Positional contrastive learning for improved thigh muscle segmentation in MR images.

The accurate segmentation of individual muscles is essential for quantitative MRI analysis of thigh images. Deep learning methods have achieved state-of-the-art results in segmentation, but they require large numbers of labeled data to perform well. However, labeling individual thigh muscles slice by slice for numerous volumes is a laborious and time-consuming task, which limits the availability of annotated datasets. To address this challenge, self-supervised learning (SSL) emerges as a promising technique to enhance model performance by pretraining the model on unlabeled data. A recent approach, called positional contrastive learning, exploits the information given by the axial position of the slices to learn features transferable on the segmentation task. The aim of this work was to propose positional contrastive SSL for the segmentation of individual thigh muscles from MRI acquisitions in a population of elderly healthy subjects and to evaluate it on different levels of limited annotated data. An unlabeled dataset of 72 T1w MRI thigh acquisitions was available for SSL pretraining, while a labeled dataset of 52 volumes was employed for the final segmentation task, split into training and test sets. The effectiveness of SSL pretraining to fine-tune a U-Net architecture for thigh muscle segmentation was compared with that of a randomly initialized model (RND), considering an increasing number of annotated volumes (S = 1, 2, 5, 10, 20, 30, 40). Our results demonstrated that SSL yields substantial improvements in Dice similarity coefficient (DSC) when using a very limited number of labeled volumes (e.g., for S $$ S $$ = 1, DSC 0.631 versus 0.530 for SSL and RND, respectively). Moreover, enhancements are achievable even when utilizing the full number of labeled subjects, with DSC = 0.927 for SSL and 0.924 for RND. In conclusion, positional contrastive SSL was effective in obtaining more accurate thigh muscle segmentation, even with a very low number of labeled data, with a potential impact of speeding up the annotation process in clinics.

A supervised deep neural network approach with standardized targets for enhanced accuracy of IVIM parameter estimation from multi-SNR images.

Extraction of intravoxel incoherent motion (IVIM) parameters from noisy diffusion-weighted (DW) images using a biexponential fitting model is computationally challenging, and the reliability of the estimated perfusion-related quantities represents a limitation of this technique. Artificial intelligence can overcome the current limitations and be a suitable solution to advance use of this technique in both preclinical and clinical settings. The purpose of this work was to develop a deep neural network (DNN) approach, trained on numerical simulated phantoms with different signal to noise ratios (SNRs), to improve IVIM parameter estimation. The proposed approach is based on a supervised fully connected DNN having 3 hidden layers, 18 inputs and 3 targets with standardized values. 14 × 103 simulated DW images, based on a Shepp-Logan phantom, were randomly generated with varying SNRs (ranging from 10 to 100). 7 × 103 images (1000 for each SNR) were used for training. Performance accuracy was assessed in simulated images and the proposed approach was compared with the state-of-the-art Bayesian approach and other DNN algorithms. The DNN approach was also evaluated in vivo on a high-field MRI preclinical scanner. Our DNN approach showed an overall improvement in accuracy when compared with the Bayesian approach and other DNN methods in most of the simulated conditions. The in vivo results demonstrated the feasibility of the proposed approach in real settings and generated quantitative results comparable to those obtained using the Bayesian and unsupervised approaches, especially for D and f, and with lower variability in homogeneous regions. The DNN architecture proposed in this work outlines two innovative features as compared with other studies: (1) the use of standardized targets to improve the estimation of parameters, and (2) the implementation of a single DNN to enhance the IVIM fitting at different SNRs, providing a valuable alternative tool to compute IVIM parameters in conditions of high background noise.

A novel bayesian approach with conditional autoregressive specification for intravoxel incoherent motion diffusion-weighted MRI.

