Search

Accurate diagnosis and treatment planning for medical conditions rely heavily on the results of medical image segmentation. Medical images are available in many modalities like CT scans, MRI, histopathological, and ultrasound images. Among all, the real-time analysis of the ultrasound is the most complex as the internal organ's visualization requires experience from the radiologist. Diagnosing the medical conditions and unavailability of experienced radiologists during an emergency requires automated segmentation which heavily depends on computer-aided diagnostic systems. The new generation CAD systems are found to incorporate advanced deep learning algorithms to produce accurate segmentation results. While most of the segmentation models relate to the encoder-decoder model as the base architecture and thus evolve a variety of modifications in its pipeline architecture. This paper presents the analytical study of the various Encoder- Decoder based models like UNet, Residual UNet (Res-U-Net), Dense UNet (DenseUNet), Attention UNet, UNet + +, Double UNet, and U2Net (U-Squared-Net) on ultrasound image segmentation. Further, the paper presents the various trade-offs, application areas, open challenges, and performance analysis of these models on benchmark datasets, namely the HC18 Challenge dataset, CUM dataset, and B-mode Ultrasound Nerve Segmentation dataset. The performance analysis of these models is presented using the six state-of-the-art metrics like Dice coefficient, Jaccard index, sensitivity, specificity, Mean Absolute distance, and Housdorff Distance. Based on the above parameters U2-Net (U-Squared-Net) outperformed all other neural network models for all three datasets. In terms of all four criteria (Dice Coefficient: 0.92, 0.89, 0.9, Jaccard Index: 0.81, 0.79, 0.81, Sensitivity: 0.86, 0.84, 0.86, Specificity: 0.97, 0.95, 0.96), the U2-Net (U-Squared-Net) model performed the best. Over the HC18 Challenge dataset, the CUM dataset, and the B-Mode Ultrasound nerve segmentation dataset, U2-Net (U-Squared-Net) model achieved the best HD results (HC18: 3.8, CUM Dataset: 4, B-mode US Dataset: 3.6) and the lowest MAD values (HC18: 2.1, CUM Dataset: 3, B-mode US Dataset: 2.15). In addition, the analysis also highlights the architectural differences between these models, focusing on their type of connections, number of layers, and additional components. The outcome of this research provides valuable perception into the strengths and limitations of each encoder-decoder-based model, aiding researchers and practitioners in selecting the most appropriate model for Ultrasound image segmentation tasks. [ABSTRACT FROM AUTHOR]

Accurately segmenting the structure of the fetal head (FH) and performing biometry measurements, including head circumference (HC) estimation, stands as a vital requirement for addressing abnormal fetal growth during pregnancy under the expertise of experienced radiologists using ultrasound (US) images. However, accurate segmentation and measurement is a challenging task due to image artifact, incomplete ellipse fitting, and fluctuations due to FH dimensions over different trimesters. Also, it is highly time-consuming due to the absence of specialized features, which leads to low segmentation accuracy. To address these challenging tasks, we propose an automatic density regression approach to incorporate appearance and shape priors into the deep learning-based network model (DR-ASPnet) with robust ellipse fitting using fetal US images. Initially, we employed multiple pre-processing steps to remove unwanted distortions, variable fluctuations, and a clear view of significant features from the US images. Then some form of augmentation operation is applied to increase the diversity of the dataset. Next, we proposed the hierarchical density regression deep convolutional neural network (HDR-DCNN) model, which involves three network models to determine the complex location of FH for accurate segmentation during the training and testing processes. Then, we used post-processing operations using contrast enhancement filtering with a morphological operation model to smooth the region and remove unnecessary artifacts from the segmentation results. After post-processing, we applied the smoothed segmented result to the robust ellipse fitting-based least square (REFLS) method for HC estimation. Experimental results of the DR-ASPnet model obtain 98.86% dice similarity coefficient (DSC) as segmentation accuracy, and it also obtains 1.67 mm absolute distance (AD) as measurement accuracy compared to other state-of-the-art methods. Finally, we achieved a 0.99 correlation coefficient (CC) in estimating the measured and predicted HC values on the HC18 dataset. [ABSTRACT FROM AUTHOR]

Neurodegeneration with brain iron accumulation (NBIA) is an umbrella term encompassing various inherited neurological disorders characterised by abnormal iron accumulation in basal ganglia. We aimed to study the clinical, radiological and molecular spectrum of disorders with NBIA. All molecular-proven cases of NBIA presented in the last 5 years at 2 tertiary care genetic centres were compiled. Demographic details and clinical and neuroimaging findings were collated. We describe 27 individuals from 20 unrelated Indian families with causative variants in 5 NBIA-associated genes. PLA2G6-associated neurodegeneration (PLAN) was the most common, observed in 13 individuals from 9 families. They mainly presented in infancy with neuroregression and hypotonia. A recurrent pathogenic variant in COASY was observed in two neonates with prenatal-onset severe neurodegeneration. Pathogenic bi-allelic variants in PANK2, FA2H and C19ORF12 genes were observed in the rest, and these individuals presented in late childhood and adolescence with gait abnormalities and extrapyramidal symptoms. No intrafamilial and interfamilial variability were observed. Iron deposition on neuroimaging was seen in only 6/17 (35.3%) patients. A total of 22 causative variants across 5 genes were detected including a multiexonic duplication in PLA2G6. The variants c.1799G > A and c.2370 T > G in PLA2G6 were observed in three unrelated families. In silico assessments of 8 amongst 9 novel variants were also performed. We present a comprehensive compilation of the phenotypic and genotypic spectrum of various subtypes of NBIA from the Indian subcontinent. Clinical presentation of NBIAs is varied and not restricted to extrapyramidal symptoms or iron accumulation on neuroimaging. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) makes a substantial contribution to decision-making in many intricate application areas of the medical sciences. One such application is organ classification in maternal–fetal ultrasound scans using sophisticated AI methodology like deep neural networks for better analysis. In this paper, we present a novel and highly dense deep neural architecture specifically designed for the multi-organ classification of fetal ultrasound scans. Our proposed approach introduces a unique combination of densely connected layers, convolution layers, and skip connections, tailored to accurately identify and classify multiple fetal organs simultaneously. To the best of our knowledge, this is the first study to address the comprehensive classification of multiple organs in fetal ultrasound images using such a highly dense neural network. The architecture is designed to capture both local and global features, critical for distinguishing intricate organ structures in ultrasound images. The model also minimizes the gradient loss for faster convergence of the model parameters in the training phase. Through extensive evaluation of a curated dataset of fetal ultrasound scans, we demonstrate that our novel architecture achieves superior classification accuracy—96.85%, precision—97.12%, recall—96.66%, F1-score—96.88%, and AUC-ROC score—97.27%, outperforming state-of-the-art methods in the context of multi-organ classification. Thus, the proposed highly dense deep neural architecture presents a promising avenue for enhancing fetal ultrasound imaging, bringing potential benefits to prenatal care, and contributing to improved neonatal outcomes. [ABSTRACT FROM AUTHOR]