Enhancing automatic prediction of clinically significant prostate cancer with deep transfer learning 2.5-dimensional segmentation on bi-parametric magnetic resonance imaging (bp-MRI)
Ontology highlight
ABSTRACT:
SUBMITTER:
PROVIDER: S-EPMC11250323 | biostudies-literature | 2024 Jun
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Backgroundaround one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─).ObjectiveTo quantify the differences between MR visible (MRI+) and MRI─ CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI).MethodsThis retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI─ CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (Dv) comprised 52 patients from a single institution, the remaining 112 patients were used for training (Dt). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI.Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on Dt to identify radiomic features associated with MRI─ and MRI+ CsPCa to generate corresponding risk scores RMRI─ and RMRI+. RbpMRI was further generated by integrating RMRI─ and RMRI+. Statistical significance was determined using the Wilcoxon signed-rank test.ResultsBoth intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI─ CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI─ and MRI+ CsPCa (p < 0.05). RbpMRI yielded the highest AUC of 0.82 (95 % CI 0.72-0.91) compared to AUCs of RMRI+ 0.76 (95 % CI 0.63-0.89), and PI-RADS 0.58 (95 % CI 0.50-0.72) on Dv. RbpMRI correctly reclassified 10 out of 14 MRI─ CsPCa on Dv.ConclusionOur preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI─ CsPCa. These features could assist in CsPCa identification on bpMRI.
| S-EPMC10311200 | biostudies-literature
Project description:ObjectivesTo develop an automatic method for identification and segmentation of clinically significant prostate cancer in low-risk patients and to evaluate the performance in a routine clinical setting.MethodsA consecutive cohort (n = 292) from a prospective database of low-risk patients eligible for the active surveillance was selected. A 3-T multi-parametric MRI at 3 months after inclusion was performed. Histopathology from biopsies was used as reference standard. MRI positivity was defined as PI-RADS score ≥ 3, histopathology positivity was defined as ISUP grade ≥ 2. The selected cohort contained four patient groups: (1) MRI-positive targeted biopsy-positive (n = 116), (2) MRI-negative systematic biopsy-negative (n = 55), (3) MRI-positive targeted biopsy-negative (n = 113), (4) MRI-negative systematic biopsy-positive (n = 8). Group 1 was further divided into three sets and a 3D convolutional neural network was trained using different combinations of these sets. Two MRI sequences (T2w, b = 800 DWI) and the ADC map were used as separate input channels for the model. After training, the model was evaluated on the remaining group 1 patients together with the patients of groups 2 and 3 to identify and segment clinically significant prostate cancer.ResultsThe average sensitivity achieved was 82-92% at an average specificity of 43-76% with an area under the curve (AUC) of 0.65 to 0.89 for different lesion volumes ranging from > 0.03 to > 0.5 cc.ConclusionsThe proposed deep learning computer-aided method yields promising results in identification and segmentation of clinically significant prostate cancer and in confirming low-risk cancer (ISUP grade ≤ 1) in patients on active surveillance.Key points• Clinically significant prostate cancer identification and segmentation on multi-parametric MRI is feasible in low-risk patients using a deep neural network. • The deep neural network for significant prostate cancer localization performs better for lesions with larger volumes sizes (> 0.5 cc) as compared to small lesions (> 0.03 cc). • For the evaluation of automatic prostate cancer segmentation methods in the active surveillance cohort, the large discordance group (MRI positive, targeted biopsy negative) should be included.
