A data-driven ultrasound approach discriminates pathological high grade prostate cancer.
Ontology highlight
ABSTRACT:
SUBMITTER: Akatsuka J
PROVIDER: S-EPMC8764059 | biostudies-literature | 2022 Jan
REPOSITORIES: biostudies-literature
Publications
A data-driven ultrasound approach discriminates pathological high grade prostate cancer.
Akatsuka Jun J Numata Yasushi Y Morikawa Hiromu H Sekine Tetsuro T Kayama Shigenori S Mikami Hikaru H Yanagi Masato M Endo Yuki Y Takeda Hayato H Toyama Yuka Y Yamaguchi Ruri R Kimura Go G Kondo Yukihiro Y Yamamoto Yoichiro Y
Scientific reports 20220117 1
Accurate prostate cancer screening is imperative for reducing the risk of cancer death. Ultrasound imaging, although easy, tends to have low resolution and high inter-observer variability. Here, we show that our integrated machine learning approach enabled the detection of pathological high-grade cancer by the ultrasound procedure. Our study included 772 consecutive patients and 2899 prostate ultrasound images obtained at the Nippon Medical School Hospital. We applied machine learning analyses u ...[more]
Similar Datasets
Project description:ObjectiveInterictal high-frequency oscillations (HFOs) are a promising neurophysiological biomarker of the epileptogenic zone (EZ). However, objective criteria for distinguishing pathological from physiological HFOs remain elusive, hindering clinical application. We investigated whether the distinct mechanisms underlying pathological and physiological HFOs are encapsulated in their signal morphology in intracranial EEG (iEEG) recordings and whether this mechanism-driven distinction could be simulated by a deep generative model.MethodsIn a retrospective cohort of 185 epilepsy patients who underwent iEEG monitoring, we analyzed 686,410 HFOs across 18,265 brain contacts. To learn morphological characteristics, each event was transformed into a time-frequency plot and input into a variational autoencoder. We characterized latent space clusters containing morphologically defined putative pathological HFOs (mpHFOs) using interpretability analysis, including latent space disentanglement and time-domain perturbation.ResultsmpHFOs showed strong associations with expert-defined spikes and were predominantly located within the seizure onset zone (SOZ). Discovered novel pathological features included high power in the gamma (30-80 Hz) and ripple (>80 Hz) bands centered on the event. These characteristics were consistent across multiple variables, including institution, electrode type, and patient demographics. Predicting 12-month postoperative seizure outcomes using the resection ratio of mpHFOs outperformed unclassified HFOs (F1=0.72 vs. 0.68) and matched current clinical standards using SOZ resection (F1=0.74). Combining mpHFO data with demographic and SOZ resection status further improved prediction accuracy (F1=0.83).InterpretationOur data-driven approach yielded a novel, explainable definition of pathological HFOs, which has the potential to further enhance the clinical use of HFOs for EZ delineation.
| S-EPMC11261948 | biostudies-literature
Project description:To identify molecules to serve as diagnostic markers for high-grade prostate cancer (PC) and targets for novel therapeutic drugs, we investigated the gene expression profiles of high-grade PCs using a cDNA microarray combined with laser microbeam microdissection.
2013-03-12 | GSE45016 | GEO
Project description:To identify molecules to serve as diagnostic markers for high-grade prostate cancer (PC) and targets for novel therapeutic drugs, we investigated the gene expression profiles of high-grade PCs using a cDNA microarray combined with laser microbeam microdissection. For this study, we collected 10 frozen specimens from high-grade PCs with high PSA levels and high Gleason score (GS) in clinically using prostatic needle biopsy. All needle biopsy specimens were at clinical stages T2 to T4 with or without N1 and M1 and their GS were 8-9. Moreover, all 10 patients had not received androgen ablation therapy. Simultaneously, normal prostate (NP) epithelial cells were also microdissected from five non-prostate cancer (BPH) patients. These NP cells from five males were used as a normal mixture control for our cDNA microarray analysis.
