Objective To observe the multimodal imaging features of retinal diseases associated with COVID-19. MethodsA retrospective case study. Sixteen patients (30 eyes) of retinal diseases associated with COVID-19 admitted to the Ophthalmology Department of the Second People's Hospital of Zhengzhou in December 2022 were included in the study. There were 5 males and 11 females, with the mean age of (26.69±9.88) years; 14 patients were bilateral and 2 patients were unilateral. The time of ocular symptoms after the diagnosis of COVID-19 was (2.63±0.89) days. All patients underwent the examinations of best corrtected visual acuity (BCVA), fundus color photography (FP), infrared fundus photography (IR), optical coherence tomography (OCT). Fluorescein fundus angiography (FFA) was performed in 2 patients (4 eyes). There were 20 eyes with acute macular neuroretinopathy (AMN), including 6 eyes with cotton wool spots; 10 eyes with Purtscher-like retinopathy (PLR). The BCVA of the patients was 0.1-1.0. No obvious abnormality was found in anterior segment examination. The features of FP, IR and OCT were analyzed retrospectively. ResultsIn 20 eyes of AMN, irregular reddish brown lesions in the central or paracentral area of the macula in 14 eyes; FP showed no obvious abnormality in 6 eyes; IR showed irregular map like low reflection in the central or paracentral area of macular in all eyes; OCT showed hyperreflectivity in outer plexiform layer and outer nuclear layer, hyporeflectivity in the ellipsoid zone and photoreceptor layers in all eyes; no abnormal fluorecence was observed in 2 eyes examined by FFA. In 10 eyes with PLR, cotton wool spots and retinal hemorrhage were observed in the posterior pole and/or peripapillary area, and the peripheral retina was generally normal, Purtscher spot was found in 5 eyes and macular edema in 4 eyes; OCT showed strong reflex signal in neuroepithelial layers, edema in neuroepithelial layers in 6 eyes; in the 2 eyes examined by FFA, fluorescein leakage from the retinal vein wall was observed, the posterior pole and peripapillary area retinal arteriole occlusions showed patchy hypofluorescence, the fluorescence was obscured by retinal hemorrhage below at inferior retina. ConclusionsFor AMN associated with COVID-19, IR can show the lesion contour , OCT shows lesions in the outer retina. PLR associated with COVID-19 are usually at the posterior pole and/or peripapillary area in FP, OCT shows neurocortical edema.
Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder. Due to the subtlety of symptoms in the early stages of AD, rapid and accurate clinical diagnosis is challenging, leading to a high rate of misdiagnosis. Current research on early diagnosis of AD has not sufficiently focused on tracking the progression of the disease over an extended period in subjects. To address this issue, this paper proposes an ensemble model for assisting early diagnosis of AD that combines structural magnetic resonance imaging (sMRI) data from two time points with clinical information. The model employs a three-dimensional convolutional neural network (3DCNN) and twin neural network modules to extract features from the sMRI data of subjects at two time points, while a multi-layer perceptron (MLP) is used to model the clinical information of the subjects. The objective is to extract AD-related features from the multi-modal data of the subjects as much as possible, thereby enhancing the diagnostic performance of the ensemble model. Experimental results show that based on this model, the classification accuracy rate is 89% for differentiating AD patients from normal controls (NC), 88% for differentiating mild cognitive impairment converting to AD (MCIc) from NC, and 69% for distinguishing non-converting mild cognitive impairment (MCInc) from MCIc, confirming the effectiveness and efficiency of the proposed method for early diagnosis of AD, as well as its potential to play a supportive role in the clinical diagnosis of early Alzheimer's disease.
Objective To review the research advancement of multimodal therapy for advanced gast ric carcinoma. Methods The literatures on multimodal therapy for advanced gastric carcinoma in recent years were collected and reviewed. Results The multimodal therapy , such as preoperative chemotherapy , preoperative adjuvant chemoradiotherapy , preoperative interventional chemoradiotherapy for advanced gast ric carcinoma was effective because it could increase the rate of R0 resection for the patients with advanced gastric carcinoma. And it can decrease the mortality rate after operation , extend the overall survival time and improve patients’life quality. Conclusion Multimodal therapy is a promising method for the treatment of advanced gastric carcinoma and it should be further developed.
