RAPHIA: A deep learning pipeline for the registration of MRI and whole-mount histopathology images of the prostate

Image registration can map the ground truth extent of prostate cancer from histopathology images onto MRI, facilitating the development of machine learning methods for early prostate cancer detection. Here, we present RAdiology PatHology Image Alignment (RAPHIA), an end-to-end pipeline for efficient and accurate registration of MRI and histopathology images. RAPHIA automates several time-consuming manual steps in existing approaches including prostate segmentation, estimation of the rotation angle and horizontal flipping in histopathology images, and estimation of MRI-histopathology slice correspondences. By utilizing deep learning registration networks, RAPHIA substantially reduces computational time. Furthermore, RAPHIA obviates the need for a multimodal image similarity metric by transferring histopathology image representations to MRI image representations and vice versa. With the assistance of RAPHIA, novice users achieved expert-level performance, and their mean error in estimating histopathology rotation angle was reduced by 51% (12 degrees vs 8 degrees), their mean accuracy of estimating histopathology flipping was increased by 5% (95.3% vs 100%), and their mean error in estimating MRI-histopathology slice correspondences was reduced by 45% (1.12 slices vs 0.62 slices). When compared to a recent conventional registration approach and a deep learning registration approach, RAPHIA achieved better mapping of histopathology cancer labels, with an improved mean Dice coefficient of cancer regions outlined on MRI and the deformed histopathology (0.44 vs 0.48 vs 0.50), and a reduced mean per-case processing time (51 vs 11 vs 4.5 min). The improved performance by RAPHIA allows efficient processing of large datasets for the development of machine learning models for prostate cancer detection on MRI. Our code is publicly available at: https://github.com/pimed/RAPHIA.

Critical evaluation of artificial intelligence as a digital twin of pathologists for prostate cancer pathology

Prostate cancer pathology plays a crucial role in clinical management but is time-consuming. Artificial intelligence (AI) shows promise in detecting prostate cancer and grading patterns. We tested an AI-based digital twin of a pathologist, vPatho, on 2603 histological images of prostate tissue stained with hematoxylin and eosin. We analyzed various factors influencing tumor grade discordance between the vPatho system and six human pathologists. Our results demonstrated that vPatho achieved comparable performance in prostate cancer detection and tumor volume estimation, as reported in the literature. The concordance levels between vPatho and human pathologists were examined. Notably, moderate to substantial agreement was observed in identifying complementary histological features such as ductal, cribriform, nerve, blood vessel, and lymphocyte infiltration. However, concordance in tumor grading decreased when applied to prostatectomy specimens (κ = 0.44) compared to biopsy cores (κ = 0.70). Adjusting the decision threshold for the secondary Gleason pattern from 5 to 10% improved the concordance level between pathologists and vPatho for tumor grading on prostatectomy specimens (κ from 0.44 to 0.64). Potential causes of grade discordance included the vertical extent of tumors toward the prostate boundary and the proportions of slides with prostate cancer. Gleason pattern 4 was particularly associated with this population. Notably, the grade according to vPatho was not specific to any of the six pathologists involved in routine clinical grading. In conclusion, our study highlights the potential utility of AI in developing a digital twin for a pathologist. This approach can help uncover limitations in AI adoption and the practical application of the current grading system for prostate cancer pathology.

Prediction and Mapping of Intraprostatic Tumor Extent with Artificial Intelligence

Background

Magnetic resonance imaging (MRI) underestimation of prostate cancer extent complicates the definition of focal treatment margins.

Objective

To validate focal treatment margins produced by an artificial intelligence (AI) model.

Design setting and participants

Testing was conducted retrospectively in an independent dataset of 50 consecutive patients who had radical prostatectomy for intermediate-risk cancer. An AI deep learning model incorporated multimodal imaging and biopsy data to produce three-dimensional cancer estimation maps and margins. AI margins were compared with conventional MRI regions of interest (ROIs), 10-mm margins around ROIs, and hemigland margins. The AI model also furnished predictions of negative surgical margin probability, which were assessed for accuracy.

Outcome measurements and statistical analysis

Comparing AI with conventional margins, sensitivity was evaluated using Wilcoxon signed-rank tests and negative margin rates using chi-square tests. Predicted versus observed negative margin probability was assessed using linear regression. Clinically significant prostate cancer (International Society of Urological Pathology grade ≥2) delineated on whole-mount histopathology served as ground truth.

Results and limitations

The mean sensitivity for cancer-bearing voxels was higher for AI margins (97%) than for conventional ROIs (37%, p < 0.001), 10-mm ROI margins (93%, p = 0.24), and hemigland margins (94%, p < 0.001). For index lesions, AI margins were more often negative (90%) than conventional ROIs (0%, p < 0.001), 10-mm ROI margins (82%, p = 0.24), and hemigland margins (66%, p = 0.004). Predicted and observed negative margin probabilities were strongly correlated (R2 = 0.98, median error = 4%). Limitations include a validation dataset derived from a single institution's prostatectomy population.

Conclusions

The AI model was accurate and effective in an independent test set. This approach could improve and standardize treatment margin definition, potentially reducing cancer recurrence rates. Furthermore, an accurate assessment of negative margin probability could facilitate informed decision-making for patients and physicians.

Patient summary

Artificial intelligence was used to predict the extent of tumors in surgically removed prostate specimens. It predicted tumor margins more accurately than conventional methods.

The Association of Tissue Change and Treatment Success During High-intensity Focused Ultrasound Focal Therapy for Prostate Cancer

BACKGROUND

Tissue preservation strategies have been increasingly used for the management of localized prostate cancer. Focal ablation using ultrasound-guided high-intensity focused ultrasound (HIFU) has demonstrated promising short and medium-term oncological outcomes. Advancements in HIFU therapy such as the introduction of tissue change monitoring (TCM) aim to further improve treatment efficacy.

OBJECTIVE

To evaluate the association between intraoperative TCM during HIFU focal therapy for localized prostate cancer and oncological outcomes 12 mo afterward.

DESIGN, SETTING, AND PARTICIPANTS

Seventy consecutive men at a single institution with prostate cancer were prospectively enrolled. Men with prior treatment, metastases, or pelvic radiation were excluded to obtain a final cohort of 55 men.

INTERVENTION

All men underwent HIFU focal therapy followed by magnetic resonance (MR)-fusion biopsy 12 mo later. Tissue change was quantified intraoperatively by measuring the backscatter of ultrasound waves during ablation.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

Gleason grade group (GG) ≥2 cancer on postablation biopsy was the primary outcome. Secondary outcomes included GG ≥1 cancer, Prostate Imaging Reporting and Data System (PI-RADS) scores ≥3, and evidence of tissue destruction on post-treatment magnetic resonance imaging (MRI). A Student's t - test analysis was performed to evaluate the mean TCM scores and efficacy of ablation measured by histopathology. Multivariate logistic regression was also performed to identify the odds of residual cancer for each unit increase in the TCM score.

RESULTS AND LIMITATIONS

A lower mean TCM score within the region of the tumor (0.70 vs 0.97, p = 0.02) was associated with the presence of persistent GG ≥2 cancer after HIFU treatment. Adjusting for initial prostate-specific antigen, PI-RADS score, Gleason GG, positive cores, and age, each incremental increase of TCM was associated with an 89% reduction in the odds (odds ratio: 0.11, confidence interval: 0.01-0.97) of having residual GG ≥2 cancer on postablation biopsy. Men with higher mean TCM scores (0.99 vs 0.72, p = 0.02) at the time of treatment were less likely to have abnormal MRI (PI-RADS ≥3) at 12 mo postoperatively. Cases with high TCM scores also had greater tissue destruction measured on MRI and fewer visible lesions on postablation MRI.

