Interpretable detection of epiretinal membrane from optical coherence tomography with deep neural networks.

This study aimed to automatically detect epiretinal membranes (ERM) in various OCT-scans of the central and paracentral macula region and classify them by size using deep-neural-networks (DNNs). To this end, 11,061 OCT-images were included and graded according to the presence of an ERM and its size (small 100-1000 µm, large > 1000 µm). The data set was divided into training, validation and test sets (75%, 10%, 15% of the data, respectively). An ensemble of DNNs was trained and saliency maps were generated using Guided-Backprob. OCT-scans were also transformed into a one-dimensional-value using t-SNE analysis. The DNNs' receiver-operating-characteristics on the test set showed a high performance for no-ERM, small-ERM and large-ERM cases (AUC: 0.99, 0.92, 0.99, respectively; 3-way accuracy: 89%), with small-ERMs being the most difficult ones to detect. t-SNE analysis sorted cases by size and, in particular, revealed increased classification uncertainty at the transitions between groups. Saliency maps reliably highlighted ERM, regardless of the presence of other OCT features (i.e. retinal-thickening, intraretinal pseudo-cysts, epiretinal-proliferation) and entities such as ERM-retinoschisis, macular-pseudohole and lamellar-macular-hole. This study showed therefore that DNNs can reliably detect and grade ERMs according to their size not only in the fovea but also in the paracentral region. This is also achieved in cases of hard-to-detect, small-ERMs. In addition, the generated saliency maps can be used to highlight small-ERMs that might otherwise be missed. The proposed model could be used for screening-programs or decision-support-systems in the future.

The Effectiveness of Adjuvant PD-1 Inhibitors in Patients With Surgically Resected Stage III/IV Acral Melanoma.

Our aim was to assess the efficacy of adjuvant programmed cell death protein-1 (PD-1) inhibitors and compare the other adjuvant treatments in patients with surgically resected stage III or IV acral melanoma. This study is a multicenter, retrospective analysis. We included 114 patients with stage III or IV acral malignant melanoma who underwent surgery within the past 10 years. We analyzed the effect of adjuvant programmed cell death protein-1 inhibitors on disease-free survival (DFS). The mean follow-up was 40 months, during which 69 (59.5%) patients experienced recurrence. Among the participants, 64 (56.1%) received systemic adjuvant therapy. Specifically, 48.4% received anti-PD-1 therapy, 29.7% received interferon, 14.1% received tezozolomide, and 7.8% received B-Raf proto-oncogene/mitogen-activated protein kinase inhibitors. Patients who received adjuvant therapy had a median DFS of 24 (10.9-37.2) months, whereas those who did not receive adjuvant therapy had a median DFS of 15 (9.8-20.2) months. Multivariate analysis for DFS revealed that the receipt of adjuvant therapy and lymph node metastasis stage were independent significant parameters ( P = 0.021, P = 0.018, respectively). No statistically significant difference was observed for DFS between programmed cell death protein-1 inhibitor treatment and other adjuvant treatments. Regarding overall survival (OS), patients who received adjuvant treatment had a median OS of 71 (30.4-111.7) months, whereas those who did not receive adjuvant treatment had a median OS of 38 (16.7-59.3; P = 0.023) months. In addition, there were no significant differences in OS observed between various adjuvant treatment agents ( P = 0.122). In our study, we have shown that adjuvant therapy had a positive effect on both DFS and OS in patients with stages III-IV acral melanoma who underwent curative intent surgery. Notably, we found no significant differences between anti-PD-1 therapy and other adjuvant therapies.

Efficacy and safety of bevacizumab in patients with low-grade serous ovarian cancer.

Aim: To investigate the efficacy and safety of bevacizumab in patients with recurrent low-grade serous ovarian carcinoma. Materials & methods: The data of patients who received at least two cycles of bevacizumab in combination with chemotherapy were retrospectively recorded. Results: The median age of 51 patients was 56 (range: 33-75) years. The complete response rate was 10.4% and the partial response rate was 43.7%. The objective response rate was 54.1%. Median progression-free survival was 15.9 months (95% CI: 9.1-22.6) and median overall survival was 42.5 months (95% CI: 37.2-47.8). Conclusion: Bevacizumab with chemotherapy is an effective option for treating recurrent ovarian low-grade serous carcinoma.

