPatients who underwent surgical treatment for renal tumors at two tertiary centers from 2012 to 2022 were included retrospectively. Preoperative arterial (corticomedullary) and venous (nephrogenic) phase CT scans from these centers, as well as from external imaging facilities, were manually segmented, and standardized radiomic features were extracted. Following preprocessing and addressing the class imbalance, a ML algorithm based on extreme gradient boosting trees (XGB) was employed to predict renal tumor subtypes using 10-fold cross-validation. The evaluation was conducted using the multiclass area under the receiver operating characteristic curve (AUC). Algorithms were trained on data from one center and independently tested on data from the other center.ResultsThe training cohort comprised n = 297 patients (64.3% clear cell renal cell cancer [RCC], 13.5% papillary renal cell carcinoma (pRCC), 7.4% chromophobe RCC, 9.4% oncocytomas, and 5.4% angiomyolipomas (AML)), and the testing cohort n = 121 patients (56.2%/16.5%/3.3%/21.5%/2.5%).The XGB algorithm demonstrated a diagnostic performance of AUC = 0.81/0.64/0.8 for venous/arterial/combined contrast phase CT in the training cohort, and AUC = 0.75/0.67/0.75 in the independent testing cohort. In pairwise comparisons, the lowest diagnostic accuracy was evident for the identification of oncocytomas (AUC = 0.57–0.69), and the highest for the identification of AMLs (AUC = 0.9–0.94)ConclusionRadiomic feature analyses can distinguish renal tumor subtypes on routinely acquired CTs, with oncocytomas being the hardest subtype to identify.Clinical relevance statementRadiomic feature analyses yield robust results for renal tumor assessment on routine CTs. Although radiologists routinely rely on arterial phase CT for renal tumor assessment and operative planning, radiomic features derived from arterial phase did not improve the accuracy of renal tumor subtype identification in our cohort.

What is the added value of specialist radiology review of multidisciplinary team meeting cases in a tertiary care center?

PurposeMultidisciplinary team meetings (MDTMs) are an important component of the workload of radiologists. This study investigated how often subspecialized radiologists change patient management in MDTMs at a tertiary care institution.Materials and methodsOver 2 years, six subspecialty radiologists documented their contributions to MDTMs at a tertiary care center. Both in-house and external imaging examinations were discussed at the MDTMs. All imaging examinations (whether primary or second opinion) were interpreted and reported by subspecialty radiologist prior to the MDTMs. The management change ratio (MCratio) of the radiologist was defined as the number of cases in which the radiologist’s input in the MDTM changed patient management beyond the information that was already provided by the in-house (primary or second opinion) radiology report, as a proportion of the total number of cases whose imaging examinations were prepared for demonstration in the MDTM.ResultsSixty-eight MDTMs were included. The time required for preparing and attending all MDTMs (excluding imaging examinations that had not been reported yet) was 11,000 min, with a median of 172 min (IQR 113–200 min) per MDTM, and a median of 9 min (IQR 8–13 min) per patient. The radiologists’ input changed patient management in 113 out of 1138 cases, corresponding to an MCratio of 8.4%. The median MCratio per MDTM was 6% (IQR 0–17%).ConclusionRadiologists’ time investment in MDTMs is considerable relative to the small proportion of cases in which they influence patient management in the MDTM. The use of radiologists for MDTMs should therefore be improved.Clinical relevance statementThe use of radiologists for MDTMs (multidisciplinary team meetings) should be improved, because their time investment in MDTMs is considerable relative to the small proportion of cases in which they influence patient management in the MDTM.Key Points• Multidisciplinary team meetings (MDTMs) are an important component of the workload of radiologists.• In a tertiary care center in which all imaging examinations have already been interpreted and reported by subspecialized radiologists before the MDTM takes place, the median time investment of a radiologist for preparing and demonstrating one MDTM patient is 9 min.• In this setting, the radiologist changes patient management in only a minority of cases in the MDTM.

Motion compensated structured low-rank reconstruction for 3D multi-shot EPI.