Objective To summarize recent advances on preoperative staging strategies in rectal cancer. Methods Relevant references about preoperative staging strategies were collected and reviewed. The multimodal preoperative evaluation (MPE) system recently documented was focused on. Results The comparably accurate T and M stage could be achieved preoperatively by following an appropriate available method; however, the N stage’s accuracy was still not satisfying. The MPE system， incorporating with the advantages of transrectal ultrasound， computerized tomography and serum amyloid A protein in a multi-disciplinary mode could display the most accurate preoperative staging for rectal cancer currently. Conclusion The MPE has potential prospects in preoperative staging of rectal cancer， and can provide the most accurate preoperative staging for rectal cancer at present.
Objective To verify the feasibility and effectiveness of the modified fast-track surgery (FTS) in the perioperative period of open liver resection. Methods A prospective randomized controlled trial was carried out in 188 consecutive patients undergoing open liver resection between March and December 2014 in the Department of Liver Surgery of West China Hospital. The modified fast recovery procedure and standard rehabilitation procedure were compared in terms of length of hospital stay after operation, hospitalization cost, complications and readmission rate. Results A total of 188 consecutive patients were enrolled in the trial. The analysis included 87 patients in the modified fast recovery group and 89 in the standard rehabilitation group. Compared with the standard rehabilitation group, the modified fast recovery group had a shorter length of hospital stay [(5.70±1.47)vs. (7.26±1.96) days] and a lower cost [(42.7±6.7)vs. (47.3±12.5) thousand yuan], and the differences were statistically significant (P<0.05). There were 20 complication cases in the modified group and 39 in the standard group with significant difference (P=0.003). There was no significant difference in the rate of readmission between the two groups (P=1.000). Compared with the standard group, patients in the modified group had less pain 8 hours, the 1st and 2nd days after surgery, better postoperative activities of daily living, more initiative cough times and off-bed activity times, longer duration of movement, and earlier bowel recovery and exhausting, and all the above differences were significantly different (P<0.05). Stepwise regression analysis showed that postoperative complications and bowel recovery and exhausting time were independent related factors for postoperative hospital stay (P<0.001). Conclusions Multimodal analgesia-based fast recovery procedure is feasible and effective in the perioperative period of partial hepatectomy. It can shorten the time of hospitalization and reduce the cost of hospitalization.
Breast cancer is a malignancy caused by the abnormal proliferation of breast epithelial cells, predominantly affecting female patients, and it is commonly diagnosed using histopathological images. Currently, deep learning techniques have made significant breakthroughs in medical image processing, outperforming traditional detection methods in breast cancer pathology classification tasks. This paper first reviewed the advances in applying deep learning to breast pathology images, focusing on three key areas: multi-scale feature extraction, cellular feature analysis, and classification. Next, it summarized the advantages of multimodal data fusion methods for breast pathology images. Finally, the study discussed the challenges and future prospects of deep learning in breast cancer pathology image diagnosis, providing important guidance for advancing the use of deep learning in breast diagnosis.
The task of automatic generation of medical image reports faces various challenges, such as diverse types of diseases and a lack of professionalism and fluency in report descriptions. To address these issues, this paper proposes a multimodal medical imaging report based on memory drive method (mMIRmd). Firstly, a hierarchical vision transformer using shifted windows (Swin-Transformer) is utilized to extract multi-perspective visual features of patient medical images, and semantic features of textual medical history information are extracted using bidirectional encoder representations from transformers (BERT). Subsequently, the visual and semantic features are integrated to enhance the model's ability to recognize different disease types. Furthermore, a medical text pre-trained word vector dictionary is employed to encode labels of visual features, thereby enhancing the professionalism of the generated reports. Finally, a memory driven module is introduced in the decoder, addressing long-distance dependencies in medical image data. This study is validated on the chest X-ray dataset collected at Indiana University (IU X-Ray) and the medical information mart for intensive care chest x-ray (MIMIC-CXR) released by the Massachusetts Institute of Technology and Massachusetts General Hospital. Experimental results indicate that the proposed method can better focus on the affected areas, improve the accuracy and fluency of report generation, and assist radiologists in quickly completing medical image report writing.
