Automated angular measurement for puncture angle using a computer-aided method in ultrasound-guided peripheral insertion.

Ultrasound guidance has become the gold standard for obtaining vascular access. Angle information, which indicates the entry angle of the needle into the vein, is required to ensure puncture success. Although various image processing-based methods, such as deep learning, have recently been applied to improve needle visibility, these methods have limitations, in that the puncture angle to the target organ is not measured. We aim to detect the target vessel and puncture needle and to derive the puncture angle by combining deep learning and conventional image processing methods such as the Hough transform. Median cubital vein US images were obtained from 20 healthy volunteers, and images of simulated blood vessels and needles were obtained during the puncture of a simulated blood vessel in four phantoms. The U-Net architecture was used to segment images of blood vessels and needles, and various image processing methods were employed to automatically measure angles. The experimental results indicated that the mean dice coefficients of median cubital veins, simulated blood vessels, and needles were 0.826, 0.931, and 0.773, respectively. The quantitative results of angular measurement showed good agreement between the expert and automatic measurements of the puncture angle with 0.847 correlations. Our findings indicate that the proposed method achieves extremely high segmentation accuracy and automated angular measurements. The proposed method reduces the variability and time required in manual angle measurements and presents the possibility where the operator can concentrate on delicate techniques related to the direction of the needle.

Development of a new body weight estimation method using head CT scout images.

BACKGROUND: Imaging examinations are crucial for diagnosing acute ischemic stroke, and knowledge of a patient's body weight is necessary for safe examination. To perform examinations safely and rapidly, estimating body weight using head computed tomography (CT) scout images can be useful. OBJECTIVE: This study aims to develop a new method for estimating body weight using head CT scout images for contrast-enhanced CT examinations in patients with acute ischemic stroke. METHODS: This study investigates three weight estimation techniques. The first utilizes total pixel values from head CT scout images. The second one employs the Xception model, which was trained using 216 images with leave-one-out cross-validation. The third one is an average of the first two estimates. Our primary focus is the weight estimated from this third new method. RESULTS: The third new method, an average of the first two weight estimation methods, demonstrates moderate accuracy with a 95% confidence interval of ±14.7 kg. The first method, using only total pixel values, has a wider interval of ±20.6 kg, while the second method, a deep learning approach, results in a 95% interval of ±16.3 kg. CONCLUSIONS: The presented new method is a potentially valuable support tool for medical staff, such as doctors and nurses, in estimating weight during emergency examinations for patients with acute conditions such as stroke when obtaining accurate weight measurements is not easily feasible.

Quality control system for mammographic breast positioning using deep learning.

This study proposes a deep convolutional neural network (DCNN) classification for the quality control and validation of breast positioning criteria in mammography. A total of 1631 mediolateral oblique mammographic views were collected from an open database. We designed two main steps for mammographic verification: automated detection of the positioning part and classification of three scales that determine the positioning quality using DCNNs. After acquiring labeled mammograms with three scales visually evaluated based on guidelines, the first step was automatically detecting the region of interest of the subject part by image processing. The next step was classifying mammographic positioning accuracy into three scales using four representative DCNNs. The experimental results showed that the DCNN model achieved the best positioning classification accuracy of 0.7836 using VGG16 in the inframammary fold and a classification accuracy of 0.7278 using Xception in the nipple profile. Furthermore, using the softmax function, the breast positioning criteria could be evaluated quantitatively by presenting the predicted value, which is the probability of determining positioning accuracy. The proposed method can be quantitatively evaluated without the need for an individual qualitative evaluation and has the potential to improve the quality control and validation of breast positioning criteria in mammography.

Usefulness of copper filters in digital chest radiography based on the relationship between effective detective quantum efficiency and deep learning-based segmentation accuracy of the tumor area.

