College of Information Engineering, Zhejiang University of Technology, Hangzhou, 310014, Zhejiang, China.
Int J Comput Assist Radiol Surg. 2023 Dec;18(12):2319-2328. doi: 10.1007/s11548-023-02857-7. Epub 2023 Mar 19.
Reliable quantification of colorectal histopathological images is based on the precise segmentation of glands but precise segmentation of glands is challenging as glandular morphology varies widely across histological grades, such as malignant glands and non-gland tissues are too similar to be identified, and tightly connected glands are even highly possibly to be incorrectly segmented as one gland.
A deep information-guided feature refinement network is proposed to improve gland segmentation. Specifically, the backbone deepens the network structure to obtain effective features while maximizing the retained information, and a Multi-Scale Fusion module is proposed to increase the receptive field. In addition, to segment dense glands individually, a Multi-Scale Edge-Refined module is designed to strengthen the boundaries of glands.
The comparative experiments on the eight recently proposed deep learning methods demonstrated that our proposed network has better overall performance and is more competitive on Test B. The F1 score of Test A and Test B is 0.917 and 0.876, respectively; the object-level Dice is 0.921 and 0.884; and the object-level Hausdorff is 43.428 and 87.132, respectively.
The proposed colorectal gland segmentation network can effectively extract features with high representational ability and enhance edge features while retaining details to the maximum, dramatically improving the segmentation performance on malignant glands, and better segmentation results of multi-scale and closed glands can also be obtained.
可靠的结直肠组织病理学图像定量分析基于对腺体的精确分割，但由于腺体形态在组织学分级中变化很大，如恶性腺体与非腺体组织过于相似而难以识别，以及紧密相连的腺体甚至很可能被错误地分割为一个腺体，因此精确的腺体分割具有挑战性。
提出了一种深度信息引导的特征细化网络来提高腺体分割的性能。具体来说，骨干网络加深了网络结构以获取有效特征，同时最大限度地保留信息，并且提出了多尺度融合模块以增加感受野。此外，为了单独分割密集的腺体，设计了多尺度边缘细化模块以增强腺体的边界。
在最近提出的八种深度学习方法的对比实验中，证明了我们提出的网络具有更好的整体性能，在 Test B 上更具竞争力。Test A 和 Test B 的 F1 得分分别为 0.917 和 0.876；对象级别的 Dice 分别为 0.921 和 0.884；对象级别的 Hausdorff 分别为 43.428 和 87.132。
所提出的结直肠腺体分割网络可以有效地提取具有高表示能力的特征，并增强边缘特征，同时最大程度地保留细节，显著提高了对恶性腺体的分割性能，并且可以获得更好的多尺度和封闭腺体的分割结果。
