Evaluation of Botox treatment in patients with chronic scrotal pain: Protocol for a randomized double-blinded control trial.

Background: Chronic scrotal pain is a common condition with a prevalence of 2.5-4.8% in male outpatients. Up to 40% of these patients report depressive symptoms and many feel isolated. Minimal invasive treatment is lacking, while spermatic cord injections of Botox® (BTX) have been proposed to offer long-term pain relief. Study Design: This research protocol comprises a prospective multicentre, randomized, double-blinded clinical trial drawing patients from other urological departments in the region of Southern Denmark. End Points: The primary end point will be reduction in pain evaluated by visual analogue score for pain at 3 months. Secondary end point will be length of effect of BTX injections along with changes in quality of life. Patients and Methods: The study will include 50 patients for randomization to either spermatic cord block with 100 IE BTX or sterile saline. All patients will prior to randomization undergo physical examination and will be asked to fulfil multiple questionnaires regarding pain and impact in daily life, that is, (1) visual analogue score for pain, (2) quality of life (EQ-5D-5L), (3) Chronic Prostatitis Symptom Index (NIH-CPSI), (4) ICD-10 depression questionnaire (MDI), (5) Likert global assessment scale, and (6) International Index of Erectile Function questionnaire. Physical examination and fulfilment of the questionnaires will be repeated multiple times throughout the study period of 12 weeks. After this time point, patients will be unblinded, and the control arm will be given the opportunity of cross-over.

Protocol of a randomised, controlled trial comparing immediate curative therapy with conservative treatment in men aged ≥75 years with non-metastatic high-risk prostate cancer (SPCG 19/GRand-P).

BACKGROUND: Older men (aged ≥75 years) with high risk, non-metastatic prostate cancer (PCa) are increasingly treated with curative therapy (surgery or radiotherapy). However, it is unclear if curative therapy prolongs life and improves health-related quality of life (HRQoL) in this age group compared to conservative therapy, which has evolved considerably during the last decade. STUDY DESIGN: The Scandinavian Prostate Cancer Group (SPCG) 19/Norwegian Get-Randomized Research Group-Prostate (GRand-P) is a randomised, two-armed, controlled, multicentre, phase III trial carried out at study centres in Norway, Denmark, Finland, and Sweden. ENDPOINTS: The primary endpoints are overall survival and HRQoL (burden of disease scale, European Organisation for the Research and Treatment of Cancer [EORTC] Elderly Cancer patients). Secondary endpoints are PCa-specific survival, metastasis-free survival, role-functioning scale (EORTC quality of life questionnaire 30-item core), urinary irritative/obstructive scale (26-item Expanded Prostate Cancer Index Composite [EPIC-26]), bowel scale (EPIC-26), intervention-free survival, PCa morbidity, use of secondary and tertiary systemic therapies, mean quality-adjusted life-years (QALYs), and mean total healthcare costs. PATIENTS AND METHODS: A total of 980 men (aged ≥75 years) with non-metastatic, high-risk PCa will initially be screened with Geriatric 8 (G8) health status screening tool and Mini-COG© brief cognitive test. Participants identified by G8 as 'fit' or 'frail' will be randomised (ratio 1:1) to either immediate curative therapy (radiotherapy or prostatectomy) or conservative therapy (endocrine therapy or observation). Participants who are unable or unwilling to participate in randomisation will be enrolled in a separate observation group. Randomised patients will be followed for 10 years. TRIAL REGISTRATION: Ethics approval has been granted in Norway (457593), Denmark (H-22051998), Finland (R23043) and Sweden (Dnr 2023-05296-01). The trial is registered on Clinicaltrials.org (NCT05448547).

Epidemiological description and trajectories of patients with prostate cancer in Denmark: an observational study of 7448 patients.

