Assessment of changes in vessel area during needle manipulation in microvascular anastomosis using a deep learning-based semantic segmentation algorithm: A pilot study.

Appropriate needle manipulation to avoid abrupt deformation of fragile vessels is a critical determinant of the success of microvascular anastomosis. However, no study has yet evaluated the area changes in surgical objects using surgical videos. The present study therefore aimed to develop a deep learning-based semantic segmentation algorithm to assess the area change of vessels during microvascular anastomosis for objective surgical skill assessment with regard to the "respect for tissue." The semantic segmentation algorithm was trained based on a ResNet-50 network using microvascular end-to-side anastomosis training videos with artificial blood vessels. Using the created model, video parameters during a single stitch completion task, including the coefficient of variation of vessel area (CV-VA), relative change in vessel area per unit time (ΔVA), and the number of tissue deformation errors (TDE), as defined by a ΔVA threshold, were compared between expert and novice surgeons. A high validation accuracy (99.1%) and Intersection over Union (0.93) were obtained for the auto-segmentation model. During the single-stitch task, the expert surgeons displayed lower values of CV-VA (p < 0.05) and ΔVA (p < 0.05). Additionally, experts committed significantly fewer TDEs than novices (p < 0.05), and completed the task in a shorter time (p < 0.01). Receiver operating curve analyses indicated relatively strong discriminative capabilities for each video parameter and task completion time, while the combined use of the task completion time and video parameters demonstrated complete discriminative power between experts and novices. In conclusion, the assessment of changes in the vessel area during microvascular anastomosis using a deep learning-based semantic segmentation algorithm is presented as a novel concept for evaluating microsurgical performance. This will be useful in future computer-aided devices to enhance surgical education and patient safety.

Tissue Acceleration as a Novel Metric for Surgical Performance During Carotid Endarterectomy.

BACKGROUND AND OBJECTIVES: Gentle tissue handling to avoid excessive motion of affected fragile vessels during surgical dissection is essential for both surgeon proficiency and patient safety during carotid endarterectomy (CEA). However, a void remains in the quantification of these aspects during surgery. The video-based measurement of tissue acceleration is presented as a novel metric for the objective assessment of surgical performance. This study aimed to evaluate whether such metrics correlate with both surgeons' skill proficiency and adverse events during CEA. METHODS: In a retrospective study including 117 patients who underwent CEA, acceleration of the carotid artery was measured during exposure through a video-based analysis. Tissue acceleration values and threshold violation error frequencies were analyzed and compared among the surgeon groups with different surgical experience (3 groups: novice , intermediate , and expert ). Multiple patient-related variables, surgeon groups, and video-based surgical performance parameters were compared between the patients with and without adverse events during CEA. RESULTS: Eleven patients (9.4%) experienced adverse events after CEA, and the rate of adverse events significantly correlated with the surgeon group. The mean maximum tissue acceleration and number of errors during surgical tasks significantly decreased from novice, to intermediate, to expert surgeons, and stepwise discriminant analysis showed that the combined use of surgical performance factors could accurately discriminate between surgeon groups. The multivariate logistic regression analysis revealed that the number of errors and vulnerable carotid plaques were associated with adverse events. CONCLUSION: Tissue acceleration profiles can be a novel metric for the objective assessment of surgical performance and the prediction of adverse events during surgery. Thus, this concept can be introduced into futuristic computer-aided surgeries for both surgical education and patient safety.

Deep learning-based body weight from scout images can be an alternative to actual body weight in CT radiation dose management.

PURPOSE: Accurate body weight measurement is essential to promote computed tomography (CT) dose optimization; however, body weight cannot always be measured prior to CT examination, especially in the emergency setting. The aim of this study was to investigate whether deep learning-based body weight from chest CT scout images can be an alternative to actual body weight in CT radiation dose management. METHODS: Chest CT scout images and diagnostic images acquired for medical checkups were collected from 3601 patients. A deep learning model was developed to predict body weight from scout images. The correlation between actual and predicted body weight was analyzed. To validate the use of predicted body weight in radiation dose management, the volume CT dose index (CTDIvol ) and the dose-length product (DLP) were compared between the body weight subgroups based on actual and predicted body weight. Surrogate size-specific dose estimates (SSDEs) acquired from actual and predicted body weight were compared to the reference standard. RESULTS: The median actual and predicted body weight were 64.1 (interquartile range: 56.5-72.4) and 64.0 (56.3-72.2) kg, respectively. There was a strong correlation between actual and predicted body weight (ρ = 0.892, p < 0.001). The CTDIvol and DLP of the body weight subgroups were similar based on actual and predicted body weight (p < 0.001). Both surrogate SSDEs based on actual and predicted body weight were not significantly different from the reference standard (p = 0.447 and 0.410, respectively). CONCLUSION: Predicted body weight can be an alternative to actual body weight in managing dose metrics and simplifying SSDE calculation. Our proposed method can be useful for CT radiation dose management in adult patients with unknown body weight.

