Development of a deep learning-based model to diagnose mixed-type gastric cancer accurately.

OBJECTIVE: The accurate diagnosis of mixed-type gastric cancer from pathology images presents a formidable challenge for pathologists, given its intricate features and resemblance to other subtypes of gastric cancer. Artificial Intelligence has the potential to overcome this hurdle. This study aimed to leverage deep machine learning techniques to establish a precise and efficient diagnostic approach for this cancer type which can also predict the metastatic risk using two software, U-Net and QuPath, which have not been trialled in gastric cancers. METHODS: A U-Net neural network was trained to recognise, and segment differentiated components from 186 pathology images of mixed-type gastric cancer. Undifferentiated components in the same images were annotated using the open-source pathology imaging software QuPath. The outcomes from U-Net and QuPath were used to calculate the ratios of differentiation/undifferentiated components which were correlated to lymph node metastasis. RESULTS: The models established by U-Net recognised ∼91% of the regions of interest, with precision, recall, and F1 values of 90.2%, 90.9% and 94.6%, respectively, indicating a high level of accuracy and reliability. Furthermore, the receiver operating characteristic curve analysis showed an area under the cure of 91%, indicating good performance. A bell-curve correlation between the differentiated/undifferentiated ratio and lymphatic metastasis was found (highest risk between 0.683 and 1.03), which is paradigm-shifting. CONCLUSION: U-Net and QuPath exhibit promising accuracy in the identification of differentiated and undifferentiated components in mixed-type gastric cancer, as well as paradigm-shifting prediction of metastasis. These findings bring us one step closer to their potential clinical application.

[Design and Verification of Human Metabolic Measurement System Based on STM32].

A high-precision human metabolic measurement system is designed. The system uses STM32F103 as the main control chip to acquire oxygen, carbon dioxide and flow signals to calculate four quantitative indicators: oxygen consumption(VO2), carbon dioxide production(VCO2), respiratory entropy(RQ) and resting energy metabolism(REE), and finally uses an upper computer to display the calculation results.In this paper, the signal acquisition circuit design was carried out for the oxygen sensor, carbon dioxide sensor and flow sensor, and the validity of the device was verified with the American machine MGCDiagnositcs using Bland-Altman analysis method, and the results showed that the four parameters of VO2,VCO2, RQ and REE of both devices fell in the agreement interval of more than 95%. The device thus provides accurate metabolic measurements and offers an effective tool for the field of general health and clinical nutrition support in China.

Maternal Cigarette Smoke Exposure Exaggerates the Behavioral Defects and Neuronal Loss Caused by Hypoxic-Ischemic Brain Injury in Female Offspring.

OBJECTIVE: Hypoxic-ischemic encephalopathy affects ∼6 in 1,000 preterm neonates, leading to significant neurological sequela (e.g., cognitive deficits and cerebral palsy). Maternal smoke exposure (SE) is one of the common causes of neurological disorders; however, female offspring seems to be less affected than males in our previous study. We also showed that maternal SE exaggerated neurological disorders caused by neonatal hypoxic-ischemic brain injury in adolescent male offspring. Here, we aimed to examine whether female littermates of these males are protected from such insult. METHODS: BALB/c dams were exposed to cigarette smoke generated from 2 cigarettes twice daily for 6 weeks before mating, during gestation and lactation. To induce hypoxic-ischemic brain injury, half of the pups from each litter underwent left carotid artery occlusion, followed by exposure to 8% oxygen (92% nitrogen) at postnatal day (P) 10. Behavioral tests were performed at P40-44, and brain tissues were collected at P45. RESULTS: Maternal SE worsened the defects in short-term memory and motor function in females with hypoxic-ischemic injury; however, reduced anxiety due to injury was observed in the control offspring, but not the SE offspring. Both hypoxic-ischemic injury and maternal SE caused significant loss of neuronal cells and synaptic proteins, along with increased oxidative stress and inflammatory responses. CONCLUSION: Oxidative stress and inflammatory response due to maternal SE may be the mechanism of worsened neurological outcomes by hypoxic-ischemic brain injury in females, which was similar to their male littermates shown in our previous study.

Metabolic low-frequency oscillation and abbreviated protocol for estimating REE by indirect calorimetry in healthy adults.

The aim of this study is to propose a new wave protocol to identify low-frequency oscillations for evaluating resting energy expenditure (REE) and compare its performance with the 5-min interval abbreviated protocol and standard protocol. Consecutive 20-min indirect calorimetry (IC) was used to collect metabolic data from 23 women and 37 men (between 23 and 43 yr old). Sliding window filter algorithms were used to eliminate noise. Three protocols were used to evaluate REE: averaging the data between two consecutive waves (wave protocol), averaging the second 5-min intervals (interval protocol), and averaging the last 15-min REE (standard protocol). Based on 60 healthy participants' metabolic data, compared with the interval protocol, the wave protocol showed better consistency with the standard protocol. The mean bias (limits of agreement) using the wave protocol was 0.3458% (-7.817% to 8.509%), and that using the interval protocol was -1.720% (-16.06% to 12.62%). The time required to evaluate REE with the wave protocol and interval protocol was measured. The measurement time for the interval protocol was 10 min, while the average measurement time for the wave protocol was 9.75 min. We recommend the wave protocol for estimating REE in healthy people. This abbreviated protocol can identify low-frequency oscillations and consider individual differences to more accurately reflect the baseline REE compared with the interval protocol. When compared with the standard protocol, the measurement time of the wave protocol was reduced by nearly half [from 20 min (standard protocol) to 9.75 min].NEW & NOTEWORTHY For estimating REE by indirect calorimetry, to shorten the measurement time, a consideration of low-frequency oscillations is essential. Based on that we proposed a new abbreviated protocol named wave protocol, which showed accuracy approaching that of the standard protocol with a measurement time close to that of the interval abbreviated protocol.