基于MRI图像的羊水体积的测量

目的 探讨基于MRI图像,通过算法计算测量羊水量的可行性。方法 利用MatLab图像处理技术,对胎儿磁共振图像进行分割,提取目标区域并计算目标区域的面积,乘以层厚得出一层的体积,再将每层体积相加计算得到羊水总体积。结果 通过该算法最终计算得出羊水的体积为495.10 ml。定性分析显示,图像羊水分割边缘与原图目标区域的边缘拟合较好。定量分析显示,手动金标准分割的体积为458.20 ml,本研究算法与手动分割结果的误差率为8.06%。脂肪抑制序列图像分割效果定性评价亦显示羊水分割边缘与原图目标区域的边缘拟合较好;定量分析显示,金标准手动计算得到的羊水量为557.34 ml,本研究算法计算得到的羊水量为604.50 ml,与手动分割的误差率为8.46%。结论 采用本研究算法测量羊水量切实可行。     

Automatic Extraction of Hiatal Dimensions in 3-D Transperineal Pelvic Ultrasound Recordings

The aims of this work were to create a robust automatic software tool for measurement of the levator hiatal area on transperineal ultrasound (TPUS) volumes and to measure the potential reduction in variability and time taken for analysis in a clinical setting. The proposed tool automatically detects the C-plane (i.e., the plane of minimal hiatal dimensions) from a 3-D TPUS volume and subsequently uses the extracted plane to automatically segment the levator hiatus, using a convolutional neural network. The automatic pipeline was tested using 73 representative TPUS volumes. Reference hiatal outlines were obtained manually by two experts and compared with the pipeline's automated outlines. The Hausdorff distance, area, a clinical quality score, C-plane angle and C-plane Euclidean distance were used to evaluate C-plane detection and quantify levator hiatus segmentation accuracy. A visual Turing test was created to compare the performance of the software with that of the expert, based on the visual assessment of C-plane and hiatal segmentation quality. The overall time taken to extract the hiatal area with both measurement methods (i.e., manual and automatic) was measured. Each metric was calculated both for computer–observer differences and for inter-and intra-observer differences. The automatic method gave results similar to those of the expert when determining the hiatal outline from a TPUS volume. Indeed, the hiatal area measured by the algorithm and by an expert were within the intra-observer variability. Similarly, the method identified the C-plane with an accuracy of 5.76 ± 5.06° and 6.46 ± 5.18 mm in comparison to the inter-observer variability of 9.39 ± 6.21° and 8.48 ± 6.62 mm. The visual Turing test suggested that the automatic method identified the C-plane position within the TPUS volume visually as well as the expert. The average time taken to identify the C-plane and segment the hiatal area manually was 2 min and 35 ± 17 s, compared with 35 ± 4 s for the automatic result. This study presents a method for automatically measuring the levator hiatal area using artificial intelligence-based methodologies whereby the C-plane within a TPUS volume is detected and subsequently traced for the levator hiatal outline. The proposed solution was determined to be accurate, relatively quick, robust and reliable and, importantly, to reduce time and expertise required for pelvic floor disorder assessment.     

羊水过少的超声诊断及对围产儿的影响

目的：分析超声对羊水过少的诊断价值。方法：应用SIEMENS黑白超声诊断仪，采用最大羊水池深度（AFD）及羊水指数（AFI）指标，对140例妊娠晚期拟诊羊水过少患者，经腹部扫查；分娩后核实羊水量，评估超声对羊水过少的诊断价值。选择年龄相近羊水正常孕妇140例作为对照组，比较其分娩方式、胎儿窘迫、新生儿窒息、新生儿体重等指标的差异。结果：①应用AFD和AFI在妊娠晚期超声对羊水过少的诊断准确率为96．43％。②妊娠晚期经超声诊断的羊水过少孕妇发生胎儿窘迫、新生儿窒息、低体重儿的机会明显增加，与对照组相比，各指标间差异均有极显著性（P＜0．01）。结论：超声羊水过少准确率高，羊水过少是围产儿危险的征兆，须给予重视。     

