Background
Radiomics or computer‐extracted texture features derived from MRI have been shown to help quantitatively characterize prostate cancer (PCa). Radiomics have not been explored depth in the ...context of predicting biochemical recurrence (BCR) of PCa.
Purpose
To identify a set of radiomic features derived from pretreatment biparametric MRI (bpMRI) that may be predictive of PCa BCR.
Study Type
Retrospective.
Subjects
In all, 120 PCa patients from two institutions, I1 and I2, partitioned into training set D1 (N = 70) from I1 and independent validation set D2 (N = 50) from I2. All patients were followed for ≥3 years.
Sequence
3T, T2‐weighted (T2WI) and apparent diffusion coefficient (ADC) maps derived from diffusion‐weighted sequences.
Assessment
PCa regions of interest (ROIs) on T2WI were annotated by two experienced radiologists. Radiomic features from bpMRI (T2WI and ADC maps) were extracted from the ROIs. A machine‐learning classifier (CBCR) was trained with the best discriminating set of radiomic features to predict BCR (pBCR).
Statistical Tests
Wilcoxon rank‐sum tests with P < 0.05 were considered statistically significant. Differences in BCR‐free survival at 3 years using pBCR was assessed using the Kaplan–Meier method and compared with Gleason Score (GS), PSA, and PIRADS‐v2.
Results
Distribution statistics of co‐occurrence of local anisotropic gradient orientation (CoLlAGe) and Haralick features from T2WI and ADC were associated with BCR (P < 0.05) on D1. CBCR predictions resulted in a mean AUC = 0.84 on D1 and AUC = 0.73 on D2. A significant difference in BCR‐free survival between the predicted classes (BCR + and BCR–) was observed (P = 0.02) on D2 compared to those obtained from GS (P = 0.8), PSA (P = 0.93) and PIRADS‐v2 (P = 0.23).
Data Conclusion
Radiomic features from pretreatment bpMRI can be predictive of PCa BCR after therapy and may help identify men who would benefit from adjuvant therapy.
Level of Evidence: 4
Technical Efficacy: Stage 5
J. Magn. Reson. Imaging 2018;48:1626–1636
Nestin, a member of the cytoskeletal family of intermediate filaments, regulates the onset of myogenic differentiation through bidirectional signaling with the kinase Cdk5. Here, we show that these ...effects are also reflected at the organism level, as there is a loss of skeletal muscle mass in nestin
(NesKO) mice, reflected as reduced lean (muscle) mass in the mice. Further examination of muscles in male mice revealed that these effects stemmed from nestin-deficient muscles being more prone to spontaneous regeneration. When the regeneration capacity of the compromised NesKO muscle was tested by muscle injury experiments, a significant healing delay was observed. NesKO satellite cells showed delayed proliferation kinetics in conjunction with an elevation in p35 (encoded by
) levels and Cdk5 activity. These results reveal that nestin deficiency generates a spontaneous regenerative phenotype in skeletal muscle that relates to a disturbed proliferation cycle that is associated with uncontrolled Cdk5 activity.
The human epidermal growth factor receptor 2 (HER2) is an oncogene targeted by several kinase inhibitors and therapeutic antibodies. While the endosomal trafficking of many other receptor tyrosine ...kinases is known to regulate their oncogenic signalling, the prevailing view on HER2 is that this receptor is predominantly retained on the cell surface. Here, we find that sortilin-related receptor 1 (SORLA; SORL1) co-precipitates with HER2 in cancer cells and regulates HER2 subcellular distribution by promoting recycling of the endosomal receptor back to the plasma membrane. SORLA protein levels in cancer cell lines and bladder cancers correlates with HER2 levels. Depletion of SORLA triggers HER2 targeting to late endosomal/lysosomal compartments and impairs HER2-driven signalling and in vivo tumour growth. SORLA silencing also disrupts normal lysosome function and sensitizes anti-HER2 therapy sensitive and resistant cancer cells to lysosome-targeting cationic amphiphilic drugs. These findings reveal potentially important SORLA-dependent endosomal trafficking-linked vulnerabilities in HER2-driven cancers.
To develop and validate a classifier system for prediction of prostate cancer (PCa) Gleason score (GS) using radiomics and texture features of T2-weighted imaging (T2w), diffusion weighted imaging ...(DWI) acquired using high b values, and T2-mapping (T2).
