An end-to-end cells detection approach for colon cancer histology images

Zhang, Xingguo; Chen, Guoyue; Saruta, Kazuki; Terata, Yuki

doi:10.1117/12.2503067

Cited by 5 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To detect only RBCs and WBCs, Zhang et al used the Faster R‐CNN‐based model. The F1_score of the system, which was able to distinguish between both isomorphic RBC and dysmorphic RBC, was 91.4% 6 . Kang et al discriminated 7 different particles from 5376 images using the Faster R‐CNN and single shot detector (SSD) models.…”

Section: Related Workmentioning

confidence: 99%

“…The F1_score of the system, which was able to distinguish between both isomorphic RBC and dysmorphic RBC, was 91.4%. 6 Kang et al discriminated 7 different particles from 5376 images using the Faster R-CNN and single shot detector (SSD) models. Average precision of 84.1% was obtained for erythrocyte, crystal, leukocyte, epithelial, mycete, cast, and epithelial cells.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

YOLOv5 based detector for eight different urine particles components on single board computer

Çınar,

Erkuş,

Tuncer

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Urine sediment examination (USE) is an important issue in the detection of urinary system diseases and is a prerequisite, especially in the diagnosis of kidney diseases. The low‐contrast urine sediment images contain many particles, and these particles are superimposed or adherent, making it difficult to detect and interpret the particles. In this paper, a YOLOv5‐based urine analysis system, which is one of the fastest and most successful architectures used for object detection, is presented to identify particles in urine. The artificial intelligence‐based system, which can recognize bacteria, leukocytes, erythrocytes, crystals, yeast, cylinders, epithelium, and other particles, provides counting and reporting of components in the images obtained from the centrifuged urine sample through a microscope. The system consists of taking images from the microscope and recording them on SBC (Single Board Computer), artificial intelligence‐based software running on SBC, and database systems where urine analysis results are recorded. Different YOLOv5x architectures were used to evaluate the performance of the system and Precision, Recall, mAP, and F1_score values were obtained as metrics. According to the results obtained with the YOLOv5n, YOLOv5s, and YOLOv5m architectures, the highest mAP value of the system, which can recognize eight different particles, was 95.8% with YOLOv5m. This artificial intelligence‐based system, which will help laboratory workers, will not only save time but also eliminate the standardization differences in manual microscopy and will provide benefits as full‐time educational material.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

YOLOv5 based detector for eight different urine particles components on single board computer

Çınar,

Erkuş,

Tuncer

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Despite the fact that qualitative and quantitative study of histopathological pictures can clarify the tumour and explore alternative cancer treatment choices, cell heterogeneity makes it difficult. When Faster R-CNN was applied in feature extraction, Zhang et al [48] demonstrated that it had good accuracy and a lower cost of time, giving a valuable quantitative analysis group for pathological practice. CNN, which is frequently used to analyze histopathology pictures, solely works on the histological images itself, ignoring the stain degradation.…”

Section: Reviewsmentioning

confidence: 99%

Artificial intelligence in colorectal cancer: a review

Singh¹

2023

Sib. onkol. ž.

View full text Add to dashboard Cite

The study objective: the study objective is to examine the use of artificial intelligence (AI) in the diagnosis, treatment, and prognosis of Colorectal Cancer (CRC) and discuss the future potential of AI in CRC. Material and Methods. The Web of Science, Scopus, PubMed, Medline, and eLIBRARY databases were used to search for the publications. A study on the application of Artificial Intelligence (AI) to the diagnosis, treatment, and prognosis of Colorectal Cancer (CRC) was discovered in more than 100 sources. In the review, data from 83 articles were incorporated. Results. The review article explores the use of artificial intelligence (AI) in medicine, specifically focusing on its applications in colorectal cancer (CRC). It discusses the stages of AI development for CRC, including molecular understanding, image-based diagnosis, drug design, and individualized treatment. The benefits of AI in medical image analysis are highlighted, improving diagnosis accuracy and inspection quality. Challenges in AI development are addressed, such as data standardization and the interpretability of machine learning algorithms. The potential of AI in treatment decision support, precision medicine, and prognosis prediction is discussed, emphasizing the role of AI in selecting optimal treatments and improving surgical precision. Ethical and regulatory considerations in integrating AI are mentioned, including patient trust, data security, and liability in AI-assisted surgeries. The review emphasizes the importance of an AI standard system, dataset standardization, and integrating clinical knowledge into AI algorithms. Overall, the article provides an overview of the current research on AI in CRC diagnosis, treatment, and prognosis, discussing its benefits, challenges, and future prospects in improving medical outcomes.

