Accurate electric dosimetry is essential for predicting treatment outcomes in Irreversible Electroporation (IRE), a promising non-thermal tumor ablation technique. However, real-time 3D electric field computation remains computationally expensive, limiting its practical use in clinical settings. In this study, we propose a hybrid approach combining deep learning (DL)-based initialization with an iterative numerical solver to accelerate dose map calculation. The novelty of our approach is to combine CNN and numerical discretization of the partial differential equation to compute fastly and accurately the electric potential. We evaluate our method on data from 10 patients undergoing IRE liver ablation under real-time clinical conditions. Our results demonstrate a 10-fold speedup compared with conventional solvers while maintaining comparable accuracy. This hybrid method offers a promising pathway toward fast and reliable electric dosimetry for on-line IRE procedures.

This study aims to develop and validate an automated artificial intelligence (AI)-driven framework for the detection of pleural plaques (PP) presence from CT scans. To achieve this, an existing pre-trained network for PP segmentation from CT lung scans was integrated into a complete framework designed to detect the presence or absence of PP in individuals, thereby eliminating the need to retrain a large deep learning network. The proposed framework incorporates a novel, lightweight machine learning module that bridges the gap between PP segmentation and presence detection. The proposed framework was evaluated in a cohort of retired workers previously exposed to asbestos. The presence or absence of PP was assessed and compared to binary annotations from CT scans, which were manually labeled by three expert radiologists. The results highlighted the framework's potential in clinical scenarios where precise localization is unnecessary or where traditional segmentation models struggle due to the presence of small, fine lung structures.

Despite extensive characterization of cellular components within tissues, the fundamental principles governing their organization remain poorly understood. In this study, we propose a comprehensive framework to bridge this gap by analyzing highresolution 3D images of biological tissues. Our approach employs a semantic segmentation pipeline to achieve digital segmentation of the primary tissue organelles (cells, nuclei, nucleoli, mitochondrial networks, lipid droplet mass, blood capillaries and hemorrhagic areas). From this, we derive five categories of bioarchitectural parameters: size, shape, inter-organelle distance, orientation, and texture, which together encompass a total of$\mathbf{3 5}$parameters. We then apply unsupervised machine learning techniques to explore the resulting highdimensional bioarchitectural data, gaining deeper insights into tissue organization. We validate our framework using patient-derived xenograft (PDX) hepatoblastoma tissue samples acquired through serial block face-scanning electron microscopy. This approach elucidates detailed associations among bioarchitectural parameters and their significance, also enabling the identification of key features that differentiate endothelial cells from tumor cells.

Accurate 3D semantic cell segmentation in volumetric electron microscopy images is crucial for analyzing tissue architecture and plays a key role in studying fundamental biological processes. While current 2D semantic segmentation methods benefiting from numerous pre-trained networks available in the literature are effective, extending these approaches to 3D segmentation remains challenging. This study introduces a novel automated approach for enhancing 3D semantic cell segmentation by propagating 2D cell delineations and integrating intercellular priors to constrain segmentation within cell boundaries. We demonstrate the efficacy of our approach for automated 3D semantic cell segmentation using patient-derived xenograft (PDX) hepatoblastoma tissue samples acquired by serial block-face scanning electron microscopy. The proposed method significantly improves 3D semantic cell segmentation, paving the way for bioarchitectural investigations at the cellular level using biological and pathological samples.

