RESUMO
To develop a deep learning-based model capable of segmenting the left ventricular (LV) myocardium on native T1 maps from cardiac MRI in both long-axis and short-axis orientations. Models were trained on native myocardial T1 maps from 50 healthy volunteers and 75 patients using manual segmentation as the reference standard. Based on a U-Net architecture, we systematically optimized the model design using two different training metrics (Sørensen-Dice coefficient = DSC and Intersection-over-Union = IOU), two different activation functions (ReLU and LeakyReLU) and various numbers of training epochs. Training with DSC metric and a ReLU activation function over 35 epochs achieved the highest overall performance (mean error in T1 10.6 ± 17.9 ms, mean DSC 0.88 ± 0.07). Limits of agreement between model results and ground truth were from -35.5 to + 36.1 ms. This was superior to the agreement between two human raters (-34.7 to + 59.1 ms). Segmentation was as accurate for long-axis views (mean error T1: 6.77 ± 8.3 ms, mean DSC: 0.89 ± 0.03) as for short-axis images (mean error ΔT1: 11.6 ± 19.7 ms, mean DSC: 0.88 ± 0.08). Fully automated segmentation and quantitative analysis of native myocardial T1 maps is possible in both long-axis and short-axis orientations with very high accuracy.
Assuntos
Aprendizado Profundo , Imageamento por Ressonância Magnética , Humanos , Imageamento por Ressonância Magnética/métodos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Processamento de Imagem Assistida por Computador/métodos , Miocárdio , Ventrículos do Coração/diagnóstico por imagem , Coração/diagnóstico por imagemRESUMO
Segmenting the left ventricle from the transgastric short-axis views (TSVs) on transesophageal echocardiography (TEE) is the cornerstone for cardiovascular assessment during perioperative management. Even for seasoned professionals, the procedure remains time-consuming and experience-dependent. The current study aims to evaluate the feasibility of deep learning for automatic segmentation by assessing the validity of different U-Net algorithms. A large dataset containing 1388 TSV acquisitions was retrospectively collected from 451 patients (32% women, average age 53.42 years) who underwent perioperative TEE between July 2015 and October 2023. With image preprocessing and data augmentation, 3336 images were included in the training set, 138 images in the validation set, and 138 images in the test set. Four deep neural networks (U-Net, Attention U-Net, UNet++, and UNeXt) were employed for left ventricle segmentation and compared in terms of the Jaccard similarity coefficient (JSC) and Dice similarity coefficient (DSC) on the test set, as well as the number of network parameters, training time, and inference time. The Attention U-Net and U-Net++ models performed better in terms of JSC (the highest average JSC: 86.02%) and DSC (the highest average DSC: 92.00%), the UNeXt model had the smallest network parameters (1.47 million), and the U-Net model had the least training time (6428.65 s) and inference time for a single image (101.75 ms). The Attention U-Net model outperformed the other three models in challenging cases, including the impaired boundary of left ventricle and the artifact of the papillary muscle. This pioneering exploration demonstrated the feasibility of deep learning for the segmentation of the left ventricle from TSV on TEE, which will facilitate an accelerated and objective alternative of cardiovascular assessment for perioperative management.
RESUMO
Introduction Internal jugular vein (IJV) cannulation is a routine procedure in operating rooms, critical care units, and perioperative settings. Ultrasound guidance has notably increased the success rates of IJV cannulation. A modified ultrasound technique known as the short-axis out-of-plane method with dynamic needle tip positioning (DNTP) allows for continuous visualization of the needle tip throughout the procedure. This study aims to compare the first-pass success rate of IJV cannulation using the DNTP and long-axis in-plane (LAIP) approaches. Methods One hundred patients between 18 and 70 years undergoing elective surgery requiring IJV cannulation were recruited. Patients were assigned randomly to the DNTP group (n = 50) or the LAIP group (n = 50). We recorded the first-pass success rate, time to achieve successful cannulation, number of skin punctures, overall success rate within five minutes, and potential complications such as pneumothorax and hematoma. Results The first pass success rate was higher in the DNTP group (48/50, 96%) as compared to the LAIP group (38/50, 76%, relative risk, 1.67; 95% confidence interval, 0.039-0.707; p = 0.008). The cannulation time was shorter in DNTP (116.98 ± 22.90 seconds) versus the LAIP group (213.04 ± 52.08 seconds; p < 0.001). No complications like pneumothorax or hematoma were noted in both groups. Conclusion We conclude that the ultrasound-guided DNTP technique for IJV cannulation, as compared with the LAIP technique, may significantly improve the first attempt cannulation, number of attempts, and cannulation time.