Correlation between fetal gastric size and amniotic fluid volume

PURPOSE: Since abnormal conditions of the fetal digestive tract may alter both amniotic fluid volume and fetal gastric volume, we sought to determine whether amniotic fluid volume is correlated with fetal gastric volume in normal pregnancy. METHODS: A total of 280 fetal gastric size measurements were made prospectively from routine sonographic examinations of women with normal singleton pregnancies between 16 and 42 weeks of gestation. The fetal stomach was defined as the largest area including the pyloric site on transverse or oblique real-time sonographic scans. Gastric volume was calculated according to the formula for a prolate ellipsoid. The amniotic fluid index (AFI) was used for the evaluation of amniotic fluid volume. RESULTS: Both fetal gastric volume and AFI were significantly correlated with gestational age (R2= 0.422 and R2= 0.128, respectively). Only a weak correlation was found between gastric volume and AFI (R2= 0.036, p <0.001). On multivariate linear regression analysis adjusting for gestational age and fetal biometric measurements, gastric volume was not an independent and significant predictor of AFI. CONCLUSIONS: Although sonographically determined fetal gastric volume measurements appear to be useful in the assessment of fetal digestive tract anomalies, fetal gastric volume has no clinically significant effect on the amniotic fluid volume in normal pregnancy.     

Deep Learning Estimation of Median Nerve Volume Using Ultrasound Imaging in a Human Cadaver Model

Median nerve swelling is one of the features of carpal tunnel syndrome (CTS), and ultrasound measurement of maximum median nerve cross-sectional area is commonly used to diagnose CTS. We hypothesized that volume might be a more sensitive measure than cross-sectional area for CTS diagnosis. We therefore assessed the accuracy and reliability of 3-D volume measurements of the median nerve in human cadavers, comparing direct measurements with ultrasound images interpreted using deep learning algorithms. Ultrasound images of a 10-cm segment of the median nerve were used to train the U-Net model, which achieved an average volume similarity of 0.89 and area under the curve of 0.90 from the threefold cross-validation. Correlation coefficients were calculated using the areas measured by each method. The intraclass correlation coefficient was 0.86. Pearson's correlation coefficient R between the estimated volume from the manually measured cross-sectional area and the estimated volume of deep learning was 0.85. In this study using deep learning to segment the median nerve longitudinally, estimated volume had high reliability. We plan to assess its clinical usefulness in future clinical studies. The volume of the median nerve may provide useful additional information on disease severity, beyond maximum cross-sectional area.     

Accuracy of ultrasonography in evaluating amniotic fluid volume at less than 24 weeks' gestation.

The purpose of this investigation was to evaluate the accuracy of common sonographic techniques in assessing the amniotic fluid volume in pregnancies of less than 24 weeks' gestation. Patients at less than 24 weeks' gestation undergoing an amniocentesis for the placement of prostaglandin F2 alpha for termination (because of genetic or fetal anomalies, or both) were assessed for amniotic fluid volume. All fetuses were alive at the time of prostaglandin instillation. The amniotic fluid index and two-diameter pocket were used to determine the amniotic fluid volume. Prior to the prostaglandin instillation, the amniotic fluid volume was determined with para-aminohippurate using a diazo dye reaction with spectrophotometric analysis. The amniotic fluid volume was determined in 21 pregnancies between 15 and 24 weeks' gestation, yielding volumes ranging from 189 to 1840 ml. Using published standards for amniotic fluid volume in singleton pregnancies, oligohydramnios was present in three gestations, the volume was found to be normal in 15, and hydramnios complicated three pregnancies. The two-diameter pocket identified the amniotic fluid volumes correctly more often (18 of 21 [85.7%]) than the amniotic fluid index (10 of 21 [47.6%]) (P = 0.02). Normal amniotic fluid volume was identified in nine of 15 (60%) pregnancies by the amniotic fluid index and in 14 of 15 (93.3%) by the two-diameter pocket (P = not significant). Abnormal amniotic fluid volumes, oligohydramnios, and hydramnios were recognized more often by the two-diameter pocket (66.7%) than by the amniotic fluid index (1 of 6 [16.7%], P = not significant).     

