Infrared Thermography with High Accuracy in a Neonatal Incubator.

As the accuracy of body temperature measurement is especially critical in premature infants on admission to the neonatal intensive care unit (NICU), noninvasive measurement using infrared thermography (IRT) has not been widely adopted in the NICU due to a lack of evidence regarding its accuracy. We have established a new calibration method for IRT in an incubator, and evaluated its accuracy and reliability at different incubator settings using a variable-temperature blackbody furnace. This method improved the accuracy and reliability of IRT with an increase in percentage of data with mean absolute error (MAE) < 0.3 °C to 93.1% compared to 4.2% using the standard method. Two of three IRTs had MAE < 0.1 °C under all conditions examined. This method provided high accuracy not only for measurements at specific times but also for continuous monitoring. It will also contribute to avoiding the risk of neonates' skin trouble caused by attaching a thermistor. This study will facilitate the development of novel means of administering neonatal body temperature.

A method for improving semantic segmentation using thermographic images in infants.

BACKGROUND: Regulation of temperature is clinically important in the care of neonates because it has a significant impact on prognosis. Although probes that make contact with the skin are widely used to monitor temperature and provide spot central and peripheral temperature information, they do not provide details of the temperature distribution around the body. Although it is possible to obtain detailed temperature distributions using multiple probes, this is not clinically practical. Thermographic techniques have been reported for measurement of temperature distribution in infants. However, as these methods require manual selection of the regions of interest (ROIs), they are not suitable for introduction into clinical settings in hospitals. Here, we describe a method for segmentation of thermal images that enables continuous quantitative contactless monitoring of the temperature distribution over the whole body of neonates. METHODS: The semantic segmentation method, U-Net, was applied to thermal images of infants. The optimal combination of Weight Normalization, Group Normalization, and Flexible Rectified Linear Unit (FReLU) was evaluated. U-Net Generative Adversarial Network (U-Net GAN) was applied to thermal images, and a Self-Attention (SA) module was finally applied to U-Net GAN (U-Net GAN + SA) to improve precision. The semantic segmentation performance of these methods was evaluated. RESULTS: The optimal semantic segmentation performance was obtained with application of FReLU and Group Normalization to U-Net, showing accuracy of 92.9% and Mean Intersection over Union (mIoU) of 64.5%. U-Net GAN improved the performance, yielding accuracy of 93.3% and mIoU of 66.9%, and U-Net GAN + SA showed further improvement with accuracy of 93.5% and mIoU of 70.4%. CONCLUSIONS: FReLU and Group Normalization are appropriate semantic segmentation methods for application to neonatal thermal images. U-Net GAN and U-Net GAN + SA significantly improved the mIoU of segmentation.

Impact of awake mapping on overall survival and extent of resection in patients with adult diffuse gliomas within or near eloquent areas: a retrospective propensity score-matched analysis of awake craniotomy vs. general anesthesia.

PURPOSE: Awake craniotomy (AC) with intraoperative mapping is the best approach to preserve neurological function for glioma surgery in eloquent or near eloquent areas, but whether AC improves the extent of resection (EOR) and overall survival (OS) is controversial. This study aimed to compare the long-term clinical outcomes of glioma resection under AC with those under general anesthesia (GA). METHODS: Data of 335 patients who underwent surgery with intraoperative magnetic resonance imaging for newly diagnosed gliomas of World Health Organization (WHO) grades II-IV between 2000 and 2013 were reviewed. EOR and OS were quantitatively compared between the AC and GA groups after 1:1 propensity score matching. The two groups were matched for age, preoperative Karnofsky performance status (KPS), tumor location, and pathology. RESULTS: After propensity score matching, 91 pairs were obtained. The median EOR was 96.1% (interquartile range [IQR] 7.3) and 97.4% (IQR 14.4) in the AC and GA groups, respectively (p = 0.31). Median KPS score 3 months after surgery was 90 (IQR 20) in both groups (p = 0.384). The median survival times were 163.3 months (95% confidence interval [CI] 77.9-248.7) and 143.5 months (95% CI 94.4-192.7) in the AC and GA groups, respectively (p = 0.585). CONCLUSION: Even if the glioma was within or close to the eloquent area, AC was comparable with GA in terms of EOR and OS. In case of difficulties in randomizing patients with eloquent or near eloquent glioma, our propensity score-matched analysis provides retrospective evidence that AC can obtain EOR and OS equivalent to removing glioma under GA.

