Search

Abstract Serial MRI is an essential assessment tool in prostate cancer (PCa) patients enrolled on active surveillance (AS). However, it has only moderate sensitivity for predicting histopathological tumour progression at follow-up, which is in part due to the subjective nature of its clinical reporting and variation among centres and readers. In this study, we used a long short-term memory (LSTM) recurrent neural network (RNN) to develop a time series radiomics (TSR) predictive model that analysed longitudinal changes in tumour-derived radiomic features across 297 scans from 76 AS patients, 28 with histopathological PCa progression and 48 with stable disease. Using leave-one-out cross-validation (LOOCV), we found that an LSTM-based model combining TSR and serial PSA density (AUC 0.86 [95% CI: 0.78–0.94]) significantly outperformed a model combining conventional delta-radiomics and delta-PSA density (0.75 [0.64–0.87]; p = 0.048) and achieved comparable performance to expert-performed serial MRI analysis using the Prostate Cancer Radiologic Estimation of Change in Sequential Evaluation (PRECISE) scoring system (0.84 [0.76–0.93]; p = 0.710). The proposed TSR framework, therefore, offers a feasible quantitative tool for standardising serial MRI assessment in PCa AS. It also presents a novel methodological approach to serial image analysis that can be used to support clinical decision-making in multiple scenarios, from continuous disease monitoring to treatment response evaluation. Key Points •LSTM RNN can be used to predict the outcome of PCa AS using time series changes in tumour-derived radiomic features and PSA density. •Using all available TSR features and serial PSA density yields a significantly better predictive performance compared to using just two time points within the delta-radiomics framework. •The concept of TSR can be applied to other clinical scenarios involving serial imaging, setting out a new field in AI-driven radiology research.

Rationale and Objectives: To develop and validate a radiomic model, with radiomic features extracted from breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) from a 1.5T scanner, for predicting the malignancy of masses with enhancement. Images were acquired using an 8-channel breast coil in the axial plane. The rationale behind this study is to show the feasibility of a radio-mics-powered model that could be integrated into the clinical practice by exploiting only standard-of-care DCE-MRI with the goal of reducing the required image pre-processing (ie, normalization and quantitative imaging map generation).Materials and Methods: 107 radiomic features were extracted from a manually annotated dataset of 111 patients, which was split into discovery and test sets. A feature calibration and pre-processing step was performed to find only robust non-redundant features. An indepth discovery analysis was performed to define a predictive model: for this purpose, a Support Vector Machine (SVM) was trained in a nested 5-fold cross-validation scheme, by exploiting several unsupervised feature selection methods. The predictive model performance was evaluated in terms of Area Under the Receiver Operating Characteristic (AUROC), specificity, sensitivity, PPV and NPV. The test was performed on unseen held-out data.Results: The model combining Unsupervised Discriminative Feature Selection (UDFS) and SVMs on average achieved the best performance on the blinded test set: AUROC = 0.725 +/- 0.091, sensitivity = 0.709 +/- 0.176, specificity = 0.741 +/- 0.114, PPV = 0.72 +/- 0.093, and NPV = 0.75 +/- 0.114.Conclusion: In this study, we built a radiomic predictive model based on breast DCE-MRI, using only the strongest enhancement phase, with promising results in terms of accuracy and specificity in the differentiation of malignant from benign breast lesions.

Unsupervised segmentation techniques, which do not require labeled data for training and can be more easily integrated into the clinical routine, represent a valid solution especially from a clinical feasibility perspective. Indeed, large-scale annotated datasets are not always available, undermining their immediate implementation and use in the clinic. Breast cancer is the most common cause of cancer death in women worldwide. In this study, breast lesion delineation in Dynamic Contrast Enhanced MRI (DCE-MRI) series was addressed by means of four popular unsupervised segmentation approaches: Split-and-Merge combined with Region Growing (SMRG), k-means, Fuzzy C-Means (FCM), and spatial FCM (sFCM). They represent well-established pattern recognition techniques that are still widely used in clinical research. Starting from the basic versions of these segmentation approaches, during our analysis, we identified the shortcomings of each of them, proposing improved versions, as well as developing ad hoc pre- and post-processing steps. The obtained experimental results, in terms of area-based—namely, Dice Index (DI), Jaccard Index (JI), Sensitivity, Specificity, False Positive Ratio (FPR), False Negative Ratio (FNR)—and distance-based metrics—Mean Absolute Distance (MAD), Maximum Distance (MaxD), Hausdorff Distance (HD)—encourage the use of unsupervised machine learning techniques in medical image segmentation. In particular, fuzzy clustering approaches (namely, FCM and sFCM) achieved the best performance. In fact, for area-based metrics, they obtained DI = 78.23% ± 6.50 (sFCM), JI = 65.90% ± 8.14 (sFCM), sensitivity = 77.84% ± 8.72 (FCM), specificity = 87.10% ± 8.24 (sFCM), FPR = 0.14 ± 0.12 (sFCM), and FNR = 0.22 ± 0.09 (sFCM). Concerning distance-based metrics, they obtained MAD = 1.37 ± 0.90 (sFCM), MaxD = 4.04 ± 2.87 (sFCM), and HD = 2.21 ± 0.43 (FCM). These experimental findings suggest that further research would be useful for advanced fuzzy logic techniques specifically tailored to medical image segmentation.