This study aimed to determine the optimal radiographic conditions for detecting lesions on digital chest radiographs using an indirect conversion flat-panel detector with a copper (Cu) filter. First, we calculated the effective detective quantum efficiency (DQE) by considering clinical conditions to evaluate the image quality. We then measured the segmentation accuracy using a U-net convolutional network to verify the effectiveness of the Cu filter. We obtained images of simulated lung tumors using 10-mm acrylic spheres positioned at the right lung apex and left middle lung of an adult chest phantom. The Dice coefficient was calculated as the similarity between the output and learning images to evaluate the accuracy of tumor area segmentation using U-net. Our results showed that effective DQE was higher in the following order up to the spatial frequency of 2 cycles/mm: 120 kV + no Cu, 120 kV + Cu 0.1 mm, and 120 kV + Cu 0.2 mm. The segmented region was similar to the true region for mass-area extraction in the left middle lobe. The lesion segmentation in the upper right lobe with 120 kV + no Cu and 120 kV + Cu 0.1 mm was less successful. However, adding a Cu filter yielded reproducible images with high Dice coefficients, regardless of the tumor location. We confirmed that adding a Cu filter decreases the X-ray absorption efficiency while improving the signal-to-noise ratio (SNR). Furthermore, artificial intelligence accurately segments low-contrast lesions.

Deep learning-based classification of adequate sonographic images for self-diagnosing deep vein thrombosis.

BACKGROUND: Pulmonary thromboembolism is a serious disease that often occurs in disaster victims evacuated to shelters. Deep vein thrombosis is the most common reason for pulmonary thromboembolism, and early prevention is important. Medical technicians often perform ultrasonography as part of mobile medical screenings of disaster victims but reaching all isolated and scattered shelters is difficult. Therefore, deep vein thrombosis medical screening methods that can be easily performed by anyone are needed. The purpose of this study was to develop a method to automatically identify cross-sectional images suitable for deep vein thrombosis diagnosis so disaster victims can self-assess their risk of deep vein thrombosis. METHODS: Ultrasonographic images of the popliteal vein were acquired in 20 subjects using stationary and portable ultrasound diagnostic equipment. Images were obtained by frame split from video. Images were classified as "Satisfactory," "Moderately satisfactory," and "Unsatisfactory" according to the level of popliteal vein visualization. Fine-tuning and classification were performed using ResNet101, a deep learning model. RESULTS: Acquiring images with portable ultrasound diagnostic equipment resulted in a classification accuracy of 0.76 and an area under the receiver operating characteristic curve of 0.89. Acquiring images with stationary ultrasound diagnostic equipment resulted in a classification accuracy of 0.73 and an area under the receiver operating characteristic curve of 0.88. CONCLUSION: A method for automatically identifying appropriate diagnostic cross-sectional ultrasonographic images of the popliteal vein was developed. This elemental technology is sufficiently accurate to automatically self-assess the risk of deep vein thrombosis by disaster victims.

Development of individual identification method using thoracic vertebral features as biometric fingerprints.

Identification of individuals is performed when a corpse is found after a natural disaster, incident, or accident. DNA and dental records are frequently used as biometric fingerprints; however, identification may be difficult in some cases due to decomposition or damage to the corpse. The present study aimed to develop an individual identification method using thoracic vertebral features as a biological fingerprint. In this method, the shortest diameter in height, width, and depth of the thoracic vertebrae in the postmortem image and a control antemortem were recorded and a database was compiled using this information. The Euclidean distance or the modified Hausdorff distance was calculated as the distance between two points on the three-dimensional feature space of these measurement data. The thoracic vertebrae T1-12 were measured and the pair with the smallest distance was considered to be from the same person. The accuracy of this method for identifying individuals was evaluated by matching images of 82 cases from a total of 702 antemortem images and showed a hit ratio of 100%. Therefore, this method may be used to identify individuals with high accuracy.

Development of a computer-aided quality assurance support system for identifying hand X-ray image direction using deep convolutional neural network.

The convenience of imaging has improved with digitization; however, there has been no progress in the methods used to prevent human error. Therefore, radiographic incidents and accidents are not prevented. In Japan, image interpretation is conducted for incident prevention; nevertheless, in some cases, incidents are overlooked. Thus, assistance from a computer-aided quality assurance support system is important. This study developed a method to identify hand image direction, which is an elementary technology of a computer-aided quality assurance support system. In total, 14,236 hand X-ray images were used to classify hand directions (upward, downward, rightward, and leftward) commonly evaluated in clinical settings. The accuracy of the conventional classification method using original images, classification method with histogram equation images, and a novel classification method using binarization images for background removal via U-Net segmentation was evaluated. The following classification accuracy rates were achieved: 89.20% if the original image was input, 99.10% if the histogram equation image was input, and 99.70% if binarization images for background removal via U-Net segmentation was input. Our computer-aided quality assurance support system can be used to identify hand direction with high accuracy.

Use of deep learning to predict postoperative recurrence of lung adenocarcinoma from preoperative CT.