Prostatic urinary tract visualization with super-resolution deep learning models.

In urethra-sparing radiation therapy, prostatic urinary tract visualization is important in decreasing the urinary side effect. A methodology has been developed to visualize the prostatic urinary tract using post-urination magnetic resonance imaging (PU-MRI) without a urethral catheter. This study investigated whether the combination of PU-MRI and super-resolution (SR) deep learning models improves the visibility of the prostatic urinary tract. We enrolled 30 patients who had previously undergone real-time-image-gated spot scanning proton therapy by insertion of fiducial markers. PU-MRI was performed using a non-contrast high-resolution two-dimensional T2-weighted turbo spin-echo imaging sequence. Four different SR deep learning models were used: the enhanced deep SR network (EDSR), widely activated SR network (WDSR), SR generative adversarial network (SRGAN), and residual dense network (RDN). The complex wavelet structural similarity index measure (CW-SSIM) was used to quantitatively assess the performance of the proposed SR images compared to PU-MRI. Two radiation oncologists used a 1-to-5 scale to subjectively evaluate the visibility of the prostatic urinary tract. Cohen's weighted kappa (k) was used as a measure of agreement of inter-operator reliability. The mean CW-SSIM in EDSR, WDSR, SRGAN, and RDN was 99.86%, 99.89%, 99.30%, and 99.67%, respectively. The mean prostatic urinary tract visibility scores of the radiation oncologists were 3.70 and 3.53 for PU-MRI (k = 0.93), 3.67 and 2.70 for EDSR (k = 0.89), 3.70 and 2.73 for WDSR (k = 0.88), 3.67 and 2.73 for SRGAN (k = 0.88), and 4.37 and 3.73 for RDN (k = 0.93), respectively. The results suggest that SR images using RDN are similar to the original images, and the SR deep learning models subjectively improve the visibility of the prostatic urinary tract.

Establishment of a New Qualitative Evaluation Method for Articular Cartilage by Dynamic T2w MRI Using a Novel Contrast Medium as a Water Tracer.

OBJECTIVE: In the early stages of cartilage damage, diagnostic methods focusing on the mechanism of maintaining the hydrostatic pressure of cartilage are thought to be useful. 17O-labeled water, which is a stable isotope of oxygen, has the advantage of no radiation exposure or allergic reactions and can be detected by magnetic resonance imaging (MRI). This study aimed to evaluate MRI images using 17O-labeled water in a rabbit model. DESIGN: Contrast MRI with 17O-labeled water and macroscopic and histological evaluations were performed 4 and 8 weeks after anterior cruciate ligament transection surgery in rabbits. A total of 18 T2-weighted images were acquired, and 17O-labeled water was manually administered on the third scan. The 17O concentration in each phase was calculated from the signal intensity at the articular cartilage. Macroscopic and histological grades were evaluated and compared with the 17O concentration. RESULTS: An increase in 17O concentration in the macroscopic and histologically injured areas was observed by MRI. Macroscopic evaluation showed that the 17O concentration significantly increased in the damaged site group. Histological evaluations also showed that 17O concentrations significantly increased at 36 minutes 30 seconds after initiating MRI scanning in the Osteoarthritis Research Society International (OARSI) grade 3 (0.493 in grade 0, 0.659 in grade 1, 0.4651 in grade 2, and 0.9964 in grade 3, P < 0.05). CONCLUSION: 17O-labeled water could visualize earlier articular cartilage damage, which is difficult to detect by conventional methods.

Medical Radiation Exposure Reduction in PET via Super-Resolution Deep Learning Model.