The Intra-Voxel Incoherent Motion (IVIM) model is largely adopted to estimate slow and fast diffusion coefficients of water molecules in biological tissues, which are used in cancer applications. The most reported fitting approach is a voxel-wise segmented non-linear least square, whereas Bayesian approaches with a direct fit, also considering spatial regularization, were proposed too. In this work a novel segmented Bayesian method was proposed, also in combination with a spatial regularization through a Conditional Autoregressive (CAR) prior specification. The two segmented Bayesian approaches, with and without CAR specification, were compared with two standard least-square and a direct Bayesian fitting methods. All approaches were tested on simulated images and real data of patients with head-and-neck and rectal cancer. Estimation accuracy and maps noisiness were quantified on simulated images, whereas the coefficient of variation and the goodness of fit were evaluated for real data. Both versions of the segmented Bayesian approach outperformed the standard methods on simulated images for pseudo-diffusion (D∗ ) and perfusion fraction (f), whilst the segmented least-square fitting remained the less biased for the diffusion coefficient (D). On real data, Bayesian approaches provided the less noisy maps, and the two Bayesian methods without CAR generally estimated lower values for f and D∗ coefficients with respect to the other approaches. The proposed segmented Bayesian approaches were superior, in terms of estimation accuracy and maps quality, to the direct Bayesian model and the least-square fittings. The CAR method improved the estimation accuracy, especially for D∗ .

Triggered intravoxel incoherent motion MRI for the assessment of calf muscle perfusion during isometric intermittent exercise.

The main aim of this paper was to propose triggered intravoxel incoherent motion (IVIM) imaging sequences for the evaluation of perfusion changes in calf muscles before, during and after isometric intermittent exercise. Twelve healthy volunteers were involved in the study. The subjects were asked to perform intermittent isometric plantar flexions inside the MRI bore. MRI of the calf muscles was performed on a 3.0 T scanner and diffusion-weighted (DW) images were obtained using eight different b values (0 to 500 s/mm2 ). Acquisitions were performed at rest, during exercise and in the subsequent recovery phase. A motion-triggered echo-planar imaging DW sequence was implemented to avoid movement artifacts. Image quality was evaluated using the average edge strength (AES) as a quantitative metric to assess the motion artifact effect. IVIM parameters (diffusion D, perfusion fraction f and pseudo-diffusion D*) were estimated using a segmented fitting approach and evaluated in gastrocnemius and soleus muscles. No differences were observed in quality of IVIM images between resting state and triggered exercise, whereas the non-triggered images acquired during exercise had a significantly lower value of AES (reduction of more than 20%). The isometric intermittent plantar-flexion exercise induced an increase of all IVIM parameters (D by 10%; f by 90%; D* by 124%; fD* by 260%), in agreement with the increased muscle perfusion occurring during exercise. Finally, IVIM parameters reverted to the resting values within 3 min during the recovery phase. In conclusion, the IVIM approach, if properly adapted using motion-triggered sequences, seems to be a promising method to investigate muscle perfusion during isometric exercise.

Early changes of parotid density and volume predict modifications at the end of therapy and intensity of acute xerostomia.

PURPOSE: To quantitatively assess the predictive power of early variations of parotid gland volume and density on final changes at the end of therapy and, possibly, on acute xerostomia during IMRT for head-neck cancer. MATERIALS AND METHODS: Data of 92 parotids (46 patients) were available. Kinetics of the changes during treatment were described by the daily rate of density (rΔρ) and volume (rΔvol) variation based on weekly diagnostic kVCT images. Correlation between early and final changes was investigated as well as the correlation with prospective toxicity data (CTCAEv3.0) collected weekly during treatment for 24/46 patients. RESULTS: A higher rΔρ was observed during the first compared to last week of treatment (-0,50 vs -0,05HU, p-value = 0.0001). Based on early variations, a good estimation of the final changes may be obtained (Δρ: AUC = 0.82, p = 0.0001; Δvol: AUC = 0.77, p = 0.0001). Both early rΔρ and rΔvol predict a higher "mean" acute xerostomia score (≥ median value, 1.57; p-value = 0.01). Median early density rate changes for patients with mean xerostomia score ≥ / < 1.57 were -0.98 vs -0.22 HU/day respectively (p = 0.05). CONCLUSIONS: Early density and volume variations accurately predict final changes of parotid glands. A higher longitudinally assessed score of acute xerostomia is well predicted by higher rΔρ and rΔvol in the first two weeks of treatment: best cut-off values were -0.50 HU/day and -380 mm(3)/day for rΔρ and rΔvol respectively. Further studies are necessary to definitively assess the potential of early density/volume changes in identifying more sensitive patients at higher risk of experiencing xerostomia.

