Automatic detection of midfacial fractures in facial bone CT images using deep learning-based object detection models.

BACKGROUND: Midfacial fractures are among the most frequent facial fractures. Surgery is recommended within 2 weeks of injury, but this time frame is often extended because the fracture is missed on diagnostic imaging in the busy emergency medicine setting. Using deep learning technology, which has progressed markedly in various fields, we attempted to develop a system for the automatic detection of midfacial fractures. The purpose of this study was to use this system to diagnose fractures accurately and rapidly, with the intention of benefiting both patients and emergency room physicians. METHODS: One hundred computed tomography images that included midfacial fractures (e.g., maxillary, zygomatic, nasal, and orbital fractures) were prepared. In each axial image, the fracture area was surrounded by a rectangular region to create the annotation data. Eighty images were randomly classified as the training dataset (3736 slices) and 20 as the validation dataset (883 slices). Training and validation were performed using Single Shot MultiBox Detector (SSD) and version 8 of You Only Look Once (YOLOv8), which are object detection algorithms. RESULTS: The performance indicators for SSD and YOLOv8 were respectively: precision, 0.872 and 0.871; recall, 0.823 and 0.775; F1 score, 0.846 and 0.82; average precision, 0.899 and 0.769. CONCLUSIONS: The use of deep learning techniques allowed the automatic detection of midfacial fractures with good accuracy and high speed. The system developed in this study is promising for automated detection of midfacial fractures and may provide a quick and accurate solution for emergency medical care and other settings.

Automatic hip osteoarthritis grading with uncertainty estimation from computed tomography using digitally-reconstructed radiographs.

PURPOSE: Progression of hip osteoarthritis (hip OA) leads to pain and disability, likely leading to surgical treatment such as hip arthroplasty at the terminal stage. The severity of hip OA is often classified using the Crowe and Kellgren-Lawrence (KL) classifications. However, as the classification is subjective, we aimed to develop an automated approach to classify the disease severity based on the two grades using digitally-reconstructed radiographs from CT images. METHODS: Automatic grading of the hip OA severity was performed using deep learning-based models. The models were trained to predict the disease grade using two grading schemes, i.e., predicting the Crowe and KL grades separately, and predicting a new ordinal label combining both grades and representing the disease progression of hip OA. The models were trained in classification and regression settings. In addition, the model uncertainty was estimated and validated as a predictor of classification accuracy. The models were trained and validated on a database of 197 hip OA patients, and externally validated on 52 patients. The model accuracy was evaluated using exact class accuracy (ECA), one-neighbor class accuracy (ONCA), and balanced accuracy. RESULTS: The deep learning models produced a comparable accuracy of approximately 0.65 (ECA) and 0.95 (ONCA) in the classification and regression settings. The model uncertainty was significantly larger in cases with large classification errors ( P < 6 e - 3 ). CONCLUSIONS: In this study, an automatic approach for grading hip OA severity from CT images was developed. The models have shown comparable performance with high ONCA, which facilitates automated grading in large-scale CT databases and indicates the potential for further disease progression analysis. Classification accuracy was correlated with the model uncertainty, which would allow for the prediction of classification errors. The code will be made publicly available at https://github.com/NAIST-ICB/HipOA-Grading .

Reproduction of forearm rotation dynamic using intensity-based biplane 2D-3D registration matching method.

This study aimed to reproduce and analyse the in vivo dynamic rotational motion of the forearm and to clarify forearm motion involvement and the anatomical function of the interosseous membrane (IOM). The dynamic forearm rotational motion of the radius and ulna was analysed in vivo using a novel image-matching method based on fluoroscopic and computed tomography images for intensity-based biplane two-dimensional-three-dimensional registration. Twenty upper limbs from 10 healthy volunteers were included in this study. The mean range of forearm rotation was 150 ± 26° for dominant hands and 151 ± 18° for non-dominant hands, with no significant difference observed between the two. The radius was most proximal to the maximum pronation relative to the ulna, moved distally toward 60% of the rotation range from maximum pronation, and again proximally toward supination. The mean axial translation of the radius relative to the ulna during forearm rotation was 1.8 ± 0.8 and 1.8 ± 0.9 mm for dominant and non-dominant hands, respectively. The lengths of the IOM components, excluding the central band (CB), changed rotation. The transverse CB length was maximal at approximately 50% of the rotation range from maximum pronation. Summarily, this study describes a detailed method for evaluating in vivo dynamic forearm motion and provides valuable insights into forearm kinematics and IOM function.

