Automatic segmentation of MRI in prospective breast volume evaluation: Comparison of different assessments for immediate breast reconstruction.

BACKGROUND: Assessment of breast volume is essential in preoperative planning of immediate breast reconstruction (IBR) surgery to achieve satisfactory cosmetic outcome. This study introduced a breast volume measurement tool that can be used to perform automatic segmentation of magnetic resonance images (MRI) and calculation of breast volume. We compared the accuracy and reliability of this measurement method with four other conventional modalities. METHODS: Patients who were scheduled to undergo mastectomy with IBR between 2016 and 2021 were enrolled in the study. Five different breast volume assessments, including automatic segmentation of MRI, manual segmentation of MRI, 3D surface imaging, mammography, and the BREAST-V formula, were used to evaluate different breast volumes. The results were validated using water displacement volumes of the mastectomy specimens. RESULTS: In this pilot study, a total of 50 female patients met the inclusion criteria and contributed 54 breast specimens to the volumetric analysis. There was a strong linear association between the MRI and water displacement methods (automatic segmentation: r = 0.911, p < 0.001; manual segmentation: r = 0.924, p < 0.001), followed by 3D surface imaging (r = 0.858, p < 0.001), mammography (r = 0.841, p < 0.001), and Breast-V formula (r = 0.838, p < 0.001). Breast volumes measured using automatic and manual segmentation of MRI had lower mean relative errors (30.3% ± 22.0% and 28.9% ± 19.8, respectively) than 3D surface imaging (38.9% ± 31.2), Breast-V formula (44.8% ± 25.8), and mammography (60.3% ± 37.6). CONCLUSION: Breast volume assessment using the MRI methods had better accuracy and reliability than the other methods used in our study. Breast volume measurement using automatic segmentation of MRI could be more efficient compared to the conventional methods.

Deep learning-based super-resolution of structural brain MRI at 1.5 T: application to quantitative volume measurement.

OBJECTIVE: This study investigated the feasibility of using deep learning-based super-resolution (DL-SR) technique on low-resolution (LR) images to generate high-resolution (HR) MR images with the aim of scan time reduction. The efficacy of DL-SR was also assessed through the application of brain volume measurement (BVM). MATERIALS AND METHODS: In vivo brain images acquired with 3D-T1W from various MRI scanners were utilized. For model training, LR images were generated by downsampling the original 1 mm-2 mm isotropic resolution images. Pairs of LR and HR images were used for training 3D residual dense net (RDN). For model testing, actual scanned 2 mm isotropic resolution 3D-T1W images with one-minute scan time were used. Normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were used for model evaluation. The evaluation also included brain volume measurement, with assessments of subcortical brain regions. RESULTS: The results showed that DL-SR model improved the quality of LR images compared with cubic interpolation, as indicated by NRMSE (24.22% vs 30.13%), PSNR (26.19 vs 24.65), and SSIM (0.96 vs 0.95). For volumetric assessments, there were no significant differences between DL-SR and actual HR images (p > 0.05, Pearson's correlation > 0.90) at seven subcortical regions. DISCUSSION: The combination of LR MRI and DL-SR enables addressing prolonged scan time in 3D MRI scans while providing sufficient image quality without affecting brain volume measurement.

Three-dimensional comprehensive evaluation of unilateral alveolar cleft bone grafting with iliac bone and chin bone blocks.

