Development and Practical Implementation of a Deep Learning-Based Pipeline for Automated Pre- and Postoperative Glioma Segmentation.

BACKGROUND AND PURPOSE: Quantitative volumetric segmentation of gliomas has important implications for diagnosis, treatment, and prognosis. We present a deep-learning model that accommodates automated preoperative and postoperative glioma segmentation with a pipeline for clinical implementation. Developed and engineered in concert, the work seeks to accelerate clinical realization of such tools. MATERIALS AND METHODS: A deep learning model, autoencoder regularization-cascaded anisotropic, was developed, trained, and tested fusing key elements of autoencoder regularization with a cascaded anisotropic convolutional neural network. We constructed a dataset consisting of 437 cases with 40 cases reserved as a held-out test and the remainder split 80:20 for training and validation. We performed data augmentation and hyperparameter optimization and used a mean Dice score to evaluate against baseline models. To facilitate clinical adoption, we developed the model with an end-to-end pipeline including routing, preprocessing, and end-user interaction. RESULTS: The autoencoder regularization-cascaded anisotropic model achieved median and mean Dice scores of 0.88/0.83 (SD, 0.09), 0.89/0.84 (SD, 0.08), and 0.81/0.72 (SD, 0.1) for whole-tumor, tumor core/resection cavity, and enhancing tumor subregions, respectively, including both preoperative and postoperative follow-up cases. The overall total processing time per case was ∼10 minutes, including data routing (∼1 minute), preprocessing (∼6 minute), segmentation (∼1-2 minute), and postprocessing (∼1 minute). Implementation challenges were discussed. CONCLUSIONS: We show the feasibility and advantages of building a coordinated model with a clinical pipeline for the rapid and accurate deep learning segmentation of both preoperative and postoperative gliomas. The ability of the model to accommodate cases of postoperative glioma is clinically important for follow-up. An end-to-end approach, such as used here, may lead us toward successful clinical translation of tools for quantitative volume measures for glioma.

Tumor Embolization through Meningohypophyseal and Inferolateral Trunks is Safe and Effective.

BACKGROUND AND PURPOSE: Skull base tumors are commonly supplied by dural branches of the meningohypophyseal and inferolateral trunks. Embolization through these arteries is often avoided due to technical challenges and inherent risks; however, successful embolization can be a valuable surgical adjunct. We aimed to review the success and complications in our series of tumor embolizations through the meningohypophyseal and inferolateral trunks. MATERIALS AND METHODS: We performed a retrospective review of patients with tumor treated with preoperative embolization at our institution between 2010 and 2020. We reviewed the following data: patients' demographics, tumor characteristics, endovascular embolization variables, and surgical results including estimated blood loss, the need for transfusion, and operative time. RESULTS: Among 155 tumor embolization cases, we identified 14 patients in whom tumor embolization was performed using the meningohypophyseal (n = 13) or inferolateral (n = 4) trunk. In this group of patients, on average, 79% of tumors were embolized. No mortality or morbidity from the embolization procedure was observed in this subgroup of patients. The average estimated blood loss in the operation was 395 mL (range, 200-750 mL). None of the patients required a transfusion, and the average operative time was 7.3 hours. CONCLUSIONS: Some skull base tumors necessitate embolization through ICA branches such as the meningohypophyseal and inferolateral trunks. Our series demonstrates that an effective and safe embolization may be performed through these routes.

Preliminary Findings Associate Hippocampal 1H-MR Spectroscopic Metabolite Concentrations with Psychotic and Manic Symptoms in Patients with Schizophrenia.

BACKGROUND AND PURPOSE: Previous hippocampal proton MR spectroscopic imaging distinguished patients with schizophrenia from controls by elevated Cr levels and significantly more variable NAA and Cho concentrations. This goal of this study was to ascertain whether this metabolic variability is associated with clinical features of the syndrome, possibly reflecting heterogeneous hippocampal pathologies and perhaps variability in its "positive" (psychotic) and "negative" (social and emotional deficits) symptoms. MATERIALS AND METHODS: In a sample of 15 patients with schizophrenia according to the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, we examined the association of NAA and Cho levels with research diagnostic interviews and clinical symptom ratings of the patients. Metabolite concentrations were previously obtained with 3D proton MR spectroscopic imaging at 3T, a technique that facilitates complete coverage of this small, irregularly shaped, bilateral, temporal lobe structure. RESULTS: The patient cohort comprised 8 men and 7 women (mean age, 39.1 [SD, 10.8] years, with a mean disease duration of 17.2 [SD, 10.8] years. Despite the relatively modest cohort size, we found the following: 1) Elevated Cho levels predict the positive (psychotic, r = 0.590, P = .021) and manic (r = 0.686, P = .005) symptom severity; and 2) lower NAA levels trend toward negative symptoms (r = 0.484, P = .08). No clinical symptoms were associated with Cr level or hippocampal volume (all, P ≥ .055). CONCLUSIONS: These preliminary findings suggest that NAA and Cho variations reflect different pathophysiologic processes, consistent with microgliosis/astrogliosis and/or lower vitality (reduced NAA) and demyelination (elevated Cho). In particular, the active state-related symptoms, including psychosis and mania, were associated with demyelination. Consequently, their deviations from the means of healthy controls may be a marker that may benefit precision medicine in selection and monitoring of schizophrenia treatment.

