Standard Planes Research Articles

Diagnostic imaging for elbow TRASH lesions in children and usefulness of ultrasonography using standard planes.

Fractures around the elbow in children should be carefully evaluated because the main portion is cartilaginous, and radiographs are not completely reliable. This study aimed to assess the diagnostic imaging for pediatric elbow fractures that require special attention and consider the usefulness of ultrasonography with seven standard planes for the diagnosis. Patients diagnosed with elbow fractures wherein TRASH (The Radiographic Appearance Seemed Harmless) lesions were evaluated retrospectively. The diagnoses on initial radiographs, final diagnoses, additional imaging excluding radiographs, and the treatments were investigated. The standard planes for ultrasonography to detect elbow fractures included an anterior transverse scan at the level of the capitellum and proximal radioulnar joint, an anterior longitudinal scan at the level of the humeroradial and humeroulnar joints, a longitudinal scan along the lateral and medial border of the distal humerus, and a posterior longitudinal scan at the level of the distal humerus. A total of 107 patients with an average age of 5.8 years (range, 0-12 years) at the time of diagnosis were included. Of 46 (43.0%) patients misdiagnosed at the initial radiograph, 19 (17.8%) needed additional treatments due to inappropriate initial management. Ultrasonography using the standard planes was useful for prompt diagnosis and appropriate treatment. Prompt and appropriate evaluation with ultrasonography can prevent the mismanagement of pediatric elbow injuries. Level of evidence: Level IV-retrospective case series.

Locating Multiple Standard Planes in First-Trimester Ultrasound Videos via the Detection and Scoring of Key Anatomical Structures

This study was aimed at developing a first-trimester standard plane detection (FTSPD) system that can automatically locate nine standard planes in ultrasound videos and investigating its utility in clinical practice. The FTSPD system, based on the YOLOv3 network, was developed to detect structures and evaluate the quality of plane images by using a pre-defined scoring system. A total of 220 videos from two different ultrasound scanners were collected to compare detection performance between our FTSPD system and sonographers with different levels of experience. The quality of the detected standard planes was quantitatively rated by an expert according to a scoring protocol. Kolmogorov-Smirnov analysis was used to compare the distributions of scores across all nine standard planes. The expert-rated scores indicated that the quality of the standard planes detected by the FTSPD system was on par with that of the planes detected by senior sonographers. There were no significant differences in the distributions of the scores across all nine standard planes. The FTSPD system performed significantly better than junior sonographers in five standard plane types. The results of this study suggest that our FTSPD system has significant potential for detecting standard planes in first-trimester ultrasound screening, which may help to improve the accuracy of fetal ultrasound screening and facilitate early diagnosis of abnormalities. The quality of the standard planes selected by junior sonographers can be significantly improved with the assistance of our FTSPD system.

Fast 3D YOLOv3 based standard plane regression of vertebral bodies in intra-operative CBCT volumes.

Mobile C-arm systems represent the standard imaging devices within the field of spine surgery. In addition to 2D imaging, they allow for 3D scans while preserving unrestricted patient access. For viewing, the acquired volumes are adjusted such that their anatomical standard planes align with the axes of the viewing modality. This difficult and time-consuming step is currently performed manually by the leading surgeon. This process is automatized within this work to improve the usability of C-arm systems. Thereby, the spinal region consisting of multiple vertebrae and the standard planes of all vertebrae being of interest to the surgeon need to be taken into account. An object detection algorithm based on the you only look once version 3 architecture, adapted to 3D inputs, is compared with a segmentation-based approach employing a 3D U-Net. Both algorithms are trained on a dataset of 440 and tested on 218 spinal volumes. Although the detection-based algorithm is slightly inferior concerning the detection (91% versus 97% accuracy), localization (1.26mm versus 0.74mm error) and alignment accuracy (5.00deg versus 4.73deg error), it outperforms the segmentation-based one in terms of speed (5s versus 38s). Both algorithms show similar good results. However, the speed gain of the detection-based algorithm, resulting in a run time of 5s, makes it more suitable for usage in an intra-operative scenario.

Towards Standard Plane Prediction of Fetal Head Ultrasound with Domain Adaption.

