Medical image fusion realizes advantage integration of functional images and anatomical images. This article discusses the research progress of multi-model medical image fusion at feature level. We firstly describe the principle of medical image fusion at feature level. Then we analyze and summarize fuzzy sets, rough sets, D-S evidence theory, artificial neural network, principal component analysis and other fusion methods' applications in medical image fusion and get summery. Lastly, we in this article indicate present problems and the research direction of multi-model medical images in the future.
Objective To evaluate the utility of collagen-gel droplet embedded-culture drug sensitivity test (CD-DST) in pancreatic carcinoma cell by compared with WST-8. Methods The chemosensitivity to 5-fluorouracil (5-FU), gemzar (GEM) and oxaliplatin (OXA) of pancreatic adenocarcinoma cells SW1990, PCT-3 and ASPC-1 were tested by WST-8 and CD-DST respectively. Results In a certain living cell number range (500-10 000), there was a linear correlation (r=0.991 1, P＜0.05) between the integral optical density in CD-DST and the cell number. The inhibition ratios of three kinds of cell growth tested by CD-DST were higher than those tested by WST-8 (P＜0.05). The results of drug chemosensitivity to 5-FU， GEM and OXA detected by two methods were uniform. Conclusion The CD-DST can be used to assay the drug chemosensitivity in vitro for pancreatic carcinoma.
The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.
Recent years, convolutional neural network (CNN) is a research hot spot in machine learning and has some application value in computer aided diagnosis. Firstly, this paper briefly introduces the basic principle of CNN. Secondly, it summarizes the improvement on network structure from two dimensions of model and structure optimization. In model structure, it summarizes eleven classical models about CNN in the past 60 years, and introduces its development process according to timeline. In structure optimization, the research progress is summarized from five aspects (input layer, convolution layer, down-sampling layer, full-connected layer and the whole network) of CNN. Thirdly, the learning algorithm is summarized from the optimization algorithm and fusion algorithm. In optimization algorithm, it combs the progress of the algorithm according to optimization purpose. In algorithm fusion, the improvement is summarized from five angles: input layer, convolution layer, down-sampling layer, full-connected layer and output layer. Finally, CNN is mapped into the medical image domain, and it is combined with computer aided diagnosis to explore its application in medical images. It is a good summary for CNN and has positive significance for the development of CNN.
There are some problems in positron emission tomography/ computed tomography (PET/CT) lung images, such as little information of feature pixels in lesion regions, complex and diverse shapes, and blurred boundaries between lesions and surrounding tissues, which lead to inadequate extraction of tumor lesion features by the model. To solve the above problems, this paper proposes a dense interactive feature fusion Mask RCNN (DIF-Mask RCNN) model. Firstly, a feature extraction network with cross-scale backbone and auxiliary structures was designed to extract the features of lesions at different scales. Then, a dense interactive feature enhancement network was designed to enhance the lesion detail information in the deep feature map by interactively fusing the shallowest lesion features with neighboring features and current features in the form of dense connections. Finally, a dense interactive feature fusion feature pyramid network (FPN) network was constructed, and the shallow information was added to the deep features one by one in the bottom-up path with dense connections to further enhance the model’s perception of weak features in the lesion region. The ablation and comparison experiments were conducted on the clinical PET/CT lung image dataset. The results showed that the APdet, APseg, APdet_s and APseg_s indexes of the proposed model were 67.16%, 68.12%, 34.97% and 37.68%, respectively. Compared with Mask RCNN (ResNet50), APdet and APseg indexes increased by 7.11% and 5.14%, respectively. DIF-Mask RCNN model can effectively detect and segment tumor lesions. It provides important reference value and evaluation basis for computer-aided diagnosis of lung cancer.
In recent years, the task of object detection and segmentation in medical image is the research hotspot and difficulty in the field of image processing. Instance segmentation provides instance-level labels for different objects belonging to the same class, so it is widely used in the field of medical image processing. In this paper, medical image instance segmentation was summarized from the following aspects: First, the basic principle of instance segmentation was described, the instance segmentation models were classified into three categories, the development context of the instance segmentation algorithm was displayed in two-dimensional space, and six classic model diagrams of instance segmentation were given. Second, from the perspective of the three models of two-stage instance segmentation, single-stage instance segmentation and three-dimensional (3D) instance segmentation, we summarized the ideas of the three types of models, discussed the advantages and disadvantages, and sorted out the latest developments. Third, the application status of instance segmentation in six medical images such as colon tissue image, cervical image, bone imaging image, pathological section image of gastric cancer, computed tomography (CT) image of lung nodule and X-ray image of breast was summarized. Fourth, the main challenges in the field of medical image instance segmentation were discussed and the future development direction was prospected. In this paper, the principle, models and characteristics of instance segmentation are systematically summarized, as well as the application of instance segmentation in the field of medical image processing, which is of positive guiding significance to the study of instance segmentation.