2013-03-12 | E-GEOD-45016 | biostudies-arrayexpress
Project description:Understanding the developmental relationship between indolent and aggressive tumors is central to understanding disease progression and making treatment decisions. For example, most men diagnosed with prostate cancer have clinically indolent disease and die from other causes. Overtreatment of prostate cancer remains a concern. Here we use laser microdissection followed by exome sequencing of low- and high-grade prostate cancer foci from four subjects, and metastatic disease from two of those subjects, to evaluate the molecular relationship of coincident cancer foci. Seventy of 79 (87%) high-confidence somatic mutations in low-grade disease were private to low-grade foci. In contrast, high-grade foci and metastases harbored many of the same mutations. In cases in which there was a metastatic focus, 15 of 80 (19%) high-confidence somatic mutations in high-grade foci were private. Seven of the 80 (9%) were shared with low-grade foci and 65 (82%) were shared with metastatic foci. Notably, mutations in cancer-associated genes and the p53 signaling pathway were found exclusively in high-grade foci and metastases. The pattern of mutations is consistent with early divergence between low- and high-grade foci and late divergence between high-grade foci and metastases. These data provide insights into the development of high-grade and metastatic prostate cancer.
| S-EPMC4317857 | biostudies-other
Project description:Following a period of slow progress, the completion of genome sequencing and the paradigm shift relative to the cell of origin for high grade serous ovarian cancer (HGSOC) led to a new perspective on the biology and therapeutic solutions for this deadly cancer. Experimental models were revisited to address old questions, and improved tools were generated. Additional pathways emerging as drivers of ovarian tumorigenesis and key dependencies for therapeutic targeting, in particular, VEGF-driven angiogenesis and homologous recombination deficiency, were discovered. Molecular profiling of histological subtypes of ovarian cancer defined distinct genetic events for each entity, enabling the first attempts toward personalized treatment. Armed with this knowledge, HGSOC treatment was revised to include new agents. Among them, PARP inhibitors (PARPis) were shown to induce unprecedented improvement in clinical benefit for selected subsets of patients. Research on mechanisms of resistance to PARPis is beginning to discover vulnerabilities and point to new treatment possibilities. This Review highlights these advances, the remaining challenges, and unsolved problems in the field.
| S-EPMC10760962 | biostudies-literature
Project description:IntroductionTesticular cancer survivors (TCS) have an increased risk of additional cancers, including prostate cancer. Our understanding of the natural history of prostate cancer in testicular cancer survivors is very limited due to its rare incidence.MethodsUsing the Surveillance, Epidemiology, and End Results (SEER) Registry from 1978 to 2011, we identified 282 TCS with subsequent prostate cancer and examined the tumor grade and clinical outcomes in contrast to men with primary prostate cancer in the general population.ResultsTCS with a subsequent prostate cancer diagnosis were more likely to be diagnosed at a younger age than men with primary prostate cancer (65.2% vs. 37.6% for age ≤65, 34.8% vs. 62.4% for age >65, p<0.001) and were more likely to have grade III/IV tumors (46.2% vs. 37.0%, p<0.002). Longer latency between testicular and prostate cancer diagnoses was associated with a higher risk of grade III/IV (p<0.001) cancer. Despite the increased risk for high-grade tumors, 10-year prostate cancer-specific survival and overall survival were not significantly different between TCS and men with primary prostate cancer. Based on the available information in SEER, we found that prior history of radiotherapy for testicular cancer had no impact on tumor grade or survival outcomes.ConclusionsProstate cancer in TCS was more likely to be diagnosed at a younger age and with higher grades. Risks of grade III/IV disease increased with longer latency between testicular and prostate cancer diagnoses. Radiotherapy for testicular cancer did not appear to have a significant impact on the outcome of subsequent prostate cancer.