The prognostic factors in patients with advanced hepatocellular carcinoma: impact of treatment sequencing.

The prognosis of patients with advanced HCC can vary widely depending on factors such as the stage of the cancer, the patient's overall health, and treatment regimens. This study aimed to investigate survival outcomes and associated factors in patients with hepatocellular carcinoma (HCC). In this retrospective study, data from 23 medical oncology clinics were analyzed. Progression-free survival (PFS) and overall survival (OS) values were estimated using the Kaplan-Meier method. Prognostic factors associated with survival which were identified in univariate analysis were subsequently evaluated in a multivariate Cox-regression survival analysis was conducted using the backward stepwise (Conditional LR) method to determine the independent predictors of PFS and OS. Of 280 patients, 131 received chemotherapy and 142 received sorafenib, 6 received atezolizumab plus bevacizumab and 1 received nivolumab for first-line setting. The median follow-up time was 30.4 (95%CI 27.1-33.6) months. For-first line, median PFS was 3.1 (95%CI2.7-3.5) months, and it was significantly longer in patients who received sorafenib or atezolizumab-bevacizumab or nivolumab (PFS 5.8 (95%CI 4.2-7.5) than in those received chemotherapy (PFS 2.1 (95%CI 1.9-2.3) in the first-line setting (p < 0.001). Multivariate analysis revealed that male gender (HR: 2.75, 95% CI: 1.53-4.94, p = 0.01), poor ECOG performance score (HR: 1.88, 95% CI: 1.10-3.21, p = 0.02), higher baseline AFP level (HR: 2.38, 95% CI: 1.54-3.67, p < 0.001) and upfront sorafenib treatment (HR,0.38; 95% CI: 0.23-0.62, p < 0.001) were significantly associated with shorter PFS. The median OS was 13.2 (95%CI 11.1-15.2) months. It was significantly longer in patients who received sorafenib or atezolizumab-bevacizumab or nivolumab in the first-line setting followed by TKIs (sorafenib or regorafenib, OS 18.6 (95%CI 13.8-23.5)) compared to those who received chemotherapy (OS 10.3 (95%CI 6.6-14.1)) in the first-line setting. The multivariate analysis revealed that upfront chemotherapy treatment approach, male gender (HR: 1.77, 95% CI: 1.07-2.94, p = 0.02), poor ECOG performance score (HR: 1.96, 95% CI: 1.24-3.09, p = 0.004) and Child-Pugh score, presence of extrahepatic disease (HR: 1.54, 95% CI: 1.09-2.18, p = 0.01), and higher baseline AFP value (HR: 1.50, 95% CI: 1.03-2.19, p = 0.03) were significantly associated with poor prognosis. Additionally, regarding of treatment sequence, upfront sorafenib followed by regorafenib showed a significantly lower risk of mortality (HR: 0.40, 95% CI: 0.25-0.66, p < 0.001). Sorafenib followed by regorafenib treatment was associated with a significantly lower risk of mortality rather than upfront sorafenib followed by BSC group or upfront chemotherapy followed by TKIs. These findings underscore the importance of the optimal treatment sequences to improve survival in patients with advanced HCC.

The real-world outcomes of Lutetium-177 PSMA-617 radioligand therapy in metastatic castration-resistant prostate cancer: Turkish Oncology Group multicenter study.

