School of Information Technology, Indian Institute of Technology, Delhi, India.
Department of Radiology, All India Institute of Medical Sciences, New Delhi, India.
Sci Rep. 2022 Jul 8;12(1):11622. doi: 10.1038/s41598-022-15259-7.
While detection of malignancies on mammography has received a boost with the use of Convolutional Neural Networks (CNN), detection of cancers of very small size remains challenging. This is however clinically significant as the purpose of mammography is early detection of cancer, making it imperative to pick them up when they are still very small. Mammography has the highest spatial resolution (image sizes as high as 3328 × 4096 pixels) out of all imaging modalities, a requirement that stems from the need to detect fine features of the smallest cancers on screening. However due to computational constraints, most state of the art CNNs work on reduced resolution images. Those that work on higher resolutions, compromise on global context and work at single scale. In this work, we show that resolution, scale and image-context are all important independent factors in detection of small masses. We thereby use a fully convolutional network, with the ability to take any input size. In addition, we incorporate a systematic multi-scale, multi-resolution approach, and encode image context, which we show are critical factors to detection of small masses. We show that this approach improves the detection of cancer, particularly for small masses in comparison to the baseline model. We perform a single institution multicentre study, and show the performance of the model on a diagnostic mammography dataset, a screening mammography dataset, as well as a curated dataset of small cancers < 1 cm in size. We show that our approach improves the sensitivity from 61.53 to 87.18% at 0.3 False Positives per Image (FPI) on this small cancer dataset. Model and code are available from https://github.com/amangupt01/Small_Cancer_Detection.
虽然卷积神经网络 (CNN) 的使用使乳腺癌的恶性肿瘤检测得到了提升，但非常小的癌症的检测仍然具有挑战性。这在临床上意义重大，因为乳房 X 光摄影的目的是早期发现癌症，因此当癌症还非常小时就必须将其检测出来。在所有成像方式中，乳房 X 光摄影具有最高的空间分辨率（高达 3328×4096 像素的图像大小），这一要求源于检测筛查中最小癌症的精细特征的需要。然而，由于计算限制，大多数最先进的 CNN 都在降低分辨率的图像上工作。那些在更高分辨率下工作的 CNN 则牺牲了全局上下文，并在单一尺度下工作。在这项工作中，我们表明分辨率、比例和图像上下文都是小肿块检测的重要独立因素。因此，我们使用具有能够接受任何输入大小的全卷积网络。此外，我们采用了系统的多尺度、多分辨率方法，并对图像上下文进行编码，我们证明这些都是检测小肿块的关键因素。我们表明，与基线模型相比，这种方法可以提高癌症的检测率，特别是对于小肿块的检测率。我们进行了一项单机构多中心研究，并在诊断性乳房 X 光摄影数据集、筛查性乳房 X 光摄影数据集以及大小小于 1 厘米的小癌症的精选数据集上展示了该模型的性能。我们表明，我们的方法在这个小癌症数据集上，将 0.3 个假阳性图像（FPI）的敏感度从 61.53%提高到了 87.18%。模型和代码可在 https://github.com/amangupt01/Small_Cancer_Detection 上获取。