Uncertainty quantification in multi-class segmentation: Comparison between Bayesian and non-Bayesian approaches in a clinical perspective.

BACKGROUND: Automatic segmentation techniques based on Convolutional Neural Networks (CNNs) are widely adopted to automatically identify any structure of interest from a medical image, as they are not time consuming and not subject to high intra- and inter-operator variability. However, the adoption of these approaches in clinical practice is slowed down by some factors, such as the difficulty in providing an accurate quantification of their uncertainty. PURPOSE: This work aims to evaluate the uncertainty quantification provided by two Bayesian and two non-Bayesian approaches for a multi-class segmentation problem, and to compare the risk propensity among these approaches, considering CT images of patients affected by renal cancer (RC). METHODS: Four uncertainty quantification approaches were implemented in this work, based on a benchmark CNN currently employed in medical image segmentation: two Bayesian CNNs with different regularizations (Dropout and DropConnect), named BDR and BDC, an ensemble method (Ens) and a test-time augmentation (TTA) method. They were compared in terms of segmentation accuracy, using the Dice score, uncertainty quantification, using the ratio of correct-certain pixels (RCC) and incorrect-uncertain pixels (RIU), and with respect to inter-observer variability in manual segmentation. They were trained with the Kidney and Kidney Tumor Segmentation Challenge launched in 2021 (Kits21), for which multi-class segmentations of kidney, RC, and cyst on 300 CT volumes are available. Moreover, they were tested considering this and other two public renal CT datasets. RESULTS: Accuracy results achieved large differences across the structures of interest for all approaches, with an average Dice score of 0.92, 0.58, and 0.21 for kidney, tumor, and cyst, respectively. In terms of uncertainties, TTA provided the highest uncertainty, followed by Ens and BDC, whereas BDR provided the lowest, and minimized the number of incorrect certain pixels worse than the other approaches. Again, large differences were seen across the three structures in terms of RCC and RIU. These metrics were associated with different risk propensity, as BDR was the most risk-taking approach, able to provide higher accuracy in its prediction, but failing to assign uncertainty on incorrect segmentation in every case. The other three approaches were more conservative, providing large uncertainty regions, with the drawback of giving alert also on correct areas. Finally, the analysis of the inter-observer segmentation variability showed a significant variation among the four approaches on the external dataset, with BDR reporting the lowest agreement (Dice = 0.82), and TTA obtaining the highest score (Dice = 0.94). CONCLUSIONS: Our outcomes highlight the importance of quantifying the segmentation uncertainty and that decision-makers can choose the approach most in line with the risk propensity degree required by the application and their policy.

The quantification of IntraVoxel incoherent motion - MRI maps cannot preserve texture information: An evaluation based on simulated and in-vivo images.

BACKGROUND: Radiomics can be applied on parametric maps obtained from IntraVoxel Incoherent Motion (IVIM) MRI to characterize heterogeneity in diffusion and perfusion tissue properties. The purpose of this work is to assess the accuracy and reproducibility of radiomic features computed from IVIM maps using different fitting methods. METHODS: 200 digitally simulated IVIM-MRI images with various SNR containing different combinations of texture patterns were generated from ground truth maps of true diffusion D, pseudo-diffusion D* and perfusion fraction f. Four different methods (segmented least-square LSQ, Bayesian, supervised and unsupervised deep learning DL) were adopted to quantify IVIM maps from simulations and from two real images of liver tumor. Radiomic features were computed from ground truth and estimated maps. Accuracy and reproducibility among quantification methods were assessed. RESULTS: Almost 50% of radiomic features computed from D maps using DL approaches, 36% using Bayes and 27% using LSQ presented errors lower than 50%. Radiomic features from f and D* maps were accurate only if computed using DL methods from histogram. High reproducibility (ICC>0.8) was found only for D maps among DL and Bayes methods, whereas features from f and D* maps were less reproducible, with LSQ approach in lower agreement with the others. CONCLUSIONS: Texture patterns were preserved and correctly estimated only on D maps, except for LSQ approach. We suggest limiting radiomic analysis only to histogram and some texture features from D maps, to histogram features from f maps, and to avoid it on D* maps.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review.

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Automatic Feature Construction Based on Genetic Programming for Survival Prediction in Lung Cancer Using CT Images.