Metastatic castration-resistant prostate cancer (mCRPC) remains a challenging condition to treat despite recent advancements. This retrospective study aimed to assess the activity and tolerability of Lutetium-177 (Lu-177) PSMA-617 radioligand therapy (RLT) in mCRPC patients across multiple cancer centers in Turkey. The study included 165 patients who received at least one cycle of Lu-177 PSMA-617 RLT, with the majority having bone metastases and undergone prior treatments. Prostate-specific antigen (PSA) levels were assessed before each treatment cycle, and the biochemical response was evaluated in accordance with the Prostate Cancer Work Group 3 Criteria. The PSA decline of ≥50% was classified as a response, while an increase of ≥25% in PSA levels was indicative of progressive disease. Neither response nor progression was considered as stable disease. The Lu-177 PSMA-617 RLT led to a significant PSA response, with 50.6% of patients achieving a >50% decrease in PSA levels. Median overall survival (OS) and progression-free survival were 13.5 and 8.2 months, respectively. Patients receiving Lu-177 PSMA-617 RLT in combination with androgen receptor pathway inhibitors (ARPIs) had a higher OS compared to those receiving Lu-177 PSMA-617 RLT alone (18.2 vs 12.3 months, P = .265). The treatment was generally well-tolerated, with manageable side effects such as anemia and thrombocytopenia. This study provides real-world evidence supporting the effectiveness and safety of Lu-177 PSMA-617 RLT in mCRPC patients, particularly when used in combination with ARPIs. These findings contribute to the growing body of evidence on the potential benefits of PSMA-targeted therapies in advanced prostate cancer.

HALP Score as a New Prognostic Factor for Patients with Metastatic Bladder Cancer.

OBJECTIVE: To investigate the effect of the haemoglobin, albumin, lymphocyte, and platelet (HALP) score (Haemoglobin, Albumin, Lymphocyte, Platelet count) on survival as a new prognostic factor in metastatic bladder cancer. STUDY DESIGN: Descriptive study. Place and Duration of the Study: Department of Medical Oncology, Celal Bayar University, Manisa, Turkey, and Adnan Menderes University, Aydin, Turkey, from 2010 to 2020. METHODOLOGY: The medical charts of patients with metastatic bladder cancer were reviewed retrospectively. Prognostic value of the HALP score as a marker of overall survival was examined through a receiver operating characteristic (ROC) curve analysis. RESULTS: The cut-off value for the HALP score in the ROC curve analysis was 29. The median overall survival (OS) was 19 months when the HALP score was less than 29, and the median OS was 40 months when the HALP score was 29 or greater, and this finding was statistically significant (p = 0.003). CONCLUSION: The HALP score is closely related to prognosis in metastatic bladder cancer. A high HALP score is associated with better survival outcomes. KEY WORDS: HALP score, Metastatic bladder cancer, Overall survival.

A foundation model for generalizable disease detection from retinal images.

Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders1. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications2. Here, we present RETFound, a foundation model for retinal images that learns generalizable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in several applications. Specifically, RETFound is trained on 1.6 million unlabelled retinal images by means of self-supervised learning and then adapted to disease detection tasks with explicit labels. We show that adapted RETFound consistently outperforms several comparison models in the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction with fewer labelled data. RETFound provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinical AI applications from retinal imaging.

Survival of Patients With Metastatic Rectum Cancer Who Underwent Metastasectomy Following Conversion Chemotherapy Sans Pelvic Radiotherapy: A Turkish Oncology Group Study.

BACKGROUND: The management of early rectal cancer is different from that of colon cancer in terms of radiotherapy (RT) requirements or neoadjuvant treatment. It is not clear how the course of rectal cancer differs from that of the colon in a metastatic setting or how it should be approached differently. This study aimed to evaluate outcomes after combining downsizing chemotherapy (CTx) with rescue surgery. METHODS: Eighty-nine patients (57 men and 32 women) diagnosed with metastatic rectal cancer with resectable disease after systemic CTx were included in the study. All patients underwent surgery for the primary mass and metastasis, but none received radiation therapy before or after surgery. Survival curves for overall survival (OS) and progression-free survival (PFS) were generated using the Kaplan-Meier method and compared with the log-rank test for subgroups. RESULTS: The median follow-up time was 28.8 (17.6-39.4) months. During the follow-up, 54 (60.7%) patients died and 78 (87.6%) patients had a PFS event. Cancer relapsed in 72 (80.9%) patients. Median OS was 35.2 (95% CI: 28.5-41.8) months, and median PFS was 17.7 (95% CI: 14.4-21) months. The five-year OS and PFS were 19% and 3.5%, respectively. Male sex (p=0.04) and a better Mandard score (p=0.021) were associated with a longer OS, while obesity was associated with a shorter PFS (p<0.001). CONCLUSION: Our study is the first to evaluate the effects of metastasectomy after conversion therapy in metastatic rectal cancer independent of colon cancer. As a result of the study, it was seen that the survival after metastasectomy in rectal cancer is worse than the colon cancer data known from previous studies.