In positron emission tomography (PET) imaging, image quality correlates with the injected [18F]-fluorodeoxyglucose (FDG) dose and acquisition time. If image quality improves from short-acquisition PET images via the super-resolution (SR) deep learning technique, it is possible to reduce the injected FDG dose. Therefore, the aim of this study was to clarify whether the SR deep learning technique could improve the image quality of the 50%-acquisition-time image to the level of that of the 100%-acquisition-time image. One-hundred-and-eight adult patients were enrolled in this retrospective observational study. The supervised data were divided into nine subsets for nested cross-validation. The mean peak signal-to-noise ratio and structural similarity in the SR-PET image were 31.3 dB and 0.931, respectively. The mean opinion scores of the 50% PET image, SR-PET image, and 100% PET image were 3.41, 3.96, and 4.23 for the lung level, 3.31, 3.80, and 4.27 for the liver level, and 3.08, 3.67, and 3.94 for the bowel level, respectively. Thus, the SR-PET image was more similar to the 100% PET image and subjectively improved the image quality, as compared to the 50% PET image. The use of the SR deep-learning technique can reduce the injected FDG dose and thus lower radiation exposure.

Artificial intelligence for nuclear medicine in oncology.

As in all other medical fields, artificial intelligence (AI) is increasingly being used in nuclear medicine for oncology. There are many articles that discuss AI from the viewpoint of nuclear medicine, but few focus on nuclear medicine from the viewpoint of AI. Nuclear medicine images are characterized by their low spatial resolution and high quantitativeness. It is noted that AI has been used since before the emergence of deep learning. AI can be divided into three categories by its purpose: (1) assisted interpretation, i.e., computer-aided detection (CADe) or computer-aided diagnosis (CADx). (2) Additional insight, i.e., AI provides information beyond the radiologist's eye, such as predicting genes and prognosis from images. It is also related to the field called radiomics/radiogenomics. (3) Augmented image, i.e., image generation tasks. To apply AI to practical use, harmonization between facilities and the possibility of black box explanations need to be resolved.

Visualizing the urethra by magnetic resonance imaging without usage of a catheter for radiotherapy of prostate cancer.

The urethra position may shift due to the presence/absence of the catheter. Our proposed post-urination-magnetic resonance imaging (PU-MRI) technique is possible to identify the urethra without catheter. We aimed to verify the inter-operator difference in contouring the urethra by PU-MRI. The mean values of the evaluation indices of dice similarity coefficient, mean slice-wise Hausdorff distance, and center coordinates were 0.93, 0.17 mm, and 0.36 mm for computed tomography, and 0.75, 0.44 mm, and 1.00 mm for PU-MRI. Therefore, PU-MRI might be useful for identifying the prostatic urinary tract without using a urethral catheter. Clinical trial registration: Hokkaido University Hospital for Clinical Research (018-0221).

Development of Combination Methods for Detecting Malignant Uptakes Based on Physiological Uptake Detection Using Object Detection With PET-CT MIP Images.

Deep learning technology is now used for medical imaging. YOLOv2 is an object detection model using deep learning. Here, we applied YOLOv2 to FDG-PET images to detect the physiological uptake on the images. We also investigated the detection precision of abnormal uptake by a combined technique with YOLOv2. Using 3,500 maximum intensity projection (MIP) images of 500 cases of whole-body FDG-PET examinations, we manually drew rectangular regions of interest with the size of each physiological uptake to create a dataset. Using YOLOv2, we performed image training as transfer learning by initial weight. We evaluated YOLOv2's physiological uptake detection by determining the intersection over union (IoU), average precision (AP), mean average precision (mAP), and frames per second (FPS). We also developed a combination method for detecting abnormal uptake by subtracting the YOLOv2-detected physiological uptake. We calculated the coverage rate, false-positive rate, and false-negative rate by comparing the combination method-generated color map with the abnormal findings identified by experienced radiologists. The APs for physiological uptakes were: brain, 0.993; liver, 0.913; and bladder, 0.879. The mAP was 0.831 for all classes with the IoU threshold value 0.5. Each subset's average FPS was 31.60 ± 4.66. The combination method's coverage rate, false-positive rate, and false-negative rate for detecting abnormal uptake were 0.9205 ± 0.0312, 0.3704 ± 0.0213, and 0.1000 ± 0.0774, respectively. The physiological uptake of FDG-PET on MIP images was quickly and precisely detected using YOLOv2. The combination method, which can be utilized the characteristics of the detector by YOLOv2, detected the radiologist-identified abnormalities with a high coverage rate. The detectability and fast response would thus be useful as a diagnostic tool.

