Model-data-driven adversarial active learning for brain tumor segmentation.

Active learning (AL) attempts to select informative samples in a dataset to minimize the number of required labels while maximizing the performance of the model. Current AL in segmentation tasks is limited to the expansion of popular classification-based methods including entropy, MC-dropout, etc. Meanwhile, most applications in the medical field are simply migrations that fail to consider the nature of medical images, such as high class imbalance, high domain difference, and data scarcity. In this study, we address these challenges and propose a novel AL framework for medical image segmentation task. Our approach introduces a pseudo-label-based filter addressing excessive blank patches in medical abnormalities segmentation tasks, e.g., lesions, and tumors, used before the AL selection. This filter helps reduce resource usage and allows the model to focus on selecting more informative samples. For the sample selection, we propose a novel query strategy that combines both model impact and data stability by employing adversarial attack. Furthermore, we harness the adversarial samples generated during the query process to enhance the robustness of the model. The experimental results verify our framework's effectiveness over various state-of-the-art methods. Our proposed method only needs less than 14% annotated patches in 3D brain MRI multiple sclerosis (MS) segmentation tasks and 20% for Low-Grade Glioma (LGG) tumor segmentation to achieve competitive results with full supervision. These promising outcomes not only improve performance but alleviate the time burden associated with expert annotation, thereby facilitating further advancements in the field of medical image segmentation. Our code is available at https://github.com/HelenMa9998/adversarial_active_learning.

Difference in Cyclic Versus Non-cyclic Symptom Patterns in Patients with the Symptoms of Gastroparesis Undergoing Bioelectric Therapy.

INTRODUCTION: Patients with gastroparesis (Gp) have symptoms with or without a cyclic pattern. This retrospective study evaluates differences in cyclic vs. non-cyclic symptoms of Gp by analyzing mucosal electrogastrogram (mEG), familial dysautonomias, and response to gastric stimulation. METHODS: 37 patients with drug refractory Gp, 7 male and 30 female, with a mean age of 41.4 years, were studied. 18 had diabetes mellitus, 25 had cyclic (Cyc), and 12 had a non-cyclic (NoCyc) pattern of symptoms. Patients underwent temporary mucosal gastric stimulator (tGES) placement, which was done as a trial before permanent stimulator (GES) placement. Electrogastrogram (EGG) by mucosal (mEG) measures, including frequency, amplitude, and frequency-amplitude ratio (FAR), were pre- and post-tGES. Patients' history of personal and familial dysautonomias, quality of life, and symptom scores were recorded. Baseline vs. follow-ups were compared by paired t tests and McNemar's tests. T tests contrasted symptom scores, gastric emptying tests (GET), and mEG measures, while chi-squared tests deciphered comorbidity differences between two groups and univariate and multivariate analyses. RESULTS: There were significantly more patients with diabetes in the Cyc group vs. the NoCyc group. Using a 1 point in symptom outcome, 18 patients did not improve and 19 did improve with tGES. Using univariable analysis, with the cyclic pattern as a predictor, patients exhibiting a cyclic pattern had an odds ratio of 0.22 (95% CI 0.05-0.81, p = 0.054) for achieving an improvement of at least one unit in vomiting at follow-up from baseline. The mucosal electrogastrogram frequency to amplitude ratio (FAR) for the "not Improved" group was 19.6 [3.5, 33.6], whereas, for the "Improved" group, it was 54.3 [25.6, 72.5] with a p-value of 0.049. For multivariate logistic regression, accounting for sex and age squared, patients exhibiting a cyclic pattern had an adjusted odds ratio (OR) of 0.16 (95% CI 0.03-0.81, p = 0.027) for achieving an improvement of at least one unit in vomiting at follow-up from baseline. The two groups had no significant differences in the personal or inherited history of investigated familial patterns. CONCLUSION: This study shows differences in Gp patients with Cyc vs. NoCyc symptoms in several areas. Larger studies are needed to elicit further differences between the two groups about cycles of symptoms, EGG, findings, familial patterns, and response to mucosal GES.

iSPAN: Explainable prediction of outcomes post thrombectomy with Machine Learning.

