Object Detection Improves Tumour Segmentation in MR Images of Rare Brain Tumours

Tumour lesion segmentation is a key step to study and characterise cancer from MR neuroradiological images. Presently, numerous deep learning segmentation architectures have been shown to perform well on the specific tumour type they are trained on (e.g., glioblastoma in brain hemispheres). However, a high performing network heavily trained on a given tumour type may perform poorly on a rare tumour type for which no labelled cases allows training or transfer learning. Yet, because some visual similarities exist nevertheless between common and rare tumours, in the lesion and around it, one may split the problem into two steps: object detection and segmentation. For each step, trained networks on common lesions could be used on rare ones following a domain adaptation scheme without extra fine-tuning. This work proposes a resilient tumour lesion delineation strategy, based on the combination of established elementary networks that achieve detection and segmentation. Our strategy allowed us to achieve robust segmentation inference on a rare tumour located in an unseen tumour context region during training. As an example of a rare tumour, Diffuse Intrinsic Pontine Glioma (DIPG), we achieve an average dice score of 0.62 without further training or network architecture adaptation.

Localized activation of the metastatic phenotype within the perineural region in prostate cancer.

253 Background: Perineural Invasion (PNI) is defined as malignant epithelial cell invasion of the perineural space and nerves. Despite widespread acknowledgement of the clinical significance of PNI as a PCa pathological finding associated with recurrence, increased risk of bone metastasis and poor survival, the molecular mechanism underlying this pathology is relatively unknown. The malignant epithelial cells within the PNI potentially provides a spatially defined “snapshot” of disease progression, as the cells switch to a more migrational phenotype associated with metastatic progression. Here we present the initial spatial PNI phenotypic characterisation in PCa. Methods: Archival FFPE blocks, with associated full clinical history, from patients who underwent a radical prostatectomy for prostate cancer were retrieved under research ethics REC#07/H1003/161+5 10_NOCL_02. Biomarkers EphA2, pEphA2s897, pMLC2, E-Cadherin, Vimentin, TOMM20, MTC01, NDUFB8, PTEN were assessed on 4µm serial sections stained using a multiplex TSA protocol, with S100, pan-cytokeratin and DAPI acting as landmarks, on a Ventana Discovery platform prior to scanning on a Versa 3 platform with Halo image analysis. Prostate zones were defined at 500µm intervals either side of the prostate capsule. Univariate and multivariate (hierarchical clustering, UMap clustering) expression analysis and correlation with clinic-pathological features was conducted within R. Results: The PNI epithelial cells within each spatial zone of the prostate are significantly different to each other (Kruskal-Wallis test p < 2.2x10−16 except for MTC01 p = 5.3x10−10). In comparison with the local tumour lesion, PNI epithelial cells localised within 1000µm of the prostate edge and outside the tumour lesion, have undergone a migrational switch, gaining features associated with an activated metastatic phenotype, with increased expression of amoeboid signalling (EphA2, pEphA2s897, pMLC2) and mitochondrial defects (loss of Complex I and IV, gain of mitochondrial mass (TOMM20)). Patients clustering by multivariate expression trends across the prostate regions showed 4 distinct patient groups, with PNI epithelial cells in patient group 1 & 2 displaying a more epithelial to mesenchymal (EMT) phenotype, especially in the first 1000µm inside the prostate organ. Conclusions: Cells within PNI close to the edge of the prostate have features consistent with a switch to migrational/metastatic activation in contrast to the more indolent cell type found deeper within the tumour. Further characterisation of this localised migrational upregulation will help in understanding the transition from a localised to a metastatic phenotype.

Differential Diagnosis of Jejunum and Ileum Tumours Based on Video Capsule Endoscopy Data Using Mathematical Analysis

Aim. The aim of this study was to develop an algorithm for identifying various types of jejunum and ileum tumour lesions based on video capsule endoscopy (VCE), which can be used by physicians in the process of decision making. Materials and methods. In the study, we analysed data on the examination and treatment of 65 patients (35 men and 30 women aged 18–80 years (mean age 46 ± 28 years)), who underwent VCE in the City Clinical Hospital No. 31 and in the Clinica K+31 during the period October 2008 — April 2017. The indications for VCE were a search for a reason of gastrointestinal bleeding, the anaemia of unknown etiology and suspected tumour of the small intestine. According to the VCE results, 181 cases of various changes in the jejunum and ileum were revealed. Each tumour object had been histologically verified before our study. Capsule endoscopy was performed using equipment produced by Olympus (Japan), MicroCam Intromedic (Korea), PillCam Given Imaging (Israel), OMOM Chongqing Jinshan Science & Technology (China).Results. Following expert interviews, 30 signs and their gradations were identified for assessing the type of lesion in the jejunum and ileum using video capsule endoscopy images. Among them, 8 were found to be statistically significant (affecting the division of objects into groups): patient gender, gut wall/lumen deformation, path of intestinal folds, polypoid changes, vascular pattern, mucosal regularity, mucosal lobulation and colour. Using a Bayesian heterogeneous diagnostic procedure and the calculation of diagnostic factors, a three-level algorithm has been developed for the differential diagnosis of jejunum and ileum lesions.Conclusions. The application of the proposed algorithm in clinical practice will not only allow the presence or absence of the jejunum or ileum tumour lesion to be verified, but also the type of this lesion to be determined with an accuracy of more than 86%. The developed diagnostic algorithm can support decision making by the clinician within the task of differentiating jejunum or ileum tumour lesions into three main types: benign epithelial tumours, benign non-epithelial tumours and malignant tumours. Differential diagnosis of the type of jejunum or ileum tumour lesion using the proposed diagnostic algorithm facilitates not only the development of a treatment tactic for managing such patients (dynamic observation, conservative therapy, operative treatment), but also the determination of terms (emergency, urgent, planned) and methods (endometrial luminal, laparoscopic, laparotomic) of surgical treatment.

Evaluation of Diagnostic Efficiency of Alpha-Fetoprotein in Patients with Liver Cirrhosis and Hepatocellular Carcinoma: Single-Center Experience

BACKGROUND: AFP serum levels are considered as diagnostic and specific for hepatocellular carcinoma (HCC) in patients with liver cirrhosis (LC). AIM: This study aimed to examine the diagnostic value of AFP in the distinguishing of patients with HCC from patients with LC, and to analyse the potential correlation between AFP levels and liver disease stages. MATERIAL AND METHODS: Fifty patients with LC and fifty patients with HCC were included in this study. The majority of the patients were males, while the HBV aetiology was dominant. RESULTS: Significant differences between LC and HCC patients were detected for AST, ALT, GGT, bilirubin, AFP and AP. Patients with HCC had higher AFP values compared to LC. There was no significant correlation between the size of the tumour lesion and serum AFP levels. A positive correlation between AFP concentration and GGT activity was determined, as was the negative correlation between AFP and age of the subjects. The AFP value of 23.34 ng/m showed high sensitivity (84%) and specificity (82%). CONCLUSION: The size of the surface below the ROC curve (AUC) was 0.877 (0.80-0.95), which makes AFP a good biomarker and this diagnostic test is sufficient to separate patients with HCC and LC.