Prognostic significance of mucinous histology in left­sided metastatic colorectal cancers with wild­type RAS and evaluation of backbone chemotherapy regimens.

Mucinous colorectal adenocarcinoma (MCAC) is a distinct subtype of colorectal carcinoma (CRC). The prognostic and predictive significance of mucinous histology remains controversial. It was aimed to investigate the prognostic and/or predictive role of mucinous histology in left-sided metastatic CRC (mCRC) with wild-type RAS. This is a retrospective multicenter study of mCRC treated with first line anti-EGFR combined 5-fluorouracil based chemotherapy (CT). Patients were stratified according to presence (>50% extracellular mucin) or absence of mucinous histology. Survival analyses were performed firstly regardless of treatment options and then performed as separating according to CT regimens. Additional analyses were performed for MCAC patients considering backbone CT regimens. A total of 125 patients were included, consisting of 40 (32.0%) patients with MCAC and 85 (68.0%) patients with non-MCAC. Median follow-up time was 19.7 months. Median progression-free survival (PFS) was 10.7 months in all patients, and PFS was lower in MCAC than non-MCAC (9.9 vs. 12.0 months, respectively, P=0.005). Median overall survival (OS) was 25.7 months in all patients. OS was lower in MCAC than non-MCAC (22.8 vs. 29.7 months, respectively, P=0.005). When considering backbone CT regimens, in multivariate analyses, mucinous histology was an independent prognostic factor for OS in both for mFOLFOX6 (HR: 1.92, P=0.04) and FOLFIRI (HR: 2.04, P=0.04) groups and was associated with poor PFS in only mFOLFOX6 (HR: 3.86, P<0.001) group. When outcomes were analyzed for the MCAC group, median OS of MCAC patients receiving mFOLFOX6 and FOLFIRI was 22.47 and 14.22 months, respectively (P=0.41). Median PFS of MCAC patients receiving mFOLFOX6 and FOLFIRI was 10.15 and 8.11 months, respectively (P=0.73). The study revealed poor prognosis of mucinous histology, both in whole study population and in backbone CT groups. Moreover, lower PFS of MCAC patients was revealed in only mFOLFOX6 group and this finding may be a valuable issue for the future research. However, considering all analyses, the present results did not indicate a special benefit of any backbone CT regimen for MCAC patients.

Multitask Learning for Activity Detection in Neovascular Age-Related Macular Degeneration.

Purpose: The purpose of this study was to provide a comparison of performance and explainability of a multitask convolutional deep neuronal network to single-task networks for activity detection in neovascular age-related macular degeneration (nAMD). Methods: From 70 patients (46 women and 24 men) who attended the University Eye Hospital Tübingen, 3762 optical coherence tomography B-scans (right eye = 2011 and left eye = 1751) were acquired with Heidelberg Spectralis, Heidelberg, Germany. B-scans were graded by a retina specialist and an ophthalmology resident, and then used to develop a multitask deep learning model to predict disease activity in neovascular age-related macular degeneration along with the presence of sub- and intraretinal fluid. We used performance metrics for comparison to single-task networks and visualized the deep neural network (DNN)-based decision with t-distributed stochastic neighbor embedding and clinically validated saliency mapping techniques. Results: The multitask model surpassed single-task networks in accuracy for activity detection (94.2% vs. 91.2%). The area under the curve of the receiver operating curve was 0.984 for the multitask model versus 0.974 for the single-task model. Furthermore, compared to single-task networks, visualizations via t-distributed stochastic neighbor embedding and saliency maps highlighted that multitask networks' decisions for activity detection in neovascular age-related macular degeneration were highly consistent with the presence of both sub- and intraretinal fluid. Conclusions: Multitask learning increases the performance of neuronal networks for predicting disease activity, while providing clinicians with an easily accessible decision control, which resembles human reasoning. Translational Relevance: By improving nAMD activity detection performance and transparency of automated decisions, multitask DNNs can support the translation of machine learning research into clinical decision support systems for nAMD activity detection.

