Prediction of Pathologic Findings with MRI-Based Clinical Staging Using the Bayesian Network Modeling in Prostate Cancer: A Radiation Oncologist Perspective.
Ontology highlight
ABSTRACT: Purpose
This study aimed to develop a model for predicting pathologic extracapsular extension (ECE) and seminal vesicle invasion (SVI) while integrating magnetic resonance imaging-based T-staging (cTMRI, cT1c-cT3b).Materials and methods
A total of 1,915 who underwent radical prostatectomy between 2006-2016 met the inclusion/exclusion criteria. We performed a multivariate logistic regression analysis as well as Bayesian network (BN) modeling based on possible confounding factors. The BN model was internally validated using 5-fold validation.Results
According to the multivariate logistic regression analysis, initial prostate-specific antigen (iPSA) (β=0.050, p < 0.001), percentage of positive biopsy cores (PPC) (β=0.033, p < 0.001), both lobe involvement on biopsy (β=0.359, p=0.009), Gleason score (β=0.358, p < 0.001), and cTMRI (β=0.259, p < 0.001) were significant factors for ECE. For SVI, iPSA (β=0.037, p < 0.001), PPC (β=0.024, p < 0.001), Gleason score (β=0.753, p < 0.001), and cTMRI (β=0.507, p < 0.001) showed statistical significance. BN models to predict ECE and SVI were also successfully established. The overall area under the receiver operating characteristic curve (AUC)/accuracy of the BN models were 0.76/73.0% and 0.88/89.6% for ECE and SVI, respectively. According to internal comparison between the BN model and Roach formula, BN model had improved AUC values for predicting ECE (0.76 vs. 0.74, p=0.060) and SVI (0.88 vs. 0.84, p < 0.001).Conclusion
Two models to predict pathologic ECE and SVI integrating cTMRI were established and installed on a separate website for public access to guide radiation oncologists.
SUBMITTER: Wee CW
PROVIDER: S-EPMC8756129 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesThe aim of this study is to evaluate the 2015 introduction of prebiopsy magnetic resonance imaging of the prostate (MRI-P) as the standard of care for diagnosing prostate cancer (PCa) by the Norwegian public health care authorities. There were three specific objectives of this study: first, to evaluate the consequences of using different TNM manuals for clinical T-staging (cT-staging) in a national setting; second, to determine if the data reveals that MRI-P based cT-staging is superior to digital rectal examination (DRE)-based cT-staging compared with pathological T-stage (pT-stage) post radical prostatectomy; and third, to assess whether treatment allocations have changed over time.Materials and methodsAll patients registered in the Norwegian Prostate Cancer Registry between 2004 and 2021 were retrieved and 5538 were eligible for inclusion. Concordance between clinical T-stage (cT-stage) and pT-stage was assessed by percentage agreement, Cohen's kappa and Gwet's agreement.ResultsMR visualisation of lesions influences reporting of tumour extension beyond DRE findings. Agreement between cT-stage and pT-stage declined from 2004 to 2009, which coincided with an increase in the percentage being pT3. From 2010, agreement increased, which aligned with changes in cT-staging and the introduction of MRI-P. From 2017, regarding the reporting of cT-DRE and cT-Total (overall cT-stage), agreement diminished for cT-DRE but remained relatively stable (>60%) for cT-Total. Regarding treatment allocation, the study suggests that staging with MRI-P has shifted treatment towards radiotherapy in locally advanced high-risk disease.ConclusionIntroduction of MRI-P has affected cT-stage reporting. Agreement between cT-stage and pT-stage appears to have improved. This study suggests that use of MRI-P influences treatment decisions in certain patient subgroups.
