A 3D Convolutional Neural Network Based on Non-enhanced Brain CT to Identify Patients with Brain Metastases.

Dedicated brain imaging for cancer patients is seldom recommended in the absence of symptoms. There is increasing availability of non-enhanced CT (NE-CT) of the brain, mainly owing to a wider utilization of Positron Emission Tomography-CT (PET-CT) in cancer staging. Brain metastases (BM) are often hard to diagnose on NE-CT. This work aims to develop a 3D Convolutional Neural Network (3D-CNN) based on brain NE-CT to distinguish patients with and without BM. We retrospectively included NE-CT scans for 100 patients with single or multiple BM and 100 patients without brain imaging abnormalities. Patients whose largest lesion was < 5 mm were excluded. The largest tumor was manually segmented on a matched contrast-enhanced T1 weighted Magnetic Resonance Imaging (MRI), and shape radiomics were extracted to determine the size and volume of the lesion. The brain was automatically segmented, and masked images were normalized and resampled. The dataset was split into training (70%) and validation (30%) sets. Multiple versions of a 3D-CNN were developed, and the best model was selected based on accuracy (ACC) on the validation set. The median largest tumor Maximum-3D-Diameter was 2.29 cm, and its median volume was 2.81 cc. Solitary BM were found in 27% of the patients, while 49% had > 5 BMs. The best model consisted of 4 convolutional layers with 3D average pooling layers, dropout layers of 50%, and a sigmoid activation function. Mean validation ACC was 0.983 (SD: 0.020) and mean area under receiver-operating characteristic curve was 0.983 (SD: 0.023). Sensitivity was 0.983 (SD: 0.020). We developed an accurate 3D-CNN based on brain NE-CT to differentiate between patients with and without BM. The model merits further external validation.

An Explainable MRI-Radiomic Quantum Neural Network to Differentiate Between Large Brain Metastases and High-Grade Glioma Using Quantum Annealing for Feature Selection.

Solitary large brain metastases (LBM) and high-grade gliomas (HGG) are sometimes hard to differentiate on MRI. The management differs significantly between these two entities, and non-invasive methods that help differentiate between them are eagerly needed to avoid potentially morbid biopsies and surgical procedures. We explore herein the performance and interpretability of an MRI-radiomics variational quantum neural network (QNN) using a quantum-annealing mutual-information (MI) feature selection approach. We retrospectively included 423 patients with HGG and LBM (> 2 cm) who had a contrast-enhanced T1-weighted (CE-T1) MRI between 2012 and 2019. After exclusion, 72 HGG and 129 LBM were kept. Tumors were manually segmented, and a 5-mm peri-tumoral ring was created. MRI images were pre-processed, and 1813 radiomic features were extracted. A set of best features based on MI was selected. MI and conditional-MI were embedded into a quadratic unconstrained binary optimization (QUBO) formulation that was mapped to an Ising-model and submitted to D'Wave's quantum annealer to solve for the best combination of 10 features. The 10 selected features were embedded into a 2-qubits QNN using PennyLane library. The model was evaluated for balanced-accuracy (bACC) and area under the receiver operating characteristic curve (ROC-AUC) on the test set. The model performance was benchmarked against two classical models: dense neural networks (DNN) and extreme gradient boosting (XGB). Shapley values were calculated to interpret sample-wise predictions on the test set. The best 10-feature combination included 6 tumor and 4 ring features. For QNN, DNN, and XGB, respectively, training ROC-AUC was 0.86, 0.95, and 0.94; test ROC-AUC was 0.76, 0.75, and 0.79; and test bACC was 0.74, 0.73, and 0.72. The two most influential features were tumor Laplacian-of-Gaussian-GLRLM-Entropy and sphericity. We developed an accurate interpretable QNN model with quantum-informed feature selection to differentiate between LBM and HGG on CE-T1 brain MRI. The model performance is comparable to state-of-the-art classical models.

Screening for Prognostic Biomarkers in Metastatic Adrenocortical Carcinoma by Tissue Micro Arrays Analysis Identifies P53 as an Independent Prognostic Marker of Overall Survival.

Advanced adrenocortical carcinoma (ACC) has poor but heterogeneous prognosis. Apart from Ki67 index, no prognostic or predictive biomarker has been validated in advanced ACC, so far. We aimed at analyzing expression of a large panel of proteins involved in known altered pathways in ACC (cell cycle, Wnt/ß-catenin, methylation) to identify and prioritize potential prognostic or predictive parameters metastatic ACC population. We conducted a retrospective multicentric study. Overall survival (OS) and partial response according to RECIST 1.1 were primary endpoints. TMA was set up and 16 markers were analyzed. Modified ENSAT and GRAS parameters were characterized for prognostic adjustment. Results: We included 66 patients with a mean age at metastatic diagnosis of 48.7 ± 15.5 years. Median survival was 27.8 months. After adjustment to mENSAT-GRAS parameters, p53 and PDxK were prognostic of OS. No potential biomarker has been identified as predictive factor of response. We identified for the first time P53 as an independent prognostic marker of metastatic adrenocortical carcinoma after mENSAT-GRAS parameter adjustment. Prognostic impact of Wnt/ß-catenin alterations was not confirmed in this cohort of metastatic ACC.

Urothelial carcinoma in the era of immune checkpoint inhibitors.

