Applications of Artificial Intelligence, Machine Learning, and Deep Learning in Nutrition: A Systematic Review.

In industry 4.0, where the automation and digitalization of entities and processes are fundamental, artificial intelligence (AI) is increasingly becoming a pivotal tool offering innovative solutions in various domains. In this context, nutrition, a critical aspect of public health, is no exception to the fields influenced by the integration of AI technology. This study aims to comprehensively investigate the current landscape of AI in nutrition, providing a deep understanding of the potential of AI, machine learning (ML), and deep learning (DL) in nutrition sciences and highlighting eventual challenges and futuristic directions. A hybrid approach from the systematic literature review (SLR) guidelines and the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines was adopted to systematically analyze the scientific literature from a search of major databases on artificial intelligence in nutrition sciences. A rigorous study selection was conducted using the most appropriate eligibility criteria, followed by a methodological quality assessment ensuring the robustness of the included studies. This review identifies several AI applications in nutrition, spanning smart and personalized nutrition, dietary assessment, food recognition and tracking, predictive modeling for disease prevention, and disease diagnosis and monitoring. The selected studies demonstrated the versatility of machine learning and deep learning techniques in handling complex relationships within nutritional datasets. This study provides a comprehensive overview of the current state of AI applications in nutrition sciences and identifies challenges and opportunities. With the rapid advancement in AI, its integration into nutrition holds significant promise to enhance individual nutritional outcomes and optimize dietary recommendations. Researchers, policymakers, and healthcare professionals can utilize this research to design future projects and support evidence-based decision-making in AI for nutrition and dietary guidance.

Predicting survival in locally advanced rectal cancer with effective chemoradiotherapy response.

BACKGROUND: Locally advanced rectal cancer patients often display favorable responses and favorable oncologic outcomes. Due to the low recurrence rate, there is scarcity of studies investigating the prognostic factors influencing their survival. Therefore, our study sought to assess the prognostic factors associated with survival in rectal cancer patients who achieved either a pathologic complete response or a pathologic stage I after neoadjuvant chemoradiotherapy combined with radical resection. METHODS: In this retrospective study, we analyzed data from cohort of 1394 patients diagnosed with locally advanced rectal cancer who underwent neoadjuvant chemoradiotherapy combined with total mesorectal excision from January 2008 to April 2017. Finally, we selected 474 (34.2 %) who exhibited either a pathologic complete response or attained pathologic stage I following the treatment. Subsequently, we analyzed the prognostic factors influencing disease-free and overall survival. RESULTS: A total of 161 (34 %) achieved a pathologic complete response. Our analysis revealed that circumferential resection margin and the administration of adjuvant chemotherapy were prognostic factors for disease-free survival (p = 0.011, p = 0.022). Furthermore, factors influencing overall survival included the clinical N stage and administration of adjuvant chemotherapy (p = 0.035, p = 0.015). CONCLUSION: In conclusion, the circumferential resection margin, clinical N stage, and administration of adjuvant chemotherapy were prognostic factors for survival in patients showing good response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. For patients with a positive circumferential resection margin and clinical N (+) stage, intensive follow-up might be needed to achieve favorable oncologic outcomes. Also, we recommend considering adjuvant chemotherapy as a beneficial treatment approach for these patients.

Digital Anti-Aging Healthcare: An Overview of the Applications of Digital Technologies in Diet Management.

Diet management has long been an important practice in healthcare, enabling individuals to get an insight into their nutrient intake, prevent diseases, and stay healthy. Traditional methods based on self-reporting, food diaries, and periodic assessments have been used for a long time to control dietary habits. These methods have shown limitations in accuracy, compliance, and real-time analysis. The rapid advancement of digital technologies has revolutionized healthcare, including the diet control landscape, allowing for innovative solutions to control dietary patterns and generate accurate and personalized recommendations. This study examines the potential of digital technologies in diet management and their effectiveness in anti-aging healthcare. After underlining the importance of nutrition in the aging process, we explored the applications of mobile apps, web-based platforms, wearables devices, sensors, the Internet of Things, artificial intelligence, blockchain, and other technologies in managing dietary patterns and improving health outcomes. The research further examines the effects of digital dietary control on anti-aging healthcare, including improved nutritional monitoring, personalized recommendations, and behavioral and sustainable changes in habits, leading to an expansion of longevity and health span. The challenges and limitations of digital diet monitoring are discussed, and some future directions are provided. Although many digital tools are used in diet control, their accuracy, effectiveness, and impact on health outcomes are not discussed much. This review consolidates the existing literature on digital diet management using emerging digital technologies to analyze their practical implications, guiding researchers, healthcare professionals, and policy makers toward personalized dietary management and healthy aging.

