arXiv subjects

David Bendahan

Publications and source records attributed to David Bendahan.

7 recordsLinked to original sources

arXiv2026

DyABD: The Abdominal Muscle Segmentation in Dynamic MRI Benchmark

This work introduces DyABD, a novel and complex benchmark dataset of dynamic abdominal MRIs from patients with abdominal hernias and associated high quality abdominal muscle annotations. DyABD is the first-of-its-kind in four key ways; (1) it proposes the first abdominal muscle segmentation task, (2) the dynamic MRIs are acquired whilst the patients perform various exercises, introducing extreme anatomical variability, making it one of the most challenging segmentation datasets to date, (3) it includes both pre and post corrective MRIs and (4) DyABD promotes clinical research into the high recurrence rates of abdominal hernias. Beyond dataset introduction, this work provides a comprehensive evaluation of the generalisation capabilities of existing segmentation models across Supervised, Few Shot and Zero Shot paradigms on the unseen DyABD dataset. This work reveals that there is still room for substantial improvement in the field of medical image segmentation, with the majority of techniques achieving a Dice Coefficient of 0.82. This work therefore sheds light on the true progress of the field and redefines the benchmark for progress in medical image segmentation.

cs.CV↗

arXiv2026

A review of ventral hernia biomechanics

Despite advancements in surgical techniques, hernia recurrence rates remain high, underscoring the need for improved understanding of abdominal wall behaviour. While surgeons are aware of many factors contributing to hernia occurrence (e.g obesity, smoking, surgical technique or site infection), it would be of interest to consider it as a biomechanical pathology. Indeed, an abdominal hernia arises from an imbalance between abdominal wall deformability and applied forces. This review article discusses how biomechanics offer a quantitative framework for assessing healthy and damaged tissue behaviour, guiding personalised surgical strategies throughout the pre-, intra-, and post-operative periods. The abdominal wall is a dynamic, load-bearing structure, continuously subjected to intra-abdominal pressure and mechanical stress. Its biomechanical properties, including elasticity and resistance to loading forces, dictate its function and response to surgical intervention. The linea alba is the stiffest component experiencing the highest stress, while the abdominal wall's anisotropic nature influences deformation patterns. Various experimental and computational methods enable biomechanical characterisation. Hernias represent mechanical failures at anatomical weak points. While surgeons qualitatively evaluate abdominal wall's biomechanics by estimating deformation and closure forces, functional imaging (elastography, dynamic acquisitions) could provide objective biomechanical insights. Hernia formation alters abdominal wall biomechanics, inducing greater mobility and elasticity. Surgical repair fundamentally alters the biomechanics of the abdominal wall. The choice of defect's suturing technique, mesh properties, placement, overlap and fixation methods (e.g. suture, tacks) significantly influence mechanical outcomes. Surgical repair tends to restore physiological biomechanics by re-establishing force transmission and hernia-induced excessive mobility. Suturing techniques, mesh selection and placement influence mechanical outcomes. However, optimal results require implants with mechanical properties mimicking native tissue. Lightweight meshes (<70 g/m2) placed in a retrorectus position, combined with a small-bite suture technique, have been associated with lower recurrence rates and improved post-operative function. By bridging biomechanics with surgical practice, this review highlights how mechanical principles shape hernia formation, diagnosis, and repair. A deeper integration of biomechanical principles into surgical decision-making could refine hernia management and lead to patient-specific, mechanics-informed strategies. For surgeons, this knowledge is not just academic - it is practical and can make a difference to patient outcomes.

physics.med-ph↗

arXiv2026

Biomechanics of the abdominal wall before and after ventral hernia repair using dynamic MRI

Purpose: This study aims to investigate the use of dynamic MRI to assess abdominal wall biomechanics before and after hernia surgery, considering that such evaluations can enhance our understanding of physiopathology and contribute to reducing recurrence rates. Methods: Patients were assessed using dynamic MRI in axial and sagittal planes while performing exercises (breathing, coughing, Valsalva) before and after their abdominal hernia surgery with mesh placement. Rectus and lateral muscles, linea alba, viscera area, defect dimensions and hernia sac were contoured with semi-automatic process to quantify the abdominal wall biomechanical temporal modifications. Results: This study enrolled 11 patients. During coughing, the axial area of the hernia sac increased by 128.4 $\pm$ 199.2%. The sac increased similarly in axial and sagittal planes during Valsalva. Post-surgical evaluations showed a 26% reduction in inter-recti distance and a lengthening of all muscles (p $\le$ 0.05). The post-operative rectus abdominis thickness change was negatively correlated with defect width during breathing (p $\le$ 0.05). The largest change in linea alba displacement was observed in the surgical site (p = 0.07). Post-operatively, lateral muscles had a larger inward displacement during Valsalva (p $\le$ 0.05). Rectus abdominis had a larger outward displacement during breathing (p = 0.09), reduced with the mesh size (p $\le$ 0.05). A large inter-individual variability was observed. Conclusion: Using a semi-automatic methodology, an in-depth analysis of the biomechanics of the abdominal wall was conducted, highlighting the importance of a patient-specific assessment. A broader study and consideration of recurrence would subsequently complete this methodological work.