T2w, DWI (12 b values, 0-2000 s/mm2), and T2 data sets of 62 patients with histologically confirmed PCa were acquired at 3T using surface array coils. The DWI data sets were post-processed using monoexponential and kurtosis models, while T2w was standardized to a common scale. Local statistics and 8 different radiomics/texture descriptors were utilized at different configurations to extract a total of 7105 unique per-tumor features. Regularized logistic regression with implicit feature selection and leave pair out cross validation was used to discriminate tumors with 3+3 vs >3+3 GS.
In total, 100 PCa lesions were analysed, of those 20 and 80 had GS of 3+3 and >3+3, respectively. The best model performance was obtained by selecting the top 1% features of T2w, ADCm and K with ROC AUC of 0.88 (95% CI of 0.82-0.95). Features from T2 mapping provided little added value. The most useful texture features were based on the gray-level co-occurrence matrix, Gabor transform, and Zernike moments.
Texture feature analysis of DWI, post-processed using monoexponential and kurtosis models, and T2w demonstrated good classification performance for GS of PCa. In multisequence setting, the optimal radiomics based texture extraction methods and parameters differed between different image types.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Purpose
To evaluate in a multi‐institutional study whether radiomic features useful for prostate cancer (PCa) detection from 3 Tesla (T) multi‐parametric MRI (mpMRI) in the transition zone (TZ) ...differ from those in the peripheral zone (PZ).
Materials and Methods
3T mpMRI, including T2‐weighted (T2w), apparent diffusion coefficient (ADC) maps, and dynamic contrast‐enhanced MRI (DCE‐MRI), were retrospectively obtained from 80 patients at three institutions. This study was approved by the institutional review board of each participating institution. First‐order statistical, co‐occurrence, and wavelet features were extracted from T2w MRI and ADC maps, and contrast kinetic features were extracted from DCE‐MRI. Feature selection was performed to identify 10 features for PCa detection in the TZ and PZ, respectively. Two logistic regression classifiers used these features to detect PCa and were evaluated by area under the receiver‐operating characteristic curve (AUC). Classifier performance was compared with a zone‐ignorant classifier.
Results
Radiomic features that were identified as useful for PCa detection differed between TZ and PZ. When classification was performed on a per‐voxel basis, a PZ‐specific classifier detected PZ tumors on an independent test set with significantly higher accuracy (AUC = 0.61–0.71) than a zone‐ignorant classifier trained to detect cancer throughout the entire prostate (P < 0.05). When classifiers were evaluated on MRI data from multiple institutions, statistically similar AUC values (P > 0.14) were obtained for all institutions.
Conclusion
A zone‐aware classifier significantly improves the accuracy of cancer detection in the PZ.
Level of Evidence: 3
Technical Efficacy: Stage 2
J. MAGN. RESON. IMAGING 2017;46:184–193
Abstract
Transurethral resection of bladder tumor (TUR-BT) and radical cystectomy (RC) are standard treatment options for bladder cancer (BC). Neoadjuvant chemotherapy (NAC) prior to RC improves ...outcome of some patients but currently there are no valid biomarkers to identify patients who benefit from NAC. Presence of cancer stem cells (CSC) has been associated with poor outcome and resistance to chemotherapy in various cancers. Here we studied the expression of stem cell markers ALDH1, SOX2 and SSEA-4 with immunohistochemistry in tissue microarray material consisting of 195 BC patients treated with RC and 74 patients treated with TUR-BT followed by NAC and RC. Post-operative follow-up data of up to 22 years was used. Negative to weak cytoplasmic SOX2 staining was associated with lymphovascular invasion and non-organ confined disease. It was also associated with shortened cancer-specific survival, but the finding was not statistically significant. Contrary to previous reports, none of the other tested biomarkers were associated with cancer-specific mortality or clinicopathological characteristics. Neither were they associated with response to NAC. Despite the promising results of previously published studies, our results suggest that CSC markers ALDH1, SOX2 and SSEA-4 have little if any prognostic or predictive value in BC treated with RC.
