Feature-guided attention network for medical image segmentation.

BACKGROUND: U-Net and its variations have achieved remarkable performances in medical image segmentation. However, they have two limitations. First, the shallow layer feature of the encoder always contains background noise. Second, semantic gaps exist between the features of the encoder and the decoder. Skip-connections directly connect the encoder to the decoder, which will lead to the fusion of semantically dissimilar feature maps. PURPOSE: To overcome these two limitations, this paper proposes a novel medical image segmentation algorithm, called feature-guided attention network, which consists of U-Net, the cross-level attention filtering module (CAFM), and the attention-guided upsampling module (AUM). METHODS: In the proposed method, the AUM and the CAFM were introduced into the U-Net, where the AUM learns to filter the background noise in the low-level feature map of the encoder and the CAFM tries to eliminate the semantic gap between the encoder and the decoder. Specifically, the AUM adopts a top-down pathway to use the high-level feature map so as to filter the background noise in the low-level feature map of the encoder. The AUM uses the encoder features to guide the upsampling of the corresponding decoder features, thus eliminating the semantic gap between them. Four medical image segmentation tasks, including coronary atherosclerotic plaque segmentation (Dataset A), retinal vessel segmentation (Dataset B), skin lesion segmentation (Dataset C), and multiclass retinal edema lesions segmentation (Dataset D), were used to validate the proposed method. RESULTS: For Dataset A, the proposed method achieved higher Intersection over Union (IoU) ( 67.91 ± 3.82 % $67.91\pm 3.82\%$ ), dice ( 79.39 ± 3.37 % $79.39\pm 3.37\%$ ), accuracy ( 98.39 ± 0.34 % $98.39\pm 0.34\%$ ), and sensitivity ( 85.10 ± 3.74 % $85.10\pm 3.74\%$ ) than the previous best method: CA-Net. For Dataset B, the proposed method achieved higher sensitivity (83.50%) and accuracy (97.55%) than the previous best method: SCS-Net. For Dataset C, the proposed method had highest IoU ( 83.47 ± 0.41 % $83.47\pm 0.41\%$ ) and dice ( 90.81 ± 0.34 % $90.81\pm 0.34\%$ ) than those of all compared previous methods. For Dataset D, the proposed method had highest dice (average: 81.53%; retina edema area [REA]: 83.78%; pigment epithelial detachment [PED] 77.13%), sensitivity (REA: 89.01%; SRF: 85.50%), specificity (REA: 99.35%; PED: 100.00), and accuracy (98.73%) among all compared previous networks. In addition, the number of parameters of the proposed method was 2.43 M, which is less than CA-Net (3.21 M) and CPF-Net (3.07 M). CONCLUSIONS: The proposed method demonstrated state-of-the-art performance, outperforming other top-notch medical image segmentation algorithms. The CAFM filtered the background noise in the low-level feature map of the encoder, while the AUM eliminated the semantic gap between the encoder and the decoder. Furthermore, the proposed method was of high computational efficiency.

Development and Validation a Nomogram Incorporating CT Radiomics Signatures and Radiological Features for Differentiating Invasive Adenocarcinoma From Adenocarcinoma In Situ and Minimally Invasive Adenocarcinoma Presenting as Ground-Glass Nodules Measuring 5-10mm in Diameter.

PURPOSE: To develop and validate a nomogram for differentiating invasive adenocarcinoma (IAC) from adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs) measuring 5-10mm in diameter. MATERIALS AND METHODS: This retrospective study included 446 patients with 478 GGNs histopathologically confirmed AIS, MIA or IAC. These patients were assigned to a primary cohort, an internal validation cohort and an external validation cohort. The segmentation of these GGNs on thin-slice computed tomography (CT) were performed semi-automatically with in-house software. Radiomics features were then extracted from unenhanced CT images with PyRadiomics. Radiological features of these GGNs were also collected. Radiomics features were investigated for usefulness in building radiomics signatures by spearman correlation analysis, minimum redundancy maximum relevance (mRMR) feature ranking method and least absolute shrinkage and selection operator (LASSO) classifier. Multivariable logistic regression analysis was used to develop a nomogram incorporating the radiomics signature and radiological features. The performance of the nomogram was assessed with discrimination, calibration, clinical usefulness and evaluated on the validation cohorts. RESULTS: Five radiomics features remained after features selection. The model incorporating radiomics signatures and four radiological features (bubble-like appearance, tumor-lung interface, mean CT value, average diameter) showed good calibration and good discrimination with AUC of 0.831(95%CI, 0.772~0.890). Application of the nomogram in the internal validation cohort with AUC of 0.792 (95%CI, 0.712~0.871) and in the external validation cohort with AUC of 0.833 (95%CI, 0.729-0.938) also indicated good calibration and good discrimination. The decision curve analysis demonstrated that the nomogram was clinically useful. CONCLUSION: This study presents a nomogram incorporating the radiomics signatures and radiological features, which can be used to predict the risk of IAC in patients with GGNs measuring 5-10mm in diameter individually.