Detection of oral cancer and oral potentially malignant disorders using artificial intelligence-based image analysis.

BACKGROUND: We aimed to construct an artificial intelligence-based model for detecting oral cancer and dysplastic leukoplakia using oral cavity images captured with a single-lens reflex camera. SUBJECTS AND METHODS: We used 1043 images of lesions from 424 patients with oral squamous cell carcinoma (OSCC), leukoplakia, and other oral mucosal diseases. An object detection model was constructed using a Single Shot Multibox Detector to detect oral diseases and their locations using images. The model was trained using 523 images of oral cancer, and its performance was evaluated using images of oral cancer (n = 66), leukoplakia (n = 49), and other oral diseases (n = 405). RESULTS: For the detection of only OSCC versus OSCC and leukoplakia, the model demonstrated a sensitivity of 93.9% versus 83.7%, a negative predictive value of 98.8% versus 94.5%, and a specificity of 81.2% versus 81.2%. CONCLUSIONS: Our proposed model is a potential diagnostic tool for oral diseases.

Primary Oral Mixed Neuroendocrine-Non-neuroendocrine Neoplasm (MiNEN): A Rare Case Report and Review of the Literature.

Mixed neuroendocrine-non-neuroendocrine neoplasms (MiNENs) are rare tumors recently characterized by the presence of both neuroendocrine and non-neuroendocrine components within the same tumor tissue. Although MiNEN found their place in the WHO classification for various organs, this composite tumor in the head and neck region remains exceptionally rare. We present a case of primary oral MiNEN in a 64-year-old male located on the left side of lower gingiva. Biopsy raised suspicion of neuroendocrine carcinoma (NEC) and the patient underwent partial mandibulectomy. The resected specimen showed two distinct components of NEC and squamous cell carcinoma (SCC) with the confirmation of immunohistochemical markers. There has been no sign of recurrence nor metastasis 6 years after the surgery. In addition, we have conducted a review of published cases with potential relevance to this entity, resulting in five cases. The diverse terminology reinforces the need for a standardized classification system of oral/head and neck MiNENs.

Myeloid-derived suppressor cells and plasmacytoid dendritic cells are associated with oncogenesis of oral squamous cell carcinoma.

Myeloid-derived suppressor cells (MDSCs) help establish the tumor microenvironment by suppressing T-cell response in tumor-bearing hosts. Plasmacytoid dendritic cells (pDCs) activate antigen-specific T cells, thereby, maximizing their antitumor effects. IDO1 is associated with both MDSCs and pDCs and plays a major role in the formation of the tumor-mediated immunosuppressive environment. We utilized immunohistochemistry to examine the involvement of IDO1 in oral squamous cell carcinoma (OSCC) and oral potentially malignant disorders (OPMDs, precancerous lesions). We examined the expression of MDSC markers, CD11b and CD33, as well as pDC markers, CD303 and IDO1, in 60 OSCC and 45 precancerous lesion specimens and analyzed their association with clinicopathological parameters. Expression of these biomarkers identifying MDSCs and pDCs was high in precancerous lesions in patients with severe dysplasia and OSCC. While detecting pDCs, high CD303 and IDO1 expression levels were frequently observed in moderately or poorly differentiated OSCCs. CD11b, CD33, and CD303 levels were significantly correlated with the mode of invasion; CD33 was correlated with OSCC invasion depth while the other three markers tended to be highly expressed in superficial cancer cases showing microinvasion. Expression levels of all four biomarkers were significantly associated with the cancerization of OPMDs to OSCCs. We show, for the first time, that the infiltration of MDSCs and pDCs is significantly associated with progression of premalignant lesions to OSCC. This suggests that these cells may act as prognostic biomarkers for premalignant lesion progression and that immunotherapeutic approaches that control each of these immunosuppressive cells may protect against progression to malignancy.

[Efficacy and toxicity of lapatinib plus capecitabine therapy in HER2-positive metastatic breast cancer].

We retrospectively investigated the efficacy and toxicity of lapatinib plus capecitabine in 45 HER2-positive breast cancer patients. The median number of treatment courses was 6(1-22). Brain metastasis developed in 18 cases(40%), and 19 cases(42.2%)had received previous capecitabine treatment for metastatic breast cancer. The objective response rate(ORR=CR+PR)was 22.2%(10/45), and clinical benefit rate(CR+PR+long SD=24w)was 46.7%(21/45).The median time to progression(TTP)was 24.9 weeks(95% CI: 15.2 -34.6 ), and the median overall survival(OS)was 78.1 weeks(95% CI: 55.7 -100.5)in all 45 cases. The median TTP was significantly longer in patients who had not received capecitabine previously(30 vs 16 weeks, 95% CI: 16.3 -43.7, p=0.0051 ). There was no statistical difference in median OS associated with previous capecitabine exposure(42.7 weeks, 95% CI: 21.4 -64, p=0.057 ). The median TTP was significantly longer in patients who received less than 2 treatment regimens with trastuzumab for MBC rather than 3 regimens more(27.3 vs 16 weeks, p=0.0257 ), but there was no statistical difference in median OS(81 vs 40.9 weeks, p=0.26 ). Lapatinib in combination with capecitabine is likely more useful in patients who are naive to capecitabine, who received less than two regimens for metastatic breast cancer.

Protein phosphatase 2A regulatory subunit Bbeta promotes MAP kinase-mediated migration of A431 cells.

BACKGROUND/AIMS: Phosphatases are involved in regulation of MAP kinase (MAPK). A431 cells migrate on collagen after EGF stimulation using MAPK. To clarify the involvement of PP2A in this MAPK-dependent migration, the expression of an isoform of the B regulatory subunit was inhibited. METHODS: An antisense sequence corresponding to Bbeta cDNA was transfected into A431 cells. Their migratory activity on collagen was examined using Transwell, and MAPK phosphorylation and phosphatase activity were measured, and the results were compared with those obtained with mock-transfected cells. RESULTS: Antisense-transfected cells showed less Bbeta protein and phosphatase activity than mock-transfected controls. Migration of antisense-transfected cells showed a low response to EGF. The response of MAPK phosphorylation of antisense-transfected cells to EGF stimulation and adhesion to collagen in the presence or absence of EGF were markedly decreased. Phosphatase activity of PP2A-Bbeta also did not respond to EGF, collagen or EGF plus collagen, and remained at low levels. CONCLUSION: These results suggested that PP2A-Bbeta promotes cell migration through the MAPK cascade.