Efficient Clinical Information Extraction from Breast Radiology Reports in French.

Radiology reports contain crucial patient information, in addition to images, that can be automatically extracted for secondary uses such as clinical support and research for diagnosis. We tested several classifiers to classify 1,218 breast MRI reports in French from two Swiss clinical centers. Logistic regression performed better for both internal (accuracy > 0.95 and macro-F1 > 0.86) and external data (accuracy > 0.81 and macro-F1 > 0.41). Automating this task will facilitate efficient extraction of targeted clinical parameters and provide a good basis for future annotation processes through automatic pre-annotation.

Barriers and facilitators of artificial intelligence conception and implementation for breast imaging diagnosis in clinical practice: a scoping review.

OBJECTIVE: Although artificial intelligence (AI) has demonstrated promise in enhancing breast cancer diagnosis, the implementation of AI algorithms in clinical practice encounters various barriers. This scoping review aims to identify these barriers and facilitators to highlight key considerations for developing and implementing AI solutions in breast cancer imaging. METHOD: A literature search was conducted from 2012 to 2022 in six databases (PubMed, Web of Science, CINHAL, Embase, IEEE, and ArXiv). The articles were included if some barriers and/or facilitators in the conception or implementation of AI in breast clinical imaging were described. We excluded research only focusing on performance, or with data not acquired in a clinical radiology setup and not involving real patients. RESULTS: A total of 107 articles were included. We identified six major barriers related to data (B1), black box and trust (B2), algorithms and conception (B3), evaluation and validation (B4), legal, ethical, and economic issues (B5), and education (B6), and five major facilitators covering data (F1), clinical impact (F2), algorithms and conception (F3), evaluation and validation (F4), and education (F5). CONCLUSION: This scoping review highlighted the need to carefully design, deploy, and evaluate AI solutions in clinical practice, involving all stakeholders to yield improvement in healthcare. CLINICAL RELEVANCE STATEMENT: The identification of barriers and facilitators with suggested solutions can guide and inform future research, and stakeholders to improve the design and implementation of AI for breast cancer detection in clinical practice. KEY POINTS: • Six major identified barriers were related to data; black-box and trust; algorithms and conception; evaluation and validation; legal, ethical, and economic issues; and education. • Five major identified facilitators were related to data, clinical impact, algorithms and conception, evaluation and validation, and education. • Coordinated implication of all stakeholders is required to improve breast cancer diagnosis with AI.

A novel image augmentation based on statistical shape and intensity models: application to the segmentation of hip bones from CT images.

BACKGROUND: The collection and annotation of medical images are hindered by data scarcity, privacy, and ethical reasons or limited resources, negatively affecting deep learning approaches. Data augmentation is often used to mitigate this problem, by generating synthetic images from training sets to improve the efficiency and generalization of deep learning models. METHODS: We propose the novel use of statistical shape and intensity models (SSIM) to generate augmented images with variety in both shape and intensity of imaged structures and surroundings. The SSIM uses segmentations from training images to create co-registered tetrahedral meshes of the structures and to efficiently encode image intensity in their interior with Bernstein polynomials. In the context of segmentation of hip joint (pathological) bones from retrospective computed tomography images of 232 patients, we compared the impact of SSIM-based and basic augmentations on the performance of a U-Net model. RESULTS: In a fivefold cross-validation, the SSIM augmentation improved segmentation robustness and accuracy. In particular, the combination of basic and SSIM augmentation outperformed trained models not using any augmentation, or relying exclusively on a simple form of augmentation, achieving Dice similarity coefficient and Hausdorff distance of 0.95 [0.93-0.96] and 6.16 [4.90-8.08] mm (median [25th-75th percentiles]), comparable to previous work on pathological hip segmentation. CONCLUSIONS: We proposed a novel augmentation varying both the shape and appearance of structures in generated images. Tested on bone segmentation, our approach is generalizable to other structures or tasks such as classification, as long as SSIM can be built from training data. RELEVANCE STATEMENT: Our data augmentation approach produces realistic shape and appearance variations of structures in generated images, which supports the clinical adoption of AI in radiology by alleviating the collection of clinical imaging data and by improving the performance of AI applications. KEY POINTS: • Data augmentation generally improves the accuracy and generalization of deep learning models. • Traditional data augmentation does not consider the appearance of imaged structures. • Statistical shape and intensity models (SSIM) synthetically generate variations of imaged structures. • SSIM support novel augmentation approaches, demonstrated with computed tomography bone segmentation.