人工智能辅助CT在COVID-19筛查及病情监测中的应用

目的探讨人工智能辅助CT在COVID-19病变筛查以及病情监测评估中的应用价值。方法收集27例COVID-19患者的CT影像资料,其中男性14例,女性13例,年龄28~85岁（48.9±14.3岁）。将图像输入基于深度学习模型的“uAI新冠肺炎智能辅助分析系统”,软件自动批量进行肺炎病灶识别和标记,并自动计算病变总体积、内部磨玻璃影体积及实变区域体积。通过PACS系统对人工智能辅助诊断软件识别病灶进行人工诊断复核,记录软件识别区域假阳性或假阴性情况,并通过手动修复少数假阳性或假阴性图像。结果人工智能辅助诊断软件可对肺炎病灶进行自动识别和标记,并计算出患者病灶总体积、内部磨玻璃影体积及实变区域体积。通过人工复核诊断显示人工智能辅助诊断软件对病灶标记的范围与肉眼观察相比具有较好的一致性。20例临床普通型患者均未见假阳性或假阴性病例;重症及危重症患者中有3例患者可见局部软件标记病灶呈假阳性表现,临床患者类型组间的差异有统计学意义（P<0.05）。人工智能辅助诊断软件提供的随访功能可直观的以图片及图表方式呈现两次检查病灶范围及密度变化的对比情况。人工复核诊断显示2例患者可见局部病灶标识区域呈假阴性表现,3例患者可见假阳性表现,临床患者类型组间的差异有统计学意义（P<0.05）。结论人工智能辅助CT可有效识别COVID-19病灶,并提供病灶相关数据信息。在患者病情评估方面通过图片及图表方式可直观的显示病变范围及内部密度差异的变化,为临床评效提供客观数据支持,同时提高了影像医师的工作效率。      

A reappraisal of amniotic fluid alpha-fetoprotein measurement at the time of genetic amniocentesis and midtrimester ultrasonography.

OBJECTIVE: To evaluate the contemporary utility of amniotic fluid alpha-fetoprotein measurement as a complementary test for fetal abnormalities at the time of invasive genetic testing. METHODS: A review of amniotic fluid alpha-fetoprotein test results was conducted to determine the frequency with which elevated alpha-fetoprotein values added independent diagnostic information and altered clinical management. Amniotic fluid specimens processed for alpha-fetoprotein between 1995 and 1998 were included. Elevated alpha-fetoprotein cases were classified as either incidental to the fetal abnormality diagnosed or central to the identification of a fetal anomaly on the basis of whether an ultrasonographic examination had already identified the anomaly before amniocentesis. The costs associated with alpha-fetoprotein testing were used to estimate the expenditure per pregnancy in which elevated alpha-fetoprotein values would add discriminatory diagnostic value. A hypothetical national cost model was constructed to explore the utility of selective rather than routine amniotic fluid alpha-fetoprotein measurement. RESULTS: Eighty-two (3%) of 2769 amniotic fluid alpha-fetoprotein values were elevated. In only 1 instance was the elevated result found to be partially discriminatory (e.g., an established diagnosis of microcephaly with an associated small encephalocele identified after the elevated amniotic fluid alpha-fetoprotein value prompted repeated ultrasonographic assessment). Sixty-one other neural tube defects were detected by ultrasonography alone (myelomeningocele, n = 28; anencephaly, n = 24; and encephalocele, n = 9). Thus, an elevated alpha-fetoprotein result added diagnostic precision in only 1 (0.036%) of 2769 cases. Cost estimates suggested that routine amniotic fluid alpha-fetoprotein assessment resulted in a $219,000 expenditure per informative case. CONCLUSIONS: Routine measurement of amniotic fluid alpha-fetoprotein during amniocentesis may not be warranted in centers with expertise in targeted ultrasonographic imaging.     

Assessment of the third-trimester fetus using 3-dimensional volumes: a pilot study

PURPOSE: To examine whether the third-trimester fetus can be assessed sonographically using 3-dimensional (3D) volume data sets. METHODS: Twenty-seven consecutive third-trimester fetuses were evaluated. Fetuses were scanned using 2-dimensional (2D) imaging followed by 5 3D volume acquisitions. The initial scan was interpreted and reported based on the 2D images. The 3D volume data sets were independently reviewed offline several weeks later by 2 sonologists. Parameters evaluated included fetal presentation, placental location, amniotic fluid volume, fetal biometry including a calculation of estimated fetal weight, and major fetal anatomic structures. The result of the interpretation via 3D reconstruction of the volume from each of the 2 sonologists was compared with the original 2D sonography report. RESULTS: Fetal presentation, amniotic fluid volume, and placental location with respect to the cervix were correctly identified 100% of the time by each sonologist. The estimated fetal weight was within 10% of the 2D estimate 89% (95% CI, 0.71-0.98) of the time for sonologist A and 96% (95% CI, 0.81-0.99) of the time for sonologist B. The majority of major anatomic landmarks were adequately seen by both sonologists. CONCLUSION: Offline review of 3D volume data sets is a reliable method for determining fetal presentation, amniotic fluid volume, placental location, and estimating fetal weight in the third trimester.     