Objective: To analyse serial changes in MRI-derived tumour measurements and apparent diffusion coefficient (ADC) values in prostate cancer (PCa) patients on active surveillance (AS) with and without histopathological disease progression. Methods: This study included AS patients with biopsy-proven PCa with a minimum of two consecutive MR examinations and at least one repeat targeted biopsy. Tumour volumes, largest axial two-dimensional (2D) surface areas, and maximum diameters were measured on T2 weighted images (T2WI). ADC values were derived from the whole lesions, 2D areas, and small-volume regions of interest (ROIs) where tumours were most conspicuous. Areas under the ROC curve (AUCs) were calculated for combinations of T2WI and ADC parameters with optimal specificity and sensitivity. Results: 60 patients (30 progressors and 30 non-progressors) were included. In progressors, T2WI-derived tumour volume, 2D surface area, and maximum tumour diameter had a median increase of +99.5%,+55.3%, and +21.7% compared to +29.2%,+8.1%, and +6.9% in non-progressors (p < 0.005 for all). Follow-up whole-volume and small-volume ROIs ADC values were significantly reduced in progressors (−11.7% and −9.5%) compared to non-progressors (−6.1% and −1.6%) (p < 0.05 for both). The combined AUC of a relative increase in maximum tumour diameter by 20% and reduction in small-volume ADC by 10% was 0.67. Conclusion: AS patients show significant differences in tumour measurements and ADC values between those with and without histopathological disease progression. Advances in knowledge: This paper proposes specific clinical cut-offs for T2WI-derived maximum tumour diameter (+20%) and small-volume ADC (−10%) to predict histopathological PCa progression on AS and supplement subjective serial MRI assessment.

Multiparametric Magnetic Resonance Imaging (MRI) is the most sensitive imaging modality for breast cancer detection and is increasingly playing a key role in lesion characterization. In this context, accurate and reliable quantification of the shape and extent of breast cancer is crucial in clinical research environments. Since conventional lesion delineation procedures are still mostly manual, automated segmentation approaches can improve this time-consuming and operator-dependent task by annotating the regions of interest in a reproducible manner. In this work, a semi-automated and interactive approach based on the spatial Fuzzy C-Means (sFCM) algorithm is proposed, used to segment masses on dynamic contrast-enhanced (DCE) MRI of the breast. Our method was compared against existing approaches based on classic image processing, namely (i) Otsu’s method for thresholding-based segmentation, and (ii) the traditional FCM algorithm. A further comparison was performed against state-of-the-art Convolutional Neural Networks (CNNs) for medical image segmentation, namely SegNet and U-Net, in a 5-fold cross-validation scheme. The results showed the validity of the proposed approach, by significantly outperforming the competing methods in terms of the Dice similarity coefficient ( 84.47 ± 4.75 ). Moreover, a Pearson’s coefficient of ρ = 0.993 showed a high correlation between segmented volume and the gold standard provided by clinicians. Overall, the proposed method was confirmed to outperform the competing literature methods. The proposed computer-assisted approach could be deployed into clinical research environments by providing a reliable tool for volumetric and radiomics analyses.

This study investigates the use of the unsupervised deep learning framework VoxelMorph for deformable registration of longitudinal abdominopelvic CT images acquired in patients with bone metastases from breast cancer. The CT images were refined prior to registration by automatically removing the CT table and all other extra-corporeal components. To improve the learning capabilities of VoxelMorph when only a limited amount of training data is available, a novel incremental training strategy is proposed based on simulated deformations of consecutive CT images. In a 4-fold cross-validation scheme, the incremental training strategy achieved significantly better registration performance compared to training on a single volume. Although our deformable image registration method did not outperform iterative registration using NiftyReg (considered as a benchmark) in terms of registration quality, the registrations were approximately 300 times faster. This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations., Background and Objectives: Deep learning is being increasingly used for deformable image registration and unsupervised approaches, in particular, have shown great potential. However, the registration of abdominopelvic Computed Tomography (CT) images remains challenging due to the larger displacements compared to those in brain or prostate Magnetic Resonance Imaging datasets that are typically considered as benchmarks. In this study, we investigate the use of the commonly used unsupervised deep learning framework VoxelMorph for the registration of a longitudinal abdominopelvic CT dataset acquired in patients with bone metastases from breast cancer. Methods: As a pre-processing step, the abdominopelvic CT images were refined by automatically removing the CT table and all other extra-corporeal components. To improve the learning capabilities of the VoxelMorph framework when only a limited amount of training data is available, a novel incremental training strategy is proposed based on simulated deformations of consecutive CT images in the longitudinal dataset. This devised training strategy was compared against training on simulated deformations of a single CT volume. A widely used software toolbox for deformable image registration called NiftyReg was used as a benchmark. The evaluations were performed by calculating the Dice Similarity Coefficient (DSC) between manual vertebrae segmentations and the Structural Similarity Index (SSIM). Results: The CT table removal procedure allowed both VoxelMorph and NiftyReg to achieve significantly better registration performance. In a 4-fold cross-validation scheme, the incremental training strategy resulted in better registration performance compared to training on a single volume, with a mean DSC of 0.929±0.037 and 0.883±0.033, and a mean SSIM of 0.984±0.009 and 0.969±0.007, respectively. Although our deformable image registration method did not outperform NiftyReg in terms of DSC (0.988±0.003) or SSIM (0.995±0.002), the registrations were approximately 300 times faster. Conclusions: This study showed the feasibility of deep learning based deformable registration of longitudinal abdominopelvic CT images via a novel incremental training strategy based on simulated deformations.

