Multi-vehicle adaptive 3D mapping for targeted ocean sampling.

Expanding spatial presentation from two-dimensional profile transects to three-dimensional ocean mapping is key for a better understanding of ocean processes. Phytoplankton distributions can be highly patchy and the accurate identification of these patches with the context, variability, and uncertainty of measurements on relevant scales is difficult to achieve. Traditional sampling methods, such as plankton nets, water samplers and in-situ vertical sensors, provide a snapshot and often miss the fine-scale horizontal and temporal variability. Here, we show how two autonomous underwater vehicles measured, adapted to, and reported real-time chlorophyll a measurements, giving insights into the spatiotemporal distribution of phytoplankton biomass and patchiness. To gain the maximum available information within their sensing scope, the vehicles moved in an adaptive fashion, looking for the regions of the highest predicted chlorophyll a concentration, the greatest uncertainty, and the least possibility of collision with other underwater vehicles and ships. The vehicles collaborated by exchanging data with each other and operators via satellite, using a common segmentation of the area to maximize information exchange over the limited bandwidth of the satellite. Importantly, the use of multiple autonomous underwater vehicles reporting real-time data combined with targeted sampling can provide better match with sampling towards understanding of plankton patchiness and ocean processes.

Whole-body magnetic resonance imaging at 0.05 Tesla.

Despite a half-century of advancements, global magnetic resonance imaging (MRI) accessibility remains limited and uneven, hindering its full potential in health care. Initially, MRI development focused on low fields around 0.05 Tesla, but progress halted after the introduction of the 1.5 Tesla whole-body superconducting scanner in 1983. Using a permanent 0.05 Tesla magnet and deep learning for electromagnetic interference elimination, we developed a whole-body scanner that operates using a standard wall power outlet and without radiofrequency and magnetic shielding. We demonstrated its wide-ranging applicability for imaging various anatomical structures. Furthermore, we developed three-dimensional deep learning reconstruction to boost image quality by harnessing extensive high-field MRI data. These advances pave the way for affordable deep learning-powered ultra-low-field MRI scanners, addressing unmet clinical needs in diverse health care settings worldwide.

High-confidence 3D template matching for cryo-electron tomography.

Visual proteomics attempts to build atlases of the molecular content of cells but the automated annotation of cryo electron tomograms remains challenging. Template matching (TM) and methods based on machine learning detect structural signatures of macromolecules. However, their applicability remains limited in terms of both the abundance and size of the molecular targets. Here we show that the performance of TM is greatly improved by using template-specific search parameter optimization and by including higher-resolution information. We establish a TM pipeline with systematically tuned parameters for the automated, objective and comprehensive identification of structures with confidence 10 to 100-fold above the noise level. We demonstrate high-fidelity and high-confidence localizations of nuclear pore complexes, vaults, ribosomes, proteasomes, fatty acid synthases, lipid membranes and microtubules, and individual subunits inside crowded eukaryotic cells. We provide software tools for the generic implementation of our method that is broadly applicable towards realizing visual proteomics.

Accurate object localization facilitates automatic esophagus segmentation in deep learning.

BACKGROUND: Currently, automatic esophagus segmentation remains a challenging task due to its small size, low contrast, and large shape variation. We aimed to improve the performance of esophagus segmentation in deep learning by applying a strategy that involves locating the object first and then performing the segmentation task. METHODS: A total of 100 cases with thoracic computed tomography scans from two publicly available datasets were used in this study. A modified CenterNet, an object location network, was employed to locate the center of the esophagus for each slice. Subsequently, the 3D U-net and 2D U-net_coarse models were trained to segment the esophagus based on the predicted object center. A 2D U-net_fine model was trained based on the updated object center according to the 3D U-net model. The dice similarity coefficient and the 95% Hausdorff distance were used as quantitative evaluation indexes for the delineation performance. The characteristics of the automatically delineated esophageal contours by the 2D U-net and 3D U-net models were summarized. Additionally, the impact of the accuracy of object localization on the delineation performance was analyzed. Finally, the delineation performance in different segments of the esophagus was also summarized. RESULTS: The mean dice coefficient of the 3D U-net, 2D U-net_coarse, and 2D U-net_fine models were 0.77, 0.81, and 0.82, respectively. The 95% Hausdorff distance for the above models was 6.55, 3.57, and 3.76, respectively. Compared with the 2D U-net, the 3D U-net has a lower incidence of delineating wrong objects and a higher incidence of missing objects. After using the fine object center, the average dice coefficient was improved by 5.5% in the cases with a dice coefficient less than 0.75, while that value was only 0.3% in the cases with a dice coefficient greater than 0.75. The dice coefficients were lower for the esophagus between the orifice of the inferior and the pulmonary bifurcation compared with the other regions. CONCLUSION: The 3D U-net model tended to delineate fewer incorrect objects but also miss more objects. Two-stage strategy with accurate object location could enhance the robustness of the segmentation model and significantly improve the esophageal delineation performance, especially for cases with poor delineation results.