show abstract

“…Fakat bu şekilde yapılan analizler, insan kaynaklı hatalara açıktır, öznel değerlendirmeler içerir ve emek yoğundur (Liang et al 2018, Zaman et al 2010. Günümüzde ise idrar tahlillerinin çoğu hastanelerde bulunan otomatik idrar analizörleri tarafından yapılmaktadır ve daha standart çıktılar elde edilmektedir (Zhang et al 2018). Fakat, bu cihazların çoğu geleneksel görüntü işleme tekniklerini kullanır ve otomatik olmalarına rağmen yine de operatör kontrolüne ihtiyaç duymaktadırlar.…”

Section: Introductionunclassified

Mask R-CNN ile Mikroskobik İdrar Görüntüsü İçeriklerinin Tespiti

YÖRÜK,

SARAOĞLU,

ÖZER

2023

Afyon Kocatepe University Journal of Sciences and Engineering

View full text Add to dashboard Cite

Mikroskobik idrar içerikleri doğru ve dikkatli bir şekilde analiz edildiğinde vücut hakkında önemli bilgiler verir. İdrar tahlilinin insan sağlığı için önemi nedeniyle mikroskobik idrar içeriklerinin tespit edilmesi amacıyla derin öğrenme görüntü işleme tekniği kullanılarak yapay zeka uygulamaları yapılmıştır. Literatürde yer alan çalışmaların çoğunda genel olarak semantik segmentasyon üzerine yoğunlaşılmıştır. Bu çalışmada ise piksel düzeyinde segmentasyon yapabilen Mask R-CNN modeli ile mikroskobik idrar görüntülerindeki alyuvar, akyuvar, epitel, kristal, bakteri ve mantar içerikleri konum ve nesne türü bilgisiyle birlikte tespit edilmiştir. Mask R-CNN ile tespit edilen nesnelere maske ve çerçeve olmak üzere iki tip sınır çizilmektedir. Sistemin performansı her iki sınır tipi için ayrı ayrı incelenmiştir. Test için kullanılan 100 görüntüdeki toplam 1154 örüntüden maskelere göre 808 ve çerçevelere göre 843 nesne doğru şekilde tespit edilmiştir (IoU=0,5). En iyi tespit oranı akyuvarlar ve alyuvarlar için gerçekleşmiştir. Epiteller çerçevelere göre hesaplamada başarılı bir şekilde tespit edilmiştir fakat düzgün maske oluşturulamamıştır. Bakteriler diğerlerine göre çok küçük olduğu için doğru tespit oranı düşük kalmıştır. Kristallerin ve mantarların çoğu doğru şekilde tespit edilmiştir. Ayrıca, nesne tespitinde sıklıkla kullanılan değerlendirme metriği mAP de hesaplanmıştır. Sistem için hesaplanan mAP değerleri maskelere göre 0,7842 ve çerçevelere göre 0,8343 olmuştur. Mask R-CNN sistemi iyi bir şekilde optimize edilip daha fazla idrar içeriğine ait görüntülerle eğitilmesi durumunda idrar analiz sistemlerinde kullanılabilir.

show abstract

An end-to-end cells detection approach for colon cancer histology images

Cited by 5 publications

References 7 publications

YOLOv5 based detector for eight different urine particles components on single board computer

YOLOv5 based detector for eight different urine particles components on single board computer

Artificial intelligence in colorectal cancer: a review

Mask R-CNN ile Mikroskobik İdrar Görüntüsü İçeriklerinin Tespiti

Contact Info

Product

Resources

About