ABSTRACT
BACKGROUND: 18F-FDG PET/CT imaging represents the most important functional imaging method in oncology. European Society of Medical Oncology and the National Comprehensive Cancer Network guidelines defined a crucial role of 18F-FDG PET/CT imaging for local/locally advanced breast cancer. The application of artificial intelligence on PET images might potentially contributes in the field of precision medicine. OBJECTIVE: This review aims to summarize the clinical indications and limitations of PET imaging for comprehensive artificial intelligence in relation to breast cancer subtype, hormone receptor status, proliferation rate, and lymphonodal (LN)/distant metastatic spread, based on recent literature. METHODS: A literature search of the Pubmed/Scopus/Google Scholar/Cochrane/EMBASE databases was carried out, searching for articles on the use of artificial intelligence and PET in breast tumors. The search was updated from January 2010 to October 2021 and was limited to original articles published in English and about humans. A combination of the search terms "artificial intelligence", "breast cancer", "breast tumor", "PET", "Positron emission tomography", "PET/CT", "PET/MRI", "radiomic"," texture analysis", "machine learning", "deep learning" was used. RESULTS: Twenty-three articles were selected following the PRISMA criteria from 139 records obtained from the Pubmed/Scopus/Google Scholar/Cochrane/EMBASE databases according to our research strategy. The QUADAS of 30 full-text articles assessed reported seven articles that were excluded for not being relevant to population and outcomes and/or for lower level of evidence. The majority of papers were at low risk of bias and applicability. The articles were divided per topic, such as the value of PET in the staging and re-staging of breast cancer patients, including new radiopharmaceuticals and simultaneous PET/MRI. CONCLUSION: Despite the current role of AI in this field remains still undefined, several applications for PET/CT imaging are under development, with some preliminary interesting results particularly focused on the staging phase that might be clinically translated after further validation studies.
Subject(s)
Fluorodeoxyglucose F18 , Neoplasms , Humans , Positron-Emission Tomography , Positron Emission Tomography Computed Tomography/methods , Artificial Intelligence , IntelligenceABSTRACT
BACKGROUND/AIM: At present, multidisciplinary tumor boards (MDTB) are considered best practice in oncology. However, web-based virtualization of MDTB may increase participation in meetings, the number of cases discussed, and adherence to guidelines, deliver better treatment, and eventually improve outcomes for patients with prostate cancer. PATIENTS AND METHODS: This is an observational study focused on exploring the structuring process and implementing a multi-institutional virtual MDTB in Sicily, Italy. Other endpoints included the analysis of cooperation between participants, adherence to guidelines, patient outcomes, and patient satisfaction. RESULTS: Overall, 126 patients were referred to the virtual MDTB for a total of 302 cases discussed in an 18-month period. Nearly 45% of cases were referred from general hospitals or tertiary centers, 38% from comprehensive cancer centers, and only 17% from academic ones. Most health professional participants (95%) reported eliminating geographical barriers and consequently reducing costs and saving time as key advantages of virtual meetings over face-to-face ones. Using a specifically designed platform for virtual MDTBs was another excellent point, especially to geolocate clinical trials and time-lapse data storage. The majority of referred patients had stage T 3-4 prostate cancer (79%). Overall, 71% of proposals discussed were approved unchanged, while 19% changed after the virtual MDTB discussion. Debated points were mostly radiologic, surgical, medical, or radiation treatment-related issues. In particular, the prescriptive appropriateness of positron emission tomography with 68Ga-prostatic specific membrane antigen, newer drugs, radiation versus surgical approach, stage T3-4 cases, and adjuvant therapy represented the most debated issues. The proposed diagnostic and/or therapeutic options were controlled for adherence to the guidelines and/or updated scientific evidence. Overall, 98% of approved proposals and changes were in line with the guidelines. Overall, most participants felt virtual MDTB was very useful and case discussions led to a major change of strategy in 19% of cases. CONCLUSION: Virtual MDTBs are a very useful way to achieve best management of prostate cancer while saving time and fostering cooperation.