Nearly half of patients with prostate cancer (PCa) harbour low- or intermediate-risk disease considered suitable for active surveillance (AS). However, up to 44% of patients discontinue AS within the first five years, highlighting the unmet clinical need for robust baseline risk-stratification tools that enable timely and accurate prediction of tumour progression. In this proof-of-concept study, we sought to investigate the added value of MRI-derived radiomic features to standard-of-care clinical parameters for improving baseline prediction of PCa progression in AS patients. Tumour T2-weighted imaging (T2WI) and apparent diffusion coefficient radiomic features were extracted, with rigorous calibration and pre-processing methods applied to select the most robust features for predictive modelling. Following leave-one-out cross-validation, the addition of T2WI-derived radiomic features to clinical variables alone improved the area under the ROC curve for predicting progression from 0.61 (95% confidence interval [CI] 0.481–0.743) to 0.75 (95% CI 0.64–0.86). These exploratory findings demonstrate the potential benefit of MRI-derived radiomics to add incremental benefit to clinical data only models in the baseline prediction of PCa progression on AS, paving the way for future multicentre studies validating the proposed model and evaluating its impact on clinical outcomes.

Funder: National Institute of Health Research Cambridge Biomedical Research Centre, Funder: Engineering and Physical Sciences Research Council Imaging Centre in Cambridge and Manchester, Funder: Cambridge Experimental Cancer Medicine Centre, Funder: Gates Cambridge Trust; doi: http://dx.doi.org/10.13039/501100005370, OBJECTIVES: To compare the performance of the PRECISE scoring system against several MRI-derived delta-radiomics models for predicting histopathological prostate cancer (PCa) progression in patients on active surveillance (AS). METHODS: The study included AS patients with biopsy-proven PCa with a minimum follow-up of 2 years and at least one repeat targeted biopsy. Histopathological progression was defined as grade group progression from diagnostic biopsy. The control group included patients with both radiologically and histopathologically stable disease. PRECISE scores were applied prospectively by four uro-radiologists with 5-16 years' experience. T2WI- and ADC-derived delta-radiomics features were computed using baseline and latest available MRI scans, with the predictive modelling performed using the parenclitic networks (PN), least absolute shrinkage and selection operator (LASSO) logistic regression, and random forests (RF) algorithms. Standard measures of discrimination and areas under the ROC curve (AUCs) were calculated, with AUCs compared using DeLong's test. RESULTS: The study included 64 patients (27 progressors and 37 non-progressors) with a median follow-up of 46 months. PRECISE scores had the highest specificity (94.7%) and positive predictive value (90.9%), whilst RF had the highest sensitivity (92.6%) and negative predictive value (92.6%) for predicting disease progression. The AUC for PRECISE (84.4%) was non-significantly higher than AUCs of 81.5%, 78.0%, and 80.9% for PN, LASSO regression, and RF, respectively (p = 0.64, 0.43, and 0.57, respectively). No significant differences were observed between AUCs of the three delta-radiomics models (p-value range 0.34-0.77). CONCLUSIONS: PRECISE and delta-radiomics models achieved comparably good performance for predicting PCa progression in AS patients. KEY POINTS: • The observed high specificity and PPV of PRECISE are complemented by the high sensitivity and NPV of delta-radiomics, suggesting a possible synergy between the two image assessment approaches. • The comparable performance of delta-radiomics to PRECISE scores applied by expert readers highlights the prospective use of the former as an objective and standardisable quantitative tool for MRI-guided AS follow-up. • The marginally superior performance of parenclitic networks compared to conventional machine learning algorithms warrants its further use in radiomics research.

Hyperpolarized 13C-MRI is an emerging tool for probing tissue metabolism by measuring 13C-label exchange between intravenously injected hyperpolarized [1–13C]pyruvate and endogenous tissue lactate. Here, we demonstrate that hyperpolarized 13C-MRI can be used to detect early response to neoadjuvant therapy in breast cancer. Seven patients underwent multiparametric 1H-MRI and hyperpolarized 13C-MRI before and 7–11 days after commencing treatment. An increase in the lactate-to-pyruvate ratio of approximately 20% identified three patients who, following 5–6 cycles of treatment, showed pathological complete response. This ratio correlated with gene expression of the pyruvate transporter MCT1 and lactate dehydrogenase A (LDHA), the enzyme catalyzing label exchange between pyruvate and lactate. Analysis of approximately 2,000 breast tumors showed that overexpression of LDHA and the hypoxia marker CAIX was associated with reduced relapse-free and overall survival. Hyperpolarized 13C-MRI represents a promising method for monitoring very early treatment response in breast cancer and has demonstrated prognostic potential. Significance: Hyperpolarized carbon-13 MRI allows response assessment in patients with breast cancer after 7–11 days of neoadjuvant chemotherapy and outperformed state-of-the-art and research quantitative proton MRI techniques.

Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstruct a 2D/3D single medical image to detect outliers either in the learned feature space or from high reconstruction loss. However, without considering continuity between multiple adjacent slices, they cannot directly discriminate diseases composed of the accumulation of subtle anatomical anomalies, such as Alzheimer's Disease (AD). Moreover, no study has shown how unsupervised anomaly detection is associated with either disease stages, various (i.e., more than two types of) diseases, or multi-sequence Magnetic Resonance Imaging (MRI) scans. Therefore, we propose unsupervised Medical Anomaly Detection Generative Adversarial Network (MADGAN), a novel two-step method using GAN-based multiple adjacent brain MRI slice reconstruction to detect brain anomalies at different stages on multi-sequence structural MRI: (Reconstruction) Wasserstein loss with Gradient Penalty + 100 L1 loss-trained on 3 healthy brain axial MRI slices to reconstruct the next 3 ones-reconstructs unseen healthy/abnormal scans; (Diagnosis) Average L2 loss per scan discriminates them, comparing the ground truth/reconstructed slices. For training, we use two different datasets composed of 1,133 healthy T1-weighted (T1) and 135 healthy contrast-enhanced T1 (T1c) brain MRI scans for detecting AD and brain metastases/various diseases, respectively. Our Self-Attention MADGAN can detect AD on T1 scans at a very early stage, Mild Cognitive Impairment (MCI), with Area Under the Curve (AUC) 0.727, and AD at a late stage with AUC 0.894, while detecting brain metastases on T1c scans with AUC 0.921., 23 pages, 11 figures, submitted to BMC Bioinformatics. Extended version of arXiv:1906.06114

Purpose To compare hyperpolarized carbon 13 (13C) MRI with dynamic contrast material–enhanced (DCE) MRI in the detection of early treatment response in breast cancer. Materials and Methods In this institutional review board–approved prospective study, a woman with triple-negative breast cancer (age, 49 years) underwent 13C MRI after injection of hyperpolarized [1–carbon 13 {13C}]-pyruvate and DCE MRI at 3 T at baseline and after one cycle of neoadjuvant therapy. The 13C-labeled lactate-to-pyruvate ratio derived from hyperpolarized 13C MRI and the pharmacokinetic parameters transfer constant (Ktrans) and washout parameter (kep) derived from DCE MRI were compared before and after treatment. Results Exchange of the 13C label between injected hyperpolarized [1-13C]-pyruvate and the endogenous lactate pool was observed, catalyzed by the enzyme lactate dehydrogenase. After one cycle of neoadjuvant chemotherapy, a 34% reduction in the 13C-labeled lactate-to-pyruvate ratio resulted in correct identification of the patient as a responder to therapy, which was subsequently confirmed via a complete pathologic response. However, DCE MRI showed an increase in mean Ktrans (132%) and mean kep (31%), which could be incorrectly interpreted as a poor response to treatment. Conclusion Hyperpolarized 13C MRI enabled successful identification of breast cancer response after one cycle of neoadjuvant chemotherapy and may improve response prediction when used in conjunction with multiparametric proton MRI. Published under a CC BY 4.0 license.

Lapa, P., Castelli, M., Gonçalves, I., Sala, E., & Rundo, L. (2020). A hybrid end-to-end approach integrating conditional random fields into CNNs for prostate cancer detection on MRI. Applied Sciences (Switzerland), 10(1), [338]. [Special Issue: Deep Learning and Neuro-Evolution Methods in Biomedicine and Bioinformatics)]. Doi: https://doi.org/10.3390/app10010338 Prostate Cancer (PCa) is the most common oncological disease inWestern men. Even though a growing effort has been carried out by the scientific community in recent years, accurate and reliable automated PCa detection methods on multiparametric Magnetic Resonance Imaging (mpMRI) are still a compelling issue. In this work, a Deep Neural Network architecture is developed for the task of classifying clinically significant PCa on non-contrast-enhanced MR images. In particular, we propose the use of Conditional Random Fields as a Recurrent Neural Network (CRF-RNN) to enhance the classificationperformance of XmasNet, a Convolutional Neural Network (CNN) architecture specifically tailored to the PROSTATEx17 Challenge. The devised approach builds a hybrid end-to-end trainable network, CRF-XmasNet, composed of an initial CNN component performing feature extraction and a CRF-based probabilistic graphical model component for structured prediction, without the need for two separate training procedures. Experimental results show the suitability of this method in terms ofclassification accuracy and training time, even though the high-variability of the observed results must be reduced before transferring the resulting architecture to a clinical environment. Interestingly, the use of CRFs as a separate postprocessing method achieves significantly lower performance with respect to the proposed hybrid end-to-end approach. The proposed hybrid end-to-end CRF-RNN approach yields excellent peak performance for all the CNN architectures taken into account, but it shows a high-variability, thus requiring future investigation on the integration of CRFs into a CNN. publishersversion published

Prostate canceris the most common cancer among US men. However, prostateimaging is still challenging despite the advances in multi-parametric magnetic resonance imaging (MRI), which provides both morphologic and functional information pertaining to the pathological regions. Alongwith whole prostate gland segmentation, distinguishingbetween the centralgland (CG) and peripheralzone (PZ) can guidetoward differential diagnosis, sincethe frequency andseverity of tumors differin these regions; however, theirboundary is often weakand fuzzy. This work presentsa preliminary study on deep learning to automatically delineate the CG and PZ, aiming at evaluating the generalization ability of convolutional neural networks (CNNs) on two multi-centric MRI prostate datasets. Especially, we compared three CNN-based architectures: SegNet, U-Net, and pix2pix. In such a context, the segmentation performances achieved with/without pre-training were compared in 4-fold cross-validation. In general, U-Net outperforms the other methods, especially when training and testing are performed on multiple datasets.

