Search

Francesco Conversano,1 Giulia Soloperto,1 Antonio Greco,1 Andrea Ragusa,1,2 Ernesto Casciaro,1 Fernanda Chiriacò,1 Christian Demitri,3 Giuseppe Gigli,2–5 Alfonso Maffezzoli,3 Sergio Casciaro11National Research Council, Institute of Clinical Physiology, Lecce, Italy; 2National Nanotechnology Laboratory of CNR-NANO, Lecce, Italy; 3University of Salento, Department of Engineering for Innovation, Lecce, Italy; 4Italian Institute of Technology – Center for Biomolecular Nanotechnology (CBN-IIT), Arnesano, Italy; 5University of Salento, Department of Mathematics and Physics ‘Ennio De Giorgi’, Lecce, ItalyPurpose: To evaluate the diagnostic performance of gold nanorod (GNR)-enhanced optoacoustic imaging employing a conventional echographic device and to determine the most effective operative configuration in order to assure optoacoustic effectiveness, nanoparticle stability, and imaging procedure safety.Methods: The most suitable laser parameters were experimentally determined in order to assure nanoparticle stability during the optoacoustic imaging procedures. The selected configuration was then applied to a novel tissue-mimicking phantom, in which GNR solutions covering a wide range of low concentrations (25–200 pM) and different sample volumes (50–200 µL) were exposed to pulsed laser irradiation. GNR-emitted optoacoustic signals were acquired either by a couple of single-element ultrasound probes or by an echographic transducer. Off-line analysis included: (a) quantitative evaluation of the relationships between GNR concentration, sample volume, phantom geometry, and amplitude of optoacoustic signals propagating along different directions; (b) echographic detection of “optoacoustic spots,” analyzing their intensity, spatial distribution, and clinical exploitability. MTT measurements performed on two different cell lines were also used to quantify biocompatibility of the synthesized GNRs in the adopted doses.Results: Laser irradiation at 30 mJ/cm2 for 20 seconds resulted in the best compromise among the requirements of effectiveness, safety, and nanoparticle stability. Amplitude of GNR-emitted optoacoustic pulses was proportional to both sample volume and concentration along each considered propagation direction for all the tested boundary conditions, providing an experimental confirmation of isotropic optoacoustic emission. Average intensity of echographically detected spots showed similar behavior, emphasizing the presence of an “ideal” GNR concentration (100 pM) that optimized optoacoustic effectiveness. The tested GNRs also exhibited high biocompatibility over the entire considered concentration range.Conclusion: An optimal configuration for GNR-enhanced optoacoustic imaging was experimentally determined, demonstrating in particular its feasibility with a conventional echographic device. The proposed approach can be easily extended to quantitative performance evaluation of different contrast agents for optoacoustic imaging.Keywords: photoacoustic imaging, tissue-mimicking phantom, laser, nanoparticle degradation

This article discusses a preliminary study on the feasibility of using an automatic algorithm to assess the likelihood of successful instrumental delivery in obstetrics. The algorithm analyzes ultrasound images to measure parameters such as the occiput position, head-perineum distance, and midline angle, and assigns a color code (green, yellow, or red) indicating the chances of success. The study found that the algorithm had a sensitivity of 0.80 and specificity of 0.82 for the green code, and a sensitivity of 0.64 and specificity of 0.80 for the yellow code. The authors conclude that these preliminary results are encouraging and suggest the potential for further improvements in clinical decision-making for delivery management. [Extracted from the article]