RESUMO
BACKGROUND: Thyroid nodules are common in the general population. Ultrasonography is the most efficient diagnostic approach to evaluate thyroid nodules. The US FNAC procedure can be performed using either the short axis (perpendicular), or a long axis (parallel) approach to visualize the needle as it is advanced toward the desired nodule. The main aim of this study was to compare the percentage of non-diagnostic results between the long and short axis approach. METHODS: A prospective study that included a randomized controlled trial and was divided into two arms-the short axis and the long axis-was conducted. A total of 245 thyroid nodules were collected through the fine needle aspiration cytology, performed with ultrasound, from march 2021 to march 2022. The patient's demographic information were collected and also nodules characteristics. RESULTS: Of 245 nodules sampled, 122 were sampled with the long axis method, while 123 with the short axis method. There is not significantly less non diagnostic approach with either method compared to the other (11.5 % vs 16.3 % respectively). DISCUSSION: Previous studies came to the conclusion that the long axis method yields fewer non diagnostic samples. This study evaluated the two FNA approaches which were proceeded by the same physician who is expert in both techniques. CONCLUSION: The US FNAC performed in the long axis approach will not produce more conclusive results and less non diagnostic results (Bethesda category 1) than the short axis approach one.
Assuntos
Nódulo da Glândula Tireoide , Humanos , Nódulo da Glândula Tireoide/patologia , Nódulo da Glândula Tireoide/diagnóstico por imagem , Estudos Prospectivos , Feminino , Masculino , Pessoa de Meia-Idade , Biópsia por Agulha Fina/métodos , Adulto , Glândula Tireoide/patologia , Glândula Tireoide/diagnóstico por imagem , Idoso , Biópsia Guiada por Imagem/métodos , Ultrassonografia de Intervenção/métodos , Ultrassonografia/métodosRESUMO
Introduction Radial artery cannulation is a commonly performed invasive procedure for assessing a patient's hemodynamic status and collecting blood samples. Ultrasound guidance has shown benefits in improving the success rate of first-attempt cannulation. Two main approaches, short-axis out-of-plane (SAOOP) and long-axis in-plane (LAIP), are commonly used. A modified technique called dynamic needle-tip positioning (DNTP) using the short-axis out-of-plane approach has been reported to enhance arterial catheterization. This study aims to compare the first-attempt success rates of radial artery cannulation using the two techniques, DNTP versus LAIP, along with overall success rates, cannulation time, and number of attempts. Methods This prospective, randomized, controlled, clinical study was conducted after obtaining clearance from the Institute Ethics Committee of AIIMS, Raipur. Ninety-six patients between the ages of 18 and 50 years, undergoing elective surgery under general anesthesia, and required radial arterial cannulation were randomized and equally allocated into two groups as the LAIP and DNTP approaches. The first-pass success rate, time to achieve successful cannulation, number of attempts needed, overall success rate within five minutes, and potential complications, such as thrombosis, vasospasm, and hematoma, were recorded. Results A total of 96 patients were included, with 48 in the LAIP group and 48 in the DNTP group. The DNTP group showed statistically significant advantages over the LAIP group, with a higher first-pass success rate (97.9% vs. 83.3%; p = 0.014) and shorter time to achieve successful cannulation (9.29±3.79 vs. 26.16±20.22 seconds; p = 0.001). Conclusion The ultrasound-guided short-axis DNTP technique for radial artery cannulation demonstrated a significant advantage as compared to the LAIP technique. The DNTP technique resulted in higher first-attempt cannulation success and shorter cannulation time.
RESUMO
Sacral insufficiency fractures commonly affect elderly women with osteoporosis and can cause debilitating lower back pain. First line management is often with conservative measures such as early mobilization, multimodal pain management, and osteoporosis management. If non-operative management fails, sacroplasty is a minimally invasive intervention that may be pursued. Candidates for sacroplasty are patients with persistent pain, inability to tolerate immobilization, or patients with low bone mineral density. Before undergoing sacroplasty, patients' bone health should be optimized with pharmacotherapy. Anabolic agents prior to or in conjunction with sacroplasty have been shown to improve patient outcomes. Sacroplasty can be safely performed through a number of techniques: short-axis, long-axis, coaxial, transiliac, interpedicular, and balloon-assisted. The procedure has been demonstrated to rapidly and durably reduce pain and improve mobility, with little risk of complications. This article aims to provide a narrative literature review of sacroplasty including, patient selection and optimization, the various technical approaches, and short and long-term outcomes.
