Out of hospital cardiac arrest, first steps to know and follow in Mexico to have cardioprotected territories. A point of view of a group of experts / Paro cardiaco extrahospitalario, primeros pasos que se deben conocer y hacer en México para tener espacios cardioprotegidos. Punto de vista de un grupo de expertos

Abstract Sudden cardiac death is a common occurrence. Out-of-hospital cardiac arrest is a global public health problem suffered by ≈3.8 million people annually. Progress has been made in the knowledge of this disease, its prevention, and treatment; however, most events occur in people without a previous diagnosis of heart disease. Due to its multifactorial and complex nature, it represents a challenge in public health, so it led us to work in a consensus to achieve the implementation of cardioprotected areas in Mexico as a priority mechanism to treat these events. Public access cardiopulmonary resuscitation (CPR) and early defibrillation require training of non-medical personnel, who are usually the first responders in the chain of survival. They should be able to establish a basic and efficient CPR and use of the automatic external defibrillator (AED) until the emergency services arrive at the scene of the incident. Some of the current problems in Mexico and alternative solutions for them are addressed in the present work.

Resumen La muerte súbita cardíaca (SCD) es un acontecimiento común. El paro cardiaco extrahospitalario (OHCA) es un problema de salud pública mundial que sufren ≈3.8 millones de personas al año. Se ha avanzado en el conocimiento de esta enfermedad, su prevención y tratamiento, sin embargo, la mayoría de los eventos se producen en personas sin diagnóstico previo de cardiopatía. Debido a su carácter multifactorial y complejo, representa un reto en salud pública, lo que obliga a trabajar en un consenso para lograr la implementación de "Espacios Cardio protegidos" en México, como mecanismo prioritario de atención a estos eventos. La reanimación cardiopulmonar básica (RCPB) y la desfibrilación temprana de acceso público requieren de entrenamiento al personal no médico, que suelen ser los primeros respondientes para iniciar la cadena de la supervivencia. Ellos deberían instaurar una RCPB eficiente y el uso del desfibrilador automático externo (AED) hasta que lleguen al lugar del incidente los servicios de emergencias. El presente trabajo menciona algunos de los problemas actuales en México y algunas opciones de solución para los mismos.

Automatic detection and classification of disease in citrus fruit and leaves using a customized CNN based model / Detección y clasificación automática de enfermedades en frutas y hojas de cítricos utilizando un modelo basado en CNN personalizado

India's commercial advancement and development depend heavily on agriculture. A common fruit grown in tropical settings is citrus. A professional judgment is required while analyzing an illness because different diseases have slight variati ons in their symptoms. In order to recognize and classify diseases in citrus fruits and leaves, a customized CNN - based approach that links CNN with LSTM was developed in this research. By using a CNN - based method, it is possible to automatically differenti ate from healthier fruits and leaves and those that have diseases such fruit blight, fruit greening, fruit scab, and melanoses. In terms of performance, the proposed approach achieves 96% accuracy, 98% sensitivity, 96% Recall, and an F1 - score of 92% for ci trus fruit and leave identification and classification and the proposed method was compared with KNN, SVM, and CNN and concluded that the proposed CNN - based model is more accurate and effective at identifying illnesses in citrus fruits and leaves.

El avance y desarrollo comercial de India dependen en gran medida de la agricultura. Un tipo de fruta comunmente cultivada en en tornos tropicales es el cítrico. Se requiere un juicio profesional al analizar una enfermedad porque diferentes enfermedades tienen ligeras variaciones en sus síntomas. Para reconocer y clasificar enfermedades en frutas y hojas de cítricos, se desarrolló e n esta investigación un enfoque personalizado basado en CNN que vincula CNN con LSTM. Al utilizar un método basado en CNN, es posible diferenciar automáticamente entre frutas y hojas más saludables y aquellas que tienen enfermedades como la plaga de frutas , el verdor de frutas, la sarna de frutas y las melanosis. En términos de desempeño, el enfoque propuesto alcanza una precisión del 96%, una sensibilidad del 98%, una recuperación del 96% y una puntuación F1 del 92% para la identificación y clasificación d e frutas y hojas de cítricos, y el método propuesto se comparó con KNN, SVM y CNN y se concluyó que el modelo basado en CNN propuesto es más preciso y efectivo para identificar enfermedades en frutas y hojas de cítricos.