Fetal Standard Plane (SP) acquisition is a key step in ultrasound based assessment of fetal health. The task detects an ultrasound (US) image with predefined anatomy. However, it requires skill to acquire a good SP in practice, and trainees and occasional users of ultrasound devices can find this challenging. In this work, we consider the task of automatically predicting the fetal head SP from the video approaching the SP. We adopt a domain transfer learning approach that maps the encoded spatial and temporal features of video in the source domain to the spatial representations of the desired SP image in the target domain, together with adversarial training to preserve the quality of the resulting image. Experimental results show that the predicted head plane is plausible and consistent with the anatomical features expected in a real SP. The proposed approach is motivated to support non-experts to find and analyse a trans-ventricular (TV) plane but could also be generalized to other planes, trimesters, and ultrasound imaging tasks for which standard planes are defined.

Three-dimensional Visualization in Diagnostic Imaging: A Renaissance in Radiology.

Supplemental material is available for this article.

Recent Advances in Artificial Intelligence-Assisted Ultrasound Scanning

Ultrasound (US) is a flexible imaging modality used globally as a first-line medical exam procedure in many different clinical cases. It benefits from the continued evolution of ultrasonic technologies and a well-established US-based digital health system. Nevertheless, its diagnostic performance still presents challenges due to the inherent characteristics of US imaging, such as manual operation and significant operator dependence. Artificial intelligence (AI) has proven to recognize complicated scan patterns and provide quantitative assessments for imaging data. Therefore, AI technology has the potential to help physicians get more accurate and repeatable outcomes in the US. In this article, we review the recent advances in AI-assisted US scanning. We have identified the main areas where AI is being used to facilitate US scanning, such as standard plane recognition and organ identification, the extraction of standard clinical planes from 3D US volumes, and the scanning guidance of US acquisitions performed by humans or robots. In general, the lack of standardization and reference datasets in this field makes it difficult to perform comparative studies among the different proposed methods. More open-access repositories of large US datasets with detailed information about the acquisition are needed to facilitate the development of this very active research field, which is expected to have a very positive impact on US imaging.

Machine learning for accurate estimation of fetal gestational age based on ultrasound images

Accurate estimation of gestational age is an essential component of good obstetric care and informs clinical decision-making throughout pregnancy. As the date of the last menstrual period is often unknown or uncertain, ultrasound measurement of fetal size is currently the best method for estimating gestational age. The calculation assumes an average fetal size at each gestational age. The method is accurate in the first trimester, but less so in the second and third trimesters as growth deviates from the average and variation in fetal size increases. Consequently, fetal ultrasound late in pregnancy has a wide margin of error of at least ±2 weeks’ gestation. Here, we utilise state-of-the-art machine learning methods to estimate gestational age using only image analysis of standard ultrasound planes, without any measurement information. The machine learning model is based on ultrasound images from two independent datasets: one for training and internal validation, and another for external validation. During validation, the model was blinded to the ground truth of gestational age (based on a reliable last menstrual period date and confirmatory first-trimester fetal crown rump length). We show that this approach compensates for increases in size variation and is even accurate in cases of intrauterine growth restriction. Our best machine-learning based model estimates gestational age with a mean absolute error of 3.0 (95% CI, 2.9–3.2) and 4.3 (95% CI, 4.1–4.5) days in the second and third trimesters, respectively, which outperforms current ultrasound-based clinical biometry at these gestational ages. Our method for dating the pregnancy in the second and third trimesters is, therefore, more accurate than published methods.

Mapping the primate thalamus: systematic approach to analyze the distribution of subcortical neuromodulatory afferents