PURPOSE: This study aimed to develop and evaluate a machine learning model and a novel clinical score for predicting outcomes in stroke patients undergoing endovascular thrombectomy. MATERIALS AND METHODS: This retrospective study included all patients aged over 18 years with an anterior circulation stroke treated at a thrombectomy centre from 2010 to 2020 with external validation. The primary outcome was day 90 mRS ≥3. Existing clinical scores (SPAN and PRE) and Machine Learning (ML) models were compared. A novel clinical score (iSPAN) was derived by adding an optimised weighting of the most important ML features to the SPAN. RESULTS: 812 patients were initially included (397 female, average age 73), 63 for external validation. The best performing clinical score and ML model were SPAN and XGB (sensitivity, specificity and accuracy 0.290, 0.967, 0.628 and 0.693, 0.783, 0.738 respectively). A significant difference was found overall and our XGB model was more accurate than SPAN (p < 0.0018). The most important features were Age, mTICI and total number of passes. The addition of 11 points for mTICI of ≤2B and 3 points for ≥3 passes to the SPAN achieved the best accuracy and was used to create the iSPAN. iSPAN was not significantly less accurate than our XGB model (p > 0.5). In the external validation set, iSPAN and SPAN achieved sensitivity, specificity, and accuracy of (0.735, 0.862, 0.79) and (0.471, 0.897, 0.67) respectively. CONCLUSION: iSPAN incorporates machine-derived features to achieve better predictions compared to existing clinical scores. It is not inferior to our XGB model and is externally generalisable.

A Radiomic "Warning Sign" of Progression on Brain MRI in Individuals with MS.

BACKGROUND AND PURPOSE: MS is a chronic progressive, idiopathic, demyelinating disorder whose diagnosis is contingent on the interpretation of MR imaging. New MR imaging lesions are an early biomarker of disease progression. We aimed to evaluate a machine learning model based on radiomics features in predicting progression on MR imaging of the brain in individuals with MS. MATERIALS AND METHODS: This retrospective cohort study with external validation on open-access data obtained full ethics approval. Longitudinal MR imaging data for patients with MS were collected and processed for machine learning. Radiomics features were extracted at the future location of a new lesion in the patients' prior MR imaging ("prelesion"). Additionally, "control" samples were obtained from the normal-appearing white matter for each participant. Machine learning models for binary classification were trained and tested and then evaluated the external data of the model. RESULTS: The total number of participants was 167. Of the 147 in the training/test set, 102 were women and 45 were men. The average age was 42 (range, 21-74 years). The best-performing radiomics-based model was XGBoost, with accuracy, precision, recall, and F1-score of 0.91, 0.91, 0.91, and 0.91 on the test set, and 0.74, 0.74, 0.74, and 0.70 on the external validation set. The 5 most important radiomics features to the XGBoost model were associated with the overall heterogeneity and low gray-level emphasis of the segmented regions. Probability maps were produced to illustrate potential future clinical applications. CONCLUSIONS: Our machine learning model based on radiomics features successfully differentiated prelesions from normal-appearing white matter. This outcome suggests that radiomics features from normal-appearing white matter could serve as an imaging biomarker for progression of MS on MR imaging.

Nutritional Assessment in Patients after Gastric Electrical Stimulation (GES).

BACKGROUND: Gastric electrical stimulation (GES) is used for patients with drug-refractory gastroparesis (Gp) symptoms. Approximately two-thirds of patients with Gp symptoms are either overweight or obese. We aimed to assess symptoms and nutritional status pre-GES and post-GES placement in a large sample of drug-refractory Gp patients. METHODS: We conducted a chart review of 282 patients with drug-refractory Gp who received temporary followed by permanent GES at an academic medical center. Gastrointestinal symptoms were collected by a traditional standardized PRO (0-4, 0 being asymptomatic and 4 being worst symptoms), baseline nutritional status by BMI plus subjective global assessment (SGA score A, B, C, for mild, moderate, and severe nutritional deficits), ability to tolerate diet, enteral tube access, and parenteral therapy were assessed at baseline and after permanent GES placement. RESULTS: Comparing baseline with permanent, GES was found to significantly improve upper GI symptoms in all quartiles. Of the 282 patients with baseline body mass index (BMI) information, 112 (40%) patients were severely malnourished at baseline, of which 36 (32%) patients' nutritional status improved after GES. Among all patients, 76 (68%) patients' nutritional status remained unchanged. Many patients with high BMI were malnourished by SGA. CONCLUSION: We conclude that symptomatic patients of different BMIs showed improvement in their GI symptoms irrespective of baseline nutritional status. Severely malnourished patients were found to have an improvement in their nutritional status after GES therapy. We conclude that BMI, even if high, is not by itself a contraindication for GES therapy for symptomatic patients.