| S-EPMC8843166 | biostudies-literature
Project description:Automatic boundary detection of 4D ultrasound (4DUS) cardiac data is a promising yet challenging application at the intersection of machine learning and medicine. Using recently developed murine 4DUS cardiac imaging data, we demonstrate here a set of three machine learning models that predict left ventricular wall kinematics along both the endo- and epi-cardial boundaries. Each model is fundamentally built on three key features: (1) the projection of raw US data to a lower dimensional subspace, (2) a smoothing spline basis across time, and (3) a strategic parameterization of the left ventricular boundaries. Model 1 is constructed such that boundary predictions are based on individual short-axis images, regardless of their relative position in the ventricle. Model 2 simultaneously incorporates parallel short-axis image data into their predictions. Model 3 builds on the multi-slice approach of model 2, but assists predictions with a single ground-truth position at end-diastole. To assess the performance of each model, Monte Carlo cross validation was used to assess the performance of each model on unseen data. For predicting the radial distance of the endocardium, models 1, 2, and 3 yielded average R2 values of 0.41, 0.49, and 0.71, respectively. Monte Carlo simulations of the endocardial wall showed significantly closer predictions when using model 2 versus model 1 at a rate of 48.67%, and using model 3 versus model 2 at a rate of 83.50%. These finding suggest that a machine learning approach where multi-slice data are simultaneously used as input and predictions are aided by a single user input yields the most robust performance. Subsequently, we explore the how metrics of cardiac kinematics compare between ground-truth contours and predicted boundaries. We observed negligible deviations from ground-truth when using predicted boundaries alone, except in the case of early diastolic strain rate, providing confidence for the use of such machine learning models for rapid and reliable assessments of murine cardiac function. To our knowledge, this is the first application of machine learning to murine left ventricular 4DUS data. Future work will be needed to strengthen both model performance and applicability to different cardiac disease models.
| S-EPMC8301599 | biostudies-literature
Project description:BackgroundThe consequences of low prostate-specific antigen (PSA) in high-grade (Gleason 8-10) prostate cancer are unknown.ObjectiveTo evaluate the clinical implications and genomic features of low-PSA, high-grade disease.Design, setting, and participantsThis was a retrospective study of clinical data for 494 793 patients from the National Cancer Data Base and 136 113 patients from the Surveillance, Epidemiology, and End Results program with cT1-4N0M0 prostate cancer (median follow-up 48.9 and 25.0 mo, respectively), and genomic data for 4960 patients from the Decipher Genomic Resource Information Database. Data were collected for 2004-2017.Outcome measurements and statistical analysisMultivariable Fine-Gray and Cox regressions were used to analyze prostate cancer-specific mortality (PCSM) and all-cause mortality, respectively.Results and limitationsFor Gleason 8-10 disease, using PSA 4.1-10.0ng/ml (n=38 719) as referent, the distribution of PCSM by PSA was U-shaped, with an adjusted hazard ratio (AHR) of 2.70 for PSA ≤2.5ng/ml (n=3862, p<0.001) versus 1.97, 1.36, and 2.56 for PSA of 2.6-4.0 (n=4199), 10.1-20.0 (n=17 372), and >20.0ng/ml (n=16 114), respectively. By contrast, the distribution of PCSM by PSA was linear for Gleason ≤7 (using PSA 4.1-10.0ng/ml as the referent, n=359 898), with an AHR of 0.41 (p=0.13) for PSA ≤2.5ng/ml (n=37 812) versus 1.38, 2.28, and 4.61 for PSA of 2.6-4.0 (n=54 152), 10.1-20.0 (n=63 319), and >20.0ng/ml (n=35 459), respectively (pinteraction<0.001). Gleason 8-10, PSA ≤2.5ng/ml disease had a significantly higher PCSM than standard high-risk/very high-risk disease with PSA >2.5ng/ml (AHR 2.15, p=0.002; 47-mo PCSM 14% vs 4.9%). Among Gleason 8-10 patients treated with radiotherapy, androgen deprivation therapy was associated with a survival benefit for PSA >2.5ng/ml (AHR 0.87; p<0.001) but not ≤2.5ng/ml (AHR 1.36; p=0.084; pinteraction=0.021). For Gleason 8-10 tumors, PSA ≤2.5ng/ml was associated with higher expression of neuroendocrine/small-cell markers compared to >2.5ng/ml (p=0.046), with no such relationship for Gleason ≤7 disease.ConclusionsLow-PSA, high-grade prostate cancer has very high risk for PCSM, potentially responds poorly to androgen deprivation therapy, and is associated with neuroendocrine genomic features.Patient summaryIn this study, we found that low-prostate-specific antigen, high-grade prostate cancer has a very high risk for prostate cancer death, may not respond well to androgen deprivation therapy, and is associated with neuroendocrine genomic features. These findings suggest that current nomograms and treatment paradigms may need modification.