Neuromodulatory afferents to thalamic nuclei are key for information transmission and thus play critical roles in sensory, motor, and limbic processes. Over the course of the last decades, diverse attempts have been made to map and describe subcortical neuromodulatory afferents to the primate thalamus, including axons using acetylcholine, serotonin, dopamine, noradrenaline, adrenaline, and histamine. Our group has been actively involved in this endeavor. The published descriptions on neuromodulatory afferents to the primate thalamus have been made in different laboratories and are not fully comparable due to methodological divergences (for example, fixation procedures, planes of cutting, techniques used to detect the afferents, different criteria for identification of thalamic nuclei…). Such variation affects the results obtained. Therefore, systematic methodological and analytical approaches are much needed. The present article proposes reproducible methodological and terminological frameworks for primate thalamic mapping. We suggest the use of standard stereotaxic planes to produce and present maps of the primate thalamus, as well as the use of the Anglo-American school terminology (vs. the German school terminology) for identification of thalamic nuclei. Finally, a public repository of the data collected under agreed-on frameworks would be a useful tool for looking up and comparing data on the structure and connections of primate thalamic nuclei. Important and agreed-on efforts are required to create, manage, and fund a unified and homogeneous resource of data on the primate thalamus. Likewise, a firm commitment of the institutions to preserve experimental brain material is much needed because neuroscience work with non-human primates is becoming increasingly rare, making earlier material still more valuable.

Controlled Prospective Study on the Use of Systematic Simulator-Based Training with a Virtual, Moving Fetus for Learning Second-Trimester Scan: FESIM III.

To analyze the feasibility of structured ultrasound simulation training (SIM-UT) in teaching second-trimester ultrasound screening using a high-end simulator with a randomly moving fetus. This was a prospective, controlled trial. A trial group of 11 medical students with minimal obstetric ultrasound experience underwent 12 hours of structured SIM-UT in individual hands-on sessions within 6 weeks. Learning progress was assessed with standardized tests. Performance after 2, 4, and 6 weeks of SIM-UT was compared with two reference groups ((A) Ob/Gyn residents and consultants, and (B) highly skilled DEGUM experts). Participants were asked to acquire 23 2nd trimester planes according to ISUOG guidelines in a realistic simulation B-mode with a randomly moving fetus as quickly as possible within a 30-minute time frame. All tests were analyzed regarding the rate of appropriately obtained images and the total time to completion (TTC). During the study, novices were able to improve their ultrasound skills significantly, reaching the physician level of the reference group (A) after 8 hours of training. After 12 hours of SIM-UT, the trial group performed significantly faster than the physician group (TTC: 621±189 vs. 1036±389 sec., p=0.011). Novices obtained 20 out of 23 2nd trimester standard planes without a significant time difference when compared to experts. TTC of the DEGUM reference group remained significantly faster (p<0.001) though. SIM-UT on a simulator with a virtual, randomly moving fetus is highly effective. Novices can obtain standard plane acquisition skills close to expert level within 12 hours of self-training.

Rapid post-eruptive maturation of porcine enamel.

The teeth of humans and pigs are similar in size, shape, and enamel thickness. While the formation of human primary incisor crowns takes about 8months, domestic pigs form their teeth within a much shorter time. Piglets are born after 115days of gestation with some of their teeth erupted that must after weaning meet the mechanical demands of their omnivorous diet without failure. We asked whether this short mineralization time before tooth eruption is combined with a post-eruptive mineralization process, how fast this process occurs, and how much the enamel hardens after eruption. To address this question, we investigated the properties of porcine teeth at two, four, and sixteen weeks after birth (N = 3 animals per time point) through analyses of composition, microstructure, and microhardness. We collected data at three standardized horizontal planes across the tooth crown to determine the change of properties throughout the enamel thickness and in relation to soft tissue eruption. Our findings indicate that porcine teeth erupt hypomineralized compared to healthy human enamel and reach a hardness that is similar to healthy human enamel within less than 4weeks.

Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries

Most artificial intelligence (AI) research and innovations have concentrated in high-income countries, where imaging data, IT infrastructures and clinical expertise are plentiful. However, slower progress has been made in limited-resource environments where medical imaging is needed. For example, in Sub-Saharan Africa, the rate of perinatal mortality is very high due to limited access to antenatal screening. In these countries, AI models could be implemented to help clinicians acquire fetal ultrasound planes for the diagnosis of fetal abnormalities. So far, deep learning models have been proposed to identify standard fetal planes, but there is no evidence of their ability to generalise in centres with low resources, i.e. with limited access to high-end ultrasound equipment and ultrasound data. This work investigates for the first time different strategies to reduce the domain-shift effect arising from a fetal plane classification model trained on one clinical centre with high-resource settings and transferred to a new centre with low-resource settings. To that end, a classifier trained with 1792 patients from Spain is first evaluated on a new centre in Denmark in optimal conditions with 1008 patients and is later optimised to reach the same performance in five African centres (Egypt, Algeria, Uganda, Ghana and Malawi) with 25 patients each. The results show that a transfer learning approach for domain adaptation can be a solution to integrate small-size African samples with existing large-scale databases in developed countries. In particular, the model can be re-aligned and optimised to boost the performance on African populations by increasing the recall to 0.92 pm 0.04 and at the same time maintaining a high precision across centres. This framework shows promise for building new AI models generalisable across clinical centres with limited data acquired in challenging and heterogeneous conditions and calls for further research to develop new solutions for the usability of AI in countries with fewer resources and, consequently, in higher need of clinical support.

Clinical workflow of sonographers performing fetal anomaly ultrasound scans: deep-learning-based analysis.

Despite decades of obstetric scanning, the field of sonographer workflow remains largely unexplored. In the second trimester, sonographers use scan guidelines to guide their acquisition of standard planes and structures; however, the scan-acquisition order is not prescribed. Using deep-learning-based video analysis, the aim of this study was to develop a deeper understanding of the clinical workflow undertaken by sonographers during second-trimester anomaly scans. We collected prospectively full-length video recordings of routine second-trimester anomaly scans. Important scan events in the videos were identified by detecting automatically image freeze and image/clip save. The video immediately preceding and following the important event was extracted and labeled as one of 11 commonly acquired anatomical structures. We developed and used a purposely trained and tested deep-learning annotation model to label automatically the large number of scan events. Thus, anomaly scans were partitioned as a sequence of anatomical planes or fetal structures obtained over time. A total of 496 anomaly scans performed by 14 sonographers were available for analysis. UK guidelines specify that an image or videoclip of five different anatomical regions must be stored and these were detected in the majority of scans: head/brain was detected in 97.2% of scans, coronal face view (nose/lips) in 86.1%, abdomen in 93.1%, spine in 95.0% and femur in 92.3%. Analyzing the clinical workflow, we observed that sonographers were most likely to begin their scan by capturing the head/brain (in 24.4% of scans), spine (in 23.2%) or thorax/heart (in 22.8%). The most commonly identified two-structure transitions were: placenta/amniotic fluid to maternal anatomy, occurring in 44.5% of scans; head/brain to coronal face (nose/lips) in 42.7%; abdomen to thorax/heart in 26.1%; and three-dimensional/four-dimensional face to sagittal face (profile) in 23.7%. Transitions between three or more consecutive structures in sequence were uncommon (up to 13% of scans). None of the captured anomaly scans shared an entirely identical sequence. We present a novel evaluation of the anomaly scan acquisition process using a deep-learning-based analysis of ultrasound video. We note wide variation in the number and sequence of structures obtained during routine second-trimester anomaly scans. Overall, each anomaly scan was found to be unique in its scanning sequence, suggesting that sonographers take advantage of the fetal position and acquire the standard planes according to their visibility rather than following a strict acquisition order. © 2022 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

A guiding approach of Ultrasound scan for accurately obtaining standard diagnostic planes of fetal brain malformation.

Standard planes (SPs) are crucial for the diagnosis of fetal brain malformation. However, it is very time-consuming and requires extensive experiences to acquire the SPs accurately due to the large difference in fetal posture and the complexity of SPs definitions. This study aims to present a guiding approach that could assist sonographer to obtain the SPs more accurately and more quickly. To begin with, sonographer uses the 3D probe to scan the fetal head to obtain 3D volume data, and then we used affine transformation to calibrate 3D volume data to the standard body position and established the corresponding 3D head model in 'real time'. When the sonographer uses the 2D probe to scan a plane, the position of current plane can be clearly show in 3D head model by our RLNet (regression location network), which can conduct the sonographer to obtain the three SPs more accurately. When the three SPs are located, the sagittal plane and the coronal planes can be automatically generated according to the spatial relationship with the three SPs. Experimental results conducted on 3200 2D US images show that the RLNet achieves average angle error of the transthalamic plane was 3.91±2.86°, which has a obvious improvement compared other published data. The automatically generated coronal and sagittal SPs conform the diagnostic criteria and the diagnostic requirements of fetal brain malformation. A guiding scanning method based deep learning for ultrasonic brain malformation screening is firstly proposed and it has a pragmatic value for future clinical application.