| S-EPMC10071082 | biostudies-literature
Project description:We report data-simple descriptions of patient characteristics, cancer categories, and non-risk-adjusted survival-for patients with pathologically staged cancer of the esophagus and esophagogastric junction after resection or ablation with no preoperative therapy from the Worldwide Esophageal Cancer Collaboration (WECC). Thirty-three institutions from six continents submitted de-identified data using standard definitions: demographics, comorbidities, clinical cancer categories, and all-cause mortality from first management decision. Of 13,300 patients, 5,631 had squamous cell carcinoma, 7,558 adenocarcinoma, 85 adenosquamous carcinoma, and 26 undifferentiated carcinoma. Patients were older (62 years) men (80%) with normal body mass index (51%), little weight loss (1.8 kg), 0-2 ECOG performance status (83%), and a history of smoking (70%). Cancers were pT1 (24%), pT2 (15%), pT3 (50%), pN0 (52%), pM0 (93%), and pG2-G3 (78%); most involved distal esophagus (71%). Non-risk-adjusted survival for both squamous cell carcinoma and adenocarcinoma was monotonic and distinctive across pTNM. Survival was more distinctive for adenocarcinoma than squamous cell carcinoma when pT was ordered by pN. Survival for pTis-1 adenocarcinoma was better than for squamous cell carcinoma, although monotonic and distinctive for both. WECC pathologic staging data is improved over that of the 7th edition, with more patients studied and patient and cancer variables collected. These data will be the basis for the 8th edition cancer staging manuals following risk adjustment for patient, cancer, and treatment characteristics, and should direct 9th edition data collection. However, the role of pure pathologic staging as the principal point of reference for esophageal cancer staging is waning.
| S-EPMC5731491 | biostudies-literature
Project description:PURPOSEBone lesions on prostate MRI often raise concern about metastases. This study aimed to evaluate the prevalence of bone metastases on staging prostate MRI and evaluate associations between their MRI features and clinical/pathologic characteristics.METHODSRetrospective, IRB-approved study of 3765 patients undergoing prostate MRI for newly diagnosed PCa between 2000 and 2014. The reference standard to calculate the prevalence of bone metastases was bone biopsy and/or ?1-year follow-up after MRI. In a subsample of 228 patients, the MRI characteristics of bone lesions were recorded by two radiologists independently. Associations between MRI and clinical/pathologic findings, including National Comprehensive Cancer Network (NCCN) risk categories, were calculated.RESULTS57/3765 patients (1.5%, 95% CI 1.2-2.0%) had bone metastases. No patient with NCCN low-risk PCa (Gleason < 7, PSA < 10 ng/mL, cT1-2a) had bone metastases. In the subsample, ?1 bone lesion was present on MRI in 74% (95% CI 0.67-0.79) and 72% (95% CI 0.66-0.78) of patients (R1 and R2). Larger lesion diameter (OR 1.33/1.19; p < 0.001 for both readers) and the absence of intralesional fat (OR 0.07/0.11; p = 0.004/0.002 for R1/R2) were significantly associated with bone metastases.CONCLUSIONBone lesions are common in prostate MRI, but only rarely represent metastases. MRI should be interpreted in the context of clinical features that influence the likelihood of metastatic disease.
| S-EPMC5247358 | biostudies-literature
Project description:BackgroundMedical image auto-segmentation is poised to revolutionize radiotherapy workflows. The quality of auto-segmentation training data, primarily derived from clinician observers, is of utmost importance. However, the factors influencing the quality of these clinician-derived segmentations have yet to be fully understood or quantified. Therefore, the purpose of this study was to determine the role of common observer demographic variables on quantitative segmentation performance.MethodsOrgan at risk (OAR) and tumor volume segmentations provided by radiation oncologist observers from the Contouring Collaborative for Consensus in Radiation Oncology public dataset were utilized for this study. Segmentations were derived from five separate disease sites comprised of one patient case each: breast, sarcoma, head and neck (H&N), gynecologic (GYN), and gastrointestinal (GI). Segmentation quality was determined on a structure-by-structure basis by comparing the observer segmentations with an expert-derived consensus gold standard primarily using the Dice Similarity Coefficient (DSC); surface DSC was investigated as a secondary metric. Metrics were stratified into binary groups based on previously established structure-specific expert-derived interobserver variability (IOV) cutoffs. Generalized linear mixed-effects models using Markov chain Monte Carlo Bayesian estimation were used to investigate the association between demographic variables and the binarized segmentation quality for each disease site separately. Variables with a highest density interval excluding zero - loosely analogous to frequentist significance - were considered to substantially impact the outcome measure.ResultsAfter filtering by practicing radiation oncologists, 574, 110, 452, 112, and 48 structure observations remained for the breast, sarcoma, H&N, GYN, and GI cases, respectively. The median percentage of observations that crossed the expert DSC IOV cutoff when stratified by structure type was 55% and 31% for OARs and tumor volumes, respectively. Bayesian regression analysis revealed tumor category had a substantial negative impact on binarized DSC for the breast (coefficient mean ± standard deviation: -0.97 ± 0.20), sarcoma (-1.04 ± 0.54), H&N (-1.00 ± 0.24), and GI (-2.95 ± 0.98) cases. There were no clear recurring relationships between segmentation quality and demographic variables across the cases, with most variables demonstrating large standard deviations and wide highest density intervals.ConclusionOur study highlights substantial uncertainty surrounding conventionally presumed factors influencing segmentation quality. Future studies should investigate additional demographic variables, more patients and imaging modalities, and alternative metrics of segmentation acceptability.
