Patients with cancer can develop bone metastasis when a solid tumor invades the bone, which is the third most commonly affected site by metastatic cancer, after the lung and liver. The early detection of bone metastases is crucial for making appropriate treatment decisions and increasing survival rates. Deep learning, a mainstream branch of machine learning, has rapidly become an effective approach to analyzing medical images. To automatically diagnose bone metastasis with bone scintigraphy, in this work, we proposed to cast the bone metastasis diagnosis problem into automated image classification by developing a deep learning-based automated classification model. A self-defined convolutional neural network consisting of a feature extraction sub-network and feature classification sub-network was proposed to automatically detect lung cancer bone metastasis, with a feature extraction sub-network extracting hierarchal features from SPECT bone scintigrams and feature classification sub-network classifying high-level features into two categories (i.e., images with metastasis and without metastasis). Using clinical data of SPECT bone scintigrams, the proposed model was evaluated to examine its detection accuracy. The best performance was achieved if the two images (i.e., anterior and posterior scans) acquired from each patient were fused using pixel-wise addition operation on the bladder-excluded images, obtaining the best scores of 0.8038, 0.8051, 0.8039, 0.8039, 0.8036, and 0.8489 for accuracy, precision, recall, specificity, F-1 score, and AUC value, respectively. The proposed two-class classification network can predict whether an image contains lung cancer bone metastasis with the best performance as compared to existing classical deep learning models. The high accumulation of 99mTc MDP in the urinary bladder has a negative impact on automated diagnosis of bone metastasis. It is recommended to remove the urinary bladder before automated analysis.
Read full abstract