Browsing by Author "Sumam David, S.D."

Now showing 1 - 4 of 4

Computerized radiogrammetry of third metacarpal using watershed and active appearance model
(Institute of Electrical and Electronics Engineers Inc., 2018) Areeckal, A.S.; Sam, M.; Sumam David, S.D.
Osteoporosis is a bone disorder, causing loss of bone mass and increased risk of fragility fracture. Osteoporosis can be diagnosed at a low cost using computerized metacarpal radiogrammetry of the third metacarpal bone of hand X-ray images. The most widely used methods for segmentation of hand bones are deformable models such as Active Shape Model (ASM), Active Appearance Model (AAM), etc. that make use of prior information of the shape and appearance of the object. However, due to the presence of other metacarpal bones having similar shape and size in its proximity, segmentation of third metacarpal bone in isolation becomes challenging and the deformable methods could fail. In this paper, we propose a method to automatically locate and segment the third metacarpal bone using marker-controlled watershed segmentation. Radio-grammetric measurements are determined automatically from the shaft of the third metacarpal bone and can be used to derive bone indices for the detection of bone loss due to osteoporosis. The measurements obtained from the proposed method and AAM are compared with ground truth. The results obtained show that the proposed approach is an efficient method for automated radiogrammetry of third metacarpal bone that can be used as a low cost tool for the early diagnosis of osteoporosis. Â© 2018 IEEE.
Cortical volumetry using 3D reconstruction of metacarpal bone from multi-view images
(Institute of Electrical and Electronics Engineers Inc., 2018) Jayakar, A.D.; Sambath, G.; Areeckal, A.S.; Sumam David, S.D.
Osteoporosis is a disease caused by decrease in bone density, which makes the bone more susceptible to fractures. The currently used techniques to diagnose osteoporosis such as Dual X-ray Absorptiometry (DXA) and Quantitative Computed Tomography (QCT) are expensive and not widely available. Computerized radiogrammetry is a low cost technique used for the detection of bone loss. But it gives an areal measurement of the cortical bone density. In this paper, we propose a novel low cost technique to measure cortical bone volume for the diagnosis of osteoporosis. The proposed method uses a 3D reconstruction of third metacarpal using three views of hand radiographs and a template model as prior. The projection contours of the template model are registered with the X-ray images and the point-pair correspondence obtained is used to deform the template model. The shaft of the reconstructed bone is used for measuring the cortical volume. The proposed 3D reconstruction method is evaluated by comparison to a ground truth model and manually segmented X-ray images. The cortical volumetric measurements obtained are statistically analyzed for correlation with DXA measurement. The results obtained show that cortical volumetry using the proposed 3D reconstruction method can be developed into a low cost technique for the diagnosis of osteoporosis. Â© 2018 IEEE.
Current and Emerging Diagnostic Imaging-Based Techniques for Assessment of Osteoporosis and Fracture Risk
(Institute of Electrical and Electronics Engineers, 2018) Areeckal, A.S.; Kocher, M.; Sumam David, S.D.
Osteoporosis is a metabolic bone disorder characterized by low bone mass, degradation of bone microarchitecture, and susceptibility to fracture. It is a growing major health concern across the world, especially in the elderly population. Osteoporosis can cause hip or spinal fractures that may lead to high morbidity and socio-economic burden. Therefore, there is a need for early diagnosis of osteoporosis and prediction of fragility fracture risk. In this review, state of the art and recent advances in imaging techniques for diagnosis of osteoporosis and fracture risk assessment have been explored. Segmentation methods used to segment the regions of interest and texture analysis methods used for classification of healthy and osteoporotic subjects are also presented. Furthermore, challenges posed by the current diagnostic tools have been studied and feasible solutions to circumvent the limitations are discussed. Early diagnosis of osteoporosis and prediction of fracture risk require the development of highly precise and accurate low-cost diagnostic techniques that would help the elderly population in low economies. Â© 2008-2011 IEEE.
Generalizable DNN model for brain tumor sub-structure segmentation from low-resolution 2D multimodal MR Images
(Elsevier Ltd, 2025) Bhaskaracharya, B.; Nair, R.P.; Prakashini, K.; R, G.M.; Litvak, P.; Mandava, P.; Vijayasenan, D.; Sumam David, S.D.
Segmenting subregions within gliomas are critical for effective treatment planning of brain tumors. However, traditional methods of analyzing these regions using multiple MRI modalities are time-consuming, tedious, and subjective. To address these challenges, automatic segmentation models have been developed but are often built with complex 3D architecture using 3D MRI data. Also, brain tumor substructure segmentation is a highly class-imbalanced problem. To overcome these limitations, we propose two models that work on low-resolution 2D MRI data, widely used in resource-constrained countries. One model employs training a 2D U-NeT model using proposed hard sampling approach, demonstrating its effectiveness in segmenting gliomas, especially in datasets with extreme class imbalance. Another model incorporates pointwise and depthwise convolutions in each convolutional layer, enabling efficient information processing and feature learning. By ensembling the prediction maps of these models, we further improve overall segmentation performance. Our models were evaluated on the BraTS2018 dataset, achieving dice scores of 0.78 for Enhancing Tumor (ET), 0.82 for Tumor Core (TC), and 0.87 for Whole Tumor (WT). On a tertiary care hospital dataset, dice scores of 0.68 (ET), 0.75 (TC), and 0.84 (WT) were obtained, demonstrating their robustness and proximity to state-of-the-art methods. In summary, the proposed models offer efficient and reliable segmentation of glioma subregions. Their high dice scores, and computational efficiency, make them valuable tools for treatment planning and advancements in brain tumor segmentation. © 2024 Elsevier Ltd