No sonographer, no radiologist: New system for automatic prenatal detection of fetal biometry, fetal presentation, and placental location

Statistical Characterisation of Fetal Anatomy in Simple Obstetric Ultrasound Video Sweeps

OBJECTIVE

We present a statistical characterisation of fetal anatomies in obstetric ultrasound video sweeps where the transducer follows a fixed trajectory on the maternal abdomen.

METHODS

Large-scale, frame-level manual annotations of fetal anatomies (head, spine, abdomen, pelvis, femur) were used to compute common frame-level anatomy detection patterns expected for breech, cephalic, and transverse fetal presentations, with respect to video sweep paths. The patterns, termed statistical heatmaps, quantify the expected anatomies seen in a simple obstetric ultrasound video sweep protocol. In this study, a total of 760 unique manual annotations from 365 unique pregnancies were used.

RESULTS

We provide a qualitative interpretation of the heatmaps assessing the transducer sweep paths with respect to different fetal presentations and suggest ways in which the heatmaps can be applied in computational research (e.g., as a machine learning prior).

CONCLUSION

The heatmap parameters are freely available to other researchers (https://github.com/agleed/calopus_statistical_heatmaps).

WATUNet: a deep neural network for segmentation of volumetric sweep imaging ultrasound

Limited access to breast cancer diagnosis globally leads to delayed treatment. Ultrasound, an effective yet underutilized method, requires specialized training for sonographers, which hinders its widespread use. Volume sweep imaging (VSI) is an innovative approach that enables untrained operators to capture high-quality ultrasound images. Combined with deep learning, like convolutional neural networks, it can potentially transform breast cancer diagnosis, enhancing accuracy, saving time and costs, and improving patient outcomes. The widely used UNet architecture, known for medical image segmentation, has limitations, such as vanishing gradients and a lack of multi-scale feature extraction and selective region attention. In this study, we present a novel segmentation model known as Wavelet_Attention_UNet (WATUNet). In this model, we incorporate wavelet gates and attention gates between the encoder and decoder instead of a simple connection to overcome the limitations mentioned, thereby improving model performance. Two datasets are utilized for the analysis: the public 'Breast Ultrasound Images' dataset of 780 images and a private VSI dataset of 3818 images, captured at the University of Rochester by the authors. Both datasets contained segmented lesions categorized into three types: no mass, benign mass, and malignant mass. Our segmentation results show superior performance compared to other deep networks. The proposed algorithm attained a Dice coefficient of 0.94 and an F1 score of 0.94 on the VSI dataset and scored 0.93 and 0.94 on the public dataset, respectively. Moreover, our model significantly outperformed other models in McNemar's test with false discovery rate correction on a 381-image VSI set. The experimental findings demonstrate that the proposed WATUNet model achieves precise segmentation of breast lesions in both standard-of-care and VSI images, surpassing state-of-the-art models. Hence, the model holds considerable promise for assisting in lesion identification, an essential step in the clinical diagnosis of breast lesions.

Baran T, O’Connell A, Parker K. Enhancing breast ultrasound segmentation through fine-tuning and optimization techniques: Sharp attention UNet

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it popular among researchers. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the Dice coefficient, specificity, sensitivity, and F1 score values obtained were 0.93, 0.99, 0.94, and 0.94, respectively. In addition, McNemar's statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperformed all other models, resulting in improved breast lesion segmentation.

Evolving the Era of 5D Ultrasound? A Systematic Literature Review on the Applications for Artificial Intelligence Ultrasound Imaging in Obstetrics and Gynecology