Background The accuracy of any radiation therapy delivery is limited by target organ translocation and distortion. Bladder filling is one of the recognised factors affecting prostate translocation and distortion. The purpose of our study was to evaluate the effect of bladder volume on prostate translocation and distortion by using detailed three-dimensional prostate delineation on MRI. Patients and methods Fifteen healthy male volunteers were recruited in this prospective, institutional review board-approved study. Each volunteer underwent 4 different drinking preparations prior to imaging, with MR images acquired pre- and post-void. MR images were co-registered by using bony landmarks and three-dimensional contouring was performed in order to assess the degree of prostate translocation and distortion. According to changes in bladder or rectum distention, subdivisions were made into bladder and rectal groups. Studies with concomitant change in both bladder and rectal volume were excluded. Results Forty studies were included in the bladder volume study group and 8 in the rectal volume study group. The differences in rectal volumes yielded higher levels of translocation (p < 0.01) and distortion (p = 0.02) than differences in bladder volume. Moderate correlation of prostate translocation with bladder filling was shown (r = 0.64, p < 0.01). There was no important prostate translocation when bladder volume change was < 2-fold (p < 0.01). Moderate correlation of prostate distortion with bladder filling was shown (r = 0.61, p < 0.01). Conclusions Bladder volume has a minimal effect on prostate translocation and effect on prostate distortion is negligible. Prostate translocation may be minimalised if there is < 2-fold increase in the bladder volume.

Due to the lackof available annotated medical images, accurate computer-assisteddiagnosis requires intensive data augmentation (DA) techniques, such as geometric/intensity transformationsof original images; however, those transformed images intrinsically havea similar distribution to the original ones, leading to limited performance improvement. To fill the data lack in the real imagedistribution, we synthesize brain contrast-enhanced magnetic resonance (MR) images—realistic but completely different fromthe original ones—using generative adversarial networks (GANs). This study exploits progressive growing of GANs (PGGANs), amultistage generative training method, to generate original-sized 256 × 256 MR images for convolutional neural network-based brain tumor detection, which is challenging via conventional GANs; difficulties arise due to unstable GAN training with high resolution and a variety of tumors in size, location, shape, and contrast. Our preliminary results show that this novel PGGAN-based DA method can achieve a promising performance improvement, when combined with classical DA, in tumor detection and also in other medical imaging tasks.

Introduction: More than a quarter of tumors are missed by magnetic resonance imaging/ultrasound (MRI/US) fusion-guided biopsy, the majority due to software-based misregistration. Transrectal approaches to biopsy are typically performed in the lateral decubitus position; conversely, diagnostic MRI is performed with the patient lying supine. Any position-related difference in prostate location or gland deformation could potentially exacerbate misregistration at subsequent biopsy. Methods: Fifteen healthy male volunteers (mean age 35.9 years, range 27–53) were included in this prospective, institutional review board-approved study. Each volunteer had an MRI performed in the supine position, followed by the second in the lateral decubitus position (mimicking a typical biopsy position). MRI images were co-registered and analyzed in order to assess prostate translocation and distortion. Results: Whole prostate translocation of ≥5 mm was observed in 20% of patients and ≥3 mm in 60% of patients. When dividing the prostate into prostatic sectors, the prostatic base demonstrated the largest positional difference. When plotting the translocation directions with relative volume difference, there was a moderate negative correlation trend in the latero-lateral direction. Only minimal distortion was observed, with similar distortion among all prostatic sectors. Conclusions: Positional change affects the prostate translocation, however, the effect on prostate distortion appears to be negligible. Prostate translocation in latero-lateral direction can be minimized with larger bladder volumes. Thereby, prostate translocation needs to be considered alongside software misregistration error; however, positional change should not affect software registration of MRI/US fusion-guided prostate biopsy.

BACKGROUND AND OBJECTIVES: Image segmentation represents one of the most challenging issues in medical image analysis to distinguish among different adjacent tissues in a body part. In this context, appropriate image pre-processing tools can improve the result accuracy achieved by computer-assisted segmentation methods. Taking into consideration images with a bimodal intensity distribution, image binarization can be used to classify the input pictorial data into two classes, given a threshold intensity value. Unfortunately, adaptive thresholding techniques for two-class segmentation work properly only for images characterized by bimodal histograms. We aim at overcoming these limitations and automatically determining a suitable optimal threshold for bimodal Magnetic Resonance (MR) images, by designing an intelligent image analysis framework tailored to effectively assist the physicians during their decision-making tasks. METHODS: In this work, we present a novel evolutionary framework for image enhancement, automatic global thresholding, and segmentation, which is here applied to different clinical scenarios involving bimodal MR image analysis: (i) uterine fibroid segmentation in MR guided Focused Ultrasound Surgery, and (ii) brain metastatic cancer segmentation in neuro-radiosurgery therapy. Our framework exploits MedGA as a pre-processing stage. MedGA is an image enhancement method based on Genetic Algorithms that improves the threshold selection, obtained by the efficient Iterative Optimal Threshold Selection algorithm, between the underlying sub-distributions in a nearly bimodal histogram. RESULTS: The results achieved by the proposed evolutionary framework were quantitatively evaluated, showing that the use of MedGA as a pre-processing stage outperforms the conventional image enhancement methods (i.e., histogram equalization, bi-histogram equalization, Gamma transformation, and sigmoid transformation), in terms of both MR image enhancement and segmentation evaluation metrics. CONCLUSIONS: Thanks to this framework, MR image segmentation accuracy is considerably increased, allowing for measurement repeatability in clinical workflows. The proposed computational solution could be well-suited for other clinical contexts requiring MR image analysis and segmentation, aiming at providing useful insights for differential diagnosis and prognosis.

