Deep Learning-based Image Cytometry Using a Bit-pattern Kernel-filtering Algorithm to Avoid Multi-counted Cell Determination.

BACKGROUND/AIM: In pathology, the digitization of tissue slide images and the development of image analysis by deep learning have dramatically increased the amount of information obtainable from tissue slides. This advancement is anticipated to not only aid in pathological diagnosis, but also to enhance patient management. Deep learning-based image cytometry (DL-IC) is a technique that plays a pivotal role in this process, enabling cell identification and counting with precision. Accurate cell determination is essential when using this technique. Herein, we aimed to evaluate the performance of our DL-IC in cell identification. MATERIALS AND METHODS: Cu-Cyto, a DL-IC with a bit-pattern kernel-filtering algorithm designed to help avoid multi-counted cell determination, was developed and evaluated for performance using tumor tissue slide images with immunohistochemical staining (IHC). RESULTS: The performances of three versions of Cu-Cyto were evaluated according to their learning stages. In the early stage of learning, the F1 score for immunostained CD8+ T cells (0.343) was higher than the scores for non-immunostained cells [adenocarcinoma cells (0.040) and lymphocytes (0.002)]. As training and validation progressed, the F1 scores for all cells improved. In the latest stage of learning, the F1 scores for adenocarcinoma cells, lymphocytes, and CD8+ T cells were 0.589, 0.889, and 0.911, respectively. CONCLUSION: Cu-Cyto demonstrated good performance in cell determination. IHC can boost learning efficiencies in the early stages of learning. Its performance is expected to improve even further with continuous learning, and the DL-IC can contribute to the implementation of precision oncology.

[A Case of Successful CDDP plus CPT-11 Therapy for Recurrent Carcinomatous Lymphangiosis Occurring during Postoperative Adjuvant Therapy for Gastric Cancer].

The case involved a 67-year-old man. Type 2 gastric cancer in the body of stomach was discovered, and the patient was referred to this department, where distal gastrectomy with Roux-en-Y reconstruction was carried out. The pathological classification was pT2N2H0P0CY0M0, pStage II B, and S-1 administration was started as postoperative adjuvant therapy. After 10 months of administration, a chest computed tomography(CT)scan revealed fine nodular shadows and irregular thickening of the alveolar septa in both lungs, a finding that was judged to be carcinomatous lymphangiosis. CDDP plus CPT- 11 therapy was subsequently started. Chest CT scan after 2 courses of administration showed the disappearance of the carcinomatous lymphangiosis. However, peritoneal metastasis was noted immediately below the abdominal wall. After completing 6courses of administration, the recurrence of peritoneal metastasis disappeared, and the administration of chemotherapy was terminated. There was no subsequent recurrence, and the patient remains alive today, 6years after the surgery. In the present case, the CT scan did not show clear mediastinal or hilar lymph node enlargement, but nodular shadows were noted at the periphery of the lung field, which were thought to be carcinomatous lymphangiosis as a result of haematogenous or anterograde metastasis into the lungs.