In this study, we aimed to provide guidance for selecting bone grafting materials in cases of alveolar clefts. Twenty-nine patients with unilateral complete alveolar clefts were categorized into three groups based on the bone grafting material used: Group A (iliac bone block grafts), Group B (iliac cancellous bone grafts), and Group C (chin bone block grafts). Cone-beam computed tomography (CBCT) data were analyzed using Mimics 19.0 software. Results showed that Group A had the highest bone formation rate, with significant differences observed between Groups A and B, as well as between Groups B and C. Group A and Group C had the highest proportion of Type I in volume assessment, while Group B had the highest proportion of Type III, Significant differences were observed in the distribution of volume assessment scores among the three groups. Bone height measurement results indicated that buccal-side measurement points had a higher proportion of Type I bone height than palatal-side measurement points. Bone width measurement results showed that Type I bone width was highest in Group C, while Type IV bone width was highest in Group B. Significant differences were observed in the distribution of implanted bone width among the three groups. Total grafting scores indicated that Types A and D were predominant in Groups A and C, while Group B had the highest proportion of Type D. Significant differences were observed in the distribution of total grafting scores among the three groups. The comprehensive evaluation method provides accurate assessment of alveolar cleft bone grafting outcomes and is applicable in clinical settings. Based on the results, we consider both iliac bone blocks and chin bone blocks as suitable materials for alveolar cleft bone grafting. Grafting material selection should consider preoperative gap volume measured using CBCT, required bone quantity, donor site complications, and overall clinical needs.

Insights into Orbital Symmetry: A Comprehensive Retrospective Study of 372 Computed Tomography Scans.

Background: The operation planning and production of individualized implants with the help of AI-based software after orbital fractures have become increasingly important in recent years. This retrospective study aimed to investigate the healthy orbitae of 372 patients from CT images in the bone and soft tissue windows using the Disior™ Bonelogic™ CMF Orbital software. (version 2.1.28). Methods: We analyzed the variables orbital volume, length, and area as a function of age and gender and compared bone and soft tissue windows. Results: For all variables, the intraclass correlation showed excellent agreement between the bone and soft tissue windows (p < 0.001). All variables showed higher values when calculated based on bone fenestration with, on average, 1 mL more volume, 0.35 mm more length, and 0.71 cm2 more area (p < 0.001). Across all age groups, men displayed higher values than women with, on average, 8.1 mL larger volume, a 4.78 mm longer orbit, and an 8.5 cm2 larger orbital area (p < 0.001). There was also a non-significant trend in all variables and both sexes toward growth with increasing age. Conclusions: These results mean that, due to the symmetry of the orbits in both the bone and soft tissue windows, the healthy orbit can be mirrored for surgical planning in the event of a fracture.

Characterization of different solid fuels from waste for an advanced online fuel control system designed for large-scale incineration plants.

Despite many years of experience in the incineration of solid fuels from waste, the heterogeneity of solid fuels and their varying properties still pose a challenge for a stable and clean combustion in large-scale incineration plants. In modern facilities such as municipal waste incineration plants there still exists a lack of knowledge on the exact amount and calorific value of waste entering onto the grate. Based on the works of Warnecke et al. and Zwiellehner et al., in our project 'AdOnFuelControl', we determined the initial bulk density at the feed hopper by measuring the weight of the waste via the crane weigher and the volume via a high-performance 3D laser scanner. With the help of the determined bulk density, the lower heating value (LHV) and the compression in the feed hopper were calculated. All this information was integrated into the combustion control system, which provided a high potential for an optimized operation of the plant. In this article, six different fuels (fresh and aged municipal solid waste, refuse-derived fuel (fluff), refuse-derived fuel (fine grain), waste wood and dried, grained sewage sludge) were examined for the elemental composition, the LHV, fuel-specific parameters and the compression behaviour. In addition, initial tests with the 3D laser scanner as well as formulas for the calculation of the density in the feed hopper were presented. Based on the results of the experiments, the chosen approach seems very promising for optimized combustion control in large-scale incineration plants. As a next step, the gained knowledge and technology should be integrated in the municipal waste incineration plant.

The International Association for the Study of Lung Cancer Early Lung Imaging Confederation Open-Source Deep Learning and Quantitative Measurement Initiative.

