Staining, magnification, and algorithmic conditions for highly accurate cell detection and cell classification by deep learning.

OBJECTIVES: Research into cytodiagnosis has seen an active exploration of cell detection and classification using deep learning models. We aimed to clarify the challenges of magnification, staining methods, and false positives in creating general purpose deep learning-based cytology models. METHODS: Using 11 types of human cancer cell lines, we prepared Papanicolaou- and May-Grünwald-Giemsa (MGG)-stained specimens. We created deep learning models with different cell types, staining, and magnifications from each cell image using the You Only Look Once, version 8 (YOLOv8) algorithm. Detection and classification rates were calculated to compare the models. RESULTS: The classification rates of all the created models were over 95.9%. The highest detection rates of the Papanicolaou and MGG models were 92.3% and 91.3%, respectively. The highest detection rates of the object detection and instance segmentation models, which were 11 cell types with Papanicolaou staining, were 94.6% and 91.7%, respectively. CONCLUSIONS: We believe that the artificial intelligence technology of YOLOv8 has sufficient performance for applications in screening and cell classification in clinical settings. Conducting research to demonstrate the efficacy of YOLOv8 artificial intelligence technology on clinical specimens is crucial for overcoming the unique challenges associated with cytology.

[A Case of Preoperative Chemotherapy for Advanced Gastric Cancer, Laparoscopic Total Gastrectomy, Pancreaticoduodenectomy, and Para-Aortic Lymph Node Dissection].

Bulky N+ gastric cancer has a poor prognosis. The results of JCOG0405 showed the efficacy of neoadjuvant chemotherapy with S-1 plus cisplatin combination therapy for Bulky N+ gastric cancer. JLSSG0901 demonstrated the safety and efficacy of laparoscopic surgery for advanced gastric cancer. But the safety of laparoscopic surgery for locally advanced and extensive nodal metastasis cancer(T4b, para-aortic lymph node metastasis)is not apparent. After DOS therapy, we performed total laparoscopic gastrectomy, DP(distal pancreatectomy), D2+ #16a2/b1 lat, and Roux-en-Y reconstruction, and histopathological results showed that the aortic lymph node metastasis disappeared. We controlled extensive lymph node metastasis using preoperative triplet chemotherapy. Laparoscopic surgery after preoperative chemotherapy for Bulky N+ gastric cancer can be a treatment option because we performed laparoscopic resection and para-aortic lymph node dissection with no complications, including pancreatic complications.

Molecular epidemiological survey of the Babesia gibsoni cytochrome b gene in western Japan.

In this study, we conducted a survey of the cytochrome b (cytb) gene of Babesia gibsoni (B. gibsoni) isolated from clinical cases to determine the prevalence of potential atovaquone (ATV)-resistant variants. Ninety-two blood samples were collected from naturally B. gibsoni infected dogs. The cytb nucleotide sequence was determined by direct sequencing. Twelve non-synonymous amino acid substitutions were identified in cytb. The principal ATV-resistant substitution, M121I, was detected in three cases. This survey determined that potentially ATV-resistant B. gibsoni strains are present in dogs in Japan.

Immunochromatographic test with recombinant Em18 antigen for the follow-up study of alveolar echinococcosis.

The performance of a rapid and simple immunochromatographic test (ICT) with recombinant Em18 (rEm18) antigen for serological follow-up of Echinococcus multilocularis infection was evaluated by comparison with that of an enzyme-linked immunosorbent assay (ELISA) with rEm18, using serum samples from patients who underwent surgery and/or received antiparasitic chemotherapy. The degree of Em18-band intensity on the ICT correlated highly with the absorbance value obtained by the ELISA. The kinetics of antibody levels obtained by the ICT paralleled those of the ELISA. These data suggest that the ICT has high potential as an easy-to-handle, fast, and reliable follow-up tool to monitor the status of alveolar echinococcosis in different stages.

Development of an immunochromatographic test to detect antibodies against recombinant Em18 for diagnosis of alveolar echinococcosis.

An immunochromatographic test (ICT) for the rapid detection of antibodies to Echinococcus multilocularis was developed. The ICT showed a sensitivity of 94% and a specificity of 95.4%. High degrees of agreement were observed between the ICT and an enzyme-linked immunosorbent assay (kappa = 0.93) and between the ICT and immunoblot analysis (kappa = 0.97). It is expected that the ICT developed in this study will be useful for the serodiagnosis of alveolar echinococcosis.