Gastroparesis and Gastroparesis Syndromes as Neuromuscular Disorders.

Gastroparesis syndromes (GpS) are a spectrum of disorders presenting with characteristic symptoms increasingly recognized as being gastrointestinal (GI) neuromuscular disorders (NMDs). This review focuses on GpS as a manifestation of neurologic disorders of GI NMD. GpS can be associated with systemic abnormalities, including inflammatory, metabolic, and serologic disorders, as well as autoimmune antibodies via nerve and muscle targets in the GI tract, which can be treated with immunotherapy, such as intravenous immunoglobulin. GpS are associated with autonomic (ANS) and enteric (ENS) dysfunction. Disorders of ANS may interact with the ENS and are the subject of continued investigation. ENS disorders have been recognized for a century but have only recently begun to be fully quantified. Anatomic structural changes in the GI tract are increasingly recognized in GpS. Detailed descriptions of anatomic changes in GpS, and their correlation with physiologic findings, have opened a new era of investigation. The management of GpS, when viewed as GI NMD, has shifted the paradigms of both diagnosis and treatment. This article concludes with current approaches to GpS directed at underlying neuromuscular pathology.

Autogenic biofeedback training improves autonomic responses in a participant with cervical motor complete spinal cord injury- case report.

STUDY DESIGN: Single-subject case design OBJECTIVE: To evaluate the Autogenic Feedback Training Exercise (AFTE) on autonomic nervous system responses. INTRODUCTION: AFTE combines specific autogenic exercises with biofeedback of multiple physiological responses. Originally developed by the National Aeronautics and Space Administration (NASA), AFTE is used to improve post-flight orthostatic intolerance and motion sickness in astronauts. Individuals with cervical or upper thoracic spinal cord injury (SCI) often present symptoms of autonomic dysfunction similar to astronauts. We hypothesize that AFTE challenges nervous system baroreflex, gastric and vascular responses often impaired after SCI. METHODS: Using a modified AFTE protocol, we trained a hypotensive female participant with cervical motor complete (C5/6-AIS A) SCI, and a male non-injured control participant (NI) and measured blood pressure (BP), heart rate (HR), gastric electrical activity, and microvascular blood volume before, during and after AFTE. The participants were instructed to complete breathing and imagery exercises to help facilitate relaxation. Subsequently, they were instructed to use stressful imagery and breathing exercises during arousal trials. RESULTS: Both participants completed 8 sessions of approximately 45 min each. Microvascular blood volume decreased 23% (SCI) and 54% (NI) from the beginning to the end of the stimulation cycles. The participant with SCI became progressively more normotensive and improved levels of gastric electrical activity, while the NI participant's changes in HR, gastric electrical activity, and BP were negligible. CONCLUSIONS: AFTE may offer a novel non-pharmacologic intervention to minimize symptoms of dysautonomia in people with SCI.

Using deep learning-derived image features in radiologic time series to make personalised predictions: proof of concept in colonic transit data.