CONCLUSIONS

Tissue change measured using TCM values during focal HIFU of the prostate was associated with histopathology and radiological outcomes 12 mo after the procedure.

PATIENT SUMMARY

In this report, we looked at how well ultrasound changes of the prostate during focal high-intensity focused ultrasound (HIFU) therapy for the treatment of prostate cancer predict patient outcomes. We found that greater tissue change measured by the HIFU device was associated with less residual cancer at 1 yr. This tool should be used to ensure optimal ablation of the cancer and may improve focal therapy outcomes in the future.

Correlation of 68Ga-RM2 PET with Postsurgery Histopathology Findings in Patients with Newly Diagnosed Intermediate- or High-Risk Prostate Cancer

⁶⁸Ga-RM2 targets gastrin-releasing peptide receptors (GRPRs), which are overexpressed in prostate cancer (PC). Here, we compared preoperative ⁶⁸Ga-RM2 PET to postsurgery histopathology in patients with newly diagnosed intermediate- or high-risk PC. Methods: Forty-one men, 64.0 ± 6.7 y old, were prospectively enrolled. PET images were acquired 42-72 min (median ± SD, 52.5 ± 6.5 min) after injection of 118.4-247.9 MBq (median ± SD, 138.0 ± 22.2 MBq) of ⁶⁸Ga-RM2. PET findings were compared with preoperative multiparametric MRI (mpMRI) (n = 36) and ⁶⁸Ga-PSMA11 PET (n = 17) and correlated to postprostatectomy whole-mount histopathology (n = 32) and time to biochemical recurrence. Nine participants decided to undergo radiation therapy after study enrollment. Results: All participants had intermediate- (n = 17) or high-risk (n = 24) PC and were scheduled for prostatectomy. Prostate-specific antigen was 8.8 ± 77.4 (range, 2.5-504) and 7.6 ± 5.3 ng/mL (range, 2.5-28.0 ng/mL) when participants who ultimately underwent radiation treatment were excluded. Preoperative ⁶⁸Ga-RM2 PET identified 70 intraprostatic foci of uptake in 40 of 41 patients. Postprostatectomy histopathology was available in 32 patients in which ⁶⁸Ga-RM2 PET identified 50 of 54 intraprostatic lesions (detection rate = 93%). ⁶⁸Ga-RM2 uptake was recorded in 19 nonenlarged pelvic lymph nodes in 6 patients. Pathology confirmed lymph node metastases in 16 lesions, and follow-up imaging confirmed nodal metastases in 2 lesions. ⁶⁸Ga-PSMA11 and ⁶⁸Ga-RM2 PET identified 27 and 26 intraprostatic lesions, respectively, and 5 pelvic lymph nodes each in 17 patients. Concordance between ⁶⁸Ga-RM2 and ⁶⁸Ga-PSMA11 PET was found in 18 prostatic lesions in 11 patients and 4 lymph nodes in 2 patients. Noncongruent findings were observed in 6 patients (intraprostatic lesions in 4 patients and nodal lesions in 2 patients). Sensitivity and accuracy rates for ⁶⁸Ga-RM2 and ⁶⁸Ga-PSMA11 (98% and 89% for ⁶⁸Ga-RM2 and 95% and 89% for ⁶⁸Ga-PSMA11) were higher than those for mpMRI (77% and 77%, respectively). Specificity was highest for mpMRI with 75% followed by ⁶⁸Ga-PSMA11 (67%) and ⁶⁸Ga-RM2 (65%). Conclusion: ⁶⁸Ga-RM2 PET accurately detects intermediate- and high-risk primary PC, with a detection rate of 93%. In addition, ⁶⁸Ga-RM2 PET showed significantly higher specificity and accuracy than mpMRI and a performance similar to ⁶⁸Ga-PSMA11 PET. These findings need to be confirmed in larger studies to identify which patients will benefit from one or the other or both radiopharmaceuticals.

Domain generalization for prostate segmentation in transrectal ultrasound images: A multi-center study

Prostate biopsy and image-guided treatment procedures are often performed under the guidance of ultrasound fused with magnetic resonance images (MRI). Accurate image fusion relies on accurate segmentation of the prostate on ultrasound images. Yet, the reduced signal-to-noise ratio and artifacts (e.g., speckle and shadowing) in ultrasound images limit the performance of automated prostate segmentation techniques and generalizing these methods to new image domains is inherently difficult. In this study, we address these challenges by introducing a novel 2.5D deep neural network for prostate segmentation on ultrasound images. Our approach addresses the limitations of transfer learning and finetuning methods (i.e., drop in performance on the original training data when the model weights are updated) by combining a supervised domain adaptation technique and a knowledge distillation loss. The knowledge distillation loss allows the preservation of previously learned knowledge and reduces the performance drop after model finetuning on new datasets. Furthermore, our approach relies on an attention module that considers model feature positioning information to improve the segmentation accuracy. We trained our model on 764 subjects from one institution and finetuned our model using only ten subjects from subsequent institutions. We analyzed the performance of our method on three large datasets encompassing 2067 subjects from three different institutions. Our method achieved an average Dice Similarity Coefficient (Dice) of 94.0±0.03 and Hausdorff Distance (HD95) of 2.28 mm in an independent set of subjects from the first institution. Moreover, our model generalized well in the studies from the other two institutions (Dice: 91.0±0.03; HD95: 3.7 mm and Dice: 82.0±0.03; HD95: 7.1 mm). We introduced an approach that successfully segmented the prostate on ultrasound images in a multi-center study, suggesting its clinical potential to facilitate the accurate fusion of ultrasound and MRI images to drive biopsy and image-guided treatments.

Evaluation of post-ablation mpMRI as a predictor of residual prostate cancer after focal high intensity focused ultrasound (HIFU) ablation

PURPOSE

To evaluate the performance of multiparametric magnetic resonance imaging (mpMRI) and PSA testing in follow-up after high intensity focused ultrasound (HIFU) focal therapy for localized prostate cancer.

METHODS

A total of 73 men with localized prostate cancer were prospectively enrolled and underwent focal HIFU followed by per-protocol PSA and mpMRI with systematic plus targeted biopsies at 12 months after treatment. We evaluated the association between post-treatment mpMRI and PSA with disease persistence on the post-ablation biopsy. We also assessed post-treatment functional and oncological outcomes.

RESULTS

Median age was 69 years (Interquartile Range (IQR): 66-74) and median PSA was 6.9 ng/dL (IQR: 5.3-9.9). Of 19 men with persistent GG ≥ 2 disease, 58% (11 men) had no visible lesions on MRI. In the 14 men with PIRADS 4 or 5 lesions, 7 (50%) had either no cancer or GG 1 cancer at biopsy. Men with false negative mpMRI findings had higher PSA density (0.16 vs. 0.07 ng/mL², P = 0.01). No change occurred in the mean Sexual Health Inventory for Men (SHIM) survey scores (17.0 at baseline vs. 17.7 post-treatment, P = 0.75) or International Prostate Symptom Score (IPSS) (8.1 at baseline vs. 7.7 at 24 months, P = 0.81) after treatment.