INTRODUCTION: With global adoption of computed tomography (CT) lung cancer screening, there is increasing interest to use artificial intelligence (AI) deep learning methods to improve the clinical management process. To enable AI research using an open-source, cloud-based, globally distributed, screening CT imaging data set and computational environment that are compliant with the most stringent international privacy regulations that also protect the intellectual properties of researchers, the International Association for the Study of Lung Cancer sponsored development of the Early Lung Imaging Confederation (ELIC) resource in 2018. The objective of this report is to describe the updated capabilities of ELIC and illustrate how this resource can be used for clinically relevant AI research. METHODS: In this second phase of the initiative, metadata and screening CT scans from two time points were collected from 100 screening participants in seven countries. An automated deep learning AI lung segmentation algorithm, automated quantitative emphysema metrics, and a quantitative lung nodule volume measurement algorithm were run on these scans. RESULTS: A total of 1394 CTs were collected from 697 participants. The LAV950 quantitative emphysema metric was found to be potentially useful in distinguishing lung cancer from benign cases using a combined slice thickness more than or equal to 2.5 mm. Lung nodule volume change measurements had better sensitivity and specificity for classifying malignant from benign lung nodules when applied to solid lung nodules from high-quality CT scans. CONCLUSIONS: These initial experiments revealed that ELIC can support deep learning AI and quantitative imaging analyses on diverse and globally distributed cloud-based data sets.

Diagnostic value of 3D volume measurement of central pulmonary artery based on CTPA images in the pulmonary hypertension.

BACKGROUND: This retrospective study aims to evaluate the diagnostic value of volume measurement of central pulmonary arteries using computer tomography pulmonary angiography (CTPA) for predicting pulmonary hypertension (PH). METHODS: A total of 59 patients in our hospital from November 2013 to April 2021 who underwent both right cardiac catheterization (RHC) and CTPA examination were included. Systolic pulmonary artery pressure (SPAP), mean PAP (mPAP), and diastolic PAP (DPAP) were acquired from RHC testing. Patients were divided into the non-PH group (18 cases) and the PH group (41 cases). The diameters of the main pulmonary artery (DMPA), right pulmonary artery (DRPA), and left pulmonary artery (DLPA) were measured manually. A 3D model software was used for the segmentation of central pulmonary arteries. The cross-sectional areas (AMPA, ARPA, ALPA) and the volumes (VMPA, VRPA, VLPA) were calculated. Measurements of the pulmonary arteries derived from CTPA images were compared between the two groups, and correlated with the parameters of RHC testing. ROC curves and decision curve analysis (DCA) were used to evaluate the benefit of the three-dimensional CTPA parameters for predicting PH. A multiple linear regression model with a forward-step approach was adopted to integrate all statistically significant CTPA parameters for PH prediction. RESULTS: All parameters (DMPA, DRPA, DLPA, AMPA, ARPA, ALPA, VMPA, VRPA, and VLPA) of CTPA images exhibited significantly elevated in the PH group in contrast to the non-PH group (P < 0.05), and showed positive correlations with the parameters of RHC testing (mPAP, DPAP, SPAP) (r ranged 0.586~0.752 for MPA, 0.527~0.640 for RPA, and 0.302~0.495 for LPA, all with P < 0.05). For the MPA and RPA, 3D parameters showed higher correlation coefficients compared to their one-dimensional and two-dimensional counterparts. The ROC analysis indicated that the VMPA showed higher area under the curves (AUC) than the DMPA and AMPA without significance, and the VRPA showed higher AUC than the DRPA and ARPA significantly (DRPA vs. VRPA, Z = 2.029, P = 0.042; ARPA vs. VRPA, Z = 2.119, P = 0.034). The DCA demonstrated that the three-dimensional parameters could provide great net benefit for MPA and RPA. The predictive equations for mPAP, DPAP, and SPAP were formulated as [8.178 + 0.0006 * VMPA], [1.418 + 0.0005 * VMPA], and [-11.137 + 0.0006*VRPA + 1.259 * DMPA], respectively. CONCLUSION: The 3D volume measurement of the MPA and RPA based on CTPA images maybe more informative than the traditional diameter and cross-sectional area in predicting PH.

Beyond Diameter: Enhancing Abdominal Aortic Aneurysm Surveillance with Volumetric Assessments after Endovascular Aneurysm Repair (EVAR).