Impacto de la Inteligencia Artificial en la Radiología

Introducción: El creciente desarrollo computacional ocurrido en los últimos años, así como el acceso a gran número de datos (Big Data) ha posibilitado la explotación de los recursos informáticos para el desarrollo de algoritmos que aumentan la calidad y alcance de la inteligencia artificial (IA), la cual está tomando un rol central en la radiología. Objetivo: Analizar el impacto de la Inteligencia Artificial en la Radiología y la necesidad de implementación en los servicios de imagenología. Método: Se emplearon 23 referencias bibliográficas en inglés y español, la mayoría extraídas de PubMed, SciELO y ScienceDirect usando los descriptores "Inteligencia Artificial", "Radiología" y "Aprendizaje automático" en idioma español y "Artificial Intelligence", "Radiology" y "Machine Learning" para el inglés. Desarrollo: No existe área de la Radiología en la cual no se haya implementado la inteligencia artificial, con el fin de mejorar y desarrollar programas que le faciliten al radiólogo y al técnico, la obtención y diagnóstico de imágenes. Cuba también está inmersa en este proceso; se están dando los primeros pasos por el desarrollo de estas tecnologías. Conclusiones: La investigación, optimización de flujo de trabajo, radiómica, predicción y clasificación de imágenes son beneficios que nos aporta la IA; lograr un aumento en la calidad de estos procesos solo es posible a través de la alianza entre las ciencias médicas e informáticas.

Introduction: The growing computational development that has occurred in recent years, as well as the access to a large number of data (Big Data), has made the exploitation of computing resources possible to develop algorithms that increase the quality and scope of artificial intelligence (AI), which is taking a central role in radiology. Objective: To analyze the impact of artificial intelligence in radiology and the need for its implementation in imaging services. Method: A total of 23 bibliographical references in English and Spanish, most of them obtained from PubMed, SciELO and ScienceDirect databases, were analyzed using descriptors such as "inteligencia artificial", "radiología" and "aprendizaje automático" for the Spanish language and "artificial intelligence", "radiology" and "machine learning" for the English language. Results: There is no area of ​​Radiology in which artificial intelligence has not been implemented in order to improve and develop programs that make it easier for the radiologist and the technician to obtain and diagnose images. Cuba is also immersed in this process; the first steps are being taken towards the development of these technologies. Conclusions: Research, workflow optimization, radiomics, prediction and classification of images are benefits that AI brings us; achieving an increase in the quality of these processes is only possible through the alliance between medical and computer sciences.

Comprobación del control automático de exposición en el tomógrafo Canon Aquilion ONE / Verification of the automatic exposure control on the Canon Aquilion ONE tomograph

Resumen Dado el uso incrementado de la tomografía computarizada en la Caja Costarricense del Seguro Social durante los últimos 10 años, se ha vuelto cada vez más importante obtener imágenes de la calidad diagnóstica requerida con la mínima dosis de radiación posible al paciente. Para lograr esto, en los sistemas de tomografía computarizada se utiliza, rutinariamente, el control automático de exposición, el cual modula la corriente del tubo según la atenuación del haz que produce el paciente y que se obtiene en el escanograma. Objetivo: Comprobar el funcionamiento del control automático de exposición de un tomógrafo Canon Aquilion ONE en la dosis suministrada al paciente y verificar la importancia de realizar un simple o doble escanograma para diferentes protocolos clínicos. Métodos: Se analizó el comportamiento de la dosis, el ruido y la intensidad de la corriente obtenida en un maniquí con diferentes secciones elípticas que varían sus dimensiones en los ejes X-Y. Se determinó el producto dosis longitud en diferentes protocolos clínicos con el control automático de exposición activado debido a un simple o doble escanograma. Resultados: Para intensidades de corrientes fijas, a medida que aumenta el tamaño de cada sección del maniquí, la dosis se reduce, aproximadamente hasta el 72% y, cuando disminuye el tamaño de cada sección, mejora hasta en un 21% la calidad de la imagen debido a la reducción del ruido. Conclusiones: Se pudo observar que, a pesar de que las dosis para localización son bajas, la utilización de un simple escanograma, en la mayoría de los protocolos, no solo permite reducir la dosis suministrada al paciente, sino también efectuar menor cantidad de disparos en el equipo e incrementar la vida útil del tubo de rayos X, pues el aporte de un segundo escanograma no representa un impacto significativo en la calidad de imagen.

