ObjectiveTo observe the multimodal imaging characteristics of combined hamatoma of the retina and retinal pigment epithelium (CHRRPE).MethodsA retrospective case study. From January 2013 to December 2017, 6 CHRRPE patients (6 eyes) diagnosed in Department of Ophthalmology, Sun Yat-sen Memorial Hospital were included in the study. There were 4 males and 2 females, with the mean age of 12.0±8.10 years. There were 5 eyes with BCVA ≤0.1, 1 eye with BCVA＞1.0. Corneal fluoroscopy showed 1 eye with an external oblique 15°, and the remaining eye had no abnormalities in the anterior segment. All eyes underwent fundus color photography, FAF, FFA, ICGA, OCT and color Doppler flow imaging (CDFI). The multimodal imaging characteristics were observed.ResultsAll the affected eyes CHRRPE were located in the posterior pole and showed mild elevation. Most of the retinal neuroepithelial layers had different degrees of hyperplasia, vascular tortuosity and retinal folds. Of the 6 eyes, 4 eyes (66.7%) involving the macula and optic disc, only 2 eyes (33.3%) involving the macula. OCT showed that the structure of the neuroepithelial layer was unclear and the signal intensity was uneven; it involved 2 eyes of the whole retina (33.3%) and only 4 eyes of the neuroepithelial layer (66.7%). FFA and ICGA showed that the choroidal background fluorescence of the early lesions was weakened, and the lesions showed slightly weak fluorescence; the late telangiectasia fluorescein was obviously leaked, and the lesions were stained with fluorescence. FAF mainly appears as weak autofluorescence with a small amount of strong autofluorescence. CDFI has no characteristic performance.ConclusionsCHRRPE is mainly a membrane-like hyperplasia without angiogenesis, involving the retinal neuroepithelial layer, and may also involve the entire retina. OCT is dominated by strong reflection; AF, FFA and ICGA are mainly weak fluorescence.
ObjectiveTo observe the multimodal imaging characteristics of tamoxifen retinopathy. MethodsA retrospective case study. From January 2019 to December 2021, 4 patients (8 eyes) with tamoxifen retinopathy diagnosed in Tangshan Eye Hospital were included in the study. All patients were female, with sick binoculus. The age was 59.5±4.6 years. After breast cancer resection, tamoxifen 20 mg/d was taken orally consecutively, including 1, 1, and 2 cases who took tamoxifen orally for 5, 7, and ≥10 years. All eyes were examined by fundus color photography, optical coherence tomography (OCT), OCT angiography (OCTA), fundus fluorescein angiography (FFA), and fundus autofluorescence (AF). The multi-mode image features of the fundus of the affected eyes were observed. ResultsThe yellow white dot crystal like material deposition in the macular area was observed in all eyes. In fundus AF examination, macular area showed patchy strong AF. FFA examination showed telangiectasia and fluorescein leakage in macular area at late stage. OCT showed that punctate strong reflexes could be seen between the neuroepithelial layers in the macular region with the formation of a space between the neuroepithelial layers, the interruption of the elliptical zone (EZ), and the formation of a hole in the outer lamella including 4, 5 and 3 eyes; The thickness of ganglion cells in macular region decreased in 7 eyes. OCTA showed that the blood flow density of the superficial retinal capillary plexus around the arch ring was decreased, and the retinal venules were dilated in 2 eyes; Deep capillary plexus (DCP) showed telangiectasia. ConclusionDeposition of yellowish white dot like crystals can be seen in the macular region of tamoxifen retinopathy; dotted strong reflex between neuroepithelial layers, cavity formation, thinning of ganglion cell layer, EZ middle fissure and outer lamellar fissure; DCP capillaries and venules around the arch were dilated; telangiectasia in macular region; flaky strong AF in macular region.