Hybrid representation-enhanced sampling for Bayesian active learning in musculoskeletal segmentation of lower extremities.

PURPOSE: Manual annotations for training deep learning models in auto-segmentation are time-intensive. This study introduces a hybrid representation-enhanced sampling strategy that integrates both density and diversity criteria within an uncertainty-based Bayesian active learning (BAL) framework to reduce annotation efforts by selecting the most informative training samples. METHODS: The experiments are performed on two lower extremity datasets of MRI and CT images, focusing on the segmentation of the femur, pelvis, sacrum, quadriceps femoris, hamstrings, adductors, sartorius, and iliopsoas, utilizing a U-net-based BAL framework. Our method selects uncertain samples with high density and diversity for manual revision, optimizing for maximal similarity to unlabeled instances and minimal similarity to existing training data. We assess the accuracy and efficiency using dice and a proposed metric called reduced annotation cost (RAC), respectively. We further evaluate the impact of various acquisition rules on BAL performance and design an ablation study for effectiveness estimation. RESULTS: In MRI and CT datasets, our method was superior or comparable to existing ones, achieving a 0.8% dice and 1.0% RAC increase in CT (statistically significant), and a 0.8% dice and 1.1% RAC increase in MRI (not statistically significant) in volume-wise acquisition. Our ablation study indicates that combining density and diversity criteria enhances the efficiency of BAL in musculoskeletal segmentation compared to using either criterion alone. CONCLUSION: Our sampling method is proven efficient in reducing annotation costs in image segmentation tasks. The combination of the proposed method and our BAL framework provides a semi-automatic way for efficient annotation of medical image datasets.

The effect of forearm rotation on the bone mineral density measurements of the distal radius.

INTRODUCTION: Forearm dual-energy X-ray absorptiometry (DXA) is often performed in clinics where central DXA is unavailable. Accurate bone mineral density (BMD) measurement is crucial for clinical assessment. Forearm rotation can affect BMD measurements, but this effect remains uncertain. Thus, we aimed to conduct a simulation study using CT images to clarify the effect of forearm rotation on BMD measurements. MATERIALS AND METHODS: Forearm CT images of 60 women were analyzed. BMD was measured at the total, ultra-distal (UD), mid-distal (MD), and distal 33% radius regions with the radius located at the neutral position using digitally reconstructed radiographs generated from CT images. Then, the rotation was altered from - 30° to 30° (supination set as positive) with a one-degree increment, and the percent BMD changes from the neutral position were quantified for all regions at each angle for each patient. RESULTS: The maximum mean BMD changes were 5.8%, 7.0%, 6.2%, and 7.2% for the total, UD, MD, and distal 33% radius regions, respectively. The analysis of the absolute values of the percent BMD changes from the neutral position showed that BMD changes of all patients remained within 2% when the rotation was between - 5° and 7° for the total region, between - 3° and 2° for the UD region, between - 4° and 3° for the MD region, and between - 3° and 1° for the distal 33% radius region. CONCLUSION: Subtle rotational changes affected the BMD measurement of each region. The results showed the importance of forearm positioning when measuring the distal radius BMD.

Automatic orbital segmentation using deep learning-based 2D U-net and accuracy evaluation: A retrospective study.

