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

PURPOSE: To analyze the cost-effectiveness of performing a renal mass biopsy in advance of ablation or concurrent with a percutaneous ablation procedure for the management of small renal masses (SRMs). METHODS: A decision-analytic model was developed with a cohort of 65-year-old male patients with an incidental, unilateral 1 to 3 cm SRM. A decision tree modeled the first year of clinical intervention, following which patients entered a Markov Model with a lifetime horizon. Patients were assumed to be treated in accordance to 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 health-care payer and converted to 2022 Canadian dollars. The primary outcome was incremental cost effectiveness ratio (ICER), at a willingness-to-pay threshold of $50,000 per quality-adjusted life-years gained. The secondary outcome was ICER at a willingness-to-pay threshold of 50,000 $/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 8494 $/QALY. The concurrent strategy was the dominant for prevalence of benign mass below 5%. Sequential biopsy and ablation was only cost effective when life-years were not quality-adjusted, and ablation cost was greater than $4300 or benign mass prevalence was greater than 28%. CONCLUSION: Concurrent biopsy and ablation is cost-effective relative to pre-treatment diagnostic biopsy for management of incidental small renal masses.

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.

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.

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.

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.

Targeting prostate lesions on multiparametric MRI with HDR brachytherapy: Optimal planning margins determined using whole-mount digital histology.

PURPOSE: Multiparametric magnetic resonance imaging (mpMRI) has demonstrated the ability to localize intraprostatic lesions. It is our goal to determine how to optimally target the underlying histopathological cancer within the setting of high-dose-rate brachytherapy (HDR-BT). METHODS AND MATERIALS: Ten prostatectomy patients had pathologist-annotated mid-gland histology registered to pre-procedural mpMRI, which were interpreted by four different observers. Simulated HDR-BT plans with realistic catheter placements were generated by registering the mpMRI lesions and corresponding histology annotations to previously performed clinical HDR-BT implants. Inverse treatment planning was used to generate treatment plans that treated the entire gland to a single dose of 15 Gy, as well as focally targeted plans that aimed to escalate dose to the mpMRI lesions to 20.25 Gy. Three margins to the lesion were explored: 0 mm, 1 mm, and 2 mm. The analysis compared the dose that would have been delivered to the corresponding histologically-defined cancer with the different treatment planning techniques. RESULTS: mpMRI-targeted plans delivered a significantly higher dose to the histologically-defined cancer (p < 0.001), in comparison to the standard treatment plans. Additionally, adding a 1 mm margin resulted in significantly higher D98, and D90 to the histologically-defined cancer in comparison to the 0 mm margin targeted plans (p = 0.019 & p = 0.0026). There was no significant difference between plans using 1 mm and 2 mm margins. CONCLUSIONS: Adding a 1 mm margin to intraprostatic mpMRI lesions significantly increased the dose to histologically-defined cancer, in comparison applying no margin. No significant effect was observed by further expanding the margins.

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.

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.

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.

Multiple objective planning for thermal ablation of liver tumors.

PURPOSE: Preoperative treatment planning is key to ensure successful thermal ablation of liver tumors. The planning aims to minimize the number of electrodes required for complete ablation and the damage to the surrounding tissues while satisfying multiple clinical constraints. This is a challenging multiple objective planning problem, in which the trade-off between different objectives must be considered. METHODS: We propose a novel method to solve the multiple objective planning problem, which combines the set cover-based model and Pareto optimization. The set cover-based model considers multiple clinical constraints and generates several clinically feasible treatment plans, among which the Pareto optimization is performed to find the trade-off between different objectives. RESULTS: We evaluated the proposed method on 20 tumors of 11 patients in two different situations used in common thermal ablation approaches: with and without the pull-back technique. Pareto optimal plans were found and verified to be clinically acceptable in all cases, which can find the trade-off between the number of electrodes and the damage to the surrounding tissues. CONCLUSION: The proposed method performs well in the two different situations we considered: with or without the pull-back technique. It can generate Pareto optimal plans satisfying multiple clinical constraints. These plans consider the trade-off between different planning objectives.

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.

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.

Automatic Radiofrequency Ablation Planning for Liver Tumors With Multiple Constraints Based on Set Covering.