The update of the cognition of fundus diseases is inseparable from the rapid development of fundus multimodal imaging. Especially in recent years, the application of wide and ultra-wide fundus photography, ultra-wide fundus fluorescein angiography, indocyanine green angiography, fundus autofluorescence and optical coherence tomography angiography contribute to observe the peripheral retinopathy more directly. The application of adaptive optics and fluorescence lifetime imaging ophthalmoscopy contribute to have a further understanding of fundus diseases at the cellular and metabolic level. Multimodal imageing reflect the pathological characteristics of the diseases from different angles and levels. At the same time, the digitization and intelligence of fundus images are also developing rapidly. However, there are some problems that the ophthalmologists needs to consider further, such as the correctly understanding the use of multimodal imaging, the application of artificial intelligence, and how to sum up from the images.
ObjectiveTo observe and analyze the multimodal imaging characteristics of fundus in patients with sympathetic ophthalmia (SO). Methods A retrospective study. From October 2012 to December 2021, 28 patients (36 eyes) diagnosed SO in the Department of Ophthalmology, Beijing Tongren Hospital were inclued in the study. There were 19 males (25 eyes) and 9 females (11 eyes), with the mean age of 51.61±12.02 years. There were 8 exciting eyes and 28 sympathizing eyes. The time to onset after trauma or surgery was 46.10±107.98 months. All patients underwent examinations including vision test, color fundus photograph, optical coherence tomography (OCT), fundus fluorescence angiography (FFA), indocyanine green angiography (ICGA). Angio-OCT (OCTA) was performed on 3 eyes and fundus autofluorescence (AF) was performed on 8 eyes. The early and late phase were defined respectively as ≤2 months and ＞2 months. Their multimodal imaging characteristics were summarized. ResultsIn 8 exciting eyes, subretinal fibrosis with mutifocal retinal atrophy and pigmentation was noted in 5 eyes (62.50%, 5/8), the other 3 eyes showed sunset glow fundus (37.50%, 3/8). In 28 sympathizing eyes, in the early phase, the fundus photograph showed shallow retinal detachment with optic disc edema in 9 eyes (32.14%, 9/28); in the late phase, peripapillary yellowish-white subretinal lesions in 11 eyes (39.29%, 11/28). In the late course of the disease, there were yellow-white lesions around the optic disc (peridisc) and peripheral subretinal area in 11 eyes (39.29%, 11/28). Dalen-Fuchs nodules were found in 10 eyes (35.71%, 10/28). On OCT, multiple serous retinal detachment and irregular choroidal folds were noted in the early phase; hill-like subretinal hyperreflective elevation was noted in peripapillary area and subfovea with presence of cystic spaces in the intraretina in the late phase. FFA examination showed "pinpoint-like" strong fluorescence in the early stage, and "multi-lake-like" fluorescein accumulation and leakage in the late stage; "map-like" weak fluorescence around the disc in the early stage of the disease, dot-like strong fluorescence lesions in each quadrant of the peripheral retina, and fluorescence in the late stage of the disease course. enhanced. ICGA examination showed that the FFA strong fluorescence lesions in the middle and late stages were weak fluorescence. FAF examination, point-like strong and weak autofluorescence lesions with unclear boundaries. Nine sympathizing eyes with subretinal yellow-white lesions has vision without light-0.1 (significantly decreased vison), while 8 eyes with sunset glow fundus was 0.5-1.0 (mildly decreased vison). ConclusionsSO could not only show the semblable features of acute phases of Vogt-Koyanagi-Harada syndrome, but also the yellowish-white lesions in the peripapillary area, macula and periphery. Most of the eyes with peripapillary lesions has a significantly decreased vison, while the eyes with sunset glow fundus has a mildly decreased vison.
With the rapid development of ophthalmic imaging methods, there are many ways of examination in the diagnosis and treatment of fundus diseases, such as FFA, ICGA, FAF, OCT and emerging blood vessels by OCT angiography in recent years. Multi-model image can understand the changes of anatomical structure and function of different levels and parts of the fundus from different aspects. A variety of imaging examinations are combined and complemented each other, which makes us have a further understanding of the location and pathological changes of many fundus diseases. But at the same time, the emergence of multi-modal images also brings a series of problems. How to standardize the use of multi-modal imaging platform to better serve the clinic is a problem that ophthalmologists need to understand.