Cost-Effectiveness Analysis Comparing Biopsy in Advance of Ablation with Concurrent Biopsy and Ablation for Small Renal Masses Measuring 1-3 cm.

PURPOSE: To analyze the cost effectiveness of performing a renal mass biopsy in advance of ablation or concurrently with a percutaneous ablation procedure for the management of small renal masses (SRMs). MATERIALS AND METHODS: A decision-analytic model was developed with a cohort of 65-year-old male patients with an incidental, unilateral 1-3 cm SRM. A decision tree modeled the first year of clinical intervention, after which patients entered a Markov model with a lifetime horizon. Patients were assumed to be treated in accordance with established clinical practice guidelines, including surveillance, repeat ablation for recurrence, and systemic therapy for metastasis. Healthcare cost and utility values were determined from published literature or local hospital estimates, discounted at 1.5%. Total lifetime costs were calculated from the perspective of a Canadian healthcare payer and converted to 2022 Canadian dollars (C$). The primary outcome was incremental cost-effectiveness ratio (ICER) at a willingness-to-pay threshold of C$50,000 per quality-adjusted life year (QALY) gained. The secondary outcome was ICER at a willingness-to-pay threshold of C$50,000 per life year (LY) gained. RESULTS: Concurrent biopsy and ablation resulted in a gain of 16.4 quality-adjusted days, at an incremental cost of $386, with an ICER of C$8,494/QALY. The concurrent strategy was the dominant strategy for a prevalence of benign mass of <5%. Sequential biopsy and ablation was only cost-effective when LYs were not quality-adjusted and ablation cost was >C$4,300 or benign mass prevalence was >28%. CONCLUSIONS: Concurrent biopsy and ablation is cost-effective relative to pretreatment diagnostic biopsy for management of incidental SRMs.

Complications After Renal Mass Biopsy: Frequency, Nature, Timing, and Associated Characteristics.

BACKGROUND. Observation periods after renal mass biopsy (RMB) range from 1 hour to overnight hospitalization. Short observation may improve efficiency by allowing use of the same recovery bed and other resources for RMBs in additional patients. OBJECTIVE. The purpose of this study was to evaluate the frequency, timing, and nature of complications after RMB, as well as to identify characteristics associated with such complications. METHODS. This retrospective study included 576 patients (mean age, 64.9 years; 345 men, 231 women) who underwent percutaneous ultrasound- or CT-guided RMB at one of three hospitals, performed by 22 radiologists, between January 1, 2008, and June 1, 2020. The EHR was reviewed to identify postbiopsy complications, which were classified as bleeding-related or non-bleeding-related and as acute (< 24 hours), subacute (24 hours to 30 days), or delayed (> 30 days). Deviations from normal clinical management (analgesia, unplanned laboratory testing, or additional imaging) were identified. RESULTS. Acute and subacute complications occurred after 3.6% (21/576) and 0.7% (4/576) of RMBs, respectively. No delayed complication or patient death occurred. A total of 76.2% (16/21) of acute complications were bleeding-related. A deviation from normal clinical management occurred after 1.6% (9/551) of RMBs that had no associated postbiopsy complication. Among the 16 patients with bleeding-related acute complications, all experienced a deviation, with mean time to deviation of 56 ± 47 (SD) minutes (range, 10-162 minutes; ≤ 120 minutes in 13/16 patients). The five non-bleeding-related acute complications all presented at the time of RMB completion. The four subacute complications occurred from 28 hours to 18 days after RMB. Patients with, versus those without, a bleeding-related complication had a lower platelet count (mean, 197.7 vs 250.4 × 109/L, p = .01) and greater frequency of entirely endophytic renal masses (47.4% vs 19.6%, p = .01). CONCLUSION. Complications after RMB were uncommon and presented either within 3 hours after biopsy or more than 24 hours after biopsy. CLINICAL IMPACT. A 3-hour monitoring window after RMB before patient discharge (in the absence of deviation from normal clinical management and complemented by informing patients of the low risk of a subacute complication) may provide both safe patient management and appropriate resource utilization.

Canadian Association of Radiologists Prostate MRI White Paper.