Clinical Application of the 4K-3D Exoscope System in Cochlear Implantation.

PURPOSE: To evaluate a system for otomicrosurgery based on 4K three-dimensional (3D) exoscope technology and apply it to cochlear implantation. METHODS: An open stereoscopic vision-based surgical system, which differs from traditional surgical microscopes, was created by utilizing 4K stereo imaging technology and combining it with low-latency 4K ultra-high-definition 3D display. The system underwent evaluation based on 57 cochlear implantation operations, three designed microscopic manipulations, and a questionnaire survey. RESULTS: The surgical images displayed by the 4K-3D exoscope system (4K-3D-ES) are stereoscopic, clear, and smooth. The use of 4K-3D-ES in cochlear implantation is not inferior to traditional microscopes in terms of intraoperative bleeding and surgical complications, and the surgical duration is not slower or may even be faster than when using traditional microscopes. The results of micromanipulation experiments conducted on 16 students also confirmed this and demonstrated that 4K-3D-ES can be easily adapted. Furthermore, additional advantages of 4K-3D-ES were gathered. Significantly enlarged and high-definition stereoscopic images contribute to the visualization of finer anatomical microstructures such as chordae tympani, ensuring safer surgery. Users feel more comfortable in their necks, shoulders, waists, and backs. Real-time shared stereoscopic view for multiple people, convenient for collaboration and teaching. The ear endoscope and 4K-3D-ES enable seamless switching on the same screen. High-definition 3D images and videos can be saved with just one click, making future publication and communication convenient. CONCLUSION: The feasibility and safety of 4K-3D-ES for cochlear implantation surgery have been demonstrated. The 4K-3D-ES also offers numerous unique advantages and holds clinical application and promotional value.

Chondrosarcoma evaluation using hematein-based x-ray staining and high-resolution 3D micro-CT: a feasibility study.

BACKGROUND: Chondrosarcomas are rare malignant bone tumors diagnosed by analyzing radiological images and histology of tissue biopsies and evaluating features such as matrix calcification, cortical destruction, trabecular penetration, and tumor cell entrapment. METHODS: We retrospectively analyzed 16 cartilaginous tumor tissue samples from three patients (51-, 54-, and 70-year-old) diagnosed with a dedifferentiated chondrosarcoma at the femur, a moderately differentiated chondrosarcoma in the pelvis, and a predominantly moderately differentiated chondrosarcoma at the scapula, respectively. We combined a hematein-based x-ray staining with high-resolution three-dimensional (3D) microscopic x-ray computed tomography (micro-CT) for nondestructive 3D tumor assessment and tumor margin evaluation. RESULTS: We detected trabecular entrapment on 3D micro-CT images and followed bone destruction throughout the volume. In addition to staining cell nuclei, hematein-based staining also improved the visualization of the tumor matrix, allowing for the distinction between the tumor and the bone marrow cavity. The hematein-based staining did not interfere with further conventional histology. There was a 5.97 ± 7.17% difference between the relative tumor area measured using micro-CT and histopathology (p = 0.806) (Pearson correlation coefficient r = 0.92, p = 0.009). Signal intensity in the tumor matrix (4.85 ± 2.94) was significantly higher in the stained samples compared to the unstained counterparts (1.92 ± 0.11, p = 0.002). CONCLUSIONS: Using nondestructive 3D micro-CT, the simultaneous visualization of radiological and histopathological features is feasible. RELEVANCE STATEMENT: 3D micro-CT data supports modern radiological and histopathological investigations of human bone tumor specimens. It has the potential for being an integrative part of clinical preoperative diagnostics. KEY POINTS: • Matrix calcifications are a relevant diagnostic feature of bone tumors. • Micro-CT detects all clinically diagnostic relevant features of x-ray-stained chondrosarcoma. • Micro-CT has the potential to be an integrative part of clinical diagnostics.

