Proposal for standardized ultrasound descriptors of abnormally invasive placenta (<scp>AIP</scp>)

Collins, Sally; Ashcroft, Anna; Braun, Thorsten; Calda, Pavel; Langhoff‐Roos, Jens; Morel, Olivier; Stefanović, Vedran; Tutschek, B.; Chantraine, Frédéric

doi:10.1002/uog.14952

Cited by 280 publications

(280 citation statements)

References 26 publications

(34 reference statements)

Supporting

Mentioning

249

Contrasting

Unclassified

Order By: Relevance

“…The ultrasound images were reviewed on the basis of standardized descriptions proposed by the European Working Group on Abnormally Invasive Placenta and the Ad‐hoc International Abnormally Invasive Placenta Expert Group . These ultrasound signs are summarized in Box .…”

Section: Methodsmentioning

confidence: 99%

Interobserver agreement on standardized ultrasound and histopathologic signs for the prenatal diagnosis of placenta accreta spectrum disorders

Zosmer

Jauniaux

Bunce

et al. 2017

Intl J Gynecology & Obste

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Interobserver agreement on standardized ultrasound and histopathologic signs for the prenatal diagnosis of placenta accreta spectrum disorders

Zosmer

Jauniaux

Bunce

et al. 2017

Intl J Gynecology & Obste

View full text Add to dashboard Cite

show abstract

“…However, as shown in Fig. 1, numerous, large, and irregular PL are more likely to occur in AIP cases than in non-AIP cases [4]. …”

Section: Introductionmentioning

confidence: 99%

Automatic Lacunae Localization in Placental Ultrasound Images via Layer Aggregation

Collins

Noble

2018

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

View full text Add to dashboard Cite

Accurate localization of structural abnormalities is a precursor for image-based prenatal assessment of adverse conditions. For clinical screening and diagnosis of abnormally invasive placenta (AIP), a life-threatening obstetric condition, qualitative and quantitative analysis of ultrasonic patterns correlated to placental lesions such as placental lacunae (PL) is challenging and time-consuming to perform even for experienced sonographers. There is a need for automated placental lesion localization that does not rely on expensive human annotations such as detailed manual segmentation of anatomical structures. In this paper, we investigate PL localization in 2D placental ultrasound images. First, we demonstrate the effectiveness of generating confidence maps from weak dot annotations in localizing PL as an alternative to expensive manual segmentation. Then we propose a layer aggregation structure based on iterative deep aggregation (IDA) for PL localization. Models with this structure were evaluated with 10-fold cross-validations on an AIP database (containing 3,440 images with 9,618 labelled PL from 23 AIP and 11 non-AIP participants). Experimental results demonstrate that the model with the proposed structure yielded the highest mean average precision (mAP=35.7%), surpassing all other baseline models (32.6%, 32.2%, 29.7%). We argue that features from shallower stages can contribute to PL localization more effectively using the proposed structure. To our knowledge, this is the first successful application of machine learning to placental lesion analysis and has the potential to be adapted for other clinical scenarios in breast, liver, and prostate cancer imaging.

show abstract

“…In placenta increta, the uterine villi invade in to the myometrium while in percreta, the villi pierce through the myometrium and may invade the adjacent organs including the urinary bladder [2]. Due to this abnormal invasion, MAP leads to failure of spontaneous placental separation resulting in severe peri-partum blood loss [4] which can eventually lead to hysterectomy. MAP has been shown to be associated with high fetomaternal morbidity and mortality [5].…”

Section: Introductionmentioning

confidence: 99%

Management, Complications and Outcomes of 14 Cases of Cesarean Scar Pregnancy in a Tertiary Care Hospital in Sri Lanka

2015

IJSR

View full text Add to dashboard Cite

Morbidly adherent placenta (MAP) is an umbrella term used to refer to abnormally invasive placentation further divided as placenta accrete, increta and percreta. In the presence of MAP, normal placental separation may fail to occur leading to increased perpartum blood loss and hysterectomy. With the increase in cesarean deliveries, the main risk factor for MAP, the incidence of the condition has increased and likely continue to do so in the near future. In this case series we describe the management and outcomes of 14 patients with MAP presenting to a single unit at a tertiary care hospital in Sri Lanka. Antenatal diagnosis using history and ISUOG ultrasound diagnostic criteria, preparation of detailed management plans in accordance with latest international recommendation and close supervision of the Consultant Obstetrician during operative management were the mainstays of management. Through this, the unit was able to maintain 100% maternal survival.

show abstract

Proposal for standardized ultrasound descriptors of abnormally invasive placenta (AIP)

Cited by 280 publications

References 26 publications

Interobserver agreement on standardized ultrasound and histopathologic signs for the prenatal diagnosis of placenta accreta spectrum disorders

Interobserver agreement on standardized ultrasound and histopathologic signs for the prenatal diagnosis of placenta accreta spectrum disorders

Automatic Lacunae Localization in Placental Ultrasound Images via Layer Aggregation

Management, Complications and Outcomes of 14 Cases of Cesarean Scar Pregnancy in a Tertiary Care Hospital in Sri Lanka

Contact Info

Product

Resources

About