CONCLUSIONS

Persistent GG ≥ 2 cancer may occur after focal HIFU. mpMRI alone without confirmatory biopsy may be insufficient to rule out residual cancer, especially in patients with higher PSA density. Our study also validates previously published studies demonstrating preservation of urinary and sexual function after HIFU treatment.

Multi-institutional analysis of clinical and imaging risk factors for detecting clinically significant prostate cancer in men with PI-RADS 3 lesions

BACKGROUND

Most Prostate Imaging-Reporting and Data System (PI-RADS) 3 lesions do not contain clinically significant prostate cancer (CSPCa; grade group ≥2). This study was aimed at identifying clinical and magnetic resonance imaging (MRI)-derived risk fac- tors that predict CSPCa in men with PI-RADS 3 lesions.

METHODS

This study analyzed the detection of CSPCa in men who underwent MRI-targeted biopsy for PI-RADS 3 lesions. Multivariable logistic regression models with goodness-of-fit testing were used to identify variables associated with CSPCa. Receiver operating curves and decision curve analyses were used to estimate the clinical utility of a predictive model.

RESULTS

Of the 1784 men reviewed, 1537 were included in the training cohort, and 247 were included in the validation cohort. The 309 men with CSPCa (17.3%) were older, had a higher prostate-specific antigen (PSA) density, and had a greater likelihood of an anteriorly located lesion than men without CSPCa (p < .01). Multivariable analysis revealed that PSA density (odds ratio [OR], 1.36; 95% confidence interval [CI], 1.05-1.85; p < .01), age (OR, 1.05; 95% CI, 1.02-1.07; p < .01), and a biopsy-naive status (OR, 1.83; 95% CI, 1.38-2.44) were independently associated with CSPCa. A prior negative biopsy was negatively associated (OR, 0.35; 95% CI, 0.24-0.50; p < .01). The application of the model to the validation cohort resulted in an area under the curve of 0.78. A predicted risk threshold of 12% could have prevented 25% of biopsies while detecting almost 95% of CSPCas with a sensitivity of 94% and a specificity of 34%.

CONCLUSIONS

For PI-RADS 3 lesions, an elevated PSA density, older age, and a biopsy-naive status were associated with CSPCa, whereas a prior negative biopsy was negatively associated. A predictive model could prevent PI-RADS 3 biopsies while missing few CSPCas.

LAY SUMMARY

Among men with an equivocal lesion (Prostate Imaging-Reporting and Data System 3) on multiparametric magnetic resonance imaging (mpMRI), those who are older, those who have a higher prostate-specific antigen density, and those who have never had a biopsy before are at higher risk for having clinically significant prostate cancer (CSPCa) on subsequent biopsy. However, men with at least one negative biopsy have a lower risk of CSPCa. A new predictive model can greatly reduce the need to biopsy equivocal lesions noted on mpMRI while missing only a few cases of CSPCa.

Bridging the gap between prostate radiology and pathology through machine learning

Background

Prostate cancer remains the second deadliest cancer for American men despite clinical advancements. Currently, magnetic resonance imaging (MRI) is considered the most sensitive non‐invasive imaging modality that enables visualization, detection, and localization of prostate cancer, and is increasingly used to guide targeted biopsies for prostate cancer diagnosis. However, its utility remains limited due to high rates of false positives and false negatives as well as low inter‐reader agreements.

Purpose

Machine learning methods to detect and localize cancer on prostate MRI can help standardize radiologist interpretations. However, existing machine learning methods vary not only in model architecture, but also in the ground truth labeling strategies used for model training. We compare different labeling strategies and the effects they have on the performance of different machine learning models for prostate cancer detection on MRI.

Methods

Four different deep learning models (SPCNet, U‐Net, branched U‐Net, and DeepLabv3+) were trained to detect prostate cancer on MRI using 75 patients with radical prostatectomy, and evaluated using 40 patients with radical prostatectomy and 275 patients with targeted biopsy. Each deep learning model was trained with four different label types: pathology‐confirmed radiologist labels, pathologist labels on whole‐mount histopathology images, and lesion‐level and pixel‐level digital pathologist labels (previously validated deep learning algorithm on histopathology images to predict pixel‐level Gleason patterns) on whole‐mount histopathology images. The pathologist and digital pathologist labels (collectively referred to as pathology labels) were mapped onto pre‐operative MRI using an automated MRI‐histopathology registration platform.

Results

Radiologist labels missed cancers (ROC‐AUC: 0.75‐0.84), had lower lesion volumes (~68% of pathology lesions), and lower Dice overlaps (0.24‐0.28) when compared with pathology labels. Consequently, machine learning models trained with radiologist labels also showed inferior performance compared to models trained with pathology labels. Digital pathologist labels showed high concordance with pathologist labels of cancer (lesion ROC‐AUC: 0.97‐1, lesion Dice: 0.75‐0.93). Machine learning models trained with digital pathologist labels had the highest lesion detection rates in the radical prostatectomy cohort (aggressive lesion ROC‐AUC: 0.91‐0.94), and had generalizable and comparable performance to pathologist label‐trained‐models in the targeted biopsy cohort (aggressive lesion ROC‐AUC: 0.87‐0.88), irrespective of the deep learning architecture. Moreover, machine learning models trained with pixel‐level digital pathologist labels were able to selectively identify aggressive and indolent cancer components in mixed lesions on MRI, which is not possible with any human‐annotated label type.

Conclusions

Machine learning models for prostate MRI interpretation that are trained with digital pathologist labels showed higher or comparable performance with pathologist label‐trained models in both radical prostatectomy and targeted biopsy cohort. Digital pathologist labels can reduce challenges associated with human annotations, including labor, time, inter‐ and intra‐reader variability, and can help bridge the gap between prostate radiology and pathology by enabling the training of reliable machine learning models to detect and localize prostate cancer on MRI.

Image quality assessment for machine learning tasks using meta-reinforcement learning

In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a neural-network-based task predictor for image classification or segmentation, the performance of the task predictor provides an objective estimate of task amenability. In this work, we use an IQA controller to predict the task amenability which, itself being parameterised by neural networks, can be trained simultaneously with the task predictor. We further develop a meta-reinforcement learning framework to improve the adaptability for both IQA controllers and task predictors, such that they can be fine-tuned efficiently on new datasets or meta-tasks. We demonstrate the efficacy of the proposed task-specific, adaptable IQA approach, using two clinical applications for ultrasound-guided prostate intervention and pneumonia detection on X-ray images.

A review of artificial intelligence in prostate cancer detection on imaging

A multitude of studies have explored the role of artificial intelligence (AI) in providing diagnostic support to radiologists, pathologists, and urologists in prostate cancer detection, risk-stratification, and management. This review provides a comprehensive overview of relevant literature regarding the use of AI models in (1) detecting prostate cancer on radiology images (magnetic resonance and ultrasound imaging), (2) detecting prostate cancer on histopathology images of prostate biopsy tissue, and (3) assisting in supporting tasks for prostate cancer detection (prostate gland segmentation, MRI-histopathology registration, MRI-ultrasound registration). We discuss both the potential of these AI models to assist in the clinical workflow of prostate cancer diagnosis, as well as the current limitations including variability in training data sets, algorithms, and evaluation criteria. We also discuss ongoing challenges and what is needed to bridge the gap between academic research on AI for prostate cancer and commercial solutions that improve routine clinical care.