In the radiomics workflow, machine learning builds classification models from a set of input features. However, some features can be irrelevant and redundant, reducing the classification performance. This paper proposes using the Genetic Programming (GP) algorithm to automatically construct a reduced number of independent and relevant radiomic features. The proposed method is applied to patients affected by Non-Small Cell Lung Cancer (NSCLC) with pre-operative computed tomography (CT) images to predict the two-year survival by the use of linear classifiers. The model built using GP features is compared with benchmark models built using traditional features. The use of the GP algorithm increased classification performance: [Formula: see text] for the proposed model vs. [Formula: see text] and 0.64 for the benchmark models. Hence, the proposed approach better stratifies patients at high and low risk according to their overall postoperative survival time.

Theranostics in Boron Neutron Capture Therapy.

Boron neutron capture therapy (BNCT) has the potential to specifically destroy tumor cells without damaging the tissues infiltrated by the tumor. BNCT is a binary treatment method based on the combination of two agents that have no effect when applied individually: 10B and thermal neutrons. Exclusively, the combination of both produces an effect, whose extent depends on the amount of 10B in the tumor but also on the organs at risk. It is not yet possible to determine the 10B concentration in a specific tissue using non-invasive methods. At present, it is only possible to measure the 10B concentration in blood and to estimate the boron concentration in tissues based on the assumption that there is a fixed uptake of 10B from the blood into tissues. On this imprecise assumption, BNCT can hardly be developed further. A therapeutic approach, combining the boron carrier for therapeutic purposes with an imaging tool, might allow us to determine the 10B concentration in a specific tissue using a non-invasive method. This review provides an overview of the current clinical protocols and preclinical experiments and results on how innovative drug development for boron delivery systems can also incorporate concurrent imaging. The last section focuses on the importance of proteomics for further optimization of BNCT, a highly precise and personalized therapeutic approach.

T2w-MRI signal normalization affects radiomics features reproducibility.

PURPOSE: Despite its increasing application, radiomics has not yet demonstrated a solid reliability, due to the difficulty in replicating analyses. The extraction of radiomic features from clinical MRI (T1w/T2w) presents even more challenges because of the absence of well-defined units (e.g. HU). Some preprocessing steps are required before the estimation of radiomic features and one of this is the intensity normalization, that can be performed using different methods. The aim of this work was to evaluate the effect of three different normalization techniques, applied on T2w-MRI images of the pelvic region, on radiomic features reproducibility. METHODS: T2w-MRI acquired before (MRI1) and 12 months after radiotherapy (MRI2) from 14 patients treated for prostate cancer were considered. Four different conditions were analyzed: (a) the original MRI (No_Norm); (b) MRI normalized by the mean image value (Norm_Mean); (c) MRI normalized by the mean value of the urine in the bladder (Norm_ROI); (d) MRI normalized by the histogram-matching method (Norm_HM). Ninety-one radiomic features were extracted from three organs of interest (prostate, internal obturator muscles and bulb) at both time-points and on each image discretized using a fixed bin-width approach and the difference between the two time-points was calculated (Δfeature). To estimate the effect of normalization methods on the reproducibility of radiomic features, ICC was calculated in three analyses: (a) considering the features extracted on MRI2 in the four conditions together and considering the influence of each method separately, with respect to No_Norm; (b) considering the features extracted on MRI2 in the four conditions with respect to the inter-observer variability in region of interest (ROI) contouring, considering also the effect of the discretization approach; (c) considering Δfeature to evaluate if some indices can recover some consistency when differences are calculated. RESULTS: Nearly 60% of the features have shown poor reproducibility (ICC < 0.5) on MRI2 and the method that most affected features reliability was Norm_ROI (average ICC of 0.45). The other two methods were similar, except for first-order features, where Norm_HM outperformed Norm_Mean (average ICC = 0.33 and 0.76 for Norm_Mean and Norm_HM, respectively). In the inter-observer setting, the number of reproducible features varied in the three structures, being higher in the prostate than in the penile bulb and in the obturators. The analysis on Δfeature highlighted that more than 60% of the features were not consistent with respect to the normalization method and confirmed the high reproducibility of the features between Norm_Mean and Norm_HM, whereas Norm_ROI was the less reproducible method. CONCLUSIONS: The normalization process impacts the reproducibility of radiomic features, both in terms of changes in the image information content and in the inter-observer setting. Among the considered methods, Norm_Mean and Norm_HM seem to provide the most reproducible features with respect to the original image and also between themselves, whereas Norm_ROI generates less reproducible features. Only a very small subset of feature remained reproducible and independent in any tested condition, regardless the ROI and the adopted algorithm: skewness or kurtosis, correlation and one among Imc2, Idmn and Idn from GLCM group.