PURPOSE: Although surgery is the primary treatment for lung cancer, some patients experience recurrence at a certain rate. If postoperative recurrence can be predicted early before treatment is initiated, it may be possible to provide individualized treatment for patients. Thus, in this study, we propose a computer-aided diagnosis (CAD) system that predicts postoperative recurrence from computed tomography (CT) images acquired before surgery in patients with lung adenocarcinoma using a deep convolutional neural network (DCNN). METHODS: This retrospective study included 150 patients who underwent curative surgery for primary lung adenocarcinoma. To create original images, the tumor part was cropped from the preoperative contrast-enhanced CT images. The number of input images to the DCNN was increased to 3000 using data augmentation. We constructed a CAD system by transfer learning using a pretrained VGG19 model. Tenfold cross-validation was performed five times. Cases with an average identification rate of 0.5 or higher were determined to be a recurrence. RESULTS: The median duration of follow-up was 73.2 months. The results of the performance evaluation showed that the sensitivity, specificity, and accuracy of the proposed method were 0.75, 0.87, and 0.82, respectively. The area under the receiver operating characteristic curve was 0.86. CONCLUSION: We demonstrated the usefulness of DCNN in predicting postoperative recurrence of lung adenocarcinoma using preoperative CT images. Because our proposed method uses only CT images, we believe that it has the advantage of being able to assess postoperative recurrence on an individual patient basis, both preoperatively and noninvasively.

Utility of U-Net for the objective segmentation of the fibroglandular tissue region on clinical digital mammograms.

This study investigates the equivalence or compatibility between U-Net and visual segmentations of fibroglandular tissue regions by mammography experts for calculating the breast density and mean glandular dose (MGD). A total of 703 mediolateral oblique-view mammograms were used for segmentation. Two region types were set as the ground truth (determined visually): (1) one type included only the region where fibroglandular tissue was identifiable (called the 'dense region'); (2) the other type included the region where the fibroglandular tissue may have existed in the past, provided that apparent adipose-only parts, such as the retromammary space, are excluded (the 'diffuse region'). U-Net was trained to segment the fibroglandular tissue region with an adaptive moment estimation optimiser, five-fold cross-validated with 400 training and 100 validation mammograms, and tested with 203 mammograms. The breast density and MGD were calculated using the van Engeland and Dance formulas, respectively, and compared between U-Net and the ground truth with the Dice similarity coefficient and Bland-Altman analysis. Dice similarity coefficients between U-Net and the ground truth were 0.895 and 0.939 for the dense and diffuse regions, respectively. In the Bland-Altman analysis, no proportional or fixed errors were discovered in either the dense or diffuse region for breast density, whereas a slight proportional error was discovered in both regions for the MGD (the slopes of the regression lines were -0.0299 and -0.0443 for the dense and diffuse regions, respectively). Consequently, the U-Net and ground truth were deemed equivalent (interchangeable) for breast density and compatible (interchangeable following four simple arithmetic operations) for MGD. U-Net-based segmentation of the fibroglandular tissue region was satisfactory for both regions, providing reliable segmentation for breast density and MGD calculations. U-Net will be useful in developing a reliable individualised screening-mammography programme, instead of relying on the visual judgement of mammography experts.

A deep convolutional neural network to predict the curve progression of adolescent idiopathic scoliosis: a pilot study.

BACKGROUND: Adolescent idiopathic scoliosis (AIS) is a three-dimensional spinal deformity that predominantly occurs in girls. While skeletal growth and maturation influence the development of AIS, accurate prediction of curve progression remains difficult because the prognosis for deformity differs among individuals. The purpose of this study is to develop a new diagnostic platform using a deep convolutional neural network (DCNN) that can predict the risk of scoliosis progression in patients with AIS. METHODS: Fifty-eight patients with AIS (49 females and 9 males; mean age: 12.5 ± 1.4 years) and a Cobb angle between 10 and 25 degrees (mean angle: 18.7 ± 4.5) were divided into two groups: those whose Cobb angle increased by more than 10 degrees within two years (progression group, 28 patients) and those whose Cobb angle changed by less than 5 degrees (non-progression group, 30 patients). The X-ray images of three regions of interest (ROIs) (lung [ROI1], abdomen [ROI2], and total spine [ROI3]), were used as the source data for learning and prediction. Five spine surgeons also predicted the progression of scoliosis by reading the X-rays in a blinded manner. RESULTS: The prediction performance of the DCNN for AIS curve progression showed an accuracy of 69% and an area under the receiver-operating characteristic curve of 0.70 using ROI3 images, whereas the diagnostic performance of the spine surgeons showed inferior at 47%. Transfer learning with a pretrained DCNN contributed to improved prediction accuracy. CONCLUSION: Our developed method to predict the risk of scoliosis progression in AIS by using a DCNN could be a valuable tool in decision-making for therapeutic interventions for AIS.