Objective To further comprehend the definition， molecular mechanism， and clinical significance of perineural invasion （PNI） so as to explore new therapy for the tumors. Methods The literatures about the definition， molecular mechanism， and clinical study of PNI were reviewed and analyzed. Results At present， widely accepted definition of PNI was that at least 33% of the circumference of the nerve should be surrounded by tumor cells or tumor cells within any of three layers of the nerve sheath. The newest theory on molecular mechanism of PNI was that PNI was more like infiltration， invasion， not just diffusion. “Path of low-resistance” and “Reciprocal signaling interactions” were the main theories. More recently， the studies had demonstrated that “Reciprocal signaling interactions” could more clearly explain the mechanism of PNI. Stromal elements， including fibroblasts， seemed to play a key role in the complex signaling interactions driving PNI. Neurotrophins and axonal guidance molecules had been implicated in promoting the progress of PNI. PNI was a prognosis index in the cancers of the head and neck， stomach， pancreas， colon and rectum， and prostate， which was positive indicated that the patients would have a poor prognosis and a low 5-year survival rate. Conclusions The mechanism of PNI is very complex， and its clear mechanism is still undefined. Keeping on researching the mechanism of PNI could provide theoretical foundation to disclose the mechanism and the therapy of PNI.
Objective To investigate the impact of intraoperative red blood cell (RBC) transfusion volume on postoperative oxygenation index in lung transplant recipients. Methods A retrospective analysis was conducted on the clinical data of lung transplant recipients at Wuxi People’s Hospital Affiliated to Nanjing Medical University from 2021 to 2023. Patients were divided into a non-severe primary graft dysfunction (PGD) group and a severe PGD group based on whether their oxygenation index was greater than 200 mm Hg at postoperative 0 h, 24 h, and 48 h. General data and intraoperative RBC transfusion volumes were compared between the two groups to assess their effects on postoperative oxygenation indices at 0 h, 24 h, and 48 h. A binary logistic regression model was constructed to explore the effect values [odds ratios (OR) and their 95% confidence intervals (CI) ] of RBC transfusion volume on oxygenation status at different postoperative time points (0 h, 24 h, 48 h), and the area under the receiver operating characteristic curve (AUC) was calculated to evaluate diagnostic efficacy. Results A total of 351 patients were included, comprising 260 males and 91 females, aged 20 to 77 years. At postoperative 0 h, the OR for intraoperative RBC transfusion was 1.486 (95%CI, P=0.061); at postoperative 24 h, the OR was 3.111 (95%CI, P<0.001); and at postoperative 48 h, the OR was 1.583 (95%CI, P=0.038), indicating that the oxygenation status of lung transplant recipients was significantly affected by the volume of intraoperative transfusion over time. Furthermore, a transfusion volume greater than 975 mL significantly impacted oxygenation at postoperative 24 h and 48 h. Conclusion The volume of intraoperative RBC transfusion has a significant effect on oxygenation status at 24 h and 48 h post-surgery. The amount of RBC transfusion during lung transplantation is associated with the occurrence of severe PGD, and controlling RBC transfusion volume during the procedure may help reduce the incidence of severe PGD.
Remarkable results have been realized by the U-Net network in the task of medical image segmentation. In recent years, many scholars have been researching the network and expanding its structure, such as improvement of encoder and decoder and improvement of skip connection. Based on the optimization of U-Net structure and its medical image segmentation techniques, this paper elucidates in the following: First, the paper elaborates on the application of U-Net in the field of medical image segmentation; Then, the paper summarizes the seven improvement mechanism of U-Net: dense connection mechanism, residual connection mechanism, multi-scale mechanism, ensemble mechanism, dilated mechanism, attention mechanism, and transformer mechanism; Finally, the paper states the ideas and methods on the U-Net structure improvement in a bid to provide a reference for later researches, which plays a significant part in advancing U-Net.