Is Robotic Surgery Beneficial for Rectal Cancer Patients with Unfavorable Characteristic After Neoadjuvant Chemoradiotherapy?

BACKGROUND: The objective of this study was to compare long-term oncologic outcomes of robot and laparoscopic surgeries for patients with advanced rectal cancer who underwent neoadjuvant chemoradiotherapy (nCRT) followed by radical resection. METHODS: This study analyzed 3240 rectal cancer patients who underwent radical surgery from 2008 to 2019. Among them, 1204 patients who received nCRT (robotic, n = 316; laparoscopic, n = 888) were analyzed. The oncological outcome according to the number of unfavorable factors (male, body mass index ≥ 25, receiving CCRT) present in patients also was analyzed. We used 1:1 propensity score matching (PSM) to adjust for potential baseline confounders between groups. RESULTS: After PSM, two groups showed similar demographics and pathological results. After PSM analysis, the robotic group showed higher 5-year disease-free survival (DFS) and local recurrence-free survival rates than the laparoscopic group, whereas 5-year overall survival and distant recurrence-free survival rates were similar between the two groups. In addition, by comparing survival rates for each yp stage, it was found 5-year DFS and local recurrence-free survival of the robotic group in yp stage III were significantly higher than those of the laparoscopic group. Five-year DFS was conducted according to the number of unfavorable factors (male, body mass index ≥ 25 kg/m2, and undergoing nCRT) as a subgroup analysis. In patients with all three unfavorable factors, the robotic group showed significantly higher DFS than the laparoscopic group. CONCLUSIONS: Robotic approach for rectal cancer after nCRT, especially for patients with yp stage III and unfavorable factors, have the advantage of improving oncologic outcomes even for surgeons specializing in colorectal cancer.

Impact of COVID-19 on the development of major mental disorders in patients visiting a university hospital: a retrospective observational study.

BACKGROUND: This study aimed to investigate the impact of coronavirus disease 2019 (COVID-19) on the development of major mental disorders in patients visiting a university hospital. METHODS: The study participants were patients with COVID-19 (n=5,006) and those without COVID-19 (n=367,162) registered in the database of Keimyung University Dongsan Hospital and standardized with the Observational Medical Outcomes Partnership Common Data Model. Data on major mental disorders that developed in both groups over the 5-year follow-up period were extracted using the FeederNet computer program. A multivariate Cox proportional hazards model was used to estimate the hazard ratio (HR) and 95% confidence interval (CI) for the incidence of major mental disorders. RESULTS: The incidences of dementia and sleep, anxiety, and depressive disorders were significantly higher in the COVID-19 group than in the control group. The incidence rates per 1,000 patient-years in the COVID-19 group vs. the control group were 12.71 vs. 3.76 for dementia, 17.42 vs. 7.91 for sleep disorders, 6.15 vs. 3.41 for anxiety disorders, and 8.30 vs. 5.78 for depressive disorders. There was no significant difference in the incidence of schizophrenia or bipolar disorder between the two groups. COVID-19 infection increased the risk of mental disorders in the following order: dementia (HR, 3.49; 95% CI, 2.45-4.98), sleep disorders (HR, 2.27; 95% CI, 1.76-2.91), anxiety disorders (HR, 1.90; 95% CI, 1.25-2.84), and depressive disorders (HR, 1.54; 95% CI, 1.09-2.15). CONCLUSION: This study showed that the major mental disorders associated with COVID-19 were dementia and sleep, anxiety, and depressive disorders.

Effectiveness and Tolerability of Combination Pharmacotherapy With Stimulant and Non-Stimulant in Children With Attention Deficit Hyperactivity Disorder.

Objectives: This study aimed to investigate the effectiveness and safety of combining psychostimulants and nonstimulants for patients under treatment for attention deficit hyperactivity disorder (ADHD). Methods: The study included 96 patients aged 6-12 years who were diagnosed with ADHD, among whom 34 received combination pharmacotherapy, 32 received methylphenidate monotherapy, and 30 received atomoxetine monotherapy. Statistical analysis was conducted to compare treatment and adverse effects among groups and to analyze changes before and after combination pharmacotherapy. The difference between combination pharmacotherapy and monotherapy was investigated. Logistic regression analysis was used to identify the predictors of combination pharmacotherapy. Results: No significant differences were observed between the groups in terms of age or pretreatment scores. The most common adverse effect experienced by 32% of patients in the combination pharmacotherapy group was decreased appetite. Clinical global impression- severity score decreased significantly after combination pharmacotherapy. All three groups showed significant clinical global impression- severity score improvements over time, with no significant differences among them. The predictive factors for combination pharmacotherapy included the Child Behavior Checklist total score internalizing subscale. Conclusion: Combination pharmacotherapy with methylphenidate and atomoxetine is a relatively effective and safe option for patients with ADHD who do not respond to monotherapy.

