Development and clinical implementation of SeedNet: A sliding-window convolutional neural network for radioactive seed identification in MRI-assisted radiosurgery (MARS)

Uncertainty in magnetic resonance imaging-based prostate postimplant dosimetry: Results of a 10-person human observer study, and comparisons with automatic postimplant dosimetry

PURPOSE

Uncertainties in postimplant quality assessment (QA) for low-dose-rate prostate brachytherapy (LDRPBT) are introduced at two steps: seed localization and contouring. We quantified how interobserver variability (IoV) introduced in both steps impacts dose-volume-histogram (DVH) parameters for MRI-based LDRPBT, and compared it with automatically derived DVH parameters.

METHODS AND MATERIALS

Twenty-five patients received MRI-based LDRPBT. Seven clinical observers contoured the prostate and four organs at risk, and 4 dosimetrists performed seed localization, on each MRI. Twenty-eight unique manual postimplant QAs were created for each patient from unique observer pairs. Reference QA and automatic QA were also performed for each patient. IoV of prostate, rectum, and external urinary sphincter (EUS) DVH parameters owing to seed localization and contouring was quantified with coefficients of variation. Automatically derived DVH parameters were compared with those of the reference plans.

RESULTS

Coefficients of variation (CoVs) owing to contouring variability (CoVcontours) were significantly higher than those due to seed localization variability (CoVseeds) (median CoVcontours vs. median CoVseeds: prostate D90-15.12% vs. 0.65%, p < 0.001; prostate V100-5.36% vs. 0.37%, p < 0.001; rectum V100-79.23% vs. 8.69%, p < 0.001; EUS V200-107.74% vs. 21.18%, p < 0.001). CoVcontours were lower when the contouring observers were restricted to the 3 radiation oncologists, but were still markedly higher than CoVseeds. Median differences in prostate D90, prostate V100, rectum V100, and EUS V200 between automatically computed and reference dosimetry parameters were 3.16%, 1.63%, -0.00 mL, and -0.00 mL, respectively.

CONCLUSIONS

Seed localization introduces substantially less variability in postimplant QA than does contouring for MRI-based LDRPBT. While automatic seed localization may potentially help improve workflow efficiency, it has limited potential for improving the consistency and quality of postimplant dosimetry.

Artificial intelligence applications in brachytherapy: A literature review

PURPOSE

Artificial intelligence (AI) has the potential to simplify and optimize various steps of the brachytherapy workflow, and this literature review aims to provide an overview of the work done in this field.

METHODS AND MATERIALS

We conducted a literature search in June 2022 on PubMed, Embase, and Cochrane for papers that proposed AI applications in brachytherapy.

RESULTS

A total of 80 papers satisfied inclusion/exclusion criteria. These papers were categorized as follows: segmentation (24), registration and image processing (6), preplanning (13), dose prediction and treatment planning (11), applicator/catheter/needle reconstruction (16), and quality assurance (10). AI techniques ranged from classical models such as support vector machines and decision tree-based learning to newer techniques such as U-Net and deep reinforcement learning, and were applied to facilitate small steps of a process (e.g., optimizing applicator selection) or even automate the entire step of the workflow (e.g., end-to-end preplanning). Many of these algorithms demonstrated human-level performance and offer significant improvements in speed.

CONCLUSIONS

AI has potential to augment, automate, and/or accelerate many steps of the brachytherapy workflow. We recommend that future studies adhere to standard reporting guidelines. We also stress the importance of using larger sample sizes and reporting results using clinically interpretable measures.

Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management-Current Trends and Future Perspectives

Artificial intelligence (AI) is the field of computer science that aims to build smart devices performing tasks that currently require human intelligence. Through machine learning (ML), the deep learning (DL) model is teaching computers to learn by example, something that human beings are doing naturally. AI is revolutionizing healthcare. Digital pathology is becoming highly assisted by AI to help researchers in analyzing larger data sets and providing faster and more accurate diagnoses of prostate cancer lesions. When applied to diagnostic imaging, AI has shown excellent accuracy in the detection of prostate lesions as well as in the prediction of patient outcomes in terms of survival and treatment response. The enormous quantity of data coming from the prostate tumor genome requires fast, reliable and accurate computing power provided by machine learning algorithms. Radiotherapy is an essential part of the treatment of prostate cancer and it is often difficult to predict its toxicity for the patients. Artificial intelligence could have a future potential role in predicting how a patient will react to the therapy side effects. These technologies could provide doctors with better insights on how to plan radiotherapy treatment. The extension of the capabilities of surgical robots for more autonomous tasks will allow them to use information from the surgical field, recognize issues and implement the proper actions without the need for human intervention.

Fully Balanced SSFP Without an Endorectal Coil for Postimplant QA of MRI-Assisted Radiosurgery (MARS) of Prostate Cancer: A Prospective Study

PURPOSE

To investigate fully balanced steady-state free precession (bSSFP) with optimized acquisition protocols for magnetic resonance imaging (MRI)-based postimplant quality assessment of low-dose-rate (LDR) prostate brachytherapy without an endorectal coil (ERC).