Non-Cartesian 3D-SPARKLING vs Cartesian 3D-EPI encoding schemes for functional Magnetic Resonance Imaging at 7 Tesla.

The quest for higher spatial and/or temporal resolution in functional MRI (fMRI) while preserving a sufficient temporal signal-to-noise ratio (tSNR) has generated a tremendous amount of methodological contributions in the last decade ranging from Cartesian vs. non-Cartesian readouts, 2D vs. 3D acquisition strategies, parallel imaging and/or compressed sensing (CS) accelerations and simultaneous multi-slice acquisitions to cite a few. In this paper, we investigate the use of a finely tuned version of 3D-SPARKLING. This is a non-Cartesian CS-based acquisition technique for high spatial resolution whole-brain fMRI. We compare it to state-of-the-art Cartesian 3D-EPI during both a retinotopic mapping paradigm and resting-state acquisitions at 1mm3 (isotropic spatial resolution). This study involves six healthy volunteers and both acquisition sequences were run on each individual in a randomly-balanced order across subjects. The performances of both acquisition techniques are compared to each other in regards to tSNR, sensitivity to the BOLD effect and spatial specificity. Our findings reveal that 3D-SPARKLING has a higher tSNR than 3D-EPI, an improved sensitivity to detect the BOLD contrast in the gray matter, and an improved spatial specificity. Compared to 3D-EPI, 3D-SPARKLING yields, on average, 7% more activated voxels in the gray matter relative to the total number of activated voxels.

[Comparative evaluation of the accuracy of 3D TMJ analysis performed by different methods of processing computed tomograms]. / Sravnitel'naya otsenka tochnosti 3D-analiza elementov visochno-nizhnechelyustnogo sustava, vypolnennogo raznymi sposobami obrabotki komp'yuternykh tomogramm.

OBJECTIVE: The aim of this study. Comparison of the accuracy of segmentation of TMJ elements in different ways and assessment of the suitability of the data obtained for the diagnosis of TMJ dysfunction. MATERIALS AND METHODS: To study the segmentation of the bone elements of the TMJ (articular fossa, head of the LF), 60 computed tomograms of the maxillofacial region of patients were randomly selected in various ways (archival material). In group 1, the results of CT processing by AI diagnostics algorithms (Russia) were collected; in group 2, the results of CT processing based on the semi-automatic segmentation method in the Avantis3D program. The results of CT processing by Avantis3D AI algorithms (Russia) with different probability modes - 0.4 and 0.9, respectively, were selected for the third and fourth groups. Visually, the coincidence of the contours of the LF heads and articular pits isolated using different methods with their contours on all possible sections of the original CT itself was evaluated. The time spent on TMJ segmentation according to CT data was determined and compared using the methods described above. RESULTS: Of the 240 objects, only 7.5% of the cases showed a slight discrepancy between the contours of the original CT in group b1, which was the lowest of all. A slight discrepancy in the TMJ contours to be corrected is characteristic of the semi-automatic method of segmentation by optical density was detected in 50.4% (group 2). The largest percentage of significant errors not subject to correction was noted in the first group, which made it impossible to perform a full 3D analysis of the TMJ, and the smallest in the second and fourth. The magnitude of the error in determining the width of the articular gap in different groups is comparable to the size of one voxel per CT. When segmentation is carried out using AI, the difference between segmented objects is close to zero values. The average time spent on TMJ segmentation in group 1 was 10.2±1.23 seconds, in group 2 - 12.6±1.87 seconds, in groups 3 and 4 - 0.46±0.12 seconds and 0.46±0.13 seconds, respectively. CONCLUSION: The developed automated method for segmenting TMJ elements using AI is obviously more suitable for practical work, since it requires minimal time, and is almost as accurate as other methods under consideration.