Video-based neonatal state assessment method for timing of procedures.

BACKGROUND: Procedures should be performed when an infant is most receptive to disruptions in order to reduce the stress on the infant. However, frequent direct observations place a heavy burden on medical staff. There is therefore a need for a method for quantitatively and automatically evaluating the neonatal state. METHODS: Ten infants in our hospital were enrolled in this study. The states of the infants were assessed by medical staff using the Brazelton Neonatal Behavioral Assessment Scale and were recorded on video at the same time. The recorded states were reclassified as activity levels, a new state classification method that includes middle activity, which is the appropriate time for a procedure. Using image analysis, motions of the infant were quantified as two indices: activity and pause time. Activity and pause time were compared for each activity level. The cutoff values of the indices were calculated, and the sensitivity and specificity of the middle activity were calculated. RESULTS: There was a significant difference between all groups of activity level (P < 0.01). The maximum sensitivity and specificity of middle activity were 71.7% and 51.2%, respectively. CONCLUSIONS: The neonatal state of infants can be quantitatively and automatically evaluated using video cameras, and the activity level can be used to determine an appropriate time for procedures in infants. This will reduce the burden on medical staff and lead to less stressful procedures for infants.

Prediction of lower-grade glioma molecular subtypes using deep learning.

INTRODUCTION: It is useful to know the molecular subtype of lower-grade gliomas (LGG) when deciding on a treatment strategy. This study aims to diagnose this preoperatively. METHODS: A deep learning model was developed to predict the 3-group molecular subtype using multimodal data including magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT). The performance was evaluated using leave-one-out cross validation with a dataset containing information from 217 LGG patients. RESULTS: The model performed best when the dataset contained MRI, PET, and CT data. The model could predict the molecular subtype with an accuracy of 96.6% for the training dataset and 68.7% for the test dataset. The model achieved test accuracies of 58.5%, 60.4%, and 59.4% when the dataset contained only MRI, MRI and PET, and MRI and CT data, respectively. The conventional method used to predict mutations in the isocitrate dehydrogenase (IDH) gene and the codeletion of chromosome arms 1p and 19q (1p/19q) sequentially had an overall accuracy of 65.9%. This is 2.8 percent point lower than the proposed method, which predicts the 3-group molecular subtype directly. CONCLUSIONS: A deep learning model was developed to diagnose the molecular subtype preoperatively based on multi-modality data in order to predict the 3-group classification directly. Cross-validation showed that the proposed model had an overall accuracy of 68.7% for the test dataset. This is the first model to double the expected value for a 3-group classification problem, when predicting the LGG molecular subtype.

Large-scale somatotopic refinement via functional synapse elimination in the sensory thalamus of developing mice.

Functional synapse elimination and strengthening are crucial developmental processes in the formation of precise neuronal circuits in the somatosensory system, but the underlying alterations in topographical organization are not yet fully understood. To address this issue, we generated transgenic mice in which afferent fibers originating from the whisker-related brain region, called the maxillary principal trigeminal nucleus (PrV2), were selectively visualized with genetically expressed fluorescent protein. We found that functional synapse elimination drove and established large-scale somatotopic refinement even after the thalamic barreloid architecture was formed. Before functional synapse elimination, the whisker sensory thalamus was innervated by afferent fibers not only from the PrV2, but also from the brainstem nuclei representing other body parts. Most notably, only afferent fibers from PrV2 onto a whisker sensory thalamic neuron selectively survived and were strengthened, whereas other afferent fibers were preferentially eliminated via their functional synapse elimination. This large-scale somatotopic refinement was at least partially dependent on somatosensory experience. These novel results uncovered a previously unrecognized role of developmental synapse elimination in the large-scale, instead of the fine-scale, somatotopic refinement even after the initial segregation of the barreloid map.