Prostate cancer is the most common malignant tumors in men but prostate Magnetic Resonance Imaging (MRI) analysis remains challenging. Besides whole prostate gland segmentation, the capability to differentiate between the blurry boundary of the Central Gland (CG) and Peripheral Zone (PZ) can lead to differential diagnosis, since tumor's frequency and severity differ in these regions. To tackle the prostate zonal segmentation task, we propose a novel Convolutional Neural Network (CNN), called USE-Net, which incorporates Squeeze-and-Excitation (SE) blocks into U-Net. Especially, the SE blocks are added after every Encoder (Enc USE-Net) or Encoder-Decoder block (Enc-Dec USE-Net). This study evaluates the generalization ability of CNN-based architectures on three T2-weighted MRI datasets, each one consisting of a different number of patients and heterogeneous image characteristics, collected by different institutions. The following mixed scheme is used for training/testing: (i) training on either each individual dataset or multiple prostate MRI datasets and (ii) testing on all three datasets with all possible training/testing combinations. USE-Net is compared against three state-of-the-art CNN-based architectures (i.e., U-Net, pix2pix, and Mixed-Scale Dense Network), along with a semi-automatic continuous max-flow model. The results show that training on the union of the datasets generally outperforms training on each dataset separately, allowing for both intra-/cross-dataset generalization. Enc USE-Net shows good overall generalization under any training condition, while Enc-Dec USE-Net remarkably outperforms the other methods when trained on all datasets. These findings reveal that the SE blocks' adaptive feature recalibration provides excellent cross-dataset generalization when testing is performed on samples of the datasets used during training., 44 pages, 6 figures, Accepted to Neurocomputing, Co-first authors: Leonardo Rundo and Changhee Han

Medical imaging systems often require the application of image enhancement techniques to help physicians in anomaly/abnormality detection and diagnosis, as well as to improve the quality of images that undergo automated image processing. In this work we introduce MedGA, a novel image enhancement method based on Genetic Algorithms that is able to improve the appearance and the visual quality of images characterized by a bimodal gray level intensity histogram, by strengthening their two underlying sub-distributions. MedGA can be exploited as a pre-processing step for the enhancement of images with a nearly bimodal histogram distribution, to improve the results achieved by downstream image processing techniques. As a case study, we use MedGA as a clinical expert system for contrast-enhanced Magnetic Resonance image analysis, considering Magnetic Resonance guided Focused Ultrasound Surgery for uterine fibroids. The performances of MedGA are quantitatively evaluated by means of various image enhancement metrics, and compared against the conventional state-of-the-art image enhancement techniques, namely, histogram equalization, bi-histogram equalization, encoding and decoding Gamma transformations, and sigmoid transformations. We show that MedGA considerably outperforms the other approaches in terms of signal and perceived image quality, while preserving the input mean brightness. MedGA may have a significant impact in real healthcare environments, representing an intelligent solution for Clinical Decision Support Systems in radiology practice for image enhancement, to visually assist physicians during their interactive decision-making tasks, as well as for the improvement of downstream automated processing pipelines in clinically useful measurements.

Despite of the development of advanced segmentation techniques, achieving accurate and reproducible gross tumor volume (GTV) segmentation results is still an important challenge in neuro-radiosurgery. Nowadays, magnetic resonance imaging (MRI) is the most prominent modality in radiation therapy for soft-tissue anatomical districts. Gamma Knife stereotactic neuro-radiosurgery is a minimally invasive technology for dealing with inaccessible or insufficiently treated tumors with traditional surgery or radiotherapy. During a treatment planning phase, the GTV is generally contoured by experienced neurosurgeons and radiation oncologists using fully manual segmentation procedures on MR images. Unfortunately, this operative methodology is definitely time-expensive and operator-dependent. Delineation result repeatability, in terms of both intra- and inter-operator reliability, can be achieved only by using computer-assisted approaches. In this paper a novel semi-automatic seeded image segmentation method, based on a cellular automata model, for MRI brain cancer detection and delineation is proposed. This approach, called GTVcut, employs an adaptive seed selection strategy and helps to segment the GTV, by identifying the target volume to be treated using the Gamma Knife device. The accuracy of GTVcut was evaluated on a dataset composed of 32 brain cancers, using both spatial overlap-based and distance-based metrics. The achieved experimental results are very reproducible, showing the effectiveness and the clinical feasibility of the proposed approach.

Computer applications for diagnostic medical imaging provide generally a wide range of tools to support physicians in their daily diagnosis activities. Unfortunately, some functionalities are specialized for specific diseases or imaging modalities, while other ones are useless for the images under investigation. Nevertheless, the corresponding Graphical User Interface (GUI) widgets are still present on the screen reducing the image visualization area. As a consequence, the physician may be affected by cognitive overload and visual stress causing a degradation of performances, mainly due to unuseful widgets. In clinical environments, a GUI must represent a sequence of steps for image investigation following a well-defined workflow. This paper proposes a software framework aimed at addressing the issues outlined before. Specifically, we designed a DICOM based mechanism of data-driven GUI generation, referring to the examined body part and imaging modality as well as to the medical image analysis task to perform. In this way, the self-configuring GUI is generated on-the-fly, so that just specific functionalities are active according to the current clinical scenario. Such a solution provides also a tight integration with the DICOM standard, which considers various aspects of the technology in medicine but does not address GUI specification issues. The proposed workflow is designed for diagnostic workstations with a local file system on an interchange media acting inside or outside the hospital ward. Accordingly, the DICOMDIR conceptual data model, defined by a hierarchical structure, is exploited and extended to include the GUI information thanks to a new Information Object Module (IOM), which reuses the DICOM information model. The proposed framework exploits the DICOM standard representing an enabling technology for an auto-consistent solution in medical diagnostic applications. In this paper we present a detailed description of the framework, its software design, and a proof-of-concept implementation as a suitable plug-in of the OsiriX imaging software.

