Adequate detection of the histopathological extraprostatic extension (EPE) of prostate cancer (PCa) remains a challenge using conventional radiomics on 3 Tesla multiparametric magnetic resonance ...imaging (3T mpMRI). This study focuses on the assessment of artificial intelligence (AI)-driven models with innovative MRI radiomics in predicting EPE of prostate cancer (PCa) at a lesion-specific level. With a dataset encompassing 994 lesions from 794 PCa patients who underwent robot-assisted radical prostatectomy (RARP) at two Dutch hospitals, the study establishes and validates three classification models. The models were validated on an internal validation cohort of 162 lesions and an external validation cohort of 189 lesions in terms of discrimination, calibration, net benefit, and comparison to radiology reporting. Notably, the achieved AUCs ranged from 0.86 to 0.91 at the lesion-specific level, demonstrating the superior accuracy of the random forest model over conventional radiological reporting. At the external test cohort, the random forest model was the best-calibrated model and demonstrated a significantly higher accuracy compared to radiological reporting (83% vs. 67%, p = 0.02). In conclusion, an AI-powered model that includes both existing and novel MRI radiomics improves the detection of lesion-specific EPE in prostate cancer.
Background: Diagnostic pathways for prostate cancer (PCa) balance detection rates and burden. MRI impacts biopsy indication and strategy. Methods: A prospectively collected cohort database (N = 496) ...of men referred for elevated PSA and/or abnormal DRE was analyzed. All underwent biparametric MRI (3 Tesla scanner) and ERSPC prostate risk-calculator. Indication for biopsy was PIRADS ≥ 3 or risk-calculator ≥ 20%. Both targeted (cognitive-fusion) and systematic cores were combined. A hypothetical full-MRI-based pathway was retrospectively studied, omitting systematic biopsies in: (1) PIRADS 1–2 but risk-calculator ≥ 20%, (2) PIRADS ≥ 3, receiving targeted biopsy-cores only. Results: Significant PCa (GG ≥ 2) was detected in 120 (24%) men. Omission of systematic cores in cases with PIRADS 1–2 but risk-calculator ≥ 20%, would result in 34% less biopsy indication, not-detecting 7% significant tumors. Omission of systematic cores in PIRADS ≥ 3, only performing targeted biopsies, would result in a decrease of 75% cores per procedure, not detecting 9% significant tumors. Diagnosis of insignificant PCa dropped by 52%. PCa undetected by targeted cores only, were ipsilateral to MRI-index lesions in 67%. Conclusions: A biparametric MRI-guided PCa diagnostic pathway would have missed one out of six cases with significant PCa, but would have considerably reduced the number of biopsy procedures, cores, and insignificant PCa. Further refinement or follow-up may identify initially undetected cases. Center-specific data on the performance of the diagnostic pathway is required.
Selecting patients with peritoneal metastases from colorectal cancer (CRCPM) who might benefit from cytoreductive surgery followed by hyperthermic intraperitoneal chemotherapy (CRS-HIPEC) is ...challenging. Computed tomography generally underestimates the peritoneal tumor load. Diagnostic laparoscopy is often used to determine whether patients are amenable for surgery. Magnetic resonance imaging (MRI) has shown to be accurate in predicting completeness of CRS. The aim of this study is to determine whether MRI can effectively reduce the need for surgical staging.
The study is designed as a multicenter randomized controlled trial (RCT) of colorectal cancer patients who are deemed eligible for CRS-HIPEC after conventional CT staging. Patients are randomly assigned to either MRI based staging (arm A) or to standard surgical staging with or without laparoscopy (arm B). In arm A, MRI assessment will determine whether patients are eligible for CRS-HIPEC. In borderline cases, an additional diagnostic laparoscopy is advised. The primary outcome is the number of unnecessary surgical procedures in both arms defined as: all surgeries in patients with definitely inoperable disease (PCI > 24) or explorative surgeries in patients with limited disease (PCI < 15). Secondary outcomes include correlations between surgical findings and MRI findings, cost-effectiveness, and quality of life (QOL) analysis.
This randomized trial determines whether MRI can effectively replace surgical staging in patients with CRCPM considered for CRS-HIPEC.
Registered in the clinical trials registry of U.S. National Library of Medicine under NCT04231175 .
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Background
Prebiopsy magnetic resonance imaging (MRI) increases the detection rate of clinically significant prostate cancer (csPCa). Prostate‐specific membrane antigen‐positron emission ...tomography/computed tomography (PSMA PET/CT) maximum standardized uptake value (SUVmax) of the prostate may offer additional value in predicting the likelihood of csPCa in biopsy.