The purpose of this study was to verify whether the accuracy of automatic segmentation (AS) of computed tomography (CT) images of fractured orbits using deep learning (DL) is sufficient for clinical application. In the surgery of orbital fractures, many methods have been reported to create a 3D anatomical model for use as a reference. However, because the orbit bone is thin and complex, creating a segmentation model for 3D printing is complicated and time-consuming. Here, the training of DL was performed using U-Net as the DL model, and the AS output was validated with Dice coefficients and average symmetry surface distance (ASSD). In addition, the AS output was 3D printed and evaluated for accuracy by four surgeons, each with over 15 years of clinical experience. One hundred twenty-five CT images were prepared, and manual orbital segmentation was performed in all cases. Ten orbital fracture cases were randomly selected as validation data, and the remaining 115 were set as training data. AS was successful in all cases, with good accuracy: Dice, 0.860 ± 0.033 (mean ± SD); ASSD, 0.713 ± 0.212 mm. In evaluating AS accuracy, the expert surgeons generally considered that it could be used for surgical support without further modification. The orbital AS algorithm developed using DL in this study is extremely accurate and can create 3D models rapidly at low cost, potentially enabling safer and more accurate surgeries.

Bone mineral density estimation from a plain X-ray image by learning decomposition into projections of bone-segmented computed tomography.

Osteoporosis is a prevalent bone disease that causes fractures in fragile bones, leading to a decline in daily living activities. Dual-energy X-ray absorptiometry (DXA) and quantitative computed tomography (QCT) are highly accurate for diagnosing osteoporosis; however, these modalities require special equipment and scan protocols. To frequently monitor bone health, low-cost, low-dose, and ubiquitously available diagnostic methods are highly anticipated. In this study, we aim to perform bone mineral density (BMD) estimation from a plain X-ray image for opportunistic screening, which is potentially useful for early diagnosis. Existing methods have used multi-stage approaches consisting of extraction of the region of interest and simple regression to estimate BMD, which require a large amount of training data. Therefore, we propose an efficient method that learns decomposition into projections of bone-segmented QCT for BMD estimation under limited datasets. The proposed method achieved high accuracy in BMD estimation, where Pearson correlation coefficients of 0.880 and 0.920 were observed for DXA-measured BMD and QCT-measured BMD estimation tasks, respectively, and the root mean square of the coefficient of variation values were 3.27 to 3.79% for four measurements with different poses. Furthermore, we conducted extensive validation experiments, including multi-pose, uncalibrated-CT, and compression experiments toward actual application in routine clinical practice.

Development and validation of an open-source tool for opportunistic screening of osteoporosis from hip CT images.

Aims: This study aimed to develop and validate a fully automated system that quantifies proximal femoral bone mineral density (BMD) from CT images. Methods: The study analyzed 978 pairs of hip CT and dual-energy X-ray absorptiometry (DXA) measurements of the proximal femur (DXA-BMD) collected from three institutions. From the CT images, the femur and a calibration phantom were automatically segmented using previously trained deep-learning models. The Hounsfield units of each voxel were converted into density (mg/cm3). Then, a deep-learning model trained by manual landmark selection of 315 cases was developed to select the landmarks at the proximal femur to rotate the CT volume to the neutral position. Finally, the CT volume of the femur was projected onto the coronal plane, and the areal BMD of the proximal femur (CT-aBMD) was quantified. CT-aBMD correlated to DXA-BMD, and a receiver operating characteristic (ROC) analysis quantified the accuracy in diagnosing osteoporosis. Results: CT-aBMD was successfully measured in 976/978 hips (99.8%). A significant correlation was found between CT-aBMD and DXA-BMD (r = 0.941; p < 0.001). In the ROC analysis, the area under the curve to diagnose osteoporosis was 0.976. The diagnostic sensitivity and specificity were 88.9% and 96%, respectively, with the cutoff set at 0.625 g/cm2. Conclusion: Accurate DXA-BMD measurements and diagnosis of osteoporosis were performed from CT images using the system developed herein. As the models are open-source, clinicians can use the proposed system to screen osteoporosis and determine the surgical strategy for hip surgery.