Prostate cancer is the most common malignancy and the third most common cause of death in Canadian men. In light of evolving diagnostic pathways for prostate cancer and the increased use of MRI, which now includes its use in men prior to biopsy, the Canadian Association of Radiologists established a Prostate MRI Working Group to produce a white paper to provide recommendations on establishing and maintaining a Prostate MRI Programme in the context of the Canadian healthcare system. The recommendations, which are based on available scientific evidence and/or expert consensus, are intended to maintain quality in image acquisition, interpretation, reporting and targeted biopsy to ensure optimal patient care. The paper covers technique, reporting, quality assurance and targeted biopsy considerations and includes appendices detailing suggested reporting templates, quality assessment tools and sample image acquisition protocols relevant to the Canadian healthcare context.

Percutaneous Ultrasound Gastrostomy: First-in-Human Experience with the PUMA-G System.

Percutaneous ultrasound gastrostomy (PUG) technique was developed to allow for gastrostomy tube insertion to be performed solely under ultrasound guidance without need for fluoroscopy or endoscopy. This report discusses the new device, proposed PUG technique, and the first-in-human experience. Five patients had PUG tube insertion performed as part of a Health Canada approved investigational study. All procedures were successful with no complications within 30 days postprocedure. Mean total procedure time was 50 ± 13 minutes. Two of 5 procedures required temporary fluoroscopy use to localize the orogastric balloon position within the stomach to achieve magnetic gastropexy.

Radiofrequency Ablation of T1a Renal Cell Carcinomas within Renal Transplant Allografts: Oncologic Outcomes and Graft Viability.

PURPOSE: To evaluate oncologic outcomes and graft viability after percutaneous radiofrequency (RF) ablation of renal cell carcinoma (RCC) developing within renal transplant allografts. MATERIALS AND METHODS: A single-institution, retrospective study reviewed all patients treated with RF ablation for RCC between February 2004 and May 2016. Ten patients were identified (age 49.6 y ± 12.6; 9 men, 1 woman) with 12 biopsy-confirmed RCC tumors within the allograft (all T1a, mean diameter 2.0 cm ± 0.7). Mean time from transplant to RCC diagnosis was 13.2 years ± 6.3. RF ablation was performed on an outpatient basis using conscious sedation. Procedural efficacy, complications, oncologic outcomes, and allograft function were evaluated. Statistical analysis with t tests and Pearson correlation compared allograft function before and after RF ablation and impact of proportional ablation size to allograft volume on function after ablation. RESULTS: Technical success rate and primary technique efficacy were 100% (12/12). No local or distant RCC progression was seen at mean follow-up of 54.3 months ± 38.7 (range, 9-136 months). Graft failure requiring hemodialysis or repeat transplantation occurred in 3 patients (26, 354, and 750 d after RF ablation), all of whom had glomerular filtration rate (GFR) < 30 mL/min/1.73 m2 before ablation. For all patients, mean GFR 6 months after RF ablation (35.8 mL/min/1.73 m2 ± 17.7) was not significantly different (P = .8) from preprocedure GFR (36.2 mL/min/1.73 m2 ± 14.3). Proportional volume of allograft that was ablated did not correlate with immediate or long-term GFR changes. One patient died of unrelated comorbidities 52 months after ablation. No major complications occurred. CONCLUSIONS: RF ablation of renal allograft RCC provided effective oncologic control without adverse impact on graft viability.

Accuracy Validation of an Automated Method for Prostate Segmentation in Magnetic Resonance Imaging.

