Weakly-supervised convolutional neural networks of renal tumor segmentation in abdominal CTA images

Abstract

Background: Renal cancer is one of the 10 most common cancers in human beings. The laparoscopic partial nephrectomy (LPN) is an effective way to treat renal cancer. Localization and delineation of the renal tumor from pre-operative CT Angiography (CTA) is an important step for LPN surgery planning. Recently, with the development of the technique of deep learning, deep neural networks can be trained to provide accurate pixel-wise renal tumor segmentation in CTA images. However, constructing the training dataset with a large amount of pixel-wise annotations is a time-consuming task for the radiologists. Therefore, weakly-supervised approaches attract more interest in research.Methods: In this paper, we proposed a novel weakly-supervised convolutional neural network (CNN) for renal tumor segmentation. A three-stage framework was introduced to train the CNN with the weak annotations of renal tumors, i.e. the bounding boxes of renal tumors. The framework includes pseudo masks generation, group and weighted training phases. Clinical abdominal CT angiographic images of 200 patients were applied to perform the evaluation.Results: Extensive experimental results show that the proposed method achieves a higher dice coefficient (DSC) of 0.826 than the other two existing weakly-supervised deep neural networks. Furthermore, the segmentation performance is close to the fully supervised deep CNN. Conclusions:The proposed strategy improves not only the efficiency of network training but also the precision of the segmentation.

Use of Internally Validated Machine and Deep Learning Models to Predict Outcomes of Percutaneous Nephrolithotomy using data from the BAUS PCNL audit

“…The addition of imaging data may increase the predictability of visceral injury. Previous studies have demonstrated the use of neural networks to identify renal tumours and their vasculature, which aids operative planning [24].…”

Weakly supervised segmentation of tumor lesions in PET-CT hybrid imaging

“…Following the second approach, the location of objects in natural images can be learned to a limited extent from a weaker annotation such as a classification of the imaged object of interest, instead of an actual voxel-wise mask (i.e., the full positional information). 9 Previous studies demonstrate the potential of weakly supervised segmentation based on bounding boxes, 10 scribbles, 11 or image level class labels. 12 In this work, we propose a framework for weakly supervised segmentation of tumor lesions in full-body PET/CT images of patients with cancer.…”

3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning With Weak Annotation

“…For this reason, weak annotation has received a lot of attention in medical imaging and has been used for tumor segmentation in organs such as brain, 15,16 lung, 17 and kidney. 18 This study aims to create a training dataset based on large-scale weak annotation and use it to create a deep learning model that shows confident performance in 3D breast cancer segmentation.…”

“…However, there is a trade‐off with supervisory power for less informative forms with lower annotation costs, so caution is needed in complex annotations. For this reason, weak annotation has received a lot of attention in medical imaging and has been used for tumor segmentation in organs such as brain, 15,16 lung, 17 and kidney 18 …”