Magnetic Resonance Imaging is increasing in importance in prostate cancer diagnosis due to the high accuracy and quality of the examination procedure. However, this process requires a time-consuming analysis of the results. Currently, machine vision is widely used in many areas. It enables automation and support in radiological studies. Successful detection of primary prostate tumors depends on the effective segmentation of the prostate itself. At times, a CT scan may be performed; alternatively, MRI may be the selected option. The data always reach a bottleneck stage. This paper presents the effective training of deep learning models to segment the prostate based on onefold and multimodal medical images. This approach supports the computer-aided diagnosis (CAD) system for radiologists as the first step in cancer exams. A comparison of two approaches designed for prostate segmentation is described. The first combines YOLOv4, the object detection neural network, and U-Net for a semantic segmentation based on onefold modality MRI images. The second presents the same method trained on multimodal images—a CT and MRI mixed dataset. The learning process was carried out in a cloud environment using GPU cards. The experiments are based on data from 120 patients who have undergone MRI and CT examinations. Several metrics evaluated the trained models. In the prostate semantic segmentation process, better results were achieved by mixed MRI with CT datasets. The best model achieved the value of 0.9685 for the Sørensen–Dice coefficient for the threshold value of 0.6.

This paper aims to explore popular CNN architectures for the generation of patient-specific dose distributions for Volumetric Modulated Arc Therapy (VMAT) radiotherapy satisfying clinical dose-volume constraints. Only organs at risk (OARs) and planning target volume (PTV) segmentations are required as input. The outcome of the research is selecting the optimal network architecture and assessing training parameters. The U-net, $\mathbf{ResNet}+\mathbf{U-net},\mathbf{ResNet}+\mathbf{PSPNet}$ networks are analyzed. The $\mathbf{Resnet}+\mathbf{U-net}$ model was chosen as the most suited to the task. The similarity measures such as mIoU and mDice coefficient as well as the dose-volume constraints in PTV and selected OARs are evaluated. The results confirm that the $\mathbf{Reset}+\boldsymbol{U}$ -net network is capable of generating patient-specific dose distribution and can be used as a valuable assistance during clinical radiotherapy planning procedures.

Background: Companies operating in the software industry or those which rely on new technologies are facing a rising level of complexity in building products. To address these new circumstances, enterprises are investing more resources in modern approaches to software delivery, such as agile methodologies. Amongst these methodologies, relative effort estimation is widely adopted. Outcomes of the estimation process are often not predictable or reliable. Aims: The objective of this paper is to research the random forest classification algorithm’s effectiveness for high-level effort estimating. Method: Authors are focusing on defining complexity factors that are treated as model features. In addition, the authors have empirically tested the proposed solution in a commercial environment. Besides these, authors have analyzed the effective impact of each complexity factor. The analysis was done on the set of seventy thousands of Jira work items. Observation has been made empirically across four major releases. Results: The results indicate that the empirical way of defining model features has a significant impact on effort estimation accuracy. During research, the authors have found several key factors that have a significant impact on model accuracy. Teams that are using agile techniques or methods for effort estimation can enhance planning outcomes with tools supporting high-level estimation. Finding out and fine-tuning such tools needs a structured process for finding the most significant key complexity factors. Conclusion: Usage of metrics such as effort estimations and their accuracy in the software development process in agile organizations could lead to more accurate planning and forecasting of project outcomes. Problems with planning on program level could also be actioned with a structured estimation framework, enhanced by modern tools such as classification models. We should remember that complexity is growing with scaling delivery structures within companies.

normal, noncancerous brain cells which render the process of measuring the tumour area/volume a critical factor in modern intensity-modulated radiotherapy (IMRT) planning and further treatment course selection. Deep learning algorithms have been applied in numerous industries with great success. Researchers, together with developers, have produced evidence for many concept solutions that fully utilize algorithms based on advanced statistics. Nevertheless, there have been relatively few revolutionary deployments of deep learning systems over the last decade in common radiology practices. In modern research, there is a trend of attempting to work using medical data in healthcare environment application and transformation, which requires appropriate standards and frameworks in order to achieve applicable outcomes. Initial efforts have the potential result of shaping medical image processing, which in turn has influence on computing software deployment. This paper proposes a universal and complex framework for two parts of the dose control process: tumours detection and tumours area segmentation, based on medical images. The framework is comprehensive and addresses the main challenges when working with medical data and applying modern deep learning techniques for automated tumour detection and segmentation. The framework is applied to shape CADx and CADe systems in the healthcare industry to assist doctors and facilitate their work. CADx/CADe objectives are achieved with the use of classification, detection, and prediction, while image processing tasks are performed with image segmentation, registration, and generation [3].

Medicine, and particularly radiology, is an area where vision systems bring significant benefits, which results in more accurate diagnoses, predictions, and treatment plans. This paper proposes a U-Net training model and simplifies the deep learning based framework for tumour detection and semantic segmentation that shapes frames for computer-aided diagnoses (CADx) and computer-aided detection (CADe) applications. The U-Net was used to segment glioma – tumour area. A training technique is proposed and convolutional neural network models capable of being trained on a dataset of fused full-size CT and PET scans – 512x512x1 – is addressed. The implemented algorithms were executed in a cloud environment, where storage was decoupled from compute (CPU and GPU). The resultant models’ performance was assessed utilizing multiple metrics. Trained models fully automatically detect tumours in a given dataset. The best scored coefficient (Dice Co-Eff) for a model is 0.8750. The paper which follows is a detailed reference with training parameters for U-Net for efficient brain tumour detection on CT and PET scans where the dataset is limited –- in this case, consisting of merely 20 patients.

Gliomas are a type of brain and spinal tumour. They originate from glial cells that form the stroma of nerve tissue. Gliomas constitute about 70% of all intracranial tumours and are perceived as the leading cause of death due to brain tumours. This paper presents a comparison of three approaches for glioma detection, volume computation and 3D visualization. The classic approaches based on thresholding and active contour methods were compared with a deep learning implementation. The state-of-the-art model, named U-Net, was used to segment biomedical images which effectively removed bone images from computed tomography (CT) scans. To portion the tumour area, the Morphological Geodesic Active Contour method was applied. Model training was enriched by implementing a data augmentation strategy. Numerical results of tumour volume in cm3 were presented as well as a 3D visualization example.

The paper presents an algorithm of segmentation of brain imaging examination results − computed tomography (CT) and positron emission tomography (PET) − to identify, compute, and visualize the brain tumors. Computer software was developed in the MATLAB environment using active contour methods: Edge and Chan-Vese. A review of the current treatment plan for patients with diagnosed glioblastoma multiforme was included to emphasize the significance of the solved problem. The work presents executed steps in the algorithm with a detailed description of thresholding process. Visual results of tumors were performed and presented.