The correlation between different ultrasound planes and computed tomography measures of abdominal aortic aneurysms.

Ultrasound measurements of the aorta are typically taken in the axial plane, with the transducer perpendicular to the aorta, and diameter measurements are obtained by placing the callipers from the anterior to the posterior wall and the transverse right to the left side of the aorta. While the 'conventional' anteroposterior walls in both sagittal and transverse plains may be suitable for aneurysms with less complicated geometry, there is controversy regarding the suitability of this approach for complicated, particularly tortuous aneurysms, as they may offer a more challenging situation. Previous work undertaken within our research group found that when training inexperienced users of ultrasound, they demonstrated more optimal calliper placement to the abdominal aorta when approached from a decubitus window to obtain a coronal image compared to the traditional ultrasound approach. To observe the level of agreement in real-world reporting between computed tomography (CT) and ultrasound measurements in three standard planes; transverse AP, sagittal AP and coronal (left to right) infra-renal abdominal aortic aneurysm (AAA) diameter. This is a retrospective review of the Otago Vascular Diagnostics database for AAA, where ultrasound and CT diameter data, available within 90 days of each other, were compared. In addition to patient demographics, the infrarenal aorta ultrasound diameter measurements in transverse AP and sagittal AP, along with a coronal decubitus image of the aorta was collected. No transverse measurement was performed from the left to the right of the aorta. Three hundred twenty-five participants (238 males, mean age 76.4 ± 7.5) were included. Mean ultrasound outer to the outer wall, transverse AP and sagittal AP diameters were 48.7 ± 10.5 mm and 48.9 ± 9.9 mm, respectively. The coronal diameter measurement of the aorta from left to right was 53.9 ± 12.8 mm in the left decubitus window. The mean ultrasound max was 54.3 ± 12.6 mm. The mean CT diameter measurement was 55.6 ± 12.7 mm. Correlation between the CT max and ultrasound max was r 2 = 0.90, and CT with the coronal measurement r 2 = 0.90, CT and AP transverse was r2=0.80, and CT with AP sagittal measurement was r 2 = 0.77. The decubitus ultrasound window of the abdominal aorta, with measurement of the coronal plane, is highly correlated and in agreement with CT scanning. This window may offer an alternative approach to measuring the infrarenal abdominal aortic aneurysm and should be considered when performing surveillance of all infra-renal AAA.

Pediatric reference values of anterior visual pathway structures measured with axis-correction on high-resolution 3D T2 fast spin echo sequences

BackgroundThe size of the anterior visual pathway (AVP) structures is affected by patient age and pathology. Normative data is useful when determining whether pathology is present. AVP structures do not respect the standard planes of magnetic resonance (MR) imaging. The aim of this study was to produce normative age-related and axis-corrected data of the AVP structures using multiplanar reformation (MPR) of high-resolution 3D T2-weighted fast spin echo (3D T2w FSE) images.MethodsFor each patient 32 measurements of AVP structures were obtained in 145 children (2 months - 18 years) with normal brain MR studies on high-resolution 3D T2w FSE images adjusted to the axis of each AVP structure. Descriptive statistics were calculated for different age classes and growth models were fitted to the data and assessed for their performance to create a formal statistical model that allows inference beyond the sample.ResultsDescriptive statistics were compiled in a reference table and prediction plots in relation to age, height, and body surface area (BSA) were obtained from the best overall performing statistical model, also taking field strength (1.5 vs. 3 T) into account. Intraclass correlation coefficient values were calculated for all variables ranging from 0.474 to 0.967, the most reliable being the transverse diameter of the globe, the maximum diameter of the retrobulbar nerve sheath, the intracranial segment of the optic nerve and the transverse diameter of the chiasm. The maximum retrobulbar diameter of the optic nerve sheath and the lateral superoinferior diameter of the chiasm showed no statistically significant change with age.ConclusionDetailed charts of reference values for AVP structures as well as prediction plots in relation to age, height and BSA were established using axis-corrected measurements from the MPR of high-resolution 3D T2w FSE images. Furthermore, an Excel spreadsheet that allows users to calculate normative values for the 9 AVP structures of key interest is provided as supplementary material.