The impact of adjuvant oxaliplatin and tumor sidedness on the overall survival of stage IIB colon cancer patients: a multicentre study.

The aim of this multicentre retrospective study was to compare the efficacy of adjuvant chemotherapy regimens both with and without oxaliplatin and tumor sidedness in stage IIB (pT4aN0) colon cancer patients. This study included patients with stage IIB colon cancer who underwent curative surgery and received adjuvant chemotherapy. The patients were divided into two groups (one with and one without oxaliplatin) to compare the overall survival (OS) in right- and left-sided tumors. The study population included 298 patients with stage IIB colon cancer (median age: 57) of whom 69.1% were male. Forty-four per cent of these patients (n = 131) were diagnosed with right-sided colon cancer. The median follow-up duration was 35.9 months. In the entire population, a median OS was not reached, and the five-year OS was 83%. The median disease-free survival (DFS) was 12 months. There was no significant difference in terms of the five-year OS between right- (82%) and left-sided (84%) colon tumors (p = 0.67). In addition, the five-year OS of patients treated with and without oxaliplatin were 76% and 89%, respectively, and there was no statistically significant difference (p = 0.23). The five-year OS of the patients treated with and without oxaliplatin were 83% and 96.5%, respectively, (p = 0.8) in right-sided colon tumors, while it was 75% and 93% (p = 0.06), respectively, in left-sided colon tumors. Tumor sidedness and the addition of oxaliplatin to adjuvant chemotherapy were not found to be associated with the OS in stage IIB colon cancer patients in our study. Further large prospective studies that also include MSI, RAS and BRAF status data are warranted in colon cancer patients.

Real life experience of patients with locally advanced gastric and gastroesophageal junction adenocarcinoma treated with neoadjuvant chemotherapy: a Turkish oncology group study.

Neoadjuvant chemotherapy (NACT) in gastroesophageal junction (GEJ) and gastric cancer (GC) was shown to improve survival in recent studies. We aimed to share our real-life experience of patients who received NACT to compare the efficacy and toxicity profile of different chemotherapy regimens in our country. This retrospective multicentre study included locally advanced GC and GEJ cancer patients who received NACT between 2007 and 2021. Relation between CT regimens and pathological evaluation were analysed. A total of 794 patients from 45 oncology centers in Turkey were included. Median age at the time of diagnosis was 60 (range: 18-86). Most frequent NACT regimens used were FLOT (65.4%), DCF (17.4%) and ECF (8.1%), respectively. In the total study group, pathological complete remission (pCR) rate was 7.2%, R0 resection rate 86.4%, and D2 dissection rate was 66.8%. Rate of pCR and near-CR (24%), and R0 resection (84%) were numerically higher in FLOT arm (p > 0.05). Patients who received FLOT had also higher chemotherapy-related toxicity rate compared to patients who received other regimens (p > 0.05). Median follow-up time was 16 months (range: 1-154 months). Estimated median overall survival (OS) was 58.4months (95% CI: 35.2-85.7) and disease-free survival (DFS) was 50.7 months (95% CI: 25.4-75.9). The highest 3-year estimated OS rate was also shown in FLOT arm (68%). We still do not know which NACT regimen is the best choice for daily practice.  Clinicians should tailor treatment regimens according to patients' multifactorial status and comorbidities for to obtain best outcomes. Longer follow-up period needs to validate our results.

The percentage of ALK-positive cells and the efficacy of first-line alectinib in advanced non-small cell lung cancer: is it a novel factor for stratification? (Turkish Oncology Group Study).