Three dimensional (3D) manual segmentation of the prostate on magnetic resonance imaging (MRI) is a laborious and time-consuming task that is subject to inter-observer variability. In this study, we developed a fully automatic segmentation algorithm for T2-weighted endorectal prostate MRI and evaluated its accuracy within different regions of interest using a set of complementary error metrics. Our dataset contained 42 T2-weighted endorectal MRI from prostate cancer patients. The prostate was manually segmented by one observer on all of the images and by two other observers on a subset of 10 images. The algorithm first coarsely localizes the prostate in the image using a template matching technique. Then, it defines the prostate surface using learned shape and appearance information from a set of training images. To evaluate the algorithm, we assessed the error metric values in the context of measured inter-observer variability and compared performance to that of our previously published semi-automatic approach. The automatic algorithm needed an average execution time of ∼60 s to segment the prostate in 3D. When compared to a single-observer reference standard, the automatic algorithm has an average mean absolute distance of 2.8 mm, Dice similarity coefficient of 82%, recall of 82%, precision of 84%, and volume difference of 0.5 cm3 in the mid-gland. Concordant with other studies, accuracy was highest in the mid-gland and lower in the apex and base. Loss of accuracy with respect to the semi-automatic algorithm was less than the measured inter-observer variability in manual segmentation for the same task.

Evaluation of MRI-TRUS fusion versus cognitive registration accuracy for MRI-targeted, TRUS-guided prostate biopsy.

OBJECTIVE: The purpose of this article is to compare transrectal ultrasound (TRUS) biopsy accuracies of operators with different levels of prostate MRI experience using cognitive registration versus MRI-TRUS fusion to assess the preferred method of TRUS prostate biopsy for MRI-identified lesions. SUBJECTS AND METHODS; One hundred patients from a prospective prostate MRI-TRUS fusion biopsy study were reviewed to identify all patients with clinically significant prostate adenocarcinoma (PCA) detected on MRI-targeted biopsy. Twenty-five PCA tumors were incorporated into a validated TRUS prostate biopsy simulator. Three prostate biopsy experts, each with different levels of experience in prostate MRI and MRI-TRUS fusion biopsy, performed a total of 225 simulated targeted biopsies on the MRI lesions as well as regional biopsy targets. Simulated biopsies performed using cognitive registration with 2D TRUS and 3D TRUS were compared with biopsies performed under MRI-TRUS fusion. RESULTS: Two-dimensional and 3D TRUS sampled only 48% and 45% of clinically significant PCA MRI lesions, respectively, compared with 100% with MRI-TRUS fusion. Lesion sampling accuracy did not statistically significantly vary according to operator experience or tumor volume. MRI-TRUS fusion-naïve operators showed consistent errors in targeting of the apex, midgland, and anterior targets, suggesting that there is biased error in cognitive registration. The MRI-TRUS fusion expert correctly targeted the prostate apex; however, his midgland and anterior mistargeting was similar to that of the less-experienced operators. CONCLUSION: MRI-targeted TRUS-guided prostate biopsy using cognitive registration appears to be inferior to MRI-TRUS fusion, with fewer than 50% of clinically significant PCA lesions successfully sampled. No statistically significant difference in biopsy accuracy was seen according to operator experience with prostate MRI or MRI-TRUS fusion.

3D US-CT/MRI registration for percutaneous focal liver tumor ablations.

PURPOSE: US-guided percutaneous focal liver tumor ablations have been considered promising curative treatment techniques. To address cases with invisible or poorly visible tumors, registration of 3D US with CT or MRI is a critical step. By taking advantage of deep learning techniques to efficiently detect representative features in both modalities, we aim to develop a 3D US-CT/MRI registration approach for liver tumor ablations. METHODS: Facilitated by our nnUNet-based 3D US vessel segmentation approach, we propose a coarse-to-fine 3D US-CT/MRI image registration pipeline based on the liver vessel surface and centerlines. Then, phantom, healthy volunteer and patient studies are performed to demonstrate the effectiveness of our proposed registration approach. RESULTS: Our nnUNet-based vessel segmentation model achieved a Dice score of 0.69. In healthy volunteer study, 11 out of 12 3D US-MRI image pairs were successfully registered with an overall centerline distance of 4.03±2.68 mm. Two patient cases achieved target registration errors (TRE) of 4.16 mm and 5.22 mm. CONCLUSION: We proposed a coarse-to-fine 3D US-CT/MRI registration pipeline based on nnUNet vessel segmentation models. Experiments based on healthy volunteers and patient trials demonstrated the effectiveness of our registration workflow. Our code and example data are publicly available in this r epository.

3D US-Based Evaluation and Optimization of Tumor Coverage for US-Guided Percutaneous Liver Thermal Ablation.