Decomposition of musculoskeletal structures from radiographs using an improved CycleGAN framework.

This paper presents methods of decomposition of musculoskeletal structures from radiographs into multiple individual muscle and bone structures. While existing solutions require dual-energy scan for the training dataset and are mainly applied to structures with high-intensity contrast, such as bones, we focused on multiple superimposed muscles with subtle contrast in addition to bones. The decomposition problem is formulated as an image translation problem between (1) a real X-ray image and (2) multiple digitally reconstructed radiographs, each of which contains a single muscle or bone structure, and solved using unpaired training based on the CycleGAN framework. The training dataset was created via automatic computed tomography (CT) segmentation of muscle/bone regions and virtually projecting them with geometric parameters similar to the real X-ray images. Two additional features were incorporated into the CycleGAN framework to achieve a high-resolution and accurate decomposition: hierarchical learning and reconstruction loss with the gradient correlation similarity metric. Furthermore, we introduced a new diagnostic metric for muscle asymmetry directly measured from a plain X-ray image to validate the proposed method. Our simulation and real-image experiments using real X-ray and CT images of 475 patients with hip diseases suggested that each additional feature significantly enhanced the decomposition accuracy. The experiments also evaluated the accuracy of muscle volume ratio measurement, which suggested a potential application to muscle asymmetry assessment from an X-ray image for diagnostic and therapeutic assistance. The improved CycleGAN framework can be applied for investigating the decomposition of musculoskeletal structures from single radiographs.

The effect of patient positioning on measurements of bone mineral density of the proximal femur: a simulation study using computed tomographic images.

The patient's position may affect the bone mineral density (BMD) measurements; however, the extent of this effect is undefined. This CT image-based simulation study quantified changes in BMD induced by hip flexion, adduction, and rotations to recommend appropriate patient positioning when acquiring dual-energy x-ray absorptiometry images. PURPOSE: Several studies have analyzed the effect of hip rotation on the measurement of bone mineral density (BMD) of the proximal femur by dual-energy x-ray absorptiometry (DXA). However, as the effects of hip flexion and abduction on BMD measurements remain uncertain, a computational simulation study using CT images was performed in this study. METHODS: Hip CT images of 120 patients (33 men and 87 women; mean age, 82.1 ± 9.4 years) were used for analysis. Digitally reconstructed radiographs of the proximal femur region were generated from CT images to calculate the BMD of the proximal femur region. BMD at the neutral position was quantified, and the percent changes in BMD when hip internal rotation was altered from -30° to 15°, when hip flexion was altered from 0° to 30°, and when hip abduction was altered from -15° to 30° were quantified. Analyses were automatically performed with a 1° increment in each direction using computer programming. RESULTS: The alteration of hip angles in each direction affected BMD measurements, with the largest changes found for hip flexion (maximum change of 17.7% at 30° flexion) and the smallest changes found for hip rotation (maximum change of 2.2% at 15° internal rotation). The BMD measurements increased by 0.34% for each 1° of hip abduction, and the maximum change was 12.3% at 30° abduction. CONCLUSION: This simulation study quantified the amount of BMD change induced by altering the hip position. Based on these results, we recommend that patients be positioned carefully when acquiring DXA images.

Development of a system to assess the two- and three-dimensional bone mineral density of the lumbar vertebrae from clinical quantitative CT images.

