Accuracy of tumor segmentation from multi-parametric prostate MRI and 18F-choline PET/CT for focal prostate cancer therapy applications

PCa-RadHop: A transparent and lightweight feed-forward method for clinically significant prostate cancer segmentation

Prostate Cancer is one of the most frequently occurring cancers in men, with a low survival rate if not early diagnosed. PI-RADS reading has a high false positive rate, thus increasing the diagnostic incurred costs and patient discomfort. Deep learning (DL) models achieve a high segmentation performance, although require a large model size and complexity. Also, DL models lack of feature interpretability and are perceived as "black-boxes" in the medical field. PCa-RadHop pipeline is proposed in this work, aiming to provide a more transparent feature extraction process using a linear model. It adopts the recently introduced Green Learning (GL) paradigm, which offers a small model size and low complexity. PCa-RadHop consists of two stages: Stage-1 extracts data-driven radiomics features from the bi-parametric Magnetic Resonance Imaging (bp-MRI) input and predicts an initial heatmap. To reduce the false positive rate, a subsequent stage-2 is introduced to refine the predictions by including more contextual information and radiomics features from each already detected Region of Interest (ROI). Experiments on the largest publicly available dataset, PI-CAI, show a competitive performance standing of the proposed method among other deep DL models, achieving an area under the curve (AUC) of 0.807 among a cohort of 1,000 patients. Moreover, PCa-RadHop maintains orders of magnitude smaller model size and complexity.

Nanoparticles Targeted to Fibroblast Activation Protein Outperform PSMA for MRI Delineation of Primary Prostate Tumors

Accurate delineation of gross tumor volumes remains a barrier to radiotherapy dose escalation and boost dosing in the treatment of solid tumors, such as prostate cancer. Magnetic resonance imaging (MRI) of tumor targets has the power to enable focal dose boosting, particularly when combined with technological advances such as MRI-linear accelerator. Fibroblast activation protein (FAP) is overexpressed in stromal components of >90% of epithelial carcinomas. Herein, the authors compare targeted MRI of prostate specific membrane antigen (PSMA) with FAP in the delineation of orthotopic prostate tumors. Control, FAP, and PSMA-targeting iron oxide nanoparticles were prepared with modification of a lymphotropic MRI agent (FerroTrace, Ferronova). Mice with orthotopic LNCaP tumors underwent MRI 24 h after intravenous injection of nanoparticles. FAP and PSMA nanoparticles produced contrast enhancement on MRI when compared to control nanoparticles. FAP-targeted MRI increased the proportion of tumor contrast-enhancing black pixels by 13%, compared to PSMA. Analysis of changes in R2 values between healthy prostates and LNCaP tumors indicated an increase in contrast-enhancing pixels in the tumor border of 15% when targeting FAP, compared to PSMA. This study demonstrates the preclinical feasibility of PSMA and FAP-targeted MRI which can enable targeted image-guided focal therapy of localized prostate cancer.

Index lesion contouring on prostate MRI for targeted MRI/US fusion biopsy - Evaluation of mismatch between radiologists and urologists

PURPOSE

Mistargeting of focal lesions due to inaccurate segmentations can lead to false-negative findings on MRI-guided targeted biopsies. The purpose of this retrospective study was to examine inter-reader agreement of prostate index lesion segmentations from actual biopsy data between urologists and radiologists.

METHOD

Consecutive patients undergoing transperineal MRI-targeted prostate biopsy for PI-RADS 3-5 lesions between January 2020 and December 2021 were included. Agreement between segmentations on T2w-images between urologists and radiologists was assessed with Dice similarity coefficient (DSC) and 95 % Hausdorff distance (95 % HD). Differences in similarity scores were compared using Wilcoxon test. Differences depending on lesion features (size, zonal location, PI-RADS scores, lesion distinctness) were tested with Mann-Whitney U test. Correlation with prostate signal-intensity homogeneity score (PSHS) and lesion size was tested with Spearman's rank correlation.

