Review of postharvest processing of edible wild-grown mushrooms.

Edible wild-grown mushrooms, plentiful in resources, have excellent organoleptic properties, flavor, nutrition, and bioactive substances. However, fresh mushrooms, which have high water and enzymatic activity, are not protected by cuticles and are easily attacked by microorganisms. And wild-grown mushroom harvesting is seasonal the harvest of edible wild-grown mushrooms is subject to seasonality, so their market availability is challenging. Many processing methods have been used for postharvest mushroom processing, including sun drying, freezing, packaging, electron beam radiation, edible coating, ozone, and cooking, whose effects on the parameters and composition of the mushrooms are not entirely positive. This paper reviews the effect of processing methods on the quality of wild and some cultivated edible mushrooms. Drying and cooking, as thermal processes, reduce hardness, texture, and color browning, with the parallel that drying reduces the content of proteins, polysaccharides, and phenolics while cooking increases the chemical composition. Freezing, which allows mushrooms to retain better hardness, color, and higher chemical content, is a better processing method. Water washing and ozone help maintain color by inhibiting enzymatic browning. Edible coating facilitates the maintenance of hardness and total sugar content. Electrolytic water (EW) maintains total phenol levels and soluble protein content. Pulsed electric field and ultrasound (US) inhibit microbial growth. Frying maintains carbohydrates, lipids, phenolics, and proteins. And the mushrooms processed by these methods are safe. They are the focus of future research that combines different methods or develops new processing methods, molecular mechanisms of chemical composition changes, and exploring the application areas of wild mushrooms.

Volatile compounds and aroma characteristics of mushrooms: a review.

Mushrooms are popular due to their rich medicinal and nutritional value. Of the many characteristics of mushrooms, aroma has received extensive attention and research as a key determinant of consumer preference. This paper reviews the production, role and contribution of common volatile compounds (VCs) in wild and cultivated mushrooms, and explores the methods used to characterize them and the factors influencing aroma. To date, more than 347 common VCs have been identified in mushrooms, such as aldehydes, ketones, alcohols and sulfur-containing compounds. Extraction and identification of VCs is a critical step and combining multiple analytical methods is an effective strategy in mushroom aroma studies. In addition, the VCs and the aroma of mushrooms are affected by a variety of factors such as genetics, growing conditions, and processing methods. However, the mechanism of influence is unknown. Further studies on the production mechanisms of VCs, their contribution to aroma, and the factors influencing their formation need to be determined in order to fully elucidate aroma and flavor of mushrooms.

Building deep learning and traditional chemometric models based on Fourier transform mid-infrared spectroscopy: Identification of wild and cultivated Gastrodia elata.

To identify wild and cultivated Gastrodia elata quickly and accurately, this study is the first to apply three-dimensional correlation spectroscopy (3DCOS) images combined with deep learning models to the identification of G. elata. The spectral data used for model building do not require any preprocessing, and the spectral data are converted into three-dimensional spectral images for model building. For large sample studies, the time cost is minimized. In addition, a partial least squares discriminant analysis (PLS-DA) model and a support vector machine (SVM) model are built for comparison with the deep learning model. The overall effect of the deep learning model is significantly better than that of the traditional chemometric models. The results show that the model achieves 100% accuracy in the training set, test set, and external validation set of the model built after 46 iterations without preprocessing the original spectral data. The sensitivity, specificity, and the effectiveness of the model are all 1. The results concluded that the deep learning model is more effective than the traditional chemometric model and has greater potential for application in the identification of wild and cultivated G. elata.

Rapid and Accurate Authentication of Porcini Mushroom Species Using Fourier Transform Near-Infrared Spectra Combined with Machine Learning and Chemometrics.

Porcini mushrooms have high nutritional value and great potential, but different species are easily confused, so it is essential to identify them rapidly and precisely. The diversity of nutrients in stipe and cap will lead to differences in spectral information. In this research, Fourier transform near-infrared (FT-NIR) spectral information about imparity species of porcini mushroom stipe and cap was collected and combined into four data matrices. FT-NIR spectra of four data sets were combined with chemometric methods and machine learning for accurate evaluation and identification of different porcini mushroom species. From the results: (1) improved visualization level of t-distributed stochastic neighbor embedding (t-SNE) results after the second derivative preprocessing compared with raw spectra; (2) after using multiple pretreatment combinations to process the four data matrices, the model accuracies based on support vector machine and partial least-square discriminant analysis (PLS-DA) under the best preprocessing method were 98.73-99.04% and 98.73-99.68%, respectively; (3) by comparing the modeling results of FT-NIR spectra with different data matrices, it was found that the PLS-DA model based on low-level data fusion has the highest accuracy (99.68%), but residual neural network (ResNet) model based on the stipe, cap, and average spectral data matrix worked better (100% accuracy). The above results suggest that distinct models should be selected for dissimilar spectral data matrices of porcini mushrooms. Additionally, FT-NIR spectra have the advantages of being nondevastate and fast; this method is expected to be a promising analytical tool in food safety control.