INTRODUCTION: Alectinib is an effective second-generation ALK tyrosine kinase inhibitor (TKI) used in the first-line treatment of patients with advanced ALK-positive NSCLC. Recent studies demonstrated that the percentage of ALK-positive tumor cells in patient groups receiving crizotinib might affect outcomes. This study aimed to investigate whether the percentage of ALK-positive cells had a predictive effect in patients with advanced NSCLC who received first-line Alectinib as ALK-TKI. MATERIALS AND METHODS: This retrospective study included patients with advanced-stage NSCLC who received alectinib as a first-line ALK-TKI and whose percentage of ALK-positive cells was determined by FISH at 27 different centers. Patients who received any ALK-TKI before alectinib were not included in the study. Patients were separated into two groups according to the median (40%) value of the percentage of ALK-positive cells (high-positive group ≥ 40% and low-positive group < 40%). The primary endpoint was PFS, and the secondary endpoints were OS, ORR, and PFS of the subgroups based on different threshold values for the percentage of ALK-positive cells. RESULTS: 211 patients were enrolled (48.3% female, 51.7% male) to study. 37% (n = 78) of the patients had received chemotherapy previously. After a median of 19.4 months of follow-up, the median PFS was not reached in the high-positive group (n = 113), but it was 10.8 months in the low-positive group (n = 98) (HR 0.39; 95% CI 0.25-0.60, p < 0.001). The median OS in the high-positive group was not reached, whereas it was 22.8 months in the low-positive group (HR 0.37; 95% CI 0.22-0.63, p < 0.001). ORR was significantly higher in the high-positive group (87.2 vs. 68.5%; p = 0.002). According to the cut-off values of < 20%, 20-39%, 40-59%, and ≥ 60%, the median PFS was 4.5, 17.1, and 26 months, respectively, and could not be reached in the ≥ 60% group. CONCLUSION: Our study demonstrated that the efficacy of alectinib varies significantly across patient subgroups with different percentages of ALK-positive cells. If these findings are prospectively validated, the percentage of ALK-positive cells may be used as a stratification factor in randomized trials comparing different ALK-TKIs.

The frequency and prognostic significance of ABO/Rh blood groups in male breast cancer patients: A multicenter study.

The study evaluated the distributions and prognostic significance of ABO and rhesus (D) groups in male breast cancer (MBC) patients. The data of 137 patients were retrospectively reviewed. Clinical, histopathological data and ABO/Rh blood groups of the patients were recorded. The ABO/Rh blood group distributions were compared to the healthy men control group (n = 120,160) by the chi-square test. Overall distributions of ABO blood groups were different between the patients (17.5% AB, 38% A, 19% B, and 25.5% O) and control group (7.88% AB, 42.06% A, 15.22% B, and 34.84% O) (P < .001). There were significant differences between the patients and control group with respect to AB vs non-AB blood group distributions (P < .001, odds ratio: 2.43, 95% CI) and O vs non-O blood group distributions (P = .016, odds ratio: 0.62, 95% CI). However, A vs non-A and B vs non-B blood group distributions were not significantly different. The distribution of the Rh factor was similar between patients and the control group (P = .93). In univariate analysis, ABO/Rh blood groups were not a prognostic factor on OS (P = .29). The frequency of the AB blood group in MBC patients is increased than in the healthy control group. AB blood group may be a risk factor for MBC, whereas O blood group may be a protective factor.

Real-world data on efficacy and safety of first-line alectinib treatment in advanced-stage, ALK-positive non-small-cell lung cancer patients: a Turkish Oncology Group study.

Aims: In this multicenter study, the authors aimed to determine the real-life efficacy and safety of first-line alectinib. Materials & methods: This retrospective trial included advanced-stage, ALK-positive non-small-cell lung cancer patients who were treated with first-line alectinib in terms of ALK-tyrosine kinase inhibitors, regardless of previous chemotherapy. The co-primary end points were progression-free survival both for all patients and for the treatment-naive population. The secondary end points were overall response rate, overall survival, rate of CNS progression and safety. Results & conclusion: A total of 274 patients (n = 177 for treatment-naive patients) were enrolled in the study. The median progression-free survival was 26 and 28.8 months for all patients and the treatment-naive group, respectively. The overall response rate, CNS progression rate and 1-year overall survival ratio were 77.9, 12.4 and 77%. Alectinib is a highly effective therapy with a favorable safety profile.

