Pilot study of an artificial intelligence-based deep learning algorithm to predict time to castration-resistant prostate cancer for metastatic hormone-naïve prostate cancer.

The object in this study is to develop an artificial intelligence-based deep learning algorithm for prediction of time to castration-resistant prostate cancer by combined androgen blockade therapy in metastatic hormone-naïve prostate cancer. We included 180 metastatic hormone-naïve prostate cancer patients who initially received combined androgen blockade. We first evaluated whether time to castration-resistant prostate cancer was a significant prognostic factor. Then, using the patients' needle-biopsy specimen images, we developed and validated our deep learning algorithm. The results are shown below. First, we confirmed that time to castration-resistant prostate cancer correlated with overall survival (P < 0.001). Next, we selected two groups by time to castration-resistant prostate cancer of >24 months (n = 18) and <6 months (n = 6) and developed a deep learning algorithm by artificial intelligence-based machine deep learning. In 16 other metastatic hormone-naïve prostate cancer patients used as an external validation set, we confirmed the prediction accuracy remained significant (P < 0.05). In conclusion, our obtained deep learning algorithm has high predictive ability for the effectiveness of combined androgen blockade.

Significance of the effects of chemotherapy on programmed death-ligand 1 expression in triple-negative breast cancer.

BACKGROUND: Atezolizumab has been approved as an antibody against programmed death-ligand 1 (PD-L1)-positive immune cells in patients with advanced or recurrent triple-negative breast cancer. However, the optimal timing to examine PD-L1 expression remains controversial. We retrospectively researched PD-L1 positivity rates in biopsy, surgical and recurrent specimens from patients with triple-negative breast cancer treated with neoadjuvant chemotherapy. We also examined alterations in PD-L1 and their meaning. METHODS: In total, 35 triple-negative breast cancer biopsy specimens obtained before neoadjuvant chemotherapy, 20 corresponding specimens obtained after neoadjuvant chemotherapy and 5 corresponding recurrent specimens were obtained. We examined PD-L1 immunohistochemistry on tumor cells and tumor-infiltrating immune cells using SP142 antibody. RESULTS: In comparison with specimens obtained before neoadjuvant chemotherapy, PD-L1 expression randomly changed in immune cells after neoadjuvant chemotherapy, but PD-L1 expression was significantly reduced in tumor cells. Pre-neoadjuvant chemotherapy specimens with low PD-L1 expression (PD-L1 scores of ≤1 for both immune cells and tumor cells) were linked to better disease-free survival (P < 0.001) and overall survival (P < 0.001) than the other specimens. CONCLUSION: This is the first study to evaluate PD-L1 expression both before and after chemotherapy in breast cancer and examine its relationship with prognosis. The results suggest that the PD-L1 level may be useful for predicting the prognosis of patients with triple-negative breast cancer who do not have pathological complete responses to neoadjuvant chemotherapy.

A case of long-term complete remission of locally advanced T4 bladder cancer treated with pembrolizumab.

A 69-year-old man with a history of non-muscle invasive bladder cancer 12 years ago presented complaining of gross hematuria. He was diagnosed as having invasive T4 bladder cancer with invasion to a branch of the internal iliac artery and received platinum-based chemo-radiation therapy. However, the tumor progressed to extensively infiltrate the pelvic wall, and left leg pain and swelling developed. Pembrolizumab was started, which entirely resolved the tumor after 14 courses of treatment. Pembrolizumab was discontinued after 20 courses of treatment because of adverse events. However, the patient has remained in complete response for over 2 years after pembrolizumab cessation.