A Deep Learning Approach for Classification and Prediction of Cirrhosis Liver: Non Alcoholic Fatty Liver Disease (NAFLD)

Prakash, K.; Saradha, S.

doi:10.1109/icoei53556.2022.9777239

Cited by 13 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prakash et al [21] groundbreaking work takes center stage in the realm of liver disease prediction, specifically targeting cirrhosis arising from non-alcoholic fatty liver disease (NAFLD). The crux of their approach lies in a sophisticated integration of features, a deep neural network (DNN), and the discerning application of Spearman's rank correlation, ushering in a new era in predictive modeling.…”

Section: Related Workmentioning

confidence: 99%

“…Accurate delineation of tumor boundaries in medical imaging is a pivotal task, crucial for subsequent analyses and clinical decision-making. The evaluation metrics employed for tumor segmentation shed light on the precision, recall, and Dice coefficient, offering a detailed understanding of the delineation accuracy achieved by various methodologies, including HistoCovAE, DM-ML [18], AAM [19], BMF [20], and DNN [21]. Precision, representing the ratio of correctly identified positive instances to the total predicted positive instances, is a key metric assessing the ability of a model to avoid false positives.…”

Section: A Tumor Segmentation Metricsmentioning

confidence: 99%

See 1 more Smart Citation

AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures

Prabaharan,

Dhinakaran,

Raghavan

et al. 2024

IJACSA

View full text Add to dashboard Cite

Liver tumor prediction plays a pivotal role in optimizing treatment strategies and improving patient outcomes. In our proposed work, we present an innovative AI-driven framework for liver tumor prediction, uniting cutting-edge techniques to enhance precision and depth of analysis. The framework integrates a Histological Convolutional Autoencoder (HistoCovAE) for meticulous tumor segmentation in medical imaging, and Genomic Feature Extraction (MIRSLiC) for a nuanced understanding of molecular markers. Additionally, a Multidimensional Feature Extraction module amalgamates videomics, radiomics, acoustics, and clinical data, creating a comprehensive dataset. These dimensions synergize in a unified model, offering detailed predictions encompassing tumor characteristics, subtypes, and prognosis. Model evaluation and continuous improvement, guided by real-world outcomes, underscore reliability. This integrative approach transcends conventional boundaries, providing clinicians' actionable insights for personalized treatment strategies and heralding a new era in liver tumor prediction. Our model undergoes rigorous evaluation against diverse datasets, and the performance metrics underscore its reliability and accuracy. With precision exceeding 87%, recall rates above 92%, and a Dice coefficient surpassing 0.89 in tumor segmentation, our model showcases exceptional accuracy and robustness. In prognostic modeling, survival prediction accuracy consistently surpasses 84%, highlighting the model's ability to provide valuable insights into the future trajectory of liver cancer.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Tumor Segmentation Metricsmentioning

confidence: 99%

AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures

Prabaharan,

Dhinakaran,

Raghavan

et al. 2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…Radiologists and oncologists utilise computed tomography (CT) or magnetic resonance imaging (MRI) to visualise the structure and texture of the liver. These anomalies are important biomarkers for early disease detection and progression in primary and secondary hepatic tumour malignancy [6].…”

Section: Figure: 2 Liver Cancermentioning

confidence: 99%

“…In [6], study proposes a deep learning approach for earlystage liver disease prediction and classification based on non-alcoholic fatty liver disease. The approach uses 52 texture features, including grey level co-occurrence matrix and gradient co-occurrence matrix, and uses a deep neural network for feature prediction and classification.…”

Section: Literature Reviewmentioning

confidence: 99%

Liver Cancer Segmentation through Enhanced Feature Extraction and Mapping using Improved Transfer Learning Techniques

N.A. Sheela Selvakumari

2023

IJRITCC

View full text Add to dashboard Cite

The largest solid organ in the body is the liver. Numerous other vital functions it carries out include removing impurities from the blood flow, controlling blood coagulation, and maintaining healthy blood sugar levels. All blood leaving the intestines and stomach is directed to the liver as its final destination. Liver illness may be brought on by infections, inherited diseases, cancer, too many harmful substances, or other conditions. Medical experts estimate that 1.6% of men and women in India could be diagnosed with liver cancer at some time in their life. The interpretation of liver CT scans often involves semi-manual or manual techniques; however these techniques are costly, time-consuming, subjective, and prone to error. To improve the detection of liver cancer, these issues have been addressed and a number of computer algorithms have been developed. To create a fully automated method for quickly extracting liver tumours from CT scan images.

show abstract

“…The potential utility of ML for liver histology has been explored in several studies in patients with NASH. [10][11][12][13] The current analysis evaluated liver biopsy samples from a randomized, double-blind, phase II trial that investigated the effect of semaglutide, a glucagon-like peptide-1 receptor agonist, on histological resolution of NASH in patients with biopsy-confirmed NASH and fibrosis. [14] The aim of this post hoc analysis was to compare the evaluation of key histological features of NASH by 2 methods: the traditional independent evaluation by expert liver pathologists and the ML-derived pathology models.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Ratziu,

Francque,

Behling

et al. 2023

Hepatology

View full text Add to dashboard Cite

Background and Aims: Artificial intelligence-powered digital pathology offers the potential to quantify histologic findings in a reproducible way. This analysis compares the evaluation of histological features of non-alcoholic steatohepatitis (NASH) between pathologists and a machine learning (ML) pathology model. Approach and Results: This post hoc analysis included data from a subset of patients (N=251) with biopsy-confirmed NASH and fibrosis stage F1–F3 from a 72-week randomised placebo-controlled trial of once-daily subcutaneous semaglutide 0.1, 0.2, or 0.4 mg (NCT02970942). Biopsies at baseline and week 72 were read by two pathologists. Digitised biopsy slides were evaluated by PathAI’s NASH ML models to quantify changes in fibrosis, steatosis, inflammation, and hepatocyte ballooning using categorical assessments and continuous scores. Pathologist and ML-derived categorical assessments detected a significantly greater percentage of patients achieving the primary endpoint of NASH resolution without worsening of fibrosis with semaglutide 0.4 mg vs placebo (pathologist 58.5% vs 22.0%, p <0.0001; ML 36.9% vs 11.9%; p=0.0015). Both methods detected a higher but non-significant percentage of patients on semaglutide 0.4 mg vs placebo achieving the secondary endpoint of liver fibrosis improvement without NASH worsening. ML continuous scores detected significant treatment-induced responses in histologic features, including a quantitative reduction in fibrosis with semaglutide 0.4 mg vs placebo (p=0.0099) that could not be detected using pathologist or ML categorical assessment. Conclusions: ML categorical assessments reproduced pathologists’ results of histological improvement with semaglutide for steatosis and disease activity. ML-based continuous scores demonstrated an antifibrotic effect not measured by conventional histopathology.

show abstract

A Deep Learning Approach for Classification and Prediction of Cirrhosis Liver: Non Alcoholic Fatty Liver Disease (NAFLD)

Cited by 13 publications

References 25 publications

AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures

AI-Enhanced Comprehensive Liver Tumor Prediction using Convolutional Autoencoder and Genomic Signatures

Liver Cancer Segmentation through Enhanced Feature Extraction and Mapping using Improved Transfer Learning Techniques

Artificial intelligence scoring of liver biopsies in a phase II trial of semaglutide in nonalcoholic steatohepatitis

Contact Info

Product

Resources

About