Abstract Given the increased use of computed tomography in the Costa Rican Social Security Fund during the last 10 years, it has become increasingly important to obtain images of the required diagnostic quality with the minimum radiation dose to the patient. To achieve this, computed tomography systems routinely use automatic exposure control, modulating the tube current according to the attenuation of the beam produced by the patient and obtained on scanogram. Aim: Check the operation of the automatic exposure control of a Canon Aquilion ONE scanner at the dose delivered to the patient and to verify the importance of performing a single or double scanogram for different clinical protocols. Methods : The behavior of the dose, the noise and the intensity of the current was analyzed in a phantom with different elliptical sections that vary their dimensions in the X-Y axes. The dose-length product was determined in different clinical protocols with the automatic exposure control activated due to a single or a double scanogram. Results: For fixed current intensities, as the size of each section of the phantom increases, the dose is reduced, approximately, up to 72% and when the size of each section decreases, the quality of image improves, due to noise reduction, up to 21%. Conclusions: It was observed that, despite the fact that the doses for localization are low, the use of a simple scanogram in most protocols not only reduces the dose to the patient, but also makes fewer shots in the equipment and increases the useful life of the X-ray tube, since the contribution of a second scanogram does not represent a significant impact on image quality.

Influence of mixing parameters in STAR automatic sample processing instruments on the detection results of internal controls / 中国输血杂志

【Objective】 To explore the significance of blending internal controls by automatic sample processing instruments in the enzyme linked immunosorbent assay (ELISA). 【Methods】 The internal controls were vortexed and mixed before the test, and then were added to the same ELISA plate by the STAR automatic sample processing instruments under the same detection conditions. The difference of S/CO value of internal controls with and without sufficient blending via the sampling needle and their frequency distribution were compared. Internal controls that were greatly affected by mixing parameters were submitted to the same test with different batches of reagents from the same manufacturer, and the results were analyzed for consistency. 【Results】 The S/CO value of anti-HCV internal controls without blending using adding sample needle was significantly lower than that of quality control samples with sufficient blending (P<0.000 1). The S/CO values of unmixed internal controls concerning anti-TP and anti-HIV detection given by some detection systems were also different from the values of mixed internal controls (P<0.05). Some of the S/CO values of the anti-HCV internal controls without mixing were distributed within the interval of less than 2. Different batches of reagents from the same manufacturer were used to detect anti-HCV internal controls, and there were differences in the partial detection values between the mixed and unmixed internal controls (P<0.05). 【Conclusion】 Although the internal controls were mixed by vortex shock before the test, the detection results of some internal controls will still be affected when the STAR automatic sample processing instruments does not set the mixing parameters for internal controls.

Automatic transfer of diversion pouches among Blood Transfusion Departments: a multicenter observation and study / 中国输血杂志

【Objective】 To explore the significance of automatic transfer of diversion pouches in blood transfusion departments on improving the standardization of quality management. 【Methods】 A total of 16 548 diversion pouches of suspended red blood cells (sRBC) were collected from Blood Transfusion Departments of ten tertiary hospitals in China. The sRBC was supplied by local blood centers from January to March 2021. The diversion pouches were randomly divided into experimental group (n=8 274, using DS-6800A automatic for transferring) and control group (n=8 274, manual transfer). The transfer duration of diversion pouches labels, whole process operation time of diversion pouches, label accuracy after transferring, table cleanliness and accurate transfer rate of diversion pouches of the two groups were recorded and compared. 【Results】 The results of experimental group and control group were as follows: transfer duration(s) of diversion pouch labels was 0.67±0.3 vs 3.67±0.6(P<0.05); whole process operation time was 16.93±0.5 vs 19.85±1 (P<0.05); label accuracy after transferring was 100% (8 274/8 274) vs 97.91% (8 101/8 274); table cleanliness was 99.19% (8 207/8 274) vs 94.39% (7 810/8 274); transfer accuracy was 100%(8 274/8 274) vs 95.85% (7 931/8 274). 【Conclusion】 Automatic transfer of diversion pouches of blood samples can improve the efficiency and quality of the sample transfer, and is conductive to the standardization of internal quality evaluation and control of blood transfusion departments.

