Predicting Outcome of Patients With Cerebral Hemorrhage Using a Computed Tomography-Based Interpretable Radiomics Model: A Multicenter Study.

OBJECTIVE: The aim of this study was to develop and validate an interpretable and highly generalizable multimodal radiomics model for predicting the prognosis of patients with cerebral hemorrhage. METHODS: This retrospective study involved 237 patients with cerebral hemorrhage from 3 medical centers, of which a training cohort of 186 patients (medical center 1) was selected and 51 patients from medical center 2 and medical center 3 were used as an external testing cohort. A total of 1762 radiomics features were extracted from nonenhanced computed tomography using Pyradiomics, and the relevant macroscopic imaging features and clinical factors were evaluated by 2 experienced radiologists. A radiomics model was established based on radiomics features using the random forest algorithm, and a radiomics-clinical model was further trained by combining radiomics features, clinical factors, and macroscopic imaging features. The performance of the models was evaluated using area under the curve (AUC), sensitivity, specificity, and calibration curves. Additionally, a novel SHAP (SHAPley Additive exPlanations) method was used to provide quantitative interpretability analysis for the optimal model. RESULTS: The radiomics-clinical model demonstrated superior predictive performance overall, with an AUC of 0.88 (95% confidence interval, 0.76-0.95; P < 0.01). Compared with the radiomics model (AUC, 0.85; 95% confidence interval, 0.72-0.94; P < 0.01), there was a 0.03 improvement in AUC. Furthermore, SHAP analysis revealed that the fusion features, rad score and clinical rad score, made significant contributions to the model's decision-making process. CONCLUSION: Both proposed prognostic models for cerebral hemorrhage demonstrated high predictive levels, and the addition of macroscopic imaging features effectively improved the prognostic ability of the radiomics-clinical model. The radiomics-clinical model provides a higher level of predictive performance and model decision-making basis for the risk prognosis of cerebral hemorrhage.

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study.

OBJECTIVES: To develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset. MATERIALS AND METHODS: Retrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions. RESULTS: The Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort. CONCLUSION: The multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model. CLINICAL RELEVANCE STATEMENT: Predicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

Antioxidative and Mitochondrial Protection in Retinal Pigment Epithelium: New Light Source in Action.

Low-color-temperature light-emitting diodes (LEDs) (called 1900 K LEDs for short) have the potential to become a healthy light source due to their blue-free property. Our previous research demonstrated that these LEDs posed no harm to retinal cells and even protected the ocular surface. Treatment targeting the retinal pigment epithelium (RPE) is a promising direction for age-related macular degeneration (AMD). Nevertheless, no study has evaluated the protective effects of these LEDs on RPE. Therefore, we used the ARPE-19 cell line and zebrafish to explore the protective effects of 1900 K LEDs. Our results showed that the 1900 K LEDs could increase the cell vitality of ARPE-19 cells at different irradiances, with the most pronounced effect at 10 W/m2. Moreover, the protective effect increased with time. Pretreatment with 1900 K LEDs could protect the RPE from death after hydrogen peroxide (H2O2) damage by reducing reactive oxygen species (ROS) generation and mitochondrial damage caused by H2O2. In addition, we preliminarily demonstrated that irradiation with 1900 K LEDs in zebrafish did not cause retinal damage. To sum up, we provide evidence for the protective effects of 1900 K LEDs on the RPE, laying the foundation for future light therapy using these LEDs.

Values of macular ganglion cell-inner plexiform layer and 10-2 visual field measurements in detecting and evaluating glaucoma.