Objectives: To describe a newly developed machine-learning (ML) algorithm for the automatic recognition of fetal head position using transperineal ultrasound (TPU) during the second stage of labor and to describe its performance in differentiating between occiput anterior (OA) and non-OA positions.Methods: This was a prospective cohort study including singleton term (> 37 weeks of gestation) pregnancies in the second stage of labor, with a non-anomalous fetus in cephalic presentation. Transabdominal ultrasound was performed to determine whether the fetal head position was OA or non-OA. For each case, one sonographic image of the fetal head was then acquired in an axial plane using TPU and saved for later offline analysis. Using the transabdominal sonographic diagnosis as the gold standard, a ML algorithm based on a pattern-recognition feed-forward neural network was trained on the TPU images to discriminate between OA and non-OA positions. In the training phase, the model tuned its parameters to approximate the training data (i.e. the training dataset) such that it would identify correctly the fetal head position, by exploiting geometric, morphological and intensity-based features of the images. In the testing phase, the algorithm was blinded to the occiput position as determined by transabdominal ultrasound. Using the test dataset, the ability of the ML algorithm to differentiate OA from non-OA fetal positions was assessed in terms of diagnostic accuracy. The F1 -score and precision-recall area under the curve (PR-AUC) were calculated to assess the algorithm's performance. Cohen's kappa (κ) was calculated to evaluate the agreement between the algorithm and the gold standard.Results: Over a period of 24 months (February 2018 to January 2020), at 15 maternity hospitals affiliated to the International Study group on Labor ANd Delivery Sonography (ISLANDS), we enrolled into the study 1219 women in the second stage of labor. On the basis of transabdominal ultrasound, they were classified as OA (n = 801 (65.7%)) or non-OA (n = 418 (34.3%)). From the entire cohort (OA and non-OA), approximately 70% (n = 824) of the patients were assigned randomly to the training dataset and the rest (n = 395) were used as the test dataset. The ML-based algorithm correctly classified the fetal occiput position in 90.4% (357/395) of the test dataset, including 224/246 with OA (91.1%) and 133/149 with non-OA (89.3%) fetal head position. Evaluation of the algorithm's performance gave an F1 -score of 88.7% and a PR-AUC of 85.4%. The algorithm showed a balanced performance in the recognition of both OA and non-OA positions. The robustness of the algorithm was confirmed by high agreement with the gold standard (κ = 0.81; P < 0.0001).Conclusions: This newly developed ML-based algorithm for the automatic assessment of fetal head position using TPU can differentiate accurately, in most cases, between OA and non-OA positions in the second stage of labor. This algorithm has the potential to support not only obstetricians but also midwives and accoucheurs in the clinical use of TPU to determine fetal occiput position in the labor ward. © 2021 International Society of Ultrasound in Obstetrics and Gynecology. [ABSTRACT FROM AUTHOR]

Objective: To evaluate the performance of a new ultrasound technique for the automatic assessment of the change in head–perineum distance (delta‐HPD) and angle of progression (delta‐AoP) during the active phase of the second stage of labor. Methods: This was a prospective observational cohort study including singleton term pregnancies with fetuses in cephalic presentation during the active phase of the second stage of labor. In each patient, two videoclips of 10 s each were acquired transperineally, one in the axial and one in the sagittal plane, between rest and the acme of an expulsive effort, in order to measure HPD and AoP, respectively. The videoclips were processed offline and the difference between the acme of the pushing effort and rest in HPD (delta‐HPD) and AoP (delta‐AoP) was calculated, first manually by an experienced sonographer and then using a new automatic technique. The reliability of the automatic algorithm was evaluated by comparing the automatic measurements with those obtained manually, which was considered as the reference gold standard. Results: Overall, 27 women were included. A significant correlation was observed between the measurements obtained by the automatic and the manual methods for both delta‐HPD (intraclass correlation coefficient (ICC) = 0.97) and delta‐AoP (ICC = 0.99). The high accuracy provided by the automatic algorithm was confirmed by the high values of the coefficient of determination (r2 = 0.98 for both delta‐HPD and delta‐AoP) and the low residual errors (root mean square error = 1.2 mm for delta‐HPD and 1.5° for delta‐AoP). A Bland–Altman analysis showed a mean difference of 0.52 mm (limits of agreement, −1.58 to 2.62 mm) for delta‐HPD (P = 0.034) and 0.35° (limits of agreement, −2.54 to 3.09°) for delta‐AoP (P = 0.39) between the manual and automatic measurements. Conclusions: The automatic assessment of delta‐AoP and delta‐HPD during maternal pushing efforts is feasible. The automatic measurement of delta‐AoP appears to be reliable when compared with the gold standard manual measurement by an experienced operator. Copyright © 2020 ISUOG. Published by John Wiley & Sons Ltd. [ABSTRACT FROM AUTHOR]

To develop an artificial intelligence-based algorithm toward the automatic classification of Anterior/Posterior/Transverse Occiput position images acquired by means of transperineal sonography. In our approach, two Convolutional Neural Networks (CNNs) were independently trained to classify Anterior/non-Anterior (CNN SB A/nA sb ) and Posterior/Transverse (CNN SB P/T sb ), respectively. [Extracted from the article]