Optimization of a Thermal Flow Meter for Failure Management of the Shunt in Pediatric Hydrocephalus Patients. Annu Int Conf IEEE Eng Med Biol Soc 2021;2021:1551-1556. [PMID: 34891580 DOI: 10.1109/embc46164.2021.9630302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Hydrocephalus patients suffer from an abnormal buildup of cerebrospinal fluid (CSF) in their ventricles, and there is currently no known way to cure hydrocephalus. The most prevalent treatment for managing hydrocephalus is to implant a ventriculoperitoneal shunt, which diverts excess CSF out of the brain. However, shunts are prone to failure, resulting in vague symptoms. Our patient survey results found that the lack of specificity of symptoms complicates the management of hydrocephalus in the pediatric population. The consequences include persistent mental burden on caretakers and a significant amount of unnecessary utilization of emergency healthcare resources due to the false-positive judgement of shunt failure. In order to reliably monitor shunt failures for hydrocephalus patients and their caretakers, we propose an optimized design of the thermal flow meter for precise measurements of the CSF flow rate in the shunt. The design is an implantable device which slides onto the shunt and utilizes sinusoidal heating and temperature measurements to improve the signal-to-noise ratio of flow-rate measurements by orders of magnitude.Clinical Relevance- An implantable flow meter would be transformative to allow hydrocephalus patients to monitor their shunt function at home, resulting in reduced hospital visits, reduced exposure to radiation typically required to rule out shunt failure, and reduced caretaker anxiety.

The stanford prostate cancer calculator: Development and external validation of online nomograms incorporating PIRADS scores to predict clinically significant prostate cancer

BACKGROUND

While multiparametric MRI (mpMRI) has high sensitivity for detection of clinically significant prostate cancer (CSC), false positives and negatives remain common. Calculators that combine mpMRI with clinical variables can improve cancer risk assessment, while providing more accurate predictions for individual patients. We sought to create and externally validate nomograms incorporating Prostate Imaging Reporting and Data System (PIRADS) scores and clinical data to predict the presence of CSC in men of all biopsy backgrounds.

METHODS

Data from 2125 men undergoing mpMRI and MR fusion biopsy from 2014 to 2018 at Stanford, Yale, and UAB were prospectively collected. Clinical data included age, race, PSA, biopsy status, PIRADS scores, and prostate volume. A nomogram predicting detection of CSC on targeted or systematic biopsy was created.

RESULTS

Biopsy history, Prostate Specific Antigen (PSA) density, PIRADS score of 4 or 5, Caucasian race, and age were significant independent predictors. Our nomogram-the Stanford Prostate Cancer Calculator (SPCC)-combined these factors in a logistic regression to provide stronger predictive accuracy than PSA density or PIRADS alone. Validation of the SPCC using data from Yale and UAB yielded robust AUC values.

CONCLUSIONS

The SPCC combines pre-biopsy mpMRI with clinical data to more accurately predict the probability of CSC in men of all biopsy backgrounds. The SPCC demonstrates strong external generalizability with successful validation in two separate institutions. The calculator is available as a free web-based tool that can direct real-time clinical decision-making.

Utility of PSA Density in Predicting Upgraded Gleason Score in Men on Active Surveillance With Negative MRI

OBJECTIVES

To determine whether PSA density (PSAD), can sub-stratify risk of biopsy upgrade among men on active surveillance (AS) with normal baseline MRI.

METHODS

We identified a cohort of patients with low and favorable intermediate-risk prostate cancer on AS at two large academic centers from February 2013 - December 2017. Analysis was restricted to patients with GG1 cancer on initial biopsy and a negative baseline or surveillance mpMRI, defined by the absence of PI-RADS 2 or greater lesions. We assessed ability of PSA, prostate volume and PSAD to predict upgrading on confirmatory biopsy.

RESULTS

We identified 98 patients on AS with negative baseline or surveillance mpMRI. Median PSA at diagnosis was 5.8 ng/mL and median PSAD was 0.08 ng/mL/mL. Fourteen men (14.3%) experienced Gleason upgrade at confirmatory biopsy. Patients who were upgraded had higher PSA (7.9 vs 5.4 ng/mL, P = .04), PSAD (0.20 vs 0.07 ng/mL/mL, P < .001), and lower prostate volumes (42.5 vs 65.8 mL, P = .01). On multivariate analysis, PSAD was associated with pathologic upgrade (OR 2.23 per 0.1-increase, P = .007). A PSAD cutoff at 0.08 generated a NPV of 98% for detection of pathologic upgrade.

CONCLUSION

PSAD reliably discriminated the risk of Gleason upgrade at confirmatory biopsy among men with low-grade prostate cancer with negative MRI. PSAD could be clinically implemented to reduce the intensity of surveillance for a subset of patients.

Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging

PURPOSE

While multi-parametric magnetic resonance imaging (MRI) shows great promise in assisting with prostate cancer diagnosis and localization, subtle differences in appearance between cancer and normal tissue lead to many false positive and false negative interpretations by radiologists. We sought to automatically detect aggressive cancer (Gleason pattern ≥ 4) and indolent cancer (Gleason pattern 3) on a per-pixel basis on MRI to facilitate the targeting of aggressive cancer during biopsy.

METHODS

We created the Stanford Prostate Cancer Network (SPCNet), a convolutional neural network model, trained to distinguish between aggressive cancer, indolent cancer, and normal tissue on MRI. Ground truth cancer labels were obtained by registering MRI with whole-mount digital histopathology images from patients who underwent radical prostatectomy. Before registration, these histopathology images were automatically annotated to show Gleason patterns on a per-pixel basis. The model was trained on data from 78 patients who underwent radical prostatectomy and 24 patients without prostate cancer. The model was evaluated on a pixel and lesion level in 322 patients, including six patients with normal MRI and no cancer, 23 patients who underwent radical prostatectomy, and 293 patients who underwent biopsy. Moreover, we assessed the ability of our model to detect clinically significant cancer (lesions with an aggressive component) and compared it to the performance of radiologists.

RESULTS

Our model detected clinically significant lesions with an area under the receiver operator characteristics curve of 0.75 for radical prostatectomy patients and 0.80 for biopsy patients. Moreover, the model detected up to 18% of lesions missed by radiologists, and overall had a sensitivity and specificity that approached that of radiologists in detecting clinically significant cancer.

CONCLUSIONS

Our SPCNet model accurately detected aggressive prostate cancer. Its performance approached that of radiologists, and it helped identify lesions otherwise missed by radiologists. Our model has the potential to assist physicians in specifically targeting the aggressive component of prostate cancers during biopsy or focal treatment.

MR method for measuring microscopic histologic soft tissue textures

PURPOSE

Provide a direct, non-invasive diagnostic measure of microscopic tissue texture in the size scale between tens of microns and the much larger scale measurable by clinical imaging. This paper presents a method and data demonstrating the ability to measure these microscopic pathologic tissue textures (histology) in the presence of subject motion in an MR scanner. This size range is vital to diagnosing a wide range of diseases.