Artificial intelligence (AI) has gained prominence in medical imaging, particularly in obstetrics and gynecology (OB/GYN), where ultrasound (US) is the preferred method. It is considered cost effective and easily accessible but is time consuming and hindered by the need for specialized training. To overcome these limitations, AI models have been proposed for automated plane acquisition, anatomical measurements, and pathology detection. This study aims to overview recent literature on AI applications in OB/GYN US imaging, highlighting their benefits and limitations. For the methodology, a systematic literature search was performed in the PubMed and Cochrane Library databases. Matching abstracts were screened based on the PICOS (Participants, Intervention or Exposure, Comparison, Outcome, Study type) scheme. Articles with full text copies were distributed to the sections of OB/GYN and their research topics. As a result, this review includes 189 articles published from 1994 to 2023. Among these, 148 focus on obstetrics and 41 on gynecology. AI-assisted US applications span fetal biometry, echocardiography, or neurosonography, as well as the identification of adnexal and breast masses, and assessment of the endometrium and pelvic floor. To conclude, the applications for AI-assisted US in OB/GYN are abundant, especially in the subspecialty of obstetrics. However, while most studies focus on common application fields such as fetal biometry, this review outlines emerging and still experimental fields to promote further research.

Evaluation of an artificial intelligent algorithm (Heartassist™) to automatically assess the quality of second trimester cardiac views: a prospective study

OBJECTIVES

The aim of this study was to evaluate the agreement between visual and automatic methods in assessing the adequacy of fetal cardiac views obtained during second trimester ultrasonographic examination.

METHODS

In a prospective observational study frames of the four-chamber view left and right outflow tracts, and three-vessel trachea view were obtained from 120 consecutive singleton low-risk women undergoing second trimester ultrasound at 19-23 weeks of gestation. For each frame, the quality assessment was performed by an expert sonographer and by an artificial intelligence software (Heartassist™). The Cohen's κ coefficient was used to evaluate the agreement rates between both techniques.

RESULTS

The number and percentage of images considered adequate visually by the expert or with Heartassist™ were similar with a percentage >87 % for all the cardiac views considered. The Cohen's κ coefficient values were for the four-chamber view 0.827 (95 % CI 0.662-0.992), 0.814 (95 % CI 0.638-0.990) for left ventricle outflow tract, 0.838 (95 % CI 0.683-0.992) and three vessel trachea view 0.866 (95 % CI 0.717-0.999), indicating a good agreement between the two techniques.

CONCLUSIONS

Heartassist™ allows to obtain the automatic evaluation of fetal cardiac views, reached the same accuracy of expert visual assessment and has the potential to be applied in the evaluation of fetal heart during second trimester ultrasonographic screening of fetal anomalies.

Assessment of a Brief Standardized Obstetric Ultrasound Training Program for Individuals Without Prior Ultrasound Experience

ABSTRACT

Obstetric volume sweep imaging (OB VSI) is a simple set of transducer movements guided by external body landmarks that can be taught to ultrasound-naive non-experts. This approach can increase access to ultrasound in rural/low-resources settings lacking trained sonographers. This study presents and evaluates a training program for OB VSI. Six trainees without previous formal ultrasound experience received a training program on the OB VSI protocol containing focused didactics and supervised live hands-on ultrasound scanning practice. Trainees then independently performed 194 OB VSI examinations on pregnancies >14 weeks with known prenatal ultrasound abnormalities. Images were reviewed by maternal-fetal medicine specialists for the primary outcome (protocol deviation rates) and secondary outcomes (examination quality and image quality). Protocol deviation was present in 25.8% of cases, but only 7.7% of these errors affected the diagnostic potential of the ultrasound. Error rate differences between trainees ranged from 8.6% to 53.8% ( P < 0.0001). Image quality was excellent or acceptable in 88.2%, and 96.4% had image quality capable of yielding a diagnostic interpretation. The frequency of protocol deviations decreased over time in the majority of trainees, demonstrating retention of training program over time. This brief OB VSI training program for ultrasound-naive non-experts yielded operators capable of producing high-quality images capable of diagnostic interpretation after 3 hours of training. This training program could be adapted for use by local community members in low-resource/rural settings to increase access to obstetric ultrasound.

