What question did this study set out to answer?

Investigate a new pseudo-labeling method within a semi-supervised learning framework for liver disease classification.

April 3, 2026Applied Sciences0 citationsOpen Access

SEN-Batch Pseudo-Labeling with NeuroStack for Robust Semi-Supervised Liver Classification

PGPranabes Gangopadhyay PGPerumal Ganeshkumar TSTirtharaj Sen

Key Points

Investigate a new pseudo-labeling method within a semi-supervised learning framework for liver disease classification.
Developed a Self-Evolving Neighborhood (SEN)-batched pseudo-labeling technique.
Utilized the NeuroStack model for dataset labeling.
Evaluated performance on ILPD, BUPA Liver Disorder, and LFT datasets.
Compared results with the FixMatch algorithm.
Achieved the best accuracy of 98%, ≈11% higher than FixMatch.
Confidence score reached 97%, ≈12% higher than FixMatch.
Average metrics included 94.6% accuracy, 94% confidence score, 0.96 F1-score, and 0.98 AUC.
Confidence interval was ±1.2, significantly lower than other algorithms.

Abstract

The liver is vital for metabolism, detoxification, and homeostasis. Untreated liver disease leads to severe consequences, stressing the need for early diagnosis. However, patient classification using statistical learning is limited by the scarcity of large, labeled datasets due to high acquisition and expertise cost. Surmounting this impediment, a novel Self-Evolving Neighborhood (SEN)-batched pseudo-labeling (PL) technique is proposed within the context of a semi-supervised learning framework. At its core, the NeuroStack model has been developed for labeling the datasets. The study examines the performance of the proposed PL algorithm across datasets like ILPD, BUPA Liver Disorder, and LFT. It is further compared to the state-of-the-art (SOTA) FixMatch. This study achieved the best accuracy of 98%, which is ≈11% higher than the FixMatch algorithm, and a confidence score of 97%, which is ≈12% higher than the FixMatch algorithm. The average accuracy, confidence score, F1-score and AUC across all the datasets are 94.6%, 94%, 0.96 and 0.98, respectively. The confidence interval was ±1.2 which is significantly lower than other algorithms. The experiments also achieved the best patient classification accuracy of 98% using the novel NeuroStack model which is adaptable for labeling any non-image datasets.

Perguntar à IA

Bookmark

View Full Paper