The applicability of Beckman PK7300 fully automatic blood group instrument for TPPA detection / 中国输血杂志

【Objective】 To investigate the applicability of Beckman PK7300 for TPPA testing on anti-TP reactive specimens from blood donors. 【Methods】 1) The TPPA test using Beckman PK7300 (abbreviated as instrument method) had been established and the performance was verificated by calculating the total compliance rate, positive compliance rate and negative compliance rate as compared with the manual method. The repeatability of this instrument method was also evaluated. 2) The applicability of the instrument method was evaluated by examing 555 TP-reactive samples for 6 consecutive days, so as to analyze the readable reading rate, agglutination strength distribution and other control methods. 【Results】 1) The total, positive, and negative compliance rates of TPPA detection by both instrumental and manual methods were 100% (kappa value =1). The SPC value of samples, read manually as " + + ", was less than or equal to 3 by Beckman PK7300; the SPC value of samples, read manually as " -", was greater than or equal to 20 by Beckman PK7300. The two methods were well consistent. The instrument method was repeated for 12 times for the same samples, and the accuracy rate was 100% (12 / 12), with good repeatability.2) The results of the TPPA test in 555 anti-TP reactivity specimens showed an overall readable rate of 99.82%(554/555). The SPC values of the negative and unsensitized particles of TPPA were distributed on both sides of the determination value without crossover. The control and monitor thoughout the test were carried out automatically by the instrument. 【Conclusion】 The TPPA test conducted by the Beckman PK7300 fully automatic blood group instrument is suitable for the confirmatory experiment of anti-TP reactive specimens in blood center laboratories, which could realize the automation and standardization of TPPA detection.

Application of U-Net network in automatic image segmentation of adenoid and airway of nasopharynx / 临床耳鼻咽喉头颈外科杂志

Objective:To explore the effect of fully automatic image segmentation of adenoid and nasopharyngeal airway by deep learning model based on U-Net network. Methods:From March 2021 to March 2022, 240 children underwent cone beam computed tomography（CBCT） in the Department of Otolaryngology, Head and Neck Surgery, General Hospital of Shenzhen University. 52 of them were selected for manual labeling of nasopharynx airway and adenoid, and then were trained and verified by the deep learning model. After applying the model to the remaining data, compare the differences between conventional two-dimensional indicators and deep learning three-dimensional indicators in 240 datasets. Results:For the 52 cases of modeling and training data sets, there was no significant difference between the prediction results of deep learning and the manual labeling results of doctors（P>0.05）. The model evaluation index of nasopharyngeal airway volume: Mean Intersection over Union（MIOU） s （86.32±0.54）%; Dice Similarity Coefficient（DSC）: （92.91±0.23）%; Accuracy: （95.92±0.25）%; Precision: （91.93±0.14）%; and the model evaluation index of Adenoid volume: MIOU: （86.28±0.61）%; DSC: （92.88±0.17）%; Accuracy: （95.90±0.29）%; Precision: （92.30±0.23）%. There was a positive correlation between the two-dimensional index A/N and the three-dimensional index AV/（AV+NAV） in 240 children of different age groups（P<0.05）, and the correlation coefficient of 9-13 years old was 0.74. Conclusion:The deep learning model based on U-Net network has a good effect on the automatic image segmentation of adenoid and nasopharynx airway, and has high application value. The model has a certain generalization ability.

Application of micro-bolus injection and piezoelectric sensors to improve the safety of radiopharmaceuticals bolus injection / 生物医学工程学杂志

Radiopharmaceutical dynamic imaging typically necessitates intravenous injection via the bolus method. However, manual bolus injection carries the risk of handling errors as well as radiological injuries. Hence, there is potential for automated injection devices to replace manual injection methods. In this study, the effect of micro-bolus pulse injection technology was compared and verified by radioactive experiments using a programmable injection pump, and the overall bubble recognition experiment and rat tail vein simulation injection verification were performed using the piezoelectric sensor preloading method. The results showed that at the same injection peak speed, the effective flushing volume of micro-bolus pulse flushing (about 83 μL/pulse) was 49.65% lower than that of uniform injection and 25.77% lower than that of manual flushing. In order to avoid the dilution effect of long pipe on the volume of liquid, the use of piezoelectric sensor for sealing preloading detection could accurately predict the bubbles of more than 100 μL in the syringe. In the simulated injection experiment of rat tail vein, when the needle was placed in different tissues by preloading 100 μL normal saline, the piezoelectric sensor fed back a large difference in pressure attenuation rate within one second, which was 2.78% in muscle, 17.28% in subcutaneous and 54.71% in vein. Micro-bolus pulse injection method and piezoelectric sensor sealing preloading method have application potential in improving the safety of radiopharmaceutical automatic bolus injection.