ObjectiveTo observe the clinical and fundus imaging features of acute macular neuroretinopathy (AMN) associated with COVID-19. MethodsA retrospective case study. A total of 32 eyes of 18 patients diagnosed of AMN associated with COVID-19 at Chengdu Aidi Eye Hospital from December 2022 to February 2023 were included. All patients had a history of fever 1 to 5 days prior to ocular onset and tested positive for SARS CoV-2 antigen. All patients were examined by best-corrected visual acuity (BCVA), color fundus photography, scanning laser ophthalmoscope (SLO), infrared fundus photography (IR), and optical coherence tomography (OCT); OCT angiography, visual field and multifocal electroretinogram (mf-ERG) were performed in 6 patients (11 eyes), 3 patients (6 eyes) and 1 patient (2 eyes), respectively. Follow-up time was 8-10 weeks. The clinical and fundus imaging features were observed and analyzed.ResultsThere were 6 males (12 eyes) and 12 females (20 eyes), aged from 15 to 36 years, with the mean age of (28.00±5.86) years. Fourteen patients were bilateral and 4 patients were unilateral. The time from the onset of eye symptoms to seeing a doctor was ranged from 1 day to 8 weeks. Among them, 6 patients (10 eyes) visited the doctor within 3 days of onset, while 12 patients (22 eyes) visited the doctor after 3 days of onset. The BCVA was 0.80±0.29. Fundus color photography and SLO examination showed that only 2 patients (4 eyes) showed sheet or petal-like dark red lesions in the macular area, and no obvious abnormal changes were observed in other patients. No obvious abnormalities were found in AF examination of all patients. IR examination showed no significant abnormality in 6 cases which came to hospital within 3 days after the onset, but irregular hyporeflective dark shadow lesions in the macular region of patients with more than 3-day course of disease was observed. OCT examinations of all eyes showed hyperreflective band or patchy lesion on the outer plexiform layer (OPL) and outer nuclear layer (ONL) and affect the ellipsoid zone (EZ) and interdigitation zone (IZ). In 11 eyes of 6 patients undergoing OCTA examination, the blood flow density of the choroidal capillary layer in the focal area decreased. In 6 eyes of 3 patients who underwent visual field examination, the physiologic scotoma was slightly enlarged. One patient (2 eyes) receiving mf-ERG showed a concave reduction in macular center amplitude. The hyperreflective band lesion on OPL and ONL disappear rapidly within 2 weeks, while the continuity of EZ recovered slowly, and the disruption of IZ kept existing for more than 10 weeks. ConclusionsMost AMN associated with COVID-19 are young women; IR showed irregular weak reflex in the lesion area. OCT showed strong OPL and ONL reflection. OCTA was characterized by decreased blood flow density in the choroidal capillary layer of the focal area.
Objective To explore the research progress of the multimodal clinical support system (CSS). Methods With recognized development and operation of the multi-model CSS, and compared to the traditional CSS, to explore the research progress of the multimodal CSS. Results Based on the realization of the concept, purpose and characteristics of the multimodal CSS, it has been known that the international research progress of the multimodal CSS. Conclusion The developing and evolving of the CSS model have offered a new assist to the multi-disciplinary treatment model, and have enhanced the improving system associated with the practice of evidence-based medicine. However, the application of clinical support system program (CSSP) in our country still needs more research.
Objective To establish the optimal morphological criteria combined with fibrinogen level for evaluation of lymph node metastasis in colorectal cancer. Methods A consecutive series of 690 patients who underwent curative surgery for colorectal cancer, were examined by abdominopelvic enhanced multi-slice spiral computed tomography (MSCT) scan. If regional lymph nodes appeared, the maximal long-axis diameter (MLAD), maximal short-axis diameter (MSAD), and axial ratio (MSAD/MLAD) were recorded. At each lymph node size cut-off value, the following were calculated: accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Moreover, preoperative plasma level of fibrinogen was retrospectively examined to identify metastatic or inflammatory lymph node combined with MSCT image. Both modalities, MSCT plus fibrinogen and MSCT alone, were compared based on the pathologic findings. Results The study population consisted of 100 patients with regional lymph nodes show. No significant difference was found between metastatic and inflammatory lymph nodes in imaging characteristics (Pgt;0.05). The best cut-off value of MSAD was 6 mm for lymph node metastasis with the sensitivity of 46.8%, specificity of 68.4%, accuracy of 55.0%, PPV of 70.7% and NPV of 44.1%. The best cut-off value of MLAD was 8 mm with the sensitivity of 43.5%, specificity of 63.2%, accuracy of 51.0%, PPV of 65.9% and NPV of 40.7%. Using hyperfibrinogenemia (FIB ≥3.5 g/L) to identify small metastatic lymph node, of which MSAD lt;6 mm or MLAD lt;8 mm, showed statistical diagnostic value (Kappa=0.256, P=0.047). Compared with MSAD (6 mm) alone, MSAD (6 mm) combined with hyperfibrinogenemia had a higher sensitivity (79.0% vs. 46.8%, Plt;0.001), but a similar accuracy (66.0% vs. 55.0%, Pgt;0.05) and a lower specificity (44.7% vs. 68.4%, P=0.037). MLAD (8 mm) combined with hyperfibrinogenemia led to a greater diagnostic value in sensitivity (80.6% vs. 43.5%, Plt;0.001) and accuracy (66.0% vs. 51.0%, P=0.031) than MLAD (8 mm) alone, with a no-significantly decreasing specificity (42.1% vs. 63.2%, Pgt;0.05). Conclusions This present study recommend MSAD ≥6 mm or MLAD ≥8 mm as the optimal criteria for preoperative N staging in colorectal cancer. Moreover, the sensitivity and even accuracy could be improved by combining hyperfibrinogenemia for lymph node metastasis identification.