This study developed a system to quantify the lumbar spine's bone mineral density (BMD) in two and three dimensions for osteoporosis screening using quantitative CT images. Measuring the two-dimensional BMD could reproduce the BMD measurement performed in dual-energy X-ray absorptiometry, and an accurate diagnosis of osteoporosis was possible. PURPOSE: To date, the assessment of bone mineral density (BMD) using CT images has been made in three dimensions, leading to errors in detecting osteoporosis based on the two-dimensional assessments of BMD using dual-energy X-ray absorptiometry (DXA-BMD). Herein, we aimed to develop a system that measures two- and three-dimensional lumbar BMD from quantitative CT images and validated the accuracy of the system in diagnosing osteoporosis with regard to the DXA classification. METHODS: Fifty-nine pairs of spinal CT and DXA images were analyzed. First, the three-dimensional BMD was measured at the axial slice of the L1 vertebra on CT images (L1-vBMD). Then, the L1-L4 vertebrae were segmented from the CT images to measure the three-dimensional BMD at the trabecular region of the L1-L4 vertebral bodies (CT-vBMD). Lastly, the segmented vertebrae were projected onto the coronal plane to measure the two-dimensional BMD (CT-aBMD). Each parameter was correlated with DXA-BMD, and the receiver operating characteristic (ROC) curve to diagnose osteoporosis was assessed. RESULTS: The correlation coefficients of DXA-BMD with L1-vBMD, CT-vBMD, and CT-aBMD were 0.364, 0.456, and 0.911, respectively (all p < 0.01). In the ROC curve analysis to diagnose osteoporosis, the area under the curve for CT-aBMD (0.941) was significantly higher than those for L1-vBMD (0.582) and CT-vBMD (0.657) (both p < 0.01). CONCLUSION: Compared with L1-vBMD and CT-vBMD, CT-aBMD could accurately predict DXA-BMD and detect patients with osteoporosis. Given that our method can quantify BMD in both two and three dimensions, it could be used to screen for osteoporosis from quantitative CT images.

4D-foot analysis on effect of arch support on ankle, subtalar, and talonavicular joint kinematics.

BACKGROUND: It has been difficult to study the effects of arch support on multiple joints simultaneously. Herein, we evaluated foot and ankle kinematics using a fully automated analysis system, "4D-Foot," consisting of a biplane X-ray imager and two-dimensional‒three-dimensional registration, with automated image segmentation and landmark detection tools. METHODS: We evaluated the effect of arch support on ankle, subtalar, and talonavicular joint kinematics in five healthy female volunteers without a clinical history of foot and ankle disorders. Computed tomography images of the foot and ankle and X-ray videos of walking barefoot and with arch support were acquired. A kinematic analysis using the "4D-Foot" system was performed. The ankle, subtalar, and talonavicular joint kinematics were quantified from heel-strike to foot-off, with and without arch support. RESULTS: For the ankle joint, significant differences were observed in dorsi/plantarflexion, inversion/eversion, and internal/external rotation in the late midstance phase. The dorsi/plantarflexion and inversion/eversion motions were smaller with arch support. For the subtalar joint, a significant difference was observed in all the dynamic motions in the heel-strike and late midstance phases. For the talonavicular joint, significant differences were observed in inversion/eversion and internal/external rotation in heel-strike and the late midstance phases. For the subtalar and talonavicular joints, the motion was larger with arch support. An extremely strong correlation was observed when the motion of the subtalar and talonavicular joints was compared for each condition and motion. CONCLUSIONS: The results indicated that the arch support decreased the ankle motion and increased the subtalar and talonavicular joint motions. Additionally, our study demonstrated that the in vivo subtalar and talonavicular joints revealed a strong correlation, suggesting that the navicular and calcaneal bones were moving similarly to the talus and that the arch support stabilizes the ankle joint and compensatively increases the subtalar and talonavicular joint motions.

Artificial intelligence-based volumetric analysis of muscle atrophy and fatty degeneration in patients with hip osteoarthritis and its correlation with health-related quality of life.