Comparison of craniomaxillofacial morphology in children with unilateral cleft lip and palate treated with/without presurgical nasoalveolar molding - a retrospective study with a mean age of 5 years.

OBJECTIVES: To three-dimensionally assess differences in craniomaxillofacial skeletal development in patients with operated unilateral cleft lip and palate (UCLP) treated with/without presurgical nasoalveolar molding (PNAM) with a mean age of 5 years. MATERIALS AND METHODS: Cone-beam CT radiographs of 30 patients with UCLP who had undergone PNAM and 34 patients with UCLP who did not receive PNAM were analyzed. The data were stored in DICOM file format and were imported into the Dolphin Imaging program for 3D image reconstruction and landmark identification. 33 landmarks, 17 linear and three angular variables representing craniofacial morphology were analyzed and compared by using the Mann-Whitney U tests. RESULTS: The vast majority of linear variables and 3D coordinates of landmark points reflecting craniofacial skeletal symmetry were not significantly different between the two groups. In terms of craniofacial skeletal development, the PNAM group had a significantly smaller anterior nasal spine offset in the midsagittal plane and a greater maxillary length compared to the non-PNAM group. CONCLUSIONS: Evaluations performed in early childhood showed that treatment with/without PNAM in the neonatal period was not a major factor influencing craniomaxillofacial hard tissue development in patients with UCLP; moreover, PNAM treatment showed significant correction of skeletal deviation at the base of the nose. CLINICAL RELEVANCE: Follow-up in early childhood has shown that PNAM treatment administered during the neonatal stage does not impede maxillary development and has benefits in correcting nasal floor deviation. It is a viable option for improving nasal deformity in children with unilateral cleft lip and palate.

Enhancing Resilience in Biometric Research: Generation of 3D Synthetic Face Data Using Advanced 3D Character Creation Techniques from High-Fidelity Video Games and Animation.

Biometric authentication plays a vital role in various everyday applications with increasing demands for reliability and security. However, the use of real biometric data for research raises privacy concerns and data scarcity issues. A promising approach using synthetic biometric data to address the resulting unbalanced representation and bias, as well as the limited availability of diverse datasets for the development and evaluation of biometric systems, has emerged. Methods for a parameterized generation of highly realistic synthetic data are emerging and the necessary quality metrics to prove that synthetic data can compare to real data are open research tasks. The generation of 3D synthetic face data using game engines' capabilities of generating varied realistic virtual characters is explored as a possible alternative for generating synthetic face data while maintaining reproducibility and ground truth, as opposed to other creation methods. While synthetic data offer several benefits, including improved resilience against data privacy concerns, the limitations and challenges associated with their usage are addressed. Our work shows concurrent behavior in comparing semi-synthetic data as a digital representation of a real identity with their real datasets. Despite slight asymmetrical performance in comparison with a larger database of real samples, a promising performance in face data authentication is shown, which lays the foundation for further investigations with digital avatars and the creation and analysis of fully synthetic data. Future directions for improving synthetic biometric data generation and their impact on advancing biometrics research are discussed.

Subcranial Encephalic Temnograph-Shaped Helmet for Brain Stroke Monitoring.

In this contribution, a wearable microwave imaging system for real-time monitoring of brain stroke in the post-acute stage is described and validated. The system exploits multistatic/multifrequency (only 50 frequency samples) data collected via a low-cost and low-complexity architecture. Data are collected by an array of only 16 antennas moved by pneumatic system. Phantoms, built from ABS material and filled with appropriate Triton X-100-based mixtures to mimic the different head human tissues, are employed for the experiments. The microwave system exploits the differential scattering measures and the Incoherent MUSIC algorithm to provide a 3D image of the region under investigation. The shown results, although preliminary, confirm the potential of the proposed microwave system in providing reliable results, including for targets whose evolution is as small as 16 mL in volume.

Quantifying Inferior Vena Cava Compliance and Distensibility in an In Vivo Ovine Model Using 3D Angiography.