physics.med-ph↗

arXiv2025

Towards a better understanding of abdominal wall biomechanics: in vivo relationship between dynamic intra-abdominal pressure and magnetic resonance imaging measurements

Background In vivo mechanical behaviour of the abdominal wall has been poorly characterised and important details are missing regarding the occurrence and post-operative recurrence rate of hernias which can be as high as 30 %. This study aimed to assess the correlation between abdominal wall displacement and intra-abdominal pressure, as well as abdominal compliance. Methods Eighteen healthy participants performed audio-guided passive (breathing) and active (coughing, Valsalva maneuver) exercises. Axial dynamic changes of abdominal muscles and visceral area were measured using MRI, and intra-abdominal pressure with ingested pressure sensor. Findings Correlations between abdominal wall displacement and intra-abdominal pressure were specific to participant, exercise, and varying between rectus abdominis and lateral muscles. Strong correlations were found between rectus abdominis displacement and intra-abdominal pressure during breathing (r = 0.92 $\pm$ 0.06), as well as lateral muscles displacement with intra-abdominal pressure during coughing and Valsalva maneuver (r = --0.98 $\pm$ 0.03 and -- 0.94 $\pm$ 0.05 respectively). The abdominal pseudo-compliance varied greatly among participants during muscular contraction, the coefficient of variation reaching up to 70 %. Interpretation The combination of intra-abdominal pressure and dynamic MRI measurements enables the identification of participant-specific behaviour pattern. Intra-abdominal pressure and abdominal wall dynamic undergo consistent and predictable interactions. However, this relationship is subject-specific and may not be extrapolated to other individuals. Therefore, both intra-abdominal pressure and abdominal wall motion must be measured in the same participant in order to accurately characterise the abdominal wall behaviour. These results are of great importance for mesh design, surgical decision-making, and personalised healthcare.

physics.med-ph↗

arXiv2022

CNN-based fully automatic wrist cartilage volume quantification in MR Image

Detection of cartilage loss is crucial for the diagnosis of osteo- and rheumatoid arthritis. A large number of automatic segmentation tools have been reported so far for cartilage assessment in magnetic resonance images of large joints. As compared to knee or hip, wrist cartilage has a more complex structure so that automatic tools developed for large joints are not expected to be operational for wrist cartilage segmentation. In that respect, a fully automatic wrist cartilage segmentation method would be of high clinical interest. We assessed the performance of four optimized variants of the U-Net architecture with truncation of its depth and addition of attention layers (U-Net_AL). The corresponding results were compared to those from a patch-based convolutional neural network (CNN) we previously designed. The segmentation quality was assessed on the basis of a comparative analysis with manual segmentation using several morphological (2D DSC, 3D DSC, precision) and a volumetric metrics. The four networks outperformed the patch-based CNN in terms of segmentation homogeneity and quality. The median 3D DSC value computed with the U-Net_AL (0.817) was significantly larger than the corresponding DSC values computed with the other networks. In addition, the U-Net_AL CNN provided the lowest mean volume error (17%) and the highest Pearson correlation coefficient (0.765) with respect to the ground truth. Of interest, the reproducibility computed from using U-Net_AL was larger than the reproducibility of the manual segmentation. U-net convolutional neural network with additional attention layers provides the best wrist cartilage segmentation performance. In order to be used in clinical conditions, the trained network can be fine-tuned on a dataset representing a group of specific patients. The error of cartilage volume measurement should be assessed independently using a non-MRI method.

eess.IV↗

arXiv2020

Deep learning-based fully automatic segmentation of wrist cartilage in MR images

The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in twenty multi-slice MRI datasets acquired with two different coils in eleven subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and patch-based U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sorensen-Dice similarity coefficient (DSC) = 0.81) in the representative (central coronal) slices with large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC=0.78-0.88 and 0.9, respectively). The proposed deep-learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.

physics.med-ph↗

arXiv2019

Automatic Segmentation of Muscle Tissue and Inter-muscular Fat in Thigh and Calf MRI Images

Magnetic resonance imaging (MRI) of thigh and calf muscles is one of the most effective techniques for estimating fat infiltration into muscular dystrophies. The infiltration of adipose tissue into the diseased muscle region varies in its severity across, and within, patients. In order to efficiently quantify the infiltration of fat, accurate segmentation of muscle and fat is needed. An estimation of the amount of infiltrated fat is typically done visually by experts. Several algorithmic solutions have been proposed for automatic segmentation. While these methods may work well in mild cases, they struggle in moderate and severe cases due to the high variability in the intensity of infiltration, and the tissue's heterogeneous nature. To address these challenges, we propose a deep-learning approach, producing robust results with high Dice Similarity Coefficient (DSC) of 0.964, 0.917 and 0.933 for muscle-region, healthy muscle and inter-muscular adipose tissue (IMAT) segmentation, respectively.

eess.IV↗