GELİŞİMSEL KALÇA DİSPLAZİSİ TANISINDA DERİN ÖĞRENME YÖNTEMLERİYLE ULTRASON TARAMALARINDAN STANDART DÜZLEM TESPİTİ

The term developmental dysplasia of the hip (DDH) describes a range of hip abnormalities affecting newborns where the femoral head and acetabulum are in improper alignment or grow abnormally, or both. The ultrasonographic evaluation technique rely on the capability of the ultrasonographer to pick up the accurate frame used for exact calculations. In our study we developed a new computer aided system that determines the exact frame from real time 2D ultrasound images and calculates the accuracy rate for each result. The deep learning architectures recently used in literature were utilized for these processes. In addition, transfer learning was carried out to increase the performance of the system using pretrained networks (SqueezeNet, VGG16, VGG19, ResNet50 and ResNet101). One of the best methods of object detection, You Only Look Once (YOLO) model, was used with pre-trained networks to determine DDH location. As a result of the study, the performance of the deep neural network model proposed with the help of these pre-trained networks was evaluated. When the obtained results were compared with expert opinions, frames (standard planes) in 605 of 676 (89.05%) test images were correctly detected. The accuracy rates for the used pre-trained networks were obtained as SqueezeNet 0.79, VGG16 0.95, VGG19 0.96, ResNet50 0.88 and ResNet101 0.93.

Multitask Deep Neural Network for the Fully Automatic Measurement of the Angle of Progression.

The angle of progression (AoP) for assessing fetal head (FH) descent during labor is measured from the standard plane of transperineal ultrasound images as the angle between a line through the long axis of pubic symphysis (PS) and a second line from the right end of PS tangentially to the contour of the FH. This paper presents a multitask network with a shared feature encoder and three task-special decoders for standard plane recognition (Task1), image segmentation (Task2) of PS and FH, and endpoint detection (Task3) of PS. Based on the segmented FH and two endpoints of PS from standard plane images, we determined the right FH tangent point that passes through the right endpoint of PS and then computed the AoP using the above three points. In this paper, the efficient channel attention unit is introduced into the shared feature encoder for improving the robustness of layer region encoding, while an attention fusion module is used to promote cross-branch interaction between the encoder for Task2 and that for Task3, and a shape-constrained loss function is designed for enhancing the robustness to noise based on the convex shape-prior. We use Pearson's correlation coefficient and the Bland–Altman graph to assess the degree of agreement. The dataset includes 1964 images, where 919 images are nonstandard planes, and the other 1045 images are standard planes including PS and FH. We achieve a classification accuracy of 92.26%, and for the AoP calculation, an absolute mean (STD) value of the difference in AoP (∆AoP) is 3.898° (3.192°), the Pearson's correlation coefficient between manual and automated AoP was 0.964 and the Bland-Altman plot demonstrates they were statistically significant (P < 0.05). In conclusion, our approach can achieve a fully automatic measurement of AoP with good efficiency and may help labor progress in the future.

A Quantitative Subarachnoid Hemorrhage Grading System, Including Supratentorial and Infratentorial Cisterns, With Multiplanar Computed Tomography Reformations.