Comprehensive profiling of DNA methylation in Korean patients with colorectal cancer.

Alterations in DNA methylation play an important pathophysiological role in the development and progression of colorectal cancer. We comprehensively profiled DNA methylation alterations in 165 Korean patients with colorectal cancer (CRC), and conducted an in-depth investigation of cancer-specific methylation patterns. Our analysis of the tumor samples revealed a significant presence of hypomethylated probes, primarily within the gene body regions; few hypermethylated sites were observed, which were mostly enriched in promoter-like and CpG island regions. The CpG Island Methylator PhenotypeHigh (CIMP-H) exhibited notable enrichment of microsatellite instability-high (MSI-H). Additionally, our findings indicated a significant correlation between methylation of the MLH1 gene and MSI-H status. Furthermore, we found that the CIMP-H had a higher tendency to affect the right-side of the colon tissues and was slightly more prevalent among older patients. Through our methylome profile analysis, we successfully verified the thylation patterns and clinical characteristics of Korean patients with CRC. This valuable dataset lays a strong foundation for exploring novel molecular insights and potential therapeutic targets for the treatment of CRC. [BMB Reports 2024; 57(2): 110-115].

Pulmonary Metastasis as the First Site of Metastasis After Curative Surgery for Colon Cancer: Incidence and Risk Factors According to the TNM Stage.

BACKGROUND: The lungs are one of the most common sites for colon cancer metastasis. A few studies reported that approximately 2% to 10% of patients with colon cancer developed pulmonary metastasis. However, among these studies, patient characteristics were heterogeneous, and information on pulmonary metastasis incidence by the TNM stage was scarce. OBJECTIVE: This study evaluated the incidence of pulmonary metastasis in colon cancer without synchronous metastasis treated with radical surgery and identified risk factors for pulmonary metastasis according to the TNM stage. DESIGN AND SETTINGS: This retrospective study included all patients with colon cancer without metastasis who underwent radical surgery for primary tumor at Samsung Medical Center between January 2007 and December 2016. PATIENTS: A total of 4889 patients who underwent radical surgery for stage I and III colon cancer were included. MAIN OUTCOME MEASURES: The main outcome measures were the incidence of pulmonary metastasis and overall survival. RESULTS: A total of 156 patients (3.2%) were diagnosed with pulmonary metastasis after a median of 16 months from the time of radical surgery for colon cancer to detection of pulmonary metastasis. The pulmonary metastasis incidence rate by the TNM stage was 0.5% in stage I, 1.6% in stage II, and 6% in stage III. Risk factors for pulmonary metastasis were preoperative CEA >5 ng/mL, cancer obstruction, N stage, vascular invasion, perineural invasion, and adjuvant chemotherapy for primary colon cancer in multivariable analysis. LIMITATION: This was a retrospective single-center study. CONCLUSIONS: Preoperative CEA >5 ng/mL, cancer obstruction, pN stage, vascular invasion, perineural invasion, and receiving adjuvant chemotherapy for primary colon cancer were risk factors for pulmonary metastasis in colon cancer. Therefore, patients with risk factors for pulmonary metastasis should be recommended for intensive follow-up to detect lung metastases. See Video Abstract . METSTASIS PULMONAR EN EL PRIMER SITIO TRAS CIRUGA CURATIVA DEL CNCER DE COLON INCIDENCIA Y FACTORES DE RIESGO SEGN ESTADIO TNM: ANTECEDENTES:Los pulmones son uno de los sitios más comunes de metástasis del cáncer de colon. Algunos estudios informaron que aproximadamente entre el 2% y el 10% de los pacientes con cáncer de colon desarrollaron metástasis pulmonar. Sin embargo, entre estos estudios, las características de los pacientes fueron heterogéneas y la información sobre la incidencia de metástasis pulmonares según el estadio TNM fue escasa.OBJETIVO:Este estudio evaluó la incidencia de metástasis pulmonar en cáncer de colon sin metástasis sincrónica tratada con cirugía radical e identificó factores de riesgo para metástasis pulmonar según el estadio TNM.DISEÑO Y AJUSTES:Este estudio retrospectivo incluyó a todos los pacientes con cáncer de colon sin metástasis que se sometieron a cirugía radical por tumor primario en el Samsung Medical Center entre enero de 2007 y diciembre de 2016.PACIENTES:Se incluyó un total de 4.889 pacientes sometidos a cirugía radical por cáncer de colon en estadio I-III.PRINCIPALES MEDIDAS DE RESULTADO:Las principales medidas de resultado fueron la incidencia de metástasis pulmonar y la supervivencia general.RESULTADOS:Un total de 156 pacientes (3,2%) fueron diagnosticados con metástasis pulmonar con una duración media de 16 meses desde el momento de la cirugía radical por cáncer de colon hasta la detección de la metástasis pulmonar. La tasa de incidencia de metástasis pulmonares por estadio TNM fue del 0,5% en el estadio I, del 1,6% en el estadio II y del 6% en el estadio III. Los factores de riesgo de metástasis pulmonar fueron CEA preoperatorio superior a 5 ng/ml, obstrucción por cáncer, estadio N, invasión vascular, invasión perineural y quimioterapia adyuvante para el cáncer de colon primario en un análisis multivariable.LIMITACIÓN:Este fue un estudio retrospectivo de un solo centro.CONCLUSIÓN:CEA preoperatorio superior a 5 ng/ml, obstrucción por cáncer, estadio pN, invasión vascular, invasión perineural y recibir quimioterapia adyuvante para el cáncer de colon primario fueron factores de riesgo de metástasis pulmonar en el cáncer de colon. Por lo tanto, se debe recomendar un seguimiento intensivo a los pacientes con factores de riesgo de metástasis pulmonares para detectar metástasis pulmonares. (Traducción-Dr Yolanda Colorado ).