RESULTS

Ninety-three patients (mean age 64.9 ± 7.1y, median serum PSA 6.5 [4.33-10.00]) were included. Mean similarity scores were statistically significantly lower between urologists and radiologists compared to radiologists only (DSC 0.41 ± 0.24 vs. 0.59 ± 0.23, p < 0.01; 95 %HD 6.38 ± 5.45 mm vs. 4.47 ± 4.12 mm, p < 0.01). There was a moderate and strong positive correlation between DSC scores and lesion size for segmentations from urologists and radiologists (ρ = 0.331, p = 0.002) and radiologists only (ρ = 0.501, p < 0.001). Similarity scores were worse in lesions ≤ 10 mm while other lesion features did not significantly influence similarity scores.

CONCLUSION

There is significant mismatch of prostate index lesion segmentations between urologists and radiologists. Segmentation agreement positively correlates with lesion size. PI-RADS scores, zonal location, lesion distinctness, and PSHS show no significant impact on segmentation agreement. These findings could underpin benefits of perilesional biopsies.

Real-Time MRI-Guided Prostate Interventions

Simple Summary

Magnetic resonance imaging has shown to be a reliable imaging method for detecting clinically significant prostate cancer and directly targeting lesions during biopsy. As newer treatment methods emerge, the role of MRI in minimally-invasive (focal) treatment of prostate cancer is also increasing. Here, we review the real-time MRI-guided prostate interventions for prostate cancer diagnosis and treatment, focusing on the technical aspects of each modality.

Abstract

Prostate cancer (PCa) is the second most common cause of cancer death in males. Targeting MRI-visible lesions has led to an overall increase in the detection of clinically significant PCa compared to the prior practice of random ultrasound-guided biopsy of the prostate. Additionally, advances in MRI-guided minimally invasive focal treatments are providing new options for patients with PCa. This review summarizes the currently utilized real-time MRI-guided interventions for PCa diagnosis and treatment.

Future perspective of focal therapy for localized prostate cancer

Objective

To summarize the recent literature discussing focal therapy for localized prostate cancer.

Methods

A thorough literature review was performed using PubMed to identify recent studies involving focal therapy for the treatment of localized prostate cancer.

Results

In an effort to decrease the morbidity associated with prostate cancer treatment, many urologists are turning to focal therapy as an alternative treatment option. With this approach, the cancer bearing portion of the prostate is targeted while leaving the benign tissue untouched. Multiparametric magnetic resonance imaging remains the gold standard for visualization during focal therapy, but new imaging modalities such as prostate specific membrane antigen/positron emission tomography and contrast enhanced ultrasound are being investigated. Furthermore, several biomarkers, such as prostate cancer antigen 3 and prostate health index, are used in conjunction with imaging to improve risk stratification prior to focal therapy. Lastly, there are several novel technologies such as nanoparticles and transurethral devices that are under investigation for use in focal therapy.

Conclusion

Focal therapy is proving to be a promising option for the treatment of localized prostate cancer. However, further study is needed to determine the true efficacy of these exciting new technologies.

A System for Co-Registration of High-Resolution Ultrasound, Magnetic Resonance Imaging, and Whole-Mount Pathology for Prostate Cancer

In order to evaluate the diagnostic accuracy of high-resolution ultrasound (HRUS) for detection of prostate cancer, it must be validated against whole-mount pathology. An ex-vivo HRUS scanning system was developed and tested in phantom and human tissue experiments to allow for in-plane computational co-registration of HRUS with magnetic resonance imaging (MRI) and whole-mount pathology. The system allowed for co-registration with an error of 1.9mm±1.4mm, while also demonstrating an ability to allow for lesion identification.Clinical Relevance- Using this system, a workflow can be established to co-register HRUS with MRI and pathology to allow for the diagnostic accuracy of HRUS to be determined with direct comparison to MRI.

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.