The 3D multi-shot EPI imaging offers several benefits including higher SNR and high isotropic resolution compared to 2D single shot EPI. However, it suffers from shot-to-shot inconsistencies arising from physiologically induced phase variations and bulk motion. This work proposed a motion compensated structured low-rank (mcSLR) reconstruction method to address both issues for 3D multi-shot EPI. Structured low-rank reconstruction has been successfully used in previous work to deal with inter-shot phase variations for 3D multi-shot EPI imaging. It circumvents the estimation of phase variations by reconstructing an individual image for each phase state which are then sum-of-squares combined, exploiting their linear interdependency encoded in structured low-rank constraints. However, structured low-rank constraints become less effective in the presence of inter-shot motion, which corrupts image magnitude consistency and invalidates the linear relationship between shots. Thus, this work jointly models inter-shot phase variations and motion corruptions by incorporating rigid motion compensation for structured low-rank reconstruction, where motion estimates are obtained in a fully data-driven way without relying on external hardware or imaging navigators. Simulation and in vivo experiments at 7T have demonstrated that the mcSLR method can effectively reduce image artifacts and improve the robustness of 3D multi-shot EPI, outperforming existing methods which only address inter-shot phase variations or motion, but not both. The proposed mcSLR reconstruction compensates for rigid motion, and thus improves the validity of structured low-rank constraints, resulting in improved robustness of 3D multi-shot EPI to both inter-shot motion and phase variations.

Cortical Thin Patch Fraction Reflects Disease Burden in MS: The Mosaic Approach.

GM pathology plays an essential role in MS disability progression, emphasizing the importance of neuroradiologic biomarkers to capture the heterogeneity of cortical disease burden. This study aimed to assess the validity of a patch-wise, individual interpretation of cortical thickness data to identify GM pathology, the "mosaic approach," which was previously suggested as a biomarker for assessing and localizing atrophy. We investigated the mosaic approach in a cohort of 501 patients with MS with respect to 89 internal and 651 external controls. The resulting metric of the mosaic approach is the so-called thin patch fraction, which is an estimate of overall cortical disease burden per patient. We evaluated the mosaic approach with respect to the following: 1) discrimination between patients with MS and controls, 2) classification between different MS phenotypes, and 3) association with established biomarkers reflecting MS disease burden, using general linear modeling. The thin patch fraction varied significantly between patients with MS and healthy controls and discriminated among MS phenotypes. Furthermore, the thin patch fraction was associated with disease burden, including the Expanded Disability Status Scale, cognitive and fatigue scores, and lesion volume. This study demonstrates the validity of the mosaic approach as a neuroradiologic biomarker in MS. The output of the mosaic approach, namely the thin patch fraction, is a candidate biomarker for assessing and localizing cortical GM pathology. The mosaic approach can furthermore enhance the development of a personalized cortical MS biomarker, given that the thin patch fraction provides a feature on which artificial intelligence methods can be trained. Most important, we showed the validity of the mosaic approach when referencing data with respect to external control MR imaging repositories.

Near infrared imaging system for preventing blood vision obstruction in endoscopy.

Spinal endoscopy procedure is commonly used in the diagnosis and treatment of various health problems and is effective. Bleeding is one of the most common complications of spinal endoscopy procedures. Blood vision obstruction (BVO), that is, obstruction of the endoscopic camera lens caused by the accumulation of blood in the surgical field, is a serious problem in endoscopic procedures. This study presents what we believe to be a new approach to addressing BVO with external multispectral imaging. The study was completed using a BVO simulation model, and the results reveal that this technology can be used to effectively overcome BVO and provide clear images of the anatomy, enabling more effective diagnosis and treatment. This technique may enable improvement of the outcomes of endoscopic procedures and could have far-reaching implications in the field of endoscopy.

Performance comparison of external IBA and SR-XRF imaging for the study of ivory

The performances of Ion Beam Analysis (IBA) at the New AGLAE accelerator external microfocus beamline and those of Synchrotron Radiation micro-X-Ray Fluorescence (SR-XRF) at the PUMA beamline at the SOLEIL synchrotron are compared for non-invasive characterization of archaeological ivory. Based on the examination of ivory artefacts from the Palaeolithic siteHohle Felsin South-western Germany, the informative value of this combination of methods is evaluated with regard to archaeological questions. Parameters such as depth of information, elemental sensitivity as a function of atomic number and imaging capacity are considered. We obtain an almost complete coverage of the chemical composition of ivory (C to Pb). Rutherford Backscattering Spectrometry (RBS) allows the identification of collagen and PIXE/PIGE provide a higher sensitivity for light elements while SR-XRF offers high resolution imaging for heavier elements. Both facilities provide different depths of information that can be exploited to better distinguish exogenous and endogenous elements.

