The paper presents a novel framework for the prediction of the raised Intracranial Pressure (ICP) from ocular ultrasound images of traumatic patients through automated measurement of Optic Nerve Sheath Diameter (ONSD) and Eyeball Transverse Diameter (ETD). The measurement of ONSD using an ocular ultrasound scan is non-invasive and correlates with the raised ICP. However, the existing studies suggested that the ONSD value alone is insufficient to indicate the ICP condition. Since the ONSD and ETD values may vary among patients belonging to different ethnicity/origins, there is a need for developing an independent global biomarker for predicting raised ICP condition. The proposed work develops an automated framework for the prediction of raised ICP by developing algorithms for the automated measurement of ONSD and ETD values. It is established that the ONSD and ETD ratio (OER) is a potential biomarker for ICP prediction independent of ethnicity and origin. The OER threshold value is determined by performing statistical analysis on the data of 57 trauma patients obtained from the AIIMS, New Delhi. The automated OER is computed and compared with the conventionally measured ICP by determining suitable correlation coefficients. It is found that there is a significant correlation of OER with ICP ( r = .81, p ≤ .01), whereas the correlation of ONSD alone with ICP is relatively less ( r = .69, p = .004). These correlation values indicate that OER is a better parameter for the prediction of ICP. Further, the threshold value of OER is found to be 0.21 for predicting raised ICP conditions in this study. Scatter plot and Heat map analysis of OER and corresponding ICP reveal that patients with OER ≥ 0.21, have ICP in the range of 17 to 35 mm Hg. In the data available for this research work, OER ranges from 0.17 to 0.35.

Cervical vertebrae fractures pose a significant risk to a patient’s health. The accurate diagnosis and prompt treatment need to be provided for effective treatment. Moreover, the automated analysis of the cervical vertebrae fracture is of utmost important, as deep learning models have been widely used and play significant role in identification and classification. In this paper, we propose a novel hybrid transfer learning approach for the identification and classification of fractures in axial CT scan slices of the cervical spine. We utilize the publicly available RSNA (Radiological Society of North America) dataset of annotated cervical vertebrae fractures for our experiments. The CT scan slices undergo preprocessing and analysis to extract features, employing four distinct pre-trained transfer learning models to detect abnormalities in the cervical vertebrae. The top-performing model, Inception-ResNet-v2, is combined with the upsampling component of U-Net to form a hybrid architecture. The hybrid model demonstrates superior performance over traditional deep learning models, achieving an overall accuracy of 98.44% on 2,984 test CT scan slices, which represents a 3.62% improvement over the 95% accuracy of predictions made by radiologists. This study advances clinical decision support systems, equipping medical professionals with a powerful tool for timely intervention and accurate diagnosis of cervical vertebrae fractures, thereby enhancing patient outcomes and healthcare efficiency.

Timely and accurate classification of breast lesions is needed on mammograms, as it will enhance clinical decisions and reduce unnecessary biopsies. The study proposes a Multi-Scale Hybrid ResNet–Transformer with Distance-Aware Learning for interpretable BI-RADS mammographic classification. The model integrates the spatial representation strength of ResNet-50 with the contextual modeling capability of lightweight multi-head self-attention layers, forming a unified hybrid architecture. Distance-Aware Learning loss is introduced to account for the ordinal nature of BI-RADS categories, penalizing predictions based on their proximity to the true class. The stage of preprocessing includes CLAHE to enhance mammographic contrast, followed by balanced oversampling and controlled augmentations to address data imbalance. Further, the model is trained and evaluated, which indicates strong generalization across validation and test sets. The hybrid model achieved a test accuracy of 0.921, with a mean AUC of 0.987 on the test set. The model performs a per-class discriminability, with F1-scores above 0.92 for clinically critical BI-RADS 4–5 categories. Moreover, the feature-space visualization and Grad-CAM based visual explanations confirm that the model focuses on clinically relevant lesion regions, providing interpretable outputs aligned with radiologist’s reasoning. The proposed framework will provide a clinically meaningful and efficient approach to automated BI-RADS classification, and may support future computer-aided diagnostic workflows.