Prostate cancer GTV delineation with biparametric MRI and 68Ga-PSMA-PET: comparison of expert contours and semi-automated methods

OBJECTIVE

The optimal method for delineation of dominant intraprostatic lesions (DIL) for targeted radiotherapy dose escalation is unclear. This study evaluated interobserver and intermodality variability of delineations on biparametric MRI (bpMRI), consisting of T₂ weighted (T₂W) and diffusion-weighted (DWI) sequences, and ⁶⁸Ga-PSMA-PET/CT; and compared manually delineated GTV contours with semi-automated segmentations based on quantitative thresholding of intraprostatic apparent diffusion coefficient (ADC) and standardised uptake values (SUV).

METHODS

16 patients who had bpMRI and PSMA-PET scanning performed prior to any treatment were eligible for inclusion. Four observers (two radiation oncologists, two radiologists) manually delineated the DIL on: (1) bpMRI (GTV_MRI), (2) PSMA-PET (GTV_PSMA) and (3) co-registered bpMRI/PSMA-PET (GTV_Fused) in separate sittings. Interobserver, intermodality and semi-automated comparisons were evaluated against consensus Simultaneous Truth and Performance Level Estimation (STAPLE) volumes, created from the relevant manual delineations of all observers with equal weighting. Comparisons included the Dice Similarity Coefficient (DSC), mean distance to agreement (MDA) and other metrics.

RESULTS

Interobserver agreement was significantly higher (p < 0.05) for GTV_PSMA (DSC: 0.822, MDA: 1.12 mm) and GTV_Fused (DSC: 0.787, MDA: 1.34 mm) than for GTV_MRI (DSC: 0.705, MDA 2.44 mm). Intermodality agreement between GTV_MRI and GTV_PSMA was low (DSC: 0.440, MDA: 4.64 mm). Agreement between semi-automated volumes and consensus GTV was low for MRI (DSC: 0.370, MDA: 8.16 mm) and significantly higher for PSMA-PET (0.571, MDA: 4.45 mm, p < 0.05).

CONCLUSION

⁶⁸Ga-PSMA-PET appears to improve interobserver consistency of DIL localisation vs bpMRI and may be more viable for simple quantitative delineation approaches; however, more sophisticated approaches to semi-automatic delineation factoring for patient- and disease-related heterogeneity are likely required.

ADVANCES IN KNOWLEDGE

This is the first study to evaluate the interobserver variability of prostate GTV delineations with co-registered bpMRI and ⁶⁸Ga-PSMA-PET.

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.

Current Status of MRI and PET in the NCCN Guidelines for Prostate Cancer

Prostate cancer (PCa) represents a significant source of morbidity and mortality for men in the United States, with approximately 1 in 9 being diagnosed with PCa in their lifetime. The role of imaging in the evaluation of men with PCa has evolved and currently plays a central role in diagnosis, treatment planning, and evaluation of recurrence. Appropriate use of multiparametric MRI (mpMRI) and MRI-guided transrectal ultrasound (MR-TRUS) biopsy increases the detection of clinically significant PCa while decreasing the detection of clinically insignificant PCa. This process may help patients with clinically insignificant PCa avoid the adverse effects of unnecessary therapy. In the setting of a known PCa, patients with low-grade disease can be observed using active surveillance, which often includes a combination of prostate-specific antigen (PSA) testing, serial mpMRI, and, if indicated, follow-up systematic and targeted TRUS-guided tissue sampling. mpMRI can provide important information in the posttreatment setting, but PET/CT is creating a paradigm shift in imaging standards for patients with locally recurrent and metastatic PCa. This article examines the strengths and limitations of mpMRI for initial PCa diagnosis, active surveillance, recurrent disease evaluation, and image-guided biopsies, and the use of PET/CT imaging in men with recurrent PCa. The goal of this review is to provide a rational basis for current NCCN Clinical Practice Guidelines in Oncology for PCa as they pertain to the use of these advanced imaging modalities.