| S-EPMC10491357 | biostudies-literature
Project description:Introduction: Deep Learning (DL) is a machine learning technique that uses deep neural networks to create a model. The application areas of deep learning in radiation oncology include image segmentation and detection, image phenotyping, and radiomic signature discovery, clinical outcome prediction, image dose quantification, dose-response modeling, radiation adaptation, and image generation. In this review, we explain the methods used in DL and perform a literature review using the Medline database to identify studies using deep learning in radiation oncology. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later. Methods: A literature review was performed using PubMed/Medline in order to identify important recent publications to be synthesized into a review of the current status of Deep Learning in radiation oncology, directed at a clinically-oriented reader. The search strategy included the search terms "radiotherapy" and "deep learning." In addition, reference lists of selected articles were hand searched for further potential hits of relevance to this review. The search was conducted in April 2018, and identified studies published between 1997 and 2018, strongly skewed toward 2015 and later. Results: Studies using DL for image segmentation were identified in Brain (n = 2), Head and Neck (n = 3), Lung (n = 6), Abdominal (n = 2), and Pelvic (n = 6) cancers. Use of Deep Learning has also been reported for outcome prediction, such as toxicity modeling (n = 3), treatment response and survival (n = 2), or treatment planning (n = 5). Conclusion: Over the past few years, there has been a significant number of studies assessing the performance of DL techniques in radiation oncology. They demonstrate how DL-based systems can aid clinicians in their daily work, be it by reducing the time required for or the variability in segmentation, or by helping to predict treatment outcomes and toxicities. It still remains to be seen when these techniques will be employed in routine clinical practice.
| S-EPMC6779810 | biostudies-literature
Project description:BackgroundThe performance of magnetic resonance imaging (MRI), the effect of patient factors, and resulting surgical management in underserved and ethnically diverse breast cancer (BC) patient populations have been understudied.MethodsWe retrospectively analyzed the data of 1116 consecutive patients who were newly diagnosed with in situ or invasive BC with preoperative staging MRI. Non-index lesions (NILs) were defined as abnormal MRI findings with BI-RADS score of 4 or 5 in breast or axillary nodes not previously detected by conventional imaging. Occult cancers (OCs) were NILs found to be malignant by biopsy or surgery. Logistic regression was used to examine associations between probabilities of NILs or OCs and patient characteristics.ResultsStaging MRI detected NILs and OCs in 24% and 7.5% of patients, respectively. Of 1116 patients, 271 (24%) had 327 NILs, and 84 (7.5%) had 87 OCs. Follow-up information was available for 306 NILs. Ipsilateral breast NILs (n = 124) were seen in 115 patients (10.3%), with OCs (n = 51) seen in 48 patients (4.4%). Contralateral breast NILs (n = 134) were seen in 118 (10.6%) patients, with OCs (n = 20) seen in 20 patients (1.8%). Laterality (p < 0.001) and disease stage (p = 0.018) were associated with probability of OC. Patients without BRCA mutations had a significantly higher probability of having NILs (p = 0.003) but not OCs.ConclusionsOur study provides useful estimates of the rates of NILs and OCs anticipated in a younger, uninsured, ethnically diverse population. Prospective trials and larger pooled retrospective analyses are needed to define the long-term impacts of MRI staging after a BC diagnosis.
