S.S. Jayakrishna , S. Sankar Ganesh , Utpal Das , Subramanian Babu , P. Aman Jayaker
{"title":"通过基于人工智能的SSFI模型检验,减缓冷冻草莓的成熟过程可以激活灰葡萄孢和根霉菌丝体真菌","authors":"S.S. Jayakrishna , S. Sankar Ganesh , Utpal Das , Subramanian Babu , P. Aman Jayaker","doi":"10.1016/j.postharvbio.2025.113984","DOIUrl":null,"url":null,"abstract":"<div><div>Frozen storage is crucial for maintaining the quality of fruit supplies. The study found that exotic strawberries stored in cold rooms to slow their ripening in supermarkets led to the growth of harmful fungi, rendering them inedible. To detect and trace mouldy fruits using a computer vision inspection system. IA-1 captures images of fruit seeds with a surface texture microscope, while IA-2 documents fungal structures using a bright field microscope. Our MTMID algorithm improves segmentation through self-annotation. We developed a deep learning model called SSFI-YOLO, which achieved a mean Average Precision of 71 %. It has a precision confidence curve of 84 %, a precision-recall curve of 70 %, and an F1 score of 64 %. The model can detect tiny seeds in just 11.3 ms under optimal lighting conditions. We observed mycelium-laden Petri plates over a period of 0–120 h at 25 °C and extracted DNA using PCR sequencing. The ITS test confirmed the presence of <em>Botrytis cinerea</em> in frozen fruit samples. Using ICP-MS, we compared the mineral content of fresh and diseased strawberries, finding a significant decrease in Magnesium (Mg) from 348.104 mg/100 g to 100.833 mg/100 g, Potassium (K) from 684.011 mg/100 g to 520.107 mg/100 g, and Calcium (Ca) from 96.243 mg/100 g to 38.471 mg/100 g. These findings show how a slowed ripening process negatively impacts the nutritional profile of strawberries.</div></div>","PeriodicalId":20328,"journal":{"name":"Postharvest Biology and Technology","volume":"232 ","pages":"Article 113984"},"PeriodicalIF":6.8000,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Slowing down the ripening process of frozen strawberries activates Botrytis Cinerea and Rhizopus mycelium fungus: Inspect through AI-based SSFI model\",\"authors\":\"S.S. Jayakrishna , S. Sankar Ganesh , Utpal Das , Subramanian Babu , P. Aman Jayaker\",\"doi\":\"10.1016/j.postharvbio.2025.113984\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Frozen storage is crucial for maintaining the quality of fruit supplies. The study found that exotic strawberries stored in cold rooms to slow their ripening in supermarkets led to the growth of harmful fungi, rendering them inedible. To detect and trace mouldy fruits using a computer vision inspection system. IA-1 captures images of fruit seeds with a surface texture microscope, while IA-2 documents fungal structures using a bright field microscope. Our MTMID algorithm improves segmentation through self-annotation. We developed a deep learning model called SSFI-YOLO, which achieved a mean Average Precision of 71 %. It has a precision confidence curve of 84 %, a precision-recall curve of 70 %, and an F1 score of 64 %. The model can detect tiny seeds in just 11.3 ms under optimal lighting conditions. We observed mycelium-laden Petri plates over a period of 0–120 h at 25 °C and extracted DNA using PCR sequencing. The ITS test confirmed the presence of <em>Botrytis cinerea</em> in frozen fruit samples. Using ICP-MS, we compared the mineral content of fresh and diseased strawberries, finding a significant decrease in Magnesium (Mg) from 348.104 mg/100 g to 100.833 mg/100 g, Potassium (K) from 684.011 mg/100 g to 520.107 mg/100 g, and Calcium (Ca) from 96.243 mg/100 g to 38.471 mg/100 g. These findings show how a slowed ripening process negatively impacts the nutritional profile of strawberries.