"KAIZEN" method realizing implementation of deep-learning models for COVID-19 CT diagnosis in real world hospitals.

Numerous COVID-19 diagnostic imaging Artificial Intelligence (AI) studies exist. However, none of their models were of potential clinical use, primarily owing to methodological defects and the lack of implementation considerations for inference. In this study, all development processes of the deep-learning models are performed based on strict criteria of the "KAIZEN checklist", which is proposed based on previous AI development guidelines to overcome the deficiencies mentioned above. We develop and evaluate two binary-classification deep-learning models to triage COVID-19: a slice model examining a Computed Tomography (CT) slice to find COVID-19 lesions; a series model examining a series of CT images to find an infected patient. We collected 2,400,200 CT slices from twelve emergency centers in Japan. Area Under Curve (AUC) and accuracy were calculated for classification performance. The inference time of the system that includes these two models were measured. For validation data, the slice and series models recognized COVID-19 with AUCs and accuracies of 0.989 and 0.982, 95.9% and 93.0% respectively. For test data, the models' AUCs and accuracies were 0.958 and 0.953, 90.0% and 91.4% respectively. The average inference time per case was 2.83 s. Our deep-learning system realizes accuracy and inference speed high enough for practical use. The systems have already been implemented in four hospitals and eight are under progression. We released an application software and implementation code for free in a highly usable state to allow its use in Japan and globally.

Laparoscopic distal gastrectomy for gastric cancer in a patient with situs inversus: a case report.

BACKGROUND: Situs inversus (SI) is a rare congenital condition characterized by organ transposition from their normal positions. Careful preoperative planning is important for the safe operation of patients with SI because only a few surgeons have operated on such patients. Here, we report the case of a patient with SI who underwent laparoscopic distal gastrectomy (LDG) with D2 lymph node dissection (LND) for advanced gastric cancer (GC). CASE PRESENTATION: The patient was a 72-year-old man diagnosed with GC. Upper endoscopy revealed a type 3 tumor in the anterior wall of the stomach body. Multidetector computed tomography showed no obvious GC metastasis or inverted organs. The preoperative diagnosis was cStage IIB (i.e., cT3, cN0, and cM0) GC with SI. Although liver retracting and intracorporeal suturing required special attention, LDG with D2 LND and Billroth-I reconstruction were safely performed by reversing the usual procedure. The patient was discharged 10 days after the surgery. CONCLUSIONS: To safely perform laparoscopic surgery for GC in patients with SI, sufficient preoperative preparation is necessary. In particular, a reversible method of liver retraction should be prepared.