Uterine fibroids are benign tumors that can affect female patients during reproductive years. Magnetic resonance-guided focused ultrasound (MRgFUS) represents a noninvasive approach that uses thermal ablation principles to treat symptomatic fibroids. During traditional treatment planning, uterus, fibroids, and surrounding organs at risk must be manually marked on MR images by an operator. After treatment, an operator must segment, again manually, treated areas to evaluate the non-perfused volume (NPV) inside the fibroids. Both pre- and post-treatment procedures are time-consuming and operator-dependent. This paper presents a novel method, based on an advanced direct region detection model, for fibroid segmentation in MR images to address MRgFUS post-treatment segmentation issues. An incremental procedure is proposed: split-and-merge algorithm results are employed as multiple seed-region selections by an adaptive region growing procedure. The proposed approach segments multiple fibroids with different pixel intensity, even in the same MR image. The method was evaluated using area-based and distance-based metrics and was compared with other similar works in the literature. Segmentation results, performed on 14 patients, demonstrated the effectiveness of the proposed approach showing a sensitivity of 84.05 %, a specificity of 92.84%, and a speedup factor of 1.56× with respect to classic region growing implementations (average values).

Prostate imaging is a very critical issue in the clinical practice, especially for diagnosis, therapy, and staging of prostate cancer. Magnetic Resonance Imaging (MRI) can provide both morphologic and complementary functional information of tumor region. Manual detection and segmentation of prostate gland and carcinoma on multispectral MRI data is not easily practicable in the clinical routine because of the long times required by experienced radiologists to analyze several types of imaging data. In this paper, a fully automatic image segmentation method, exploiting an unsupervised Fuzzy C-Means (FCM) clustering technique for multispectral T1-weighted and T2-weighted MRI data processing, is proposed. This approach enables prostate segmentation and automatic gland volume calculation. Segmentation trials have been performed on a dataset composed of 7 patients affected by prostate cancer, using both area-based and distance-based metrics for its evaluation. The achieved experimental results are encouraging, showing good segmentation accuracy.

The aim of this study is to combine Biological Target Volume (BTV) segmentation and Gross Target Volume (GTV) segmentation in stereotactic neurosurgery.Our goal is to enhance Clinical Target Volume (CTV) definition, including metabolic and morphologic information, for treatment planning and patient follow-up.We propose a fully automatic approach for multimodal PET and MR image segmentation. This method is based on the Random Walker (RW) and Fuzzy C-Means clustering (FCM) algorithms. A total of 19 brain metastatic tumors, undergone stereotactic neuro-radiosurgery, were retrospectively analyzed. A framework for the evaluation of multimodal PET/MRI segmentation is presented, considering volume-based, overlap-based and spatial distance-based metrics. Statistics was also included to measure correlation. Finally, a five-point Likert scale was used to provide a qualitative evaluation about the clinical value of the proposed multimodal approach. Background and objectives: Nowadays, clinical practice in Gamma Knife treatments is generally based on MRI anatomical information alone. However, the joint use of MRI and PET images can be useful for considering both anatomical and metabolic information about the lesion to be treated. In this paper we present a co-segmentation method to integrate the segmented Biological Target Volume (BTV), using [11C]-Methionine-PET (MET-PET) images, and the segmented Gross Target Volume (GTV), on the respective co-registered MR images. The resulting volume gives enhanced brain tumor information to be used in stereotactic neuro-radiosurgery treatment planning. GTV often does not match entirely with BTV, which provides metabolic information about brain lesions. For this reason, PET imaging is valuable and it could be used to provide complementary information useful for treatment planning. In this way, BTV can be used to modify GTV, enhancing Clinical Target Volume (CTV) delineation.Methods: A novel fully automatic multimodal PET/MRI segmentation method for Leksell Gamma Knife treatments is proposed. This approach improves and combines two computer-assisted and operator-independent single modality methods, previously developed and validated, to segment BTV and GTV from PET and MR images, respectively. In addition, the GTV is utilized to combine the superior contrast of PET images with the higher spatial resolution of MRI, obtaining a new BTV, called BTVMRI. A total of 19 brain metastatic tumors, undergone stereotactic neuro-radiosurgery, were retrospectively analyzed. A framework for the evaluation of multimodal PET/MRI segmentation is also presented. Overlap-based and spatial distance-based metrics were considered to quantify similarity concerning PET and MRI segmentation approaches. Statistics was also included to measure correlation among the different segmentation processes. Since it is not possible to define a gold-standard CTV according to both MRI and PET images without treatment response assessment, the feasibility and the clinical value of BTV integration in Gamma Knife treatment planning were considered. Therefore, a qualitative evaluation was carried out by three experienced clinicians.Results: The achieved experimental results showed that GTV and BTV segmentations are statistically correlated (Spearman's rank correlation coefficient: 0.898) but they have low similarity degree (average Dice Similarity Coefficient: 61.8714.64). Therefore, volume measurements as well as evaluation metrics values demonstrated that MRI and PET convey different but complementary imaging information. GTV and BTV could be combined to enhance treatment planning. In more than 50% of cases the CTV was strongly or moderately conditioned by metabolic imaging. Especially, BTVMRI enhanced the CTV more accurately than BTV in 25% of cases.Conclusions: The proposed fully automatic multimodal PET/MRI segmentation method is a valid operator-independent methodology helping the clinicians to define a CTV that includes both metabolic and morphologic information. BTVMRI and GTV should be considered for a comprehensive treatment planning. Display Omitted