| S-EPMC7494176 | biostudies-literature
Project description:There is growing evidence supporting incorporating multiparametric (mp) magnetic resonance imaging (MRI) scans into risk stratification, active surveillance, and treatment paradigms for prostate cancer. The purpose of our study was to determine whether demographic disparities exist in staging MRI utilization for prostate cancer patients.An institutional database of 705 nonmetastatic prostate cancer patients treated with radiation therapy from 2005 through 2013 was used to identify patients undergoing versus not undergoing pretreatment diagnostic prostate mpMRI. Uni- and multivariable logistic regression evaluated the relationship of clinical and demographic characteristics with MRI utilization.All demographic variables assessed, except the other race category, were significantly associated with MRI utilization (all P < .05), including age (odds ratio [OR], 0.92), black race (OR, 0.51), poverty (OR, 0.53), closer distance to radiation facility (OR, 1.79), and nonprivate primary insurance (OR, 0.57) on univariable analysis, while clinical stage T3 (OR, 3.37) was the only clinical characteristic. On multivariable analysis stratified by D'Amico risk group, age remained significant across all risk groups, whereas the black versus white racial (OR, 0.21; 95% confidence interval, 0.08-0.55) and nonprivate versus private insurance type (OR, 0.37; 95% confidence interval, 0.16-0.86) disparities persisted in the low-risk group. Clinical stage T3 remained associated in the high-risk group. For race specifically, the percentages of whites, blacks, and others undergoing MRI in the overall cohort and by risk group were, respectively: overall, 80% (343/427), 68% (156/231), and 85% (40/47); low risk, 86%, 56%, and 63%; intermediate risk, 79%, 72%, and 95%; and high risk, 72%, 72%, and 100%.In this urban, academic center cohort, older patients across all risk groups and black or nonprivate insurance patients in the low risk group were less likely to undergo staging prostate MRI scans. Further research should investigate these differences to ensure equitable utilization across all demographic groups considering the burden of prostate cancer disparities.
| S-EPMC5514159 | biostudies-other
Project description:ImportanceProstate-specific membrane antigen (PSMA) demonstrates overexpression in prostate cancer and correlates with tumor aggressiveness. PSMA positron emission tomography (PET) is superior to conventional imaging for the metastatic staging of prostate cancer per current research but studies of second-generation PSMA PET radioligands for locoregional staging are limited.ObjectiveTo determine the accuracy of fluorine-18 PSMA-1007 PET/computed tomography (18F-PSMA-1007 PET/CT) compared to multiparametric magnetic resonance imaging (MRI) in the primary locoregional staging of intermediate-risk and high-risk prostate cancers.Design, setting, and participantsThe Next Generation Trial was a phase 2 prospective validating paired cohort study assessing the accuracy of 18F-PSMA-1007 PET/CT and MRI for locoregional staging of prostate cancer, with results of histopathologic examination as the reference standard comparator. Radiologists, nuclear medicine physicians, and pathologists were blinded to preoperative clinical, pathology, and imaging data. Patients underwent all imaging studies and radical prostatectomies at 2 tertiary care hospitals in Alberta, Canada. Eligible participants included men with intermediate-risk or high-risk prostate cancer who consented to radical prostatectomy. Participants who underwent radical prostatectomy were included in the final analysis. Patients were recruited between March 2022 and June 2023, and data analysis occurred between July 2023 and December 2023.ExposuresAll participants underwent both 18F-PSMA-1007 PET/CT and MRI within 2 weeks of one another and before radical prostatectomy.Main outcomes and measuresThe primary outcome was the correct identification of the prostate cancer tumor stage by each imaging test. The secondary outcomes were correct identification of the dominant nodule, laterality, extracapsular extension, and seminal vesical invasion.ResultsOf 150 eligible men with prostate cancer, 134 patients ultimately underwent radical prostatectomy (mean [SD] age at prostatectomy, 62.0 [5.7] years). PSMA PET was superior to MRI for the accurate identification of the final pathological tumor stage (61 [45%] vs 38 [28%]; P = .003). PSMA PET was also superior to MRI for the correct identification of the dominant nodule (126 [94%] vs 112 [83%]; P = .01), laterality (86 [64%] vs 60 [44%]; P = .001), and extracapsular extension (100 [75%] vs 84 [63%]; P = .01), but not for seminal vesicle invasion (122 [91%] vs 115 [85%]; P = .07).Conclusions and relevanceIn this phase 2 prospective validating paired cohort study, 18F-PSMA-1007 PET/CT was superior to MRI for the locoregional staging of prostate cancer. These findings support PSMA PET in the preoperative workflow of intermediate-risk and high-risk tumors.