Chidamide enhances cytotoxicity of doxorubicin by promoting autophagy and apoptosis in breast cancer.

BACKGROUND: Breast cancer (BC) is a prevalent disease that harms women's health, and in-depth investigations of the pathogenesis, treatment, and prevention of BC are the focus of many research programs. Chidamide (CHI) is a histone deacetylase suppressor that depresses histone deacetylase functions, thereby influencing cell growth through an epigenetic mechanism. However, CHI effects upon BC are largely unknown. Present research aimed to confirm the possibility of using CHI combined with chemotherapy drug doxorubicin (DOX) to prevent chemotherapeutic BC resistance in vivo and in vitro. METHODS: In this study, CCK8 (a plate colony formation assay) was applied to detect cell proliferation. Flow cytometry detection showed the apoptotic cell death of both T47D and MCF-7 cells. Nude mouse xenografts were used to detect tumor growth and pulmonary metastasis. High-throughput sequencing was used to detect expression of different genes. RESULTS: Our data showed that CHI treatment reduced BC cell proliferation, tumor growth, and cell invasion. CHI treatments stimulated BC cell apoptosis by promoting ULK2-mediated autophagy and increasing MCF-7 cell sensitivity to DOX, resulting in decreased tumor growth. CONCLUSION: Collectively, our results illustrated that CHI enhanced DOX cytotoxicity by promoting apoptosis and autophagy in BC cells, which advised that CHI could be a candidate drug for BC patient treatments.

Machine learning and deep learning based on the small FT-MIR dataset for fine-grained sampling site recognition of boletus tomentipes.

This study proposed the necessity of identifying the sampling sites for Boletus tomentipes (B.tomentipes) in combination with cadmium content and environmental factors. Based on fourier transform mid-infrared spectroscopy (FT-MIR) preprocessing by 1st, 2nd, MSC, SNV and SG, five machine learning (ML) algorithms (NB, DT, KNN, RF, SVM) and three Gradient Boosting Machine (GBM) algorithms (XGBoost, LightGBM, CatBoost) were built. To avoid complex preprocessing, we construct BoletusResnet model, propose the concepts of 3DCOS, 3DCOS projected images, index images in addition to 2DCOS, and combine them with deep learning (DL) for classification for the first time. It shows that GBM has higher accuracy than ML and DL has better accuracy than GBM. The four DL models presented in this paper achieve fine-grained sampling sites recognition based on small samples with 100 % accuracy, and a computer application system was developed on them. Therefore, spectral image processing combined with DL is a rapid and efficient classification method which can be widely used in food identification.

A new effective method for identifying boletes species based on FT-MIR and three dimensional correlation spectroscopy projected image processing.

This study proposed the necessity of identifying the species for boletes in combination with the medicinal value, nutritional value and the problems existing in the industrial development of boletes. Based on the preprocessing of Fourier transform mid-infrared spectroscopy (FT-MIR) by 1st, 2nd, SNV, 2nd + MSC and 2nd + SG, Multilayer Perceptron (MLP) and CatBoost models were established. To avoid complex preprocessing and feature extraction, we try deep learning modeling methods based on image processing. In this paper, the concept of three-dimensional correlation spectroscopy (3DCOS) projection image was proposed, and 9 datasets of synchronous, asynchronous and integrative images are generated by computer method. In addition, 18 deep learning models were established for 9 image datasets with different sizes. The results showed that the accuracy of the three types of synchronous spectral models reached 100%, while the accuracy of the asynchronous spectral and integrative spectral models of 3DCOS projection images were 96.97% and 97.98% in the case of big datasets, which overcame the defects of poor modeling effect of asynchronous spectral and integrative spectral in previous two-dimensional correlation spectroscopy (2DCOS) studies. In conclusion, the modeling results of 3DCOS projection images are perfect, and we can apply this method to other identification fields in the future.

Interactive effects of molecular subtypes with tumor size and extracranial metastatic pattern on risk of brain metastasis in breast cancer patients: A population-based study.