</div></div>\",\"PeriodicalId\":20328,\"journal\":{\"name\":\"Postharvest Biology and Technology\",\"volume\":\"232 \",\"pages\":\"Article 113984\"},\"PeriodicalIF\":6.8000,\"publicationDate\":\"2025-10-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Postharvest Biology and Technology\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0925521425005964\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRONOMY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Postharvest Biology and Technology","FirstCategoryId":"97","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0925521425005964","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 0
摘要
冷冻储存对于保持水果供应的质量至关重要。研究发现,在超市里,为了减缓草莓的成熟,将它们存放在冷藏室中会导致有害真菌的生长,使它们无法食用。用计算机视觉检测系统检测和追踪发霉的水果。IA-1用表面纹理显微镜捕捉水果种子的图像,IA-2用亮场显微镜记录真菌结构。我们的MTMID算法通过自标注改进了分割。我们开发了一种名为SSFI-YOLO的深度学习模型,其平均平均精度达到了71% %。其精密度置信曲线为84 %,精密度-召回率曲线为70 %,F1分数为64 %。在最佳光照条件下,该模型可以在11.3 ms内检测到微小的种子。我们在25°C条件下观察含菌丝的培养皿0-120 h,并通过PCR测序提取DNA。ITS测试证实冷冻水果样本中含有葡萄孢杆菌。使用icp,我们新鲜的矿物含量和患病的草莓相比,发现显著降低镁(Mg)从348.104 100.833毫克/ 100 g 毫克/ 100 g钾(K)从684.011 520.107毫克/ 100 g 毫克/ 100 g和钙(Ca)从96.243 38.471毫克/ 100 g 毫克/ 100 g。这些发现表明,缓慢的成熟过程如何对草莓的营养状况产生负面影响。
Slowing down the ripening process of frozen strawberries activates Botrytis Cinerea and Rhizopus mycelium fungus: Inspect through AI-based SSFI model
Frozen storage is crucial for maintaining the quality of fruit supplies. The study found that exotic strawberries stored in cold rooms to slow their ripening in supermarkets led to the growth of harmful fungi, rendering them inedible. To detect and trace mouldy fruits using a computer vision inspection system. IA-1 captures images of fruit seeds with a surface texture microscope, while IA-2 documents fungal structures using a bright field microscope. Our MTMID algorithm improves segmentation through self-annotation. We developed a deep learning model called SSFI-YOLO, which achieved a mean Average Precision of 71 %. It has a precision confidence curve of 84 %, a precision-recall curve of 70 %, and an F1 score of 64 %. The model can detect tiny seeds in just 11.3 ms under optimal lighting conditions. We observed mycelium-laden Petri plates over a period of 0–120 h at 25 °C and extracted DNA using PCR sequencing. The ITS test confirmed the presence of Botrytis cinerea in frozen fruit samples. Using ICP-MS, we compared the mineral content of fresh and diseased strawberries, finding a significant decrease in Magnesium (Mg) from 348.104 mg/100 g to 100.833 mg/100 g, Potassium (K) from 684.011 mg/100 g to 520.107 mg/100 g, and Calcium (Ca) from 96.243 mg/100 g to 38.471 mg/100 g. These findings show how a slowed ripening process negatively impacts the nutritional profile of strawberries.
期刊介绍:
The journal is devoted exclusively to the publication of original papers, review articles and frontiers articles on biological and technological postharvest research. This includes the areas of postharvest storage, treatments and underpinning mechanisms, quality evaluation, packaging, handling and distribution of fresh horticultural crops including fruit, vegetables, flowers and nuts, but excluding grains, seeds and forages.
Papers reporting novel insights from fundamental and interdisciplinary research will be particularly encouraged. These disciplines include systems biology, bioinformatics, entomology, plant physiology, plant pathology, (bio)chemistry, engineering, modelling, and technologies for nondestructive testing.
Manuscripts on fresh food crops that will be further processed after postharvest storage, or on food processes beyond refrigeration, packaging and minimal processing will not be considered.