Methods
A single‐center cohort study involving patients with biopsy‐proven PCa who underwent both MRI and PSMA PET/CT between 2020 and 2021. Logistic regression models were developed for International Society of Urological Pathology (ISUP) Grade Group (GG) ≥ 2 and GG ≥ 3 using noninvasive prebiopsy parameters: age, (log‐)prostate‐specific antigen (PSA) density, PI‐RADS 5 lesion presence, extraprostatic extension (EPE) on MRI, and SUVmax of the prostate. Models with and without SUVmax were compared using Likelihood ratio tests and area under the curve (AUC). DeLong's test was used to compare the AUCs.
Results
The study included 386 patients, with 262 (68%) having ISUP GG ≥ 2 and 180 (47%) having ISUP GG ≥ 3. Including SUVmax significantly improved both models' goodness of fit (p < 0.001). The GG ≥ 2 model had a higher AUC with SUVmax 89.16% (95% confidence interval CI: 86.06%–92.26%) than without 87.34% (95% CI: 83.93%–90.76%) (p = 0.026). Similarly, the GG ≥ 3 model had a higher AUC with SUVmax 82.51% (95% CI: 78.41%–86.6%) than without 79.33% (95% CI: 74.84%–83.83%) (p = 0.003). The SUVmax inclusion improved the GG ≥ 3 model's calibration at higher probabilities.
Conclusion
SUVmax of the prostate on PSMA PET/CT potentially improves diagnostic accuracy in predicting the likelihood of csPCa in prostate biopsy.
Background
Pelvic morphological parameters on magnetic resonance imaging (MRI), such as the membranous urethral length (MUL), can predict urinary incontinence after radical prostatectomy but are ...prone to interobserver disagreement. Our objective was to improve interobserver agreement among radiologists in measuring pelvic parameters using deep learning (DL)-based segmentation of pelvic structures on MRI scans.
Methods
Preoperative MRI was collected from 167 prostate cancer patients undergoing radical prostatectomy within our regional multicentric cohort. Two DL networks (nnU-Net) were trained on coronal and sagittal scans and evaluated on a test cohort using an 80/20% train-test split. Pelvic parameters were manually measured by three abdominal radiologists on raw MRI images and with the use of DL-generated segmentations. Automated measurements were also performed for the pelvic parameters. Interobserver agreement was evaluated using the intraclass correlation coefficient (ICC) and the Bland–Altman plot.
Results
The DL models achieved median Dice similarity coefficient (DSC) values of 0.85–0.97 for coronal structures and 0.87–0.98 for sagittal structures. When radiologists used DL-generated segmentations of pelvic structures, the interobserver agreement for sagittal MUL improved from 0.64 (95% confidence interval 0.28–0.83) to 0.91 (95% CI 0.84–0.95). Furthermore, there was an increase in ICC values for the obturator internus muscle from 0.74 (95% CI 0.42–0.87) to 0.86 (95% CI 0.75–0.92) and for the levator ani muscle from 0.40 (95% CI 0.05–0.66) to 0.61 (95% CI 0.31–0.78).
Conclusions
DL-based automated segmentation of pelvic structures improved interobserver agreement in measuring pelvic parameters on preoperative MRI scans.
Relevance statement
The implementation of deep learning segmentations allows for more consistent measurements of pelvic parameters by radiologists. Standardized measurements are crucial for incorporating these parameters into urinary continence prediction models.
Key points
• DL-generated segmentations improve interobserver agreement for pelvic measurements among radiologists.
• Membranous urethral length measurement improved from substantial to almost perfect agreement.
• Artificial intelligence enhances objective pelvic parameter assessment for continence prediction models.