Mutations of the tumor suppressor TP53 are present in many forms of human cancer and are associated with increased tumor cell invasion and metastasis. Several mechanisms have been identified for ...promoting dissemination of cancer cells with TP53 mutations, including increased targeting of integrins to the plasma membrane. Here, we demonstrate a role for the filopodia-inducing motor protein Myosin-X (Myo10) in mutant p53-driven cancer invasion. Analysis of gene expression profiles from 2 breast cancer data sets revealed that MYO10 was highly expressed in aggressive cancer subtypes. Myo10 was required for breast cancer cell invasion and dissemination in multiple cancer cell lines and murine models of cancer metastasis. Evaluation of a Myo10 mutant without the integrin-binding domain revealed that the ability of Myo10 to transport β₁ integrins to the filopodia tip is required for invasion. Introduction of mutant p53 promoted Myo10 expression in cancer cells and pancreatic ductal adenocarcinoma in mice, whereas suppression of endogenous mutant p53 attenuated Myo10 levels and cell invasion. In clinical breast carcinomas, Myo10 was predominantly expressed at the invasive edges and correlated with the presence of TP53 mutations and poor prognosis. These data indicate that Myo10 upregulation in mutant p53-driven cancers is necessary for invasion and that plasma-membrane protrusions, such as filopodia, may serve as specialized metastatic engines.
Lung adenocarcinoma is the most common type of lung cancer and typically carries a high number of mutations. However, the genetic background of the tumors varies according to patients’ ethnic ...background and smoking status. Little data is available on the mutational landscape and the frequency of actionable genomic alterations in lung adenocarcinoma in the Finnish population.
We evaluated the gene alteration frequencies of 135 stage I–IV lung adenocarcinomas operated at Turku University Hospital between 2004 and 2017 with a large commercial comprehensive genomic profiling panel. Additionally, we correlated the alterations in selected genes with disease outcomes in 115 stage I–III patients with comprehensive follow-up data. The genomic alterations in a sub-cohort of 30 never-smokers were assessed separately.
Seventy percent of patients in the overall cohort and 77% in the never-smoker sub-cohort harbored an alteration or a genomic signature targetable by FDA and/or EMA approved drug for non-small cell carcinoma, respectively. In multivariable analysis for disease-specific survival, any alteration in SMARCA4 (DSS; HR 3.911, 95%CI 1.561–9.795, P=0.004) exhibited independent prognostic significance along with stage, tumor mutation burden, and predominant histological subtypes.
Over two thirds of our overall cohort, and especially never-smokers had an actionable genomic alteration or signature. SMARCA4 alterations, detected in 7.4% of the tumors, independently predicted a shortened overall and disease-specific survival regardless of the alteration type. Most SMARCA4 alterations in our cohort were missense mutations associated with differentiated predominant histological subtypes and immunohistochemical SMARCA4/BRG1 and TTF-1 positive status.
Objectives
To evaluate short-term test-retest repeatability of a deep learning architecture (U-Net) in slice- and lesion-level detection and segmentation of clinically significant prostate cancer ...(csPCa: Gleason grade group > 1) using diffusion-weighted imaging fitted with monoexponential function, ADC
m
.
Methods
One hundred twelve patients with prostate cancer (PCa) underwent 2 prostate MRI examinations on the same day. PCa areas were annotated using whole mount prostatectomy sections. Two U-Net-based convolutional neural networks were trained on three different ADC
m
b
value settings for (a) slice- and (b) lesion-level detection and (c) segmentation of csPCa. Short-term test-retest repeatability was estimated using intra-class correlation coefficient (ICC(3,1)), proportionate agreement, and dice similarity coefficient (DSC). A 3-fold cross-validation was performed on training set (
N
= 78 patients) and evaluated for performance and repeatability on testing data (
N
= 34 patients).
Results
For the three ADC
m
b
value settings, repeatability of mean ADC
m
of csPCa lesions was ICC(3,1) = 0.86–0.98. Two CNNs with U-Net-based architecture demonstrated ICC(3,1) in the range of 0.80–0.83, agreement of 66–72%, and DSC of 0.68–0.72 for slice- and lesion-level detection and segmentation of csPCa. Bland-Altman plots suggest that there is no systematic bias in agreement between inter-scan ground truth segmentation repeatability and segmentation repeatability of the networks.
Conclusions
For the three ADC
m
b
value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level. The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.
Key Points
•
For the three ADC
m
b value settings, two CNNs with U-Net-based architecture were repeatable for the problem of detection of csPCa at the slice-level.
•
The network repeatability in segmenting csPCa lesions is affected by inter-scan variability and ground truth segmentation repeatability and may thus improve with better inter-scan reproducibility.