Magnetic resonance imaging T1 and T2 mapping provide complementary information on the bone mineral density regarding cancellous bone strength in the femoral head of postmenopausal women with osteoarthritis.

BACKGROUND: Since bone mass is not the only determinant of bone strength, there has been increasing interest in incorporating the bone quality into fracture risk assessments. We aimed to examine whether the magnetic resonance imaging (MRI) T1 or T2 mapping value could provide information that is complementary to bone mineral density for more accurate prediction of cancellous bone strength. METHODS: Four postmenopausal women with hip osteoarthritis underwent 3.0-T MRI to acquire the T1 and T2 values of the cancellous bone of the femoral head before total hip arthroplasty. After the surgery, the excised femoral head was portioned into multiple cubic cancellous bone specimens with side of 5 mm, and the specimens were then subjected to microcomputed tomography followed by biomechanical testing. FINDINGS: The T1 value positively correlated with the yield stress (σy) and collapsed stress (σc). The T2 value did not correlate with the yield stress, but it correlated with the collapsed stress and strength reduction ratio (σc/σy), which reflects the progressive re-fracture risk. Partial correlation coefficient analyses, after adjusting for the bone mineral density, showed a statistically significant correlation between T1 value and yield stress. The use of multiple coefficients of determination by least squares analysis emphasizes the superiority of combining the bone mineral density and the MRI mapping values in predicting the cancellous bone strength compared with the bone mineral density-based prediction alone. INTERPRETATION: The MRI T1 and T2 values predict cancellous bone strength including the change in bone quality.

Acceleration of ASL-based time-resolved MR angiography by acquisition of control and labeled images in the same shot (ACTRESS).

PURPOSE: Noncontrast 4D-MR-angiography (MRA) using arterial spin labeling (ASL) is beneficial because high spatial and temporal resolution can be achieved. However, ASL requires acquisition of labeled and control images for each phase. The purpose of this study is to present a new accelerated 4D-MRA approach that requires only a single control acquisition, achieving similar image quality in approximately half the scan time. METHODS: In a multi-phase Look-Locker sequence, the first phase was used as the control image and the labeling pulse was applied before the second phase. By acquiring the control and labeled images within a single Look-Locker cycle, 4D-MRA was generated in nearly half the scan time of conventional ASL. However, this approach potentially could be more sensitive to off-resonance and magnetization transfer (MT) effects. To counter this, careful optimizations of the labeling pulse were performed by Bloch simulations. In in-vivo studies arterial visualization was compared between the new and conventional ASL approaches. RESULTS: Optimization of the labeling pulse successfully minimized off-resonance effects. Qualitative assessment showed that residual MT effects did not degrade visualization of the peripheral arteries. CONCLUSION: This study demonstrated that the proposed approach achieved similar image quality as conventional ASL-MRA approaches in just over half the scan time. Magn Reson Med 79:224-233, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Quantification of myocardial blood flow with dynamic perfusion 3.0 Tesla MRI: Validation with (15) O-water PET.

BACKGROUND: To develop and validate a method for quantifying myocardial blood flow (MBF) using dynamic perfusion magnetic resonance imaging (MBFMRI ) at 3.0 Tesla (T) and compare the findings with those of (15) O-water positron emission tomography (MBFPET ). METHODS: Twenty healthy male volunteers underwent magnetic resonance imaging (MRI) and (15) O-water positron emission tomography (PET) at rest and during adenosine triphosphate infusion. The single-tissue compartment model was used to estimate the inflow rate constant (K1). We estimated the extraction fraction of Gd-DTPA using K1 and MBF values obtained from (15) O-water PET for the first 10 subjects. For validation, we calculated MBFMRI values for the remaining 10 subjects and compared them with the MBFPET values. In addition, we compared MBFMRI values of 10 patients with coronary artery disease with those of healthy subjects. RESULTS: The mean resting and stress MBFMRI values were 0.76 ± 0.10 and 3.04 ± 0.82 mL/min/g, respectively, and showed excellent correlation with the mean MBFPET values (r = 0.96, P < 0.01). The mean stress MBFMRI value was significantly lower for the patients (1.92 ± 0.37) than for the healthy subjects (P < 0.001). CONCLUSION: The use of dynamic perfusion MRI at 3T is useful for estimating MBF and can be applied for patients with coronary artery disease.