Objective: To evaluate the accuracy and reliability of an automatic ultrasound technique for assessment of the angle of progression (AoP) during labor.Methods: Thirty-nine pregnant women in the second stage of labor, with fetus in cephalic presentation, underwent conventional labor management with additional translabial sonographic examination. AoP was measured in a total of 95 acquisition sessions, both automatically by an innovative algorithm and manually by an experienced sonographer, who was blinded to the algorithm outcome. The results obtained from the manual measurement were used as the reference against which the performance of the algorithm was assessed. In order to overcome the common difficulties encountered when visualizing by sonography the pubic symphysis, the AoP was measured by considering as the symphysis landmark its centroid rather than its distal point, thereby assuring high measurement reliability and reproducibility, while maintaining objectivity and accuracy in the evaluation of progression of labor.Results: There was a strong and statistically significant correlation between AoP values measured by the algorithm and the reference values (r = 0.99, P < 0.001). The high accuracy provided by the automatic method was also highlighted by the corresponding high values of the coefficient of determination (r2  = 0.98) and the low residual errors (root mean square error = 2°27' (2.1%)). The global agreement between the two methods, assessed through Bland-Altman analysis, resulted in a negligible mean difference of 1°1' (limits of agreement, 4°29').Conclusions: The proposed automatic algorithm is a reliable technique for measurement of the AoP. Its (relative) operator-independence has the potential to reduce human errors and speed up ultrasound acquisition time, which should facilitate management of women during labor. Copyright © 2017 ISUOG. Published by John Wiley & Sons Ltd. [ABSTRACT FROM AUTHOR]

Acoustic sensing is a viable approach for solving issues related to many applications, namely, biomedical, distance measurements, mechanical, health infrastructure monitoring, etc. It is generally sustainable and of no negative impact on the object under test. The use of acoustic sensing under beamforming technique is an important asset to be exploited, especially for the aforementioned applications. This paper illustrates a generalized approach of modeling and designing a full beamfomer using two specific classes: LCMP (Linear Constrained Minimum Power) beamformers that are used to overcome robustness limitations and MVDR (Minimum Variance Distortionless Response) beamformers. Any aspect of modeling and designing is always related to the DOA (Direction of Arrival). The obtained results are based on assumptions extracted from an actual case of constructed system. [ABSTRACT FROM AUTHOR]

Diagnosis by imaging is one of the most important findings in biomedical imaging because it allows not only the diagnosing of a specific pathology but to perform online and offline surgical operations using imaging as it is noticed in interventional radiology. This paper illustrates the use Hough transform in identifying pathological structures included in CT (Computer Tomography) and HRCT (High Resolution Computer Tomography) images related to patients suffering from lung disease. These abnormal areas appear as bulges of the trophic vessels and they are similar to circular structures with level of lighter gray near to white. Circular Hough transform (CHT) identifies regions with a circular shape. However, a metrics is defined in order to understand if the pointed out area has a pathological morphology. CHT is used here for helping to detect possible events of indolent tumors or undetermined significance pathologies for lung apparatus. For this aim, we use entropy approach with CHT because it measures the scatter of the directional elements in an image. In fact a high entropy value is related to areas with a strong contrast in grayscale, and abnormalities in the image are present as a set of points with more lighter than the dark background. The results have shown, by means of an accuracy true table, rendering a comparison between clinicians'diagnosis and CHT detection, it is possible to indicate, with a better accuracy, potential areas of undetermined significance pathologies. Finally, a receiver operational curve (ROC) is used as an accuracy index for evaluating the positive impact of entropy on diagnosis. [ABSTRACT FROM AUTHOR]