This study aimed to investigate the relationship between maximum transverse diameter (MTD) and volume measurements in patients who underwent reoperations after endovascular aneurysm repair (EVAR), and their association with the occurrence of endoleaks. The study included 51 patients who underwent EVAR and subsequent re-operations caused by endoleaks type I-III. In some number of events, multiple re-operations were needed. MTD was measured using the Horos software, and segmentations of the AAA were performed using 3D Slicer. This study first evaluated post-operative computed tomography angiography (CTA) to measure MTD and volume. Then, similar measurements were made in the control scan for re-operation qualification. Negative remodeling (increase in MTD and/or volume) was observed in 40 cases using MTD, and 48 cases using volume measurements. The volume measurement showed lower missed negatives than MTD, indicating its effectiveness in screening for negative remodeling (p < 0.001). Combining both methods identified 51 negative remodeling cases and 8 positive changes, with a higher sensitivity compared to MTD alone. The volume of the sac did not predict specific endoleak types. Decreases in MTD were observed in smaller sacs, with smaller volume changes. Volume measurement is a valuable screening tool, and combining MTD and volume enhances sensitivity. However, sac volume does not predict endoleak type.

A novel approach to determining augmented bone volume in intraoral bone block augmentation using an intraoral scanner: an in vitro study.

INTRODUCTION: Bone augmentation procedures are established tools for reshaping the alveolar ridge and increasing bone volume. Different approaches are being used to measure postoperative bone volume gain. This study aimed to develop an objective and automated volume measurement tool equally as precise as manual slice-by-slice annotation. MATERIALS AND METHODS: To evaluate the proposed workflow, we performed an in vitro study with 20 pig mandibles that were grafted using three different grafting techniques-autogenous full block, split block bone and shell augmentation. The pig jaws were scanned pre- and postoperatively using an intraoral scanner. The resulting surface files (baseline, full block, split block, shell) were processed using the new volume-measuring workflow as well as using manual slice-by-slice annotation at baseline (t0) and at 6 months (t1) using the same population. Two TOSTs (Test of One-Sided Significance) and NHSTs (Null Hypothesis Significance Test) were used to compare the two workflows. The intra-rater reliability between t0 and t1 was determined using intraclass correlation coefficients. RESULTS: The mean difference for the full block augmentation technique was - 0.015 cm3 (p < 0.001); for the split block technique, it was - 0.034 cm3 p = 0.01, and for the shell technique, it was - 0.042 cm3. All results were statistically not different from zero and statistically equivalent to zero. The results also showed an excellent absolute intra-rater agreement. CONCLUSIONS: The semiautomatic volume measurement established in this article achieves comparable results to manual slice-by-slice measuring in determining volumes on STL files generated by intraoral scanners and shows an excellent intra-rater reliability.

[Creation of 3D Stereo and MPR Color Anatomical Charts in the Hepatic Segments].

We used the Voronoi diagram of a computed tomography (CT) application (i.e., CT liver volume measurement) to depict the liver area, and we obtained depictions of the hepatic segments as a three-dimensional (3D) image based on clinical data; this information can be used for the patient's education and for surgical planning. The hepatic segments use the inter-relationships among the eight subsegments illustrated by Couinaud, those indicated by the portal veins and those provided by hepatic veins. The liver has dual portal and arterial innervation, with the thick portal vein intertwined with thin arteries similar to the intertwining of ivy plants. Couinaud divided the liver into eight segments (S1 to S8) based on portal vein casts. The Voronoi diagram estimates the dominant region of the portal vein, divides the liver into segments, and produces 3D images and multiplanar reconstruction (MPR) images in color. To support understanding of Couinaud's eight hepatic segments (which are explained only in the illustration of the frontal view of the liver), using 3D images created by the Voronoi diagram, we created 3D stereo color anatomical charts of the liver that Couinaud's eight hepatic segments can be confirmed from multiple directions. In addition, we created the MPR color anatomical charts of the liver (S1 to S8) that can be confirmed by color from three directions: axial images, coronal images, and sagittal images in the same way. We converted the data of this anatomical chart into an electronic file that provides a tool that can be easily used in radiological examinations, and we were able to make improvements based on requests from users.

