[A clinicopathological classification of space-occupying lesions of the orbit in 1 913 patients from 2000 to 2021].

Objective: To investigate the histopathological classification of orbital space-occupying lesions. Methods: This is a retrospective case series study. The clinical and pathological data of 1 913 tissue specimens from 1 913 patients with space-occupying lesions of the orbit which were examined in the Second Affiliated Hospital, Zhejiang University School of Medicine from January 2000 to December 2021 were collected. The mass lesions were classified based on histogenesis, pathological nature and age. Results: There were 913 males (47.7%) and 1 000 females (52.3%). The lesions were benign in 1 489 patients (77.8%) and malignant in 424 patients (22.2%). Based on histogenesis, there were 521 vasculogenic lesions (27.2%), which rancked first, 407 cystoid lesions (21.3%), 277 lymphoproliferative lesions (14.5%), 182 lacrimal gland lesions (9.5%) and 121 inflammatory lesions (6.3%). By pathological nature, there were 1 489 benign lesions, including cavernous hemangioma (275, 14.4%), dermoid cyst (225, 11.8%), other hemangiomas (199, 10.4%), epidermoid cyst (136, 7.1%) and benign mixed tumor of the lacrimal gland (134, 7.0%), and 257 malignant lesions, including lymphoma (210, 11.0%) and sebaceous gland carcinoma (47, 2.5%). The age of all patients ranged from 0 to 90 years, while 247 lesions (12.9%) occurred in patients aged 0 to18 years, 1 270 lesions (66.4%) in patients aged 19 to 59 years, and 396 lesions (20.7%) in patients aged 60 to 90 years. Conclusions: In 22 years, almost 2/3 benign orbital lesions in the Second Affiliated Hospital, Zhejiang University School of Medicine occurred in young and middle-aged patients, and males were fewer than females. The most common benign orbital tumors was cavernous hemangioma, followed by dermoid cyst and epidermoid cyst. And the most common malignant orbital tumor was lymphoma, which occurred more frequently in older patients.

Trends in clinical validation and usage of US Food and Drug Administration-cleared artificial intelligence algorithms for medical imaging.

AIM: To examine the current landscape of US Food and Drug Administration (FDA)-approved artificial intelligence (AI) medical imaging devices and identify trends in clinical validation strategy. MATERIALS AND METHODS: A retrospective study was conducted that analysed data extracted from the American College of Radiology (ACR) Data Science Institute AI Central database as of November 2021 to identify trends in FDA clearance of AI products related to medical imaging. Product and clinical validation information of each device was gathered from their respective public 510(k) summary or de novo request submission, depending on their type of authorisation. RESULTS: Overall, the database included a total of 151 AI algorithms that were cleared by the FDA between 2008 and November 2021. Out of the 151 FDA summaries reviewed, 97 (64.2%) reported the use of clinical data to validate their device, with six (4%) revealing study participant demographics, and eight (5.3%) reporting the specifications of the machines used. A total of 51 (33.8%) AI devices characterised their clinical data as multicentre, three (2%) as single-centre, and the remaining 97 (64.2%) did not specify. The ground truth used for clinical validation was specified in 78 (51.6%) FDA summaries. CONCLUSION: A wide breadth of AI algorithms has been developed for medical imaging. Most of the FDA summaries of the devices mention their use of clinical data and patient cases for device validation; however, few devices revealed the patient demographics or machine specifications used in their clinical studies, which may lead some consumers to question their external validation.

Radiomics-Based Machine Learning for Outcome Prediction in a Multicenter Phase II Study of Programmed Death-Ligand 1 Inhibition Immunotherapy for Glioblastoma.

BACKGROUND AND PURPOSE: Imaging assessment of an immunotherapy response in glioblastoma is challenging due to overlap in the appearance of treatment-related changes with tumor progression. Our purpose was to determine whether MR imaging radiomics-based machine learning can predict progression-free survival and overall survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy. MATERIALS AND METHODS: Post hoc analysis was performed of a multicenter trial on the efficacy of durvalumab in glioblastoma (n = 113). Radiomics tumor features on pretreatment and first on-treatment time point MR imaging were extracted. The random survival forest algorithm was applied to clinical and radiomics features from pretreatment and first on-treatment MR imaging from a subset of trial sites (n = 60-74) to train a model to predict long overall survival and progression-free survival and was tested externally on data from the remaining sites (n = 29-43). Model performance was assessed using the concordance index and dynamic area under the curve from different time points. RESULTS: The mean age was 55.2 (SD, 11.5) years, and 69% of patients were male. Pretreatment MR imaging features had a poor predictive value for overall survival and progression-free survival (concordance index = 0.472-0.524). First on-treatment MR imaging features had high predictive value for overall survival (concordance index = 0.692-0.750) and progression-free survival (concordance index = 0.680-0.715). CONCLUSIONS: A radiomics-based machine learning model from first on-treatment MR imaging predicts survival in patients with glioblastoma on programmed death-ligand 1 inhibition immunotherapy.

Automatic Machine Learning to Differentiate Pediatric Posterior Fossa Tumors on Routine MR Imaging.

BACKGROUND AND PURPOSE: Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging. MATERIALS AND METHODS: This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n = 111), ependymoma (n = 70), and pilocytic astrocytoma (n = 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation. RESULTS: For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method χ2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P < .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma. CONCLUSIONS: Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review.