Currently, the development of deep learning-based multimodal learning is advancing rapidly, and is widely used in the field of artificial intelligence-generated content, such as image-text conversion and image-text generation. Electronic health records are digital information such as numbers, charts, and texts generated by medical staff using information systems in the process of medical activities. The multimodal fusion method of electronic health records based on deep learning can assist medical staff in the medical field to comprehensively analyze a large number of medical multimodal data generated in the process of diagnosis and treatment, thereby achieving accurate diagnosis and timely intervention for patients. In this article, we firstly introduce the methods and development trends of deep learning-based multimodal data fusion. Secondly, we summarize and compare the fusion of structured electronic medical records with other medical data such as images and texts, focusing on the clinical application types, sample sizes, and the fusion methods involved in the research. Through the analysis and summary of the literature, the deep learning methods for fusion of different medical modal data are as follows: first, selecting the appropriate pre-trained model according to the data modality for feature representation and post-fusion, and secondly, fusing based on the attention mechanism. Lastly, the difficulties encountered in multimodal medical data fusion and its developmental directions, including modeling methods, evaluation and application of models, are discussed. Through this review article, we expect to provide reference information for the establishment of models that can comprehensively utilize various modal medical data.
Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative disease. Neuroimaging based on magnetic resonance imaging (MRI) is one of the most intuitive and reliable methods to perform AD screening and diagnosis. Clinical head MRI detection generates multimodal image data, and to solve the problem of multimodal MRI processing and information fusion, this paper proposes a structural and functional MRI feature extraction and fusion method based on generalized convolutional neural networks (gCNN). The method includes a three-dimensional residual U-shaped network based on hybrid attention mechanism (3D HA-ResUNet) for feature representation and classification for structural MRI, and a U-shaped graph convolutional neural network (U-GCN) for node feature representation and classification of brain functional networks for functional MRI. Based on the fusion of the two types of image features, the optimal feature subset is selected based on discrete binary particle swarm optimization, and the prediction results are output by a machine learning classifier. The validation results of multimodal dataset from the AD Neuroimaging Initiative (ADNI) open-source database show that the proposed models have superior performance in their respective data domains. The gCNN framework combines the advantages of these two models and further improves the performance of the methods using single-modal MRI, improving the classification accuracy and sensitivity by 5.56% and 11.11%, respectively. In conclusion, the gCNN-based multimodal MRI classification method proposed in this paper can provide a technical basis for the auxiliary diagnosis of Alzheimer’s disease.
Objective To understand the effect of World Health Organization(WHO) multimodal hand hygiene improvement strategy on hand hygiene compliance among acupuncturists. Methods All the acupuncturists in departments (Department of Acupuncture, Department of Encephalopathy, Department of Orthopedics and Traumatology) with acupuncture programs in Xi’an Hospital of TCM were chosen in this study between September 2015 and August 2016. Based on the WHO multimodal hand hygiene improvement strategy, comprehensive measures were regulated among acupuncturists. Hand hygiene compliance and accuracy, and hand hygiene knowledge score were compared before and after the strategy intervention. Then, the effects of key strategies were evaluated. Results Overall hand hygiene compliance rate, accuracy and knowledge scores increased from 51.07%, 19.86% and 81.90±2.86 before intervention to 72.34%, 51.70%, and 98.62±2.92 after intervention (P<0.05). Hand hygiene compliance rates also increased in various occasions such as before contacting the patient, after contacting the patient, before acupuncture treatment, and before acupuncture needle manipulation (P<0.05). Conclusion Hand hygiene compliance in acupuncturists can be significantly improved by the implementation of WHO multimodal hand hygiene improvement strategy.
Macular choroidal macrovessel (MCM) is a recently reported rare choroidal vascular abnormality, characterized by a distinctly thickened choroidal vessel extending from the macular area to the temporal periphery area in fundus examinations. MCM may be an abnormal dilatation of the posterior ciliary artery. The diagnosis of MCM relies on multimodal imaging examinations, with indocyanine green angiography and optical coherence tomography being particularly critical, while optical coherence tomography angiography serves as an essential supplementary and non-invasive alternative. Due to its rarity, ophthalmologists generally have limited awareness of MCM. In clinical practice, it is essential to be familiar with the clinical manifestations and imaging characteristics of MCM, to improve diagnostic levels, enhance differentiation capabilities, and minimize the occurrence of misdiagnosis.
Stellate multiform amelanotic choroidopathy (SMACH) is a rare choroidal disease that can cause persistent subretinal fluid (SRF). It is more common in young individuals, with a similar male-to-female ratio, it is most often unilateral, and its clinical manifestations are diverse. The pathogenesis of SMACH is not well understood, but it may be a form of congenital choroidal dysplasia. The progressive impact of the lesion on the choroidal capillaries and the retinal pigment epithelium may be the cause of SRF. Its characteristic multimodal imaging changes include optical coherence tomography showing hyperreflective fibrous-like changes located in the inner choroidal stroma. Typical finger-like projections arranged in a stellate configuration are best seen on near-infrared imaging, indocyanine green angiography, and en face optical coherence tomography. The lesion is stable, with no progressive changes, and is unresponsive to treatment. Clinicians have limited knowledge about SMACH, which can lead to patients undergoing unnecessary or inappropriate treatments. Therefore, it is necessary to understand and recognize SMACH early in clinical practice.