Comparison of cross-sectional imaging techniques for the detection of prostate cancer lymph node metastasis: a critical review

Conventional staging for prostate cancer (PCa) is performed for men diagnosed with unfavorable-intermediate or higher risk disease. Computed tomography (CT) of the abdomen and pelvis and whole body bone scan remains the standard of care for the detection of visceral, nodal, and bone metastasis. The implementation of the 2012 United States Preventive Services Task Force recommendation against routine prostate specific antigen (PSA) screening resulted in a rise of metastatic PCa at the time of diagnosis, emphasizing the importance of effective imaging modalities for evaluating metastatic disease. CT plays a major role in clinical staging at the time of PCa diagnosis, but multi-parametric magnetic resonance imaging (MRI) is now integrated into many prostate biopsy protocols for the detection of primary PCa, and may be a surrogate for CT for nodal staging. Current guidelines incorporate both CT and MRI as appropriate cross-sectional imaging modalities for the identification of nodal metastasis in indicated patients. There is an ongoing debate about the utility of traditional cross-sectional imaging modalities as well as advanced imaging modalities in detection of both organ-confined PCa detection and nodal involvement.

Quantitative Prostate MRI

Prostate MRI is reported in clinical practice using the Prostate Imaging and Data Reporting System (PI-RADS). PI-RADS aims to standardize, as much as possible, the acquisition, interpretation, reporting, and ultimately the performance of prostate MRI. PI-RADS relies upon mainly subjective analysis of MR imaging findings, with very few incorporated quantitative features. The shortcomings of PI-RADS are mainly: low-to-moderate interobserver agreement and modest accuracy for detection of clinically significant tumors in the transition zone. The use of a more quantitative analysis of prostate MR imaging findings is therefore of interest. Quantitative MR imaging features including: tumor size and volume, tumor length of capsular contact, tumor apparent diffusion coefficient (ADC) metrics, tumor T₁ and T₂ relaxation times, tumor shape, and texture analyses have all shown value for improving characterization of observations detected on prostate MRI and for differentiating between tumors by their pathological grade and stage. Quantitative analysis may therefore improve diagnostic accuracy for detection of cancer and could be a noninvasive means to predict patient prognosis and guide management. Since quantitative analysis of prostate MRI is less dependent on an individual users' assessment, it could also improve interobserver agreement. Semi- and fully automated analysis of quantitative (radiomic) MRI features using artificial neural networks represent the next step in quantitative prostate MRI and are now being actively studied. Validation, through high-quality multicenter studies assessing diagnostic accuracy for clinically significant prostate cancer detection, in the domain of quantitative prostate MRI is needed. This article reviews advances in quantitative prostate MRI, highlighting the strengths and limitations of existing and emerging techniques, as well as discussing opportunities and challenges for evaluation of prostate MRI in clinical practice when using quantitative assessment. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

How accurately can multiparametric magnetic resonance imaging measure the tumour volume of a prostate cancer? Results of a systematic review

The tumour volume of a cancer within the prostate gland is commonly measured with multiparametric MRI. The measurement has a role in many clinical scenarios including focal therapy, but the accuracy of it has never been systematically reviewed. We included articles if they compared tumour volume measurements obtained by mpMRI with a reference volume measurement obtained after radical prostatectomy. Correlation and concordance statistics were summarised. A simple accuracy score was derived by dividing the given mean or median mpMRI volume by the histopathological reference volume. Factors affecting the accuracy were noted. Scores for potential bias and quality were calculated for each article. A total of 18 articles describing 1438 patients were identified. Nine articles gave Pearson's correlation scores, with a median value of 0.75 but the range was wide (0.42-0.97). A total of 11 articles reported mean values for volume while 9 reported median values. For all 18 articles, the mean or median values for MRI volumes were lower than the corresponding reference values suggesting consistent underestimation. For articles reporting mean and median values for volume, the median accuracy scores were 0.83 and 0.80, respectively. The accuracy was higher for tumours of greater volume, higher grade and when an endorectal coil was used. Accuracy did not seem to improve over time, with a 3 Tesla magnet or by applying a shrinkage factor to the reference measurement. Most studies showed evidence of at least moderate bias, and their quality was highly variable, but neither of these appeared to affect accuracy.