RESUMO
Accurate segmentation of the left ventricle myocardium is the key step of automatic assessment of cardiac function. However, the current methods mainly focus on the end-diastolic and the end-systolic frames in cine MR sequences and lack the attention to myocardial motion in the cardiac cycle. Additionally, due to the lack of fine segmentation tools, the simplified approach, excluding papillary muscles and trabeculae from myocardium, is applied in clinical practice. To solve these problems, we propose a motion-aware DNN model with edge focus loss and quality control in this paper. Specifically, the bidirectional ConvLSTM layer and a new motion attention layer are proposed to encode motion-aware feature maps, and an edge focus loss function is proposed to train the model to generate the fine segmentation results. Additionally, a quality control method is proposed to filter out the abnormal segmentations before subsequent analyses. Compared with state-of-the-art segmentation models on the public dataset and the in-house dataset, the proposed method has obtained high segmentation accuracy. On the 17-segment model, the proposed method has obtained the highest Pearson correlation coefficient at 14 of 17 segments, and the mean PCC of 85%. The experimental results highlight the segmentation accuracy of the proposed method as well as its availability to substitute for the manually annotated boundaries for the automatic assessment of cardiac function.
Assuntos
Ventrículos do Coração , Imagem Cinética por Ressonância Magnética , Humanos , Ventrículos do Coração/diagnóstico por imagem , Ventrículos do Coração/fisiopatologia , Imagem Cinética por Ressonância Magnética/métodos , Controle de Qualidade , Redes Neurais de Computação , Algoritmos , Processamento de Imagem Assistida por Computador/métodos , Interpretação de Imagem Assistida por Computador/métodosRESUMO
BACKGROUND: In adult patients, there has never been an evaluation of short-axis out-of-plane versus long-axis in-plane approaches of ultrasound-guided dorsalis pedis artery cannulation. This research was conducted to compare these two techniques to cannulate the dorsal pedis artery. METHODS: In this trial, 128 adult patients undergoing surgery and necessitating arterial cannulation were examined. Dorsalis pedis artery cannulation was performed utilizing an ultrasound by long-axis in-plane approach (group L) or short-axis out-of-plane (group S) techniques. RESULTS: Group S had a higher first attempt success rate than group L (46.9% vs 28.6%, p = 0.039). The S group had a lower assessment time than the L group (11.48 ± 3.07 vs 19.68 ± 2.79 s; p = 0.000). Cannulation time was higher in the S group (18.91 ± 1.92 s) compared to the L group (12.48 ± 1.61 s; p = 0.000). Nevertheless, the total procedure time was comparable between the L group and the S group (32.16 ± 2.95 vs 30.42 ± 4.07 s; p = 0.107). CONCLUSIONS: In adults, both views of ultrasonography can be used to guide DPA cannulation. The cannulation time for the DPA in L group was less than the S group, whereas the assessment time was less in S group. The total procedure time, however, was similar between both the groups.
RESUMO
Background and Aims: There are two approaches for ultrasound (US)-guided vessel cannulation: the short axis (SA) approach and the long axis (LA) approach. However, it remains to be seen which approach is better. Therefore, we performed the present updated systematic review and meta-analysis to assess the effectiveness and safety of US-guided vascular cannulation between the SA and LA techniques. Methods: We performed a comprehensive electronic database search in PubMed, Embase, Cochrane Library and Web of Science for the relevant studies from inception to June 2022. Randomised controlled trials comparing the SA approach and the LA approach for US-guided vascular access were incorporated in this updated meta-analysis. The first-attempt success rate was the primary outcome. The secondary outcomes were the overall success rate, cannulation time, number of attempts and the incidence of complications. The statistical analysis was conducted using RevMan software (version 5.4; the Nordic Cochrane Centre, the Cochrane Collaboration, Copenhagen, Denmark). The Cochrane risk of bias tool was used to evaluate each study's potential risk for bias. Results: In total, 16 studies consisting of 1885 participants were incorporated in this updated meta-analysis. No statistically significant difference was found between the SA and LA vascular access techniques for first-pass success rate (risk ratio = 1.07, 95% confidence interval: 0.94-1.22). The overall cannulation success rate, complication rate, average cannulation time and average number of attempts were not significantly different between the SA and LA groups. Conclusion: This updated meta-analysis demonstrated that the SA and LA approaches of US-guided vessel cannulation are similar regarding first-pass success, overall cannulation success rate, total complication rate, cannulation time and the number of attempts.