Complete tumor coverage by the thermal ablation zone and with a safety margin (5 or 10 mm) is required to achieve the entire tumor eradication in liver tumor ablation procedures. However, 2D ultrasound (US) imaging has limitations in evaluating the tumor coverage by imaging only one or multiple planes, particularly for cases with multiple inserted applicators or irregular tumor shapes. In this paper, we evaluate the intra-procedural tumor coverage using 3D US imaging and investigate whether it can provide clinically needed information. Using data from 14 cases, we employed surface- and volume-based evaluation metrics to provide information on any uncovered tumor region. For cases with incomplete tumor coverage or uneven ablation margin distribution, we also proposed a novel margin uniformity -based approach to provide quantitative applicator adjustment information for optimization of tumor coverage. Both the surface- and volume-based metrics showed that 5 of 14 cases had incomplete tumor coverage according to the estimated ablation zone. After applying our proposed applicator adjustment approach, the simulated results showed that 92.9% (13 of 14) cases achieved 100% tumor coverage and the remaining case can benefit by increasing the ablation time or power. Our proposed method can evaluate the intra-procedural tumor coverage and intuitively provide applicator adjustment information for the physician. Our 3D US-based method is compatible with the constraints of conventional US-guided ablation procedures and can be easily integrated into the clinical workflow.

Effect of dataset size, image quality, and image type on deep learning-based automatic prostate segmentation in 3D ultrasound.

Three-dimensional (3D) transrectal ultrasound (TRUS) is utilized in prostate cancer diagnosis and treatment, necessitating time-consuming manual prostate segmentation. We have previously developed an automatic 3D prostate segmentation algorithm involving deep learning prediction on radially sampled 2D images followed by 3D reconstruction, trained on a large, clinically diverse dataset with variable image quality. As large clinical datasets are rare, widespread adoption of automatic segmentation could be facilitated with efficient 2D-based approaches and the development of an image quality grading method. The complete training dataset of 6761 2D images, resliced from 206 3D TRUS volumes acquired using end-fire and side-fire acquisition methods, was split to train two separate networks using either end-fire or side-fire images. Split datasets were reduced to 1000, 500, 250, and 100 2D images. For deep learning prediction, modified U-Net and U-Net++ architectures were implemented and compared using an unseen test dataset of 40 3D TRUS volumes. A 3D TRUS image quality grading scale with three factors (acquisition quality, artifact severity, and boundary visibility) was developed to assess the impact on segmentation performance. For the complete training dataset, U-Net and U-Net++ networks demonstrated equivalent performance, but when trained using split end-fire/side-fire datasets, U-Net++ significantly outperformed the U-Net. Compared to the complete training datasets, U-Net++ trained using reduced-size end-fire and side-fire datasets demonstrated equivalent performance down to 500 training images. For this dataset, image quality had no impact on segmentation performance for end-fire images but did have a significant effect for side-fire images, with boundary visibility having the largest impact. Our algorithm provided fast (<1.5 s) and accurate 3D segmentations across clinically diverse images, demonstrating generalizability and efficiency when employed on smaller datasets, supporting the potential for widespread use, even when data is scarce. The development of an image quality grading scale provides a quantitative tool for assessing segmentation performance.

Successful percutaneous transgastric diversion of a chronic post-operative combined pancreaticocutaneous and gastrocutaneous fistula using a snare-target technique: A case report.