BACKGROUND: Early detection of brain metastasis (BM) is essential for prognostic improvement in breast cancer (BC) patients. The aim was to identify predictors of BCBM in different molecular subtypes on a population-based level. METHODS: The Surveillance, Epidemiology, and End Results database was used to select BC patients diagnosed from 2010 to 2018. We evaluated the incidence and risk factors of BCBM and tested the interaction effects between molecular subtypes and other risk factors. RESULTS: Among the 527,525 selected patients, molecular subtypes significantly interacted with T stage and extracranial metastasis (ECM) patterns on the risk of BM in the whole BC population (interaction p = 0.002, <0.001, respectively) and after excluding patients with unknown states of key factors. BM development was independent of the T stage only in HR-/HER2- patients (trend p = 0.126). We selected BC patients with single-organ ECM and found a significant interaction between molecular subtypes and ECM patterns (interaction p = 0.013). The impact of ECM patterns on the risk of BM was limited to HR-/HER2- patients (trend p < 0.001), for whom using bone metastasis as a reference, lung metastasis increased the risk of BM (OR = 1.936, 95% CI: 1.300-2.882, p = 0.001). CONCLUSION: T stage and ECM patterns had different associations with BM in different molecular subtypes. HR-/HER2- BC had distinct features on BM development, manifested as a lack of tumor size effect and is associated with lung metastasis. Close surveillance for BM should be considered for HR-/HER2- BC patients.

Application of Identification and Evaluation Techniques for Edible Mushrooms: A Review.

Edible mushrooms are healthy food with high nutritional value, which is popular with consumers. With the increase of the problem of mushrooms being confused with the real and pollution in the market, people pay more and more attention to food safety. More than 167 articles of edible mushroom published in the past 20 years were reviewed in this paper. The analysis tools and data analysis methods of identification and quality evaluation of edible mushroom species, origin, mineral elements were reviewed. Five techniques for identification and evaluation of edible mushrooms were introduced and summarized. The macroscopic, microscopic and molecular identification techniques can be used to identify species. Chromatography, spectroscopy technology combined with chemometrics can be used for qualitative and quantitative study of mushroom and evaluation of mushroom quality. In addition, multiple supervised pattern-recognition techniques have good classification ability. Deep learning is more and more widely used in edible mushroom, which shows its advantages in image recognition and prediction. These techniques and analytical methods can provide strong support and guarantee for the identification and evaluation of mushroom, which is of great significance to the development and utilization of edible mushroom.

Application of UV-Vis and Infrared Spectroscopy on Wild Edible Bolete Mushrooms Discrimination and Evaluation: A Review.

Nowadays, wild edible bolete mushrooms are more and more attractive among consumers due to their natural health, nutrition, and delicious characteristics. Appropriate analytical techniques together with multivariate statistics analysis are required for the quality control and evaluation of these edible mushrooms. Ultraviolet-visible (UV-Vis) and infrared (IR) technologies have the advantages of time-saving, low-cost, and environmentally friendly, are now prominent among major analytical technologies for quality evaluation of bolete mushrooms. Chemometrics methods have been developed to solve classification and regression issues of bolete mushrooms in combination with spectrum. This paper reviewed the most recent applications of UV-Vis and IR technology coupled with chemometrics in wild edible bolete mushrooms, including the identification of species, origin, and storage duration, fraud detection, and antioxidant properties evaluation, and discussed the limitations and prospects of spectroscopy technologies in the researches of bolete mushrooms, excepting to provide a reference for further research and practical application of wild edible bolete mushrooms.

Neoadjuvant therapy in triple-negative breast cancer: A systematic review and network meta-analysis.

