Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment.
Neural Netw
; 178: 106405, 2024 Oct.
Article
in En
| MEDLINE
| ID: mdl-38815471
ABSTRACT
Automated detection of cervical abnormal cells from Thin-prep cytologic test (TCT) images is crucial for efficient cervical abnormal screening using computer-aided diagnosis systems. However, the construction of the detection model is hindered by the preparation of the training images, which usually suffers from issues of class imbalance and incomplete annotations. Additionally, existing methods often overlook the visual feature correlations among cells, which are crucial in cervical lesion cell detection as pathologists commonly rely on surrounding cells for identification. In this paper, we propose a distillation framework that utilizes a patch-level pre-training network to guide the training of an image-level detection network, which can be applied to various detectors without changing their architectures during inference. The main contribution is three-fold (1) We propose the Balanced Pre-training Model (BPM) as the patch-level cervical cell classification model, which employs an image synthesis model to construct a class-balanced patch dataset for pre-training. (2) We design the Score Correction Loss (SCL) to enable the detection network to distill knowledge from the BPM model, thereby mitigating the impact of incomplete annotations. (3) We design the Patch Correlation Consistency (PCC) strategy to exploit the correlation information of extracted cells, consistent with the behavior of cytopathologists. Experiments on public and private datasets demonstrate the superior performance of the proposed distillation method, as well as its adaptability to various detection architectures.
Key words
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Uterine Cervical Neoplasms
/
Neural Networks, Computer
Limits:
Female
/
Humans
Language:
En
Journal:
Neural Netw
Journal subject:
NEUROLOGIA
Year:
2024
Document type:
Article
Affiliation country:
China
Country of publication:
United States