PURPOSE: Artificial intelligence (AI) technologies have enabled precise three-dimensional analysis of individual muscles on computed tomography (CT) or magnetic resonance images via automatic segmentation. This study aimed to perform three-dimensional assessments of pelvic and thigh muscle atrophy and fatty degeneration in patients with unilateral hip osteoarthritis using CT and to evaluate the correlation with health-related quality of life (HRQoL). METHODS: The study included one man and 43 women. Six muscle groups were segmented, and the muscle atrophy ratio was calculated volumetrically. The degree of fatty degeneration was defined as the difference between the mean CT values (Hounsfield units [HU]) of the healthy and affected sides. HRQoL was evaluated using the Western Ontario and McMaster Universities Osteoarthritis (WOMAC) index and the Japanese Orthopaedic Association Hip Disease Evaluation Questionnaire (JHEQ). RESULTS: The mean muscle atrophy rate was 16.3%, and the mean degree of muscle fatty degeneration was 7.9 HU. Multivariate correlation analysis revealed that the WOMAC stiffness subscale was significantly related to fatty degeneration of the hamstrings, the WOMAC physical function subscale was significantly related to fatty degeneration of the iliopsoas muscle, and the JHEQ movement subscale was significantly related to fatty degeneration of the hip adductors. CONCLUSION: We found that fatty degeneration of the hamstrings, iliopsoas, and hip adductor muscles was significantly related to HRQoL in patients with hip osteoarthritis. These findings suggest that these muscles should be targeted during conservative rehabilitation for HOA and perioperative rehabilitation for THA.

Rotational-motion measurement of the sacroiliac joint using upright MRI scanning and intensity-based registration: is there a sex difference?

PURPOSE: The sacroiliac joint (SIJ) has attracted increasing attention as a source of low back and groin pain, but the kinematics of SIJ against standing load and its sex difference remain unclear due to the difficulty of in vivo load study. An upright magnetic resonance imaging (MRI) system can provide in vivo imaging both in the supine and standing positions. The reliability of the mobility of SIJ against the standing load was evaluated and its sex difference was examined in healthy young volunteers using an upright MRI. METHOD: Static (reliability) and kinematic studies were performed. In the static study, a dry bone of pelvic ring embedded in gel form and frozen in the plastic box was used. In the kinematic study, 19 volunteers (10 males, 9 females) with a mean age of 23.9 years were included. The ilium positions for the sacrum in supine and standing positions were measured against the pelvic coordinates to evaluate the mobility of the SIJ. RESULTS: In the static study, the residual error of the rotation of the SIJ study was < 0.2°. In the kinematic study, the mean values of SIJ sagittal rotation from supine to standing position in males and females were - 0.9° ± 0.7° (mean ± standard deviation) and - 1.7° ± 0.8°, respectively. The sex difference was statistically significant (p = 0.04). The sagittal rotation of the SIJ showed a significant correlation with the sacral slope. CONCLUSION: The residual error for measuring the SIJ rotation using the upright MRI was < 0.2°. The young healthy participants showed sex differences in the sagittal rotation of the SIJ against the standing load and the females showed a larger posterior rotation of the ilium against the sacrum from the supine to standing position than the males. Therefore, upright MRI is useful to investigate SIJ motion.

Attention induction for a CT volume classification of COVID-19.

PURPOSE: This study proposes a method to draw attention toward the specific radiological findings of coronavirus disease 2019 (COVID-19) in CT images, such as bilaterality of ground glass opacity (GGO) and/or consolidation, in order to improve the classification accuracy of input CT images. METHODS: We propose an induction mask that combines a similarity and a bilateral mask. A similarity mask guides attention to regions with similar appearances, and a bilateral mask induces attention to the opposite side of the lung to capture bilaterally distributed lesions. An induction mask for pleural effusion is also proposed in this study. ResNet18 with nonlocal blocks was trained by minimizing the loss function defined by the induction mask. RESULTS: The four-class classification accuracy of the CT images of 1504 cases was 0.6443, where class 1 was the typical appearance of COVID-19 pneumonia, class 2 was the indeterminate appearance of COVID-19 pneumonia, class 3 was the atypical appearance of COVID-19 pneumonia, and class 4 was negative for pneumonia. The four classes were divided into two subgroups. The accuracy of COVID-19 and pneumonia classifications was evaluated, which were 0.8205 and 0.8604, respectively. The accuracy of the four-class and COVID-19 classifications improved when attention was paid to pleural effusion. CONCLUSION: The proposed attention induction method was effective for the classification of CT images of COVID-19 patients. Improvement of the classification accuracy of class 3 by focusing on features specific to the class remains a topic for future work.