Synthetic vascular grafts overcome some challenges of allografts, autografts, and xenografts but are often more rigid and less compliant than the native vessel into which they are implanted. Compliance matching with the native vessel is emerging as a key property for graft success. The current gold standard for assessing vessel compliance involves the vessel's excision and ex vivo biaxial mechanical testing. We developed an in vivo method to assess venous compliance and distensibility that better reflects natural physiology and takes into consideration the impact of a pressure change caused by flowing blood and by any morphologic changes present. This method is designed as a survival procedure, facilitating longitudinal studies while potentially reducing the need for animal use. Our method involves injecting a 20 mL/kg saline bolus into the venous vasculature, followed by the acquisition of pre and post bolus 3D angiograms to observe alterations induced by the bolus, concurrently with intravascular pressure measurements in target regions. We are then able to measure the circumference and the cross-sectional area of the vessel pre and post bolus. With these data and the intravascular pressure, we are able to calculate the compliance and distensibility with specific equations. This method was used to compare the inferior vena cava's compliance and distensibility in native unoperated sheep to the conduit of sheep implanted with a long-term expanded polytetrafluorethylene (PTFE) graft. The native vessel was found to be more compliant and distensible than the PTFE graft at all measured locations. We conclude that this method safely provides in vivo measurements of vein compliance and distensibility.

A three-dimensional algorithm for precise measurement of human auricle parameters.

Measurement of auricle parameters for planning and post-operative evaluation presents substantial challenges due to the complex 3D structure of the human auricle. Traditional measurement methods rely on manual techniques, resulting in limited precision. This study introduces a novel automated surface-based three-dimensional measurement method for quantifying human auricle parameters. The method was applied to virtual auricles reconstructed from Computed Tomography (CT) scans of a cadaver head and subsequent measurement of important clinically relevant aesthetical auricular parameters (length, width, protrusion, position, auriculocephalic angle, and inclination angle). Reference measurements were done manually (using a caliper and using a 3D landmarking method) and measurement precision was compared to the automated method. The CT scans were performed using both a contemporary high-end and a low-end CT scanner. Scans were conducted at a standard scanning dose, and at half the dose. The automatic method demonstrated significantly higher precision in measuring auricle parameters compared to manual methods. Compared to traditional manual measurements, precision improved for auricle length (9×), width (5×), protrusion (5×), Auriculocephalic Angle (5-54×) and posteroanterior position (23×). Concerning parameters without comparison with a manual method, the precision level of supero-inferior position was 0.489 mm; and the precisions of the inclination angle measurements were 1.365 mm and 0.237 mm for the two automated methods investigated. Improved precision of measuring auricle parameters was associated with using the high-end scanner. A higher dose was only associated with a higher precision for the left auricle length. The findings of this study emphasize the advantage of automated surface-based auricle measurements, showcasing improved precision compared to traditional methods. This novel algorithm has the potential to enhance auricle reconstruction and other applications in plastic surgery, offering a promising avenue for future research and clinical application.

3D intraoral scanning techniques support the effects of crown morphology on dental caries.

BACKGROUND: With the development and utilization of three-dimensional (3D) intraoral scanning (IOS) technology, the morphological characteristics of teeth were quantitatively assessed. In this research, we aimed to explore the prevalence of dental caries in relation to each measurable morphological indicator of the tooth body via 3D intraoral scanning techniques. METHODS: A hospital-based single-centre study was conducted at our hospital from Dec. 2021 to Apr. 2023. A total of 53 patients were involved in the study, providing complete morphological data for 79 teeth. Each patient completed an oral hygiene routine questionnaire and underwent examination by an experienced dentist to evaluate caries conditions before undergoing 3D intraoral scanning to obtain a digital dental model. Geomagic Studio 2014 was used to extract oral morphological data from the models. The acquired data were entered, cleaned and edited using Excel 2016 and subsequently exported to SPSS version 25.0 for analysis. Chi-square analysis and logistic regression analyses were employed to test the associations. RESULTS: Among the participants, 33 (61.1%) were female, with a mean age of 26.52 ± 10.83 years. Significant associations were found between dental caries and the vertical distance between the distal tip and the gum (OR 14.02; 95% CI 1.80-109.07; P = 0.012), the distal lateral horizontal distance of occlusion (OR 0.40; 95% CI 0.18-0.90; P = 0.026), and the mesial horizontal distance of occlusion (OR 2.20; 95% CI 1.12-4.31; P = 0.021). The Hosmer-Lemeshow test indicated a P value of 0.33. CONCLUSIONS: The vertical distance between the distal tip and the gum, the distal lateral horizontal distance of the occlusion and the mesial horizontal distance of the occlusion were the influencing factors for dental caries (identified as independent risk factors). We hypothesize that these factors may be associated with the physiological curvature of teeth and the role of chewing grooves in plaque formation over time. However, further studies involving larger population samples and more detailed age stratification are still needed.