THEORY/METHODS

MR micro-Texture (MRµT) resolves these textures by a combination of measuring a targeted set of k-values to characterize texture-as in diffraction analysis of materials, performing a selective internal excitation to isolate a volume of interest (VOI), applying a high k-value phase encode to the excited spins in the VOI, and acquiring each individual k-value data point in a single excitation-providing motion immunity and extended acquisition time for maximizing signal-to-noise ratio. Additional k-value measurements from the same tissue can be made to characterize the tissue texture in the VOI-there is no need for these additional measurements to be spatially coherent as there is no image to be reconstructed. This method was applied to phantoms and tissue specimens including human prostate tissue.

RESULTS

Data demonstrating resolution <50 µm, motion immunity, and clearly differentiating between normal and cancerous tissue textures are presented.

CONCLUSION

The data reveal textural differences not resolvable by standard MR imaging. As MRµT is a pulse sequence, it is directly translatable to MRI scanners currently in clinical practice to meet the need for further improvement in cancer imaging.

ProsRegNet: A deep learning framework for registration of MRI and histopathology images of the prostate

Magnetic resonance imaging (MRI) is an increasingly important tool for the diagnosis and treatment of prostate cancer. However, interpretation of MRI suffers from high inter-observer variability across radiologists, thereby contributing to missed clinically significant cancers, overdiagnosed low-risk cancers, and frequent false positives. Interpretation of MRI could be greatly improved by providing radiologists with an answer key that clearly shows cancer locations on MRI. Registration of histopathology images from patients who had radical prostatectomy to pre-operative MRI allows such mapping of ground truth cancer labels onto MRI. However, traditional MRI-histopathology registration approaches are computationally expensive and require careful choices of the cost function and registration hyperparameters. This paper presents ProsRegNet, a deep learning-based pipeline to accelerate and simplify MRI-histopathology image registration in prostate cancer. Our pipeline consists of image preprocessing, estimation of affine and deformable transformations by deep neural networks, and mapping cancer labels from histopathology images onto MRI using estimated transformations. We trained our neural network using MR and histopathology images of 99 patients from our internal cohort (Cohort 1) and evaluated its performance using 53 patients from three different cohorts (an additional 12 from Cohort 1 and 41 from two public cohorts). Results show that our deep learning pipeline has achieved more accurate registration results and is at least 20 times faster than a state-of-the-art registration algorithm. This important advance will provide radiologists with highly accurate prostate MRI answer keys, thereby facilitating improvements in the detection of prostate cancer on MRI. Our code is freely available at https://github.com/pimed//ProsRegNet.

3D Registration of pre-surgical prostate MRI and histopathology images via super-resolution volume reconstruction

The use of MRI for prostate cancer diagnosis and treatment is increasing rapidly. However, identifying the presence and extent of cancer on MRI remains challenging, leading to high variability in detection even among expert radiologists. Improvement in cancer detection on MRI is essential to reducing this variability and maximizing the clinical utility of MRI. To date, such improvement has been limited by the lack of accurately labeled MRI datasets. Data from patients who underwent radical prostatectomy enables the spatial alignment of digitized histopathology images of the resected prostate with corresponding pre-surgical MRI. This alignment facilitates the delineation of detailed cancer labels on MRI via the projection of cancer from histopathology images onto MRI. We introduce a framework that performs 3D registration of whole-mount histopathology images to pre-surgical MRI in three steps. First, we developed a novel multi-image super-resolution generative adversarial network (miSRGAN), which learns information useful for 3D registration by producing a reconstructed 3D MRI. Second, we trained the network to learn information between histopathology slices to facilitate the application of 3D registration methods. Third, we registered the reconstructed 3D histopathology volumes to the reconstructed 3D MRI, mapping the extent of cancer from histopathology images onto MRI without the need for slice-to-slice correspondence. When compared to interpolation methods, our super-resolution reconstruction resulted in the highest PSNR relative to clinical 3D MRI (32.15 dB vs 30.16 dB for BSpline interpolation). Moreover, the registration of 3D volumes reconstructed via super-resolution for both MRI and histopathology images showed the best alignment of cancer regions when compared to (1) the state-of-the-art RAPSODI approach, (2) volumes that were not reconstructed, or (3) volumes that were reconstructed using nearest neighbor, linear, or BSpline interpolations. The improved 3D alignment of histopathology images and MRI facilitates the projection of accurate cancer labels on MRI, allowing for the development of improved MRI interpretation schemes and machine learning models to automatically detect cancer on MRI.

Registration of presurgical MRI and histopathology images from radical prostatectomy via RAPSODI

PURPOSE

Magnetic resonance imaging (MRI) has great potential to improve prostate cancer diagnosis; however, subtle differences between cancer and confounding conditions render prostate MRI interpretation challenging. The tissue collected from patients who undergo radical prostatectomy provides a unique opportunity to correlate histopathology images of the prostate with preoperative MRI to accurately map the extent of cancer from histopathology images onto MRI. We seek to develop an open-source, easy-to-use platform to align presurgical MRI and histopathology images of resected prostates in patients who underwent radical prostatectomy to create accurate cancer labels on MRI.

METHODS

Here, we introduce RAdiology Pathology Spatial Open-Source multi-Dimensional Integration (RAPSODI), the first open-source framework for the registration of radiology and pathology images. RAPSODI relies on three steps. First, it creates a three-dimensional (3D) reconstruction of the histopathology specimen as a digital representation of the tissue before gross sectioning. Second, RAPSODI registers corresponding histopathology and MRI slices. Third, the optimized transforms are applied to the cancer regions outlined on the histopathology images to project those labels onto the preoperative MRI.

RESULTS

We tested RAPSODI in a phantom study where we simulated various conditions, for example, tissue shrinkage during fixation. Our experiments showed that RAPSODI can reliably correct multiple artifacts. We also evaluated RAPSODI in 157 patients from three institutions that underwent radical prostatectomy and have very different pathology processing and scanning. RAPSODI was evaluated in 907 corresponding histpathology-MRI slices and achieved a Dice coefficient of 0.97 ± 0.01 for the prostate, a Hausdorff distance of 1.99 ± 0.70 mm for the prostate boundary, a urethra deviation of 3.09 ± 1.45 mm, and a landmark deviation of 2.80 ± 0.59 mm between registered histopathology images and MRI.

CONCLUSION

Our robust framework successfully mapped the extent of cancer from histopathology slices onto MRI providing labels from training machine learning methods to detect cancer on MRI.

Multicenter analysis of clinical and MRI characteristics associated with detecting clinically significant prostate cancer in PI-RADS (v2.0) category 3 lesions

OBJECTIVES

We sought to identify clinical and magnetic resonance imaging (MRI) characteristics in men with the Prostate Imaging - Reporting and Data System (PI-RADS) category 3 index lesions that predict clinically significant prostate cancer (CaP) on MRI targeted biopsy.

MATERIALS AND METHODS

Multicenter study of prospectively collected data for biopsy-naive men (n = 247) who underwent MRI-targeted and systematic biopsies for PI-RADS 3 index lesions. The primary endpoint was diagnosis of clinically significant CaP (Grade Group ≥2). Multivariable logistic regression models assessed for factors associated with clinically significant CaP. The probability distributions of clinically significant CaP based on different levels of predictors of multivariable models were plotted in a heatmap.