The aim of the present work was to demonstrate the possibility of selective detection of nanoparticle contrast agents (NPCAs) on diagnostic echographic images by exploiting the second harmonic component they introduce in the spectra of corresponding ultrasound signals, as a consequence of nonlinear distortion during ultrasound propagation. We employed silica nanospheres (SiNSs) of variable diameter (160 nm, 330 nm, and 660 nm) dispersed in different volume concentrations (range 0.07-0.8%) in agarose gel samples that were automatically scanned through a digital ecograph using narrow-band ultrasound pulses at 6.6 MHz and variable mechanical index (MI range 0.2-0.6). In the first part of the study, the intensity peaks of four different spectral components of the backscattered signal were considered: fundamental (detected in correspondence of the incident ultrasound frequency), subharmonic (detected at half of the fundamental frequency), ultra harmonic (detected at 1.5 times the fundamental frequency), and second harmonic (detected at twice the fundamental frequency). Subsequently, based on the experimental results of the first part of the study and on our recently reported findings, the focus was moved to a detailed comparison between subharmonic and second harmonic trend, which were determined as a function of nanoparticle composition, sample concentration, and MI. The experiments were also repeated on different agarose samples, containing SiNSs covered by an outer shell of smaller magnetic nanoparticles, made of either iron oxide (IO) or FePt-IO nanocrystals. Obtained results show that this new ultrasound-based method for NPCA imaging has a detection sensitivity similar to that of our previously introduced subharmonic-based technique in the presence of 330-nm SiNSs, but performs significantly better in the detection of both the types of “dual mode” NPCAs. The fact that the reported detection method was optimized for identification of 330-nm SiNSs (a sort of “ideal” size for the development of novel tumor-targeting NPCAs) and that the magnetically coated particles are detectable also through magnetic resonance imaging makes the presented second harmonic ultrasound method a valuable solution for the introduction of new protocols for multimodal molecular diagnoses employing only nonionizing radiations. [ABSTRACT FROM PUBLISHER]

Recent literature has reported increasing interest in using contrast agents for ultrasound imaging, in the form of shelled gas microbubbles, for innovative advanced purposes such as noninvasive targeted imaging and drug delivery. Effectiveness of such agents is time-dependent and is determined by microbubble dissolution behavior, a complex phenomenon whose knowledge is still limited. In the present study, we monitored the microbubbles of an experimental phospholipid-shelled perfluorobutane contrast agent through time-scheduled size distribution measurements. The diameter-time curve we obtained for shelled perfluorobutane microbubbles showed a rapid diameter increment up to about 1.4 times the initial value, followed by a slow decrement towards bubble disappearance. This behavior is qualitatively similar to the one theoretically predicted by Kabalnov's model for unshelled bubbles, with an extended lifetime due to shell effect. Kabalnov's model, devised for spontaneous dissolution of unshelled microbubbles, was consequently modified in order to get a proper prediction of experimental results also in the case of encapsulated bubbles. A theoretical diameter-time curve was then derived from this new model and fitted to our experimental data points, to estimate microbubble surface tension and to determine the value of an empirical parameter accounting for the shell effect. The proposed model has the potential to predict the dissolution behavior of all kinds of microbubble contrast agents for ultrasound imaging and the adopted experimental methodology represents a new and simple way to estimate microbubble surface tension, essential also for predicting microbubble oscillation performance. [ABSTRACT FROM PUBLISHER]

An adaptive initialization method was developed to produce fully automatic processing frameworks based on graph-cut and gradient flow active contour algorithms. This method was applied to abdominal Computed Tomography (CT) images for segmentation of liver tissue and hepatic tumors. Twenty-five anonymized datasets were randomly collected from several radiology centres without specific request on acquisition parameter settings nor patient clinical situation as inclusion criteria. Resulting automatic segmentations of liver tissue and tumors were compared to their reference standard delineations manually performed by a specialist. Segmentation accuracy has been assessed through the following evaluation framework: dice similarity coefficient (DSC), false negative ratio (FNR), false positive ratio (FPR) and processing time. Regarding liver surfaces, graph-cuts achieved a DSC of 95.49% ( FPR=2.35% and FNR=5.10%), while active contours reached a DSC of 96.17% (FPR=3.35% and FNR=3.87%). The analyzed datasets presented 52 tumors: graph-cut algorithm detected 48 tumors with a DSC of 88.65%, while active contour algorithm detected only 44 tumors with a DSC of 87.10%. In addition, in terms of time performances, less time was requested for graph-cut algorithm with respect to active contour one. The implemented initialization method allows fully automatic segmentation leading to superior overall performances of graph-cut algorithm in terms of accuracy and processing time. The initialization method here presented resulted suitable and reliable for two different segmentation techniques and could be further extended. [ABSTRACT FROM PUBLISHER]

