Multimodal fusion model for classifying placenta ultrasound imaging in pregnancies with hypertension disorders

Sun, Hongshuang; Jiao, Jing; Ren, Yanping; Guo, Yuanyuan; Wang, Yuanyuan

doi:10.1016/j.preghy.2022.12.003

Cited by 4 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although placental ultrasound data measurement and visual observation were limited, the radiomics technique allowed the identification of subtle nuance that were significantly different from normal performance. In the previous study we constructed a GMNet model that could sensitively identify abnormal changes in the placental microstructure in pregnancies with HDP (hypertension disorders of pregnancy) 32 . Krishan also discovered the ability to identify changes in the features of placental ultrasound images prior to clinical presentation of HDP through artificial intelligence techniques 33 .…”

Section: Discussionmentioning

confidence: 99%

Ultrasound-based radiomics model: a potential adjunctive tool for assessing impaired placental function in preeclampsia

Sun,

Jiao,

Wang

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose Combined with ultrasound-based radiomics, our research team has successfully developed a novel model that enables the evaluation of placental function in rats with pre-eclampsia. Material and Methods We have developed a rat model of preeclampsia induced by L-NAME and evaluated placental dysfunction through the analysis of microstructural alterations and immunoprotein levels in placental tissue. After feature extraction of ultrasound images, the Boruta feature selection method was employed to determine the most effective combination of features, and a ten-fold cross-validation method was utilized to establish the optimal model for classifying placental dysfunction. The accuracy, sensitivity, specificity, and AUC were employed to assess the efficacy of the developed model. Results In pregnant rats with preeclampsia, significant changes were observed in the microstructure of placental tissue and the expression of the angiogenic factor in the tissue. Ultrasound images of the placenta yielded a total of 558 radiomics features based on high-throughput mining of quantitative image features. After assessment of impaired placental function, an evaluation model was successfully constructed for assessing placental function in pregnant rats. The evaluation model had an AUC of 0.95, with high sensitivity, specificity, accuracy, positive predictive value, and negative predictive value, reaching 88.7%, 91.5%, 90.2%, 90.4%, and 90.0%, respectively. Conclusion Ultrasound-based radiomics could effectively identify abnormal placental features in pregnant rats with preeclampsia, and exhibiting high performance in evaluating normal and poor placental function.

show abstract

Section: Discussionmentioning

confidence: 99%

Ultrasound-based radiomics model: a potential adjunctive tool for assessing impaired placental function in preeclampsia

Sun,

Jiao,

Wang

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The automated classification of placental maturity was proposed by Lei et al and Li et al [116,117]. Early and small changes in placental tissue texture were detected by Gupta et al and Sun et al through using AI-assisted US and microvascular Doppler imaging in women with hypertensive disorders of pregnancy [118,119] and gestational diabetes [120].…”

Section: Placenta and Umbilical Cordmentioning

confidence: 99%

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

Jost,

Kosian,

Jimenez Cruz

et al. 2023

JCM

View full text Add to dashboard Cite

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.

show abstract

“…Related Work. Considerable progress has been made in segmenting [20,17,23] and classifying [1,13,8,15,21,26,10] placenta images using histopathological, ultrasound, or MRI data. However, these methods are dependent on expensive and bulky equipment, restricting the accessibility of reproductive healthcare.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Automatic Placenta Analysis Through Distributional Feature Recomposition in Vision-Language Contrastive Learning

Pan,

Cai,

Mehta

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The placenta is a valuable organ that can aid in understanding adverse events during pregnancy and predicting issues postbirth. Manual pathological examination and report generation, however, are laborious and resource-intensive. Limitations in diagnostic accuracy and model efficiency have impeded previous attempts to automate placenta analysis. This study presents a novel framework for the automatic analysis of placenta images that aims to improve accuracy and efficiency. Building on previous vision-language contrastive learning (VLC) methods, we propose two enhancements, namely Pathology Report Feature Recomposition and Distributional Feature Recomposition, which increase representation robustness and mitigate feature suppression. In addition, we employ efficient neural networks as image encoders to achieve model compression and inference acceleration. Experiments validate that the proposed approach outperforms prior work in both performance and efficiency by significant margins. The benefits of our method, including enhanced efficacy and deployability, may have significant implications for reproductive healthcare, particularly in rural areas or low-and middleincome countries.

show abstract

Multimodal fusion model for classifying placenta ultrasound imaging in pregnancies with hypertension disorders

Cited by 4 publications

References 32 publications

Ultrasound-based radiomics model: a potential adjunctive tool for assessing impaired placental function in preeclampsia

Ultrasound-based radiomics model: a potential adjunctive tool for assessing impaired placental function in preeclampsia

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

Enhancing Automatic Placenta Analysis Through Distributional Feature Recomposition in Vision-Language Contrastive Learning

Contact Info

Product

Resources

About