Manual prostate cancer segmentation in MRI: interreader agreement and volumetric correlation with transperineal template core needle biopsy

OBJECTIVES

To assess interreader agreement of manual prostate cancer lesion segmentation on multiparametric MR images (mpMRI). The secondary aim was to compare tumor volume estimates between MRI segmentation and transperineal template saturation core needle biopsy (TTSB).

METHODS

We retrospectively reviewed patients who had undergone mpMRI of the prostate at our institution and who had received TTSB within 190 days of the examination. Seventy-eight cancer lesions with Gleason score of at least 3 + 4 = 7 were manually segmented in T2-weighted images by 3 radiologists and 1 medical student. Twenty lesions were also segmented in apparent diffusion coefficient (ADC) and dynamic contrast enhanced (DCE) series. First, 20 volumetric similarity scores were computed to quantify interreader agreement. Second, manually segmented cancer lesion volumes were compared with TTSB-derived estimates by Bland-Altman analysis and Wilcoxon testing.

RESULTS

Interreader agreement across all readers was only moderate with mean T2 Dice score of 0.57 (95%CI 0.39-0.70), volumetric similarity coefficient of 0.74 (0.48-0.89), and Hausdorff distance of 5.23 mm (3.17-9.32 mm). Discrepancy of volume estimate between MRI and TTSB was increasing with tumor size. Discrepancy was significantly different between tumors with a Gleason score 3 + 4 vs. higher grade tumors (0.66 ml vs. 0.78 ml; p = 0.007). There were no significant differences between T2, ADC, and DCE segmentations.

CONCLUSIONS

We found at best moderate interreader agreement of manual prostate cancer segmentation in mpMRI. Additionally, our study suggests a systematic discrepancy between the tumor volume estimate by MRI segmentation and TTSB core length, especially for large and high-grade tumors.

KEY POINTS

• Manual prostate cancer segmentation in mpMRI shows moderate interreader agreement. • There are no significant differences between T2, ADC, and DCE segmentation agreements. • There is a systematic difference between volume estimates derived from biopsy and MRI.

Liver-specific 3D sectioning molds for correlating in vivo CT and MRI with tumor histopathology in woodchucks (Marmota monax)

Purpose

To evaluate the spatial registration and correlation of liver and tumor histopathology sections with corresponding in vivo CT and MRI using 3D, liver-specific cutting molds in a woodchuck (Marmota monax) hepatic tumor model.

Methods

Five woodchucks chronically infected with woodchuck hepatitis virus following inoculation at birth and with confirmed hepatic tumors were imaged by contrast enhanced CT or MRI. Virtual 3D liver or tumor models were generated by segmentation of in vivo CT or MR imaging. A specimen-specific cavity was created inside a block containing cutting slots aligned with an imaging plane using computer-aided design software, and the final cutting molds were fabricated using a 3D printer. Livers were resected two days after initial imaging, fixed with formalin or left unfixed, inserted into the 3D molds, and cut into parallel pieces by passing a sharp blade through the parallel slots in the mold. Histopathology sections were acquired and their spatial overlap with in vivo image slices was quantified using the Dice similarity coefficient (DSC).

Results

Imaging of the woodchucks revealed heterogeneous hepatic tumors of varying size, number, and location. Specimen-specific 3D molds provided accurate co-localization of histopathology of whole livers, liver lobes, and pedunculated tumors with in vivo CT and MR imaging, with or without tissue fixation. Visual inspection of histopathology sections and corresponding in vivo image slices revealed spatial registration of analogous pathologic features. The mean DSC for all specimens was 0.83+/-0.05.