| S-EPMC7599141 | biostudies-literature
Project description:The objectives of the study were to develop a framework for automatic outer and inner breast tissue segmentation using multi-parametric MRI images of the breast tumor patients; and to perform breast density and tumor tissue analysis. MRI of the breast was performed on 30 patients at 3T-MRI. T1, T2 and PD-weighted(W) images, with and without fat saturation(WWFS), and dynamic-contrast-enhanced(DCE)-MRI data were acquired. The proposed automatic segmentation approach was performed in two steps. In step-1, outer segmentation of breast tissue from rest of body parts was performed on structural images (T2-W/T1-W/PD-W without fat saturation images) using automatic landmarks detection technique based on operations like profile screening, Otsu thresholding, morphological operations and empirical observation. In step-2, inner segmentation of breast tissue into fibro-glandular(FG), fatty and tumor tissue was performed. For validation of breast tissue segmentation, manual segmentation was carried out by two radiologists and similarity coefficients(Dice and Jaccard) were computed for outer as well as inner tissues. FG density and tumor volume were also computed and analyzed. The proposed outer and inner segmentation approach worked well for all the subjects and was validated by two radiologists. The average Dice and Jaccard coefficients value for outer segmentation using T2-W images, obtained by two radiologists, were 0.977 and 0.951 respectively. These coefficient values for FG tissue were 0.915 and 0.875 respectively whereas for tumor tissue, values were 0.968 and 0.95 respectively. The volume of segmented tumor ranged over 2.1 cm3-7.08 cm3. The proposed approach provided automatic outer and inner breast tissue segmentation, which enables automatic calculations of breast tissue density and tumor volume. This is a complete framework for outer and inner breast segmentation method for all structural images.
| S-EPMC5761869 | biostudies-literature
Project description:Gadolinium-enhancing lesions reflect active disease and are critical for in-patient monitoring in multiple sclerosis (MS). In this work, we have developed the first fully automated method to segment and count the gadolinium-enhancing lesions from routine clinical MRI of MS patients. The proposed method first segments the potential lesions using 2D-UNet from multi-channel scans (T1 post-contrast, T1 pre-contrast, FLAIR, T2, and proton-density) and classifies the lesions using a random forest classifier. The algorithm was trained and validated on 600 MRIs with manual segmentation. We compared the effect of loss functions (Dice, cross entropy, and bootstrapping cross entropy) and number of input contrasts. We compared the lesion counts with those by radiologists using 2,846 images. Dice, lesion-wise sensitivity, and false discovery rate with full 5 contrasts were 0.698, 0.844, and 0.307, which improved to 0.767, 0.969, and 0.00 in large lesions (>100 voxels). The model using bootstrapping loss function provided a statistically significant increase of 7.1% in sensitivity and of 2.3% in Dice compared with the model using cross entropy loss. T1 post/pre-contrast and FLAIR were the most important contrasts. For large lesions, the 2D-UNet model trained using T1 pre-contrast, FLAIR, T2, PD had a lesion-wise sensitivity of 0.688 and false discovery rate 0.083, even without T1 post-contrast. For counting lesions in 2846 routine MRI images, the model with 2D-UNet and random forest, which was trained with bootstrapping cross entropy, achieved accuracy of 87.7% using T1 pre-contrast, T1 post-contrast, and FLAIR when lesion counts were categorized as 0, 1, and 2 or more. The model performs well in routine non-standardized MRI datasets, allows large-scale analysis of clinical datasets, and may have clinical applications.
| S-EPMC8409666 | biostudies-literature
Project description:Selective identification of men with clinically significant prostate cancer (sPC) is a pivotal issue. Development of a risk model for detecting sPC based on the prostate imaging reporting and data system (PI-RADS) for bi-parametric magnetic resonance imaging (bpMRI) and clinical parameters in a Japanese cohort is expected to prove beneficial. We retrospectively analyzed clinical parameters and bpMRI findings from 773 biopsy-naïve patients between January 2011 and December 2016. A risk model was established using multivariate logistic regression analysis and presented on a nomogram. Discrimination of the risk model was compared using the area under the receiver operating characteristic curve. Statistical differences between the predictive model and clinical parameters were analyzed using DeLong test. sPC was detected in 343 men (44.3%). Multivariate logistic regression analysis to predict sPC revealed age (P = 0.002), log prostate-specific antigen (P < 0.001), prostate volume (P < 0.001) and PI-RADS scores (P < 0.001) as significant contributors to the model. Area under the curve was higher for the risk model (0.862), than for age (0.646), log prostate-specific antigen (0.652), prostate volume (0.697) or imaging score (0.822). DeLong test results also showed that the novel risk model performed significantly better than those parameters (P < 0.05). This novel risk model performed significantly better compared with PI-RADS scores and other parameters alone, and is thus expected to prove beneficial in making decisions regarding biopsy on suspicion of sPC.