Artificial intelligence in obstetric ultrasound: A scoping review

The objective is to summarize the current use of artificial intelligence (AI) in obstetric ultrasound. PubMed, Cochrane Library, and ClinicalTrials.gov databases were searched using the following keywords "neural networks", OR "artificial intelligence", OR "machine learning", OR "deep learning", AND "obstetrics", OR "obstetrical", OR "fetus", OR "foetus", OR "fetal", OR "foetal", OR "pregnancy", or "pregnant", AND "ultrasound" from inception through May 2022. The search was limited to the English language. Studies were eligible for inclusion if they described the use of AI in obstetric ultrasound. Obstetric ultrasound was defined as the process of obtaining ultrasound images of a fetus, amniotic fluid, or placenta. AI was defined as the use of neural networks, machine learning, or deep learning methods. The authors' search identified a total of 127 papers that fulfilled our inclusion criteria. The current uses of AI in obstetric ultrasound include first trimester pregnancy ultrasound, assessment of placenta, fetal biometry, fetal echocardiography, fetal neurosonography, assessment of fetal anatomy, and other uses including assessment of fetal lung maturity and screening for risk of adverse pregnancy outcomes. AI holds the potential to improve the ultrasound efficiency, pregnancy outcomes in low resource settings, detection of congenital malformations and prediction of adverse pregnancy outcomes.

Enhancing Breast Ultrasound Segmentation through Fine-tuning and Optimization Techniques: Sharp Attention UNet

Segmentation of breast ultrasound images is a crucial and challenging task in computer-aided diagnosis systems. Accurately segmenting masses in benign and malignant cases and identifying regions with no mass is a primary objective in breast ultrasound image segmentation. Deep learning (DL) has emerged as a powerful tool in medical image segmentation, revolutionizing how medical professionals analyze and interpret complex imaging data. The UNet architecture is a highly regarded and widely used DL model in medical image segmentation. Its distinctive architectural design and exceptional performance have made it a popular choice among researchers in the medical image segmentation field. With the increase in data and model complexity, optimization and fine-tuning models play a vital and more challenging role than before. This paper presents a comparative study evaluating the effect of image preprocessing and different optimization techniques and the importance of fine-tuning different UNet segmentation models for breast ultrasound images. Optimization and fine-tuning techniques have been applied to enhance the performance of UNet, Sharp UNet, and Attention UNet. Building upon this progress, we designed a novel approach by combining Sharp UNet and Attention UNet, known as Sharp Attention UNet. Our analysis yielded the following quantitative evaluation metrics for the Sharp Attention UNet: the dice coefficient, specificity, sensitivity, and F1 score obtained values of 0.9283, 0.9936, 0.9426, and 0.9412, respectively. In addition, McNemar's statistical test was applied to assess significant differences between the approaches. Across a number of measures, our proposed model outperforms the earlier designed models and points towards improved breast lesion segmentation algorithms.

Diagnosis of Pregnancy Complications Using Blind Ultrasound Sweeps Performed by Individuals Without Prior Formal Ultrasound Training

OBJECTIVE

To estimate the diagnostic accuracy of blind ultrasound sweeps performed with a low-cost, portable ultrasound system by individuals with no prior formal ultrasound training to diagnose common pregnancy complications.

METHODS

This is a single-center, prospective cohort study conducted from October 2020 to January 2022 among people with second- and third-trimester pregnancies. Nonspecialists with no prior formal ultrasound training underwent a brief training on a simple eight-step approach to performing a limited obstetric ultrasound examination that uses blind sweeps of a portable ultrasound probe based on external body landmarks. The sweeps were interpreted by five blinded maternal-fetal medicine subspecialists. Sensitivity, specificity, and positive and negative predictive values for blinded ultrasound sweep identification of pregnancy complications (fetal malpresentation, multiple gestations, placenta previa, and abnormal amniotic fluid volume) were compared with a reference standard ultrasonogram as the primary analysis. Kappa for agreement was also assessed.

RESULTS

Trainees performed 194 blinded ultrasound examinations on 168 unique pregnant people (248 fetuses) at a mean of 28±5.85 weeks of gestation for a total of 1,552 blinded sweep cine clips. There were 49 ultrasonograms with normal results (control group) and 145 ultrasonograms with abnormal results with known pregnancy complications. In this cohort, the sensitivity for detecting a prespecified pregnancy complication was 91.7% (95% CI 87.2-96.2%) overall, with the highest detection rate for multiple gestations (100%, 95% CI 100-100%) and noncephalic presentation (91.8%, 95% CI 86.4-97.3%). There was high negative predictive value for placenta previa (96.1%, 95% CI 93.5-98.8%) and abnormal amniotic fluid volume (89.5%, 95% CI 85.3-93.6%). There was also substantial to perfect mean agreement for these same outcomes (range 87-99.6% agreement, Cohen κ range 0.59-0.91, P<.001 for all).