BackgroundSubarachnoid hemorrhage (SAH) grading scales typically evaluate a limited number of cisterns on the axial plane. The goal of our study is to apply a simple quantitative yet comprehensive SAH grading scale to all major intracranial cisterns, including the infratentorial cisterns, with multiplanar computed tomography (CT) reformations.MethodologyWe performed a retrospective review of 94 consecutive cases of spontaneous SAH presenting within 72 hours of onset. SAH was categorized into five grades based on the short-axis thickness of SAH in 20 intracranial cisterns measured on the axial, coronal, and sagittal planes. Statistical analysis was performed for inter-rater agreement with kappa statistics, for inter-plane agreement by Spearman correlation statistics, and for inter-rater and inter-plane agreement by Pearson correlation statistics.ResultsThe extended kappa coefficient for the three reviewers across all 20 cisterns varied from 0.38 (0.27, 0.50) to 0.59 (0.52, 0.65) on the axial plane. The kappa coefficient for two reviewers varied from 0.46 (0.33, 0.59) to 0.70 (0.60, 0.80) on the coronal plane and from 0.35 (0.20, 0.49) to 0.87 (0.77, 0.96) on the sagittal plane. The average grade of cisterns per case demonstrated mostly excellent correlation between the imaging planes with Spearman correlation statistics (≥0.70). Pairwise concordance correlation coefficient of the total SAH score revealed agreement ranging from 0.81 to 0.90 in all three planes. Pearson correlation statistics of the average total SAH scores revealed excellent correlation among the three planes (≥0.91).ConclusionA simple quantitative SAH grading scale can be successfully applied to the supratentorial and infratentorial cisterns in three standard CT imaging planes.

Computed Tomography Findings for Predicting Invasiveness of Lung Adenocarcinomas Manifesting as Pure Ground-Glass Nodules.

Purpose: To comprehensively evaluate qualitative and quantitative features for predicting invasiveness of pure ground-glass nodules (pGGNs) using multiplanar computed tomography. Methods: Ninety-three resected pGGNs (16 atypical adenomatous hyperplasia [AAH], 18 adenocarcinoma in situ [AIS], 31 minimally invasive adenocarcinoma [MIA], and 28 invasive adenocarcinoma [IA]) were retrospectively included. Two radiologists analyzed qualitative and quantitative features on three standard planes. Univariable and multivariable logistic regression analyses were performed to identify features to distinguish the pre-invasive (AAH/AIS) from the invasive (MIA/IA) group. Results: Tumor size showed high area under the curve (AUC) for predicting invasiveness (.860, .863, .874, and .893, for axial long diameter [AXLD], multiplanar long diameter, mean diameter, and volume, respectively). The AUC for AXLD (cutoff, 11mm) was comparable to that of the volume (P = .202). The invasive group had a significantly higher number of qualitative features than the pre-invasive group, regardless of tumor size. Six out of 59 invasive nodules (10.2%) were smaller than 11mm, and all had at least one qualitative feature. pGGNs smaller than 11mm without any qualitative features (n = 16) were all pre-invasive. In multivariable analysis, AXLD, vessel change, and the presence or number of qualitative features were independent predictors for invasiveness. The model with AXLD and the number of qualitative features achieved the highest AUC (.902, 95% confidence interval .833-.971). Conclusion: In adenocarcinomas manifesting as pGGNs on computed tomography, AXLD and the number of qualitative features are independent risk factors for invasiveness; small pGGNs (<11mm) without qualitative features have low probability of invasiveness.

VesNet-RL: Simulation-Based Reinforcement Learning for Real-World US Probe Navigation

Ultrasound (US) is one of the most common medical imaging modalities since it is radiation-free, low-cost, and real-time. In freehand US examinations, sonographers often navigate a US probe to visualize standard examination planes with rich diagnostic information. However, reproducibility and stability of the resulting images often suffer from intra- and inter-operator variation. Reinforcement learning (RL), as an interaction-based learning method, has demonstrated its effectiveness in visual navigating tasks; however, RL is limited in terms of generalization. To address this challenge, we propose a simulation-based RL framework for real-world navigation of US probes towards the standard longitudinal views of vessels. A UNet is used to provide binary masks from US images; thereby, the RL agent trained on simulated binary vessel images can be applied in real scenarios without further training. To accurately characterize actual states, a multi-modality state representation structure is introduced to facilitate the understanding of environments. Moreover, considering the characteristics of vessels, a novel standard view recognition approach based on the minimum bounding rectangle is proposed to terminate the searching process. To evaluate the effectiveness of the proposed method, the trained policy is validated virtually on 3D volumes of a volunteer’s in-vivo carotid artery, and physically on custom-designed gel phantoms using robotic US. The results demonstrate that proposed approach can effectively and accurately navigate the probe towards the longitudinal view of vessels.