OBJECTIVE: Identification of patients at high risk of aggressive prostate cancer is a major clinical challenge. With the view of developing artificial intelligence-based methods for identification of these patients, we are constructing a comprehensive clinical database including 7448 prostate cancer (PCa) Danish patients. In this paper we provide an epidemiological description and patients' trajectories of this retrospective observational population, to contribute to the understanding of the characteristics and pathways of PCa patients in Denmark. RESULTS: Individuals receiving a PCa diagnosis during 2008-2014 in Region Southern Denmark were identified, and all diagnoses, operations, investigations, and biochemistry analyses, from 4 years prior, to 5 years after PCa diagnosis were obtained. About 85.1% were not diagnosed with metastatic PCa during the study period (unaggressive PCa); 9.2% were simultaneously diagnosed with PCa and metastasis (aggressive-advanced PCa), while 5.7% were not diagnosed with metastatic PCa at first, but they were diagnosed with metastasis at some point during the 5 years follow-up (aggressive-not advanced PCa). Patients with unaggressive PCa had more clinical investigations directly related to PCa detection (prostate ultrasounds and biopsies) during the 4 years prior to PCa diagnosis, compared to patients with aggressive PCa, which may have contributed to the early detection of PCa.

Danish Prostate Cancer Consortium Study 1 (DPCC-1) protocol: Multicentre prospective validation of the urine-based three-microRNA biomarker model uCaP.

INTRODUCTION: The primary objective of the Danish Prostate Cancer Consortium Study 1 (DPCC-1) is to provide validation for a novel urine-based microRNA biomarker, called uCaP, for a diagnosis of prostate cancer. METHODS AND ANALYSIS: Eligible participants are biopsy naïve men aged ≥18 years with prostate-specific antigen (PSA) levels ≥3 ng/mL, who are referred to prostate MRI due to suspicion of PC at one of the following three major urology/uroradiology centers: Aarhus University Hospital, Herlev & Gentofte University Hospital, or Odense University Hospital, where MRI and targeted biopsy are implemented in clinical use. Exclusion criteria include previous diagnosis of urogenital cancer, contraindication to MRI, gender reassignment treatment or PSA level >20 ng/mL. The participants will be asked to donate a urine sample in connection with their MRI. The study is observational, uses a diagnostic accuracy testing setup and will integrate into the current diagnostic pathway.We will measure the levels of the three microRNAs in the uCaP model (miR-222-3 p, miR-24-3 p and miR-30c-5p) in extracellular vesicle-enriched cell-free urine samples, to assess if uCaP can improve specificity and retain sensitivity for International Society of Urological Pathology Grade Group ≥2 PC, when used as a reflex test to PSA ≥3 ng/mL. We hypothesise that uCaP can improve selection for prostate MRI and reduce the number of unnecessary scans and biopsies. ETHICS AND DISSEMINATION: This study is approved by the Central Denmark Region Committee on Health Research Ethics (reference number: 1-10-72-85-22). All participants will provide written informed consent. Study results will be published in peer-reviewed journals and presented in scientific meetings. TRIAL REGISTRATION NUMBER: NCT05767307 at clinicaltrials.gov.

A randomised trial of [18F]PSMA-1007-PET/CT versus NaF-PET/CT for staging primary prostate cancer: A trial protocol.

Background: Prostate-specific membrane antigen (PSMA)-positron emission tomography/contrast-enhanced computed tomography (PET/CT) is a sensitive imaging modality for prostate cancer (PCa). Due to lack of knowledge of the patient benefit, PSMA-PET/CT is not yet recommended in the European guidelines for staging and treatment planning of patients with newly diagnosed PCa. We will investigate the potential difference in progression-free survival (PFS) and quality of life (QoL) of using PSMA-PET/CT versus sodium fluoride (NaF)-PET/CT for staging and treatment planning in patients with newly diagnosed PCa. Study Design: This is a prospective randomised controlled multicentre trial carried out at three centres in the Region of Southern Denmark. Endpoints: The primary endpoint is PFS. Secondary endpoints are residual disease, stage migration, impact on treatment strategies, stage distribution, QoL and diagnostic accuracy measures. Patients and Methods: Patients eligible for the study have newly diagnosed unfavourable intermediate- or high-risk PCa. A total of 448 patients will be randomised 1:1 into two groups: (A) a control group staged with Na[18F]F-PET/CT and (B) an intervention group staged with [18F]PSMA-1007-PET/CT. A subgroup in the intervention group will have a supplementary blinded Na[18F]F-PET/CT performed for the purpose of performing accuracy analyses. QoL will be assessed at baseline and with regular intervals (3-12 months) during the study period. Treatment decisions are achieved at multidisciplinary team conferences based on the results of the respective scans and according to current Danish guidelines. Trial Registration: The Regional Committees on Health Research Ethics for Southern Denmark (S-20190161) and the Danish Medicines Agency (EudraCT Number 2021-000123-12) approved the study, and it has been registered on clinicaltrials.gov (Record 2020110469).