The advancements in cancer treatment, particularly in the last two decades, have been promising. Non-small-cell lung cancer (NSCLC) is one of the most important diseases experiencing these promising developments. ALK positivity, which is caused by the rearrangement of different gene fragments between two chromosomes, affects about 5% of NSCLC patients. This provides a target for next-generation therapies. One of these targeted therapy drugs is alectinib. The authors examined the outcomes of 271 patients with body-disseminated NSCLC who received alectinib as initial targeted therapy. These patients were not chosen to participate in a clinical phase study. They were treated with an approved drug; the study also included 97 patients who had previously received chemotherapy. The median duration of survival without disease worsening was 26 months for all patients receiving alectinib treatment. This value was 28.8 months in 177 patients who had not received any treatment before alectinib. Regardless of disease status, 77% of all patients were found to be alive at the end of the first year. Alectinib treatment resulted in a significant improvement of the disease in approximately four out of five patients. The treatment's side effects were generally tolerable or manageable. Only four patients were reported to have discontinued their medication due to treatment-related side effects. These real-world findings are compatible with previous clinical research. Alectinib is an important first-line treatment option for patients with advanced, ALK-positive NSCLC.

The effectiveness and safety of neoadjuvant pertuzumab and trastuzumab in women with locally advanced, inflammatory, or early-stage human epidermal growth factor receptor 2-positive breast cancer: Turkish Oncology Group study.

In our study, we aimed to evaluate the pathological response rates and side effect profile of adding pertuzumab to the treatment of HER2+ locally advanced, inflammatory, or early-stage breast cancer. This study was conducted by the Turkish Oncology Group (TOG) with data collected from 32 centers. Our study was multicentric, and a total of 364 patients were included. The median age of the patients was 49 years (18-85 years). Two hundred fifteen (60%) of the cases were hormone receptor/HER2+ positive(ER+ or PR+, or both), and 149 (40%) of them were HER2-rich (ER and PR negative). The number of complete responses was 124 (54%) in the docetaxel+trastuzumab+pertuzumab arm and 102 (45%) in the paclitaxel+trastuzumab+pertuzumab arm, and there was no difference between the groups in terms of complete response. In 226 (62%) patients with complete response, a significant correlation was found with DCIS, tumor focality, removed lymph node, and ER status P < 0.05. Anemia, nausea, vomiting, myalgia, alopecia, and mucosal inflammation were significantly higher in the docetaxel arm, P < 0.05. In our study, no statistical difference was found between the before-after echocardiography values. DCIS positivity in biopsy before neoadjuvant chemotherapy, tumor focality; the number of lymph nodes removed and ER status were found to be associated with pCR. In conclusion, we think that studies evaluating pCR-related clinicopathological variables and radiological imaging features will play a critical role in the development of nonsurgical treatment approaches.

Is the benefit of using adjuvant capecitabine in patients with residual triple-negative breast cancer related to pathological response to neoadjuvant chemotherapy?

BACKGROUND: Triple-negative-breast-cancer (TNBC) has a poor prognosis if pathologic complete response (pCR) cannot be achieved following neoadjuvant chemotherapy (NAC). The group of patients that benefit most from adjuvant capecitabine remains unclear. MATERIALS AND METHODS: We analyzed data of 160 consecutive patients with residual TNBC from eight cancer-center. Pathologic response was defined into two groups as having good-pathologic-response (MillerPayneGrading (MPG) IV-III) or poor-pathologic-response (MPG I-II). The characteristics of patients were compared regarding adjuvant capecitabine usage. RESULTS: Univariate-analysis revealed that age, histology, clinical-stage, tumor-size, lymph-nodes number, menopausal status, and pathological-stage were significantly different between two groups. In multivariate-analysis, menopausal status (p = 0.043) and residual tumor-size (p < 0.001) were found to be independent prognostic factors for pathological response. The hazard-ratio for disease recurrence and death in the poor-response group with adjuvant capecitabine was 2.94 (95% confidence-interval (CI), 1.21 to 7.10; p = 0.016) and 4.080 (95% CI, 1.22 to 13.64; p = 0.022), respectively. DFS (p = 0.58) and OS (p = 0.89) improvements with adjuvant capecitabine were not demonstrated in good-response groups. CONCLUSION: This multicenter-study suggested that only the poor-response group to NAC achieved benefit from adjuvant capecitabine. Postmenopausal status and residual tumor-size were related to poor prognosis.

Clinical validation of saliency maps for understanding deep neural networks in ophthalmology.