| S-EPMC6615042 | biostudies-literature
Project description:ObjectiveThis study aims to analyse multiparametric MRI (mpMRI) characteristics of patients diagnosed with ISUP grade group (GG) 1 prostate cancer (PC) on initial target plus systematic MRI/TRUS fusion-guided biopsy and investigate histopathological progression during follow-up.MethodsA retrospective single-centre cohort analysis was conducted on consecutive patients with mpMRI visible lesions (PI-RADS ≥ 3) and detection of ISUP-1-PC at the time of initial biopsy. The study assessed clinical, mpMRI, and histopathological parameters. Subcohorts were analysed with (1) patients who had confirmed ISUP-1-PC and (2) patients who experienced histopathological upgrading to ISUP ≥ 2 PC during follow-up either at re-biopsy or radical prostatectomy (RP).ResultsA total of 156 patients (median age 65 years) between March 2014 and August 2021 were included. Histopathological upgrading to ISUP ≥ 2 was detected in 55% of patients during a median follow-up of 9.5 months (IQR 2.2-16.4). When comparing subgroups with an ISUP upgrade and sustained ISUP 1 PC, they differed significantly in contact length of the index lesion to the pseudocapsule, ADC value, PI-RADS category, and the MRI grading group (mGG) (p < 0.05). In the ISUP GG ≥ 2 subgroup, 91% of men had PI-RADS category 4 or 5 and 82% exhibited the highest mGG (mGG3). In multivariate analysis, mGG was the only independent parameter for predicting ISUP ≥ 2-PC in these patients.ConclusionsMRI reveals important information about PC aggressiveness and should be incorporated into clinical decision-making when ISUP-1-PC is diagnosed. In cases of specific MRI characteristics adverse to the histopathology, early re-biopsy might be considered.Clinical relevance statementIn cases with clear MRI characteristics for clinically significant prostate cancer (e.g., mGG 3 and/or PI-RADS 5, cT3, or clear focal PI-RADS 4 lesions on MRI) and ISUP GG 1 PC diagnosed on initial prostate biopsy, MRI findings should be incorporated into clinical decision-making and early re-biopsy (e.g., within 6 months) might be considered.Key pointsMRI reveals important information about prostate cancer (PC) aggressiveness. MRI should be incorporated into clinical decision-making when ISUP GG 1 PC is diagnosed on initial prostate biopsy. In cases of specific MRI characteristics adverse to the histopathology, early re-biopsy might be considered.
| S-EPMC11913941 | biostudies-literature
Project description:Observational studies suggest an inverse association between selenium and risk of prostate cancer. However, randomized controlled trials of selenium supplementation have reported conflicting results. Thus, we examined plasma selenium and selenium-related genes in relation to risk of high-grade prostate cancer and prostate cancer recurrence among men initially diagnosed with non-metastatic disease.We measured plasma selenium and genotyped 73 single nucleotide polymorphisms in TXNRD1, TXNRD2, GPX1, GPX3, GPX4, SEP15, SEPP1, SELENBP1, OGG1, and CAT among 568 men with non-metastatic prostate cancer who underwent radical prostatectomy. We examined associations between plasma selenium, genotypes, and risk of high-grade prostate cancer (Gleason grade ?8 or 7 with primary score ?4; n?=?111) using logistic regression, and risk of prostate cancer recurrence (61 events; 3.8 y median follow-up) using Cox proportional hazards regression.Plasma selenium was not associated with risk of high-grade prostate cancer or prostate cancer recurrence. Less common alleles of rs11913319 in TXNRD2 and rs125701 in OGG1 were associated with an increased risk of high-grade prostate cancer. We observed associations between the risk of prostate cancer recurrence and multiple SNPs in TXNRD1, TXNRD2, GPX3, and SEP15. These associations were no longer statistically significant after adjustment for multiple comparisons.Among men with non-metastatic prostate cancer, there is suggestive evidence that genetic variation in selenoproteins and related antioxidant enzymes may be associated with risk of high-grade disease at diagnosis and prostate cancer recurrence.
| S-EPMC4257852 | biostudies-literature