Conclusion

Use of specimen-specific 3D molds for en bloc liver dissection provided strong spatial overlap and feature correspondence between in vivo image slices and histopathology sections.

Contemporary treatments in prostate cancer focal therapy

PURPOSE OF REVIEW

Radical treatments for prostate cancer are associated with significant morbidity, including incontinence and erectile dysfunction. Advances in the field of prostate MRI and desire to reduce treatment morbidities have led to a rapid growth in focal treatments for prostate cancer. Here, we review novel focal prostate cancer treatments and their associated recent clinical data, with a particular focus on data reported within the last 24 months.

RECENT FINDINGS

High-intensity focal ultrasound, focal laser ablation, irreversible electroporation, focal cryotherapy, and photodynamic therapy have been used as treatment modalities for localized prostate cancer treatment. Despite the great variety of treatment techniques, each of these modalities is characterized by a significant rate of prostate cancer persistence within treatment zones (6-50%) and the presence of residual cancer within the prostate on rebiopsy (24-49%). These treatments, however, are associated with very low rates of high-grade complications, rare incontinence, and only mild or transient reductions in erectile function. The most common adverse events are urinary tract infections, hematuria, and urinary retention.

SUMMARY

Prostate cancer focal therapy is an attractive option for well-selected patients because of its low complication profile; however, long-term oncologic outcome is still lacking and early recurrence rates are high, limiting the ability of most urologic associations from endorsing its routine use.

Dosimetric Evaluation of PSMA PET-Delineated Dominant Intraprostatic Lesion Simultaneous Infield Boosts

PURPOSE

Prostate cancer is multifocal. However, there often exists a single dominant focus in the gland responsible for driving the biology of the disease. Dose escalation to the dominant lesion is a proposed strategy to increase tumor control. We applied radiobiological modeling to evaluate the dosimetric feasibility and benefit of dominant intraprostatic lesion simultaneous in-field boosts (DIL-SIB) to the gross tumor volume (GTV), defined using a novel molecular positron emission tomography (PET) probe (18F-DCFPyL) directed against prostate specific membrane antigen (PSMA).

METHODS AND MATERIALS

Patients with clinically localized, biopsy-proven prostate cancer underwent preoperative [18F]-DCFPyL PET/computed tomography (CT). DIL-SIB plans were generated by importing the PET/CT into the RayStation treatment planning system. GTV-PET for the DIL-SIB was defined by the highest %SUVmax (percentage of maximum standardized uptake value) that generated a biologically plausible volume. Volumetric arc-based plans incorporating prostate plus DIL-SIB treatment were generated. Tumor control probability (TCP) and normal tissue complication probability (NTCP) with fractionation schemes and boost doses specified in the FLAME (Investigate the Benefit of a Focal Lesion Ablative Microboost in Prostate Cancer; NCT01168479), PROFIT (Prostate Fractionated Irradiation Trial; NCT00304759), PACE (Prostate Advances in Comparative Evidence; NCT01584258), and hypoFLAME (Hypofractionated Focal Lesion Ablative Microboost in prostatE Cancer 2.0; NCT02853110) protocols were compared.

RESULTS

Comparative DIL-SIB plans for 6 men were generated from preoperative [18F]-DCFPyL PET/CT. Median boost GTV volume was 1.015 cm3 (0.42-1.83 cm3). Median minimum (D99%) DIL-SIB dose for F35BS, F20BS, F5BS, and F5BSH were 97.3 Gy, 80.8 Gy, 46.5 Gy, and 51.5Gy. TCP within the GTV ranged from 84% to 88% for the standard plan and 95% to 96% for the DIL-SIB plans. Within the rest of the prostate, TCP ranged from 89% to 91% for the standard plans and 90% to 92% for the DIL-SIB plans. NTCP for the rectum NTCP was similar for the DIL-SIB plans (0.3%-2.7%) compared with standard plans (0.7%-2.6%). Overall, DIL-SIB plans yielded higher uncomplicated TCP (NTCP, 90%-94%) versus standard plans (NTCP, 83%-85%).