Rationale and Objectives: The aim of this study was to identify the optimal parameter configuration of a new algorithm for fully automatic segmentation of hepatic vessels, evaluating its accuracy in view of its use in a computer system for three-dimensional (3D) planning of liver surgery. Materials and Methods: A phantom reproduction of a human liver with vessels up to the fourth subsegment order, corresponding to a minimum diameter of 0.2 mm, was realized through stereolithography, exploiting a 3D model derived from a real human computed tomographic data set. Algorithm parameter configuration was experimentally optimized, and the maximum achievable segmentation accuracy was quantified for both single two-dimensional slices and 3D reconstruction of the vessel network, through an analytic comparison of the automatic segmentation performed on contrast-enhanced computed tomographic phantom images with actual model features. Results: The optimal algorithm configuration resulted in a vessel detection sensitivity of 100% for vessels > 1 mm in diameter, 50% in the range 0.5 to 1 mm, and 14% in the range 0.2 to 0.5 mm. An average area overlap of 94.9% was obtained between automatically and manually segmented vessel sections, with an average difference of 0.06 mm(2). The average values of corresponding false-positive and false-negative ratios were 7.7% and 2.3%, respectively. Conclusions: A robust and accurate algorithm for automatic extraction of the hepatic vessel tree from contrast-enhanced computed tomographic volume images was proposed and experimentally assessed on a liver model, showing unprecedented sensitivity in vessel delineation. This automatic segmentation algorithm is promising for supporting liver surgery planning and for guiding intraoperative resections. [ABSTRACT FROM AUTHOR]

Accurate knowledge of the liver structure, including liver surface and lesion localization, is usually required in treatments such as liver tumor ablations and/or radiotherapy. This paper presents a new method and corresponding algorithm for fast segmentation of the liver and its internal lesions from CT scans. No interaction between the user and analysis system is required for initialization since the algorithm is fully automatic. A statistical model-based approach was created to distinguish hepatic tissue from other abdominal organs. It was combined to an active contour technique using gradient vector flow in order to obtain a smoother and more natural liver surface segmentation. Thereafter, automatic classification was performed to isolate hepatic lesions from liver parenchyma. Twenty-one datasets, presenting different anatomical and pathological situations, have been processed and analyzed. Special focus has been driven to the resulting processing time together with quality assessment. Our method allowed robust and efficient liver and lesion segmentations very close to the ground truth, in a relatively short processing time (average of 11.4 s for a 512 x 512-pixel slice). A volume overlap of 94.2% and an accuracy of 3.7 mm were achieved for liver surface segmentation. Sensitivity and specificity for tumor lesion detection were 82.6% and 87.5%, respectively. [ABSTRACT FROM AUTHOR]

Although in recent years the use of purine analogues has increased the percentage of long‐term complete response the effect on overall survival of HCL patients is not yet clear. This study aimed to evaluate the long‐term outcome (mean follow up of 92 months) of sixty‐four patients receiving IFN as first‐line therapy. IFN was well tolerated and effective. The overall response rate was 91% (PR 65%, CR 13%, GPR 13%). Forty‐one patients (63%) received IFN 3 MU/wk as maintenance therapy. The 10‐yr projected survival rate of responding patients (CR and GPR 100%; PR 95%) and non responders (SD, PD 80%) clearly shows that type of response does not affect survival. Patients receiving IFN maintenance had a statistically higher PFS than those who did not (p<0.01). This study shows that IFN is still one of the standard therapies for this disease, that achieving CR has no primary relevance for the control of the disease, and that good utilization of therapeutic resources may assure HCL patients a survival rate comparable to that of a normal, healthy population. [ABSTRACT FROM AUTHOR]

The ML-based algorithm correctly classified the fetal occiput position in 90.6% of cases (357 out of 395), including 224/246 (91.0%) OA and 133/149 (89.3%) non-OA positions. Firstly, transabdominal ultrasound was performed to assess the fetal occiput position, which was labelled into occiput anterior (OA) or non-OA and represented the gold standard reference for training and validation. To develop a machine learning (ML) algorithm for the automatic classification of fetal occiput position at transperineal ultrasound (TPU) during the second stage of labour. [Extracted from the article]

EP27.35: A new ultrasound-based Artificial intelligence system for the automatic identification of the fetal occiput position in labour In this work, we propose the development of an algorithm for the automated assessment of the fetal occiput position at TP US. The effectiveness could be further improved by acquiring new sample images and employing artificial intelligence algorithm based on convolutional neural networks in order to distinguish between anterior and posterior occiput position. [Extracted from the article]

An abstract of the article "Intrapartum echographic monitoring for automatic assessment of labour progression," by P. Pisani and colleagues is presented.