BACKGROUND: Evidence for the preferred neoadjuvant therapy regimen in triple-negative breast cancer (TNBC) is not yet established. METHODS: Literature search was conducted from inception to February 12, 2022. Phase 2 and 3 randomized controlled trials (RCTs) investigating neoadjuvant therapy for TNBC were eligible. The primary outcome was pathologic complete response (pCR); the secondary outcomes were all-cause treatment discontinuation, disease-free survival or event-free survival (DFS/EFS), and overall survival. Odd ratios (OR) with 95% credible intervals (CrI) were used to estimate binary outcomes; hazard ratios (HR) with 95% CrI were used to estimate time-to-event outcomes. Bayesian network meta-analysis was implemented for each endpoint. Sensitivity analysis and network meta-regression were done. RESULTS: 41 RCTs (N = 7109 TNBC patients) were eligible. Compared with anthracycline- and taxane-based chemotherapy (ChT), PD-1 inhibitor plus platinum plus anthracycline- and taxane-based ChT was associated with a significant increased pCR rate (OR 3.95; 95% CrI 1.81-9.44) and a higher risk of premature treatment discontinuation (3.25; 1.26-8.29). Compared with dose-dense anthracycline- and taxane-based ChT, the combined treatment was not associated with significantly improved pCR (OR 2.57; 95% CrI 0.69-9.92). In terms of time-to-event outcomes, PD-1 inhibitor plus platinum plus anthracycline- and taxane-based ChT was associated with significantly improved DFS/EFS (HR 0.42; 95% CrI 0.19-0.81). CONCLUSIONS: PD-1 inhibitor plus platinum and anthracycline- and taxane-based ChT was currently the most efficacious regimen for pCR and DFS/EFS improvement in TNBC. The choice of chemotherapy backbone, optimization of patient selection with close follow-up and proactive symptomatic managements are essential to the antitumor activity of PD-1 inhibitor.

Ultrasound-assisted carbon nanoparticle suspension mapping versus dual tracer-guided sentinel lymph node biopsy in patients with early breast cancer (ultraCars): phase III randomized clinical trial.

BACKGROUND: Appropriate tracing methods for sentinel lymph node biopsy (SLNB) play a key role in accurate axillary staging. This prospective, non-inferiority, phase III RCT compared the feasibility and diagnostic performance of ultrasound-assisted carbon nanoparticle suspension (CNS) mapping with dual tracer-guided SLNB in patients with early breast cancer. METHODS: Eligible patients had primary breast cancer without nodal involvement (cN0), or had clinically positive lymph nodes (cN1) that were downstaged to cN0 after neoadjuvant chemotherapy. Patients were randomly assigned (1 : 1) to undergo either ultrasound-assisted CNS sentinel lymph node (SLN) mapping (UC group) or dual tracer-guided mapping with CNS plus indocyanine green (ICG) (GC group). The primary endpoint was the SLN identification rate. RESULTS: Between 1 December 2019 and 30 April 2021, 330 patients were assigned randomly to the UC (163 patients) or GC (167 patients) group. The SLN identification rate was 94.5 (95 per cent c.i. 90.9 to 98.0) per cent in the UC group and 95.8 (92.7 to 98.9) per cent in the GC group. The observed difference of -1.3 (-5.9 to 3.3) per cent was lower than the prespecified non-inferiority margin of 6 per cent (Pnon-inferiority = 0.024). No significant difference was observed in metastatic node rate (30.5 versus 24.4 per cent; P = 0.222), median number of SLNs harvested (3 (range 1-7) versus 3 (1-8); P = 0.181), or duration of surgery (mean(s.d.) 7.53(2.77) versus 7.63(3.27) min; P = 0.316) between the groups. Among the subgroup of patients who had undergone neoadjuvant treatment, the SLN identification rate was 91.7 (82.2 to 100) per cent in the UC group and 90.7 (81.7 to 99.7) per cent in the GC group. CONCLUSION: The diagnostic performance of ultrasound-assisted CNS mapping was non-inferior to that of dual tracer-guided SLN mapping with CNS plus ICG in patients with early breast cancer. REGISTRATION NUMBER: NCT04951245 (http://www.clinicaltrials.gov).

Research Progress on Elements of Wild Edible Mushrooms.

Wild edible mushrooms are distributed all over the world and are delicious seasonal foods, rich in polysaccharides, amino acids, vitamins, and other components. At the same time, they contain many essential trace elements and are highly enriched in heavy metals (compared to green plants and cultivated edible mushrooms). Consumers may be exposed to health risks due to excessive heavy metals in the process of consumption. This is also one of the important factors affecting the import and export of edible mushrooms, which is of great concern to consumers and entry and exit inspection and quarantine departments. In this paper, the contents of four essential trace elements of iron, manganese, zinc, and copper and four harmful heavy metals of cadmium, lead, mercury, and arsenic in nearly 400 species of wild edible mushrooms from 10 countries are reviewed. It was found that the factors affecting the elemental content of edible mushrooms are mainly divided into internal and external factors. Internal is mainly the difference in species element-enrichment ability, and external is mainly environmental pollution and geochemical factors. The aim is to provide a reference for the risk assessment of edible mushrooms and their elemental distribution characteristics.

Review of Recent Modern Analytical Technology Combined with Chemometrics Approach Researches on Mushroom Discrimination and Evaluation.