Bladder cancer is the seventh most frequent cancer worldwide. The majority of patients present with nonmuscle invasive disease, while 20% of the patients are diagnosed with muscle-invasive bladder cancer. The treatment of nonmuscle invasive disease is endoscopic resection followed by intravesical adjuvant treatment for high risk patients. The standard treatment of localized muscle-invasive disease is neoadjuvant chemotherapy followed by radical cystectomy. Platinum-based chemotherapy is the first-line treatment in locally advanced or metastatic urothelial carcinoma. Immune checkpoint inhibitors have been approved for the treatment of metastatic urothelial carcinoma as second-line treatment or first-line in platinum-ineligible patients. Recently, pembrolizumab have been approved in bacillus Calmette-Guérin (BCG)-refractory nonmuscle invasive bladder cancer. This review summarizes the current evidence concerning immunotherapy in the treatment of urothelial carcinoma.

Lay abstract Bladder cancer is one of the most frequent cancers worldwide with multiple known risk factors such as cigarette smoking and occupational exposures. The majority of patients present with a superficial disease treated with endoscopic resection and intravesical treatment if needed. The localized form of bladder cancer is treated with chemotherapy followed by radical cystectomy. Metastatic bladder cancer is an incurable disease and historic treatment remains on chemotherapy. Recently, immunotherapy has been approved for the treatment of bladder cancer after progression on chemotherapy. In this article we reviewed the most recent available data concerning immunotherapy for the treatment of early-stage and advanced disease.

Impact of expert review of histological diagnosis of papillary and follicular thyroid cancer.

PURPOSE: Histologic and pTNM classification of differentiated thyroid cancer (DTC) is mandatory to assess risk of relapse, risk of death, and radioactive iodine administration. The impact of an expert central review of external pathology reports has not yet been reported. METHODS: Monocentric retrospective study to evaluate the difference between initial and second-opinion histopathologic diagnosis for DTC patients referred for post-operative radioactive iodine administration between January 2014 and December 2016. We evaluated major discordance (change of diagnosis from malignant to benign or in main histological subtype or a description of aggressive pathological subtypes), minor discordance (change in histological subtype or description of an aggressive component, multifocality or extrathyroidal extension), and change in ATA classification. RESULTS: A second-opinion histological diagnosis was available for 199 patients. A major discordance was observed in 42 (21%) cases (changes in malignancy in 4 cases, changes in main histological subtype in 22, changes in aggressive pathology variants of PTC in 16). One hundred and four minor discordances were observed regarding 92 patients. These histopathological changes led to changes in the ATA 2015 risk stratification classification in 61 (31%) of cases. There were no predictive factors of major/minor histologic changes or ATA risk stratification changes. CONCLUSION: Expert central review of pathology has an impact on the 2015 ATA risk stratification classification that can lead to changes in the management of patients with differentiated thyroid cancer.

[Evaluation of tumor-infiltrating lymphocytes in breast cancer: How to use the 2014 international guidelines?] / Évaluation des lymphocytes infiltrant la tumeur dans les cancers du sein : comment appliquer les recommandations internationales 2014 ?

With the major development of immunotherapies, evaluation of the immune response associated to cancer has become the new challenge for pathologists. In breast cancer, this perspective has been notably anticipated by the recent publication, in 2014, of international guidelines for assessment of tumor-infiltrating lymphocytes (TILs), on routine haematoxylin-eosin stains. This technical article aims at reviewing the main key points and different steps in evaluation of tumor-infiltrating lymphocytes, in order to allow an easy implementation of this putative biomarker in routine practice. Widespread diffusion of international guidelines is the key to development of a standardized and reproducible biomarker. This early learning phase is of particular importance, as immune response will probably play a major role as a prognostic and predictive biomarker, especially in triple-negative and HER2 positive breast cancer.

Cerebral white matter hyperintensities (WMH): an analysis of cerebrovascular risk factors in Lebanon.

BACKGROUND: Cerebral white matter hyperdensities (WMH) are frequently reported on brain magnetic resonance images (MRI) of elderly people; its significance is still under debate. METHODS: WMH subtypes may correlate with vascular risk factors, such as aging, hypertension (HTN) and diabetes mellitus (DM). The suggested hypothesis was to find if any of the periventricular WMH (PVWMH) or the deep WMH (DWMH) would be significantly more correlated with the above vascular risk factors. According to the Fazekas semiquantitative rating scale, we classified WMH into four subtypes: (1) absence of WMH, (2) presence of DWML, (3) presence of PVWMH, (4) presence of both DWML and PVWML. The study was performed on 257 Lebanese inpatients aged 40 years and above who underwent a brain MRI, regardless of their underlying pathology and who were admitted to an Internal Medicine Department in Beirut. The study patients were categorized into five subgroups by age intervals of 10 years. RESULTS: Mean age was 62; 54.1% were females; WMH were observed in 59.5% of study population; we found a linear correlation with WMH and aging with a clear shift for patients over age 60, reaching 84% in patients subgroup of 70-79-year-old and 94% patients subgroup over 80-year-old. PVWMH was found significantly more frequently and in linear correlation with aging and HTN. WMH were also found more frequently among the DM individuals. CONCLUSION: From this first ever retrospective Lebanese study, WMH was reported increasingly with aging in accordance with data from the literature; PVWMH was found significantly more correlated with aging and HTN than was DWMH alone.