OBJECTIVES: Siamese neural networks (SNN) were used to classify the presence of radiopaque beads as part of a colonic transit time study (CTS). The SNN output was then used as a feature in a time series model to predict progression through a CTS. METHODS: This retrospective study included all patients undergoing a CTS in a single institution from 2010 to 2020. Data were partitioned in an 80/20 Train/Test split. Deep learning models based on a SNN architecture were trained and tested to classify images according to the presence, absence, and number of radiopaque beads and to output the Euclidean distance between the feature representations of the input images. Time series models were used to predict the total duration of the study. RESULTS: In total, 568 images of 229 patients (143, 62% female, mean age 57) patients were included. For the classification of the presence of beads, the best performing model (Siamese DenseNET trained with a contrastive loss with unfrozen weights) achieved an accuracy, precision, and recall of 0.988, 0.986, and 1. A Gaussian process regressor (GPR) trained on the outputs of the SNN outperformed both GPR using only the number of beads and basic statistical exponential curve fitting with MAE of 0.9 days compared to 2.3 and 6.3 days (p < 0.05) respectively. CONCLUSIONS: SNNs perform well at the identification of radiopaque beads in CTS. For time series prediction our methods were superior at identifying progression through the time series compared to statistical models, enabling more accurate personalised predictions. CLINICAL RELEVANCE STATEMENT: Our radiologic time series model has potential clinical application in use cases where change assessment is critical (e.g. nodule surveillance, cancer treatment response, and screening programmes) by quantifying change and using it to make more personalised predictions. KEY POINTS: • Time series methods have improved but application to radiology lags behind computer vision. Colonic transit studies are a simple radiologic time series measuring function through serial radiographs. • We successfully employed a Siamese neural network (SNN) to compare between radiographs at different points in time and then used the output of SNN as a feature in a Gaussian process regression model to predict progression through the time series. • This novel use of features derived from a neural network on medical imaging data to predict progression has potential clinical application in more complex use cases where change assessment is critical such as in oncologic imaging, monitoring for treatment response, and screening programmes.

Gastroparesis syndromes: emerging drug targets and potential therapeutic opportunities.

INTRODUCTION: Gastroparesis (Gp) and related disorders such as chronic unexplained nausea and vomiting and functional dyspepsia, known as gastropareis syndromes (GpS), have large unmet needs. Mainstays of GpS treatments are diet and drugs. AREAS COVERED: The purpose of this review is to explore potential new medications and other therapies for gastroparesis. Before discussing possible new drugs, the currently used drugs are discussed. These include dopamine receptor antagonists, 5-hydroxytryptamine receptor agonists and antagonists, neurokinin-1 receptor antagonists and other anti-emetics. The article also considers future drugs that may be used for Gp, based on currently known pathophysiology. EXPERT OPINION: Gaps in knowledge about the pathophysiology of gastroparesis and related syndromes are critical to developing therapeutic agents that will be successful. Recent major developments in the gastroparesis arena are related to microscopic anatomy, cellular function, and pathophysiology. The major challenges moving forward will be to develop the genetic and biochemical correlates of these major developments in gastroparesis research.

Baseline Characteristics and Predictive Factors of Intravenous Immunoglobulin Response in Drug and Device Refractory Gastroparesis Symptoms.

INTRODUCTION: Intravenous immunoglobulin (IVIG) has been shown in a small pilot series to be helpful for some patients with gastroparesis that is refractory to drugs, devices, and surgical therapies. Many but not all patients have serologic neuromuscular markers. We hypothesize that those patients with serologic markers and/or longer duration of therapy would have better responses to IVIG. MATERIALS AND METHODS: We studied 47 patients with a diagnosis of gastroparesis and gastroparesis-like syndrome that had all failed previous therapies including available and investigational drugs, devices, and/or pyloric therapies. Patients had a standardized 12-week course of IVIG, dosed as 400 mg/kg per week intravenously. Symptom assessment was done with Food and Drug Administration (FDA) compliant traditional patient-reported outcomes. Success to IVIG was defined as 20% or greater reduction in average symptom scores from baseline to the latest evaluation. RESULTS: Fourteen patients (30%) had a response, and 33 (70%) had no response per our definition. Patients responding had a higher glutamic acid decarboxylase 65 positivity (64% vs. 30%, P =0.049, missing=3) and longer duration of therapy (>12 wk/continuous: 86% vs. 48%, P =0.09). CONCLUSIONS: In this moderately sized open-label series of refractory patients with gastroparesis symptoms treated with IVIG, 30% of patients responded. While serologic markers and extended therapies show a trend to greater response, neither was statistically significant, except for glutamic acid decarboxylase 65 which showed a higher positivity rate in responders. We conclude that a clinical trial of IVIG may be warranted in severely refractory patients with gastroparesis symptoms.

Gastric Electrical Stimulation for the Treatment of Gastroparesis or Gastroparesis-like Symptoms: A Systemic Review and Meta-analysis.

