This study investigates the effectiveness of machine learning (ML)-based radiomics in classifying mammographic lesions. Leveraging the publicly available CBIS-DDSM and the matRadiomics toolbox, Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) models were tested across progressively larger training sets. LDA achieved the highest performance, demonstrating excellent discrimination between masses and calcifications (AUC of 97.08%, Accuracy of 95.63%). However, classification of benign versus malignant lesions yielded lower AUCs of 68.28% for microcalcifications and 61.53% for masses highlighting the limitations of traditional ML approaches. These findings point toward the need for more advanced methods, such as deep learning, in future research.

In this paper we analyze different Mixed Integer Linear Programming (MILP) models in order to produce 1D and 3D Spread-Out Bragg peaks (SOBP) for protons in water. Our techniques do not use much computational resources; in particular, all our experiments have been performed by a standard personal computer. As main result we give the proof of concept that the techniques that we use to create parameterized uniform SOBP can be fruitfully used in Treatment Planning Systems (TPS) for Intensity Modulated Proton Therapy (IMPT). As technical result we show, for the first time to our best knowledge, that there is a trade-off between the minimum number of energies (or layers) to be used to have a SOBP peak within a uniformity tolerance parameter Dtand the same parameter Dt. Minimizing the number of energies also has the advantage of reducing the delivery time using the facilities in operation nowadays.

Proton therapy is nowadays a major clinical modality in the fight against cancer due to the advantages offered by its peculiar depth dose profile, that allows to improve its efficacy on tumors while reducing damages to healthy tissues. The number of worldwide facilities and of treated patients is increasing every year. A challenge of proton therapy is that treatment planning systems require accurate dose computation, but the golden standard in accuracy are Monte Carlo algorithms that are slow. For this reason, accurate and faster dose calculation algorithms are needed. In this paper we use Deep Learning to achieve both speed and accuracy in dose calculation for proton therapy. The results positively compare with previous existing literature in the thorax cases, that are usually the most difficult to calculate by fast algorithms.

Abstract Background Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure. This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[11C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification. Results For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUVmean, SULpeak, SUVmin, SULpeakprod-surface-area, SUVmeanprod-sphericity, surface mean SUV 3, SULpeakprod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features. Conclusions The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.

Natural phenomena and mechanisms have always intrigued humans, inspiring the design of effective solutions for real-world problems. Indeed, fascinating processes occur in nature, giving rise to an ever-increasing scientific interest. In everyday life, the amount of heterogeneous biomedical data is increasing more and more thanks to the advances in image acquisition modalities and high-throughput technologies. The automated analysis of these large-scale datasets creates new compelling challenges for data-driven and model-based computational methods. The application of intelligent algorithms, which mimic natural phenomena, is emerging as an effective paradigm for tackling complex problems, by considering the unique challenges and opportunities pertaining to biomedical images. Therefore, the principal contribution of computer science research in life sciences concerns the proper combination of diverse and heterogeneous datasets—i.e., medical imaging modalities (considering also radiomics approaches), Electronic Health Record engines, multi-omics studies, and real-time monitoring—to provide a comprehensive clinical knowledge. In this paper, the state-of-the-art of nature-inspired medical image analysis methods is surveyed, aiming at establishing a common platform for beneficial exchanges among computer scientists and clinicians. In particular, this review focuses on the main natureinspired computational techniques applied to medical image analysis tasks, namely: physical processes, bio-inspired mathematical models, Evolutionary Computation, Swarm Intelligence, and neural computation. These frameworks, tightly coupled with Clinical Decision Support Systems, can be suitably applied to every phase of the clinical workflow. We show that the proper combination of quantitative imaging and healthcare informatics enables an in-depth understanding of molecular processes that can guide towards personalised patient care.

Summary Radiotherapy techniques deliver ionizing radiations (X‐rays, photons, electrons, protons, etc.) inside cancerous tissues to kill the abnormal cells. Radiotherapy‐related activities such as the optimization of the therapeutic radiation dose to patients, workers' radioprotection, linear accelerator commissioning, quality assurance processes and technical innovations of linear accelerators are strongly based on the ability to predict the dose distribution. Monte Carlo based simulations are so far the most accurate tool for the calculation of dosimetric parameters, with the drawback of requiring extensive computing resources to achieve statistically meaningful results in a reasonable time frame. In the last years, advanced cancer treatment clinical and research communities have used e‐Infrastructures to support their activities. The present paper reports on the development of a computing facility for helping clinical researchers in using modern R&E networking and distributed computing and storage resources for a new radiotherapy technique: the Intra‐Operative Electron Radiotherapy. The web application developed addresses some technical and clinical needs as the design of linear accelerators' collimation systems and the optimization of the patient therapeutic dose distribution. Copyright © 2014 John Wiley & Sons, Ltd.

Fibroids are benign tumors growing in the uterus. Most of fibroids do not require treatment unless they are causing symptoms. Traditional surgery treatments, like myomectomy and hysterectomy, are very invasive therapeutic approaches which not always preserves reproductive potential of the woman. MRgFUS, performed with Insightec ExAblate 2100 equipment, is a new and noninvasive technique for uterine fibroids treatment, not requiring hospitalization and recovery time for patients. An initial assessment of MRgFUS treatment is made by computing the ablated volume of uterine fibroid. In this paper a semi-automatic approach, based on region-growing segmentation technique, is proposed. The implemented approach gives a quantitative and qualitative evaluation of the treatment providing the volume and the three-dimensional (3D) model of the treated fibroid area. Considering these characteristics, the proposed approach can be used as a tool to integrate the information used by a Medical Decision Support System (MDSS). As step in the MRgFUS treatment evaluation, the achieved results improve the current methodology based on the manual uterine fibroid ROT segmentation.