METHODS AND MATERIALS

Seventeen patients at a major academic cancer center who underwent MRI-assisted radiosurgery (MARS) LDR prostate cancer brachytherapy were imaged with moderate, high, or very high spatial resolution fully bSSFP MRIs without using an ERC. Between 1 and 3 signal averages (NEX) were acquired with acceleration factors (R) between 1 and 2, with the goal of keeping scan times between 4 and 6 minutes. Acquisitions with R >1 were reconstructed with parallel imaging and compressed sensing (PICS) algorithms. Radioactive seeds were identified by 3 medical dosimetrists. Additionally, some of the MRI techniques were implemented and tested at a community hospital; 3 patients underwent MARS LDR prostate brachytherapy and were imaged without an ERC.

RESULTS

Increasing the in-plane spatial resolution mitigated partial volume artifacts and improved overall seed and seed marker visualization at the expense of reduced signal-to-noise ratio (SNR). The reduced SNR as a result of imaging at higher spatial resolution and without an ERC was partially compensated for by the multi-NEX acquisitions enabled by PICS. Resultant image quality was superior to the current clinical standard. All 3 dosimetrists achieved near-perfect precision and recall for seed identification in the 17 patients. The 3 postimplant MRIs acquired at the community hospital were sufficient to identify 208 out of 211 seeds implanted without reference to computed tomography (CT).

CONCLUSIONS

Acquiring postimplant prostate brachytherapy MRI without an ERC has several advantages including better patient tolerance, lower costs, higher clinical throughput, and widespread access to precision LDR prostate brachytherapy. This prospective study confirms that the use of an ERC can be circumvented with fully bSSFP and advanced MRI scan techniques in a major academic cancer center and community hospital, potentially enabling postimplant assessment of MARS LDR prostate brachytherapy without CT.

Deep learning-based digitization of prostate brachytherapy needles in ultrasound images

PURPOSE

To develop, and evaluate the performance of, a deep learning-based three-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy.

METHODS

Transrectal ultrasound (TRUS) image volumes from 1102 treatments were used to create a clinical ground truth (CGT) including 24422 individual needles that had been manually digitized by medical physicists during brachytherapy procedures. A 3D CNN U-net with 128 × 128 × 128 TRUS image volumes as input was trained using 17215 needle examples. Predictions of voxels constituting a needle were combined to yield a 3D linear function describing the localization of each needle in a TRUS volume. Manual and AI digitizations were compared in terms of the root-mean-square distance (RMSD) along each needle, expressed as median and interquartile range (IQR). The method was evaluated on a data set including 7207 needle examples. A subgroup of the evaluation data set (n = 188) was created, where the needles were digitized once more by a medical physicist (G1) trained in brachytherapy. The digitization procedure was timed.

RESULTS

The RMSD between the AI and CGT was 0.55 (IQR: 0.35-0.86) mm. In the smaller subset, the RMSD between AI and CGT was similar (0.52 [IQR: 0.33-0.79] mm) but significantly smaller (P < 0.001) than the difference of 0.75 (IQR: 0.49-1.20) mm between AI and G1. The difference between CGT and G1 was 0.80 (IQR: 0.48-1.18) mm, implying that the AI performed as well as the CGT in relation to G1. The mean time needed for human digitization was 10 min 11 sec, while the time needed for the AI was negligible.

CONCLUSIONS

A 3D CNN can be trained to identify needles in TRUS images. The performance of the network was similar to that of a medical physicist trained in brachytherapy. Incorporating a CNN for needle identification can shorten brachytherapy treatment procedures substantially.

Development and evaluation of a deep learning based artificial intelligence for automatic identification of gold fiducial markers in an MRI-only prostate radiotherapy workflow

Identification of prostate gold fiducial markers in magnetic resonance imaging (MRI) images is challenging when CT images are not available, due to misclassifications from intra-prostatic calcifications. It is also a time consuming task and automated identification methods have been suggested as an improvement for both objectives. Multi-echo gradient echo (MEGRE) images have been utilized for manual fiducial identification with 100% detection accuracy. The aim is therefore to develop an automatic deep learning based method for fiducial identification in MRI images intended for MRI-only prostate radiotherapy. MEGRE images from 326 prostate cancer patients with fiducials were acquired on a 3T MRI, post-processed with N4 bias correction, and the fiducial center of mass (CoM) was identified. A 9 mm radius sphere was created around the CoM as ground truth. A deep learning HighRes3DNet model for semantic segmentation was trained using image augmentation. The model was applied to 39 MRI-only patients and 3D probability maps for fiducial location and segmentation were produced and spatially smoothed. In each of the three largest probability peaks, a 9 mm radius sphere was defined. Detection sensitivity and geometric accuracy was assessed. To raise awareness of potential false findings a 'BeAware' score was developed, calculated from the total number and quality of the probability peaks. All datasets, annotations and source code used were made publicly available. The detection sensitivity for all fiducials were 97.4%. Thirty-six out of thirty-nine patients had all fiducial markers correctly identified. All three failed patients generated a user notification using the BeAware score. The mean absolute difference between the detected fiducial and ground truth CoM was 0.7 ± 0.9 [0 3.1] mm. A deep learning method for automatic fiducial identification in MRI images was developed and evaluated with state-of-the-art results. The BeAware score has the potential to notify the user regarding patients where the proposed method is uncertain.