CONCLUSIONS

PSMA PET provides a novel approach to define GTV for SIB-DIL dose escalation. Work is ongoing to validate PSMA PET-delineated GTV through correlation to coregistered postprostatectomy digitized histopathology.

Deep Learning Improved Clinical Target Volume Contouring Quality and Efficiency for Postoperative Radiation Therapy in Non-small Cell Lung Cancer

Purpose: To investigate whether a deep learning-assisted contour (DLAC) could provide greater accuracy, inter-observer consistency, and efficiency compared with a manual contour (MC) of the clinical target volume (CTV) for non-small cell lung cancer (NSCLC) receiving postoperative radiotherapy (PORT).

Materials and Methods: A deep dilated residual network was used to achieve the effective automatic contour of the CTV. Eleven junior physicians contoured CTVs on 19 patients by using both MC and DLAC methods independently. Compared with the ground truth, the accuracy of the contour was evaluated by using the Dice coefficient and mean distance to agreement (MDTA). The coefficient of variation (CV) and standard distance deviation (SDD) were rendered to measure the inter-observer variability or consistency. The time consumed for each of the two contouring methods was also compared.

Results: A total of 418 CTV sets were generated. DLAC improved contour accuracy when compared with MC and was associated with a larger Dice coefficient (mean ± SD: 0.75 ± 0.06 vs. 0.72 ± 0.07, p < 0.001) and smaller MDTA (mean ± SD: 2.97 ± 0.91 mm vs. 3.07 ± 0.98 mm, p < 0.001). The DLAC was also associated with decreased inter-observer variability, with a smaller CV (mean ± SD: 0.129 ± 0.040 vs. 0.183 ± 0.043, p < 0.001) and SDD (mean ± SD: 0.47 ± 0.22 mm vs. 0.72 ± 0.41 mm, p < 0.001). In addition, a value of 35% of time saving was provided by the DLAC (median: 14.81 min vs. 9.59 min, p < 0.001).

Conclusions: Compared with MC, the DLAC is a promising strategy to obtain superior accuracy, consistency, and efficiency for the PORT-CTV in NSCLC.

18F-Choline PET/mpMRI for Detection of Clinically Significant Prostate Cancer: Part 1. Improved Risk Stratification for MRI-Guided Transrectal Prostate Biopsies

A prospective single-arm clinical trial was conducted to determine whether ¹⁸F-choline PET/mpMRI can improve the specificity of multiparametric MRI (mpMRI) of the prostate for Gleason ≥ 3+4 prostate cancer. Methods: Before targeted and systematic prostate biopsy, mpMRI and ¹⁸F-choline PET/CT were performed on 56 evaluable subjects with 90 Likert score 3-5 mpMRI target lesions, using a ¹⁸F-choline target-to-background ratio of greater than 1.58 to indicate a positive ¹⁸F-choline result. Prostate biopsies were performed after registration of real-time transrectal ultrasound with T2-weighted MRI. A mixed-effects logistic regression was applied to measure the performance of mpMRI (based on prospective Likert and retrospective Prostate Imaging Reporting and Data System, version 2 [PI-RADS], scores) compared with ¹⁸F-choline PET/mpMRI to detect Gleason ≥ 3+4 cancer. Results: The per-lesion accuracy of systematic plus targeted biopsy for mpMRI alone was 67.8% (area under receiver-operating-characteristic curve [AUC], 0.73) for Likert 4-5 and 70.0% (AUC, 0.76) for PI-RADS 3-5. Several PET/MRI models incorporating ¹⁸F-choline with mpMRI data were investigated. The most promising model selected all high-risk disease on mpMRI (Likert 5 or PI-RADS 5) plus low- and intermediate-risk disease (Likert 4 or PI-RADS 3-4), with an elevated ¹⁸F-choline target-to-background ratio greater than 1.58 as positive for significant cancer. Using this approach, the accuracy on a per-lesion basis significantly improved to 88.9% for Likert (AUC, 0.90; P < 0.001) and 91.1% for PI-RADS (AUC, 0.92; P < 0.001). On a per-patient basis, the accuracy improved to 92.9% for Likert (AUC, 0.93; P < 0.001) and to 91.1% for PI-RADS (AUC, 0.91; P = 0.009). Conclusion: ¹⁸F-choline PET/mpMRI improved the identification of Gleason ≥ 3+4 prostate cancer compared with mpMRI, with the principal effect being improved risk stratification of intermediate-risk mpMRI lesions.