Contrast-enhanced ultrasound (CEUS) is a non-invasive imaging technique extensively used for blood perfusion imaging of various organs. This modality is based on the acoustic detection of gas-filled microbubble contrast agents used as intravascular flow tracers. Recent efforts aim at quantifying parameters related to the enhancement in the vascular compartment using time-intensity curve (TIC), and at using these latter as indicators for several pathological conditions. However, this quantification is mainly hampered by two reasons: first, the quantification intrinsically solely relies on temporal intensity variation, the explicit spatial transport of the contrast agent being left out. Second, the exact relationship between the acquired US-signal and the local microbubble concentration is hardly accessible. This paper introduces the use of a fluid dynamic model for the analysis of dynamic CEUS (DCEUS), in order to circumvent the two above-mentioned limitations. A new kinetic analysis is proposed in order to quantify the velocity amplitude of the bolus arrival. The efficiency of proposed methodology is evaluated both in-vitro, for the quantitative estimation of microbubble flow rates, and in-vivo, for the classification of placental insufficiency (control versus ligature) of pregnant rats from DCEUS. Besides, for the in-vivo experimental setup, we demonstrated that the proposed approach outperforms the performance of existing TIC-based methods.

Proton resonance frequency shift-based magnetic resonance thermometry is a currently used technique for monitoring temperature during targeted thermal therapies. However, in order to provide temperature updates with very short latency times, fast MR acquisition schemes are usually employed, which in turn might lead to noisy temperature measurements. This will, in general, have a direct impact on therapy control and endpoint detection. In this paper, we address this problem through an improved non-local filtering technique applied on the temperature images. Compared with previous non-local filtering methods, the proposed approach considers not only spatial information but also exploits temporal redundancies. The method is fully automatic and designed to improve the precision of the temperature measurements while at the same time maintaining output accuracy. In addition, the implementation was optimized in order to ensure real-time availability of the temperature measurements while having a minimal impact on latency. The method was validated in three complementary experiments: a simulation, an ex-vivo and an in-vivo study. Compared to the original non-local means filter and two other previously employed temperature filtering methods, the proposed approach shows considerable improvement in both accuracy and precision of the filtered data. Together with the low computational demands of the numerical scheme, the proposed filtering technique shows great potential for improving temperature measurements during real-time MR thermometry dedicated to targeted thermal therapies.

Dynamic magnetic resonance (MR)-imaging can provide functional and positional information in real-time, which can be conveniently used online to control a cancer therapy, e.g., using high intensity focused ultrasound or radio therapy. However, a precise real-time correction for motion is fundamental in abdominal organs to ensure an optimal treatment dose associated with a limited toxicity in nearby organs at risk. This paper proposes a real-time direct principal component analysis (PCA)-based technique which offers a robust approach for motion estimation of abdominal organs and allows correcting motion related artifacts. The PCA was used to detect spatio-temporal coherences of the periodic organ motion in a learning step. During the interventional procedure, physiological contributions were characterized quantitatively using a small set of parameters. A coarse-to-fine resolution scheme is proposed to improve the stability of the algorithm and afford a predictable constant latency of 80 ms. The technique was evaluated on 12 free-breathing volunteers and provided an improved real-time description of motion related to both breathing and cardiac cycles. A reduced learning step of 10 s was sufficient without any need for patient-specific control parameters, rendering the method suitable for clinical use.

Real time magnetic resonance (MR) thermometry has evolved into the method of choice for the guidance of high-intensity focused ultrasound (HIFU) interventions. For this role, MR-thermometry should preferably have a high temporal and spatial resolution and allow observing the temperature over the entire targeted area and its vicinity with a high accuracy. In addition, the precision of real time MR-thermometry for therapy guidance is generally limited by the available signal-to-noise ratio (SNR) and the influence of physiological noise. MR-guided HIFU would benefit of the large coverage volumetric temperature maps, including characterization of volumetric heating trajectories as well as near- and far-field heating. In this paper, continuous volumetric MR-temperature monitoring was obtained as follows. The targeted area was continuously scanned during the heating process by a multi-slice sequence. Measured data and a priori knowledge of 3-D data derived from a forecast based on a physical model were combined using an extended Kalman filter (EKF). The proposed reconstruction improved the temperature measurement resolution and precision while maintaining guaranteed output accuracy. The method was evaluated experimentally ex vivo on a phantom, and in vivo on a porcine kidney, using HIFU heating. On the in vivo experiment, it allowed the reconstruction from a spatio-temporally under-sampled data set (with an update rate for each voxel of 1.143 s) to a 3-D dataset covering a field of view of 142.5×285×54 mm(3) with a voxel size of 3×3×6 mm(3) and a temporal resolution of 0.127 s. The method also provided noise reduction, while having a minimal impact on accuracy and latency.