| S-EPMC8458280 | biostudies-literature
Project description:PurposeThis study was conducted to compare the accuracy of bi-parametric magnetic resonance imaging (bpMRI) with high b-value (b=1,000 s/mm², b1000) diffusion-weighted imaging (DWI) to that of bpMRI with ultra-high b-value (b=1,800 s/mm², b1800) DWI to detect clinically significant prostate cancer (csPCa).Materials and methodsA total of 408 patients with suspected PCa were evaluated by bpMRI prior to biopsy. One reader retrospectively reviewed all images for confirmation of Prostate Imaging-Reporting and Data System (PI-RADS) score. Cognitive magnetic resonance/ultrasound fusion target biopsy was done for all visible lesions (PI-RADS 3-5). Systematic biopsy was done for all cases. The csPCa detection rates were compared according to the bpMRI protocol (with/without b1800 DWI) or PI-RADS score. The accuracy of PI-RADS score was estimated using receiver operating characteristics curve. The signal intensity (SI) ratio (visible lesion/surrounding background) was evaluated.ResultsAmong 164 men confirmed having PCa, 102 had csPCa (Gleason score≥7). Proportions of PI-RADS score 1-2/3/4/5 without b1800 DWI (n=133) and with b1800 DWI (n=275) were 19.5%/57.9%/15.8%/6.8% and 21.1%/48.7%/22.2%/8.0%, respectively. csPCa detection rates with/without b1800 DWI were 27.6%/19.5% (p=0.048), respectively. Areas under the curve of PI-RADS grading with/without b1800 DWI for csPCa detection were 0.885 and 0.705, respectively. The SI ratio in b1800 DWI was higher than that in b1000 DWI (p<0.001).ConclusionsAdding b1800 DWI to bpMRI protocol improved the diagnostic accuracy and detection rate of csPCa. The higher SI ratio (lesion/background) in b1800 DWI enabled clearer identification of lesions.
| S-EPMC7308233 | biostudies-literature
Project description:Objectives: To develop and validate a predictive model for discriminating clinically significant prostate cancer (csPCa) from clinically insignificant prostate cancer (ciPCa). Methods: This retrospective study was performed with 159 consecutively enrolled pathologically confirmed PCa patients from two medical centers. The dataset was allocated to a training group (n = 54) and an internal validation group (n = 22) from one center along with an external independent validation group (n = 83) from another center. A total of 1,188 radiomic features were extracted from T2WI, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) images derived from DWI for each patient. Multivariable logistic regression analysis was performed to develop the model, incorporating the radiomic signature, ADC value, and independent clinical risk factors. This was presented using a radiomic nomogram. The receiver operating characteristic (ROC) curve was utilized to assess the predictive efficacy of the radiomic nomogram in both the training and validation groups. The decision curve analysis was used to evaluate which model achieved the most net benefit. Results: The radiomic signature, which was made up of 10 selected features, was significantly associated with csPCa (P < 0.001 for both training and internal validation groups). The area under the curve (AUC) values of discriminating csPCa for the radiomics signature were 0.95 (training group), 0.86 (internal validation group), and 0.81 (external validation group). Multivariate logistic analysis identified the radiomic signature and ADC value as independent parameters of predicting csPCa. Then, the combination nomogram incorporating the radiomic signature and ADC value demonstrated a favorable classification capability with the AUC of 0.95 (training group), 0.93 (internal validation group), and 0.84 (external validation group). Appreciable clinical utility of this model was illustrated using the decision curve analysis for the nomogram. Conclusions: The nomogram, incorporating radiomic signature and ADC value, provided an individualized, potential approach for discriminating csPCa from ciPCa.