Costs and Complications After a Diagnosis of Prostate Cancer Treated With Time-Efficient Modalities: An Analysis of National Medicare Data

PURPOSE

Recent trends in payer and patient preferences increasingly incentivize time-efficient (≤2-week treatment time) prostate cancer treatments.

METHODS AND MATERIALS

National Medicare claims from January 1, 2011, through December 31, 2014, were analyzed to identify newly diagnosed prostate cancers. Three "radical treatment" cohorts were identified (prostatectomy, brachytherapy, and stereotactic body radiation therapy [SBRT]) and matched to an active surveillance (AS) cohort by using inverse probability treatment weighting via propensity score. Total costs at 1 year after biopsy were calculated for each cohort, and treatment-specific costs were estimated by subtracting total 1-year costs in each radical treatment group from those in the AS group.

RESULTS

Mean 1-year adjusted costs were highest among patients receiving SBRT ($26,895), lower for prostatectomy ($23,632), and lowest for brachytherapy ($19,980), whereas those for AS were $9687. Costs of radical modalities varied significantly by region, with the Mid-Atlantic and New England regions having the highest cost ranges (>$10,000) and the West South Central and Mountain regions the lowest range in costs (<$2000). Quantification of toxic effects showed that prostatectomy was associated with higher genitourinary incontinence (hazard ratio [HR] = 10.8 compared with AS) and sexual dysfunction (HR = 3.5), whereas the radiation modalities were associated with higher genitourinary irritation/bleeding (brachytherapy HR = 1.7; SBRT HR = 1.5) and gastrointestinal ulcer/stricture/fistula (brachytherapy HR = 2.7; SBRT HR = 3.0). Overall mean toxicity costs were highest among patients treated with prostatectomy ($3500) followed by brachytherapy ($1847), SBRT ($1327), and AS ($1303).

CONCLUSIONS

Time-efficient treatment techniques exhibit substantial variability in toxicity and costs. Furthermore, geographic location substantially influenced treatment costs.

MRI-assisted radiosurgery: A quality assurance nomogram for palladium-103 and iodine-125 prostate brachytherapy

PURPOSE

We sought to develop an activity nomogram for magnetic resonance (MR)-planned permanent seed prostate brachytherapy to improve quality assurance through a secondary dosimetric check.

METHODS AND MATERIALS

Patients undergoing MRI-assisted radiosurgery (MARS), whereby MRI is used for preoperative planning and postimplant dosimetry, were reviewed from May 2016 to September 2018. Planned activity (U) was fitted by MR-prostate volume (cc) via simple linear regression. Resulting monotherapy nomograms were compared with institutional nomograms from an ultrasound-planned cohort. Dosimetric coverage and external urinary sphincter (EUS) dose were also assessed for MR-planned patients.

RESULTS

We identified 183 patients treated with MARS: 146 patients received palladium-103 (¹⁰³Pd; 102 monotherapy and 44 boost), and 37 received iodine-125 (¹²⁵I) monotherapy. Median prostate volume was 28 cc (interquartile range: 22-35). Lines of best fit for implant activity were U = 4.344 × (vol) + 54.13 (R²: 95%) for ¹⁰³Pd monotherapy, U = 3.202 (vol) + 39.72 (R²: 96%) for ¹⁰³Pd boost and U = 0.684 (vol) + 13.38 (R²: 96%) for ¹²⁵I monotherapy. Compared with ultrasound, MR-planned nomograms had lower activity per volume (p < 0.05) for both ¹⁰³Pd monotherapy (∼6%) and ¹²⁵I monotherapy (∼11%), given a median size (30 cc) prostate. Across all MARS implants, postimplant dosimetry revealed a median V100% of 94% (interquartile range: 92-96%). Median EUS V125 was <1 cc for all patients, regardless of isotope.

CONCLUSIONS

We developed a quality assurance nomogram for MR-planned prostate brachytherapy. When compared with ultrasound-planned, MR-planned monotherapy resulted in a lower activity-to-volume ratio while maintaining dosimetric coverage, likely secondary to EUS-sparing and reduced planning target margins.

Deep learning application engine (DLAE): Development and integration of deep learning algorithms in medical imaging

Herein we introduce a deep learning (DL) application engine (DLAE) system concept, present potential uses of it, and describe pathways for its integration in clinical workflows. An open-source software application was developed to provide a code-free approach to DL for medical imaging applications. DLAE supports several DL techniques used in medical imaging, including convolutional neural networks, fully convolutional networks, generative adversarial networks, and bounding box detectors. Several example applications using clinical images were developed and tested to demonstrate the capabilities of DLAE. Additionally, a model deployment example was demonstrated in which DLAE was used to integrate two trained models into a commercial clinical software package.