Risk of Neurodegenerative Diseases in Elderly Koreans with an Initial Diagnosis of Type 2 Diabetes: A Nationwide Retrospective Cohort Study.

Type 2 diabetes (T2D) and neurodegenerative diseases (NDs) are common among elderly individuals. Growing evidence has indicated a strong link between T2D and NDs, such as Alzheimer's disease. However, previous studies have limitations in exploring the epidemiological relationship among these diseases as a group of NDs rather than as a specific type of ND. We aimed to investigate the risk of NDs in elderly Koreans who were first diagnosed with T2D and determine the association between T2D and NDs. We conducted a retrospective longitudinal cohort study of patients with who were initially diagnosed with T2D using the Korean National Health Information Database. The study participants were categorized into a T2D group (n = 155,459) and a control group (n = 155,459), aged 60-84 years, that were matched for age, sex, and comorbidities. We followed the participants for 10 years to investigate the incidence of NDs. The Cox proportional hazards regression model was used to estimate the hazard ratios (HRs) and 95% confidence intervals (CIs) for NDs. The numbers of patients diagnosed with ND at the end of follow-up were as follows: 51,096/155,459 (32.9%) in the T2D group and 44,673/155,459 (28.7%) in the control group (χ2 = 622.53, p < 0.001). The incidences of NDs in the T2D and control groups were 44.68 (95% CI: 44.29, 45.07) and 36.89 (95% CI: 36.55, 37.24) cases per 1,000 person-years at risk, respectively. The overall incidence of NDs was higher in the T2D group than that in the control group (HR: 1.23, 95% CI: 1.22, 1.25, p < 0.001). This study revealed a higher incidence of NDs in elderly Koreans who were initially diagnosed with T2D. This suggests that T2D is a risk factor for NDs in elderly Koreans.

Comprehensive molecular analysis to predict the efficacy of chemotherapy containing bevacizumab in patients with metastatic colorectal cancer.

Background: Although bevacizumab is an important treatment for metastatic colorectal cancer (CRC), not all patients with CRC benefit from it; in unselected patient populations, only modest survival benefits have been reported. Methods: We evaluated clinical outcomes in 110 patients using comprehensive molecular characterization to identify biomarkers for a response to bevacizumab-containing treatment. The molecular analysis comprised whole-exome sequencing, ribonucleic acid sequencing, and a methylation array on patient tissues. Results: Genomic and molecular characterization was successfully conducted in 103 patients. Six of 103 CRC samples were hypermutated, and none of the non-hypermutant tumors were microsatellite unstable. Among those 103 patients, 89 had adenocarcinoma (ADC), 15 were diagnosed with mucinous ADC, and six had signet-ring cell carcinoma (SRCC). Consensus molecular subtype (CMS) 2 was unique to ADC. Of the four SRCCs, two were CMS1, one was CMS4, and the other was CMS3. APC mutation status was a significantly enriched factor in responders to bevacizumab treatment. Fibroblast growth factor receptor (FGFR) 1/2 signaling was upregulated in non-responders, whereas cell cycle, transfer ribonucleic acid processing, nucleotide excision repair, and oxidative phosphorylation pathways were enriched in responders. In addition, IGF1 was differentially expressed in non-responders (log2 fold change = -1.43, p = 4.11 × 10-5, false discovery rate = 0.098), and FLT1 was highly methylated in non-responders (p = 7.55 × 10-3). When the molecular pathways were reanalyzed separately according to the backbone chemotherapy (FOLFOX vs. FOLFIRI), the significance of the molecular pathways varied according to the backbone chemotherapy. Conclusions: This study sought a subset of CRC patients with a distinct clinical response to chemotherapy containing bevacizumab. Our results need to be validated in a large group of homogenous patient cohort and examined according to the different chemotherapy backbones to create personalized therapeutic opportunities in CRC.