Sonographic assessment of amniotic fluid volume between 11 and 24 weeks of gestation: construction of reference intervals related to gestational age.

OBJECTIVE: At present, most of the methods for sonographic assessment of amniotic fluid volume are unreliable in the second trimester of pregnancy, or else they do not present nomograms related to gestational age. DESIGN: The aim of this prospective cross-sectional study was to construct normal reference ranges of four ultrasound parameters for the evaluation of amniotic fluid volume which could be applied in the second trimester. For these parameters we calculated normal curve limits suitable for use in clinical practice. SUBJECTS: From a population of normal pregnant women between the 12th and the 24th weeks of gestation undergoing a routine ultrasound examination during 1997 at our institute, 273 were found to be suitable for the study, after the exclusion of all cases which presented any feto-maternal pathology or complications up to the 24th week. METHODS: The largest 'amniotic pocket' in a vertical direction, free of small fetal parts and umbilical cord, was measured: the maximum vertical and transverse diameters were measured on the same scan; the mean diameter and the product of the two diameters were calculated. The 'mean amniotic fluid diameter', the 'two-diameter pocket', the 'largest vertical pocket' and the 'largest transverse pocket' were the four sonographic parameters considered. RESULTS: The four parameters correlated well with gestational week and with the biparietal diameter; the normal reference intervals and normal curve were then calculated. All these parameters were found to have good intra- and interoperative reproducibility. CONCLUSIONS: We conclude that the use of an ultrasound semiquantitative method based on the measurement of a single amniotic fluid pocket and involving normal reference intervals according to gestational age could improve the early diagnosis of amniotic fluid variations during the second trimester, although this has yet to be confirmed by extensive clinical trials.     

Subjective versus objective evaluation of amniotic fluid volume of pregnancies of less than 24 weeks' gestation: how can we be accurate?

This study was undertaken to compare subjective versus objective ultrasonic evaluation of amniotic fluid volume in pregnancies of less than 24 weeks' gestation. Amniotic fluid volume was subjectively (visualization without ultrasonic measurements) and objectively (visual interpretation with ultrasonic measurements) evaluated in 42 singleton pregnancies undergoing termination. The actual amniotic fluid volume was then determined using a dye-dilution technique. The women evaluated were in their mid-20s, primarily African American, and between 15 and 23 weeks' gestation. There was no significant difference in the total number of correct estimates of amniotic fluid volume when the data were stratified by level of operator experience (P = .34), ultrasonic technique (P = .33), or the combined correct subjective versus combined correct objective estimates (P = .68). We have concluded that the accuracy of amniotic fluid volume assessment in pregnancies of less than 24 weeks is not influenced by the level of operator experience or the type of ultrasonic measurement.     

Does measurement of amniotic fluid index detect changes in amniotic fluid volume after second-trimester amniocentesis?

The objective of this study was to establish whether variations of amniotic fluid volume induced by second-trimester amniocentesis could be detected by serial measurements of amniotic fluid index. A total of 130 singleton pregnancies undergoing second-trimester amniocentesis for genetic indications were considered. Amniotic fluid index was measured at three different time intervals: 30-60 min before amniocentesis, immediately after the procedure, and 60 min after the procedure. Serial measurements were obtained either by a single operator (n = 55) or by the three independent operators (n = 75). Significantly lower amniotic fluid index values were demonstrated immediately after amniocentesis when compared with the pre-amniocentesis and subsequent measurements in the study design with both the single and multiple operators. No statistically significant changes were found between the first amniotic fluid index measurements and those obtained 1 h after amniocentesis. These results suggest that second-trimester amniocentesis induces a temporary decrease of amniotic fluid volume detectable by serial amniotic fluid index measurements, no longer evident 1 h after the procedure.     