Design and development of a multifunctional moxibustion treatment machine based on heat-sensitive moxibustion therapy / 中国针灸

A multifunctional moxibustion treatment machine is designed and developed to assist the heat-sensitive moxibustion therapy. Through the motion control of the stepping motor by programmable logic controller (PLC), the automatic control is obtained for the acupoint detection of heat-sensitive moxibustion therapy and the manual operation of moxibustion. The skin temperature is monitored in real-time, using infrared non-contact temperature measurement technology. Based on the deviation of the temperature set value and the monitoring one, the distance between the moxibustion device and the exerted region is adjusted automatically by PLC so that the temperature is controlled practically. The multifunctional moxibustion treatment machine based on the heat-sensitive moxibustion therapy is capable of the operation control of mild moxibustion, circling moxibustion, sparrow-pecking moxibustion and along-meridian moxibustion techniques, as well as real-time monitoring of skin temperature. The temperature change curve of this machine is coincident with that obtained by the manual operation of heat-sensitive moxibustion. This multifunctional moxibustion treatment machine assists the delivery of heat-sensitive moxibustion therapy and it is satisfactory in temperature control and precise in operation.

The Objective Assessment of Event-Related Potentials: An Influence of Chronic Pain on ERP Parameters / 神经科学通报·英文版

The article presents an original method for the automatic assessment of the quality of event-related potentials (ERPs), based on the calculation of the coefficient ε, which describes the compliance of recorded ERPs with some statistically significant parameters. This method was used to analyze the neuropsychological EEG monitoring of patients suffering from migraines. The frequency of migraine attacks was correlated with the spatial distribution of the coefficients ε, calculated for EEG channels. More than 15 migraine attacks per month was accompanied by an increase in calculated values in the occipital region. Patients with infrequent migraines exhibited maximum quality in the frontal areas. The automatic analysis of spatial maps of the coefficient ε demonstrated a statistically significant difference between the two analyzed groups with different means of migraine attack numbers per month.

Automatic sleep staging model based on single channel electroencephalogram signal / 生物医学工程学杂志

Sleep staging is the basis for solving sleep problems. There's an upper limit for the classification accuracy of sleep staging models based on single-channel electroencephalogram (EEG) data and features. To address this problem, this paper proposed an automatic sleep staging model that mixes deep convolutional neural network (DCNN) and bi-directional long short-term memory network (BiLSTM). The model used DCNN to automatically learn the time-frequency domain features of EEG signals, and used BiLSTM to extract the temporal features between the data, fully exploiting the feature information contained in the data to improve the accuracy of automatic sleep staging. At the same time, noise reduction techniques and adaptive synthetic sampling were used to reduce the impact of signal noise and unbalanced data sets on model performance. In this paper, experiments were conducted using the Sleep-European Data Format Database Expanded and the Shanghai Mental Health Center Sleep Database, and achieved an overall accuracy rate of 86.9% and 88.9% respectively. When compared with the basic network model, all the experimental results outperformed the basic network, further demonstrating the validity of this paper's model, which can provide a reference for the construction of a home sleep monitoring system based on single-channel EEG signals.

Application of automatic injection device based on automatic hemostasis in injection of radiopharmaceutical bolus injection / 生物医学工程学杂志

In clinical practice, radiopharmaceutical dynamic imaging technology requires the bolus injection method to complete injection. Due to the failure rate and radiation damage of manual injection, even experienced technicians still bear a lot of psychological burden. This study combined the advantages and disadvantages of various manual injection modes to develop the radiopharmaceutical bolus injector, and explored the application of automatic injection in the field of bolus injection from four aspects: radiation protection, occlusion response, sterility of injection process and effect of bolus injection. Compared with the current mainstream manual injection method, the bolus manufactured by the radiopharmaceutical bolus injector based on the automatic hemostasis method had a narrower full width at half maximum and better repeatability. At the same time, radiopharmaceutical bolus injector had reduced the radiation dose of the technician's palm by 98.8%, and ensured more efficient vein occlusion recognition performance and sterility of the entire injection process. The radiopharmaceutical bolus injector based on automatic hemostasis has application potential in improving the effect and repeatability of bolus injection.

Automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning / 生物医学工程学杂志

The existing automatic sleep staging algorithms have the problems of too many model parameters and long training time, which in turn results in poor sleep staging efficiency. Using a single channel electroencephalogram (EEG) signal, this paper proposed an automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning (TL-SDResNet). Firstly, a total of 30 single-channel (Fpz-Cz) EEG signals from 16 individuals were selected, and after preserving the effective sleep segments, the raw EEG signals were pre-processed using Butterworth filter and continuous wavelet transform to obtain two-dimensional images containing its time-frequency joint features as the input data for the staging model. Then, a ResNet50 pre-trained model trained on a publicly available dataset, the sleep database extension stored in European data format (Sleep-EDFx) was constructed, using a stochastic depth strategy and modifying the output layer to optimize the model structure. Finally, transfer learning was applied to the human sleep process throughout the night. The algorithm in this paper achieved a model staging accuracy of 87.95% after conducting several experiments. Experiments show that TL-SDResNet50 can accomplish fast training of a small amount of EEG data, and the overall effect is better than other staging algorithms and classical algorithms in recent years, which has certain practical value.

Prevalence and Predictors of Anxiety and Depressive Symptoms among Adult Patients with Atopic Dermatitis in Malaysia Tertiary Referral Hospital

@#Introduction: Atopic dermatitis (AD) is not only a cosmetic nuisance but is also associated with a significant impact on mental health and quality of life. Psychological symptoms are highly related to poor treatment adherence and recovery, more comorbidities, and a significant overall socioeconomic burden. Identifying the factors associated with anxiety and depression among patients with AD is important to modify and reduce the risk of developing these psychiatric complications. Methods: This was correlational research conducted in the dermatology clinic of four hospitals in Klang Valley, namely Hospital Kuala Lumpur, Hospital Tengku Ampuan Rahimah Klang, Hospital Selayang, and Hospital Ampang. By using a purposive sampling method, 128 samples (n=128) of adult patients with AD aged 18-65 were included. A questionnaire was administered regarding sociodemographic background, illness characteristics of AD, the Investigator’s Global Assessment (IGA), Malay version of the Automatic Thought Questionnaire-17, GAD-7, and PHQ-9. Results: The prevalence of anxiety and depressive symptoms among adult patients with AD is 31.3% and 46.9% respectively. Multivariable logistic regression analysis revealed that age and personal maladjustment (PM) predict anxiety symptoms, while only negative self-concept/expectation (NSNE) predicts depressive symptoms. The hierarchical logistic regression model explained 51% (Nagelkerke’s R2) of the variance in anxiety symptoms and 56% (Nagelkerke’s R2) of depressive symptoms. Conclusion: There is a high proportion of anxiety and depressive symptoms among adult patients with AD which is associated with negative automatic thoughts. In the management of adult patients with AD, clinicians should consider mental health symptom screening and monitoring.

Research on multi-Atlas segmentation based on feature clustering / 中华放射肿瘤学杂志

Objective:To study the improvement of normal tissue region of interest (ROI) segmentation based on clustering-based multi-Atlas segmentation method, thereby achieving better delineation of organs at risk.Methods:CT images of 100 patients with cervical cancer who had completed treatment in Zhejiang Cancer Hospital during 2019-2020 were selected as the Atlas database. According to the volume characteristic parameters of the organs at risk (bladder, rectum and outer contour), the Atlas database was divided into several subsets by k-means clustering algorithm. The image to be segmented was matched to the corresponding Atlas library for multi-Atlas segmentation. The dice similarity coefficient (DSC) was used to evaluate the segmentation results.Results:Using 30 patients as the test set, the sub-Atlas generated by different clustering methods were compared for the improvement of image segmentation results. Compared with general multi-Atlas segmentation methods, clustering-based multi-Atlas segmentation method significantly improve the segmentation accuracy for the bladder (DSC=0.83±0.09 vs. 0.69±0.15, P<0.001) and the rectum (0.7±0.07 vs. 0.56±0.16, P<0.001), but no statistical significance was observed for left and right femoral head (0.92±0.04, 0.91±0.02) and bone marrow (0.91±0.06). The average segmentation time of clustering-based multi-Atlas segmentation method was shorter than that of the general multi-Atlas segmentation method (2.7 min vs. 6.3 min). Conclusion:The clustering-based multi-Atlas segmentation method can not only reduce the number of Atlas images registered with the image to be segmented, but also can be expected to improve the segmentation effect and obtain higher accuracy.