Information about immune cell proportions and tumor stage improves the prediction of recurrence in patients with colorectal cancer.

Predicting cancer recurrence is essential to improving the clinical outcomes of patients with colorectal cancer (CRC). Although tumor stage information has been used as a guideline to predict CRC recurrence, patients with the same stage show different clinical outcomes. Therefore, there is a need to develop a method to identify additional features for CRC recurrence prediction. Here, we developed a network-integrated multiomics (NIMO) approach to select appropriate transcriptome signatures for better CRC recurrence prediction by comparing the methylation signatures of immune cells. We validated the performance of the CRC recurrence prediction based on two independent retrospective cohorts of 114 and 110 patients. Moreover, to confirm that the prediction was improved, we used both NIMO-based immune cell proportions and TNM (tumor, node, metastasis) stage data. This work demonstrates the importance of (1) using both immune cell composition and TNM stage data and (2) identifying robust immune cell marker genes to improve CRC recurrence prediction.

Star Shaped Quivers in Four Dimensions.

We discuss 4D Lagrangian descriptions, across dimensions IR duals, of compactifications of the 6D (D, D) minimal conformal matter theory on a sphere with arbitrary number of punctures and a particular value of flux as a gauge theory with a simple gauge group. The Lagrangian has the form of a "star shaped quiver" with the rank of the central node depending on the 6D theory and the number and type of punctures. Using this Lagrangian one can construct across dimensions duals for arbitrary compactifications (any, genus, any number and type of USp punctures, and any flux) of the (D, D) minimal conformal matter gauging only symmetries which are manifest in the ultraviolet.

Prognostic Impact of Mucinous Adenocarcinoma in Stage II and III Colon Cancer.