A new Probabilistic Active Contour region-based method for multiclass medical image segmentation.

In medical imaging, the availability of robust and accurate automatic segmentation methods is very important for a user-independent and time-saving delineation of regions of interest. In this work, we present a new variational formulation for multiclass image segmentation based on active contours and probability density functions demonstrating that the method is fast, accurate, and effective for MRI brain image segmentation. We define an energy function assuming that the regions to segment are independent. The first term of this function measures how much the pixels belong to each class and forces the regions to be disjoint. In order for this term to be outlier-resistant, probability density functions were used allowing to define the structures to be segmented. The second one is the classical regularization term which constrains the border length of each region removing inhomogeneities and noise. Experiments with synthetic and real images showed that this approach is robust to noise and presents an accuracy comparable to other classical segmentation approaches (in average DICE coefficient over 90% and ASD below one pixel), with further advantages related to segmentation speed. Graphical Abstract.

Texture analysis of T1-w and T2-w MR images allows a quantitative evaluation of radiation-induced changes of internal obturator muscles after radiotherapy for prostate cancer.

PURPOSE: To investigate the potential of texture analysis applied on T2-w and postcontrast T1-w images acquired before radiotherapy for prostate cancer (PCa) and 12 months after its completion in quantitatively characterizing local radiation effect on the muscular component of internal obturators, as organs potentially involved in urinary toxicity. METHODS: T2-w and postcontrast T1-w MR images were acquired at 1.5 T before treatment (MRI1) and at 12 months of follow-up (MRI2) in 13 patients treated with radiotherapy for PCa. Right and left internal obturator muscle contours were manually delineated upon MRI1 and then automatically propagated on MRI2 by an elastic registration method. Planning CT images were coregistered to both MRIs and dose maps were deformed accordingly. A high-dose region receiving >55 Gy and a low-dose region receiving <55 Gy were identified in each muscle volume. Eighteen textural features were extracted from each region of interest and differences between MRI1 and MRI2 were evaluated. RESULTS: A signal increase was highlighted in both T2-w and T1-w images in the portion of the obturators near the prostate, i.e., in the region receiving medium-high doses. A change in the spatial organization was identified, as an increase in homogeneity and a decrease in contrast and complexity, compatible with an inflammatory status. In particular, the region receiving medium-high doses presented more significant or, at least, stronger differences. CONCLUSIONS: Texture analysis applied on T1-w and T2-w MR images has demonstrated its ability in quantitative evaluating radiation-induced changes in obturator muscles after PCa radiotherapy.

Texture analysis of medical images for radiotherapy applications.

The high-throughput extraction of quantitative information from medical images, known as radiomics, has grown in interest due to the current necessity to quantitatively characterize tumour heterogeneity. In this context, texture analysis, consisting of a variety of mathematical techniques that can describe the grey-level patterns of an image, plays an important role in assessing the spatial organization of different tissues and organs. For these reasons, the potentiality of texture analysis in the context of radiotherapy has been widely investigated in several studies, especially for the prediction of the treatment response of tumour and normal tissues. Nonetheless, many different factors can affect the robustness, reproducibility and reliability of textural features, thus limiting the impact of this technique. In this review, an overview of the most recent works that have applied texture analysis in the context of radiotherapy is presented, with particular focus on the assessment of tumour and tissue response to radiations. Preliminary, the main factors that have an influence on features estimation are discussed, highlighting the need of more standardized image acquisition and reconstruction protocols and more accurate methods for region of interest identification. Despite all these limitations, texture analysis is increasingly demonstrating its ability to improve the characterization of intratumour heterogeneity and the prediction of clinical outcome, although prospective studies and clinical trials are required to draw a more complete picture of the full potential of this technique.

Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification.

MOTIVATION: Patients under radiotherapy for head-and-neck cancer often suffer of long-term xerostomia, and/or consistent shrinkage of parotid glands. In order to avoid these drawbacks, adaptive therapy can be planned for patients at risk, if the prediction is obtained timely, before or during the early phase of treatment. Artificial intelligence can address the problem, by learning from examples and building classification models. In particular, fuzzy logic has shown its suitability for medical applications, in order to manage uncertain data, and to build transparent rule-based classifiers. In previous works, clinical, dosimetric and image-based features were considered separately, to find different possible predictors of parotid shrinkage. On the other hand, a few works reported possible image-based predictors of xerostomia, while the combination of different types of features has been little addressed. OBJECTIVE: This paper proposes the application of a novel machine learning approach, based on both statistics and fuzzy logic, aimed at the classification of patients at risk of i) parotid gland shrinkage and ii) 12-months xerostomia. Both problems are addressed with the aim of individuating predictors and models to classify respective outcomes. METHODS: Knowledge is extracted from a real dataset of radiotherapy patients, by means of a recently developed method named Likelihood-Fuzzy Analysis, based on the representation of statistical information by fuzzy rule-based models. This method enables to manage heterogeneous variables and missing data, and to obtain interpretable fuzzy models presenting good generalization power (thus high performance), and to measure classification confidence. Numerous features are extracted to characterize patients, coming from different sources, i.e. clinical features, dosimetric parameters, and radiomics-based measures obtained by texture analysis of Computed Tomography images. A learning approach based on the composition of simple models in a more complicated one allows to consider the features separately, in order to identify predictors and models to use when only some data source is available, and obtaining more accurate results when more information can be combined. RESULTS: Regarding parotid shrinkage, a number of good predictors is detected, some already known and confirmed here, and some others found here, in particular among radiomics-based features. A number of models are also designed, some using single features and others involving models composition to improve classification accuracy. In particular, the best model to be used at the initial treatment stage, and another one applicable at the half treatment stage are identified. Regarding 12-months toxicity, some possible predictors are detected, in particular among radiomics-based features. Moreover, the relation between final parotid shrinkage rate and 12-months xerostomia is evaluated. The method is compared to the naïve Bayes classifier, which reveals similar results in terms of classification accuracy and best predictors. The interpretable fuzzy rule-based models are explicitly presented, and the dependence between predictors and outcome is explained, thus furnishing in some cases helpful insights about the considered problems. CONCLUSION: Thanks to the performance and interpretability of the fuzzy classification method employed, predictors of both parotid shrinkage and xerostomia are detected, and their influence on each outcome is revealed. Moreover, models for predicting parotid shrinkage at initial and half radiotherapy stages are found.

A Comparative Evaluation of 3 Different Free-Form Deformable Image Registration and Contour Propagation Methods for Head and Neck MRI: The Case of Parotid Changes During Radiotherapy.

PURPOSE: To validate and compare the deformable image registration and parotid contour propagation process for head and neck magnetic resonance imaging in patients treated with radiotherapy using 3 different approaches-the commercial MIM, the open-source Elastix software, and an optimized version of it. MATERIALS AND METHODS: Twelve patients with head and neck cancer previously treated with radiotherapy were considered. Deformable image registration and parotid contour propagation were evaluated by considering the magnetic resonance images acquired before and after the end of the treatment. Deformable image registration, based on free-form deformation method, and contour propagation available on MIM were compared to Elastix. Two different contour propagation approaches were implemented for Elastix software, a conventional one (DIR_Trx) and an optimized homemade version, based on mesh deformation (DIR_Mesh). The accuracy of these 3 approaches was estimated by comparing propagated to manual contours in terms of average symmetric distance, maximum symmetric distance, Dice similarity coefficient, sensitivity, and inclusiveness. RESULTS: A good agreement was generally found between the manual contours and the propagated ones, without differences among the 3 methods; in few critical cases with complex deformations, DIR_Mesh proved to be more accurate, having the lowest values of average symmetric distance and maximum symmetric distance and the highest value of Dice similarity coefficient, although nonsignificant. The average propagation errors with respect to the reference contours are lower than the voxel diagonal (2 mm), and Dice similarity coefficient is around 0.8 for all 3 methods. CONCLUSION: The 3 free-form deformation approaches were not significantly different in terms of deformable image registration accuracy and can be safely adopted for the registration and parotid contour propagation during radiotherapy on magnetic resonance imaging. More optimized approaches (as DIR_Mesh) could be preferable for critical deformations.

