Laparoscopic image enhancement based on distributed retinex optimization with refined information fusion

LRENet: a location-related enhancement network for liver lesions in CT images

Objective. Liver cancer is a major global health problem expected to increase by more than 55% by 2040. Accurate segmentation of liver tumors from computed tomography (CT) images is essential for diagnosis and treatment planning. However, this task is challenging due to the variations in liver size, the low contrast between tumor and normal tissue, and the noise in the images.

APPROACH

In this study, we propose a novel method called location-related enhancement network (LRENet) which can enhance the contrast of liver lesions in CT images and facilitate their segmentation. LRENet consists of two steps: (1) locating the lesions and the surrounding tissues using a morphological approach and (2) enhancing the lesions and smoothing the other regions using a new loss function.

MAIN RESULTS

We evaluated LRENet on two public datasets (LiTS and 3Dircadb01) and one dataset collected from a collaborative hospital (Liver cancer dateset), and compared it with state-of-the-art methods regarding several metrics. The results of the experiments showed that our proposed method outperformed the compared methods on three datasets in several metrics. We also trained the Swin-Transformer network on the enhanced datasets and showed that our method could improve the segmentation performance of both liver and lesions.

SIGNIFICANCE

Our method has potential applications in clinical diagnosis and treatment planning, as it can provide more reliable and informative CT images of liver tumors.

Joint-Prior-Based Uneven Illumination Image Enhancement for Surface Defect Detection

Images in real surface defect detection scenes often suffer from uneven illumination. Retinex-based image enhancement methods can effectively eliminate the interference caused by uneven illumination and improve the visual quality of such images. However, these methods suffer from the loss of defect-discriminative information and a high computational burden. To address the above issues, we propose a joint-prior-based uneven illumination enhancement (JPUIE) method. Specifically, a semi-coupled retinex model is first constructed to accurately and effectively eliminate uneven illumination. Furthermore, a multiscale Gaussian-difference-based background prior is proposed to reweight the data consistency term, thereby avoiding the loss of defect information in the enhanced image. Last, by using the powerful nonlinear fitting ability of deep neural networks, a deep denoised prior is proposed to replace existing physics priors, effectively reducing the time consumption. Various experiments are carried out on public and private datasets, which are used to compare the defect images and enhanced results in a symmetric way. The experimental results demonstrate that our method is more conducive to downstream visual inspection tasks than other methods.