Detecting multiple lesions of lung cancer-caused metastasis with bone scans using a self-defined object detection model based on SSD framework

Lin, Qiang; Chen, Xiaoyan; Liu, Liangxia; Cao, Ye; Man, Zhengxing; Zeng, Xianwu; Huang, Xiaodi

doi:10.1088/1361-6560/ac944d

Cited by 4 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lung cancer detection methods based on single-stage detection, such as the YOLO series [18][19][20] or SSD [21], complete the object detection task in a single forward pass stage. For instance, Lin et al [22] proposed an automatic lesion detection model based on SSD for lung metastases caused by lung cancer in low-resolution SPECT bone scan images. Loraksa et al [23] proposed the SSD-VGG16 model for detecting nodules of osteosarcoma metastasis to the lungs, enhancing the ability to extract nodules and detection accuracy.…”

Section: The Lung Cancer Detection Methods Based On Deep Learningmentioning

confidence: 99%

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans

Wang,

Zhang,

Zhang

et al. 2024

Bioengineering

View full text Add to dashboard Cite

When dealing with small targets in lung cancer detection, the YOLO V8 algorithm may encounter false positives and misses. To address this issue, this study proposes an enhanced YOLO V8 detection model. The model integrates a large separable kernel attention mechanism into the C2f module to expand the information retrieval range, strengthens the extraction of lung cancer features in the Backbone section, and achieves effective interaction between multi-scale features in the Neck section, thereby enhancing feature representation and robustness. Additionally, depth-wise convolution and Coordinate Attention mechanisms are embedded in the Fast Spatial Pyramid Pooling module to reduce feature loss and improve detection accuracy. This study introduces a Minimum Point Distance-based IOU loss to enhance correlation between predicted and ground truth bounding boxes, improving adaptability and accuracy in small target detection. Experimental validation demonstrates that the improved network outperforms other mainstream detection networks in terms of average precision values and surpasses other classification networks in terms of accuracy. These findings validate the outstanding performance of the enhanced model in the localization and recognition aspects of lung cancer auxiliary diagnosis.

show abstract

Section: The Lung Cancer Detection Methods Based On Deep Learningmentioning

confidence: 99%

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans

Wang,

Zhang,

Zhang

et al. 2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…The authors of Ref. [39] proposed an automatic lesion detection model based on single shot multibox object detector for the automatic detection of lung cancer bone metastases in low-resolution SPECT bone scintigraphy images. The authors of Ref.…”

Section: Related Workmentioning

confidence: 99%

Bone Metastases Lesion Segmentation on Breast Cancer Bone Scan Images with Negative Sample Training

Chen,

Yu,

Lai

et al. 2023

Diagnostics

View full text Add to dashboard Cite

The use of deep learning methods for the automatic detection and quantification of bone metastases in bone scan images holds significant clinical value. A fast and accurate automated system for segmenting bone metastatic lesions can assist clinical physicians in diagnosis. In this study, a small internal dataset comprising 100 breast cancer patients (90 cases of bone metastasis and 10 cases of non-metastasis) and 100 prostate cancer patients (50 cases of bone metastasis and 50 cases of non-metastasis) was used for model training. Initially, all image labels were binary. We used the Otsu thresholding method or negative mining to generate a non-metastasis mask, thereby transforming the image labels into three classes. We adopted the Double U-Net as the baseline model and made modifications to its output activation function. We changed the activation function to SoftMax to accommodate multi-class segmentation. Several methods were used to enhance model performance, including background pre-processing to remove background information, adding negative samples to improve model precision, and using transfer learning to leverage shared features between two datasets, which enhances the model’s performance. The performance was investigated via 10-fold cross-validation and computed on a pixel-level scale. The best model we achieved had a precision of 69.96%, a sensitivity of 63.55%, and an F1-score of 66.60%. Compared to the baseline model, this represents an 8.40% improvement in precision, a 0.56% improvement in sensitivity, and a 4.33% improvement in the F1-score. The developed system has the potential to provide pre-diagnostic reports for physicians in final decisions and the calculation of the bone scan index (BSI) with the combination with bone skeleton segmentation.

show abstract

AI‐powered automated analysis of bone scans: A survey

Lin,

He,

Guo

2024

IET Image Processing

View full text Add to dashboard Cite

As one of the key techniques of artificial intelligence, deep learning has emerged as an effective approach for analysing medical images. Various imaging techniques including the planar bone scintigraphy, single photon emission computed tomography and PET can be used to evaluate, in vivo, bone conditions. The introduction of deep learning techniques especially the convolutional neural networks can significantly improve diagnosis accuracy and efficiency of nuclear medicine physicians. Focusing on bone scans acquired by various nuclear medicine imaging techniques, his paper reviews existing work on deep learning‐based classification, segmentation and object detection of bone scans. Specifically, an overview of existing work about research objective is presented, deep learning models are adopted, and main results are achieved. Research challenges and directions for developing automated analysis of bone scans with deep learning techniques are then discussed.

show abstract

Detecting multiple lesions of lung cancer-caused metastasis with bone scans using a self-defined object detection model based on SSD framework

Cited by 4 publications

References 31 publications

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans

Bone Metastases Lesion Segmentation on Breast Cancer Bone Scan Images with Negative Sample Training

AI‐powered automated analysis of bone scans: A survey

Contact Info

Product

Resources

About