Robust machine learning challenge: An AIFM multicentric competition to spread knowledge, identify common pitfalls and recommend best practice.

Purpose: A novel and unconventional approach to a machine learning challenge was designed to spread knowledge, identify robust methods and highlight potential pitfalls about machine learning within the Medical Physics community.

Methods: A public dataset comprising 41 radiomic features and 535 patients was employed to assess the potential of radiomics in distinguishing between primary lung tumors and metastases. Each participant developed two classification models using: (i) all features (base model); (ii) only robust features (robust model).

Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study.

Background: To address the numerous unmeet clinical needs, in recent years several Machine Learning models applied to medical images and clinical data have been introduced and developed. Even when they achieve encouraging results, they lack evolutionary progression, thus perpetuating their status as autonomous entities. We postulated that different algorithms which have been proposed in the literature to address the same diagnostic task, can be aggregated to enhance classification performance.

Cutaneous squamous cell carcinoma of the lip successfully treated with rhenium-188 brachytherapy.

Cutaneous squamous cell carcinoma (SCC) is the second most common form of skin cancer. In most cases, non-invasive SCC has a good prognosis and is curable by surgical resection. Nevertheless, a small percentage of patients pose specific management problems due to the technical difficulty of maintaining function and aesthetics because of the size or location of the tumor.

Applications of Artificial Intelligence and Radiomics in Molecular Hybrid Imaging and Theragnostics for Neuro-Endocrine Neoplasms (NENs).

Nuclear medicine has acquired a crucial role in the management of patients with neuroendocrine neoplasms (NENs) by improving the accuracy of diagnosis and staging as well as their risk stratification and personalized therapies, including radioligand therapies (RLT). Artificial intelligence (AI) and radiomics can enable physicians to further improve the overall efficiency and accuracy of the use of these tools in both diagnostic and therapeutic settings by improving the prediction of the tumor grade, differential diagnosis from other malignancies, assessment of tumor behavior and aggressiveness, and prediction of treatment response. This systematic review aims to describe the state-of-the-art AI and radiomics applications in the molecular imaging of NENs.

Radiomics and artificial intelligence in prostate cancer: new tools for molecular hybrid imaging and theragnostics.

In prostate cancer (PCa), the use of new radiopharmaceuticals has improved the accuracy of diagnosis and staging, refined surveillance strategies, and introduced specific and personalized radioreceptor therapies. Nuclear medicine, therefore, holds great promise for improving the quality of life of PCa patients, through managing and processing a vast amount of molecular imaging data and beyond, using a multi-omics approach and improving patients' risk-stratification for tailored medicine. Artificial intelligence (AI) and radiomics may allow clinicians to improve the overall efficiency and accuracy of using these "big data" in both the diagnostic and theragnostic field: from technical aspects (such as semi-automatization of tumor segmentation, image reconstruction, and interpretation) to clinical outcomes, improving a deeper understanding of the molecular environment of PCa, refining personalized treatment strategies, and increasing the ability to predict the outcome.

Artificial intelligence applications in medical imaging: A review of the medical physics research in Italy.

Purpose: To perform a systematic review on the research on the application of artificial intelligence (AI) to imaging published in Italy and identify its fields of application, methods and results.

Materials And Methods: A Pubmed search was conducted using terms Artificial Intelligence, Machine Learning, Deep learning, imaging, and Italy as affiliation, excluding reviews and papers outside time interval 2015-2020. In a second phase, participants of the working group AI4MP on Artificial Intelligence of the Italian Association of Physics in Medicine (AIFM) searched for papers on AI in imaging.

Impact of missing attenuation and scatter corrections on Tc-MAA SPECT 3D dosimetry for liver radioembolization using the patient relative calibration methodology: A retrospective investigation on clinical images.

Purpose: To investigate the clinical implication of performing pre-treatment dosimetry for Y-microspheres liver radioembolization on Tc-MAA SPECT images reconstructed without attenuation or scatter correction and quantified with the patient relative calibration methodology.

Methods: Twenty-five patients treated with SIR-Spheres at Istituto Europeo di Oncologia and 31 patients treated with TheraSphere at Istituto Nazionale Tumori were considered. For each acquired Tc-MAA SPECT, four reconstructions were performed: with attenuation and scatter correction (AC_SC), only attenuation (AC_NoSC), only scatter (NoAC_SC) and without corrections (NoAC_NoSC).

The Italian multicentre dosimetric study for lesion dosimetry in Ra therapy of bone metastases: Calibration protocol of gamma cameras and patient eligibility criteria.

Purpose: The aims of this work were to explore patient eligibility criteria for dosimetric studies in Ra therapy and evaluate the effects of differences in gamma camera calibration procedures into activity quantification.

Methods: Calibrations with Ra were performed with four gamma cameras (3/8-inch crystal) acquiring planar static images with double-peak (82 and 154keV, 20% wide) and MEGP collimator. The sensitivity was measured in air by varying activity, source-detector distance, and source diameter.

Impact of SPECT corrections on 3D-dosimetry for liver transarterial radioembolization using the patient relative calibration methodology.

Purpose: Many centers aim to plan liver transarterial radioembolization (TARE) with dosimetry, even without CT-based attenuation correction (AC), or with unoptimized scatter correction (SC) methods. This work investigates the impact of presence vs absence of such corrections, and limited spatial resolution, on 3D dosimetry for TARE.

Methods: Three voxelized phantoms were derived from CT images of real patients with different body sizes.

A case report of image-based dosimetry of bone metastases with Alpharadin ((223)Ra-dichloride) therapy: inter-fraction variability of absorbed dose and follow-up.

A 70-year-old man affected by bone metastases from castration resistant prostate cancer underwent Alpharadin ((223)Ra-dichloride) therapy (6 administrations of 50 kBq per kg i.v., once every 4 weeks).

Dosimetry of bone metastases in targeted radionuclide therapy with alpha-emitting (223)Ra-dichloride.

Purpose: Ra-dichloride is an alpha-emitting radiopharmaceutical used in the treatment of bone metastases from castration-resistant prostate cancer. Image-based dosimetric studies remain challenging because the emitted photons are few. The aim of this study was to implement a methodology for in-vivo quantitative planar imaging, and to assess the absorbed dose to lesions using the MIRD approach.