A national test of dyslexia.

Different definitions and tests of dyslexia can cause unfairness and make life difficult for people with dyslexia as well as for the professionals. In 2012, the Danish government decided to support the fight against dyslexia. The government issued a public tender for the development of "a standardized, electronically administered test of dyslexia for use […] from primary Grade 3 and up through all educational levels to 5-year university education." The present paper reports from the development of this National Dyslexia Test. The paper focuses on the definition of dyslexia and the composition, reliability, and validity of the test. Data from the development of the test demonstrate the psychometric properties of the test. Reliability was indicated by a high agreement between the two (computer-administered) measures that are part of the test. External convergent validity was indicated by a high agreement between test results and results from prior practice and by agreement between test results and reading comprehension of educational texts. The paper concludes with a discussion of the practical uses and potential issues with the test since its release in 2015.

Prostate cancer.

This review investigates prostate cancer which with approx. 4,500 new cases annually is the most frequent male cancer, and the incidence is expected to increase due to demographic developments. Prostate cancer can have a natural history without progression to symptomatic or fatal disease, which is why overdiagnosis is one of the disease's biggest challenges. In contrast to potential curable localized clinically significant disease, this is not the case after metastasis. Fortunately, new treatments, and not least combinations thereof, have increased both lifespan and quality of life in these patients significantly.

Prevalence of prostate cancer in men with haematuria: a systematic review and meta-analysis.

OBJECTIVES: To investigate the prevalence of prostate cancer in men attending evaluation for haematuria, as this could help healthcare providers to determine whether men with haematuria should have prostate examinations performed. METHODS: The study was performed according to a pre-specified protocol uploaded to the International Prospective Register of Systematic Reviews (PROSPERO; CRD42022299383). A systematic search of MEDLINE, Ovid and Google Scholar was performed in December 2021. Two independent researchers evaluated all titles, available abstracts, and full texts. We included studies on adult men (aged ≥18 years) describing haematuria and prostate cancer. RESULTS: We screened 4252 titles and abstracts when available and assessed 350 studies in full text. In total, 65 studies were included and 42 was summarised in a meta-analysis. In total, 18 752 men with haematuria were included, and the pooled prevalence (95% confidence interval [CI]) of prostate cancer was 3.0% (2.0-4.1%). In men with macroscopic haematuria, the pooled prevalence (95% CI) of prostate cancer was 5.9% (2.9-9.9%; n = 265/5373). In men with microscopic haematuria, the pooled prevalence (95% CI) of prostate cancer was 1.4% (0.8-2.2%; n = 71/6642). CONCLUSION: Our findings indicate that the prevalence of prostate cancer is considerable in men attending evaluation for haematuria. Therefore, digital rectal examination and prostate-specific antigen measurement should become a standard procedure for all men with haematuria, especially for men with macroscopic haematuria.

Introduction of free-hand MRI-guided transperineal prostate biopsies as an outpatient procedure.