Measurement of Blood Volume in Patients with Heart Failure: Clinical Relevance, Surrogates, Historical Background and Contemporary Methodology.

The development of clinical congestion resulting from volume overload, either by renal fluid retention or redistribution of blood volume from venous reservoirs, is a recurrent scenario in patients with chronic heart failure (HF). As a result, the treatment of congestion, most commonly by initiating aggressive diuretic therapy, is a front-line issue in the management of patients with HF. However, the association of clinical congestion and volume overload with physical signs and symptoms, as well as other surrogates of volume assessment, has limitations in accuracy and, therefore, reliability to direct appropriate interventions. The ability to quantitate intravascular volume and identify the variability in volume profiles among patients with HF can uniquely inform individualized volume management and aid in risk stratification. This tool is provided by contemporary nuclear medicine-based BVA-100 methodology, which uses the well-established indicator-dilution principle and is a requested topic for discussion in this review.

A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study.

Bladder volume assessments are crucial for managing urinary disorders. Ultrasound imaging (US) is a preferred noninvasive, cost-effective imaging modality for bladder observation and volume measurements. However, the high operator dependency of US is a major challenge due to the difficulty in evaluating ultrasound images without professional expertise. To address this issue, image-based automatic bladder volume estimation methods have been introduced, but most conventional methods require high-complexity computing resources that are not available in point-of-care (POC) settings. Therefore, in this study, a deep learning-based bladder volume measurement system was developed for POC settings using a lightweight convolutional neural network (CNN)-based segmentation model, which was optimized on a low-resource system-on-chip (SoC) to detect and segment the bladder region in ultrasound images in real time. The proposed model achieved high accuracy and robustness and can be executed on the low-resource SoC at 7.93 frames per second, which is 13.44 times faster than the frame rate of a conventional network with negligible accuracy drawbacks (0.004 of the Dice coefficient). The feasibility of the developed lightweight deep learning network was demonstrated using tissue-mimicking phantoms.

Downsizing of rectal cancer following neoadjuvant radiotherapy (5 × 5 Gy) and long interval surgery evaluated using MRI semiautomated volumetric measurements, a retrospective study.

Introduction: Neoadjuvant conventional chemoradiation (CRT) is the standard treatment for primary locally non-curatively resectable rectal cancer, as tumor downsizing may allow R0 resectability. Short-term neoadjuvant radiotherapy (5x5 Gy) followed by an interval before surgery (SRT- delay) is an alternative for multimorbid patients who cannot tolerate CRT. This study examined the extent of tumor downsizing achieved with the SRT-delay approach in a limited cohort that underwent complete re-staging before surgery. Methods: Between March 2018 and July 2021, 26 patients with locally advanced primary adenocarcinoma (>uT3 or/and N+) of the rectum were treated with SRT-delay. 22 patients underwent initial staging and complete re-staging (CT, endoscopy, MRI). Tumor downsizing was assessed by staging and re-staging data and pathologic findings. Semiautomated measurement of tumor volume was performed using mint Lesion™ 1.8 software to evaluate tumor regression. Results: The mean tumor diameter determined on sagittal T2 MRI images decreased significantly from 54.1 (23-78) mm at initial staging to 37.9 (18-65) mm at re-staging before surgery (p <0.001) and to 25.5 (7-58) mm at pathologic examination (p <0.001). This corresponds to a mean reduction in tumor diameter of 28.9 (4.3-60.7) % at re-staging and 51.1 (8.7-86.5) % at pathology. Mean tumor volume determined from transverse T2 MR images mint LesionTM 1.8 software significantly decreased from 27.5 (9.8 - 89.6) cm3 at initial staging to 13.1 (3.7 - 32.8) cm3 at re-staging (p <0.001), corresponding to a mean reduction of 50.8 (21.6 - 77) %. The frequency of positive circumferential resection margin (CRM) (less than 1mm) decreased from 45,5 % (10 patients) at initial staging to 18,2 % (4 patients) at re-staging. On pathologic examination, the CRM was negative in all cases. However, multivisceral resection for T4 tumors was required in 2 patients (9%). Tumor downstaging was noted in 15 of 22 patients after SRT-delay. Conclusion: In conclusion, the observed extent of downsizing is broadly comparable to the results of CRT, making SRT-delay a serious alternative for patients who cannot tolerate chemotherapy.