Graphical Abstract
Summary Background Case series suggest that laparoscopic peritoneal lavage might be a promising alternative to sigmoidectomy in patients with perforated diverticulitis. We aimed to assess the ...superiority of laparoscopic lavage compared with sigmoidectomy in patients with purulent perforated diverticulitis, with respect to overall long-term morbidity and mortality. Methods We did a multicentre, parallel-group, randomised, open-label trial in 34 teaching hospitals and eight academic hospitals in Belgium, Italy, and the Netherlands (the Ladies trial). The Ladies trial is split into two groups: the LOLA group comparing laparoscopic lavage with sigmoidectomy and the DIVA group comparing Hartmann's procedure with sigmoidectomy plus primary anastomosis. The DIVA section of this trial is still underway but here we report the results of the LOLA section. Patients with purulent perforated diverticulitis were enrolled for LOLA, excluding patients with faecal peritonitis, aged older than 85 years, with high-dose steroid use (≥20 mg daily), and haemodynamic instability. Patients were randomly assigned (2:1:1; stratified by age <60 years vs ≥60 years) using secure online computer randomisation to laparoscopic lavage, Hartmann's procedure, or primary anastomosis in a parallel design after diagnostic laparoscopy. Patients were analysed according to a modified intention-to-treat principle and were followed up after the index operation at least once in the outpatient setting and after sigmoidoscopy and stoma reversal, according to local protocols. The primary endpoint was a composite endpoint of major morbidity and mortality within 12 months. This trial is registered with ClinicalTrials.gov , number NCT01317485. Findings Between July 1, 2010, and Feb 22, 2013, 90 patients were randomly assigned in the LOLA section of the Ladies trial when the study was terminated by the data and safety monitoring board because of an increased event rate in the lavage group. Two patients were excluded for protocol violations. The primary endpoint occurred in 30 (67%) of 45 patients in the lavage group and 25 (60%) of 42 patients in the sigmoidectomy group (odds ratio 1·28, 95% CI 0·54–3·03, p=0·58). By 12 months, four patients had died after lavage and six patients had died after sigmoidectomy (p=0·43). Interpretation Laparoscopic lavage is not superior to sigmoidectomy for the treatment of purulent perforated diverticulitis. Funding Netherlands Organisation for Health Research and Development.
Background
Antibiotics are advised in most guidelines on acute diverticulitis, despite a lack of evidence to support their routine use. This trial compared the effectiveness of a strategy with or ...without antibiotics for a first episode of uncomplicated acute diverticulitis.
Methods
Patients with CT‐proven, primary, left‐sided, uncomplicated, acute diverticulitis were included at 22 clinical sites in the Netherlands, and assigned randomly to an observational or antibiotic treatment strategy. The primary endpoint was time to recovery during 6 months of follow‐up. Main secondary endpoints were readmission rate, complicated, ongoing and recurrent diverticulitis, sigmoid resection and mortality. Intention‐to‐treat and per‐protocol analyses were done.
Results
A total of 528 patients were included. Median time to recovery was 14 (i.q.r. 6–35) days for the observational and 12 (7–30) days for the antibiotic treatment strategy, with a hazard ratio for recovery of 0·91 (lower limit of 1‐sided 95 per cent c.i. 0·78; P = 0·151). No significant differences between the observation and antibiotic treatment groups were found for secondary endpoints: complicated diverticulitis (3·8 versus 2·6 per cent respectively; P = 0·377), ongoing diverticulitis (7·3 versus 4·1 per cent; P = 0·183), recurrent diverticulitis (3·4 versus 3·0 per cent; P = 0·494), sigmoid resection (3·8 versus 2·3 per cent; P = 0·323), readmission (17·6 versus 12·0 per cent; P = 0·148), adverse events (48·5 versus 54·5 per cent; P = 0·221) and mortality (1·1 versus 0·4 per cent; P = 0·432). Hospital stay was significantly shorter in the observation group (2 versus 3 days; P = 0·006). Per‐protocol analyses were concordant with the intention‐to‐treat analyses.
Conclusion
Observational treatment without antibiotics did not prolong recovery and can be considered appropriate in patients with uncomplicated diverticulitis. Registration number: NCT01111253 (http://www.clinicaltrials.gov).
Antibiotics not needed
Purpose
In biopsy naïve men suspected for prostate cancer (PCa), it is uncertain how a risk-calculator and bi-parametric (bp) MRI should be combined to decide on prostate biopsy, balancing cancer ...detection rates and diagnostic burden.
Methods
Prospective, single centre cohort study (August 2018–April 2019). All patients referred with serum PSA ≥ 3 ng/ml or abnormal digital rectal examination received bpMRI and risk for PCa was calculated using the ERSPC risk-calculator. Men with either PI-RADS ≥ 3 or calculator risk-score > 20% were recommended to undergo systematic biopsy (SB) and targeted biopsy (TB) of any visible lesion (reference pathway). Eight different derived diagnostic pathways were compared to the reference pathway regarding cancer detection, number of biopsies and bpMRIs performed.