Real-time magnetic resonance imaging is a promising tool for image-guided interventions. For applications such as thermotherapy on moving organs, a precise image-based compensation of motion is required in real time to allow quantitative analysis, retrocontrol of the interventional device, or determination of the therapy endpoint. Reduced field-of-view imaging represents a promising way to improve spatial and/or temporal resolution. However, it introduces new challenges for target motion estimation, since structures near the target may appear transiently due to the respiratory motion and the limited spatial coverage. In this paper, a new image-based motion estimation method is proposed combining a global motion estimation with a novel optical flow approach extending the initial Horn and Schunck (H&S) method by an additional regularization term. This term integrates the displacement of physiological landmarks into the variational formulation of the optical flow problem. This allowed for a better control of the optical flow in presence of transient structures. The method was compared to the same registration pipeline employing the H&S approach on a synthetic dataset and in vivo image sequences. Compared to the H&S approach, a significant improvement (p<0.05) of the Dice's similarity criterion computed between the reference and the registered organ positions was achieved.

Real time magnetic resonance (MR) thermometry is gaining clinical importance for monitoring and guiding high intensity focused ultrasound (HIFU) ablations of tumorous tissue. The temperature information can be employed to adjust the position and the power of the HIFU system in real time and to determine the therapy endpoint. The requirement to resolve both physiological motion of mobile organs and the rapid temperature variations induced by state-of-the-art high-power HIFU systems require fast MRI-acquisition schemes, which are generally hampered by low signal-to-noise ratios (SNRs). This directly limits the precision of real time MR-thermometry and thus in many cases the feasibility of sophisticated control algorithms. To overcome these limitations, temporal filtering of the temperature has been suggested in the past, which has generally an adverse impact on the accuracy and latency of the filtered data. Here, we propose a novel filter that aims to improve the precision of MR-thermometry while monitoring and adapting its impact on the accuracy. For this, an adaptive extended Kalman filter using a model describing the heat transfer for acoustic heating in biological tissues was employed together with an additional outlier rejection to address the problem of sparse artifacted temperature points. The filter was compared to an efficient matched FIR filter and outperformed the latter in all tested cases. The filter was first evaluated on simulated data and provided in the worst case (with an approximate configuration of the model) a substantial improvement of the accuracy by a factor 3 and 15 during heat up and cool down periods, respectively. The robustness of the filter was then evaluated during HIFU experiments on a phantom and in vivo in porcine kidney. The presence of strong temperature artifacts did not affect the thermal dose measurement using our filter whereas a high measurement variation of 70% was observed with the FIR filter.

Real time magnetic resonance (MR) thermometry is gaining clinical importance for monitoring and guiding high intensity focused ultrasound (HIFU) ablations of tumorous tissue. The temperature information can be employed to adjust the position and the power of the HIFU system in real time and to determine the therapy end-point. However, the precision of real time MR-thermometry is generally limited by the available signal to noise ratio (SNR). In order to improve the efficiency of applications, which are based on online temperature measurements, temporal filtering can be employed. Here, we propose a novel digital filter combining extended Kalman filtering with a temperature predictive model based on the bio heat transfer equation. The proposed approach is evaluated on simulated datasets and on MR-guided HIFU ablation experiments on ex-vivo porcine muscle. The proposed filter showed a significantly improved precision and accuracy in comparison to an optimized FIR filter.