RESULTS

Men with clinically significant CaP had smaller prostate volume (39.20 vs. 55.10 ml, P < 0.001) and lower apparent diffusion coefficient (ADC) values (973 vs. 1068 μm²/s, P = 0.013), but higher prostate-specific antigen (PSA) density (0.21 vs. 0.13 ng/ml², P = 0.027). On multivariable analyses, lower prostate volume (odds ratio [OR]: 0.95, 95% confidence interval [CI]: 0.92-0.97), lower ADC value (OR: 0.99, 95% CI: 0.99-1.00), and Prostate-specific antigen density >0.15 ng/ml² (OR: 3.51, 95% CI 1.61-7.68) were independently associated with significant CaP.

CONCLUSION

Higher PSA density, lower prostate volume and ADC values are associated with clinically significant CaP in biopsy-naïve men with PI-RADS 3 lesions. We present regression-derived probabilities of detecting clinically significant CaP based on various clinical and imaging values that can be used in decision-making. Our findings demonstrate an opportunity for MRI refinement or biomarker discovery to improve risk stratification for PI-RADS 3 lesions.

Applying the PRECISION approach in biopsy naïve and previously negative prostate biopsy patients

OBJECTIVES

The PRECISION trial provides level 1 evidence supporting prebiopsy multiparametric magnetic resonance imaging (mpMRI) followed by targeted biopsy only when mpMRI is abnormal [1]. This approach reduced over-detection of low-grade cancer while increasing detection of clinically significant cancer (CSC). Still, important questions remain regarding the reproducibility of these findings outside of a clinical trial and quantifying missed CSC diagnoses using this approach. To address these issues, we retrospectively applied the PRECISION strategy in men who each underwent prebiopsy mpMRI followed by systematic and targeted biopsy.

METHODS AND MATERIALS

Clinical, imaging, and pathology data were prospectively collected from 358 biopsy naïve men and 202 men with previous negative biopsies. To apply the PRECISION approach, a retrospective analysis was done comparing the cancer yield from 2 diagnostic strategies: (1) mpMRI followed by targeted biopsy alone for men with Prostate Imaging Reporting and Data System ≥ 3 lesions and (2) systematic biopsy alone for all men. Primary outcomes were biopsies avoided and the proportion of CSC cancer (Grade Group 2-5) and non-CSC (Grade Group 1).

RESULTS

In biopsy naïve patients, the mpMRI diagnostic strategy would have avoided 19% of biopsies while detecting 2.5% more CSC (P= 0.480) and 12% less non-CSC (P< 0.001). Thirteen percent (n= 9) of men with normal mpMRI had CSC on systematic biopsy. For previous negative biopsy patients, the mpMRI diagnostic strategy avoided 21% of biopsies, while detecting 1.5% more CSC (P= 0.737) and 13% less non-CSC (P< 0.001). Seven percent (n= 3) of men with normal mpMRI had CSC on systematic biopsy.

CONCLUSIONS

Our results provide external validation of the PRECISION finding that mpMRI followed by targeted biopsy of suspicious lesions reduces biopsies and over-diagnosis of low-grade cancer. Unlike PRECISION, we did not find increased diagnosis of CSC. This was true in both biopsy naïve and previously negative biopsy cohorts. We have incorporated this information into shared decision making, which has led some men to choose to avoid biopsy. However, we continue to recommend targeted and systematic biopsy in men with abnormal MRI.

Teaching Urologists "How to Read Multi-Parametric Prostate MRIs Using PIRADSv2": Results of an iBook Pilot Study

OBJECTIVE

To create an online resource that teaches urologists how to interpret prostate multiparametric magnetic resonance imaging (mpMRI). As prostate mpMRI becomes widely adopted for cancer diagnosis and targeted biopsy, it is increasingly important that urologists are comfortable and experienced in assessing the images. The purpose of this study was to create an online mpMRI ibook and measure its effect on instilling proficiency among urology residents.

METHODS

We created a case-based ibook aimed at teaching clinicians how to identify and score prostate lesions on mpMRI using the Prostate Imaging-Reporting and Data System (PIRADS) v2. Residents completed a 43-question pretest before gaining access to the ibook for 1 month. The test asks participants to identify and score visible lesions using interactive mpMRI images. After a formal review of the material, they completed a post-test. Participants also rated their diagnostic confidence on a scale of 1-10 before and after reviewing the ibook. The change in performance and confidence scores for each resident was compared using Wilcoxon signed-rank test.

RESULTS

Eleven urology residents completed the pretest, review session and post-test. The mean test score rose from 37% (median 40%) to 57% (median 58%) after reviewing the ibook. Improvement was significant (P= .0039). Confidence scores also improved (P = .001).

CONCLUSION

We created an interactive ibook that teaches urologists how to evaluate prostate mpMRIs and demonstrated improved performance in interpretation among urology residents. This effective module can be incorporated into resident education on a national level and offered as a self-teaching resource for practicing urologists.

How Often is the Dynamic Contrast Enhanced Score Needed in PI-RADS Version 2?

BACKGROUND

Prostate imaging reporting and data system version 2 (PI-RADS v2) relegates dynamic contrast enhanced (DCE) imaging to a minor role. We sought to determine how often DCE is used in PI-RADS v2 scoring.

MATERIALS AND METHODS

We retrospectively reviewed data from 388 patients who underwent prostate magnetic resonance imaging and subsequent biopsy from January 2016 through December 2017. In accordance with PI-RADS v2, DCE was deemed necessary if a peripheral-zone lesion had a diffusion-weighted imaging score of 3, or if a transition-zone lesion had a T2 score of 3 and diffusion-weighted imaging experienced technical failure. Receiver operating characteristic curve analysis assessed the accuracy of prostate-specific antigen density (PSAD) at different threshold values for differentiating lesions that would be equivocal with noncontrast technique. Accuracy of PSAD was compared to DCE using McNemar's test.

RESULTS

Sixty-nine lesions in 62 patients (16%) required DCE for PI-RADS scoring. Biopsy of 10 (14%) of these lesions showed clinically significant cancer (Gleason score ≥7). In the subgroup of patients with equivocal lesions, those with clinically significant cancer had significantly higher PSADs than those with clinically insignificant lesions (means of 0.18 and 0.13 ng/mL/mL, respectively; P= 0.038). In this subgroup, there was no statistical difference in accuracy in determining clinically significant cancer between a PSAD threshold value of 0.13 and DCE (P= 0.25).

CONCLUSIONS

Only 16% of our patients needed DCE to generate the PI-RADS version 2 score, raising the possibility of limiting the initial screening prostate MRI to a noncontrast exam. PSAD may also be used to further decrease the need for or to replace DCE altogether.

GENERALIZABLE MULTI-SITE TRAINING AND TESTING OF DEEP NEURAL NETWORKS USING IMAGE NORMALIZATION

The ability of medical image analysis deep learning algorithms to generalize across multiple sites is critical for clinical adoption of these methods. Medical imging data, especially MRI, can have highly variable intensity characteristics across different individuals, scanners, and sites. However, it is not practical to train algorithms with data from all imaging equipment sources at all possible sites. Intensity normalization methods offer a potential solution for working with multi-site data. We evaluate five different image normalization methods on training a deep neural network to segment the prostate gland in MRI. Using 600 MRI prostate gland segmentations from two different sites, our results show that both intra-site and inter-site evaluation is critical for assessing the robustness of trained models and that training with single-site data produces models that fail to fully generalize across testing data from sites not included in the training.