[Analysis of the histopathological features of recurrent retinoblastoma after vitrectomy].

Objective: To analyze the histopathological features and histopathological risk factors (HRF) of tumor recurrence after vitrectomy in patients with retinoblastoma (RB). Methods: Retrospective case series. Twenty-nine patients (29 eyes) who underwent enucleation from April 2014 to April 2019 at the Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University due to tumor recurrence after vitrectomy in the other hospitals were enrolled and archived. The pathological sections of the other hospitals were read by the pathologists of the department and the pathological report was written. Histopathological features and HRF were analyzed in this group of patients. The HRF used in this study was defined as tumor invasion of the optic nerve, the choroid (the largest diameter ≥ 3 mm and mostly reaching the inner sclera), the sclera, the anterior segment of the eye, and tumor passing through the scleral and growing outside the eyeball. Results: Of the 29 patients with RB recurrence after vitrectomy, 18 (62.1%) were male and 11 (37.9%) were female. The age was 1-10 years with a median age of 3 years. Among 29 eyes, the tumor invaded the ciliary body in 19 eyes (65.5%), the iris in 14 eyes (48.3%), the anterior chamber in 10 eyes (34.5%), and the anterior chamber angle in 7 eyes (24.1%). Of the 29 eyes, 27 eyes (93.1%) had HRF. The most common HRF was invading the anterior segment of the eye(77.8%, 21/27). Conclusions: In patients with recurrence after vitrectomy for RB, the most common tumor invasion site in histopathology is the anterior segment of the eye, particularly the ciliary body. More than 90% of the patients have HRF. Vitrectomy for RB treatment requires a rigorous surgical indication assessment. (Chin J Ophthalmol, 2019, 55: 854-859).

[Cautious choice of vitrectomy in patients with retinoblastoma].

In recent years, the treatment concept of retinoblastoma has changed from focusing on saving children's life to preserving the eyeballs and useful visual function. As a promising way to retain the eyeball, the application of vitrectomy in patients with retinoblastoma has long been debated. In view of the special anatomical structure of eyes and the biological characteristics of retinoblastoma cells, retinoblastoma is always prone to recurrence and metastasis after vitrectomy. Therefore, vitrectomy could hardly be a routine treatment and it should be used in retinoblastoma patients cautiously. (Chin J Ophthalmol, 2018, 54: 649-651).

Diagnostic Accuracy of Amino Acid and FDG-PET in Differentiating Brain Metastasis Recurrence from Radionecrosis after Radiotherapy: A Systematic Review and Meta-Analysis.

BACKGROUND: Current studies that analyze the usefulness of amino acid and FDG-PET in distinguishing brain metastasis recurrence and radionecrosis after radiation therapy are limited by small cohort size. PURPOSE: Our aim was to assess the diagnostic accuracy of amino acid and FDG-PET in differentiating brain metastasis recurrence from radionecrosis after radiation therapy. DATA SOURCES: Studies were retrieved from PubMed, Embase, and the Cochrane Library. STUDY SELECTION: Fifteen studies were included from the literature. Each study used PET to differentiate radiation necrosis from tumor recurrence in contrast-enhancing lesions on follow-up brain MR imaging after treating brain metastasis with radiation therapy. DATA ANALYSIS: Data were analyzed with a bivariate random-effects model. Sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were pooled, and a summary receiver operating characteristic curve was fit to the data. DATA SYNTHESIS: The overall pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio of PET were 0.85, 0.88, 7.0, 0.17, and 40, respectively. The area under the receiver operating characteristic curve was 0.93. On subgroup analysis of different tracers, amino acid and FDG-PET had similar diagnostic accuracy. Meta-regression analysis demonstrated that the method of quantification based on patient, lesion, or PET scan (based on lesion versus not, P = .07) contributed to the heterogeneity. LIMITATIONS: Our study was limited by small sample size, and 60% of the included studies were of retrospective design. CONCLUSIONS: Amino acid and FDG-PET had good diagnostic accuracy in differentiating brain metastasis recurrence from radionecrosis after radiation therapy.

[Genetic analysis of mutant genes and RAPD marker of mutant gene of narrow leaflet in soybean].

Mutant E182 with "narrow leaflet-4 seeded pod" was selected from descendents of EMS-treated seeds of soybean variety Lu Dou No. 4 (LD4) with "ovate leaflet-without 4 seeded pod". Genetic analyses of F2 individuals of crossing between mutant E182 and parent LD4 indicated that segregation ratio between ovate and narrow leaflet was 3:1, so was segregation ratio between "without 4 seeded pod" and "4 seeded pod". Segregation ratios of four character types in F2 population of 1,654 individuals were beyond 9:3:3:1 of two pairs of independent gene, showing linkage inheritance. Reccmbinant ratio between mutant genes of narrow leaflet and 4 seeded pod was 11.24% +/- 0.81%. On the other hand, mutant E182, parent LD4 and F2, F3 individuals of their hybrids were analyzed by means of RAPD technique. The marker OPY6-1300 linked with the mutant gene of narrow leaflet was generated, and genetic distance of the marker and mutant gene was 8 cent Morgan (cM), being 10 cM nearer than RFLP marker of narrow leaflet generated by shoemaker.