INTRODUCTION: Direct biopsy of the prostate is used for diagnosing prostate cancer and most prostate biopsies are performed transrectally with ultrasonic guidance (TRUS-BX). The transrectal approach carries a risk of sepsis as bacteria may transfer directly into the prostate from the rectum. Approximately 6% of the patients will be hospitalised within seven days after TRUX-BX. Increasing antibiotic resistance has spurred a renewed interest in the transperineal approach (TP-BX). Aseptic TP-BX may be performed, significantly reducing the risk of infection. We described the first Danish experience with multiparametric MRI-guided freehand TP-BX. METHODS: Men scheduled for TP-BX were included. Patient age, prostate-specific antigen level, previous biopsy history, weight and height were recorded. We employed a visual analogue scale (VAS) for the various procedure parts and the patients rated their satisfaction. Complications and International Society of Urological Pathology scores were recorded and cancer detection rates calculated. RESULTS: A total of 143 men had TP-BX performed in a consecutive series. The cancer detection rate was 81.8% (95% confidence interval: 74.5-87.8%). The procedure was well tolerated with a median VAS of 2 (range: 0-7), and patients expressed a high degree of satisfaction with the procedure. One patient was hospitalised due to infection. CONCLUSION: TP-BX is well tolerated and feasible as an outpatient procedure performed in local anaesthesia. Transperineal biopsies have a low risk of infection. FUNDING: none. TRIAL REGISTRATION: not relevant.

Transperineal biopsy of the prostate.

Prostate needle biopsies are an essential step in the diagnostic evaluation of prostate cancer. The conventional ultrasound-guided transrectal needle biopsy entails a significant risk of infection, which with increasing antibiotic resistance is thought to increase in the future. This has sparked a renewed interest in transperineal prostate biopsies, as this approach avoids the multiple passages of the rectal mucosa, thus reducing the risk of infection significantly. This review describes the devolvement, technical aspects, and current recommendations of transperineal biopsies.

Implementation of sacral neuromodulation for urinary indications. A Danish prospective study during the initial 15 months of a new service in a tertiary referral hospital.

OBJECTIVE: Sacral neuromodulation (SNM) is a well-established treatment modality for idiopathic overactive bladder and urgency incontinence, idiopathic fecal incontinence and non-obstructive urinary retention. This study describes the start-up phase of establishing the SNM service. Primary objective: To investigate the patient-reported outcome measures of SNM on lower urinary tract dysfunction symptoms. Secondary objectives: To investigate bowel function, sexual satisfaction and to monitor SNM safety. MATERIALS AND METHODS: Twenty-two patients with refractory idiopathic and neurogenic lower urinary tract dysfunction were offered a two-stage test-phase procedure and SNM device implantation. On completing the study, the patients rated their satisfaction with the treatment using a five-point Likert scale and a bother score of urinary, bowel and sexual symptoms on a scale of 1-10 (the worst). Their complications were assessed. RESULTS: Nineteen patients (86%) were responders during the test phase and had the pulse generator implanted. Seventeen patients were very satisfied/satisfied. A statistically significant change in urinary symptoms bother score was observed in the idiopathic and neurogenic patients, a reduction from 10 to 4 (p = .0057) and 10 to 3 (p = .014), respectively. Eleven patients (58%) had symptoms from two or three pelvic compartments. Nine patients (47%) had complications. All but one event was resolved. CONCLUSIONS: SNM is safe in this heterogeneous group of patients with refractory lower urinary tract dysfunction of various etiologies. A substantial improvement was observed in the pelvic organ dysfunction, demanding a multidisciplinary approach. More studies are required to standardize the evaluation of the subjective and objective outcomes of SNM.

Introduction of salvage prostatectomy in Denmark: the initial experience.

OBJECTIVE: To introduce salvage prostatectomy in Denmark. Prior to this, no national curative treatment for recurrent prostate cancer following radiation therapy existed in Denmark. This pilot study represent our initial experiences and the feasibility of performing salvage robot-assisted radical prostatectomy for true local, high-risk recurrence after initial therapy with external beam radiation for high-risk prostate cancer. RESULTS: Five patients underwent sRARP between April 2020 and July 2021. All patients were discharged within 48 h and no major complications were observed within 3 months. All patients had unmeasurable PSA (< 0.1 ng/ml) at follow-up 6 months after surgery. One patient with longer follow-up than 6 months experienced biochemical recurrence. At 3-months follow-up all patients reported considerable incontinence, at 6-month follow-up, pad usage decreased to 1 or 2 pads daily. Based on our initial results, the idea to introduce sRARP as a nationwide option remains and further patients will be included to establish the true role of sRARP in patients with recurrence after primary radiotherapy for PCa.