Performance of multiparametric MRI appears better when measured in patients who undergo radical prostatectomy

Utilization of pre-biopsy multiparametric MRI (mpMRI) is increasing. To optimize the usefulness of mpMRI, physicians should accurately quote patients a numerical risk of cancer based on their MRI. The Prostate Imaging Reporting and Data System (PIRADS) standardizes interpretation of mpMRI; however, reported rates of clinically significant prostate cancer (CSC) stratified by PIRADS score vary widely. While some publications use radical prostatectomy (RP) specimens as gold standard, others use biopsy. We hypothesized that much of the variation in CSC stems from differences in cancer prevalence in RP cohorts (100% prevalence) vs biopsy cohorts. To quantify the impact of this selection bias on cancer yield according to PIRADS score, we analyzed data from 614 men with 854 lesions who underwent targeted biopsy from 2014 to 2018. Of these, 125 men underwent RP. We compared the PIRADS detection rates of CSC (Gleason ≥7) on targeted biopsy between the biopsy-only and RP cohorts. For all PIRADS scores, CSC yield was much greater in patients who underwent RP. For example, CSC was found in 30% of PIRADS 3 lesions in men who underwent RP vs 7.6% in men who underwent biopsy. Our results show that mpMRI performance appears to be better in men who undergo RP compared with those who only receive biopsy. Physicians should understand the effect of this selection bias and its magnitude when discussing mpMRI results with patients considering biopsy, and take great caution in quoting CSC yields from publications using RP as gold standard.

Gallium 68 PSMA-11 PET/MR Imaging in Patients with Intermediate- or High-Risk Prostate Cancer

Purpose To report the results of dual-time-point gallium 68 (⁶⁸Ga) prostate-specific membrane antigen (PSMA)-11 positron emission tomography (PET)/magnetic resonance (MR) imaging prior to prostatectomy in patients with intermediate- or high-risk cancer. Materials and Methods Thirty-three men who underwent conventional imaging as clinically indicated and who were scheduled for radical prostatectomy with pelvic lymph node dissection were recruited for this study. A mean dose of 4.1 mCi ± 0.7 (151.7 MBq ± 25.9) of ⁶⁸Ga-PSMA-11 was administered. Whole-body images were acquired starting 41-61 minutes after injection by using a GE SIGNA PET/MR imaging unit, followed by an additional pelvic PET/MR imaging acquisition at 87-125 minutes after injection. PET/MR imaging findings were compared with findings at multiparametric MR imaging (including diffusion-weighted imaging, T2-weighted imaging, and dynamic contrast material-enhanced imaging) and were correlated with results of final whole-mount pathologic examination and pelvic nodal dissection to yield sensitivity and specificity. Dual-time-point metabolic parameters (eg, maximum standardized uptake value [SUV_max]) were compared by using a paired t test and were correlated with clinical and histopathologic variables including prostate-specific antigen level, Gleason score, and tumor volume. Results Prostate cancer was seen at ⁶⁸Ga-PSMA-11 PET in all 33 patients, whereas multiparametric MR imaging depicted Prostate Imaging Reporting and Data System (PI-RADS) 4 or 5 lesions in 26 patients and PI-RADS 3 lesions in four patients. Focal uptake was seen in the pelvic lymph nodes in five patients. Pathologic examination confirmed prostate cancer in all patients, as well as nodal metastasis in three. All patients with normal pelvic nodes in PET/MR imaging had no metastases at pathologic examination. The accumulation of ⁶⁸Ga-PSMA-11 increased at later acquisition times, with higher mean SUV_max (15.3 vs 12.3, P < .001). One additional prostate cancer was identified only at delayed imaging. Conclusion This study found that ⁶⁸Ga-PSMA-11 PET can be used to identify prostate cancer, while MR imaging provides detailed anatomic guidance. Hence, ⁶⁸Ga-PSMA-11 PET/MR imaging provides valuable diagnostic information and may inform the need for and extent of pelvic node dissection.

Reduction of Muscle Contractions during Irreversible Electroporation Therapy Using High-Frequency Bursts of Alternating Polarity Pulses: A Laboratory Investigation in an Ex Vivo Swine Model

PURPOSE

To compare the intensity of muscle contractions in irreversible electroporation (IRE) treatments when traditional IRE and high-frequency IRE (H-FIRE) waveforms are used in combination with a single applicator and distal grounding pad (A+GP) configuration.

MATERIALS AND METHODS

An ex vivo in situ porcine model was used to compare muscle contractions induced by traditional monopolar IRE waveforms vs high-frequency bipolar IRE waveforms. Pulses with voltages between 200 and 5,000 V were investigated, and muscle contractions were recorded by using accelerometers placed on or near the applicators.

RESULTS

H-FIRE waveforms reduced the intensity of muscle contractions in comparison with traditional monopolar IRE pulses. A high-energy burst of 2-μs alternating-polarity pulses energized for 200 μs at 4,500 V produced less intense muscle contractions than traditional IRE pulses, which were 25-100 μs in duration at 3,000 V.

CONCLUSIONS

H-FIRE appears to be an effective technique to mitigate the muscle contractions associated with traditional IRE pulses. This may enable the use of voltages greater than 3,000 V necessary for the creation of large ablations in vivo.

Asymmetric Waveforms Decrease Lethal Thresholds in High Frequency Irreversible Electroporation Therapies

Irreversible electroporation (IRE) is a promising non-thermal treatment for inoperable tumors which uses short (50-100 μs) high voltage monopolar pulses to disrupt the membranes of cells within a well-defined volume. Challenges with IRE include complex treatment planning and the induction of intense muscle contractions. High frequency IRE (H-FIRE) uses bursts of ultrashort (0.25-5 μs) alternating polarity pulses to produce more predictable ablations and alleviate muscle contractions associated with IRE. However, H-FIRE generally ablates smaller volumes of tissue than IRE. This study shows that asymmetric H-FIRE waveforms can be used to create ablation volumes equivalent to standard IRE treatments. Lethal thresholds (LT) of 505 V/cm and 1316 V/cm were found for brain cancer cells when 100 μs IRE and 2 μs symmetric H-FIRE waveforms were used. In contrast, LT as low as 536 V/cm were found for 2 μs asymmetric H-FIRE waveforms. Reversible electroporation thresholds were 54% lower than LTs for symmetric waveforms and 33% lower for asymmetric waveforms indicating that waveform symmetry can be used to tune the relative sizes of reversible and irreversible ablation zones. Numerical simulations predicted that asymmetric H-FIRE waveforms are capable of producing ablation volumes which were 5.8-6.3x larger than symmetric H-FIRE waveforms indicating that in vivo investigation of asymmetric waveforms is warranted.

A novel device to preserve intestinal tissue ex-vivo by cold peristaltic perfusion

In the past two decades, much advancement has been made in the area of organ procurement and preservation for the transplant of kidneys, livers, and lungs. However, small intestine preservation remains unchanged. We propose a new preservation system for intestinal grafts that has the potential to increase the viability of the organ during transport. When experimented with porcine intestine, our device resulted in superior tissue quality than tissue in standard of care.