Results
Of 496 patients; 233 (47%) had a risk-calculator score of > 20%; 201 (41%) had PI-RADS score ≥ 3. The reference pathway detected PCa in 32.1%, clinically significant (cs) PCa in 19.4%, with 41% avoided biopsies, but 0% avoided bpMRI. Stratification with only risk-calculator: 76% csPCa diagnosed, 53% avoided biopsies and 100% avoided bpMRI. Stratification with only bpMRI: 97% csPCa diagnosed, 59% avoided biopsies, but 0% avoided bpMRI. A pathway with risk-calculator first, followed only with bpMRI when high-risk: 81% csPCa diagnosed, 72% avoided biopsies and 53% avoided bpMRI.
Conclusion
Upfront bpMRI as a risk stratification tool outperforms risk-calculator in detecting significant disease. Applying the risk-calculator first to decide on performing an MRI, avoids 1 out of 2 MRIs, but up to 1 out of 5 significant cancers are missed.
This side study investigated the effect of chemotherapy on thyroid function and the extent to which it can predict pathological complete response (pCR) in patients with early breast cancer taking ...part in NEOZOTAC phase III trial, randomizing between neoadjuvant chemotherapy with or without additional zoledronic acid. Moreover, we examined the impact of thyroid function on toxicity. Serum samples of 38 patients were available for analyses. Free thyroxin (fT4) and thyroid stimulating hormone (TSH) levels were compared between baseline and before the 6th cycle and between subjects with and without pCR. The relation between toxicity and the variation in fT4 and TSH levels during chemotherapy was tested. Samples at baseline and before the 6th cycle were available for 31 and 21 patients, respectively. The mean baseline fT4 level was 16.0 pmol/L and TSH level 1.11 mU/L, and these did not differ between both arms at each time point. During six cycles of chemotherapy, fT4 levels decreased (
p
= 0.0001), and TSH levels increased significantly (
p
= 0.019). Interestingly, the decrease of fT4 was significantly greater in patients without nausea, vomiting, or neuropathy, than in patients with those side effects (
p
= 0.037,
p
= 0.043, and
p
= 0.050, respectively). Baseline TSH levels tended to be higher in patients with pCR (
p
= 0.035 univariate analysis and
p
= 0.074 multivariate analysis). Chemotherapy blunts thyroid function, which was associated with less side effects. These data urge further evaluation of the effects of thyroid function on toxicity and outcome of breast cancer therapy.
The immune system is important in epithelial ovarian cancer (EOC). Interleukin-6 is associated with chemoresistance and an immune-suppressive tumor microenvironment. We investigated whether a ...combination of chemotherapeutics, blockade of interleukin 6 (IL-6) receptor (IL-6R; tocilizumab), and immune enhancer interferon-&agr; (Peg-Intron) is feasible, safe, and able to enhance immunity in patients with recurrent EOC.
In this dose-escalation study, patients received tocilizumab 1, 2, 4, or 8 mg/kg i.v., q4 weeks during the first three cycles of carboplatin (AUC5) plus doxorubicin pegylated liposomal doxorubicin (PLD) 30 mg/m2 or doxorubicin 50 mg/m2 i.v., day 1, q4 weeks, for six cycles. At the highest tocilizumab dose (8 mg/kg), Peg-Intron (1 µg/kg s.c.) was added. Peripheral blood mononuclear cells were collected for immunomonitoring at baseline, after three and six cycles. Dose-limiting toxicity (DLT), CA-125, and radiologic response were evaluated.
In the 23 patients enrolled, no DLT was established. The most frequent grade 3/4 adverse events (CTCAE v4.03) were neutropenia (23%), febrile neutropenia (19%), and ileus (19%). No treatment-related deaths occurred. Using CT evaluation, 11 of 21 assessable patients responded, 6 had stable disease and 3 progressive disease. Patients receiving highest dose tocilizumab showed a functional blockade of IL-6R with increased levels of serum IL-6 (P = 0.02) and soluble IL-6R (P = 0.008). Consequently, immune cells displayed decreased levels of pSTAT3, myeloid cells produced more IL-12 and IL-1&bgr; while T cells were more activated and secreted higher amounts of effector cytokines interferon-γ and tumor necrosis factor-&agr;. An increase in sIL-6R was potentially associated with a survival benefit (P = 0.03).
Functional IL-6R blocking is feasible and safe in EOC patients treated with carboplatin/(pegylated liposomal)doxorubicin, using 8 mg/kg tocilizumab. This combination is recommended for phase II evaluation based on immune parameters.
NCT01637532.