Experimenting ‘In Vivo’ with Dynamic Glottal Parameters: Methodological Issues, Technical Tips &amp; Tricks and Preventable Pitfalls

‘In vivo’ studies pertaining to dynamics of vocal fold vibration motion, to vocal fold contact and collision, to vocal onset and offset and to mechanical efficiency all need valid, sensitive and precise measurements of the different mechanical parameters involved. This is also true for investigating the physiological correlates of particular acoustic events like register breaks or diplophonia. The main physical parameters involved are: vocal fold movement and shaping, particularly the velocity of tissue displacement, glottal area, tissue distortion, intraglottal pressure, transglottal air flow, vocal fold contact and collision stress, etc. This article presents a critical review of the instruments and techniques involved in the direct measurements of the glottal dimensions and movements, the transglottal airflow, the VF contact changes, the pressures and the sound acoustic pressure. In each case are analyzed the methodological aspects that are critical for validly calibrating and synchronizing these signals, and correcting them for time delays. Moreover, it is shown how new parameters, like vocal fold velocity, intraglottal pressure, vocal fold collision stress, can be inferred from these (raw or after differentiation) signals by combining them. Finally, the discussion focuses on weighing advantages and limitations of techniques for monitoring the glottal area, i.e. photometry and the high-speed imaging, the latter involving the relevance in this scope of future developments in endoscopic and external imaging techniques, and in image processing software. Our aim is to facilitate the work of future researchers by showing how to solve important technical pitfalls, how to apply the necessary corrective measures - and which ones - where needed, and how to get the most out of combinatorial measures.

Radiology E-Consults: Reinterpretation of Outside CT and MRI Exams to Improve Quality, Reduce Unneeded Imaging, and Lower Costs

ObjectiveAdvanced imaging examinations commonly uncover incidental findings. Without access to prior imaging that is external to their healthcare system, radiologists may struggle to assess the significance of these findings. This can lead to unnecessary imaging follow-up recommendations and management uncertainty. We created a program to facilitate outside advanced imaging reinterpretation in the context of both internal and external prior imaging, resulting in more complete and accurate follow-up recommendations. MethodsOur value-based care organization created a program to facilitate outside advanced imaging reinterpretation, including importing the outside examinations and reports into our PACS/RIS platform. A total of 222 of these reinterpretations were performed between November 2020 and June 2022. In each case, a radiologist reinterpreted the entire examination and placed an official report into the electronic medical record, comparing their conclusions and recommendations with those of the outside imaging report. The reinterpretation report included a trackable code for future data mining purposes. ResultsThese E-consults seamlessly fitted into a radiologist's normal workflow and resulted in revenue generation as well as wRVU credit. The E-consults resulted in a change in management recommendations for approximately 46% of the overall number of cases. Approximately 37% of all examinations resulted in a recommendation of no further imaging required, or adjustment of the imaging modality/interval. DiscussionAn official radiology E-consult program can synthesize disparate sources of imaging data, transforming it into clear and documented recommendations which providers can use to improve patient safety and reduce unnecessary imaging and costs.

Kinematic Modeling of a Trepanation Surgical Robot System

This paper presents the concept of a parallel medical robotic service system to assist in a surgical procedure involving precise exploratory trepanation holes in a patient’s skull. The target position and orientation of the trepanation tool in the cranial region is determined using a prior intracranial image analysis using an external medical imaging system. A trepanning actuation system is attached to the end-effector of the parallel robot. The end-effector will act as an accurate positioner for the trepanning drill in the medical intervention area. The conceptual design of the mechanical actuation subsystem of a trepanning robot was developed in the SolidWorks 2022 software environment. The virtual model of the kinematic chain of the robot and the assumed design parameters were used to analytically derive the equations describing the inverse kinematics task. An analysis of the forward kinematics task of the parallel manipulator was also carried out using analytical and numerical methods. A workspace analysis was performed using Matlab based on the kinematic model of the parallel robot. This paper significantly advances the field by presenting the conceptual design of the actuation subsystem, deriving the kinematics equations, conducting a thorough workspace analysis, and establishing a foundation for subsequent control-algorithm development.

Self-sensing intelligent microrobots for noninvasive and wireless monitoring systems

Microrobots have garnered tremendous attention due to their small size, flexible movement, and potential for various in situ treatments. However, functional modification of microrobots has become crucial for their interaction with the environment, except for precise motion control. Here, a novel artificial intelligence (AI) microrobot is designed that can respond to changes in the external environment without an onboard energy supply and transmit signals wirelessly in real time. The AI microrobot can cooperate with external electromagnetic imaging equipment and enhance the local radiofrequency (RF) magnetic field to achieve a large penetration sensing depth and a high spatial resolution. The working ranges are determined by the structure of the sensor circuit, and the corresponding enhancement effect can be modulated by the conductivity and permittivity of the surrounding environment, reaching ~560 times at most. Under the control of an external magnetic field, the magnetic tail can actuate the microrobotic agent to move accurately, with great potential to realize in situ monitoring in different places in the human body, almost noninvasively, especially around potential diseases, which is of great significance for early disease discovery and accurate diagnosis. In addition, the compatible fabrication process can produce swarms of functional microrobots. The findings highlight the feasibility of the self-sensing AI microrobots for the development of in situ diagnosis or even treatment according to sensing signals.