Lateralization of word and face processing in developmental dyslexia and developmental prosopagnosia.

In right-handed adults, face processing is lateralized to the right hemisphere and visual word processing to the left hemisphere. According to the many-to-many account (MTMA) of functional cerebral organization this lateralization pattern is partly dependent on the acquisition of literacy. Hence, the MTMA predicts that: (i) processing of both words and faces should show no or at least less lateralization in individuals with developmental dyslexia compared with controls, and (ii) lateralization in word processing should be normal in individuals with developmental prosopagnosia whereas lateralization in face processing should be absent. To test these hypotheses, 21 right-handed adults with developmental dyslexia and 21 right-handed adults with developmental prosopagnosia performed a divided visual field paradigm with delayed matching of faces, words and cars. Contrary to the predictions, we find that lateralization effects in face processing are within the normal range for both developmental dyslexics and prosopagnosics. Moreover, the group with developmental dyslexia showed right hemisphere lateralization for word processing. We argue that these findings are incompatible with the specific predictions of the MTMA.

Plasma Chemokine C-C Motif Ligand 2 as a Potential Biomarker for Prostate Cancer.

PURPOSE: Serum levels of the polypeptide chemokine C-C motif ligand 2 (CCL2) have previously shown potential as a prostate cancer diagnostic and prognostic biomarker. Plasma CCL2 levels may be superior to serum levels as a biomarker because of their potentially lower signal-to-noise ratio. MATERIALS AND METHODS: Before initiating a large comparative study of plasma and serum CCL2 levels, we performed a prospective, diagnostic pilot study Of 133 individuals from a clinically relevant population. CCL2 plasma levels were measured using a validated assay kit. Plasma was obtained independently of digital rectal examination. RESULTS: In this pilot study, we found no relationship between CCL2 plasma values and risk of proven prostate cancer, whereas previous studies found a strong diagnostic relationship between CCL2 serum values and prostate cancer. CONCLUSION: Our contribution to the existing literature strengthens the idea that early in the pathological process, CCL2 mainly circulates in large, membrane-enclosed compartments, whereas plasma CCL2 levels increase markedly during disease progression. We conclude that whereas plasma CCL2 levels are not useful as a diagnostic measure, a ratio of CCL2 plasma to serum levels may prove useful as a marker of disease progression, which warrants further study.

Remembering sentences is not all about memory: Convergent and discriminant validity of syntactic knowledge and its relationship with reading comprehension.

Recent studies have found correlations between sentence-level tests and reading comprehension. However, the task demands of sentence-level tests are not well understood. The present study investigated syntactic knowledge as a construct by examining the convergent and discriminant validity of two sentence-level tasks, sentence comprehension and sentence repetition, designed to test syntactic knowledge and their relation with reading comprehension. Results from 86 Grade 6 students showed that the syntax tests were more highly correlated with each other than with tests of working memory and vocabulary. This suggests that the syntax measures tap into a set of skills that are at least partially separate from these other cognitive constructs. Furthermore, syntactic knowledge explained unique variance in reading comprehension beyond controls. The syntax tasks were working memory dependent, but working memory was not the primary reason why syntax tasks are correlated with reading comprehension.

Tissue distribution of ethanol after intraprostatic injection using a porous needle.