FDG PET/CT diagnostic criteria may need adjustment based on MRI to estimate the presurgical risk of extrapelvic infiltration in patients with uterine endometrial cancer.

PURPOSE: The staging of endometrial cancer requires surgery which carries the risk of morbidity. FDG PET/CT combined with anatomical imaging may reduce the number of unnecessary lymphadenectomies by demonstrating the risk of extrapelvic infiltration. The purpose of this study was to optimize FDG PET/CT diagnostic criteria for risk assessment in endometrial cancer after first-line risk triage with MRI. METHODS: The study population comprised 37 patients who underwent curative surgery for the treatment of endometrial cancer. First, the risk of extrapelvic infiltration was triaged using MRI. Second, multiple glucose metabolic profiles of the primary lesion were assessed with FDG PET/CT, and these were correlated with the histopathological risk of extrapelvic infiltration including lymphovascular space invasion (LVSI) and high-grade malignancy (grades 2 and 3). The results of histological correlation were used to adjust FDG PET/CT diagnostic criteria. RESULTS: Presurgical assessment using MRI was positive for deep (>50 %) myometrial invasion in 17 patients. The optimal FDG PET/CT diagnostic criteria vary depending on the results of MRI. Specifically, SUVmax (≥16.0) was used to indicate LVSI risk with an overall diagnostic accuracy of 88.2 % in patients with MRI findings showing myometrial invasion. High-grade malignancy did not correlate with any of metabolic profiles in this patient group. In the remaining patients without myometrial invasion, lesion glycolysis (LG) or metabolic volume were better indicators of LVSI than SUVmax with the same diagnostic accuracy of 80.0 %. In addition, LG (≥26.9) predicted high-grade malignancy with an accuracy of 72.2 %. Using the optimized cut-off criteria for LVSI, glucose metabolic profiling of primary lesions correctly predicted lymph node metastasis with an accuracy of 73.0 %, which was comparable with the accuracy of visual assessment for lymph node metastasis using MRI and FDG PET/CT. CONCLUSION: FDG PET/CT diagnostic criteria may need adjustment based on the anatomical information provided by MRI. The optimized criteria can predict the risk of pathology-proven LVSI correctly in 83.8 % of patients before surgery, and thus would improve presurgical treatment planning.

[Comparison of fat suppression techniques of bilateral breast dynamic sequence at 3.0 T: utility of three-point DIXON technique].

The purposes of this study were to determine optimum flip angles (FAs) and to compare the effectiveness of fat suppression and signal homogeneity among three techniques, spectral attenuated with inversion recovery (SPAIR), principle of selective excitation technique (PROSET), and three-point DIXON technique (DIXON), of the bilateral breast dynamic sequence acquired using the optimum FA at 3.0 T. Using a homemade phantom that represented a tumor, fat, and a mammary gland, the optimum FAs were determined from the change of fat signal intensity, signal-to-noise ratio (SNR) of the mammary gland, and contrast ratio (CR) between the tumor and mammary gland. The effectiveness of fat suppression and signal homogeneity were compared in ten breast cancer cases, using the CR between fat and pectoralis muscle signal intensities and the standard deviation (SD) of fat signal intensity, respectively. The optimum FAs for SPAIR, PROSET, and DIXON were 10, 20, and 20 degrees, respectively. The mean CR between fat and pectoralis muscle signal intensities achieved using SPAIR, PROSET, and DIXON were 0.19, 0.30 and 0.40, respectively, and the mean SDs of the fat signal intensities were 90.2, 103.1, and 30.5, respectively. The DIXON technique provided better fat suppression and signal homogeneity than the other two techniques. The results of this study suggest the possible application of the DIXON technique in combination with the optimum FA setting as an effective fat suppression technique for the bilateral breast dynamic sequence at 3.0 T.