LEAPSE: Learning Environment Affordances for 3D Human Pose and Shape Estimation.

We live in a 3D world where people interact with each other in the environment. Learning 3D posed humans therefore requires us to perceive and interpret these interactions. This paper proposes LEAPSE, a novel method that learns salient instance affordances for estimating a posed body from a single RGB image in a non-parametric manner. Existing methods mostly ignore the environment and estimate the human body independently from the surroundings. We capture the influences of non-contact and contact instances on a posed body as an adequate representation of the "environment affordances". The proposed method learns the global relationships between 3D joints, body mesh vertices, and salient instances as environment affordances on the human body. LEAPSE achieved state-of-the-art results on the 3DPW dataset with many affordance instances, and also demonstrated excellent performance on Human3.6M dataset. We further demonstrate the benefit of our method by showing that the performance of existing weak models can be significantly improved when combined with our environment affordance module.

Clinical usability of 3D gradient-echo-based ultrashort echo time imaging: Is it enough to facilitate diagnostic decision in real-world practice?

BACKGROUND: With recent advances in magnetic resonance imaging (MRI) technology, the practical role of lung MRI is expanding despite the inherent challenges of the thorax. The purpose of our study was to evaluate the current status of the concurrent dephasing and excitation (CODE) ultrashort echo-time sequence and the T1-weighted volumetric interpolated breath-hold examination (VIBE) sequence in the evaluation of thoracic disease by comparing it with the gold standard computed tomography (CT). METHODS: Twenty-four patients with lung cancer and mediastinal masses underwent both CT and MRI including T1-weighted VIBE and CODE. For CODE images, data were acquired in free breathing and end-expiratory images were reconstructed using retrospective respiratory gating. All images were evaluated through qualitative and quantitative approaches regarding various anatomical structures and lesions (nodule, mediastinal mass, emphysema, reticulation, honeycombing, bronchiectasis, pleural plaque and lymphadenopathy) inside the thorax in terms of diagnostic performance in making specific decisions. RESULTS: Depiction of the lung parenchyma, mediastinal and pleural lesion was not significant different among the three modalities (p > 0.05). Intra-tumoral and peritumoral features of lung nodules were not significant different in the CT, VIBE or CODE images (p > 0.05). However, VIBE and CODE had significantly lower image quality and poorer depiction of airway, great vessels, and emphysema compared to CT (p < 0.05). Image quality of central airways and depiction of bronchi were significantly better in CODE than in VIBE (p < 0.001 and p = 0.005). In contrast, the depiction of the vasculature was better for VIBE than CODE images (p = 0.003). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were significant greater in VIBE than CODE except for SNRlung and SNRnodule (p < 0.05). CONCLUSIONS: Our study showed the potential of CODE and VIBE sequences in the evaluation of localized thoracic abnormalities including solid pulmonary nodules.

Evaluating the reliability of the lateral femoral condyle measuring methods by different modalities for patients with lateral patellar dislocation.