Haptic biofeedback for improving compliance with lower-extremity partial weight bearing

After lower-extremity orthopedic trauma and surgery, patients are often advised to restrict weight bearing on the affected limb. Conventional training methods are not effective at enabling patients to comply with recommendations for partial weight bearing. The current study assessed a novel method of using real-time haptic (vibratory/vibrotactile) biofeedback to improve compliance with instructions for partial weight bearing. Thirty healthy, asymptomatic participants were randomized into 1 of 3 groups: verbal instruction, bathroom scale training, and haptic biofeedback. Participants were instructed to restrict lower-extremity weight bearing in a walking boot with crutches to 25 lb, with an acceptable range of 15 to 35 lb. A custom weight bearing sensor and biofeedback system was attached to all participants, but only those in the haptic biofeedback group were given a vibrotactile signal if they exceeded the acceptable range. Weight bearing in all groups was measured with a separate validated commercial system. The verbal instruction group bore an average of 60.3±30.5 lb (mean±standard deviation). The bathroom scale group averaged 43.8±17.2 lb, whereas the haptic biofeedback group averaged 22.4±9.1 lb (P<.05). As a percentage of body weight, the verbal instruction group averaged 40.2±19.3%, the bathroom scale group averaged 32.5±16.9%, and the haptic biofeedback group averaged 14.5±6.3% (P<.05). In this initial evaluation of the use of haptic biofeedback to improve compliance with lower-extremity partial weight bearing, haptic biofeedback was superior to conventional physical therapy methods. Further studies in patients with clinical orthopedic trauma are warranted.

Fabrication of a thin-film capacitive force sensor array for tactile feedback in robotic surgery

Although surgical robotic systems provide several advantages over conventional minimally invasive techniques, they are limited by a lack of tactile feedback. Recent research efforts have successfully integrated tactile feedback components onto surgical robotic systems, and have shown significant improvement to surgical control during in vitro experiments. The primary barrier to the adoption of tactile feedback in clinical use is the unavailability of suitable force sensing technologies. This paper describes the design and fabrication of a thin-film capacitive force sensor array that is intended for integration with tactile feedback systems. This capacitive force sensing technology could provide precise, high-sensitivity, real-time responses to both static and dynamic loads. Capacitive force sensors were designed to operate with optimal sensitivity and dynamic range in the range of forces typical in minimally invasive surgery (0-40 N). Initial results validate the fabrication of these capacitive force-sensing arrays. We report 16.3 pF and 146 pF for 1-mm(2) and 9-mm(2) capacitive areas, respectively, whose values are within 3% of theoretical predictions.

The role of tactile feedback in grip force during laparoscopic training tasks

BACKGROUND

Laparoscopic minimally invasive surgery has revolutionized surgical care by reducing trauma to the patient, thereby decreasing the need for medication and shortening recovery times. During open procedures, surgeons can directly feel tissue characteristics. However, in laparoscopic surgery, tactile feedback during grip is attenuated and limited to the resistance felt in the tool handle. Excessive grip force during laparoscopic surgery can lead to tissue damage. Providing additional supplementary tactile feedback may allow subjects to have better control of grip force and identification of tissue characteristics, potentially decreasing the learning curve associated with complex minimally invasive techniques.

METHODS

A tactile feedback system has been developed and integrated into a modified laparoscopic grasper that allows forces applied at the grasper tips to be felt by the surgeon's hands. In this study, 15 subjects (11 novices, 4 experts) were asked to perform single-handed peg transfers using these laparoscopic graspers in three trials (feedback OFF, ON, OFF). Peak and average grip forces (newtons) during each grip event were measured and compared using a Wilcoxon ranked test in which each subject served as his or her own control.

RESULTS

After activating the tactile feedback system, the novice subject population showed significant decreases in grip force (p < 0.003). When the system was deactivated for the third trial, there were significant increases in grip force (p < 0.003). Expert subjects showed no significant improvements with the addition of tactile feedback (p > 0.05 in all cases).

CONCLUSION

Supplementary tactile feedback helped novice subjects reduce grip force during the laparoscopic training task but did not offer improvements for the four expert subjects. This indicates that tactile feedback may be beneficial for laparoscopic training but has limited long-term use in the nonrobotic setting.

Remote tactile sensing glove-based system

A complete glove-based master-slave tactile feedback system was developed to provide users with a remote sense of touch. The system features a force-sensing master glove with piezoresistive force sensors mounted at each finger tip, and a pressure-transmitting slave glove with silicone-based pneumatically controlled balloon actuators, mounted at each finger tip on another hand. A control system translates forces detected on the master glove, either worn by a user or mounted on a robotic hand, to discrete pressure levels at the fingers of another user. System tests demonstrated that users could accurately identify the correct finger and detect three simultaneous finger stimuli with 99.3% and 90.2% accuracy, respectively, when the subjects were located in separate rooms. The glove-based tactile feedback system may have application to virtual reality, rehabilitation, remote surgery, medical simulation, robotic assembly, and military robotics.

Characterization of a pneumatic balloon actuator for use in refreshable Braille displays

Many existing refreshable Braille display technologies are costly or lack robust performance. A process has been developed to fabricate consistent and reliable pneumatic balloon actuators at low material cost, using a novel manufacturing process. This technique has been adapted for use in refreshable Braille displays that feature low power consumption, ease of manufacture and small form factor. A prototype refreshable cell, conforming to American Braille standards, was developed and tested. The cell was fabricated from molded PDMS to form balloon actuators with a spin-coated silicone film, and fast pneumatic driving elements and an electronic control system were developed to drive the Braille dots. Perceptual testing was performed to determine the feasibility of the approach using a single blind human subject. The subject was able to detect randomized Braille letters rapidly generated by the actuator with 100% character detection accuracy.

A haptic feedback system for lower-limb prostheses

A haptic feedback system has been developed to provide sensory information to patients with lower-limb prostheses or peripheral neuropathy. Piezoresistive force sensors were mounted against four critical contact points of the foot to collect and relay force information to a system controller, which in turn drives four corresponding pneumatically controlled balloon actuators. The silicone-based balloon actuators were mounted on a cuff worn on the middle thigh, with skin contacts on the posterior, anterior, medial, and lateral surfaces of the thigh. Actuator characterization and human perceptual testing were performed to determine the effectiveness of the system in providing tactile stimuli. The actuators were determined to have a monotonic input pressure-vertical deflection response. Six normal subjects wearing the actuator cuff were able to differentiate inflation patterns, directional stimuli and discriminate between three force levels with 99.0%, 94.8%, and 94.4% accuracy, respectively. With force sensors attached to a shoe insole worn by an operator, subjects were able to correctly indicate the movements of the operator with 95.8% accuracy. These results suggest that the pneumatic haptic feedback system design is a viable method to provide sensory feedback for the lower limbs.

A prototype haptic feedback system for lower-limb prostheses and sensory neuropathy

Lower-limb sensory loss as a result of peripheral neuropathy or amputation results in sub-optimal movement and an increased incidence of injury. While the adoption of lower-limb prostheses and therapeutic footwear can reduce tissue injury and support movement, the fundamental problem of sensory loss continues to exist. A prototype haptic feedback system has been developed to aid in the recovery of lower-limb sensation due to these causes. Thin-film force sensors placed at the critical points for gait and balance functions collect essential force data, which is delivered to the user via pneumatically controlled balloon inflation. It is postulated that the use of this system will increase the tactile awareness of a patient's lower-limb or prosthesis, and when used in concert with modern rehabilitation techniques will create a method that will reduce the duration and improve the quality of lower-limb rehabilitation, especially in gait and balance functions.