Explainable and Generalizable Blind Image Quality Assessment via Semantic Attribute Reasoning

Huang, Yipo; Li, Leida; Yang, Yuzhe; Li, Yaqian; Guo, Yandong

doi:10.1109/tmm.2022.3225728

Cited by 5 publications

(2 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…p z (z)dz (8) where P Y (y) is the probability of the mixing variable z and N is the number of filters in the neighborhoods. To create neighboring wavelet coefficients, we utilize steerable pyramid decomposition on a medical image in both real and imaginary domains for improved discriminatory capabilities.…”

Section: ) Removal Of Positional Embeddingmentioning

confidence: 99%

“…This critical evaluation directly impacts disease diagnosis and grading, making it a crucial component of effective healthcare practices [6,7]. Image Quality Assessment (IQA) plays a vital role in understanding human perception which can be full-reference IQA or blind IQA [8]. There has been a notable focus on BIQA models, as they offer the ability to evaluate image quality without relying on reference information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Label-free Medical Image Quality Evaluation by Semantics-aware Contrastive Learning in IoMT

Yi,

Hua,

Murchie

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

With the rapid development of the Internetof-Medical-Things (IoMT) in recent years, it has emerged as a promising solution to alleviate the workload of medical staff, particularly in the field of Medical Image Quality Assessment (MIQA). By deploying MIQA based on IoMT, it proves to be highly valuable in assisting the diagnosis and treatment of various types of medical images, such as fundus images, ultrasound images, and dermoscopic images. However, traditional MIQA models necessitate a substantial number of labeled medical images to be effective, which poses a challenge in acquiring a sufficient training dataset. To address this issue, we present a label-free MIQA model developed through a zero-shot learning approach. This paper introduces a Semantics-Aware Contrastive Learning (SCL) model that can effectively generalise quality assessment to diverse medical image types. The proposed method integrates features extracted from zero-shot learning, the spatial domain, and the frequency domain. Zero-shot learning is achieved through a tailored Contrastive Language-Image Pre-training (CLIP) model. Natural Scene Statistics (NSS) and patch-based features are extracted in the spatial domain, while frequency features are hierarchically extracted from both local and global levels. All of this information is utilised to derive a final quality score for a medical image.To ensure a comprehensive evaluation, we not only utilise two existing datasets, EyeQ and LiverQ, but also create a dataset specifically for skin image quality assessment. As a result, our SCL method undergoes extensive evaluation using all three medical image quality datasets, demonstrating its superiority over advanced models.

show abstract

Section: ) Removal Of Positional Embeddingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%