The accuracy of ultrasound evaluation of amniotic fluid volume in singleton pregnancies: The effect of operator experience and ultrasound interpretative technique

The objective of this study was to evaluate the effect of operator experience and ultrasound interpretation technique on the accuracy of ultrasound estimates of amniotic fluid volume. Ultrasound evaluation was carried out by an obstetric resident, a nurse sonographer, a maternal-fetal medicine fellow, and a maternal-fetal medicine staff member to subjectively estimate (visual interpretation without sonographic measurements) amniotic fluid volume in 63 pregnancies. Amniotic fluid volume was also evaluated using ultrasound measurements based on the largest vertical pocket technique, the amniotic fluid index, and the two-diameter pocket method. The accuracy of these ultrasound estimates was assessed by comparing the ultrasound results to actual amniotic fluid volume as determined by a dye-dilution technique. For analysis, amniotic fluid volumes were classified as oligohydramnios, normal, or hydramnios using established volumetric criteria for singleton pregnancies. Subjective estimates ranged from 65% to 70% correct and did not differ by operator experience except for the more accurate diagnosis of hydramnios by the maternal-fetal medicine staff. The three sonographic measurements were similar in overall accuracy (59–67%). The two-diameter pocket method was, however, significantly more accurate in identifying oligohydramnios. It appears that neither operator experience nor sonographic technique greatly affects the accuracy of ultrasound estimates of amniotic fluid volume. © 1997 John Wiley & Sons, Inc. J Clin Ultrasound 25:249–253, 1997     

Objective method of diagnosing oligohydramnios in postterm pregnancies

Oligohydramnios is an important factor influencing the management of postterm pregnancies. However, sonographic assessment of oligohydramnios has been based largely on the subjective judgement of the sonologist. From January 1982 to December 1984, 54 patients had articulated-arm B-scan ultrasound examinations and were identified as postterm. Of these patients, 25 were subjectively diagnosed as having oligohydramnios. Five patients were considered to have low normal amounts of amniotic fluid. The remainder were considered to have normal or greater than normal quantities of amniotic fluid. From this population, an amniotic fluid index was determined for each patient by finding the product of the length, width, and depth of the largest amniotic fluid pocket. Patients with a fluid index less than 60 showed a strong association with the postmaturity syndrome. Indeed, all but one postmature infant was born of a pregnancy with a fluid index less than 60. No other fetal or perinatal complications were statistically correlated with oligohydramnios in this small patient series.     

Effect of indomethacin on individual amniotic fluid indices in multiple gestations.

To determine the effect of indomethacin on the amniotic fluid index of individual fetuses in multiple gestations, we evaluated seven sets of twins and two sets of triplets in preterm labor (eight cases) or with polyhydramnios (one case). The dose of oral indomethacin was either 25 mg every 12 hours or 25 mg every 6 hours. The amniotic fluid volume of individual amniotic sacs was estimated serially by the amniotic fluid index. When an oral dose of indomethacin of 25 mg every 6 hours was used, oligohydramnios eventually occurred in five of eight amniotic sacs and a subjective decrease in amniotic fluid occurred in one sac. Oligohydramnios was detected in only one of 13 amniotic sacs when the dose of indomethacin was 25 mg every 12 hours. The amniotic fluid volume returned to normal in these seven amniotic sacs within 4 days of discontinuing indomethacin. We conclude that maternal indomethacin therapy has a variable effect on the individual amniotic fluid volumes in multiple gestations.     

胎儿期中胚层肾瘤超声特征及病理对照分析

目的 总结胎儿期中胚层肾瘤的超声表现并与病理组织学类型对照分析.方法 对2003年1月至2018年12月湖北省妇幼保健院产前超声发现肾区肿块并经病理证实的4例中胚层肾瘤胎儿的超声图像、磁共振影像特征、病理组织学类型及随访结果进行综合分析.结果 4例中胚层肾瘤超声特征:4例胎儿中胚层肾瘤均于晚孕期被检出,发现肿块时径线均...     

Analysis and validation of automated skull stripping tools: a validation study based on 296 MR images from the Honolulu Asia aging study