BACKGROUND: Mucinous adenocarcinoma is a rare histologic feature of colorectal cancer and is characterized by oncologic features that are different from those of adenocarcinoma. However, there are conflicting views regarding the prognostic impact of mucinous adenocarcinoma on colon cancer. OBJECTIVE: This study aimed to evaluate the prognostic impact of mucinous adenocarcinoma in stage II and III colon cancer. DESIGN: This was a retrospective cohort study. SETTINGS: This study was conducted between January 2010 and December 2015. Patients were divided into the mucinous adenocarcinoma and nonmucinous adenocarcinoma groups. Disease-free survival and overall survival were assessed using propensity score matching. PATIENTS: Overall, 2532 patients who underwent radical surgery for stage II and III colon cancer were included in the study. MAIN OUTCOME MEASURES: The main outcome measures were disease-free survival and overall survival. RESULTS: The median follow-up duration was 86 months. The disease-free survival and overall survival were significantly lower in the mucinous adenocarcinoma group than in the nonmucinous adenocarcinoma group. In subgroup analysis, there was no significant difference in the disease-free survival and overall survival between patients with and without mucinous adenocarcinoma with stage II colon cancer. In stage III colon cancer, the disease-free survival and overall survival were significantly lower in patients with mucinous adenocarcinoma than in those without mucinous adenocarcinoma. Multivariable analysis showed that mucinous adenocarcinoma was a poor prognostic factor for disease-free survival and overall survival. LIMITATION: The study's limitations include those that are inherently associated with retrospective single-center studies. CONCLUSIONS: Mucinous adenocarcinoma is a poor prognostic factor in stage III but not in stage II colon cancer. Therefore, mucinous adenocarcinoma might not be regarded as an independent risk factor requiring chemotherapy for favorable oncologic outcomes. However, for stage III colon cancer, patients with mucinous adenocarcinoma require close observation. IMPACTO PRONSTICO DEL ADENOCARCINOMA MUCINOSO EN LAS ETAPAS II Y III DE CNCER DE CLON: ANTECEDENTES:El adenocarcinoma mucinoso es una característica histológica rara del cáncer colorrectal, se caracteriza por propiedades oncológicas que son diferentes a las del adenocarcinoma. Sin embargo, existen puntos de vista contradictorios con respecto al impacto pronóstico del adenocarcinoma mucinoso en el cáncer de colon.OBJETIVO:Este estudio tuvo como objetivo evaluar el impacto pronóstico del adenocarcinoma mucinoso en las etapas II y III de cáncer de cólon.DISEÑO Y CONFIGURACIONES:Este estudio de cohorte retrospectivo se realizó entre enero de 2010 y diciembre de 2015. Los pacientes se dividieron entre grupos de adenocarcinoma mucinoso y adenocarcinoma no mucinoso. La supervivencia libre de enfermedad y la supervivencia global se evaluaron utilizando emparejamiento por puntuación de propensión.PACIENTES:En general, 2,532 pacientes que se sometieron a cirugía radical para etapa II y III de cáncer de colon se incluyeron en el estudio.PRINCIPALES MEDIDAS DE RESULTADO:Las principales medidas de resultado fueron la supervivencia libre de enfermedad y la supervivencia general.RESULTADOS:La mediana de duración del seguimiento fue de 86 meses. La supervivencia libre de enfermedad y la supervivencia global fueron significativamente menores en el grupo de adenocarcinoma mucinoso que en el grupo de adenocarcinoma no mucinoso. En el análisis de subgrupos, no hubo diferencias significativas en la supervivencia libre de enfermedad y la supervivencia global entre los pacientes con o sin adenocarcinoma mucinoso con cáncer de cólon etapa II. En el cáncer de colon etapa III, la supervivencia libre de enfermedad y la supervivencia global fueron significativamente más bajas en pacientes con adenocarcinoma mucinoso que en aquellos sin adenocarcinoma mucinoso. El análisis multivariable mostró que el adenocarcinoma mucinoso era un factor de mal pronóstico para la supervivencia libre de enfermedad y la supervivencia global.LIMITACIONES:Las limitaciones del estudio incluyen aquellas que están inherentemente asociadas con estudios retrospectivos de un solo centro.CONCLUSIONES:El adenocarcinoma mucinoso es un factor de mal pronóstico en el cáncer de colon etapa III pero no en etapa II. Por lo tanto, el adenocarcinoma mucinoso podría no considerarse un factor de riesgo independiente que requiera quimioterapia para obtener resultados oncológicos favorables. Sin embargo, para el cáncer de colon etapa III, los pacientes con adenocarcinoma mucinoso requieren observación cercana. (Traducción-Dr. Aurian Garcia Gonzalez ).

Densely Convolutional Spatial Attention Network for nuclei segmentation of histological images for computational pathology.

Introduction: Automatic nuclear segmentation in digital microscopic tissue images can aid pathologists to extract high-quality features for nuclear morphometrics and other analyses. However, image segmentation is a challenging task in medical image processing and analysis. This study aimed to develop a deep learning-based method for nuclei segmentation of histological images for computational pathology. Methods: The original U-Net model sometime has a caveat in exploring significant features. Herein, we present the Densely Convolutional Spatial Attention Network (DCSA-Net) model based on U-Net to perform the segmentation task. Furthermore, the developed model was tested on external multi-tissue dataset - MoNuSeg. To develop deep learning algorithms for well-segmenting nuclei, a large quantity of data are mandatory, which is expensive and less feasible. We collected hematoxylin and eosin-stained image data sets from two hospitals to train the model with a variety of nuclear appearances. Because of the limited number of annotated pathology images, we introduced a small publicly accessible data set of prostate cancer (PCa) with more than 16,000 labeled nuclei. Nevertheless, to construct our proposed model, we developed the DCSA module, an attention mechanism for capturing useful information from raw images. We also used several other artificial intelligence-based segmentation methods and tools to compare their results to our proposed technique. Results: To prioritize the performance of nuclei segmentation, we evaluated the model's outputs based on the Accuracy, Dice coefficient (DC), and Jaccard coefficient (JC) scores. The proposed technique outperformed the other methods and achieved superior nuclei segmentation with accuracy, DC, and JC of 96.4% (95% confidence interval [CI]: 96.2 - 96.6), 81.8 (95% CI: 80.8 - 83.0), and 69.3 (95% CI: 68.2 - 70.0), respectively, on the internal test data set. Conclusion: Our proposed method demonstrates superior performance in segmenting cell nuclei of histological images from internal and external datasets, and outperforms many standard segmentation algorithms used for comparative analysis.