X-ray imaging detector for radiological applications adapted to the context and requirements of low- and middle-income countries.

This paper describes the development of a novel medical x-ray imaging system adapted to the needs and constraints of low- and middle-income countries. The developed system is based on an indirect conversion chain: a scintillator plate produces visible light when excited by the x rays, and then, a calibrated multi-camera architecture converts the visible light from the scintillator into a set of digital images. The partial images are then unwarped, enhanced, and stitched through parallel field programmable gate array processing units and specialized software. All the detector components were carefully selected focusing on optimizing the system's image quality, robustness, cost-effectiveness, and capability to work in harsh tropical environments. With this aim, different customized and commercial components were characterized. The resulting detector can generate high quality medical diagnostic images with detective quantum efficiency levels up to 60% (@2.34 µGy), even under harsh environments, i.e., 60 °C and 98% humidity.

A new 2D-3D registration gold-standard dataset for the hip joint based on uncertainty modeling.

PURPOSE: Estimation of the accuracy of 2D-3D registration is paramount for a correct evaluation of its outcome in both research and clinical studies. Publicly available datasets with standardized evaluation methodology are necessary for validation and comparison of 2D-3D registration techniques. Given the large use of 2D-3D registration in biomechanics, we introduced the first gold standard validation dataset for computed tomography (CT)-to-x-ray registration of the hip joint, based on fluoroscopic images with large rotation angles. As the ground truth computed with fiducial markers is affected by localization errors in the image datasets, we proposed a new methodology based on uncertainty propagation to estimate the accuracy of a gold standard dataset. METHODS: The gold standard dataset included a 3D CT scan of a female hip phantom and 19 2D fluoroscopic images acquired at different views and voltages. The ground truth transformations were estimated based on the corresponding pairs of extracted 2D and 3D fiducial locations. These were assumed to be corrupted by Gaussian noise, without any restrictions of isotropy. We devised the multiple projective points criterion (MPPC) that jointly optimizes the transformations and the noisy 3D fiducial locations for all views. The accuracy of the transformations obtained with the MPPC was assessed in both synthetic and real experiments using different formulations of the target registration error (TRE), including a novel formulation of the TRE (uTRE) derived from the uncertainty analysis of the MPPC. RESULTS: The proposed MPPC method was statistically more accurate compared to the validation methods for 2D-3D registration that did not optimize the 3D fiducial positions or wrongly assumed the isotropy of the noise. The reported results were comparable to previous published works of gold standard datasets. However, a formulation of the TRE commonly found in these gold standard datasets was found to significantly miscalculate the true TRE computed in synthetic experiments with known ground truths. In contrast, the uncertainty-based uTRE was statistically closer to the true TRE. CONCLUSIONS: We proposed a new gold standard dataset for the validation of CT-to-X-ray registration of the hip joint. The gold standard transformations were derived from a novel method modeling the uncertainty in extracted 2D and 3D fiducials. Results showed that considering possible noise anisotropy and including corrupted 3D fiducials in the optimization resulted in improved accuracy of the gold standard. A new uncertainty-based formulation of the TRE also appeared as a good alternative to the unknown true TRE that has been replaced in previous works by an alternative TRE not fully reflecting the gold standard accuracy.

Deformable multisurface segmentation of the spine for orthopedic surgery planning and simulation.