INTRODUCTION: Gastrocutaneous fistula complicating a post-operative or post-pancreatitis pancreatic fistula is uncommon, but has a high mortality rate and typically occurs 6-9 weeks after initial drainage. Conventional methods of treatment may be limited by the size of the fistula tract and visibility. PRESENTATION OF CASE: A 57-year-old man presented with a pancreatic duct leak, ten days after undergoing a distal pancreatectomy for renal cell carcinoma metastasis. Initial drainage attempts resulted in a chronic pancreaticocutaneous fistula (PCF)1 complicated by a separate gastric fistula sharing the same cutaneous tract along the inserted drain as well as recurrent symptomatic pleural effusions requiring repeat hospitalizations for management. The chronic fistula tract was too small for conventional direct puncture under fluoroscopic or endoscopic ultrasound guidance; therefore, percutaneous transgastric diversion of the combined pancreatico-gastrocutaneous fistula using a snare-target approach was performed with complete resolution of clinical symptoms. DISCUSSION: Complicated pancreatico-gastrocutaneous fistulae are rare and typically require drainage, either surgically or via percutaneous direct transgastric puncture or endoscopic-ultrasound guided stent insertion. This case report demonstrates that a minimally-invasive percutaneous snare-target approach can be effective in treating complex fistulae too small to be accessed through these conventional methods. This case also demonstrates that transgastric drainage along the tract, remote from either organ's fistula origin, can successfully divert and resolve the complex fistula without requiring direct drainage of the pancreatic duct itself. CONCLUSION: Incorporating the snare-target technique facilitates accurate transgastric drain placement within chronic fistula, particularly when the fistula caliber is too small for conventional drainage methods.

Percutaneous ultrasound gastrostomy (PUG): first prospective clinical trial.

GRAPHICAL ABSTARCT: PURPOSE: To report the results of the first-in-human trial evaluating the safety and efficacy of the percutaneous ultrasound gastrostomy (PUG) technique. METHODS: A prospective, industry-sponsored single-arm clinical trial of PUG insertion was performed in 25 adult patients under investigational device exemption (mean age 64 ± 15 years, 92% men, 80% inpatients, mean BMI 24.5 ± 2.7 kg/m2). A propensity score-matched retrospective cohort of 25 patients who received percutaneous radiologic gastrostomy (PRG) was generated as an institutional control (mean age 66 ± 14 years, 92% men, 80% inpatients, mean BMI 24.0 ± 2.7 kg/m2). Primary outcomes included successful insertion and 30-day procedure-related adverse events (AE's). Secondary outcomes included procedural duration, sedation requirements, and hospital length of stay. RESULTS: All PUG procedures were successful, including 3/25 [12%] performed bedside within the ICU. There was no significant difference between PUG and PRG in rates of mild AE's (3/25 [12%] for PUG and 7/25 [28%] for PRG, p = 0.16) or moderate AE's (1/25 [4%] for PUG and 0/25 for PRG, p = 0.31). There were no severe AE's or 30-day procedure-related mortality in either group. Procedural room time was longer for PUG (56.5 ± 14.1 min) than PRG (39.3 ± 15.0 min, p < 0.001). PUG procedure time was significantly shorter after a procedural enhancement, the incorporation of a Gauss meter to facilitate successful magnetic gastropexy. Length of stay for outpatients did not significantly differ (2.4 ± 0.5 days for PUG and 2.6 ± 1.0 days for PRG, p = 0.70). CONCLUSION: PUG appears effective with a safety profile similar to PRG. Bedside point-of-care gastrostomy tube insertion using the PUG technique shows promise. TRIAL REGISTRATION NUMBER: ClinicalTrials.gov ID NCT03575754.

A multiobserver study investigating the effectiveness of prostatic multiparametric magnetic resonance imaging to dose escalate corresponding histologic lesions using high-dose-rate brachytherapy.

PURPOSE: Using multiparametric MRI data and the pathologic data from radical prostatectomy specimens, we simulated the treatment planning of dose-escalated high-dose-rate brachytherapy (HDR-BT) to the Multiparametric MRI dominant intraprostatic lesion (mpMRI-DIL) to compare the dose potentially delivered to the pathologically confirmed locations of the high-grade component of the cancer. METHODS AND MATERIALS: Pathologist-annotated prostatectomy midgland histology sections from 12 patients were registered to preprostatectomy mpMRI scans that were interpreted by four radiologists. To simulate realistic HDR-BT, we registered each observer's mpMRI-DILs and corresponding histology to two transrectal ultrasound images of other HDR-BT patients with a 15-Gy whole-gland prescription. We used clinical inverse planning to escalate the mpMRI-DILs to 20.25 Gy. We compared the dose that the histopathology would have received if treated with standard treatment plans to the dose mpMRI-targeting would have achieved. The histopathology was grouped as high-grade cancer (any Gleason Grade 4 or 5) and low-grade cancer (only Gleason Grade 3). RESULTS: 212 mpMRI-targeted HDR-BT plans were analyzed. For high-grade histology, the mpMRI-targeted plans achieved significantly higher median [IQR] D98 and D90 values of 18.2 [16.7-19.5] Gy and 19.4 [17.8-20.9] Gy, respectively, in comparison with the standard plans (p = 0.01 and p = 0.003). For low-grade histology, the targeted treatment plans would have resulted in a significantly higher median D90 of 17.0 [16.1-18.4] Gy in comparison with standard plans (p = 0.015); the median D98 was not significantly higher (p = 0.2). CONCLUSIONS: In this retrospective pilot study of 12 patients, mpMRI-based dose escalation led to increased dose to high-grade, but not low-grade, cancer. In our data set, different observers and mpMRI sequences had no substantial effect on dose to histologic cancer.

