An efficient fluorescence in situ hybridization (FISH)-based circulating genetically abnormal cells (CACs) identification method based on Multi-scale MobileNet-YOLO-V4

Abstract

Background: Circulating tumor cells (CTCs) acting as "liquid biopsy" of cancer are cells that have been shed from the primary tumor, which cause the development of a secondary tumor in a distant organ site, leading to cancer metastasis. Recent research suggests that CTCs with abnormalities in gene copy numbers in mononuclear cell-enriched peripheral blood samples, namely circulating genetically abnormal cells (CACs), could be used as a non-invasive decision tool to detect patients with benign pulmonary nodules. Such cells are identified by counting the fluorescence signals of fluorescence in situ hybridization (FISH). However, owing to the rarity of CACs in the blood, identification of CACs using this technique is time-consuming and is a drawback of this method.Methods: This study has proposed an efficient and automatic FISH-based CACs identification approach which is based on a combination of the high accuracy of You Only Look Once (YOLO)-V4 and the lightweight and rapidness of MobileNet-V3. The backbone of YOLO-V4 was replaced with MobileNet-V3 to improve the detection efficiency and prevent overfitting, and the architecture of YOLO-V4 was optimized by utilizing a new feature map with a larger scale to enable the enhanced detection ability for small targets.Results: We trained and tested the proposed model using a dataset containing more than 7,000 cells based on five-fold cross-validation. All the images in the dataset were 2,448×2,048 (pixels) in size. The number of cells in each image was >70. The accuracy of four-color fluorescence signals detection for our proposed model were all approximately 98%, and the mean average precision (mAP) were close to 100%. The final outcome of the developed method was the type of cells, i.e., normal cells, CACs, gaining cells or deletion cells. The method had a CACs identification accuracy of 93.86% (similar to an expert pathologist), and a detection speed that was about 500 times greater than that of a pathologist. Conclusions:The developed method could greatly increase the review accuracy, enhance the efficiency of reviewers, and reduce the review turnaround time during CACs identification.

Deep Learning in Left and Right Footprint Image Detection Based on Plantar Pressure

“…The YOLOv4 results indicate that the model may have advantages in multi-color channel imaging detection [34]. Compared with YOLOv4, YOLOv3 was more accurate in grayscale medical images [22].…”

“…However, the left and right foot detection results show differentiation values, possibly due to the side difference between the dominant and non-dominant foot. In addition, the data acquisition tools in plantar pressure under a few images in the dataset may have high accuracy due to the multi-color channel in image features [34].…”

AttentionMask R‐CNNwith edge refinement algorithm for identifying circulating genetically abnormal cells

“…Furthermore, the method used in this study is significantly faster than manual identification by a factor of approximately 1500. The proposed model also outperformed the other state‐of‐the‐art FISH‐based automatic method on identification of CACs utilizing multi‐scale YOLO (You Only Look Once)‐V4 algorithm (accuracy 93.96% and sensitivity 91.82%) [30]. The above‐mentioned model was a single‐throughput and multi‐stage algorithm, relying on segmenting all nuclei and identifying the signals points per nucleus in two steps.…”

Artificial intelligence for heart sound classification: A review

“…For example, unsupervised learning has been used to identify three distinct cardiac phenotypes in type 2 diabetic individuals (Vickers, 2017). Principal component analysis, K‐means clustering, and hierarchical clustering are common unsupervised techniques used for this purpose (Xu, Li, Lan, et al, 2023). Reinforcement learning is the strategy in which a machine learns by interacting with outcomes to maximize rewards (Long et al, 2020).…”