Background: Hepatocyte ballooning (HB) is a significant histological characteristic linked to the advancement of non-alcoholic fatty liver disease (NAFLD) and non-alcoholic steatohepatitis (NASH). Although clinicians now consider liver biopsy the most reliable method for identifying HB, its invasive nature and related dangers highlight the need for the development of non-invasive diagnostic options. Objective: This study aims to develop a novel methodology that combines deep learning and machine learning techniques to accurately identify and measure hepatobiliary abnormalities in liver ultrasound images. Methods: The research team expanded the dataset, consisting of ultrasound images, and used it for training deep convolutional neural networks (CNNs) such as InceptionV3, ResNet50, DenseNet121, and EfficientNetB0. A hybrid approach, combining InceptionV3 for feature extraction with a Random Forest classifier, emerged as the most accurate and stable method. An approach of dual dichotomy classification was used to categorize images into two stages: healthy vs. sick, and then mild versus severe ballooning.. Features obtained from CNNs were integrated with conventional machine learning classifiers like Random Forest and Support Vector Machines (SVM). Results: The hybrid approach achieved an accuracy of 97.40%, an area under the curve (AUC) of 0.99, and a sensitivity of 99% for the ‘Many’ class during the third phase of evaluation. The dual dichotomy classification enhanced the sensitivity in identifying severe instances of HB. The cross-validation process confirmed the strength and reliability of the suggested models. Conclusions: These results indicate that this combination method can decrease the need for invasive liver biopsies by providing a non-invasive and precise alternative for early identification and monitoring of NAFLD and NASH. Subsequent research will prioritize the validation of these models using larger datasets from multiple centers to evaluate their generalizability and incorporation into clinical practice.

Non-alcoholic fatty liver disease (NAFLD) is one of the most common liver diseases, along with steatosis and non-alcoholic steatohepatitis (NASH), and is associated with cirrhosis and hepatocellular carcinoma. Candidate gene and genome-wide association studies have validated the relationships between NAFLD, NASH, PNPLA3, TM6SF2, and HFE. The present study utilized five polymorphisms in three genes: PNPLA3 (I148M and K434E) TM6SF2 (E167K), and HFE (H63D and C282Y), based on undocumented case–control studies in the Saudi Arabian population. A total of 95 patients with NAFLD and 78 non-NAFLD subjects were recruited. Genomic DNA was isolated, and polymerase chain reaction and Sanger sequencing were performed using specific primers for the I148M, K434E, E167K, H63D, and C282Y. NAFLD subjects were older when compared to controls and showed the significant association (p = 0.0001). Non-significant association was found between gender (p = 0.26). However, both weight and BMI were found to be associated. Hardy–Weinberg equilibrium analysis confirmed that H63D, I148M, and K434E polymorphisms were associated. Genotype analysis showed only K434E variant was associated with NAFLD and non-NAFLD (OR-2.16; 95% CI: 1.08–4.31; p = 0.02). However, other polymorphisms performed with NAFLD and NASH were not associated (p > 0.05), and similar analysis was found when ANOVA was performed (p > 0.05). In conclusion, we confirmed that K434E polymorphism showed a positive association in the Saudi population.