Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation

Nagendram, Sanam; Singh, Arunendra; Babu, Gade Harish; Joshi, Rahul; Pande, Sandeep Dwarkanath; Ahammad, S. K. Hasane; Dhabliya, Dharmesh; Bisht, Aadarsh

doi:10.1515/biol-2022-0665

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional Neural Networks (CNNs) have swiftly become a crucial method for analyzing medical images, particularly in image recognition and visual learning tasks. Numerous studies across various medical fields, including X-ray, ultrasound, CT, MRI, microscopy, and endoscopy, have reported promising results in diagnosis and classification using CNNs [28][29][30][31][32][33]. ResNet, as exemplified by He et al [34], not only address the issue of gradient vanishing by allowing gradients to pass through shortcut paths but also enable the learning of identity functions, ensuring that higher-level performance Detecting target lesions in medical images and accurately segmenting them pose significant challenges.…”

Section: Discussionmentioning

confidence: 99%

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections

Liu,

Chen,

Fan

et al. 2024

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Objective To develop an AI-assisted MRI model to identify surgical target areas in pediatric hip and periarticular infections. Methods A retrospective study was conducted on the pediatric patients with hip and periarticular infections who underwent Magnetic Resonance Imaging(MRI)examinations from January 2010 to January 2023 in three hospitals in China. A total of 7970 axial Short Tau Inversion Recovery (STIR) images were selected, and the corresponding regions of osteomyelitis (label 1) and abscess (label 2) were labeled using the Labelme software. The images were randomly divided into training group, validation group, and test group at a ratio of 7:2:1. A Mask R-CNN model was constructed and optimized, and the performance of identifying label 1 and label 2 was evaluated using receiver operating characteristic (ROC) curves. Calculation of the average time it took for the model and specialists to process an image in the test group. Comparison of the accuracy of the model in the interpretation of MRI images with four orthopaedic surgeons, with statistical significance set at P < 0.05. Results A total of 275 patients were enrolled, comprising 197 males and 78 females, with an average age of 7.10 ± 3.59 years, ranging from 0.00 to 14.00 years. The area under curve (AUC), accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 1 were 0.810, 0.976, 0.995, 0.969, 0.922, and 0.957, respectively. The AUC, accuracy, sensitivity, specificity, precision, and F1 score for the model to identify label 2 were 0.890, 0.957, 0.969, 0.915, 0.976, and 0.972, respectively. The model demonstrated a significant speed advantage, taking only 0.2 s to process an image compared to average 10 s required by the specialists. The model identified osteomyelitis with an accuracy of 0.976 and abscess with an accuracy of 0.957, both statistically better than the four orthopaedic surgeons, P < 0.05. Conclusion The Mask R-CNN model is reliable for identifying surgical target areas in pediatric hip and periarticular infections, offering a more convenient and rapid option. It can assist unexperienced physicians in pre-treatment assessments, reducing the risk of missed and misdiagnosis.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections

Liu,

Chen,

Fan

et al. 2024

BMC Musculoskelet Disord

View full text Add to dashboard Cite

show abstract

F-Net: Follicles Net an efficient tool for the diagnosis of polycystic ovarian syndrome using deep learning techniques

S.,

Umapathy,

Alhajlah

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The study’s primary objectives encompass the following: (i) To implement the object detection of ovarian follicles using you only look once (YOLO)v8 and subsequently segment the identified follicles using a hybrid fuzzy c-means-based active contour technique. (ii) To extract statistical features and evaluate the effectiveness of both machine learning (ML) and deep learning (DL) classifiers in detecting polycystic ovary syndrome (PCOS). The research involved a two different dataset in which dataset1 comprising both normal (N = 50) and PCOS (N = 50) subjects, dataset 2 consists of 100 normal and 100 PCOS affected subjects for classification. The YOLOv8 method was employed for follicle detection, whereas statistical features were derived using Gray-level co-occurrence matrices (GLCM). For PCOS classification, various ML models such as Random Forest (RF), k- star, and stochastic gradient descent (SGD) were employed. Additionally, pre-trained models such as MobileNet, ResNet152V2, and DenseNet121 and Vision transformer were applied for the categorization of PCOS and healthy controls. Furthermore, a custom model named Follicles Net (F-Net) was developed to enhance the performance and accuracy in PCOS classification. Remarkably, the F-Net model outperformed among all ML and DL classifiers, achieving an impressive classification accuracy of 95% for dataset1 and 97.5% for dataset2 respectively in detecting PCOS. Consequently, the custom F-Net model holds significant potential as an effective automated diagnostic tool for distinguishing between normal and PCOS.

show abstract

Lung nodule segmentation via semi-residual multi-resolution neural networks

Wang,

Dai

2023

Open Life Sciences

View full text Add to dashboard Cite

The integration of deep neural networks and cloud computing has become increasingly prevalent within the domain of medical image processing, facilitated by the recent strides in neural network theory and the advent of the internet of things (IoTs). This juncture has led to the emergence of numerous image segmentation networks and innovative solutions that facilitate medical practitioners in diagnosing lung cancer. Within the contours of this study, we present an end-to-end neural network model, christened as the “semi-residual Multi-resolution Convolutional Neural Network” (semi-residual MCNN), devised to engender precise lung nodule segmentation maps within the milieu of cloud computing. Central to the architecture are three pivotal features, each coalescing to effectuate a notable enhancement in predictive accuracy: the incorporation of semi-residual building blocks, the deployment of group normalization techniques, and the orchestration of multi-resolution output heads. This innovative model is systematically subjected to rigorous training and testing regimes, using the LIDC-IDRI dataset – a widely embraced and accessible repository – comprising a diverse ensemble of 1,018 distinct lung CT images tailored to the realm of lung nodule segmentation.

show abstract

Stochastic gradient descent optimisation for convolutional neural network for medical image segmentation

Cited by 3 publications

References 24 publications

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections

Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections

F-Net: Follicles Net an efficient tool for the diagnosis of polycystic ovarian syndrome using deep learning techniques

Lung nodule segmentation via semi-residual multi-resolution neural networks

Contact Info

Product

Resources

About