Purpose: We describe a shape-aware multisurface simplex deformable model for the segmentation of healthy as well as pathological lumbar spine in medical image data. Approach: This model provides an accurate and robust segmentation scheme for the identification of intervertebral disc pathologies to enable the minimally supervised planning and patient-specific simulation of spine surgery, in a manner that combines multisurface and shape statistics-based variants of the deformable simplex model. Statistical shape variation within the dataset has been captured by application of principal component analysis and incorporated during the segmentation process to refine results. In the case where shape statistics hinder detection of the pathological region, user assistance is allowed to disable the prior shape influence during deformation. Results: Results demonstrate validation against user-assisted expert segmentation, showing excellent boundary agreement and prevention of spatial overlap between neighboring surfaces. This section also plots the characteristics of the statistical shape model, such as compactness, generalizability and specificity, as a function of the number of modes used to represent the family of shapes. Final results demonstrate a proof-of-concept deformation application based on the open-source surgery simulation Simulation Open Framework Architecture toolkit. Conclusions: To summarize, we present a deformable multisurface model that embeds a shape statistics force, with applications to surgery planning and simulation.

An automated segmentation framework for nasal computational fluid dynamics analysis in computed tomography.

The use of computational fluid dynamics (CFD) to model and predict surgical outcomes in the nasal cavity is becoming increasingly popular. Despite a number of well-known nasal segmentation methods being available, there is currently a lack of an automated, CFD targeted segmentation framework to reliably compute accurate patient-specific nasal models. This paper demonstrates the potential of a robust nasal cavity segmentation framework to automatically segment and produce nasal models for CFD. The framework was evaluated on a clinical dataset of 30 head Computer Tomography (CT) scans, and the outputs of the segmented nasal models were further compared with ground truth models in CFD simulations on pressure drop and particle deposition efficiency. The developed framework achieved a segmentation accuracy of 90.9 DSC, and an average distance error of 0.3 mm. Preliminary CFD simulations revealed similar outcomes between using ground truth and segmented models. Additional analysis still needs to be conducted to verify the accuracy of using segmented models for CFD purposes.

Segmentation of the proximal femur in radial MR scans using a random forest classifier and deformable model registration.

BACKGROUND: Radial 2D MRI scans of the hip are routinely used for the diagnosis of the cam type of femoroacetabular impingement (FAI) and of avascular necrosis (AVN) of the femoral head, both considered causes of hip joint osteoarthritis in young and active patients. A method for automated and accurate segmentation of the proximal femur from radial MRI scans could be very useful in both clinical routine and biomechanical studies. However, to our knowledge, no such method has been published before. PURPOSE: The aims of this study are the development of a system for the segmentation of the proximal femur from radial MRI scans and the reconstruction of its 3D model that can be used for diagnosis and planning of hip-preserving surgery. METHODS: The proposed system relies on: (a) a random forest classifier and (b) the registration of a 3D template mesh of the femur to the radial slices based on a physically based deformable model. The input to the system are the radial slices and the manually specified positions of three landmarks. Our dataset consists of the radial MRI scans of 25 patients symptomatic of FAI or AVN and accompanying manual segmentation of the femur, treated as the ground truth. RESULTS: The achieved segmentation of the proximal femur has an average Dice similarity coefficient (DSC) of 96.37 ± 1.55%, an average symmetric mean absolute distance (SMAD) of 0.94 ± 0.39 mm and an average Hausdorff distance of 2.37 ± 1.14 mm. In the femoral head subregion, the average SMAD is 0.64 ± 0.18 mm and the average Hausdorff distance is 1.41 ± 0.56 mm. CONCLUSIONS: We validated a semiautomated method for the segmentation of the proximal femur from radial MR scans. A 3D model of the proximal femur is also reconstructed, which can be used for the planning of hip-preserving surgery.

MyHip: supporting planning and surgical guidance for a better total hip arthroplasty : A pilot study.