BACKGROUND: A variety of measurement methods and imaging modalities are in use to quantify the morphology of lateral femoral condyle (LFC), but the most reliable method remains elusive in patients with lateral patellar dislocation (LPD). The purpose of this study was to determine the intra- and inter-observer reliability of different measurement methods for evaluating the morphology of LFC on different imaging modalities in patients with LPD. METHODS: Seventy-three patients with LPD were included. Four parameters for quantifying the morphology of LFC were retrospectively measured by three observers on MRI, sagittal CT image, conventional radiograph (CR), and three-dimensional CT (3D-CT). The intra-class correlation coefficient was calculated to determine the intra- and inter-observer reliability. Bland-Altman analysis was conducted to identify the bias between observers. RESULTS: The lateral femoral condyle index (LFCI) showed better intra- and inter-observer reliability on MRI and 3D-CT than on CR and sagittal CT images. The mean difference in the LFCI between observers was lowest on 3D-CT (0.047), higher on MRI (0.053), and highest on sagittal CT images (0.062). The LFCI was associated with the lateral femoral condyle ratio (ρ = 0.422, P = 0.022), lateral condyle index (r = 0.413, P = 0.037), and lateral femoral condyle distance (r = 0.459, P = 0.014). The LFCI could be reliably measured by MRI and 3D-CT. CONCLUSION: The LFCI could be reliably measured by MRI and 3D-CT. The LFCI was associated with both the height and length of LFC and could serve as a comprehensive parameter for quantifying the morphology of LFC in patients with LPD.

Svetlana a supervised segmentation classifier for Napari.

We present Svetlana (SuperVised sEgmenTation cLAssifier for NapAri), an open-source Napari plugin dedicated to the manual or automatic classification of segmentation results. A few recent software tools have made it possible to automatically segment complex 2D and 3D objects such as cells in biology with unrivaled performance. However, the subsequent analysis of the results is oftentimes inaccessible to non-specialists. The Svetlana plugin aims at going one step further, by allowing end-users to label the segmented objects and to pick, train and run arbitrary neural network classifiers. The resulting network can then be used for the quantitative analysis of biophysical phenoma. We showcase its performance through challenging problems in 2D and 3D and provide a comprehensive discussion on its strengths and limits.

Deformable registration of magnetic resonance images using unsupervised deep learning in neuro-/radiation oncology.

PURPOSE: Accurate deformable registration of magnetic resonance imaging (MRI) scans containing pathologies is challenging due to changes in tissue appearance. In this paper, we developed a novel automated three-dimensional (3D) convolutional U-Net based deformable image registration (ConvUNet-DIR) method using unsupervised learning to establish correspondence between baseline pre-operative and follow-up MRI scans of patients with brain glioma. METHODS: This study involved multi-parametric brain MRI scans (T1, T1-contrast enhanced, T2, FLAIR) acquired at pre-operative and follow-up time for 160 patients diagnosed with glioma, representing the BraTS-Reg 2022 challenge dataset. ConvUNet-DIR, a deep learning-based deformable registration workflow using 3D U-Net style architecture as a core, was developed to establish correspondence between the MRI scans. The workflow consists of three components: (1) the U-Net learns features from pairs of MRI scans and estimates a mapping between them, (2) the grid generator computes the sampling grid based on the derived transformation parameters, and (3) the spatial transformation layer generates a warped image by applying the sampling operation using interpolation. A similarity measure was used as a loss function for the network with a regularization parameter limiting the deformation. The model was trained via unsupervised learning using pairs of MRI scans on a training data set (n = 102) and validated on a validation data set (n = 26) to assess its generalizability. Its performance was evaluated on a test set (n = 32) by computing the Dice score and structural similarity index (SSIM) quantitative metrics. The model's performance also was compared with the baseline state-of-the-art VoxelMorph (VM1 and VM2) learning-based algorithms. RESULTS: The ConvUNet-DIR model showed promising competency in performing accurate 3D deformable registration. It achieved a mean Dice score of 0.975 ± 0.003 and SSIM of 0.908 ± 0.011 on the test set (n = 32). Experimental results also demonstrated that ConvUNet-DIR outperformed the VoxelMorph algorithms concerning Dice (VM1: 0.969 ± 0.006 and VM2: 0.957 ± 0.008) and SSIM (VM1: 0.893 ± 0.012 and VM2: 0.857 ± 0.017) metrics. The time required to perform a registration for a pair of MRI scans is about 1 s on the CPU. CONCLUSIONS: The developed deep learning-based model can perform an end-to-end deformable registration of a pair of 3D MRI scans for glioma patients without human intervention. The model could provide accurate, efficient, and robust deformable registration without needing pre-alignment and labeling. It outperformed the state-of-the-art VoxelMorph learning-based deformable registration algorithms and other supervised/unsupervised deep learning-based methods reported in the literature.