Skin Cancer Detection Using Deep Learning-A Review.

Skin cancer is one the most dangerous types of cancer and is one of the primary causes of death worldwide. The number of deaths can be reduced if skin cancer is diagnosed early. Skin cancer is mostly diagnosed using visual inspection, which is less accurate. Deep-learning-based methods have been proposed to assist dermatologists in the early and accurate diagnosis of skin cancers. This survey reviewed the most recent research articles on skin cancer classification using deep learning methods. We also provided an overview of the most common deep-learning models and datasets used for skin cancer classification.

The Prognostic Value of Micropapillary Pattern in Colon Cancer and Its Role as a High-Risk Feature in Patients With Stage II Disease.

BACKGROUND: The association of a micropapillary pattern with oncologic outcomes has not been fully studied in patients with colon cancer. OBJECTIVE: We evaluated the prognostic value of a micropapillary pattern, especially for patients with stage II colon cancer. DESIGN: A retrospective comparative cohort study using propensity score matching. SETTING: This study was conducted at a single tertiary center. PATIENTS: Patients with primary colon cancer undergoing curative resection from October 2013 to December 2017 were enrolled. Patients were grouped into micropapillary pattern positive or micropapillary pattern negative. MAIN OUTCOME MEASUREMENTS: Disease-free survival and overall survival. RESULTS: Of the eligible 2192 patients, 334 (15.2%) were with micropapillary pattern (+). After 1:2 propensity score matching, 668 patients with micropapillary pattern-negative status were selected. The micropapillary pattern-positive group showed significantly worse 3-year disease-free survival (77.6% vs 85.1%, p = 0.007). Three-year overall survival of micropapillary pattern-positive and micropapillary pattern-negative patients did not show a statistically significant difference (88.9% vs 90.4%, p = 0.480). In multivariable analysis, micropapillary pattern-positive was an independent risk factor for poor disease-free survival (HR 1.547, p = 0.008). In the subgroup analysis for 828 patients with stage II disease, 3-year disease-free survival deteriorated significantly in micropapillary pattern-positive patients (82.6% vs 93.0, p < 0.001). Three-year overall survival was 90.1% and 93.9% in patients positive and negative for micropapillary pattern, respectively ( p = 0.082). In the multivariable analysis for patients with stage II disease, micropapillary pattern-positive status was an independent risk factor for poor disease-free survival (HR 2.003, p = 0.031). LIMITATIONS: Selection bias due to the retrospective nature of the study. CONCLUSIONS: Micropapillary pattern-positive status may serve as an independent prognostic factor for colon cancer, especially for patients with stage II disease. VALOR PRONSTICO DEL PATRN MICROPAPILAR Y SU PAPEL COMO CARACTERSTICA DE ALTO RIESGO EN PACIENTES CON CNCER DE COLON EN ESTADO II: ANTECEDENTES:La asociación del patrón micropapilar con los resultados oncológicos no ha sido completamente estudiada en pacientes con cáncer de colon.OBJETIVO:Evaluamos el valor pronóstico del patrón micropapilar, especialmente en pacientes con cáncer de colon en estadio II.DISEÑO:Estudio de cohortes comparativo y retrospectivo que utilize el emparejamiento por puntuación de propensiones.AJUSTE:Estudio realizado en un solo centro terciario.PACIENTES:Se incluyeron los pacientes con cáncer de colon primario sometidos a resección curativa desde octubre de 2013 hasta diciembre de 2017. Los pacientes se agruparon en patrón micropapilar positivo ( + ) o patrón micropapilar negativo ( - ).PRINCIPALES MEDIDAS DE RESULTADO:Sobrevida libre de enfermedad y la sobrevida global.RESULTADOS:De los 2192 pacientes elegibles, 334 (15,2%) tenían patrón micropapilar (+). Después de emparejar el puntaje de propensión 1:2, se seleccionaron 668 pacientes con patrón micropapilar (-). El grupo con patrón micropapilar (+) mostró una sobrevida libre de enfermedad significativamente inferior a los tres años (77,6% frente a 85,1%, p = 0,007). La sobrevida global a los tres años del patrón micropapilar (+) y del patrón micropapilar (-) no mostró una diferencia estadísticamente significativa (88,9 % frente a 90,4%, p = 0,480). En el análisis multivariable, el patrón micropapilar (+) fue un factor de riesgo independiente para una deficiente sobrevida libre de enfermedad (índice de riesgo 1,547, p = 0,008). En el análisis de subgrupos de 828 pacientes con enfermedad en estadio II, la sobrevida libre de enfermedad a los tres años se deterioró significativamente en los pacientes con patrón micropapilar (+) (82,6% frente a 93,0, p < 0,001). La sobrevida global a los tres años fué del 90,1% y del 93,9% en el patrón micropapilar (+) y el patrón micropapilar (-), respectivamente ( p = 0,082). En el análisis multivariable de los pacientes con enfermedad en estadio II, el patrón micropapilar (+) fue un factor de riesgo independiente para una sobrevida libre de enfermedad deficiente (índice de riesgo 2,003, p = 0,031).LIMITACIONES:Sesgo de selección debido a la naturaleza retrospectiva del estudio.CONCLUSIONES:El patrón micropapilar (+) sirve como factor pronóstico independiente para el cáncer de colon, especialmente para pacientes con enfermedad en estadio II. (Traducción-Dr. Xavier Delgadillo ).