Vehicle Target Recognition Method Based on Visible and Infrared Image Fusion Using Bayesian Inference

The accuracy of single-mode optical imaging systems for vehicle target recognition is limited by external ambient illumination or imaging equipment resolution. In this paper, a vehicle target recognition method based on visible and infrared image fusion using Bayesian inference is proposed. Based on the significance area detection combined with Spectral Residual (SR) and EdgeBox algorithms, the target area is marked on the visible light image, and the maximum between-class variance method and GrabCut algorithm are used to segment vehicle targets in marked images. The open operation filter is employed to extract the vehicle target features in the infrared image, and the fusion result of the visible light image and the infrared image is obtained by introducing the Intersection Over Union (IOU), and as the parameter of Bayesian inference, the class and attribute of the parameter are defined and substituted into the established naive Bayesian classification model, and the probability of the class is calculated to determine whether the vehicle target is recognized. Experiments under different test conditions were carried out, and the experimental results were as follows: the accuracy of image target recognition reached 77% when the vehicle target was not occluded; when the vehicle target was partially occluded, the accuracy of image target recognition reached 74%; the results verified that the proposed method can recognize vehicle targets in different scenarios.

Describing complex disease progression using joint latent class models for multivariate longitudinal markers and clinical endpoints.

Neurodegenerative diseases are characterized by numerous markers of progression and clinical endpoints. For instance, multiple system atrophy (MSA), a rare neurodegenerative synucleinopathy, is characterized by various combinations of progressive autonomic failure and motor dysfunction, and a very poor prognosis. Describing the progression of such complex and multi-dimensional diseases is particularly difficult. One has to simultaneously account for the assessment of multivariate markers over time, the occurrence of clinical endpoints, and a highly suspected heterogeneity between patients. Yet, such description is crucial for understanding the natural history of the disease, staging patients diagnosed with the disease, unravelling subphenotypes, and predicting the prognosis. Through the example of MSA progression, we show how a latent class approach modeling multiple repeated markers and clinical endpoints can help describe complex disease progression and identify subphenotypes for exploring new pathological hypotheses. The proposed joint latent class model includes class-specific multivariate mixed models to handle multivariate repeated biomarkers possibly summarized into latent dimensions and class-and-cause-specific proportional hazard models to handle time-to-event data. Maximum likelihood estimation procedure, validated through simulations is available in the lcmm R package. In the French MSA cohort comprising data of 598 patients during up to 13 years, five subphenotypes of MSA were identified that differ by the sequence and shape of biomarkers degradation, and the associated risk of death. In posterior analyses, the five subphenotypes were used to explore the association between clinical progression and external imaging and fluid biomarkers, while properly accounting for the uncertainty in the subphenotypes membership.

Efficiency of non-operative management for pectus deformities in children using an X-ray-free protocol.

To explore the correlation between the Haller index (HI), the external depth of protrusion, and the external Haller index (EHI) for both pectus excavatum (PE) and carinatum (PC). To assess the variation of the HI during this first year of non-operative treatment for pectus deformities in children. From January 2018 to December 2022, all children treated for PE by vacuum bell and for PC by compression therapy at our institution were evaluated by external gauge, 3D scanning (iPad with Structure Sensor and Captevia-Rodin4D), and magnetic resonance imaging (MRI). The main objectives were to assess the effectiveness of the treatment during the first year and to compare the HI determined by MRI to the EHI evaluated with 3D scanning and external measurements. The HI determined by MRI was compared to the EHI evaluated with 3D scanning and external measurements at M0 and M12. 118 patients (80 PE and 38 PC) had been referred for pectus deformity. Of these, 79 met the inclusion criteria (median age 13.7 years, 8.6-17.8). There was a statistically significant difference in the external measurements of the depth for PE between M0 and M12: 23.0 mm ± 7.2 vs 13.8 mm ± 6.1, respectively; p < 0.05 and for PC 31.1 mm ± 10.6 vs 16.7 mm ± 8.9, respectively; p < 0.01. During this first year of treatment, the reduction in the external measurement increased more rapidly for PE compared with PC. We found a strong correlation between the HI by MRI and the EHI by 3D scanning for PE (Pearson coefficient = 0.910, p < 0.001) and for PC (Pearson coefficient = 0.934, p < 0.001). A correlation between the EHI by 3D scanning and the external measurements by profile gauge was found for PE (Pearson coefficient = 0.663, p < 0.001) but not for PC. Excellent results were observed as soon as the sixth month for both PE and PC. Measurement of protrusion is a reliable monitoring tool at clinical consultation but caution is required for PC as it does not appear to be correlated to the HI by MRI.