Characterization of cervical lymph-nodes using a multi-parametric and multi-modal approach for an early prediction of tumor response to chemo-radiotherapy.

PURPOSE: In the treatment of Head-and-Neck Squamous Cell Carcinoma (HNSCC), the early prediction of residual malignant lymph nodes (LNs) is currently required. Here, we investigated the potential of a multi-modal characterization (combination of CT, T2w-MRI and DW-MRI) at baseline and at mid-treatment, based on texture analysis (TA), for the early prediction of LNs response to chemo-radiotherapy (CRT). METHODS: 30 patients with pathologically confirmed HNSCC treated with CRT were considered. All patients underwent a planning CT and two serial MR examinations (including T2w and DW images), one before and one at mid-CRT. For each patient the largest malignant LN was selected and within each LN, morphological and textural features were estimated from T2w-MRI and CT, besides a quantification of the apparent diffusion coefficient (ADC) from DW-MRI. After a median follow-up time of 26.6months, 19 LNs showed regional control, while 11 LNs showedregional failure at a median time of 4.6months. Linear discriminant analysis was used to test the accuracy of the image-based features in predicting the final response. RESULTS: Pre-treatment features showed higher predictive power than mid-CRT features, the ADC having the highest accuracy (80%); CT-based indices were found not predictive. When ADC was combined with TA, the classification performance increased (accuracy=82.8%). If only T2w-MRI features were considered, the best combination of pre-CRT indices and their variation reached an equivalent accuracy (81.8%). CONCLUSION: Our results may suggest that TA on T2w-MRI and ADC can be combined together to obtain a more accurate prediction of response to CRT.

Assessment and clinical validation of margins for adaptive simultaneous integrated boost in neo-adjuvant radiochemotherapy for rectal cancer.

PURPOSE: An adaptive concomitant boost (ACB) for the neo-adjuvant treatment of rectal cancer was clinically implemented. In this study population margins M(90,90) considering rectal deformation were derived for 10 consecutive patients treated at 18 × 2.3Gy with Helical Tomotherapy (HT) and prospectively validated on 20 additional patients treated with HT, delivering ACB in the last 6 fractions. METHODS: Sectorial margins M(90,90) of the whole and second treatment parts were assessed for 90% population through a method combining the 90% coverage probability maps of rectal positions (CPC90%) with 3D local distance measurements between the CPC90% and a reference rectal contour. M(90,90) were compared with the margins M(90,90)(95%/99%), ensuring CPC90% coverage with 95%/99% confidence level. M(90,90) of the treatment second part were chosen as ACB margins which were clinically validated for each patient by means of %volume missing of CPC5/6 excluded by the ACB margins. RESULTS: The whole treatment M(90,90) ranged between 1.9 mm and 9 mm in the lower-posterior and upper-anterior sectors, respectively. Regarding ACB, M(90,90) were 7 mm in the anterior direction and <5 mm elsewhere. M(90,90)(95%/99%) did not significantly differ from M(90,90). The %volume excluded by the ACB margin was<2% for all male and <5% for 9/10 female patients. The dosimetry impact on R_adapt for the patients with the largest residual error was negligible. CONCLUSIONS: Local deformation measurements confirm an anisotropic motion of rectum once set-up error is rigidly corrected. Margins of 7 mm anterior and 5 mm elsewhere are adequate for ACB. Female patients show a slightly larger residual error.

Analysis of serial CT images for studying the RT effects in head-neck cancer patients.

Images taken during and after RT for head and neck cancer have the potential to quantitatively assess xerostomia. Image information may be used as biomarkers of RT effects on parotid glands with significant potential to support adaptive treatment strategies. We investigated the possibility to extract information based on in-room CT images (kVCT, MVCT), acquired for daily image-guided radiotherapy treatment of head-and-neck cancer patients, in order to predict individual response in terms of toxicity. Follow-up MRI images were also used in order to investigate long term parotid gland deformation.