AIM: To assess the performance of macular ganglion cell-inner plexiform layer thickness (mGCIPLT) and 10-2 visual field (VF) parameters in detecting early glaucoma and evaluating the severity of advanced glaucoma. METHODS: Totally 127 eyes from 89 participants (36 eyes of 19 healthy participants, 45 eyes of 31 early glaucoma patients and 46 eyes of 39 advanced glaucoma patients) were included. The relationships between the optical coherence tomography (OCT)-derived parameters and VF sensitivity were determined. Patients with early glaucoma were divided into eyes with or without central 10° of the VF damages (CVFDs), and the diagnostic performances of OCT-derived parameters were assessed. RESULTS: In early glaucoma, the mGCIPLT was significantly correlated with 10-2 VF pattern standard deviation (PSD; with average mGCIPLT: ß=-0.046, 95%CI, -0.067 to -0.024, P<0.001). In advanced glaucoma, the mGCIPLT was related to the 24-2 VF mean deviation (MD; with average mGCIPLT: ß=0.397, 95%CI, 0.199 to 0.595, P<0.001), 10-2 VF MD (with average mGCIPLT: ß=0.762, 95%CI, 0.485 to 1.038, P<0.001) and 24-2 VF PSD (with average mGCIPLT: ß=0.244, 95%CI, 0.124 to 0.364, P<0.001). Except for the minimum and superotemporal mGCIPLT, the decrease of mGCIPLT in early glaucomatous eyes with CVFDs was more severe than that of early glaucomatous eyes without CVFDs. The area under the curve (AUC) of the average mGCIPLT (AUC=0.949, 95%CI, 0.868 to 0.982) was greater than that of the average circumpapillary retinal nerve fiber layer thickness (cpRNFLT; AUC=0.827, 95%CI, 0.674 to 0.918) and rim area (AUC=0.799, 95%CI, 0.610 to 0.907) in early glaucomatous eyes with CVFDs versus normal eyes. CONCLUSION: The 10-2 VF and mGCIPLT parameters are complementary to 24-2 VF, cpRNFLT and ONH parameters, especially in detecting early glaucoma with CVFDs and evaluating the severity of advanced glaucoma in group level.

[Application of FTIR spectrometry to monitoring chemosensitivity of breast cancer cell line using 5-FU].

The purpose of the present study was to compare the changes of infrared spectrum of breast cancer cell line MCF-7 treated by 5-fluorouracil with various concentrations and treating time. The results indicate that the relative intensity ratios of I2 920/I1 460 increased in the FTIR spectra of cell line MCF-7 while I1 400/I1 460, I1 080 /I1 550 and I1 240/I1 550 decreased significantly within forty-eight hours, however, no regular change was observed during 48-72 hours. The relative intensity ratio of I1 640/ I1 550 decreases along with the increase in the concentration of 5-fluorouracil. The changes of infrared spectra are consistent with the biochemical changes in breast cancer cell, and it can be the reference designators when assessing curative effect of breast cancer cell by FTIR spectrometry.

Magnetic resonance imaging assessment of the lateral geniculate nucleus volume and height in patients with glaucoma: a Meta-analysis.

AIM: To evaluate the lateral geniculate nucleus (LGN) volume and height using magnetic resonance imaging (MRI) in glaucoma patients. METHODS: Literatures retrieval was carried out through PubMed, Web of Science, Embase, and Cochrane Library. Studies that compared the volume and height of LGN in glaucoma patients with that in control subjects were included. The volume and height of LGN were extracted from the included studies. The Review Manager 5.4.1 software was used for the Meta-analysis. RESULTS: This Meta-analysis included 10 cross-sectional studies, including the eyes of 223 glaucoma patients and 185 healthy controls. Compared with the control subjects, the volume and height of LGN in glaucoma patients measured by MRI were significantly reduced {-29.13 mm3, 95% [confidence interval (CI): -44.82 to -13.43, P=0.0003; -0.61 mm, 95%CI: -0.78 to -0.44, P<0.00001, respectively]}. Subgroup analysis demonstrated that the differences of LGN volume and height between glaucoma patients and control subjects in the older group were smaller than that in the younger group, and LGN volume decreased with the increase of glaucoma severity. CONCLUSION: The results demonstrate that the volume and height of LGN are decreased in glaucoma patients, and LGN volume can be considered a parameter of glaucoma severity.

A pedigree with retinitis pigmentosa and its concomitant ophthalmic diseases.

AIM: To characterize the ophthalmic clinical phenotype of a family with retinitis pigmentosa (RP) and closed-angle glaucoma and to detect pathogenic genes and mutation sites causing RP in this family. METHODS: Ophthalmic clinic performance was examined in detail in 8 enrolled family members. Genomic DNA was extracted from the peripheral blood of 4 family members for whole-exome sequencing (WES) to select potential genetic mutations whose structures were identified by bioinformatics analysis. Then, Sanger sequencing was used in 12 family members and control group members to validate and confirm the disease-causing mutation loci, and we analyzed the genotype-phenotype relationships. RESULTS: The known c.512C>T (p.P171L) mutation in the rhodopsin (RHO) gene was only found in afflicted family members and was confirmed by WES and Sanger sequencing as the pathogenic mutation in this family. In addition to being diagnosed with RP, family member III:4 was found to have bilateral closed-angle glaucoma, high myopia, and concurrent cataracts, and family members II:2 and II:4 had pathological changes of anterior chamber angle narrowing. Family members IV:3 and IV:4 were found to have retinoschisis. CONCLUSION: Glaucoma and related pathological changes, such as retinoschisis, in family members are preliminarily considered RP complications caused by RHO mutation.