BACKGROUND: The effects of gastric electrical stimulation are not fully understood. We aimed to assess the efficacy of gastric electrical stimulation (GES) for patients with gastroparesis and gastroparesis-like symptoms. MATERIALS AND METHODS: We searched PubMed, Scopus, Cochrane, Web of Science, Embase, and Science Direct to identify controlled trials and cohort studies. We used random effects models to estimate pooled effects. A total of nine studies met the criteria and were included for the final qualitative synthesis and the quantitative analysis. We examined the mean absolute differences (MD) and 95% CIs. RESULTS: Nine studies (n = 730) met the criteria and were included for the final qualitative synthesis and the quantitative analysis. There was significant improvement in gastrointestinal (GI) total symptom score (TSS) with the GES group compared with controls during the randomized blind trials. This effect was sustained at 12 months after treatment compared with before treatment (MD = -6.07; 95% CI, -4.5 to -7.65; p < 0.00001). The pooled effect estimate showed a significant improvement in frequency of weekly vomiting episodes at 12 months compared with before treatment (MD = -15.59; 95% CI, -10.29 to -20.9; p < 0.00001). CONCLUSION: GES appears beneficial, with significant improvement in GI TSS, weekly vomiting frequency, gastric emptying study, and quality of life.

Radiology artificial intelligence: a systematic review and evaluation of methods (RAISE).

OBJECTIVE: There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed. METHODS: We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered. RESULTS: Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range .49-.99), AUC of 0.903 (range 1.00-0.61) and Accuracy of 89.4 (range 70.2-100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%). CONCLUSION: This systematic review has surveyed the major advances in AI as applied to clinical radiology. KEY POINTS: • While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic.

Low-Resolution Electrogastrogram at Baseline and Response to Temporary Gastric Electrical Stimulation-A Comparison of Cutaneous With Mucosal Recordings.

INTRODUCTION: Gastric electrical stimulation (GES) is a widely accepted therapy for gastroparesis symptoms, but how a brief cutaneous electrogastrogram (EGG) can be used in conjunction with GES has not been well defined. We evaluated the clinical importance of EGG, its correlation with mucosal electrograms (mEGs), gastric emptying tests (GETs), and gastrointestinal symptoms before and after temporary GES (tGES). MATERIALS AND METHODS: We studied 1345 patients; 991 had complete data. EGG measurements like frequency and amplitude were recorded at baseline and five days post-tGES using short recording periods. A total of 266 participants having additional cutaneous propagation values were separately analyzed. Patients underwent solid GET before and after tGES and self-reported symptoms using standardized traditional patient-reported outcomes (TradPRO) scores. Pearson correlations were assessed at baseline, post-stimulation, and their changes over the follow-up period. RESULTS: EGG measures correlated with symptoms and GET results. Patients with abnormal baseline cutaneous frequency had higher baseline total symptom scores (p < 0.003). Post-tGES, one-hour gastric emptying was significantly changed (p < 0.0001) and was mainly observed with abnormal baseline cutaneous frequencies (p < 0.0001). Cutaneous frequency significantly increased after tGES (p < 0.0001), correlating positively with TradPRO scores and one-hour gastric emptying. Mucosal and cutaneous measures correlated pre- and post-treatment. Of the 266 patients, 153 changed propagation states between baseline and temporary; changing states from lower at baseline to higher at temporary was more likely than vice versa. Short EGG recording times can demonstrate changes after the bioelectric therapy of GES. CONCLUSION: EGG is valuable in the diagnosis of delayed gastric emptying and comparable with mEG. It is less invasive and can identify patients who may require GES. Frequency, amplitude, their ratio (frequency-amplitude ratio), and propagation appear to be reliable measures of EGG. EGG provides cost-effective measurement of electrophysiological properties and significantly correlates with important clinical measures. Shorter EGG recording times may be adequate to see changes from bioelectric therapies. CLINICAL TRIAL REGISTRATION: The Clinicaltrials.gov registration number for the study is NCT03876288.

Baseline predictive factors for foregut and hindgut response to long-term gastric electrical stimulation using augmented energy.