Automatic-delineation model construction for prostate cancer target volume of postoperative radiotherapy based on artificial intelligence / 中华放射肿瘤学杂志

Objective:To explore the method of constructing automatic delineation model for clinical target volume (CTV) and partially organs at risk (OAR) of postoperative radiotherapy for prostate cancer based on convolutional neural network, aiming to improve the clinical work efficiency and the unity of target area delineation.Methods:Postoperative CT data of 117 prostate cancer patients manually delineated by one experienced clinician were retrospectively analyzed. A multi-class auto-delineation model was designed based on 3D UNet. Dice similarity coefficient (DSC), 95% Hausdorf distance (95%HD), and average surface distance (ASD) were used to evaluate the segmentation ability of the model. In addition, the segmentation results in the test set were evaluated by two senior physicians. And the CT data of 78 patients treated by other physicians were also collected for external validation of the model. The automatic segmentation of these 78 patients by CTV-UNet model was also evaluated by two physicians.Results:The mean DSC for tumor bed area (CTV1), pelvic lymph node drainage area (CTV2), bladder and rectum of CVT-UNet auto-segmentation model in the test set were 0.74, 0.82, 0.94 and 0.79, respectively. Both physicians' scoring results of the test set and the external validation showed more consensus on the delineation of CTV2 and OAR. However, the consensus of CTV1 delineation was less.Conclusions:The automatic delineation model based on convolutional neural network is feasible for CTV and related OAR of postoperative radiotherapy for prostate cancer. The automatic segmentation ability of tumor bed area still needs to be improved.

A comparative study of automatic delineation of organs at risk for prostate cancer based on deep learning and atlas library / 中华放射医学与防护杂志

Objective:To compare the effect of uPWS R15 software based on deep learning with MIM-Maestro 6.9 software based on atlas library to automatically delineate the organs at risk of prostate cancer in order to provide a reference for clinical application.Methods:The CT data of 90 prostate cancer patients admitted to the Department of Oncology Radiotherapy of the Affiliated Hospital of North Sichuan Medical College from 2018 to 2022 were retrospectively selected. Based on the uPWS R15 software developed by Shanghai United Imaging Medical Technology Company and the MIM-Maestro 6.9 software developed by Beijing Mingwei Vision Medical Software Company, the effects of uPWS and MIM software on automatic delineation of organs at risk were evaluated according to five parameters, including delineation time (T), Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), Hausdorff distance (HD) and the mean distance to agreement (MDA).Results:The sketching time of uPWS software was less than that of MIM software. There were no significant differences in the sketching effect of femoral head and skin between the two software (all P>0.05). The delineation of right kidney ( tMDA=-3.43, zDSC=-4.03, zJSC=-4.16, P<0.05), left kidney ( tMDA=-3.87, zDSC=-4.18, zJSC=-4.41, P<0.05), small intestine ( tMDA=-8.57, zDSC=-9.99, tJSC=14.21, P<0.05) and rectum ( zMDA=-4.00, tDSC=-9.98, tJSC= 9.72, P< 0.05) except HD, was statistically different. The bladder ( z=-7.88, -9.00, -8.17, -8.74, P<0.05) and spinalcord ( z=-3.87, -4.43, 4.03, 3.05, P<0.05) were also delineated with significant differences. The DSC automatically delineated by uPWS software was >0.7, while the DSC automatically delineated by MIM software was >0.7 for all other organs at risk except small intestine and rectum. In addition, the HD, MDA and JSC values of the organs at risk (bilateral femoral head, bilateral kidneys, spinal cord, bladder, skin, rectum and small intestine) automatically delineated by uPWS software were generally better than those with MIM software. Conclusions:The uPWS software outlines better than the MIM software, but the MIM software can also be used clinically with modifications to the small bowel and rectum, saving a great deal of time in preparation for radiation therapy.

A metaheuristics-based automatic planning method for intensity-modulated radiation therapy / 中华放射医学与防护杂志