Validation of acoustic voided volume measure: a pilot prospective study.

PURPOSE: We evaluated the accuracy and reliability of a new smartphone-based acoustic voided volume (VV) measurement application compared to VV estimation based on the measurement of urine volume in a bladder by ultrasound bladder scan. PATIENTS AND METHODS: A total of 53 subjects from 01/2021 to 09/2021 were prospectively enrolled. Bladder scan-based VV estimation is based on the difference in the volume of urine in a bladder measured before urination and volume measured after urination. The acoustic VV measurement is based on smartphone-based acoustic VV measurement mobile application. VV estimates for the same void were compared between two techniques. Urinary measures were obtained from 49 male subjects resulting in a total of 245 measurements for analysis. VV measures were compared using Pearson's correlation coefficient (PCC), evaluation of observed versus predicted VV measures using linear regression fit indices, and Bland-Altman method. RESULTS: VV between the two techniques revealed strong correlation (PCC 0.811, p < 0.001). Means of the number of measurements per patient and inpatient days for measurements analyzed are 5 and 2.7, respectively. In 245 measurements, VV measured by bladder scan is 238.69 ± 122.32 mL, VV measured by mobile application is 254.69 ± 119.28 mL, and their difference of two measurements is 16 ± 74.29 mL. CONCLUSION: Through the comparison with VV estimated by ultrasound bladder scan, which is a technology to measure the urine volume in a bladder, it was confirmed that the smartphone-based acoustic VV measurement application proudP® is accurate.

Use of 3D ultrasound to characterise temporal changes in thyroid nodules: an in vitro study.

OBJECTIVE: Thyroid nodules are extremely common, with prevalence rate up to 68%, yet only 7-15% of these are malignant. Many nodules require surveillance and 2-dimensional ultrasound (2D US) is used. Issues include the huge workload of obtaining and labeling images and difficulty comparing sizes of nodules over time due to large inter-operator variability. Inaccuracies may result in unnecessary FNAC or missed diagnosis of malignant nodules. METHODS: We compared two techniques: freehand plain 2D US against freehand 2D US with gyroscopic guidance, both followed by 3D reconstruction using software. We measured the volume of nodules and a normal thyroid gland. RESULTS: We found 2D US with gyroscopic guidance to be superior to plain 2D US as 3D reconstructions of greater accuracy are produced. The volume of the thyroid lobe measured 8.42 cm3 ± 0.94 was reasonably close to the normal average volume. However, the measured volume of the ellipsoidal nodule by the software is 8.69 cm3 ± 0.97 while the measured volume of the spherical nodule is 7.09 cm3 ± 0.79. As the expected volume of the nodules were 4.24cm3 and 4.19 cm3 respectively, the measured volume of the nodule was not accurate. The time taken to characterise nodules was reduced greatly from over 30 min in usual procedure to less than 10 min. CONCLUSION: We find 3D US promising for evaluating size of thyroid nodules, with potential to study other TIRAD characteristics. Freehand 2D US with gyroscopic guidance shows the most promise for producing reliable, accurate and faster 3D reconstructions of thyroid nodules.

Effect of mechanical ventilation during cardiopulmonary bypass on end-expiratory lung volume in the perioperative period of cardiac surgery: an observational study.