As population-based epidemiologic studies may acquire images from thousands of subjects, automated image post-processing is needed. However, error in these methods may be biased and related to subject characteristics relevant to the research question. Here, we compare two automated methods of brain extraction against manually segmented images and evaluate whether method accuracy is associated with subject demographic and health characteristics. MRI data (n = 296) are from the Honolulu Asia Aging Study, a population-based study of elderly Japanese-American men. The intracranial space was manually outlined on the axial proton density sequence by a single operator. The brain was extracted automatically using BET (Brain Extraction Tool) and BSE (Brain Surface Extractor) on axial proton density images. Total intracranial volume was calculated for the manually segmented images (ticvM), the BET segmented images (ticvBET) and the BSE segmented images (ticvBSE). Mean ticvBSE was closer to that of ticvM, but ticvBET was more highly correlated with ticvM than ticvBSE. BSE had significant over (positive error) and underestimated (negative error) ticv, but net error was relatively low. BET had large positive and very low negative error. Method accuracy, measured in percent positive and negative error, varied slightly with age, head circumference, presence of the apolipoprotein eepsilon4 polymorphism, subcortical and cortical infracts and enlarged ventricles. This epidemiologic approach to the assessment of potential bias in image post-processing tasks shows both skull-stripping programs performed well in this large image dataset when compared to manually segmented images. Although method accuracy was statistically associated with some subject characteristics, the extent of the misclassification (in terms of percent of brain volume) was small.     

Quantification of the focal progression of coronary atherosclerosis through automated co-registration of virtual histology-intravascular ultrasound imaging data

The goal of this study was to evaluate the accuracy of a novel algorithm that circumferentially co-registers serial virtual histology-intravascular ultrasound (VH-IVUS) data for the focal assessment of coronary atherosclerosis progression. Thirty-three patients with an abnormal non-invasive cardiac stress test or stable angina underwent baseline and follow-up (6 or 12 months) invasive evaluation that included acquisition of VH-IVUS image data. Baseline and follow-up image pairs (n?=?4194) were automatically co-registered in the circumferential direction via a multi-variate cross-correlation algorithm. Algorithm stability and accuracy were assessed by comparing results from multiple iterations of the algorithm (iteration 1 vs. iteration 2) and against values determined manually by two expert VH-IVUS readers (algorithm vs. two expert readers). Furthermore, focal plaque progression values were compared between the algorithm and expert readers following co-registration by the independently determined angles. Strong agreement in circumferential co-registration angles were observed across multiple iterations of the algorithm (stability) and between the algorithm and expert readers (accuracy; all concordance correlation coefficients >0.98). Furthermore, circumferential co-registration angles determined by the algorithm were not statistically when compared to values determined by two expert readers (p?=?0. 99). Bland–Altman analysis indicated minimal bias when comparing focal VH-IVUS defined plaque progression in corresponding sectors following circumferential co-registration between the algorithm and expert readers. Finally, average differences in changes in total plaque and constituent areas between the algorithm and readers were within the average range of difference between readers (interobserver variability). We present a stable and validated algorithm to automatically circumferentially co-register serial VH-IVUS imaging data for the focal quantification of coronary atherosclerosis progression.     

孕早、中期人体鱼序列征胎儿超声表现

目的 观察孕早、中期人体鱼序列征胎儿超声表现。方法 回顾性分析22胎经引产证实的人体鱼序列征胎儿超声表现，对比观察孕早、中期差异。结果 22胎中，9胎于孕早期诊断，超声表现为羊水量正常或略少，胎儿双下肢融合、足缺如或发育不良及单脐动脉起自高位腹主动脉，其中5胎双足并腿畸形、1胎单足并腿畸形，3胎无足并腿畸形，8胎(8/9,88.89%)合并其他结构畸形；13胎于孕中期诊断，超声表现为无羊水或羊水过少，胎儿双下肢融合、单脐动脉起自高位腹主动脉、肾脏发育不良，膀胱均未显示，其中4胎双足并腿畸形、3胎单足并腿畸形，6胎无足并腿畸形，9胎(9/13,69.23%)合并其他结构畸形。结论 人体鱼序列征胎儿孕早、中期典型超声表现包括并腿畸形及单脐动脉起自高位腹主动脉；孕早期羊水充足，为最佳诊断时机。     

The sensitivity and specificity of subjective and a semi-quantitative technique of amniotic fluid volume assessment in predicting intrapartum morbidity.

The aim of this study was to evaluate the ability of two techniques of amniotic fluid volume assessment to predict intrapartum morbidity in a high-risk population. A total of 213 pregnant women at the Grace Maternity Hospital, Vancouver, Canada were examined ultrasonically and the amniotic fluid volume was assessed subjectively and using the amniotic fluid index. Both techniques showed high specificity and negative predictive values for all outcome measures, but had an associated poor sensitivity and positive predictive value. Both techniques were similar in their ability to identify situations involving intrapartum morbidity. It is concluded that amniotic fluid assessment is a weak predictor of intrapartum morbidity but may be useful in certain conditions such as when the pregnancy is post-dates.