PURPOSE: Total hip arthroplasty (THA) aims to restore patient mobility by providing a pain-free and stable artificial joint. A successful THA depends on the planning and its execution during surgery. Both tasks rely on the experience of the surgeon to understand the complex biomechanical behavior of the hip. We investigate the hypothesis that a computer-assisted solution for THA effectively supports the preparation and execution of the planning. METHODS: We devised MyHip as a computer-assisted framework for THA. The framework provides pre-operative planning based on medical imaging and optical motion capture to optimally select and position the implant. The planning considers the morphology and range of motion of the patient's hip to reduce the risk of impingements and joint instability. The framework also provides intra-operative support based on patient-specific surgical guides. We performed a post-operative analysis on three patients who underwent THA. Based on post-operative radiological images, we reconstructed a patient-specific model of the prosthetic hip to compare planned and effective positioning of the implants. RESULTS: When the guides were used, we measured non-significant variations of planned executions such as bone cutting. Moreover, patients' hip motions were acquired and used in a dynamic simulation of the prosthetic hip. Conflicts prone to implant failure, such as impingements or subluxations, were not detected. CONCLUSIONS: The results show that MyHip provides a promising computer assistance for THA. The results of the dynamic simulation highlighted the quality of the surgery and especially of its planning. The planning was properly executed since non-significant variations were detected during the radiological analysis.

Analysis of hip range of motion in everyday life: a pilot study.

Patients undergoing total hip arthroplasty are increasingly younger and have a higher demand concerning hip range of motion. To date, there is no clear consensus as to the amplitude of the "normal hip" in everyday life. It is also unknown if the physical examination is an accurate test for setting the values of true hip motion. The purpose of this study was: 1) to precisely determine the necessary hip joint mobility for everyday tasks in young active subjects to be used in computer simulations of prosthetic models in order to evaluate impingement and instability during their practice; 2) to assess the accuracy of passive hip range of motion measurements during clinical examination. A total of 4 healthy volunteers underwent Magnetic Resonance Imaging and 2 motion capture experiments. During experiment 1, routine activities were recorded and applied to prosthetic hip 3D models including nine cup configurations. During experiment 2, a clinical examination was performed, while the motion of the subjects was simultaneously captured. Important hip flexion (mean range 95°-107°) was measured during daily activities that could expose the prosthetic hip to impingement and instability. The error made by the clinicians during physical examination varied in the range of ±10°, except for flexion and abduction where the error was higher. This study provides useful information for the surgical planning to help restore hip mobility and stability, when dealing with young active patients. The physical examination seems to be a precise method for determining passive hip motion, if care is taken to stabilise the pelvis during hip flexion and abduction.

Sensitivity of hip tissues contact evaluation to the methods used for estimating the hip joint center of rotation.

Computer-based simulations of human hip joints generally include investigating contacts happening among soft or hard tissues during hip movement. In many cases, hip movement is approximated as rotation about an estimated hip center. In this paper, we investigate the effect of different methods used for estimating hip joint center of rotation on the results acquired from hip simulation. For this reason, we use three dimensional models of hip tissues reconstructed from MRI datasets of 10 subjects, and estimate their center of rotation by applying five different methods (including both predictive and functional approaches). Then, we calculate the amount of angular and radial penetrations that happen among three dimensional meshes of cartilages, labrum, and femur bone, when hip is rotating about different estimated centers of rotation. The results indicate that hip simulation can be highly affected by the method used for estimating hip center of rotation. However, under some conditions (e.g. when Adduction or External Rotation are considered) we can expect to have a more robust simulation. In addition, it was observed that applying some methods (e.g. the predictive approach based on acetabulum) may result in less robust simulation, comparing to the other methods.

Robust statistical shape models for MRI bone segmentation in presence of small field of view.