BACKGROUND: Many studies explored the impact of ventilation during cardiopulmonary bypass (CPB) period with conflicting results. Functional residual capacity or End Expiratory Lung Volume (EELV) may be disturbed after cardiac surgery but the specific effects of CPB have not been studied. Our objective was to compare the effect of two ventilation strategies during CPB on EELV. METHODS: Observational single center study in a tertiary teaching hospital. Adult patients undergoing on-pump cardiac surgery by sternotomy were included. Maintenance of ventilation during CPB was left to the discretion of the medical team, with division between "ventilated" and "non-ventilated" groups afterwards. Iterative intra and postoperative measurements of EELV were carried out by nitrogen washin-washout technique. Main endpoint was EELV at the end of surgery. Secondary endpoints were EELV one hour after ICU admission, PaO2/FiO2 ratio, driving pressure, duration of mechanical ventilation and post-operative pulmonary complications. RESULTS: Forty consecutive patients were included, 20 in each group. EELV was not significantly different between the ventilated versus non-ventilated groups at the end of surgery (1796 ± 586 mL vs. 1844 ± 524 mL, p = 1) and one hour after ICU admission (2095 ± 562 vs. 2045 ± 476 mL, p = 1). No significant difference between the two groups was observed on PaO2/FiO2 ratio (end of surgery: 339 ± 149 vs. 304 ± 131, p = 0.8; one hour after ICU: 324 ± 115 vs. 329 ± 124, p = 1), driving pressure (end of surgery: 7 ± 1 vs. 8 ± 1 cmH2O, p = 0.3; one hour after ICU: 9 ± 3 vs. 9 ± 3 cmH2O), duration of mechanical ventilation (5.5 ± 4.8 vs 8.2 ± 10.0 h, p = 0.5), need postoperative respiratory support (2 vs. 1, p = 1), occurrence of pneumopathy (2 vs. 0, p = 0.5) and radiographic atelectasis (7 vs. 8, p = 1). CONCLUSION: No significant difference was observed in EELV after cardiac surgery between not ventilated and ventilated patients during CPB.

Deep learning-based computed tomography image segmentation and volume measurement of intracerebral hemorrhage.

The study aims to enhance the accuracy and practicability of CT image segmentation and volume measurement of ICH by using deep learning technology. A dataset including the brain CT images and clinical data of 1,027 patients with spontaneous ICHs treated from January 2010 to December 2020 were retrospectively analyzed, and a deep segmentation network (AttFocusNet) integrating the focus structure and the attention gate (AG) mechanism is proposed to enable automatic, accurate CT image segmentation and volume measurement of ICHs. In internal validation set, experimental results showed that AttFocusNet achieved a Dice coefficient of 0.908, an intersection-over-union (IoU) of 0.874, a sensitivity of 0.913, a positive predictive value (PPV) of 0.957, and a 95% Hausdorff distance (HD95) (mm) of 5.960. The intraclass correlation coefficient (ICC) of the ICH volume measurement between AttFocusNet and the ground truth was 0.997. The average time of per case achieved by AttFocusNet, Coniglobus formula and manual segmentation is 5.6, 47.7, and 170.1 s. In the two external validation sets, AttFocusNet achieved a Dice coefficient of 0.889 and 0.911, respectively, an IoU of 0.800 and 0.836, respectively, a sensitivity of 0.817 and 0.849, respectively, a PPV of 0.976 and 0.981, respectively, and a HD95 of 5.331 and 4.220, respectively. The ICC of the ICH volume measurement between AttFocusNet and the ground truth were 0.939 and 0.956, respectively. The proposed segmentation network AttFocusNet significantly outperforms the Coniglobus formula in terms of ICH segmentation and volume measurement by acquiring measurement results closer to the true ICH volume and significantly reducing the clinical workload.

Identification of genetic loci for flag-leaf-related traits in wheat (Triticum aestivum L.) and their effects on grain yield.

