Automatic Detection of Brain Metastases in T1-Weighted Construct-Enhanced MRI Using Deep Learning Model

SIMPLE SUMMARY: In this research, we introduced an improved deep learning model for automatic brain metastases detection in MRI. In order to reduce false-positive results while retaining high accuracy, a modified YOLOv5 algorithm with self-attention mechanism is proposed. Our proposed deep learning model showed promising results on the internal testing set, achieving better recall and precision compared to standard algorithms. Furthermore, we also demonstrated the method’s effectiveness and generalizability on the external testing set. The study proved that our proposed framework can be used as a reliable computer-aided diagnosis system for brain metastases detection. ABSTRACT: As a complication of malignant tumors, brain metastasis (BM) seriously threatens patients’ survival and quality of life. Accurate detection of BM before determining radiation therapy plans is a paramount task. Due to the small size and heterogeneous number of BMs, their manual diagnosis faces enormous challenges. Thus, MRI-based artificial intelligence-assisted BM diagnosis is significant. Most of the existing deep learning (DL) methods for automatic BM detection try to ensure a good trade-off between precision and recall. However, due to the objective factors of the models, higher recall is often accompanied by higher number of false positive results. In real clinical auxiliary diagnosis, radiation oncologists are required to spend much effort to review these false positive results. In order to reduce false positive results while retaining high accuracy, a modified YOLOv5 algorithm is proposed in this paper. First, in order to focus on the important channels of the feature map, we add a convolutional block attention model to the neck structure. Furthermore, an additional prediction head is introduced for detecting small-size BMs. Finally, to distinguish between cerebral vessels and small-size BMs, a Swin transformer block is embedded into the smallest prediction head. With the introduction of the F2-score index to determine the most appropriate confidence threshold, the proposed method achieves a precision of 0.612 and recall of 0.904. Compared with existing methods, our proposed method shows superior performance with fewer false positive results. It is anticipated that the proposed method could reduce the workload of radiation oncologists in real clinical auxiliary diagnosis.