INTRODUCTION: Gastric electrical stimulation (GES) has been recommended for drug refractory patients with gastroparesis, but no clear baseline predictors of symptom response exist. We hypothesized that long-term predictors to GES for foregut and hindgut symptoms exist, particularly when using augmented energies. PATIENTS: We evaluated 307 patients at baseline, 1 week post temporary GES, and one year after permanent GES. Baseline measures included upper and lower symptoms by patient-reported outcomes (PRO), solid and liquid gastric emptying (GET), cutaneous, mucosal, and serosal electrophysiology (EGG, m/s EG), BMI, and response to temporary stimulation. METHODS: Foregut and hindgut PRO symptoms were analyzed for 12-month patient outcomes. All patients utilized a standardized energy algorithm with the majority of patients receiving medium energy at 12 months. Patients were categorized based on change in average GI symptom scores at the time of permanent GES compared to baseline using a 10% decrease over time as the cutoff between improvers versus non-improvers. RESULTS: By permanent GES implant, average foregut and hindgut GI symptom scores reduced 42% in improved patients (n = 199) and increased 27% in non-improved patients (n = 108). Low BMI, baseline infrequent urination score, mucosal EG ratio, and proximal mucosal EG low-resolution amplitude remained significant factors for improvement status. CONCLUSIONS: GES, for patients responding positively, improved both upper/foregut and lower/hindgut symptoms with most patients utilizing higher than nominal energies. Low baseline BMI and the presence of infrequent urination along with baseline gastric electrophysiology may help identify those patients with the best response to GES/bio-electric neuromodulation.

Vessel-CAPTCHA: An efficient learning framework for vessel annotation and segmentation.

Deep learning techniques for 3D brain vessel image segmentation have not been as successful as in the segmentation of other organs and tissues. This can be explained by two factors. First, deep learning techniques tend to show poor performances at the segmentation of relatively small objects compared to the size of the full image. Second, due to the complexity of vascular trees and the small size of vessels, it is challenging to obtain the amount of annotated training data typically needed by deep learning methods. To address these problems, we propose a novel annotation-efficient deep learning vessel segmentation framework. The framework avoids pixel-wise annotations, only requiring weak patch-level labels to discriminate between vessel and non-vessel 2D patches in the training set, in a setup similar to the CAPTCHAs used to differentiate humans from bots in web applications. The user-provided weak annotations are used for two tasks: (1) to synthesize pixel-wise pseudo-labels for vessels and background in each patch, which are used to train a segmentation network, and (2) to train a classifier network. The classifier network allows to generate additional weak patch labels, further reducing the annotation burden, and it acts as a second opinion for poor quality images. We use this framework for the segmentation of the cerebrovascular tree in Time-of-Flight angiography (TOF) and Susceptibility-Weighted Images (SWI). The results show that the framework achieves state-of-the-art accuracy, while reducing the annotation time by ∼77% w.r.t. learning-based segmentation methods using pixel-wise labels for training.

Evaluation of a marker-less, intra-operative, augmented reality guidance system for robot-assisted laparoscopic radical prostatectomy.

PURPOSE: Robot-assisted laparoscopic radical prostatectomy (RALRP) using the da Vinci surgical robot is a common treatment for organ-confined prostate cancer. Augmented reality (AR) can help during RALRP by showing the surgeon the location of anatomical structures and tumors from preoperative imaging. Previously, we proposed hand-eye and camera intrinsic matrix estimation procedures that can be carried out with conventional instruments within the patient during surgery, take < 3 min to perform, and fit seamlessly in the existing surgical workflow. In this paper, we describe and evaluate a complete AR guidance system for RALRP and quantify its accuracy. METHODS: Our AR system requires three transformations: the transrectal ultrasound (TRUS) to da Vinci transformation, the camera intrinsic matrix, and the hand-eye transformation. For evaluation, a 3D-printed cross-wire was visualized in TRUS and stereo endoscope in a water bath. Manually triangulated cross-wire points from stereo images were used as ground truth to evaluate overall TRE between these points and points transformed from TRUS to camera. RESULTS: After transforming the ground-truth points from the TRUS to the camera coordinate frame, the mean target registration error (TRE) (SD) was [Formula: see text] mm. The mean TREs (SD) in the x-, y-, and z-directions are [Formula: see text] mm, [Formula: see text] mm, and [Formula: see text] mm, respectively. CONCLUSIONS: We describe and evaluate a complete AR guidance system for RALRP which can augment preoperative data to endoscope camera image, after a deformable magnetic resonance image to TRUS registration step. The streamlined procedures with current surgical workflow and low TRE demonstrate the compatibility and readiness of the system for clinical translation. A detailed sensitivity study remains part of future work.