Disease quantification on PET/CT images without explicit object delineation

PURPOSE

The derivation of quantitative information from images in a clinically practical way continues to face a major hurdle because of image segmentation challenges. This paper presents a novel approach, called automatic anatomy recognition-disease quantification (AAR-DQ), for disease quantification (DQ) on positron emission tomography/computed tomography (PET/CT) images. This approach explores how to decouple DQ methods from explicit dependence on object (e.g., organ) delineation through the use of only object recognition results from our recently developed automatic anatomy recognition (AAR) method to quantify disease burden.

METHOD

The AAR-DQ process starts off with the AAR approach for modeling anatomy and automatically recognizing objects on low-dose CT images of PET/CT acquisitions. It incorporates novel aspects of model building that relate to finding an optimal disease map for each organ. The parameters of the disease map are estimated from a set of training image data sets including normal subjects and patients with metastatic cancer. The result of recognition for an object on a patient image is the location of a fuzzy model for the object which is optimally adjusted for the image. The model is used as a fuzzy mask on the PET image for estimating a fuzzy disease map for the specific patient and subsequently for quantifying disease based on this map. This process handles blur arising in PET images from partial volume effect entirely through accurate fuzzy mapping to account for heterogeneity and gradation of disease content at the voxel level without explicitly performing correction for the partial volume effect. Disease quantification is performed from the fuzzy disease map in terms of total lesion glycolysis (TLG) and standardized uptake value (SUV) statistics. We also demonstrate that the method of disease quantification is applicable even when the "object" of interest is recognized manually with a simple and quick action such as interactively specifying a 3D box ROI. Depending on the degree of automaticity for object and lesion recognition on PET/CT, DQ can be performed at the object level either semi-automatically (DQ-MO) or automatically (DQ-AO), or at the lesion level either semi-automatically (DQ-ML) or automatically.

RESULTS

We utilized 67 data sets in total: 16 normal data sets used for model building, and 20 phantom data sets plus 31 patient data sets (with various types of metastatic cancer) used for testing the three methods DQ-AO, DQ-MO, and DQ-ML. The parameters of the disease map were estimated using the leave-one-out strategy. The organs of focus were left and right lungs and liver, and the disease quantities measured were TLG, SUV_Mean, and SUV_Max. On phantom data sets, overall error for the three parameters were approximately 6%, 3%, and 0%, respectively, with TLG error varying from 2% for large "lesions" (37 mm diameter) to 37% for small "lesions" (10 mm diameter). On patient data sets, for non-conspicuous lesions, those overall errors were approximately 19%, 14% and 0%; for conspicuous lesions, these overall errors were approximately 9%, 7%, 0%, respectively, with errors in estimation being generally smaller for liver than for lungs, although without statistical significance.

CONCLUSIONS

Accurate disease quantification on PET/CT images without performing explicit delineation of lesions is feasible following object recognition. Method DQ-MO generally yields more accurate results than DQ-AO although the difference is statistically not significant. Compared to current methods from the literature, almost all of which focus only on lesion-level DQ and not organ-level DQ, our results were comparable for large lesions and were superior for smaller lesions, with less demand on training data and computational resources. DQ-AO and even DQ-MO seem to have the potential for quantifying disease burden body-wide routinely via the AAR-DQ approach.