Effectiveness of personalized treatment stage-adjusted digital therapeutics in colorectal cancer: a randomized controlled trial.

BACKGROUND: Colorectal cancer survivors often experience decline in physical performance and poor quality of life after surgery and during adjuvant therapies. In these patients, preserving skeletal muscle mass and high-quality nourishment are essential to reduce postoperative complications and improve quality of life and cancer-specific survival. Digital therapeutics have emerged as an encouraging tool for cancer survivors. However, to the best of our knowledge, randomized clinical trials applying personalized mobile application and smart bands as a supportive tool to several colorectal patients remain to be conducted, intervening immediately after the surgical treatment. METHODS: This study is a prospective, multi-center, single-blinded, two-armed, randomized controlled trial. The study aims to recruit 324 patients from three hospitals. Patients will be randomly allocated to two groups for one year of rehabilitation, starting immediately after the operation: a digital healthcare system rehabilitation (intervention) group and a conventional education-based rehabilitation (control) group. The primary objective of this protocol is to clarify the effect of digital healthcare system rehabilitation on skeletal muscle mass increment in patients with colorectal cancer. The secondary outcomes would be the improvement in quality of life measured by EORTC QLQ C30 and CR29, enhanced physical fitness level measured by grip strength test, 30-sec chair stand test and 2-min walk test, increased physical activity measured by IPAQ-SF, alleviated pain intensity, decreased severity of the LARS, weight, and fat mass. These measurements will be held on enrollment and at 1, 3, 6 and 12 months thereafter. DISCUSSION: This study will compare the effect of personalized treatment stage-adjusted digital health interventions on immediate postoperative rehabilitation with that of conventional education-based rehabilitation in patients with colorectal cancer. This will be the first randomized clinical trial performing immediate postoperative rehabilitation in a large number of patients with colorectal cancer with a tailored digital health intervention, modified according to the treatment phase and patient condition. The study will add foundations for the application of comprehensive digital healthcare programs focusing on individuality in postoperative rehabilitation of patients with cancer. TRIAL REGISTRATION: NCT05046756. Registered on 11 May 2021.

Transcriptomes of the tumor-adjacent normal tissues are more informative than tumors in predicting recurrence in colorectal cancer patients.

BACKGROUND: Previous investigations of transcriptomic signatures of cancer patient survival and post-therapy relapse have focused on tumor tissue. In contrast, here we show that in colorectal cancer (CRC) transcriptomes derived from normal tissues adjacent to tumors (NATs) are better predictors of relapse. RESULTS: Using the transcriptomes of paired tumor and NAT specimens from 80 Korean CRC patients retrospectively determined to be in recurrence or nonrecurrence states, we found that, when comparing recurrent with nonrecurrent samples, NATs exhibit a greater number of differentially expressed genes (DEGs) than tumors. Training two prognostic elastic net-based machine learning models-NAT-based and tumor-based in our Samsung Medical Center (SMC) cohort, we found that NAT-based model performed better in predicting the survival when the model was applied to the tumor-derived transcriptomes of an independent cohort of 450 COAD patients in TCGA. Furthermore, compositions of tumor-infiltrating immune cells in NATs were found to have better prognostic capability than in tumors. We also confirmed through Cox regression analysis that in both SMC-CRC as well as in TCGA-COAD cohorts, a greater proportion of genes exhibited significant hazard ratio when NAT-derived transcriptome was used compared to when tumor-derived transcriptome was used. CONCLUSIONS: Taken together, our results strongly suggest that NAT-derived transcriptomes and immune cell composition of CRC are better predictors of patient survival and tumor recurrence than the primary tumor.