CONCLUSION

Blind ultrasound sweeps of the gravid abdomen guided by an eight-step protocol using only external anatomic landmarks and performed by previously untrained operators with a low-cost, portable, battery-powered device had excellent sensitivity and specificity for high-risk pregnancy complications such as malpresentation, placenta previa, multiple gestations, and abnormal amniotic fluid volume, similar to results of a diagnostic ultrasound examination using a trained ultrasonographer and standard-of-care ultrasound machine. This approach has the potential to improve access to obstetric ultrasonography globally.

Sustainable volume sweep imaging lung teleultrasound in Peru: Public health perspectives from a new frontier in expanding access to imaging

Background

Pulmonary disease is a common cause of morbidity and mortality, but the majority of the people in the world lack access to diagnostic imaging for its assessment. We conducted an implementation assessment of a potentially sustainable and cost-effective model for delivery of volume sweep imaging (VSI) lung teleultrasound in Peru. This model allows image acquisition by individuals without prior ultrasound experience after only a few hours of training.

Methods

Lung teleultrasound was implemented at 5 sites in rural Peru after a few hours of installation and staff training. Patients were offered free lung VSI teleultrasound examination for concerns of respiratory illness or research purposes. After ultrasound examination, patients were surveyed regarding their experience. Health staff and members of the implementation team also participated in separate interviews detailing their views of the teleultrasound system which were systematically analyzed for key themes.

Results

Patients and staff rated their experience with lung teleultrasound as overwhelmingly positive. The lung teleultrasound system was viewed as a potential way to improve access to imaging and the health of rural communities. Detailed interviews with the implementation team revealed obstacles to implementation important for consideration such as gaps in lung ultrasound understanding.

Conclusions

Lung VSI teleultrasound was successfully deployed to 5 health centers in rural Peru. Implementation assessment revealed enthusiasm for the system among members of the community along with important areas of consideration for future teleultrasound deployment. This system offers a potential means to increase access to imaging for pulmonary illness and improve the health of the global community.

Breast Ultrasound Volume Sweep Imaging: A New Horizon in Expanding Imaging Access for Breast Cancer Detection

OBJECTIVE

The majority of people in the world lack basic access to breast diagnostic imaging resulting in delay to diagnosis of breast cancer. In this study, we tested a volume sweep imaging (VSI) ultrasound protocol for evaluation of palpable breast lumps that can be performed by operators after minimal training without prior ultrasound experience as a means to increase accessibility to breast ultrasound.

METHODS

Medical students without prior ultrasound experience were trained for less than 2 hours on the VSI breast ultrasound protocol. Patients presenting with palpable breast lumps for standard of care ultrasound examination were scanned by a trained medical student with the VSI protocol using a Butterfly iQ handheld ultrasound probe. Video clips of the VSI scan imaging were later interpreted by an attending breast imager. Results of VSI scan interpretation were compared to the same-day standard of care ultrasound examination.

RESULTS

Medical students scanned 170 palpable lumps with the VSI protocol. There was 97% sensitivity and 100% specificity for a breast mass on VSI corresponding to 97.6% agreement with standard of care (Cohen's κ = 0.95, P < .0001). There was a detection rate of 100% for all cancer presenting as a sonographic mass. High agreement for mass characteristics between VSI and standard of care was observed, including 87% agreement on Breast Imaging-Reporting and Data System assessments (Cohen's κ = 0.82, P < .0001).

CONCLUSIONS

Breast ultrasound VSI for palpable lumps offers a promising means to increase access to diagnostic imaging in underserved areas. This approach could decrease delay to diagnosis for breast cancer, potentially improving morbidity and mortality.