Subject(s)
Prostatic Neoplasms , Male , Humans , Prostatic Neoplasms/diagnosis , Prostatic Neoplasms/therapy , Prostatic Neoplasms/pathology , Medical Oncology , Hospitals , Prospective Studies , ItalyABSTRACT
PURPOSE: In DTC patients, 131-radioiodine therapy has routinely been used for many years for thyroid remnant ablation after thyroid surgery. To date, two different strategies can be used to achieve sufficient TSH stimulation on thyroid remnant: (I) Levo-thyroxine withdrawal or (II) rhTSH stimulation. The aim of our study was to compare the abdominal absorbed dose ratio between differentiated thyroid cancer patients who underwent thyroid remnant ablation after either L-T4 withdrawal or rhTSH stimulation. METHODS: We reviewed the records of 63 patients affected by differentiated thyroid cancer. All patients underwent thyroid remnant ablation after either L-T4 withdrawal or rhTSH stimulation. A post-therapy whole-body scan was obtained 5 days after 131-radioiodine therapy. Qualitative and quantitative image analysis was performed. Quantitative analysis was performed by drawing seven regions of interest on the abdomen (anterior and posterior views) to estimate both the activity ratio (AR) and absorbed dose ratio (DR) obtained in patients treated in hypothyroidism or after rhTSH stimulation. RESULTS: The values of the activity and absorbed dose ratios obtained on each abdomen region (liver, stomach, ascending colon, transverse colon, descending colon, rectum, and small intestine) were always higher in patients treated after L-T4 withdrawal than after rhTSH stimulation with p-values of 0.000, 0.000, 0.001, 0.000, 0.022, 0.007, and 0.002, respectively. CONCLUSIONS: DTC patients treated with 131-radioiodine after rhTSH stimulation have lower abdominal radioiodine activity than hypothyroid patients. Our data could be of practical relevance in terms of patient management. The potential impact on rare radioiodine-related gastrointestinal side effects is to be established in specifically designed prospective studies.
Subject(s)
Abdomen/radiation effects , Adenocarcinoma , Iodine Radioisotopes/therapeutic use , Thyroid Neoplasms , Thyrotropin/administration & dosage , Thyroxine/administration & dosage , Adenocarcinoma/drug therapy , Adenocarcinoma/metabolism , Adenocarcinoma/radiotherapy , Adenocarcinoma/surgery , Drug Administration Schedule , Female , Gastrointestinal Absorption/radiation effects , Humans , Male , Middle Aged , Neoplasm, Residual , Organs at Risk , Radiation Injuries/etiology , Radiation Injuries/prevention & control , Radiotherapy Dosage , Radiotherapy, Adjuvant , Recombinant Proteins/administration & dosage , Recombinant Proteins/pharmacokinetics , Retrospective Studies , Thyroid Neoplasms/drug therapy , Thyroid Neoplasms/metabolism , Thyroid Neoplasms/radiotherapy , Thyroid Neoplasms/surgery , Thyroidectomy , Thyrotropin/pharmacokinetics , Thyroxine/pharmacokinetics , Treatment Outcome , Withholding TreatmentABSTRACT
PURPOSE: To evaluate the utility of serum and urinary neutrophil gelatinase-associated lipocalin (NGAL) in depicting an event of contrast material-induced nephropathy (CIN) in patients who received iodinated contrast media, gadoterate meglumine, or radiopharmaceutical technetium-99m ((99m)Tc) and to evaluate the protective effect exerted by isotonic saline infusion, sodium bicarbonate administration, or N-acetylcysteine administration. MATERIALS AND METHODS: Institutional ethics committee approval was given, and informed consent was obtained. One hundred twenty patients were enrolled in a prospective study and divided into three groups: iomeprol group, magnetic resonance (MR) imaging group (gadoterate meglumine), and renal scintigraphy group ((99m)Tc). They randomly received N-acetylcysteine, physiologic saline, or sodium bicarbonate. Receiver operating characteristic (ROC) analysis, Kaplan-Meier curves, and Cox proportional hazard regression analysis were used. RESULTS: In the MR imaging and renal scintigraphy groups, there were significant changes in serum creatinine and NGAL levels, and there were no cases of CIN. In the iomeprol group, an early rise in NGAL was found, while serum creatinine level changes occurred 24 hours after contrast material administration. At ROC analysis, NGAL showed high sensitivity and specificity (serum NGAL: area under the curve, 0.995; 95% confidence interval [CI]: 0.868, 0.992; urinary NGAL: area under the curve, 0.992; 95% CI: 0.925, 1.000) in identifying CIN 8 hours after iomeprol administration. Regression analysis showed that NGAL independently predicted CIN. Administration of N-acetylcysteine, sodium bicarbonate, or physiologic saline did not influence NGAL level. CONCLUSION: NGAL depicted CIN in patients who received iodinated contrast material within 8 hours of contrast material administration. SUPPLEMENTAL MATERIAL: http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.12120578/-/DC1.