Development of an automatic multiplanar reconstruction processing method for head computed tomography.

BACKGROUND: Head computed tomography (CT) is a commonly used imaging modality in radiology facilities. Since multiplanar reconstruction (MPR) processing can produce different results depending on the medical staff in charge, there is a possibility that the antemortem and postmortem images of the same person could be assessed and identified differently. OBJECTIVE: To propose and test a new automatic MPR method in order to address and overcome this limitation. METHODS: Head CT images of 108 cases are used. We employ the standardized transformation of statistical parametric mapping 8. The affine transformation parameters are obtained by standardizing the captured CT images. Automatic MPR processing is performed by using this parameter. The sphenoidal sinus of the orbitomeatal cross section of the automatic MPR processing of this study and the conventional manual MPR processing are cropped with a matrix size of 128×128, and the value of zero mean normalized correlation coefficient is calculated. RESULTS: The computed zero mean normalized cross-correlation coefficient (Rzncc) of≥0.9, 0.8≤Rzncc < 0.9 and 0.7≤Rzncc < 0.8 are achieved in 105 cases (97.2%), 2 cases (1.9%), and 1 case (0.9%), respectively. The average Rzncc was 0.96±0.03. CONCLUSION: Using the proposed new method in this study, MPR processing with guaranteed accuracy is efficiently achieved.

U-Net-based image segmentation of the whole heart and four chambers on pediatric X-ray computed tomography.

This study aimed to determine whether a U-Net-based segmentation method could be used to automatically extract regions of the whole heart and atrioventricular regions from pediatric cardiac computed tomography images with high accuracy. Pediatric cardiac contrast computed tomography images with no abnormalities (n = 20; patient age, 0-13 years; mean 5 years) were used for segmentation of the whole heart and each atrioventricular region using U-Net. Segmentation accuracy was evaluated using the Dice similarity coefficient. The mean Dice similarity coefficient for the whole-heart segmentation was high at 0.95. There were no significant differences between age categories. The median Dice similarity coefficients for segmentation of the atria and ventricles were good (> 0.86). There were significant differences between age categories at some sites. Differences in the Dice similarity coefficient may have occurred because the target diseases and examination procedures differed according to subject age. There was no clear tendency for similar values between subjects of school age, close to adulthood, and newborns; good agreement was obtained in all age categories. These results suggest that U-Net-based segmentation may be useful for automatic extraction of the whole heart and atrioventricular regions from pediatric computed tomography images.

Traceable Reference Full Metrology Chain for Innovative Aspheric and Freeform Optical Surfaces Accurate at the Nanometer Level.

The design of innovative reference aspheric and freeform optical elements was investigated with the aim of calibration and verification of ultra-high accurate measurement systems. The verification is dedicated to form error analysis of aspherical and freeform optical surfaces based on minimum zone fitting. Two thermo-invariant material measures were designed, manufactured using a magnetorheological finishing process and selected for the evaluation of a number of ultra-high-precision measurement machines. All collected data sets were analysed using the implemented robust reference minimum zone (Hybrid Trust Region) fitting algorithm to extract the values of form error. Agreement among the results of several partners was observed, which demonstrates the establishment of a traceable reference full metrology chain for aspherical and freeform optical surfaces with small amplitudes.

Scanning deflectometric profiler for measurement of transparent parallel plates.

An angle-based deflectometric surface profiler has been improved for the measurement of transparent parallel plates. In the developed system, the unwanted beam reflected from the back surface of the transparent parallel plate is removed by ensuring that the beam is obliquely incident to the measurement surface; this is realized by using a modified pentamirror unit comprising two mirrors installed at a predetermined angle to one another. The surface profile measurement of a transparent parallel plate with a repeatability of less than ±0.7 nm was successfully achieved. A measurement accuracy of around 3 nm was reached by comparing the developed system with other scanning deflectometric profiler systems for the measurement of a silicon bar mirror with a length of 300 mm.