Deep neural networks (DNNs) have achieved physician-level accuracy on many imaging-based medical diagnostic tasks, for example classification of retinal images in ophthalmology. However, their decision mechanisms are often considered impenetrable leading to a lack of trust by clinicians and patients. To alleviate this issue, a range of explanation methods have been proposed to expose the inner workings of DNNs leading to their decisions. For imaging-based tasks, this is often achieved via saliency maps. The quality of these maps are typically evaluated via perturbation analysis without experts involved. To facilitate the adoption and success of such automated systems, however, it is crucial to validate saliency maps against clinicians. In this study, we used three different network architectures and developed ensembles of DNNs to detect diabetic retinopathy and neovascular age-related macular degeneration from retinal fundus images and optical coherence tomography scans, respectively. We used a variety of explanation methods and obtained a comprehensive set of saliency maps for explaining the ensemble-based diagnostic decisions. Then, we systematically validated saliency maps against clinicians through two main analyses - a direct comparison of saliency maps with the expert annotations of disease-specific pathologies and perturbation analyses using also expert annotations as saliency maps. We found the choice of DNN architecture and explanation method to significantly influence the quality of saliency maps. Guided Backprop showed consistently good performance across disease scenarios and DNN architectures, suggesting that it provides a suitable starting point for explaining the decisions of DNNs on retinal images.

The real-life efficacy and safety of osimertinib in pretreated advanced non-small cell lung cancer patients with T790M mutation: a Turkish Oncology Group Study.

INTRODUCTION: Osimertinib, an irreversible third-generation EGFR-TKI, is the standard of care for second-line treatment of T790M-mutant advanced NSCLC patients whose disease progressed after first-line EGFR-TKI therapy. In this multicenter study, we aimed to determine the real-life efficacy and safety of Osimertinib in pretreated advanced NSCLC patients with T790M mutation. MATERIALS AND METHODS: This retrospective trial included advanced T790M-mutant pretreated NSCLC patients who received Osimertinib from 24 different centers in Turkey. Primary endpoint was time-to-treatment discontinuation (TTD). Secondary endpoints were objective response rate (ORR), overall survival (OS), and safety. RESULTS: Of 163 patients, 68.7% had EGFR exon 19 deletion and 22.7% had exon 21 L858R mutation. Osimertinib was given as second-line treatment in 96 patients (58.9%) and third-line in 48 patients (29.4%). After median of 13-month follow-up, median TTD was 21.6 months with an 82.2% ORR. Estimated median OS was 32.1 months. Grade 3-4 adverse events were seen in 11.7% of the patients. CONCLUSION: Osimertinib is a highly effective option in second- or third-line treatment of NSCLC patients with T790M mutation, with a favorable safety profile.

Side effects of immune-checkpoint inhibitors: Can multiple side effects be seen in a patient?

INTRODUCTION: Nivolumab is a human immunoglobulin G4 monoclonal antibody that inhibits programmed cell death-1 activity by binding to the programmed cell death-1 receptors. Cancer cells express increased number of programmed cell death-1 ligands and this allows them to escape the cytotoxic effects of the T cells. Therefore, the negative programmed cell death-1 receptor signal regulates T-cell proliferation and activation is disrupted. However, this change in the activity of the T cells can cause them to lose their ability to recognize host cells. The immune response enabled by these agents has led to side effects, commonly known as "immune-related adverse events." CASE REPORT: We report a case of a 66-year-old male patient who was treated with nivolumab for recurrent renal cell carcinoma presented with hepatitis and adrenalitis. Three weeks after starting nivolumab, the patient had abdominal pain and weakness, and then aspartate and alanine transaminase levels were found to be elevated. MANAGEMENT AND OUTCOME: Hepatitis was predicted to be due to nivolumab, because other causes were excluded. He started using oral methylprednisolone and then, hepatitis improved. However, while receiving methylprednisolone treatment, fludrocortisone was started with the pre-diagnosis of adrenalitis due to the persistence of fatigue, weakness, and hyponatremia and hyperkalemia. With both treatments, the patient's symptoms and sodium and potassium level returned to normal. DISCUSSION: This case emphasizes the need for patient's education and awareness of immune-related adverse events, and the importance of understanding the management of life-threatening complications of the checkpoint inhibitors, because these side effects require prompt recognition and treatment.