Repeat prostate biopsy accuracy: simulator-based comparison of two- and three-dimensional transrectal US modalities.

PURPOSE: To compare the accuracy of biopsy with two-dimensional (2D) transrectal ultrasonography (US) with that of biopsy with conventional three-dimensional (3D) transrectal US and biopsy with guided 3D transrectal US in the guidance of repeat prostate biopsy procedures in a prostate biopsy simulator. MATERIALS AND METHODS: The institutional review board approved this retrospective study. Five residents and five experts performed repeat biopsies with a biopsy simulator that contained the transrectal US prostate images of 10 patients who had undergone biopsy. Simulated repeat biopsies were performed with 2D transrectal US, conventional 3D transrectal US, and guided 3D transrectal US (an extension of 3D transrectal US that enables active display of biopsy targets). The modalities were compared on the basis of time per biopsy and how accurately simulated repeat biopsies could be guided to specific targets. The probability for successful biopsy of a repeat target was calculated for each modality. RESULTS: Guided 3D transrectal US was significantly (P < .01) more accurate for simulated biopsy of repeat targets than was 2D or 3D transrectal US, with a biopsy accuracy of 0.86 mm +/- 0.47 (standard deviation), 3.68 mm +/- 2.60, and 3.60 mm +/- 2.57, respectively. Experts had a 70% probability of sampling a prior biopsy target volume of 0.5 cm(3) with 2D transrectal US; however, the probability approached 100% with guided 3D transrectal US. Biopsy accuracy was not significantly different between experts and residents for any modality; however, experts were significantly (P < .05) faster than residents with each modality. CONCLUSION: Repeat biopsy of the prostate with 2D transrectal US has limited accuracy. Compared with 2D transrectal US, the biopsy accuracy of both experts and residents improved with guided 3D transrectal US but did not improve with conventional 3D transrectal US.

Temporal-based needle segmentation algorithm for transrectal ultrasound prostate biopsy procedures.

PURPOSE: Automatic identification of the biopsy-core tissue location during a prostate biopsy procedure would provide verification that targets were adequately sampled and would allow for appropriate intraprocedure biopsy target modification. Localization of the biopsy core requires accurate segmentation of the biopsy needle and needle tip from transrectal ultrasound (TRUS) biopsy images. A temporal-based TRUS needle segmentation algorithm was developed specifically for the prostate biopsy procedure to automatically identify the TRUS image containing the biopsy needle from a collection of 2D TRUS images and to segment the biopsy-core location from the 2D TRUS image. METHODS: The temporal-based segmentation algorithm performs a temporal analysis on a series of biopsy TRUS images collected throughout needle insertion and withdrawal. Following the identification of points of needle insertion and retraction, the needle axis is segmented using a Hough transform-based algorithm, which is followed by a temporospectral TRUS analysis to identify the biopsy-needle tip. Validation of the temporal-based algorithm is performed on 108 TRUS biopsy sequences collected from the procedures of ten patients. The success of the temporal search to identify the proper images was manually assessed, while the accuracies of the needle-axis and needle-tip segmentations were quantitatively compared to implementations of two other needle segmentation algorithms within the literature. RESULTS: The needle segmentation algorithm demonstrated a >99% accuracy in identifying the TRUS image at the moment of needle insertion from the collection of real-time TRUS images throughout the insertion and withdrawal of the biopsy needle. The segmented biopsy-needle axes were accurate to within 2.3 +/- 2.0 degrees and 0.48 +/- 0.42 mm of the gold standard. Identification of the needle tip to within half of the biopsy-core length (<10 mm) was 95% successful with a mean error of 2.4 +/- 4.0 mm. Needle-tip detection using the temporal-based algorithm was significantly more accurate (p < 0.001) than the other two algorithms tested, while the segmentation of the needle axis was not significantly different between the three algorithms. CONCLUSIONS: The temporal-based needle segmentation algorithm accurately segments the location of the biopsy core from 2D TRUS images of clinical prostate biopsy procedures. The results for needle-tip localization demonstrated that the temporal-based algorithm is significantly more accurate than implementations of some existing needle segmentation algorithms within the literature.