Objective:To establish a metaheuristics-based automatic radiotherapy treatment planning method (ATP-STAR) and verify its effectiveness.Methods:The main process of the ATP-STAR method was as follows. First, the optimization parameters were vectorized for encoding and corrected using Gaussian convolution. Then, the candidate optimization parameter vector set was selected through simulated annealing. Finally, the optimal combination of optimization parameters was determined by combining the field fluence optimization to achieve automatic trial-and-error. Twenty cases with large individual differences in tumors were selected for testing. Clinical physicists with more than five years of experience were invited to perform manual planning. Both the manual and ATP-STAR plans were made utilizing the matRad open source software for radiation treatment planning, with the fields and prescribed doses consistent with those of the clinical treatment plans. The dosimetric differences of target volumes and organs at risk between the ATP-STAR and manual plans for different diseases were analyzed.Results:For the target volumes, the ATP-STAR plans showed superior homogeneity compared with the manual plans (brain tumors: z = 2.28, P = 0.022; lung cancers: z = 2.29, P = 0.022; liver cancers: z = 2.11, P = 0.035). The conformability of the ATP-STAR plans was comparable to that of the manual plans for brain tumors and liver cancer and was slightly lower than that of the manual plans for lung cancer ( z = 2.29, P = 0.022). The comparison result of doses to organs at risk (OARs) between the manual plans and STAR plans were as follows. For OARs of brain tumors, the ATP-STAR plans decreased the mean left lens Dmean from 2.19 Gy to 1.76 Gy ( z = 2.28, P = 0.022), decreased left optic nerve Dmean from 11.36 Gy to 10.22 Gy ( z = 2.28, P = 0.022), decreased right optic nerve Dmax from 32.92 Gy to 29.97 Gy ( z = 2.10, P = 0.036), and decreased pituitary Dmax from 39.53 Gy to 35.21 Gy ( z = 2.29, P = 0.022). For OARs of lung cancer, the ATP-STAR plans decreased the mean spinal cord Dmax from 38.00 Gy to 31.17 Gy ( z = 2.12, P = 0.034), decreased the bilateral lungs Dmean from 8.51 Gy to 8.07 Gy ( z = 2.29, P = 0.022), and decreased cardiac Dmean from 3.21 Gy to 2.69 Gy ( z =2.29, P = 0.022). For OARs of liver cancer, the ATP-STAR plans decreased spinal cord Dmax from 18.19 Gy to 14.76 Gy ( z = 2.11, P = 0.035), decreased liver Dmean from 15.61 Gy to 14.45 Gy ( z = 2.11, P = 0.035), and decreased kidneys Dmean from 4.76 Gy to 4.04 Gy ( z = 2.10, P = 0.036). Conclusions:The proposed ATP-STAR method relies little on the experience of manual planning and thus is easy to be widely applied. This method is expected to improve the quality and consistency of IMRT plans and save clinical labor and time costs.

A modal study of the effect of adjusting density exposure steps on image quality and radiation dose in digital mammography / 中华放射学杂志

Objective:To investigate the effect of adjusting density exposure steps on image quality and radiation dose in digital mammography.Methods:Using the automatic exposure control (AEC) mode of the digital mammography machine, five different gland thicknesses of 4.3, 5.3, 6.3, 7.3, and 8.3 cm were simulated by attaching 0, 1, 2, 3, and 4 PMMA plexiglass plates under the RMI-156 modal body, and the density exposure steps were adjusted to -3, -2, -1, 0, 1, 2, 3, and 4 for each thickness. The target/filter combination, tube voltage, tube current, incident body surface dose (ESD), incident surface air kerma (ESAK), half-value layer (HVL) and the average glandular dose displayed by the device (displayed AGD) were recorded at each step and thickness, and the signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), figure of merit (FOM) and the calculated average glandular dose (calculated AGD) were calculated. Then, the display effects of simulated fibers, simulated calcifications and simulated masses within the modal body were scored subjectively, and the changes in image quality and radiation dose at different steps were analyzed, and the relationships between ESD and ESAK, displayed AGD and calculated AGD, and displayed AGD/ESD and calculated AGD/ESAK were analyzed. A linear fit was used for the steps with SNR, CNR, and FOM, and an exponential function curve fit was used for the steps with mAs, ESAK, and calculated AGD. The differences between ESD and ESAK, displayed AGD and calculated AGD, and displayed AGD/ESD and calculated AGD/ESAK were analyzed by paired-samples t test. Results:The CNR and SNR of mammographic images rose and fell by about 8% with each increase or decrease of one step. The scores of image simulated fibers, simulated calcifications, and simulated masses showed an overall upward trend with increasing steps, but there were still cases where the scores decreased with increasing grades. FOM varied from 97% to 104% at each grade with little variability. ESD, ESAK, displayed AGD, and calculated AGD, which could measure radiation dose, showed an exponential trend of increasing function with increasing steps, with a variation of about 63% to 165%. There were statistically significant differences ( t=-9.61, P=0.001) between ESD (15.14±10.08) and ESAK (16.66±11.07). However, there were no statistically significant differences ( t=1.20, P=0.240) between displayed AGD and calculated AGD, which were 3.66±2.18 and 3.61±1.99, respectively. Conclusions:The adjustment of density exposure steps can make the image quality change linearly and the radiation dose change exponentially with increasing speed, and the mode and magnitude of the adjustment are appropriately stable with high application value.