Flag-leaf-related traits including length (FLL), width (FLW), area (FLA), thickness (FLT), and volume (FLV) of flag leaves are the most important determinants of plant architecture and yield in wheat. Understanding the genetic basis of these traits could accelerate the breeding of high yield wheat varieties. In this study, we constructed a doubled haploid (DH) population and analyzed flag-leaf-related traits in five experimental locations/years using the wheat 90K single-nucleotide polymorphism array. It's worth noting that a novel method was used to measure FLT and FLV easily. Leaf thickness at two-thirds of the leaf length from tip to collar represented the average leaf thickness as measured with freehand sections and was used to calculate the leaf volume. In addition, flag-leaf-related traits showed positive correlations with yield related traits under two different water regimes. A total of 79 quantitative trait loci (QTL) controlling the five traits were detected among all chromosomes except 4D and 5A, explaining 3.09-14.52% of the phenotypic variation. Among them, 15 stable QTL were identified in more than three environments, including two major QTL for FLT, six for FLW, three for FLA, two for FLT and two for FLV. DH lines with positive alleles at both QTL regions had an average FLL (9.90%), FLW (32.87%), FLT (6.62%), FLA (18.47%), and FLV (20.87%) greater than lines with contrasting alleles. QFLT-2B, QFLV-2A, and QFLV-7D were co-located with yield-related traits. The 15 QTL were validated by tightly linked kompetitive allele specific PCR (KASP) markers in a recombinant inbred line (RIL) population derived from a different cross. QFLL-4A, QFLW-4B, QFLA-5D.1, QFLA-7A, QFLA-7D.1, QFLT-2B, QFLT-6A, QFLV-2A, and QFLV-7D are likely novel loci. These results provide a better understanding of the genetic basis underlying flag-leaf-related traits. Also, target regions for fine mapping and marker-assisted selection were identified and these will be valuable for breeding high yielding bread wheat.

Fine-Grained Assessment of COVID-19 Severity Based on Clinico-Radiological Data Using Machine Learning.

BACKGROUND: The severe and critical cases of COVID-19 had high mortality rates. Clinical features, laboratory data, and radiological features provided important references for the assessment of COVID-19 severity. The machine learning analysis of clinico-radiological features, especially the quantitative computed tomography (CT) image analysis results, may achieve early, accurate, and fine-grained assessment of COVID-19 severity, which is an urgent clinical need. OBJECTIVE: To evaluate if machine learning algorithms using CT-based clinico-radiological features could achieve the accurate fine-grained assessment of COVID-19 severity. METHODS: The clinico-radiological features were collected from 78 COVID-19 patients with different severities. A neural network was developed to automatically measure the lesion volume from CT images. The severity was clinically diagnosed using two-type (severe and non-severe) and fine-grained four-type (mild, regular, severe, critical) classifications, respectively. To investigate the key features of COVID-19 severity, statistical analyses were performed between patients' clinico-radiological features and severity. Four machine learning algorithms (decision tree, random forest, SVM, and XGBoost) were trained and applied in the assessment of COVID-19 severity using clinico-radiological features. RESULTS: The CT imaging features (CTscore and lesion volume) were significantly related with COVID-19 severity (p < 0.05 in statistical analysis for both in two-type and fine-grained four-type classifications). The CT imaging features significantly improved the accuracy of machine learning algorithms in assessing COVID-19 severity in the fine-grained four-type classification. With CT analysis results added, the four-type classification achieved comparable performance to the two-type one. CONCLUSIONS: CT-based clinico-radiological features can provide an important reference for the accurate fine-grained assessment of illness severity using machine learning to achieve the early triage of COVID-19 patients.

Photogrammetry-Based Volume Measurement Framework for the Particle Density Estimation of LECA.

This paper presents a photogrammetry-based volume measurement framework for the particle density estimation of Lightweight expanded clay aggregate (LECA). The results are compared with computed tomography (CT) and Archimedes' method measurements. All of the steps required in order to apply the proposed approach are explained. Next, we discuss how the interpretation of open pores affects the results of volume measurements. We propose to process the shapes obtained from different methods by applying an Ambient Occlusion algorithm with the same threshold, t = 0.175. The difference between the CT and SfM methods is less than 0.006 g/cm3, proving that the photogrammetry-based approach is accurate enough. The Archimedes' method significantly overestimates the density of the particles. Nevertheless, its accuracy is acceptable for most engineering purposes. Additionally, we evaluate the accuracy of shape reconstruction (in terms of the Hausdorff distance). For 95% of the grain's surface, the maximum error is between 0.073 mm and 0.129 mm (depending on the grain shape). The presented approach is helpful for measuring the particle density of porous aggregates. The proposed methodology can be utilized in order to estimate intergranular porosity, which is valuable information for the calibration of DEM models.