Deep learning segmentation of general interventional tools in two-dimensional ultrasound images.

PURPOSE: Many interventional procedures require the precise placement of needles or therapy applicators (tools) to correctly achieve planned targets for optimal diagnosis or treatment of cancer, typically leveraging the temporal resolution of ultrasound (US) to provide real-time feedback. Identifying tools in two-dimensional (2D) images can often be time-consuming with the precise position difficult to distinguish. We have developed and implemented a deep learning method to segment tools in 2D US images in near real-time for multiple anatomical sites, despite the widely varying appearances across interventional applications. METHODS: A U-Net architecture with a Dice similarity coefficient (DSC) loss function was used to perform segmentation on input images resized to 256 × 256 pixels. The U-Net was modified by adding 50% dropouts and the use of transpose convolutions in the decoder section of the network. The proposed approach was trained with 917 images and manual segmentations from prostate/gynecologic brachytherapy, liver ablation, and kidney biopsy/ablation procedures, as well as phantom experiments. Real-time data augmentation was applied to improve generalizability and doubled the dataset for each epoch. Postprocessing to identify the tool tip and trajectory was performed using two different approaches, comparing the largest island with a linear fit to random sample consensus (RANSAC) fitting. RESULTS: Comparing predictions from 315 unseen test images to manual segmentations, the overall median [first quartile, third quartile] tip error, angular error, and DSC were 3.5 [1.3, 13.5] mm, 0.8 [0.3, 1.7]°, and 73.3 [56.2, 82.3]%, respectively, following RANSAC postprocessing. The predictions with the lowest median tip and angular errors were observed in the gynecologic images (median tip error: 0.3 mm; median angular error: 0.4°) with the highest errors in the kidney images (median tip error: 10.1 mm; median angular error: 2.9°). The performance on the kidney images was likely due to a reduction in acoustic signal associated with oblique insertions relative to the US probe and the increased number of anatomical interfaces with similar echogenicity. Unprocessed segmentations were performed with a mean time of approximately 50 ms per image. CONCLUSIONS: We have demonstrated that our proposed approach can accurately segment tools in 2D US images from multiple anatomical locations and a variety of clinical interventional procedures in near real-time, providing the potential to improve image guidance during a broad range of diagnostic and therapeutic cancer interventions.

Three-dimensional therapy needle applicator segmentation for ultrasound-guided focal liver ablation.