| S-EPMC7339043 | biostudies-literature
Project description:PurposeThis study aimed to develop and validate a predictive model for the assessment of clinically significant prostate cancer (csPCa) in men, prior to prostate biopsies, based on bi-parametric magnetic resonance imaging (bpMRI) and clinical parameters.Materials and methodsWe retrospectively analyzed 300 men with clinical suspicion of prostate cancer (prostate-specific antigen [PSA] ≥ 4.0 ng/mL and/or abnormal findings in a digital rectal examination), who underwent bpMRI-ultrasound fusion transperineal targeted and systematic biopsies in the same session, at a Korean university hospital. Predictive models, based on Prostate Imaging Reporting and Data Systems scores of bpMRI and clinical parameters, were developed to detect csPCa (intermediate/high grade [Gleason score ≥ 3+4]) and compared by analyzing the areas under the curves and decision curves.ResultsA predictive model defined by the combination of bpMRI and clinical parameters (age, PSA density) showed high discriminatory power (area under the curve, 0.861) and resulted in a significant net benefit on decision curve analysis. Applying a probability threshold of 7.5%, 21.6% of men could avoid unnecessary prostate biopsy, while only 1.0% of significant prostate cancers were missed.ConclusionThis predictive model provided a reliable and measurable means of risk stratification of csPCa, with high discriminatory power and great net benefit. It could be a useful tool for clinical decision-making prior to prostate biopsies.
| S-EPMC8524004 | biostudies-literature
Project description:Prostate cancer is one of the most prevalent cancers in the male population. Its diagnosis and classification rely on unspecific measures such as PSA levels and DRE, followed by biopsy, where an aggressiveness level is assigned in the form of Gleason Score. Efforts have been made in the past to use radiomics coupled with machine learning to predict prostate cancer aggressiveness from clinical images, showing promising results. Thus, the main goal of this work was to develop supervised machine learning models exploiting radiomic features extracted from bpMRI examinations, to predict biological aggressiveness; 288 classifiers were developed, corresponding to different combinations of pipeline aspects, namely, type of input data, sampling strategy, feature selection method and machine learning algorithm. On a cohort of 281 lesions from 183 patients, it was found that (1) radiomic features extracted from the lesion volume of interest were less stable to segmentation than the equivalent extraction from the whole gland volume of interest; and (2) radiomic features extracted from the whole gland volume of interest produced higher performance and less overfitted classifiers than radiomic features extracted from the lesions volumes of interest. This result suggests that the areas surrounding the tumour lesions offer relevant information regarding the Gleason Score that is ultimately attributed to that lesion.
| S-EPMC8657292 | biostudies-literature
Project description:PurposeSegmentation of cardiac medical images, an important step in measuring cardiac function, is usually performed either manually or semiautomatically. Fully automatic segmentation of the left ventricle (LV), the right ventricle (RV) as well as the myocardium of three-dimensional (3D) magnetic resonance (MR) images throughout the entire cardiac cycle (four-dimensional, 4D), remains challenging. This study proposes a deformable-based segmentation methodology for efficiently segmenting 4D (3D + t) cardiac MR images.MethodsThe proposed methodology first used the Hough transform and the local Gaussian distribution method (LGD) to segment the LV endocardial contours from cardiac MR images. Following this, a novel level set-based shape prior method was applied to generate the LV epicardial contours and the RV boundary.ResultsThis automatic image segmentation approach has been applied to studies on 17 subjects. The results demonstrated that the proposed method was efficient compared to manual segmentation, achieving a segmentation accuracy with average Dice values of 88.62 ± 5.47%, 87.35 ± 7.26%, and 82.63 ± 6.22% for the LV endocardial, LV epicardial, and RV contours, respectively.ConclusionsWe have presented a method for accurate LV and RV segmentation. Compared to three existing methods, the proposed method can successfully segment the LV and yield the highest Dice value. This makes it an option for clinical assessment of the volume, size, and thickness of the ventricles.
| S-EPMC6322927 | biostudies-literature