An important prerequisite for improving the reliability of lung cancer surveillance and clinical interventions is accurate lung nodule segmentation. Although deep learning is effective at performing medical image segmentation, lung CT image heterogeneity, nodule size, shape, and location variations, convolutional localized feature extraction characteristics, the receptive field limitations of continuous downsampling, lesion edge information losses, fuzzy boundary segmentation challenges, and the low segmentation accuracy achieved when segmenting lung CT images using deep learning remain. An edge-enhanced multiscale Sobel coordinate attention-atrous spatial convolutional pooling pyramid V-Net (SCA-VNet) algorithm for lung nodule segmentation was proposed to solve these problems. First, a residual edge enhancement module was designed, which was used to enhance the edges of the original data. Using an edge detection operator in combination with a residual module, this module could reduce data redundancy and alleviate the gray level similarity between the foreground and background. Then, a 3D atrous spatial convolutional pooling pyramid module set different expansion rates, which could obtain feature maps under different receptive fields and capture the multiscale information of the segmentation target. Finally, a three-dimensional coordinate attention network (3D CA-Net) module was added to the encoding and decoding paths to extract channel weights from multiple dimensions. This step propagated the spatial information in the coding layer to the subsequent layers, and it could reduce the loss of information during the forward propagation process. The proposed method achieved a Dice coefficient of 87.50% on the lung image database consortium and image database resource initiative (LIDC-IDRI). It significantly outperformed the existing lung nodule segmentation models (UGS-Net, REMU-Net, and multitask models) and compared favorably with the Med3D, CENet, and PCAM_Net segmentation models in terms of their Dice coefficients, which were 3.37%, 2.2%, and 1.43%, respectively. The experimental results showed that the proposed SCA-VNet model attained improved lung nodule segmentation accuracy and laid a good foundation for improving the early detection rate of lung cancer.

Breast cancer is the cancer with the highest incidence in women worldwide, and seriously threatens the lives and health of women. Mammography, which is commonly used for screening, is considered to be the most effective means of diagnosing breast cancer. Currently, computer-assisted breast mass systems based on mammography can help doctors improve film reading efficiency, but improving the accuracy of assisted diagnostic systems and reducing the false positive rate are still challenging tasks. In the image classification field, convolutional neural networks have obvious advantages over other classification algorithms. Aiming at the very small percentage of breast lesion area in breast X-ray images, in this paper, the classical VGG16 network model is improved by simplifying the network structure, optimizing the convolution form and introducing an attention mechanism. The improved model achieves 99.8 and 98.05% accuracy on the Mammographic Image Analysis Society (MIAS) and The Digital Database for Screening Mammography (DDSM), respectively, which is obviously superior to some methods of recent studies.

Breast cancer has a very high incidence rate worldwide, and effective screening and early diagnosis are particularly important. In this paper, two improved You Only Look Once version 8 (YOLOv8) models, the YOLOv8-GHOST and YOLOv8-P2 models, are proposed to address the difficulty of distinguishing lesions from normal tissues in mammography images. The YOLOv8-GHOST model incorporates GHOSTConv and C3GHOST modules into the original YOLOv8 model to capture richer feature information while using only 57% of the number of parameters required by the original model. The YOLOv8-P2 algorithm significantly reduces the number of necessary parameters by streamlining the number of channels in the feature map. This paper proposes the YOLOv8-GHOST-P2 model by combining the above two improvements. Experiments conducted on the MIAS and DDSM datasets show that the new models achieved significantly improved computational efficiency while maintaining high detection accuracy. Compared with the traditional YOLOv8 method, the three new models improved and achieved F1 scores of 98.38%, 98.8%, and 98.57%, while the number of parameters reduced by 42.9%, 46.64%, and 2.8%. These improvements provide a more efficient and accurate tool for clinical breast cancer screening and lay the foundation for subsequent studies. Future work will explore the potential applications of the developed models to other medical image analysis tasks.