Enhanced YOLOv5 network-based object detection (BALFilter Reader) promotes PERFECT filter-enabled liquid biopsy of lung cancer from bronchoalveolar lavage fluid (BALF)

• Published in: Microsystems & nanoengineering 2023-09, Vol.9 (1), p.121-121, Article 121
• Main Authors: Liu, Zheng, Zhang, Jixin, Wang, Ningyu, Feng, Yun’ai, Tang, Fei, Li, Tingyu, Lv, Liping, Li, Haichao, Wang, Wei, Liu, Yaoping
• Format: Article
• Language: English
• Subjects: 639/166/987; 639/925; Alveoli; Bias; Biopsy; Bronchus; Controllability; Deep learning; Engineering; Fluid filters; Image enhancement; Image filters; Inspection; Lavage; Lung cancer; Machine learning; Medical imaging; New technology; Object recognition; Pathology; Robust control; Sensitivity; Transplantation; Tumor cells; Tumors
• ISSN: 2055-7434; 2096-1030; 2055-7434
• DOI: 10.1038/s41378-023-00580-6

Liquid biopsy of cancers, detecting tumor-related information from liquid samples, has attracted wide attentions as an emerging technology. Our previously reported large-area PERFECT ( P recise- E fficient- R obust- F lexible- E asy- C ontrollable- T hin) filter has demonstrated competitive sensitivity in recovering rare tumor cells from clinical samples. However, it is time-consuming and easily biased to manually inspect rare target cells among numerous background cells distributed in a large area ( Φ  ≥ 13 mm). This puts forward an urgent demand for rapid and bias-free inspection. Hereby, this paper implemented deep learning-based object detection for the inspection of rare tumor cells from large-field images of PERFECT filters with hematoxylin-eosin (HE)-stained cells recovered from bronchoalveolar lavage fluid (BALF). CenterNet, EfficientDet, and YOLOv5 were trained and validated with 240 and 60 image blocks containing tumor and/or background cells, respectively. YOLOv5 was selected as the basic network given the highest mAP@0.5 of 92.1%, compared to those of CenterNet and EfficientDet at 85.2% and 91.6%, respectively. Then, tricks including CIoU loss, image flip, mosaic, HSV augmentation and TTA were applied to enhance the performance of the YOLOv5 network, improving mAP@0.5 to 96.2%. This enhanced YOLOv5 network-based object detection, named as BALFilter Reader, was tested and cross-validated on 24 clinical cases. The overall diagnosis performance (~2 min) with sensitivity@66.7% ± 16.7%, specificity@100.0% ± 0.0% and accuracy@75.0% ± 12.5% was superior to that from two experienced pathologists (10–30 min) with sensitivity@61.1%, specificity@16.7% and accuracy@50.0%, with the histopathological result as the gold standard. The AUC of the BALFilter Reader is 0.84 ± 0.08. Moreover, a customized Web was developed for a user-friendly interface and the promotion of wide applications. The current results revealed that the developed BALFilter Reader is a rapid, bias-free and easily accessible AI-enabled tool to promote the transplantation of the BALFilter technique. This work can easily expand to other cytopathological diagnoses and improve the application value of micro/nanotechnology-based liquid biopsy in the era of intelligent pathology.