PURPOSE: Minimally invasive procedures, such as microwave ablation, are becoming first-line treatment options for early-stage liver cancer due to lower complication rates and shorter recovery times than conventional surgical techniques. Although these procedures are promising, one reason preventing widespread adoption is inadequate local tumor ablation leading to observations of higher local cancer recurrence compared to conventional procedures. Poor ablation coverage has been associated with two-dimensional (2D) ultrasound (US) guidance of the therapy needle applicators and has stimulated investigation into the use of three-dimensional (3D) US imaging for these procedures. We have developed a supervised 3D US needle applicator segmentation algorithm using a single user input to augment the addition of 3D US to the current focal liver tumor ablation workflow with the goals of identifying and improving needle applicator localization efficiency. METHODS: The algorithm is initialized by creating a spherical search space of line segments around a manually chosen seed point that is selected by a user on the needle applicator visualized in a 3D US image. The most probable trajectory is chosen by maximizing the count and intensity of threshold voxels along a line segment and is filtered using the Otsu method to determine the tip location. Homogeneous tissue mimicking phantom images containing needle applicators were used to optimize the parameters of the algorithm prior to a four-user investigation on retrospective 3D US images of patients who underwent microwave ablation for liver cancer. Trajectory, axis localization, and tip errors were computed based on comparisons to manual segmentations in 3D US images. RESULTS: Segmentation of needle applicators in ten phantom 3D US images was optimized to median (Q1, Q3) trajectory, axis, and tip errors of 2.1 (1.1, 3.6)°, 1.3 (0.8, 2.1) mm, and 1.3 (0.7, 2.5) mm, respectively, with a mean ± SD segmentation computation time of 0.246 ± 0.007 s. Use of the segmentation method with a 16 in vivo 3D US patient dataset resulted in median (Q1, Q3) trajectory, axis, and tip errors of 4.5 (2.4, 5.2)°, 1.9 (1.7, 2.1) mm, and 5.1 (2.2, 5.9) mm based on all users. CONCLUSIONS: Segmentation of needle applicators in 3D US images during minimally invasive liver cancer therapeutic procedures could provide a utility that enables enhanced needle applicator guidance, placement verification, and improved clinical workflow. A semi-automated 3D US needle applicator segmentation algorithm used in vivo demonstrated localization of the visualized trajectory and tip with less than 5° and 5.2 mm errors, respectively, in less than 0.31 s. This offers the ability to assess and adjust needle applicator placements intraoperatively to potentially decrease the observed liver cancer recurrence rates associated with current ablation procedures. Although optimized for deep and oblique angle needle applicator insertions, this proposed workflow has the potential to be altered for a variety of image-guided minimally invasive procedures to improve localization and verification of therapy needle applicators intraoperatively.

A comparison of prostate tumor targeting strategies using magnetic resonance imaging-targeted, transrectal ultrasound-guided fusion biopsy.

PURPOSE: Magnetic resonance imaging (MRI)-targeted, three-dimensional (3D) transrectal ultrasound (TRUS)-guided prostate biopsy aims to reduce the 21-47% false-negative rate of clinical two-dimensional (2D) TRUS-guided systematic biopsy, but continues to yield false-negative results. This may be improved via needle target optimization, accounting for guidance system errors and image registration errors. As an initial step toward the goal of optimized prostate biopsy targeting, we investigated how needle delivery error impacts tumor sampling probability for two targeting strategies. METHODS: We obtained MRI and 3D TRUS images from 49 patients. A radiologist and radiology resident assessed these MR images and contoured 81 suspicious regions, yielding tumor surfaces that were registered to 3D TRUS. The biopsy system's root-mean-squared needle delivery error (RMSE) and systematic error were modeled using an isotropic 3D Gaussian distribution. We investigated two different prostate tumor-targeting strategies using (a) the tumor's centroid and (b) a ring in the lateral-elevational plane. For each simulation, targets were spaced at equal arc lengths on a ring with radius equal to the systematic error magnitude. A total of 1000 biopsy simulations were conducted for each tumor, with RMSE and systematic error magnitudes ranging from 1 to 6 mm. The difference in median tumor sampling probability and probability of obtaining a 50% core involvement was determined for ring vs centroid targeting. RESULTS: Our simulation results indicate that ring targeting outperformed centroid targeting in situations where systematic error exceeds RMSE. In these instances, we observed statistically significant differences showing 1-32% improvement in sampling probability due to ring targeting. Likewise, we observed statistically significant differences showing 1-39% improvement in 50% core involvement probability due to ring targeting. CONCLUSIONS: Our results suggest that the optimal targeting scheme for prostate biopsy depends on the relative levels of systematic and random errors in the system. Where systematic error dominates, a ring-targeting scheme may yield improved probability of tumor sampling. The findings presented in this paper may be used to aid in target selection strategies for clinicians performing targeted prostate biopsies on any MRI targeted, 3D TRUS-guided biopsy system and could support earlier diagnosis of prostate cancer while it remains localized to the gland and curable.