Radiofrequency ablation (RFA) is now a widely used minimally invasive treatment method for hepatic tumors. Preoperative planning plays a vital role in RFA therapy. With increasing tumor size, multiple overlapping ablations are needed, which are challenging to optimize while considering clinical constraints. In this paper, we present a new automatic RFA planning method. First, a 2-steps set cover-based model is formulated, which can integrate multiple clinical constraints for optimization of overlapping ablations. To ensure that the planning model can be solved in a reasonable time, a search space reducing strategy is then proposed. We also developed an algorithm for automatic RFA electrode selection, which provides a proper electrode ablation zone for the planning model. The proposed method was evaluated with 20 tumors of varying sizes (0.92 cm3 to 28.4 cm3). Results showed that the proposed method can generate clinical feasible RFA plans with a minimum number of RFA electrodes and ablations, complete tumor coverage and minimized ablation of normal tissue.

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.

Prostate lesion delineation from multiparametric magnetic resonance imaging based on locality alignment discriminant analysis.

PURPOSE: Multiparametric MRI (mpMRI) has shown promise in the detection and localization of prostate cancer foci. Although techniques have been previously introduced to delineate lesions from mpMRI, these techniques were evaluated in datasets with T2 maps available. The generation of T2 map is not included in the clinical prostate mpMRI consensus guidelines; the acquisition of which requires repeated T2-weighted (T2W) scans and would significantly lengthen the scan time currently required for the clinically recommended acquisition protocol, which includes T2W, diffusion-weighted (DW), and dynamic contrast-enhanced (DCE) imaging. The goal of this study is to develop and evaluate an algorithm that provides pixel-accurate lesion delineation from images acquired based on the clinical protocol. METHODS: Twenty-five pixel-based features were extracted from the T2-weighted (T2W), apparent diffusion coefficient (ADC), and dynamic contrast-enhanced (DCE) images. The pixel-wise classification was performed on the reduced space generated by locality alignment discriminant analysis (LADA), a version of linear discriminant analysis (LDA) localized to patches in the feature space. Postprocessing procedures, including the removal of isolated points identified and filling of holes inside detected regions, were performed to improve delineation accuracy. The segmentation result was evaluated against the lesions manually delineated by four expert observers according to the Prostate Imaging-Reporting and Data System (PI-RADS) detection guideline. RESULTS: The LADA-based classifier (60 ± 11%) achieved a higher sensitivity than the LDA-based classifier (51 ± 10%), thereby demonstrating, for the first time, that higher classification performance was attained on the reduced space generated by LADA than by LDA. Further sensitivity improvement (75 ± 14%) was obtained after postprocessing, approaching the sensitivities attained by previous mpMRI lesion delineation studies in which nonclinical T2 maps were available. CONCLUSION: The proposed algorithm delineated lesions accurately and efficiently from images acquired following the clinical protocol. The development of this framework may potentially accelerate the clinical uses of mpMRI in prostate cancer diagnosis and treatment planning.

A self-tuned graph-based framework for localization and grading prostate cancer lesions: An initial evaluation based on multiparametric magnetic resonance imaging.

Multiparametric magnetic resonance imaging (mpMRI) has been established as the state-of-the-art examination for the detection and localization of prostate cancer lesions. Prostate Imaging-Reporting and Data System (PI-RADS) has been established as a scheme to standardize the reporting of mpMRI findings. Although lesion delineation and PI-RADS ratings could be performed manually, human delineation and ratings are subjective and time-consuming. In this article, we developed and validated a self-tuned graph-based model for PI-RADS rating prediction. 34 features were obtained at the pixel level from T2-weighted (T2W), apparent diffusion coefficient (ADC) and dynamic contrast enhanced (DCE) images, from which PI-RADS scores were predicted. Two major innovations were involved in this self-tuned graph-based model. First, graph-based approaches are sensitive to the choice of the edge weight. The proposed model tuned the edge weights automatically based on the structure of the data, thereby obviating empirical edge weight selection. Second, the feature weights were tuned automatically to give heavier weights to features important for PI-RADS rating estimation. The proposed framework was evaluated for its lesion localization performance in mpMRI datasets of 12 patients. In the evaluation, the PI-RADS score distribution map generated by the algorithm and from the observers' ratings were binarized by thresholds of 3 and 4. The sensitivity, specificity and accuracy obtained in these two threshold settings ranged from 65 to 77%, 86 to 93% and 85 to 88% respectively, which are comparable to results obtained in previous studies in which non-clinical T2 maps were available. The proposed algorithm took 10s to estimate the PI-RADS score distribution in an axial image. The efficiency achievable suggests that this technique can be developed into a prostate MR analysis system suitable for clinical use after a thorough validation involving more patients.