Multi-center evaluation of artificial intelligent imaging and clinical models for predicting neoadjuvant chemotherapy response in breast cancer.

BACKGROUND: Neoadjuvant chemotherapy (NAC) plays an important role in the management of locally advanced breast cancer. It allows for downstaging of tumors, potentially allowing for breast conservation. NAC also allows for in-vivo testing of the tumors' response to chemotherapy and provides important prognostic information. There are currently no clearly defined clinical models that incorporate imaging with clinical data to predict response to NAC. Thus, the aim of this work is to develop a predictive AI model based on routine CT imaging and clinical parameters to predict response to NAC. METHODS: The CT scans of 324 patients with NAC from multiple centers in Singapore were used in this study. Four different radiomics models were built for predicting pathological complete response (pCR): first two were based on textural features extracted from peri-tumoral and tumoral regions, the third model based on novel space-resolved radiomics which extract feature maps using voxel-based radiomics and the fourth model based on deep learning (DL). Clinical parameters were included to build a final prognostic model. RESULTS: The best performing models were based on space-resolved and DL approaches. Space-resolved radiomics improves the clinical AUCs of pCR prediction from 0.743 (0.650 to 0.831) to 0.775 (0.685 to 0.860) and our DL model improved it from 0.743 (0.650 to 0.831) to 0.772 (0.685 to 0.853). The tumoral radiomics model performs the worst with no improvement of the AUC from the clinical model. The peri-tumoral combined model gives moderate performance with an AUC of 0.765 (0.671 to 0.855). CONCLUSIONS: Radiomics features extracted from diagnostic CT augment the predictive ability of pCR when combined with clinical features. The novel space-resolved radiomics and DL radiomics approaches outperformed conventional radiomics techniques.

Stage 1C grade 3 endometrial cancer: the KK Hospital gynaecological oncology group experience.

OBJECTIVE: It is our standard of care to include pelvic lymph node dissection (PLND) in the staging of endometrial cancer, followed by adjuvant vaginal vault brachytherapy. We report our experience and outcome of patients with stage 1C grade 3 endometrial cancer from KK Hospital Singapore. METHODS: Records of patients with a diagnosis of stage 1C grade 3 endometrial cancer (based on the 1988 FIGO [International Federation of Gynecology and Obstetrics] staging system) from 1995 to 2008 were retrospectively reviewed. Details of surgery, chemotherapy, and radiotherapy were recorded, as were prognostic factors such as histological subtype and number of lymph nodes removed. Dates and sites of relapses were noted. RESULTS: A total of 31 cases were reviewed; 29 had sufficient records to be analyzed, of which one was excluded as she had a second primary cancer (breast). Median follow-up was 50.1 months (15.5-154 months). All cases underwent total hysterectomy and bilateral salpingo-oophorectomy; the majority (22 [76%]) had PLND as well. Those who did not undergo PLND received external beam radiotherapy instead. All but 1 case received postoperative vaginal vault brachytherapy. Eight of 10 patients with nonendometrioid adenocarcinoma (eg, clear cell) histology also received adjuvant chemotherapy. There were 5 systemic relapses (17.9%) and 1 pelvic recurrence (3.6%). The 5-year disease-free survival is 78.6%. No serious (grade 3 or 4) adverse effects were recorded. CONCLUSION: Pelvic lymph node dissection and vaginal vault brachytherapy seem to be effective in preventing locoregional recurrences, with few associated adverse effects. However, the rate of systemic relapse is relatively high. Adjuvant chemotherapy should also be considered for cases with poor prognostic factors.

Associations of lifestyle and diet with the risk of nasopharyngeal carcinoma in Singapore: a case-control study.

BACKGROUND: Nasopharyngeal carcinoma (NPC) is a commonly diagnosed cancer in Southeast Asia. Many studies have examined the risk factors for NPC, yet the roles of some risk factors remain inconclusive. The purpose of this study was to examine associations between modifiable lifestyle factors and the risk of NPC in the Singaporean population. METHODS: We conducted a case-control study in Singapore with 300 patients and 310 controls who were recruited between 2008 and 2012. Each control was selected and individually matched to each patient based on sex, ethnicity, and age (±5 years). A total of 290 pairs of cases and controls were matched successfully. We examined lifestyle factors such as tobacco smoking, alcohol drinking, various salted and preserved food consumption, and weaning practices. RESULTS: After adjusting for covariates, multivariate analysis showed that those participants who were current smokers and had ever smoked tobacco had a higher risk of NPC than participants who had never smoked, with odds ratios (ORs) of 4.50 (95% confidence interval [CI] 2.58-7.86; P < 0.001) and 2.52 (95% CI 1.54-4.12; P < 0.001), respectively. Those who consumed salted vegetables at least once a week also showed a significantly increased risk of NPC than those who never or rarely consumed salted vegetables, with an OR of 4.18 (95% CI 1.69-10.38; P = 0.002). CONCLUSION: Smoking (currently and ever-smoked) and consuming salted vegetables once a week or more were lifestyle risk factors for NPC, and changes of these factors for the better may reduce the risk of NPC.