Identification and further differentiation of subendocardial and transmural myocardial infarction by fast strain-encoded (SENC) magnetic resonance imaging at 3.0 Tesla.

OBJECTIVES: To investigate whether subendocardial and transmural myocardial infarction can be identified and differentiated using the peak circumferential and longitudinal strains measured by fast strain-encoded (SENC). METHODS: Nineteen patients with ischemic heart diseases underwent imaging with fast SENC and late gadolinium enhancement (LGE) MRI at 3 T. Fast SENC measurements were performed in three short-axis slices (basal, mid-ventricular and apical levels) and one long-axis view (four-chamber) to assess peak longitudinal and circumferential systolic strains. RESULTS: All patients showed myocardial infarction with an average of 7 positive LGE segments. A total of 304 segments for longitudinal strains (LS) and 114 segments for circumferential strains (CS) could be analysed. Positive LGE segments showed lower peak CS and LS compared with the no LGE segments (P < 0.0001 for both). Segments with subendocardial infarction showed reduced CS and LS compared with the no LGE segments (P < 0.0001 for both). There was a significant difference in CS between subendocardial and transmural infarct segments (P = 0.03), but no significant difference in LS between them (P = 0.64). CONCLUSIONS: Fast SENC can identify old myocardial infarction and differentiate subendocardial from transmural infarction.

VIBE MRI for evaluating the normal and abnormal gastrointestinal tract in fetuses.

OBJECTIVE: The great potential of MRI for assessing gastrointestinal abnormalities in fetuses has been described. T1-weighted images may add additional information to T2-weighted images in diagnosing fetal gastrointestinal abnormalities. The objective of this study was to assess the performance of a 3D volumetric interpolated breath-hold sequence (VIBE) in evaluating the normal and abnormal fetal gastrointestinal tract. CONCLUSION: VIBE provides high-quality T1-weighted and 3D MR colonography images for the evaluation of the normal and abnormal gastrointestinal tract in fetuses, and 3D MR colonography provides excellent delineation of the meconium.

Thymic hyperplasia and thymus gland tumors: differentiation with chemical shift MR imaging.

PURPOSE: To prospectively evaluate chemical shift magnetic resonance (MR) imaging for differentiating thymic hyperplasia from tumors of the thymus gland. MATERIALS AND METHODS: The institutional review board approved this study; informed consent was obtained and patient confidentiality was protected. The authors assessed 41 patients (17 male, 24 female; age range, 16-78 years) in whom thymic lesions were seen at chest computed tomography. Patients were assigned to a hyperplasia group (n=23) (18 patients with hyperplastic thymus associated with Graves disease and five with rebound thymic hyperplasia) and a tumor group (n=18) (seven patients with thymomas, four with invasive thymomas, five with thymic cancers, and two with malignant lymphomas). T2-weighted fast spin-echo and T1-weighted in-phase and opposed-phase MR images were obtained in all patients and visually assessed. A chemical shift ratio (CSR), determined by comparing the signal intensity of the thymus gland with that of the paraspinal muscle, was calculated for quantitative analysis. Mean CSRs for the patient groups and subgroups were analyzed by using Welch t and Newman-Keuls tests. P<.05 indicated a significant difference. RESULTS: The thymus gland had homogeneous signal intensity in all 23 patients in the hyperplasia group and in 12 of the 18 patients in the tumor group. The mean CSR (+/- standard deviation) was 0.614 +/- 0.130 in the hyperplasia group and 1.026 +/- 0.039 in the tumor group. Mean CSRs in the patients with a hyperplastic thymus and Graves disease, rebound thymic hyperplasia, thymoma, invasive thymoma, thymic cancer, and malignant lymphoma were 0.594 +/- 0.120, 0.688 +/- 0.154, 1.033 +/- 0.043, 1.036 +/- 0.040, 1.020 +/- 0.044, and 0.997 +/- 0.010, respectively. The difference in CSR between the hyperplasia and tumor groups was significant (P<.001). Mean CSRs in the hyperplasia subgroups were lower than those in the tumor subgroups (P<.001). All hyperplasia group patients had an apparent decrease in thymus gland signal intensity at chemical shift MR imaging; no tumor group patients had a decrease in thymus gland signal intensity. CONCLUSION: Chemical shift MR imaging can be used to differentiate thymic hyperplasia from thymic tumors.