Mushroom is a macrofungus with precious fruiting body, as a food, a tonic, and a medicine, human have discovered and used mushrooms for thousands of years. Nowadays, mushroom is also a "super food" recommended by the World Health Organization (WHO) and Food and Agriculture Organization (FAO), and favored by consumers. Discrimination of mushroom including species, geographic origin, storage time, etc., is an important prerequisite to ensure their edible safety and commodity quality. Moreover, the effective evaluation of its chemical composition can help us better understand the nutritional properties of mushrooms. Modern analytical technologies such as chromatography, spectroscopy and mass spectrometry, etc., are widely used in the discrimination and evaluation researches of mushrooms, and chemometrics is an effective means of scientifically processing the multidimensional information hidden in these analytical technologies. This review will outline the latest applications of modern analytical technology combined with chemometrics in qualitative and quantitative analysis and quality control of mushrooms in recent years. Briefly describe the basic principles of these technologies, and the analytical processes of common chemometrics in mushroom researches will be summarized. Finally, the limitations and application prospects of chromatography, spectroscopy and mass spectrometry technology are discussed in mushroom quality control and evaluation.

Low-dose apatinib combined with neoadjuvant chemotherapy in the treatment of early-stage triple-negative breast cancer (LANCET): a single-center, single-arm, phase II trial.

Background: Antiangiogenic therapy combined with chemotherapy could improve pathological complete response (pCR) for breast cancer. Apatinib is an oral tyrosine kinase inhibitor that selectively inhibits vascular endothelial growth factor receptor 2. We assessed the efficacy and safety of apatinib combined with standard neoadjuvant chemotherapy in patients with triple-negative breast cancer (TNBC). Materials and methods: This single-arm, phase II study enrolled patients aged 18-70 years with previously untreated stage IIA-IIIB TNBC. Patients received oral apatinib at a dose of 250 mg once daily and intravenously docetaxel every 3 weeks for four cycles, followed by epirubicin plus cyclophosphamide every 3 weeks for four cycles. The primary endpoint was the pCR rate in the breast and lymph nodes. Secondary endpoints included objective response rate, event-free survival (EFS), overall survival (OS), and safety. Results: In all, 31 patients were enrolled, and the median follow-up time was 22.9 months (range: 10.1-41.6 months). The pCRs in both breast and lymph nodes were achieved in 17 [54.8%; 95% confidence interval (CI): 36.0-72.7] of 31 patients. Objective responses were achieved in 29 patients (93.5%; 95% CI: 78.6-99.2), and disease control was achieved in 31 patients (100%; 95% CI: 88.8-100.0). The 2-year EFS and 2-year OS were 90.9% and 94.4%, respectively. The five most common treatment-related adverse events were fatigue (51%), hypertension (41%), anorexia (39%), hand-foot syndrome (35%), and diarrhea (32%). Few grade 3 or more adverse events were observed. Conclusion: The combination of apatinib with docetaxel followed by epirubicin plus cyclophosphamide showed excellent efficacy and manageable toxicities; and further randomized controlled phase III trials are warranted. Trial registration: This trial was registered with ClinicalTrials.gov (NCT03243838) on 5 August 2017.

Prevention of taxane-associated acute pain syndrome with etoricoxib for patients with breast cancer: A phase II randomised trial.

BACKGROUND: For patients with breast cancer who receive docetaxel chemotherapy, taxane-associated acute pain syndrome (T-APS), considered a form of neural pathology, is a significant clinical problem. We evaluated the effect of prophylactic etoricoxib on T-APS in patients with breast cancer. MATERIALS AND METHODS: We conducted a phase II randomised trial including 144 patients with breast cancer receiving four cycles of docetaxel-based chemotherapy. Patients were randomised in the ratio 1:1 to receive prophylactic etoricoxib (60 mg, Day 1 to Day 8) or no prophylactic treatment. The primary end-point was the overall incidence of T-APS across all cycles. Secondary end-points included the incidence of severe pain (greater than 5 on a scale 0-10); severity and duration of T-APS; Functional Assessment of Cancer Therapy-Breast subscale; chronic sensory and motor neurotoxicity and adverse events. RESULTS: The overall incidence of T-APS across all cycles of chemotherapy in the etoricoxib group was 57.1%, while that in the control group was 91.5% (P < 0.001). The incidences of severe T-APS were 11.4% and 54.9% for the etoricoxib and control groups, respectively (P < 0.001). The mean Functional Assessment of Cancer Therapy-Breast subscale score of the etoricoxib group (103.79-107.24) was significantly higher than that of the control group (93.88-96.71) (P = 0.001 at cycle 1 and P < 0.001 at cycles 2-4). After four cycles of docetaxel chemotherapy, the etoricoxib group demonstrated a significantly higher mean Functional Assessment of Cancer Treatment Neurotoxicity subscale score than the control group (38.46, 95% CI: 37.63-39.29; 34.59, 95% CI: 33.73-35.45, respectively; P < 0.001). Electromyography showed that most peripheral sensory nerves in the etoricoxib group had significantly improved action potential amplitudes and conduction velocities compared with those in the control group. CONCLUSION: Prophylactic use of etoricoxib could significantly reduce the incidence and severity of docetaxel-induced acute pain syndrome and potentially decrease docetaxel-induced peripheral neuropathy. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04565600.

