Our study provides a precise assessment of the comprehensive risk of metastasis and feasible predictive markers for T1 ESCC.

No abstract

A 52-year-old Japanese woman presented with a mass in the left breast. A tumor 2.9 cm in diameter was found in the D area on ultrasonography. An ipsilateral swollen axillary lymph node was detected. Invasion of the tumor to the pectoralis major muscle was seen. Based on a diagnosis of malignant lymphoma by fine needle aspiration cytology, radical mastectomy with ipsilateral axillary lymph node dissection was performed. Malignant diffuse large B-cell type lymphoma was diagnosed histologically according to the World Health Organization classification, and the clinical stage was II E by the Ann Arbor staging system. Four courses of adjuvant chemotherapy with cyclophosphamide, doxorubicin, vincristine and prednisone (CHOP) were subsequently performed. The patient is free of recurrence 7 years after surgery. Up to 2002, 380 cases of primary breast non-Hodgkin's lymphoma had been documented in the Japanese literature. When the tumor size was bigger than 4.5 cm, the outcome was poor. Regarding treatment methods, we showed that only enucleation of the tumor is necessary and axillary dissection is not necessary. In our case, we thought that the prognosis was good despite the large tumor and axillary lymph node metastasis, and that we could omit axillary dissection.

Objective: This study aimed to use convolutional neural network (CNN), a deep learning software, to assist in cT1b diagnosis. Methods: This retrospective study used 190 colon lesion images from 41 cases of colon endoscopies performed between February 2015 and October 2016. Unenhanced colon endoscopy images (520 × 520 pixels) with white light were used. Images included 14 cTis cases with endoscopic resection and 14 cT1a and 13 cT1b cases with surgical resection. Protruding, flat, and recessed lesions were analyzed. AlexNet and Caffe were used for machine learning. Fine tuning of data to increase image numbers was performed. Oversampling for the training images was conducted to avoid impartiality in image numbers, and learning was carried out. The 3-fold cross-validation method was used. Sensitivity, specificity, accuracy, and area under the curve (AUC) values in the receiver operating characteristic curve were calculated for each group. Results: The results were the average of obtained values. With CNN learning, cT1b sensitivity, specificity, and accuracy were 67.5, 89.0, and 81.2%, respectively, and AUC was 0.871. Conclusion: Quantitative diagnosis is possible using an endoscopic diagnostic support system with machine learning, without relying on the skill and experience of endoscopists. Moreover, this system could be used to objectively evaluate endoscopic diagnoses.

Background Postoperative docetaxel plus S-1 (DS) chemotherapy is expected to be the standard therapeutic strategy for pStage III gastric cancer based on the results of the JACCRO GC-07 study. Neoadjuvant chemotherapy (NAC) is thought to have several advantages over adjuvant settings. Objective This study aimed to compare the efficacies of NAC DS and the surgery-first strategy for advanced gastric cancer patients with D2 gastrectomy. Methods This was a retrospective, single-institution observational study. Of 171 patients with locally advanced (cStage IIB or III) gastric cancer who underwent curative D2 gastrectomy and received NAC DS and/or S-1 adjuvant chemotherapy between 2011 and 2017, 76 (after propensity score matching for 132 patients who met the eligibility criteria) were enrolled in this study. The 3-year progression-free survival (PFS) rate was used to directly compare efficacies between NAC DS patients and surgery-first patients. Results The 3-year PFS rates for the NAC DS group were significantly higher than those for the surgery-first group (80.0 vs. 58.7; p = 0.037), and the progression hazard ratio of the NAC DS group compared with the surgery-first group was 0.394 (95% confidence interval 0.159–0.978; p = 0.045). Conclusions The NAC DS group showed a high 3-year PFS compared with the surgery-first group, with standard S-1 postoperative chemotherapy or observation. NAC DS can be expected to be beneficial as the standard therapy for advanced gastric cancer and should be adopted for the test arm of a randomized controlled phase III trial. Electronic supplementary material The online version of this article (10.1245/s10434-019-07299-7) contains supplementary material, which is available to authorized users.