Automatic Image Guidance for Assessment of Placenta Location in Ultrasound Video Sweeps

Ultrasound-based assistive tools are aimed at reducing the high skill needed to interpret a scan by providing automatic image guidance. This may encourage uptake of ultrasound (US) clinical assessments in rural settings in low- and middle-income countries (LMICs), where well-trained sonographers can be scarce. This paper describes a new method that automatically generates an assistive video overlay to provide image guidance to a user to assess placenta location. The user captures US video by following a sweep protocol that scans a U-shape on the lower maternal abdomen. The sweep trajectory is simple and easy to learn. We initially explore a 2-D embedding of placenta shapes, mapping manually segmented placentas in US video frames to a 2-D space. We map 2013 frames from 11 videos. This provides insight into the spectrum of placenta shapes that appear when using the sweep protocol. We propose classification of the placenta shapes from three observed clusters: complex, tip and rectangular. We use this insight to design an effective automatic segmentation algorithm, combining a U-Net with a CRF-RNN module to enhance segmentation performance with respect to placenta shape. The U-Net + CRF-RNN algorithm automatically segments the placenta and maternal bladder. We assess segmentation performance using both area and shape metrics. We report results comparable to the state-of-the-art for automatic placenta segmentation on the Dice metric, achieving 0.83 ± 0.15 evaluated on 2127 frames from 10 videos. We also qualitatively evaluate 78,308 frames from 135 videos, assessing if the anatomical outline is correctly segmented. We found that addition of the CRF-RNN improves over a baseline U-Net when faced with a complex placenta shape, which we observe in our 2-D embedding, up to 14% with respect to the percentage shape error. From the segmentations, an assistive video overlay is automatically constructed that (i) highlights the placenta and bladder, (ii) determines the lower placenta edge and highlights this location as a point and (iii) labels a 2-cm clearance on the lower placenta edge. The 2-cm clearance is chosen to satisfy current clinical guidelines. We propose to assess the placenta location by comparing the 2-cm region and the bottom of the bladder, which represents a coarse localization of the cervix. Anatomically, the bladder must sit above the cervix region. We present proof-of-concept results for the video overlay.

Volume sweep imaging lung teleultrasound for detection of COVID-19 in Peru: a multicentre pilot study

OBJECTIVES

Pulmonary disease is a significant cause of morbidity and mortality in adults and children, but most of the world lacks diagnostic imaging for its assessment. Lung ultrasound is a portable, low-cost, and highly accurate imaging modality for assessment of pulmonary pathology including pneumonia, but its deployment is limited secondary to a lack of trained sonographers. In this study, we piloted a low-cost lung teleultrasound system in rural Peru during the COVID-19 pandemic using lung ultrasound volume sweep imaging (VSI) that can be operated by an individual without prior ultrasound training circumventing many obstacles to ultrasound deployment.

DESIGN

Pilot study.

SETTING

Study activities took place in five health centres in rural Peru.

PARTICIPANTS

There were 213 participants presenting to rural health clinics.

INTERVENTIONS

Individuals without prior ultrasound experience in rural Peru underwent brief training on how to use the teleultrasound system and perform lung ultrasound VSI. Subsequently, patients attending clinic were scanned by these previously ultrasound-naïve operators with the teleultrasound system.

PRIMARY AND SECONDARY OUTCOME MEASURES

Radiologists examined the ultrasound imaging to assess its diagnostic value and identify any pathology. A random subset of 20% of the scans were analysed for inter-reader reliability.

RESULTS

Lung VSI teleultrasound examinations underwent detailed analysis by two cardiothoracic attending radiologists. Of the examinations, 202 were rated of diagnostic image quality (94.8%, 95% CI 90.9% to 97.4%). There was 91% agreement between radiologists on lung ultrasound interpretation among a 20% sample of all examinations (κ=0.76, 95% CI 0.53 to 0.98). Radiologists were able to identify sequelae of COVID-19 with the predominant finding being B-lines.

CONCLUSION

Lung VSI teleultrasound performed by individuals without prior training allowed diagnostic imaging of the lungs and identification of sequelae of COVID-19 infection. Deployment of lung VSI teleultrasound holds potential as a low-cost means to improve access to imaging around the world.