Classification and visual explanation for COVID-19 pneumonia from CT images using triple learning.

This study presents a novel framework for classifying and visualizing pneumonia induced by COVID-19 from CT images. Although many image classification methods using deep learning have been proposed, in the case of medical image fields, standard classification methods are unable to be used in some cases because the medical images that belong to the same category vary depending on the progression of the symptoms and the size of the inflamed area. In addition, it is essential that the models used be transparent and explainable, allowing health care providers to trust the models and avoid mistakes. In this study, we propose a classification method using contrastive learning and an attention mechanism. Contrastive learning is able to close the distance for images of the same category and generate a better feature space for classification. An attention mechanism is able to emphasize an important area in the image and visualize the location related to classification. Through experiments conducted on two-types of classification using a three-fold cross validation, we confirmed that the classification accuracy was significantly improved; in addition, a detailed visual explanation was achieved comparison with conventional methods.

The Effect of Region of Interest on Measurement of Bone Mineral Density of the Proximal Femur: Simulation Analysis Using CT Images.

While accurate measurement of bone mineral density (BMD) is essential in the diagnosis of osteoporosis and in evaluating the treatment of osteoporosis, it is unclear how region of interest (ROI) settings affect measurement of BMD at the total proximal femur region. In this study, we performed a simulation analysis to clarify the effect on BMD measurement of changing the ROI using hip computed tomography (CT) images of 75 females (mean age, 62.4 years). Digitally reconstructed radiographs of the proximal femur region were generated from CT images to calculate the change in BMD when the proximal boundary of the ROI was altered by 0-10 mm, and when the distal boundary of the ROI was altered by 0-30 mm. Further, changes in BMD were compared across BMD classification groups. A mean BMD increase of 0.62% was found for each 1-mm extension of the distal boundary. A mean BMD decrease of 0.18% was found for each 1-mm alteration of the proximal boundary. Comparing BMD classification groups, patients with osteoporosis and osteopenia demonstrated greater BMD changes than patients with normal BMD for the distal boundary (0.68%, 0.64%, and 0.54%, respectively) and patients with osteoporosis demonstrated greater BMD changes than patients with osteoporosis and normal BMD for the proximal boundary (0.37%, 0.13%, and 0.03%, respectively). In conclusion, our study found that a consistent ROI setting, especially on the distal boundary, is necessary for the accurate measurement of total proximal femur BMD. Based on the findings, we recommend confirming that the ROI setting shown on the BMD result form is consistent with changes in serial BMD.

Development of an open-source measurement system to assess the areal bone mineral density of the proximal femur from clinical CT images.

Commercial software is generally needed to measure the areal bone mineral density (aBMD) of the proximal femur from clinical computed tomography (CT) images. This study developed and verified an open-source reproducible system to quantify CT-aBMD to screen osteoporosis using clinical CT images. PURPOSE: For existing CT images acquired for various reasons other than osteoporosis, it might be beneficial to estimate areal BMD as assessed by dual-energy X-ray absorptiometry (DXA-based BMD) to ascertain the bone status based on DXA. In this study, we aimed to (1) develop an open-source reproducible measurement system to quantify DXA-based BMD from CT images and (2) validate its accuracy. METHODS: This study analyzed 75 pairs of hip CT and DXA images of women that were acquired for the preoperative assessment of total hip arthroplasty. From the CT images, the femur and a calibration phantom were automatically segmented using pre-trained codes/models available at https://github.com/keisuke-uemura . The proximal femoral region was isolated by manually selected landmarks and was projected onto the coronal plane to measure the areal density (CT-aHU). The calibration phantom was employed to convert the CT-aHU into CT-aBMD. Each parameter was correlated with DXA-based BMD, and the residual errors of CT images to estimate the T-scores in DXA were calculated using the standard error of estimate (SEE). RESULTS: The correlation coefficients of DXA-based BMD with CT-aHU and CT-aBMD were 0.947 and 0.950, respectively (both p < 0.001). The SEE for quantifying the T-scores in DXA were 0.51 and 0.50 for CT-aHU and CT-aBMD, respectively. CONCLUSION: With the method developed herein, CT permits estimation of the DXA-based BMD of the proximal femur within the standard DXA total hip region of interest with an SEE of 0.5 in T-scores. The radiation dose for CT acquisition needs consideration; therefore, our data do not provide a rationale for performing CT for screening osteoporosis. However, on CT images already acquired for clinical indications other than osteoporosis, researchers may use this open-source system to investigate osteoporosis status through the estimated DXA-based BMD of the proximal femur.