Purpose: To develop a safe and precise method for intraprostatic injection, and to establish correlation between the volume of ethanol injectate and the volume of subsequent infiltrated prostate tissue. Materials and methods: We performed intraprostatic injection of 96% ethanol using a needle which has a segment of its wall made of capillary membrane with hundreds of pores in an acute and chronic canine experiment, in heart-beating cadaveric organ donors, and in a xenograft model of human prostate cancer. Whole mount tissue sections were used for three-dimensional reconstruction of the necrotic lesions and calculation of their volumes. Results: The ethanol injection resulted in oval shaped lesions of well-delineated coagulative necrosis. In both healthy human and canine prostates, the prostatic pseudocapsule and neurovascular bundle remained intact without evidence of disruption. There was a linear correlation between administered volume of ethanol and the volume of necrotic lesion. Regression analysis showed strong correlation in the acute canine experiments and in experiments performed on xenografts of human prostate cancer. A formula was calculated for each experiment to estimate the relationship between the injected volume and the volume of infiltrated prostate tissue area. Conclusions: Intraprostatic injection using a porous needle allows for effective and predictable tissue distribution of the injectate in the prostate. Through varying the volume of the agent injected and use of needles with a different length of the porous segment, the volume of infiltrated tissue could be adjusted allowing for targeted focal treatment.

Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients.

OBJECTIVE: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUVmax, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. METHODS: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using 18F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUVmax were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model. RESULTS: Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUVmax (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not. CONCLUSION: AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUVmax and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.

Safety and Effects of Football in Skeletal Metastatic Prostate Cancer: a Subgroup Analysis of the FC Prostate Community Randomised Controlled Trial.

BACKGROUND: Skeletal metastatic disease excludes many cancer patients from participating in exercise and physical activity due to safety concerns. Empirical evidence from high-quality trials is warranted to guide clinicians and patients. OBJECTIVE: To evaluate the safety and potential benefits of high-impact aerobic exercise in patients with prostate cancer with skeletal metastases. DESIGN: Exploratory subgroup analysis of a pragmatic, multicentre, parallel randomised controlled trial. SETTING: The trial recruited 214 patients from five hospital urological departments in Denmark. PARTICIPANTS: Patients with prostate cancer with skeletal metastases (n = 41). INTERVENTION: Six months of football training twice weekly at a local club or usual care. Both groups received brief information on physical activity recommendations at the time of randomisation. MAIN OUTCOME(S) AND MEASURE(S): Safety, defined as falls, fractures and hospital admissions. Effects were evaluated on the primary outcome (prostate cancer-specific quality of life) and secondary outcomes (lean body mass, fat mass, hip and spine bone mineral density, and general physical and mental health). RESULTS: The original trial comprised 214 participants, 41 of whom had skeletal metastases at enrolment. Of these, 22 were allocated to football and 19 to usual care. The trial retention rate was 95% at 12 weeks and 88% at 6 months. Football participants attended 13 sessions on average at 12 weeks and 23 at 6 months. There were two falls, one in each group after 6 months, and no fractures. There were four unplanned hospital admissions in the study period, all four in the usual care group. Statistically significant between-group difference was observed in the primary outcome change in prostate cancer-specific quality of life at 12 weeks (7.6 points [95% CI 0.5 to 15.0]; P = 0.038). No statistical changes were found in the secondary outcomes. CONCLUSION: The analysis showed that football training was safe in patients with skeletal metastatic prostate cancer and significantly improved quality of life. Larger analyses and/or trials are warranted to confirm the safety of exercise more broadly in cancer patients with skeletal metastatic disease. TRIAL REGISTRATION: ClinicalTrials.gov, NCT02430792 . Date of registration 30 April 2015.

Face recognition in developmental dyslexia: evidence for dissociation between faces and words.

Developmental dyslexia is primarily a reading disorder, but recent studies have indicated that face processing problems may also be present. Using a case-series approach, we tested face recognition and visual word recognition in 24 high school students diagnosed with developmental dyslexia. Contrary to previous findings, no face recognition problems were found on the group-level. Rather, a significant classical dissociation with impaired word reading and normal face recognition was demonstrated on a group-level and for six individuals with developmental dyslexia. However, four individuals with dyslexia did show face recognition problems. Thus, while problems in face recognition can be present in developmental dyslexia, the dissociation strongly suggests that face recognition can also be preserved. Combined with previously reported dissociations between face and word recognition in developmental prosopagnosia, this constitutes a double dissociation.

Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival.

INTRODUCTION: Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. METHODS: A group of 399 patients with biopsy-proven PCa who had undergone 18 F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated. RESULTS: The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117; p = .045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111; p = .63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival. CONCLUSION: This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.