Real time magnetic resonance imaging (MRI) is rapidly gaining importance in interventional therapies. An accurate motion estimation is required for mobile targets and can be conveniently addressed using an image registration algorithm. Since the adaptation of the control parameters of the algorithm depends on the application (targeted organ, location of the tumor, slice orientation, etc.), typically an individual calibration is required. However, the assessment of the estimated motion accuracy is difficult since the real target motion is unknown. In this paper, existing criteria based only on anatomical image similarity are demonstrated to be inadequate. A new criterion is introduced, which is based on the local magnetic field distribution. The proposed criterion was used to assess, during a preparative calibration step, the optimal configuration of an image registration algorithm derived from the Horn and Schunck method. The accuracy of the proposed method was evaluated in a moving phantom experiment, which allows the comparison with the known motion pattern and to an established criterion based on anatomical images. The usefulness of the method for the calibration of optical-flow based algorithms was also demonstrated in vivo under conditions similar to thermo-ablation for the abdomen of twelve volunteers. In average over all volunteers, a resulting displacement error of 1.5 mm was obtained (largest observed error equal to 4-5 mm) using a criterion based on anatomical image similarity. A better average accuracy of 1 mm was achieved using the proposed criterion (largest observed error equal to 2 mm). In both kidney and liver, the proposed criterion was shown to provide motion field accuracy in the range of the best achievable.

Thermotherapies can now be guided in real-time using magnetic resonance imaging (MRI). This technique is rapidly gaining importance in interventional therapies for abdominal organs such as liver and kidney. An accurate online estimation and characterization of organ displacement is mandatory to prevent misregistration and correct for motion related thermometry artifacts. In addition, when the ablation is performed with an extracorporal heating device such as high intensity focused ultrasound (HIFU), the continuous estimation of the organ displacement is the basis for the dynamic adjustment of the focal point position to track the targeted pathological tissue. In this paper, we describe the use of an optimized principal component analysis (PCA)-based motion descriptor to characterize in real-time the complex organ deformation during the therapy. The PCA was used to detect, in a preparative learning step, spatio-temporal coherences in the motion of the targeted organ. During hyperthermia, incoherent motion patterns could be discarded, which enabled improvements in motion estimation robustness, the compensation of motion related errors in thermal maps, and the adjustment of the beam position. The suggested method was evaluated for a moving phantom, and tested in vivo in the kidney and the liver of 12 healthy volunteers under free breathing conditions. The ability to perform a MR-guided thermotherapy in vivo during HIFU intervention was finally demonstrated on a porcine kidney.

Continuous magnetic resonance (MR) imaging is a promising tool for image-guided cardiac interventions. However, cardiac imaging is complicated by both, cardiac and respiratory motion. While the former is commonly addressed by cardiac gating, the latter requires a real time motion compensation. Here, a new image based motion estimation is proposed, extending the initial Horn & Schunck optical flow approach by an additional regularization term. This term allows to integrate displacement of physiological landmarks, which are obtained in a preparation step using pattern matching. The proposed method was evaluated on the left ventricle (LV) of cardiac MR-images and showed a better estimation accuracy compared to the original Horn & Schunck approach.

Real-time magnetic resonance (MR) thermometry provides continuous temperature mapping inside the human body and is therefore a promising tool to monitor and control interventional therapies based on thermal ablation. Temperature information must be mapped to a reference position of observed organs in order to allow thermal dose computation, as the history of temperature is required for each pixel. Motion compensated MR-thermometry for thermotherapy has to cope with radio-frequency (RF) artifacts and relaxation-time changes of the monitored tissue. While purely optical-flow-based realignment may lead to temperature map computation errors for the case of local or global intensity changes, principal component analysis based realignment results in accurately registered temperature maps. The motion estimation process described in this paper consists of two steps : a parameterized flow models is initially computed using a principal component analysis during a preparative learning step; during the intervention, motion is characterized with a small set of parameters using a least square solver.

Magnetic resonance (MR) systems can be used to monitor temperature changes in and around a treated region during an hyperthermic ablation procedure. Dynamic temperature monitoring allows on-line prediction of cellular destruction during the intervention. MRI systems associate each volume unit with a complex number. Phase component is 2pi periodic (it is a function of the wrapped phase) and accounts for noise sources present in MR imaging. Robust spatial phase unwrapping is a necessary prerequisite for several applications. This study proposes a spatial phase unwrapping algorithm for MR images, allowing a real time implementation for on-line temperature monitoring.