Accurate bone modeling from medical images is essential in the diagnosis and treatment of patients because it supports the detection of abnormal bone morphology, which is often responsible for many musculoskeletal diseases (MSDs) of human articulations. In a clinical setting, images of the suspected joints are acquired in a high resolution but with a small field of view (FOV) in order to maximize the image quality while reducing acquisition time. However bones are only partially visible in such small FOVs. This presents difficult challenges in automated bone segmentation and thus limits the application of sophisticated algorithms such as statistical shape models (SSM), which have been generally proven to be an efficient technique for bone segmentation. Indeed, the reduced image information affects the initialization and evolution of these deformable model-based approaches. In this paper, we present a robust multi-resolution SSM algorithm with an adapted initialization to address the segmentation of MRI bone images acquired in small FOVs for modeling and computer-aided diagnosis. Our innovation stems from the derivation of a robust SSM based on complete and corrupted shapes, as well as from a simultaneous optimization of transformation and shape parameters to yield an efficient initialization technique. We demonstrate our segmentation algorithm using 86 clinical MRI images of the femur and hip bones. These images have a varied resolution and limited FOVs. The results of our segmentation (e.g., average distance error of 1.12 ± 0.46 mm) are within the needs of image-based clinical diagnosis.

Extreme leg motion analysis of professional ballet dancers via MRI segmentation of multiple leg postures.

PURPOSE: Professional ballet dancers are subject to constant extreme motion which is known to be at the origin of many articular disorders. To analyze their extreme motion, we exploit a unique magnetic resonance imaging (MRI) protocol, denoted as 'dual-posture' MRI, which scans the subject in both the normal (supine) and extreme (split) postures. However, due to inhomogeneous tissue intensities and image artifacts in these scans, coupled with unique acquisition protocol (split posture), segmentation of these scans is difficult. We present a novel algorithm that exploits the correlation between scans (bone shape invariance, appearance similarity) in automatically segmenting the dancer MRI images. METHODS: While validated segmentation algorithms are available for standard supine MRI, these algorithms cannot be applied to the split scan which exhibits a unique posture and strong inter-subject variations. In this study, the supine MRI is segmented with a deformable models method. The appearance and shape of the segmented supine models are then re-used to segment the split MRI of the same subject. Models are first registered to the split image using a novel constrained global optimization, before being refined with the deformable models technique. RESULTS: Experiments with 10 dual-posture MRI datasets in the segmentation of left and right femur bones reported accurate and robust results (mean distance error: 1.39 ± 0.31 mm). CONCLUSIONS: The use of segmented models from the supine posture to assist the split posture segmentation was found to be equally accurate and consistent to supine results. Our results suggest that dual-posture MRI can be efficiently and robustly segmented.

Coupled registration-segmentation: application to femur analysis with intra-subject multiple levels of detail MRI data.

The acquisition of intra-subject data from multiple images is routinely performed to provide complementary information where a single image is not sufficient. However, these images are not always co-registered since they are acquired with different scanners, affected by subject's movements during scans, and consist of different image attributes, e.g. image resolution, field of view (FOV) and intensity distributions. In this study, we propose a coupled registration-segmentation framework that simultaneously registers and segments intra-subject images with different image attributes. The proposed coupled framework is demonstrated with the processing of multiple level of detail (LOD) MRI acquisitions of the hip joint structures, which yield efficient and automated approaches to analyze soft tissues (from high-resolution MRI) in conjunction with the entire hip joint structures (from low resolution MRI).

MRI bone segmentation using deformable models and shape priors.

This paper addresses the problem of automatically segmenting bone structures in low resolution clinical MRI datasets. The novel aspect of the proposed method is the combination of physically-based deformable models with shape priors. Models evolve under the influence of forces that exploit image information and prior knowledge on shape variations. The prior defines a Principal Component Analysis (PCA) of global shape variations and a Markov Random Field (MRF) of local deformations, imposing spatial restrictions in shapes evolution. For a better efficiency, various levels of details are considered and the differential equations system is solved by a fast implicit integration scheme. The result is an automatic multilevel segmentation procedure effective with low resolution images. Experiments on femur and hip bones segmentation from clinical MRI depict a promising approach (mean accuracy: 1.44 +/- 1.1 mm, computation time: 2 mn 43 s).