Prevalence of Cerebral Microhemorrhage following Chronic Blast-Related Mild Traumatic Brain Injury in Military Service Members Using Susceptibility-Weighted MRI.

BACKGROUND AND PURPOSE: Cerebral microhemorrhages are a known marker of mild traumatic brain injury. Blast-related mild traumatic brain injury relates to a propagating pressure wave, and there is evidence that the mechanism of injury in blast-related mild traumatic brain injury may be different from that in blunt head trauma. Two recent reports in mixed cohorts of blunt and blast-related traumatic brain injury in military personnel suggest that the prevalence of cerebral microhemorrhages is lower than in civilian head injury. In this study, we aimed to characterize the prevalence of cerebral microhemorrhages in military service members specifically with chronic blast-related mild traumatic brain injury. MATERIALS AND METHODS: Participants were prospectively recruited and underwent 3T MR imaging. Susceptibility-weighted images were assessed by 2 neuroradiologists independently for the presence of cerebral microhemorrhages. RESULTS: Our cohort included 146 veterans (132 men) who experienced remote blast-related mild traumatic brain injury (mean, 9.4 years; median, 9 years after injury). Twenty-one (14.4%) reported loss of consciousness for <30 minutes. Seventy-seven subjects (52.7%) had 1 episode of blast-related mild traumatic brain injury; 41 (28.1%) had 2 episodes; and 28 (19.2%) had >2 episodes. No cerebral microhemorrhages were identified in any subject, as opposed to the frequency of SWI-detectable cerebral microhemorrhages following blunt-related mild traumatic brain injury in the civilian population, which has been reported to be as high as 28% in the acute and subacute stages. CONCLUSIONS: Our results may reflect differences in pathophysiology and the mechanism of injury between blast- and blunt-related mild traumatic brain injury. Additionally, the chronicity of injury may play a role in the detection of cerebral microhemorrhages.

Observations on the effect of shortening the dry period on milk yield, body weight, and circulating glucose and FFA levels in dairy cows.

The effect of shortening the dry period from 60 to 30 days in dairy cows was studied. For this purpose 18 pairs of dairy cows were matched, one member of each pair serving as a 60-day dry-period control. Singificant post-parturient differences between the two groups were observed: in the experimental group body weight and blood glucose levels did not decrease significantly, while significant decrements were observed in the control group, unlike FCM production trends during that period. In the experimental group monthly FCM production varied less than in the control group. It appeared that ante-parturient conditions programmed post-parturient energy partition.

Effects of recombinant bovine somatotropin under conditions of high production and heat stress.

The effect of bST injection on milk production of Israeli Holsteins was tested under conditions of mean production > 9000 kg/yr and climatic stress; mean maximum and minimum summer temperatures are 38 and 25 degrees C, respectively, in the Jordan Valley, located 200 m below sea level. In 1989, 111 cows were injected, and 115 cows were recorded as controls. In 1990, 108 cows were injected, and 93 cows were included as controls. Fifty-nine of the cows injected in 1990 were also injected in 1989. Production records were corrected for parity, calving month, days to first injection, and days in milk. Injection with bST increased total lactation milk production by 12%, fat production by 15%, and protein production by 13%. Injection also resulted in slight increases in fat and protein percentages. Daily milk production during the injection period was increased by 4.4 kg. Injection during the previous lactation slightly decreased production of cows injected during the following lactation. Advancing the commencement of injection from the 4th to the 2nd mo in milk did not affect total lactation production. Weight gains and dry matter intake were higher for injected cows, but body condition score was higher for the control group. Injection had no discernible effect on fertility variables.