Prostate imaging analysis is difficult in diagnosis, therapy, and staging of prostate cancer. In clinical practice, Magnetic Resonance Imaging (MRI) is increasingly used thanks to its morphologic and functional capabilities. However, manual detection and delineation of prostate gland on multispectral MRI data is currently a time-expensive and operator-dependent procedure. Efficient computer-assisted segmentation approaches are not yet able to address these issues, but rather have the potential to do so. In this paper, a novel automatic prostate MR image segmentation method based on the Fuzzy C-Means (FCM) clustering algorithm, which enables multispectral T1-weighted (T1w) and T2-weighted (T2w) MRI anatomical data processing, is proposed. This approach, using an unsupervised Machine Learning technique, helps to segment the prostate gland effectively. A total of 21 patients with suspicion of prostate cancer were enrolled in this study. Volume-based metrics, spatial overlap-based metrics and spatial distance-based metrics were used to quantitatively evaluate the accuracy of the obtained segmentation results with respect to the gold-standard boundaries delineated manually by an expert radiologist. The proposed multispectral segmentation method was compared with the same processing pipeline applied on either T2w or T1w MR images alone. The multispectral approach considerably outperforms the monoparametric ones, achieving an average Dice Similarity Coefficient 90.77 ± 1.75, with respect to 81.90 ± 6.49 and 82.55 ± 4.93 by processing T2w and T1w imaging alone, respectively. Combining T2w and T1w MR image structural information significantly enhances prostate gland segmentation by exploiting the uniform gray appearance of the prostate on T1w MRI.

Gross Tumor Volume (GTV) segmentation on medical images is an open issue in neuro-radiosurgery. Magnetic Resonance Imaging (MRI) is the most promi-nent modality in radiation therapy for soft-tissue anatomical districts. Gamma Knife stereotactic neuro-radiosurgery is a mini-invasive technique used to deal with inaccessible or insufficiently treated tumors. During the planning phase, the GTV is usually contoured by radiation oncologists using a manual segmentation procedure on MR images. This methodology is certainly time-consuming and op-erator-dependent. Delineation result repeatability, in terms of both intra- and inter-operator reliability, is only obtained by using computer-assisted approaches. In this paper a novel semi-automatic segmentation method, based on Cellular Au-tomata, is proposed. The developed approach allows for the GTV segmentation and computes the lesion volume to be treated. The method was evaluated on 10 brain cancers, using both area-based and distance-based metrics.

Nowadays, radiation treatment is beginning to intensively use MRI thanks to its greater ability to discriminate healthy and diseased soft-tissues. Leksell Gamma Knife® is a radio-surgical device, used to treat different brain lesions, which are often inaccessible for conventional surgery, such as benign or malignant tumors. Currently, the target to be treated with radiation therapy is contoured with slice-by-slice manual segmentation on MR datasets. This approach makes the segmentation procedure time consuming and operator-dependent. The repeatability of the tumor boundary delineation may be ensured only by using automatic or semiautomatic methods, supporting clinicians in the treatment planning phase. This article proposes a semiautomatic segmentation method, based on the unsupervised Fuzzy C-Means clustering algorithm. Our approach helps segment the target and automatically calculates the lesion volume. To evaluate the performance of the proposed approach, segmentation tests on 15 MR datasets were performed, using both area-based and distance-based metrics, obtaining the following average values: Similarity Index = 95.59%, Jaccard Index = 91.86%, Sensitivity = 97.39%, Specificity = 94.30%, Mean Absolute Distance = 0.246[pixels], Maximum Distance = 1.050[pixels], and Hausdorff Distance = 1.365[pixels]. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 213–225, 2015

PurposeMagnetic Resonance guided Focused UltraSound (MRgFUS) represents a non-invasive surgical approach that uses thermal ablation to treat uterine fibroids. After the MRgFUS treatment, an operator must manually segment the treated fibroid areas to evaluate the NonPerfused Volume (NPV). This manual approach is operator-dependent, introducing issues of result reproducibility, which could lead to errors in the subsequent follow-up phase. Moreover, manual segmentation is time-consuming, and can have a negative impact on the optimization of both machine-time and operator-time. MethodTo address these issues, in this paper a novel fully automatic method based on the unsupervised Fuzzy C-Means clustering and iterative optimal threshold selection algorithms for uterus and fibroid segmentation is proposed. The developed method could be used to enhance the current manual methodology performed by healthcare operators for post-operative NPV evaluation in uterine fibroid MRgFUS treatments. ResultsThe proposed method was tested on 15 MR datasets of 15 different patients with uterine fibroids and evaluated using area-based and distance-based metrics. A comparison of extracted volume was also performed. Average values for fibroid (ROT) segmentation are SDI=88.67%, JI=80.70%, SE=89.79%, SP=88.73%, MAD=2.200 pixels], MAXD=6.233 pixels] and HD=2.988 pixels]. Moreover, to make a quantitative evaluation of this method, our experimental results were compared with similar literature approaches. ConclusionsThe proposed method provides a practical approach for the automatic evaluation of the boundary and volume of ablated fibroid regions, without any external user input. The achieved segmentation results show the validity and the effectiveness of the proposed solution. Display Omitted The proposed method performs a fully automatic uterus and fibroids segmentation.We provide the boundary and volume of ablated fibroid regions and uterus.Our approach is based on FCM and iterative optimal threshold selection algorithms.This solution could optimize the current operative MRgFUS methodology.Our approach can improve the follow-up of patients undergone MRgFUS treatments.