FMRI is a technique using BOLD contrast to identify areas of cerebral activity. Large vessels contribution to this signal induces a delay in the measured response. It is therefore imperative to precisely colocalize brain activity and large veins. MR venography is an acquisition procedure using phase variations to reinforce cerebral vasculature on anatomical data. In this article, we present a method to register brain large veins and activation map in order to achieve an accurate interpretation of measured activity.

Contrast-enhanced dynamic Magnetic Resonance Imaging (MRI) acquisition is a common method to retrieve functional information from organs in the human body. Applied to the kidney, the observation of the signal evolution in the cortex of a MR-series gives access to the renal perfusion and filtration. The glomerular filtration rate (GFR) is in particular the most useful quantitative index of renal function. Since the rapid bolus passage hampers the use of gated sequences, fast sequences have to be employed to enable a data acquisition while free-breathing. As a result, the acquired data contains motion artifacts caused by the respiratory cycle, spontaneous movements and drifts which limit quantitative analysis of the data. Although these problems can in principle be addressed with motion correction algorithms applied in a post processing step, additional challenges arise from the fact that image amplitude changes not only due to motion but also due to the contrast change during bolus passage. This study proposes a 2D region tracking method for retrospective motion correction without sacrificing temporal resolution which addresses the latter point by a preparative learning phase.

Magnetic resonance (MR) systems can be used to monitor temperature changes in and around a treated region during an hyperthermic ablation procedure. Dynamic temperature monitoring allows on-line prediction of cellular destruction during the intervention. However, organ displacements due to physiological activity (respiratory cycle) may induce important artifacts in computed temperature maps. In addition, focused ultrasound (FUS) is an extra-corporal heating device which makes possible to perform local hyperthermia non-invasively. For intervention on mobile organs, the position of the focal point must be adjusted dynamically to track the targeted pathologic tissue. Without such corrections, treatment is inefficient or may induce unwanted destruction of healthy tissue. In this paper, image processing methods are developed to propose an efficient solution to correct on-line motion artifacts on temperature maps, and to adjust the focal point position of the FUS device in order to track the targeted organ moving.

Magnetic resonance (MR) temperature mapping can be used to monitor temperature changes during minimally invasive thermal therapies during the procedure. Robust 3D estimation of organ displacement during the intervention is hardly feasible due to technical limitations (spatial and temporal resolution are not sufficient to perform classic 3D registration methods on anatomical images). However, organ displacements due to physiological activity (heart and respiration) may induce important artifacts on apparent temperature maps and prevent the treatment of a tumor with an external heating device. Recent development has allowed increasing external information for 3D motion estimation. This paper presents a new method that exploits image information for robust 3D motion estimation from MR images, in order to make possible the treatment of organs such as the kidney, and to improve the precision of temperature estimation using the proton resonance frequency (PRF) shift. The motion estimation described in this paper consists of two steps: a reference volume is initially computed in a preparation phase; during the intervention a 3D displacement vector is estimated on-line for each pixel of the acquired images by using this reference volume. This method can be applied to any type of image sequences and thus is not restricted to MR images.

Magnetic resonance (MR) temperature mapping can be used to monitor temperature changes in minimally invasive thermal therapies during the procedure. However, organs displacements due to physiological activity (heart and respiration) may induce important artifacts on apparent temperature maps. This paper presents a new method for motion quantification and correction in such MR images, in order to improve the precision of temperature estimation using the proton resonance frequency (PRF) shift. The PRF shift technique gives an estimate of the relative temperature variation, comparing contrast between dynamically acquired images and a reference data sets. The correction method described in this paper consists of two steps: a motion atlas is initially computed in a preparation phase; during the intervention, the appropriate reference image is chosen from the atlas, allowing correct computation of the temperature map despite tissue motion. This method can be applied to any type of image sequences and is not restricted to MR images.