STBi-YOLO: A Real-Time Object Detection Method for Lung Nodule Recognition

Abstract

Lung cancer is the most prevalent and deadly oncological disease in the world, but a timely detection of lung nodules can greatly improve the survival rate of this disease. However, due to the tiny size of lung nodules and inconspicuous edges, lung nodules are not easily distinguished by naked eyes thus medical image diagnosticians are prone to misdiagnosis simply based on their own experiences and subjective judgements. In recent years, the machine-learning-based image processing techniques find their wide applications in the field of medical diagnosis, and have been proved to be an efficient way to aid diagnosticians to accurately identify subtle lesions in images. To accurately recognize lung nodules in CT images, in this paper, we propose an approach, called STBi-YOLO. This approach stems from YOLO-v5, but makes significant improvements from three dimensions-we first use the spatial pyramid pooling network that is based on stochastic-pooling method to modify the basic network structure of YOLO-v5; then apply a bidirectional feature pyramid network to perform multi-scale feature fusion; finally improve the loss function of the YOLO-v5 and adopt the EIoU function to optimize the training model. To evaluate our approach, we compare STBi-YOLO with YOLO-v3, YOLO-v4, YOLO-v5, and multiple leading object detection models, such as Faster R-CNN and SSD. The experiments show that STBi-YOLO achieves an accuracy of 96.1% and a recall rate of 93.3% for the detection of lung nodules, while producing a 4× smaller model size in memory consumption than YOLO-v5 and exhibiting comparable results in terms of mAP and time cost against Faster R-CNN and SSD.

State of-the-Art Analysis of Multiple Object Detection Techniques using Deep Learning

“…Additionally, a study by M. Rodriguez et al utilized Roboflow for annotating medical images and training a YOLOv5-based model to detect abnormalities in lung X-rays [38]. These examples demonstrate the successful integration of Roboflow in diverse applications, emphasizing its role in facilitating data annotation and model training pipelines and in medical one of its standard applications, is detecting the Lung nodule using YOLO5 [39].…”

A Literature review on Lung Cancer Detection approaches using Medical Images

“…Kehong Liu at al. 11 proposed a real-time object detection method for lung nodule recognition. The approach is based on the YOLO (You Only Look Once) object detection algorithm, which detects objects in real time using a single convolutional neural network.…”

University Student Control Detection System Based on Machine Learning and Artificial Intelligence

“…Existen diferentes versiones de este framework, en abril del 2020 se presentó una nueva versión Yolo v5 creada por Glenn Jocher. En esta versión se encuentran 4 diferentes modelos de acuerdo a los pesos, el ancho y la profundidad de cada modelo aumentado secuencialmente: YOLO v5S, YOLO v5M, YOLO v5L, YOLO v5X [13]. Debido al excelente rendimiento en tiempo real de los algoritmos de YOLO, se utilizará el modelo de mayor precisión.…”