[Surgical Outcomes and Clinicopathological Analysis of Laparoscopic Distal Pancreatectomy].

SUBJECTS: We first reviewed surgical outcomes and pathological findings of 32 patients(laparoscopic group: LDP n=11, open group: ODP n=21)who underwent distal pancreatectomy for pancreatic cancer from January 2018 to October 2022. Then we reviewed long-term outcomes, and recurrence type for 20 patients(LDP: n=5, ODP: n=15)from January 2018 to February 2021. RESULTS: LDP group had significantly longer operation time and less blood loss. There was no difference in length of hospital stay, postoperative complications, number of dissected lymph nodes, positive lymph node metastasis rate, and adjuvant chemotherapy rate. Because of high rate of pancreatic stump closure by hand sewing in ODP, postoperative pancreatic fistula rate was higher in ODP than in LDP. The 2-year relapse-free survival rate was 60% in LDP, 33% in ODP, and the 2-year overall survival rate was 60% in LDP, 71% in ODP, and there were no significant differences. As for the type of recurrence, in LDP group, 2 cases of distant metastases and no local recurrence was observed, and in ODP group, 6 cases each of local recurrences and distant metastases were observed. CONCLUSION: LDP was not inferior to ODP in short and long- term outcomes, safety, curability, and local control ability.

Automatic discrimination of Yamamoto-Kohama classification by machine learning approach for invasive pattern of oral squamous cell carcinoma using digital microscopic images: a retrospective study.

OBJECTIVE: The Yamamoto-Kohama criteria are clinically useful for determining the mode of tumor invasion, especially in Japan. However, this evaluation method is based on subjective visual findings and has led to significant differences in determinations between evaluators and facilities. In this retrospective study, we aimed to develop an automatic method of determining the mode of invasion based on the processing of digital medical images. STUDY DESIGN: Using 101 digitized photographic images of anonymized stained specimen slides, we created a classifier that allowed clinicians to introduce feature values and subjected the cases to machine learning using a random forest approach. We then compared the Yamamoto-Kohama grades (1, 2, 3, 4C, 4D) determined by a human oral and maxillofacial surgeon with those determined using the machine learning approach. RESULTS: The input of multiple test images into the newly created classifier yielded an overall F-measure value of 87% (grade 1, 93%; grade 2, 67%; grade 3, 89%; grade 4C, 83%; grade 4D, 94%). These results suggest that the output of the classifier was very similar to the judgments of the clinician. CONCLUSIONS: This system may be valuable for diagnostic support to provide an accurate determination of the mode of invasion.