根據我國衛生福利部統計，肺癌是國人死因中的第一名，並且在全球亦是主要的死因之一。肺結節的辨識對於肺癌篩檢至關重要。 然而，X光影像肺結節偵測相關研究受到註釋資料稀少和結節區域定位不精確的阻礙，使得標準物件偵測演算法在定位肺結節上難以有良好的表現。為解決物件偵測效能不如預期之問題，本研究提出了一種自適應影像區塊(patch)聚合方法，通過同時進行肺結節識別和定位，一方面透過影像區塊增加訓練樣本以及加強面積小的病灶之定位，另一方面透過弱監督式學習的方式，使訓練樣本能夠更有效的被利用。本研究所提出的模型可以在訓練階段同時利用有無定位標註之資料，以端到端(End-to-End)的方式最佳化模型參數。本研究亦提出影像塊位置分類模組，以進一步提升模型保留全局解剖學構造之能力。
本研究在多個資料集上評估我們的模型，其中本研究的模型在分類任務中獲得了 79.4% AUROC ，在肺結節定位任務中獲得了 51.52% AP50 ，和現行許多肺部病灶偵測演算法相比，有著顯著的提升。

Lung cancer is a major cause of death worldwide. The identification of lung nodules is crucial to lung cancer screening. However, research in lung nodule detection suffers from scarce annotated data and imprecise localization of the nodule regions. We proposed an adaptive patch aggregating approach to perform lung nodule identification and localization through a unified framework. The proposed model can utilize both data samples with and without bounding box annotations during the training phase to optimize the parameters of the network in an end-to-end manner. We evaluate our model on multiple datasets, where our model achieved a 79.4% AUROC score on the classification task and a 51.52% AP50 score on the lung nodule localization task, which significantly improves upon standard object detection methods in lung lesions.

Carse, J., & McKenna, S. (2019). Active learning for patch-based digital pathology using convolutional neural networks to reduce annotation costs. European Congress on Digital Pathology, 20–27.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 248–255. https://doi.org/10.1109/CVPR.2009.5206848
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., & others. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv Preprint ArXiv:2010.11929.
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 580–587.
Ilse, M., Tomczak, J., & Welling, M. (2018). Attention-based deep multiple instance learning. International Conference on Machine Learning, 2127–2136.
Li, Z., Wang, C., Han, M., Xue, Y., Wei, W., Li, L.-J., & Fei-Fei, L. (2018). Thoracic disease identification and localization with limited supervision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 8290–8299.
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, 2980–2988.
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft coco: Common objects in context. European Conference on Computer Vision, 740–755.
Liu, R., Lehman, J., Molino, P., Petroski Such, F., Frank, E., Sergeev, A., & Yosinski, J. (2018). An intriguing failing of convolutional neural networks and the coordconv solution. Advances in Neural Information Processing Systems, 31.
Liu, Y.-C., Ma, C.-Y., He, Z., Kuo, C.-W., Chen, K., Zhang, P., Wu, B., Kira, Z., & Vajda, P. (2021). Unbiased teacher for semi-supervised object detection. ArXiv Preprint ArXiv:2102.09480.
Nguyen, H. Q., Lam, K., Le, L. T., Pham, H. H., Tran, D. Q., Nguyen, D. B., Le, D. D., Pham, C. M., Tong, H. T. T., Dinh, D. H., & others. (2020). VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations. ArXiv Preprint ArXiv:2012.15029.
Oh, Y., Park, S., & Ye, J. C. (2020). Deep learning COVID-19 features on CXR using limited training data sets. IEEE Transactions on Medical Imaging, 39(8), 2688–2700.
Ozge Unel, F., Ozkalayci, B. O., & Cigla, C. (2019). The power of tiling for small object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 0.
Pandey, N. (2019). Chest Xray Masks and Labels. Pulmonary Chest X-Ray Defect Detection. https://www.kaggle.com/nikhilpandey360/chest-xray-masks-and-labels
PyTorch. (2022). TORCHVISION.MODELS. https://pytorch.org/vision/stable/models.html
RadiologyInfo.org. (2021). Radiation Dose in X-Ray and CT Exams. https://www.radiologyinfo.org/en/info/safety-xray
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779–788.
Schultheiss, M., Schmette, P., Bodden, J., Aichele, J., Müller-Leisse, C., Gassert, F. G., Gassert, F. T., Gawlitza, J. F., Hofmann, F. C., Sasse, D., & others. (2021). Lung nodule detection in chest X-rays using synthetic ground-truth data comparing CNN-based diagnosis to human performance. Scientific Reports, 11(1), 1–10.
Schultheiss, M., Schober, S. A., Lodde, M., Bodden, J., Aichele, J., Müller-Leisse, C., Renger, B., Pfeiffer, F., & Pfeiffer, D. (2020). A robust convolutional neural network for lung nodule detection in the presence of foreign bodies. Scientific Reports, 10(1), 1–9.
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, 618–626.
Society, A. C. (2021). Can Lung Cancer Be Found Early? https://www.cancer.org/cancer/lung-cancer/detection-diagnosis-staging/detection.html
Team, N. L. S. T. R. (2011). Reduced lung-cancer mortality with low-dose computed tomographic screening. New England Journal of Medicine, 365(5), 395–409.
Tizhoosh, H. R., & Pantanowitz, L. (2018). Artificial intelligence and digital pathology: challenges and opportunities. Journal of Pathology Informatics, 9.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2097–2106.
Yao, L., Prosky, J., Poblenz, E., Covington, B., & Lyman, K. (2018). Weakly supervised medical diagnosis and localization from multiple resolutions. ArXiv Preprint ArXiv:1803.07703.
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2921–2929.