| S-EPMC11217889 | biostudies-literature
Project description:OBJECTIVE:To determine if magnetic resonance imaging (MRI)/ultrasound fusion-targeted prostate biopsy (TB) would lead to increased recommendations of aggressive radiotherapy treatments for higher risk prostate cancer compared to systematic biopsy (SB) results. METHODS:Clinicopathologic data of 533 men who underwent both TB and SB from 2014 to 2017 was analyzed. TB was performed in addition to SB in patients with detection of MRI suspicious lesions. Three patient cohorts were established: (1) biopsy naïve (80/533, 15.0%), (2) active surveillance (185/533, 34.7%), and (3) prior negative biopsy (268/533, 50.3%). Cancer risk categorical criteria were established with recommended radiotherapy treatment for each. Variation of risk classification due to biopsy method for all patients and within each cohort was analyzed using either a chi-squared statistic or Fisher's exact test. McNemar's pairwise analyses were performed for all risk categories between TB and SB to assess the effects of TB on high-risk cancer identification and subsequent radiotherapy recommendations. RESULTS:Number of patients within cancer risk categories (1. "No Cancer or Low-Risk"; 2. "More Favorable Intermediate-Risk"; 3. "Less Favorable Intermediate-Risk"; 4. "High-Risk") varied significantly based on TB and SB pathology among all patients combined (P <.0001), in cohort 2 (P?=?.0005), and in cohort 3 (P <0.0001). Further, among all patients, TB increased cancer risk classification and correspondingly would result in more aggressive radiotherapy recommendations: "No Cancer or Low-Risk" to "Less Favorable Intermediate-Risk" (30/343, P <0.0001) and "No Cancer or Low-Risk" to "High-Risk" (31/353, P <.0001). CONCLUSION:Among men with prostate cancer, TB commonly led to reclassification to a higher risk group, which is accompanied by more aggressive radiotherapy treatment recommendations when compared with SB findings alone.
| S-EPMC6295220 | biostudies-literature
Project description:BACKGROUND: Radiotherapy to the head and neck regions can result in serious consequences to the temporomandibular joint (TMJ) and chewing muscles. Magnetic resonance imaging (MRI) demonstrates soft-tissue alterations after radiotherapy, such as morphology and signal intensity. OBJECTIVE: The purpose of this review is to critically and systematically analyse the available evidence regarding the masticatory muscles alterations, as demonstrated on MRI, after radiotherapy for head and neck cancer. DATA SOURCES: Electronic search of MEDLINE, EMBASE, EBM reviews and Scopus. INCLUSION CRITERIA: Reports of any study design investigating radiation-induced changes in masticatory muscles after radiotherapy in patients with head and neck cancer were included. RESULTS AND SYNTHESIS METHODS: An electronic database search resulted in 162 papers. Sixteen papers were initially selected as potentially relevant studies; however, only four papers satisfied all inclusion criteria. The included papers focused on the MRI appearance of masticatory muscles following radiotherapy protocol. Two papers reported outcome based on retrospective clinical and imaging records, whereas the remaining two papers were case reports. Irradiated muscles frequently show diffuse increase in T2 signal and post-gadolinium enhancement post-irradiation. Also, muscle size changes were reported based on subjective comparison with the contralateral side. The quality of all included papers was considered poor with high risk of bias. CONCLUSION: There is no evidence that MRI interpretations indicate specific radiation-induced changes in masticatory muscles. There is a clear need for a cohort study comparing patients with pre- and post-radiotherapy MRI.
| S-EPMC3651244 | biostudies-other