RESUMO
Significant controversies exist with regards to the optimal management of lateral pelvic lymph nodes metastases (mLLN) in patients with low rectal cancer. The differing views held by Japanese and Western clinicians on the management of mLLN have been well documented. However, the adequacy of pelvic lymph node dissection (PLND) or neoadjuvant chemoradiation (NACRT) alone in addition to total mesorectal excision (TME) have recently come into question, due to the relatively high incidence of lateral local recurrences following PLND and TME, or NACRT and TME alone. Recently, a more selective approach to PLND has been suggested, involving a combination of neoadjuvant therapy, followed by PLND only to patients in whom the oncological benefit is likely to outweigh the risk of potential adverse events. A number of studies have attempted to retrospectively identify certain nodal characteristics on preoperative imaging, such as nodal size, appearance, and size reduction following neoadjuvant therapy. However, no consensus has been reached regarding the optimal criteria for a selective approach to PLND, partly due to the heterogeneity and retrospective nature of most of these studies. This review aims to provide an overview of recent evidence with regards to the diagnostic challenges, considerations for, and outcomes of the current management strategies for mLLN in rectal cancer patients.
RESUMO
Abstract Background and objectives: There are different ultrasound probe positions used for internal jugular venous catheter placement. Also, in-plane or out of plane needle approach may be used for catheterization. Transverse short-axis classic approach is the most popular performed approach in literature. "Syringe-Free" is a new described technique that is performed with oblique long-axis approach. We aimed to compare performance of these two approaches. Methods: This study was conducted as a prospective and randomized study. 80 patients were included the study and allocated into two groups that were named Group C (transverse short-axis classic approach) and Group SF (oblique long-axis syringe-free approach) by a computer-generated randomization. The primary outcome was mean time that guidewire is seen in the Internal jugular vein (performing time). The secondary outcomes were to compare number of needle pass, number of skin puncture and complications between two groups. Results: Demographic and hemodynamic data were not significantly different. The mean performing time was 54.9 ± 19.1 s in Group C and 43.9 ± 15.8 s in Group SF. Significant differences were found between the groups (p = 0.006). Mean number of needle pass was 3.2 (± 2.1) in Group C and 2.1 (± 1.6) in Group SF. There were statistically significant differences between two groups (p = 0.002). The number of skin puncture was 1.6 (± 0.8) and 1.2 (± 0.5) in Group C and SF, respectively (p = 0.027). Conclusion: "Syringe-Free" technique has lower performing time, number of needle pass and skin puncture. Also, it allows to follow progress of guide-wire under continuous ultrasound visualization and the procedure does not need assistance during catheter insertion. Namely, "Syringe-Free" is effective, safe and fast technique that may be used to place internal jugular venous catheter.
Resumo Justificativa e objetivos: Há diferentes posições do probe do ultrasom que são utilizadas para a colocação de cateter em veia jugular interna. Além disso, a aproximação da agulha no plano ou fora do plano pode ser usada para o cateterismo. A abordagem transversal clássica no eixo curto é a abordagem mais popular na literatura. Sem seringa é uma nova técnica descrita, realizada com a abordagem oblíqua no eixo longo. Nosso objetivo foi comparar o desempenho dessas duas abordagens. Métodos: Este foi um estudo prospectivo e randômico. No total, 80 pacientes foram incluídos no estudo e divididos em dois grupos denominados Grupo C (abordagem transversal clássica no eixo curto) e Grupo SF (abordagem sem seringa oblíqua no eixo longo) por meio de randomização gerada por computador. O desfecho primário foi o tempo médio para a visibilização do fio-guia na veia jugular interna (tempo de execução). Os desfechos secundários foram o número de passagens da agulha, o número de punções da pele e as complicações entre os dois grupos. Resultados: Os dados demográficos e hemodinâmicos não foram significativamente diferentes. O tempo médio de execução foi de 54,9 ± 19,1 segundos no Grupo C e 43,9 ± 15,8 segundos no Grupo SF. Diferenças significativas foram observadas entre os grupos (p = 0,006). O número médio de passagens da agulha foi de 3,2 (± 2,1) no Grupo C e 2,1 (± 1,6) no Grupo SF. Houve diferença estatisticamente significativa entre os dois grupos (p = 0,002). O número de punções da pele foi de 1,6 (± 0,8) no Grupo C e 1,2 (± 0,5) C no Grupo SF (p = 0,027). Conclusão: A técnica sem seringa apresentou tempo de execução, número de passagens da agulha e número de punções da pele menores. Além disso, essa técnica permite acompanhar o progresso do fio-guia com visibilização ecográfica contínua e o procedimento não precisa de auxílio durante a inserção do cateter. Ou seja, sem seringa é uma técnica eficaz, segura e rápida que pode ser usada para a colocação de cateter em veia jugular interna.