Quantitative Comparison of Surgical Device Usage in Laparoscopic Gastrectomy Between Surgeons' Skill Levels: an Automated Analysis Using a Neural Network.

BACKGROUND: Whether surgical device usage in laparoscopic gastrectomy differs with respect to operator's skill levels is unknown. Further, device usage analysis using artificial intelligence has not been reported to date. Herein, we compared the patterns of surgical device usage during laparoscopic gastrectomy for gastric cancer among surgeons at different skill levels. The data of device usage was acquired from laparoscopic video recordings using an automated surgical-instrument detection system. METHODS: In total, 100 video recordings of infrapyloric lymphadenectomy and 33 of D2 suprapancreatic lymphadenectomy during laparoscopic gastrectomy for gastric cancer were analyzed in this retrospective study. The system's accuracy was evaluated by comparing the automatic and the manual usage time. Surgical device usage patterns were compared between qualified and nonqualified surgeons of The Japan Society for Endoscopic Surgery Endoscopic Surgical Skill Qualification System. RESULTS: For every device, the automatic detection time and manual detection time were consistent with each other. In infrapyloric lymphadenectomy, the usage time proportions of dissector forceps and clip applier were higher among nonqualified operators than among qualified operators (dissector, 5.1% vs. 2.3%, P < 0.001; clip applier, 1.6% vs. 1.3%, P < 0.01). In suprapancreatic lymphadenectomy, the usage time proportions of energy devices, clip applier, and grasper forceps were significantly different (energy devices, 59.6% vs. 50.6%, P < 0.001; clip applier, 1.4% vs. 0.9%, P < 0.001; only grasper forceps; 18.3% vs. 27.9%, P = 0.022). CONCLUSIONS: Quantitative analysis of laparoscopic device usage using the automated surgical device detection system showed that the patterns of device usage during laparoscopic gastrectomy differed depending on surgeons' skill levels. These differences could suggest how the qualified and nonqualified surgeons performed the procedures.

Translation of Cellular Protein Localization Using Convolutional Networks.

Protein localization in cells has been analyzed by fluorescent labeling using indirect immunofluorescence and fluorescent protein tagging. However, the relationships between the localization of different proteins had not been analyzed using artificial intelligence. Here, we applied convolutional networks for the prediction of localization of the cytoskeletal proteins from the localization of the other proteins. Lamellipodia are one of the actin-dependent subcellular structures involved in cell migration and are mainly generated by the Wiskott-Aldrich syndrome protein (WASP)-family verprolin homologous protein 2 (WAVE2) and the membrane remodeling I-BAR domain protein IRSp53. Focal adhesion is another actin-based structure that contains vinculin protein and promotes lamellipodia formation and cell migration. In contrast, microtubules are not directly related to actin filaments. The convolutional network was trained using images of actin filaments paired with WAVE2, IRSp53, vinculin, and microtubules. The generated images of WAVE2, IRSp53, and vinculin were highly similar to their real images. In contrast, the microtubule images generated from actin filament images were inferior without the generation of filamentous structures, suggesting that microscopic images of actin filaments provide more information about actin-related protein localization. Collectively, this study suggests that image translation by the convolutional network can predict the localization of functionally related proteins, and the convolutional network might be used to describe the relationships between the proteins by their localization.