A fast multi-source information fusion strategy based on deep learning for species identification of boletes.

Wild mushroom market is an important economic source of Yunnan province in China, and its wild mushroom resources are also valuable wealth in the world. This work will put forward a method of species identification and optimize the method in order to maintain the market order and protect the economic benefits of wild mushrooms. Here we establish deep learning (DL) models based on the two-dimensional correlation spectroscopy (2DCOS) images of near-infrared spectroscopy from boletes, and optimize the identification effect of the model. The results show that synchronous 2DCOS is the best method to establish DL model, and when the learning rate was 0.01, the epochs were 40, using stipes and caps data, the identification effect would be further improved. This method retains the complete information of the samples and can provide a fast and noninvasive method for identifying boletes species for market regulators.

A Novel Metabolic Reprogramming Strategy for the Treatment of Diabetes-Associated Breast Cancer.

Diabetes is directly related to the risk of breast cancer (BC) occurrence and worsened BC prognosis. Currently, there are no specific treatments for diabetes-associated BC. This paper aims to understand the fundamental mechanisms of diabetes-induced BC progression and to develop personalized treatments. It reports a metabolic reprogramming strategy (MRS) that pharmaceutical induction of glucose import and glycolysis with metformin and NF-κB inhibitor (NF-κBi) while blocking the export of excessive lactate via inhibiting monocarboxylate transporter 4 (MCT4) leads to a metabolic crisis within the cancer cells. It demonstrates that the MRS shifts the metabolism of BC cells toward higher production of lactate, blocks lactate secretion, prompts intracellular acidification and induces significant cytotoxicity. Moreover, a novel MCT4 inhibitor CB-2 has been identified by structure-based virtual screening. A triple combination of metformin, CB-2, and trabectedin, a drug that impedes NF-κB signaling, strongly inhibits BC cells. Compared to normal glucose condition, MRS elicits more potent cancer cell-killing effects under high glucose condition. Animal model studies show that diabetic conditions promote the proliferation and progression of BC xenografts in nude mice and that MRS treatment significantly inhibits HG-induced BC progression. Therefore, inhibition of MCT4 combined with metformin/NF-κBi is a promising cancer therapy, especially for diabetes-associated BC.

Verified the rapid evaluation of the edible safety of wild porcini mushrooms, using deep learning and PLS-DA.

BACKGROUND: How to quickly identify poisonous mushrooms is a worldwide problem, because poisonous mushrooms and edible mushrooms have very similar appearances. Even some edible mushrooms must be processed further before they can be eaten. In addition, mushrooms from different geographical origins contain different levels of heavy metals. Eating frequent mushrooms with excessive heavy metal content can also cause food poisoning. This information is very important and needs to be informed to consumers in advance. Through the demand for the safety of porcini mushrooms in the Yunnan area we propose a hierarchical identification system based on Fourier-transform near-infrared (FT-NIR) spectroscopy to evaluate the edible safety of porcini species. RESULTS: We found that deep learning is the most effective means to identify the edible safety of porcini, and the recognition accuracy was 100%, by comparing two pattern recognition tools, deep learning and partial least square discriminant analysis (PLS-DA). Although the accuracy of the PLS-DA test set is 96.10%, the poisonous porcini is not allowed to be wrongly judged. In addition, the cadmium (Cd) content of Leccinum rugosiceps in the Midu area exceeded the standard. Deep learning can trace Le. rugosiceps geographic origin with an accuracy of 100%. CONCLUSION: The overall results show that deep learning methods based on FT-NIR can identify porcini that is at risk of being eaten. This has useful application prospects in food safety. © 2021 Society of Chemical Industry.