Joint EANM/SNMMI guideline on radiomics in nuclear medicine : Jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council

PURPOSE

The purpose of this guideline is to provide comprehensive information on best practices for robust radiomics analyses for both hand-crafted and deep learning-based approaches.

METHODS

In a cooperative effort between the EANM and SNMMI, we agreed upon current best practices and recommendations for relevant aspects of radiomics analyses, including study design, quality assurance, data collection, impact of acquisition and reconstruction, detection and segmentation, feature standardization and implementation, as well as appropriate modelling schemes, model evaluation, and interpretation. We also offer an outlook for future perspectives.

CONCLUSION

Radiomics is a very quickly evolving field of research. The present guideline focused on established findings as well as recommendations based on the state of the art. Though this guideline recognizes both hand-crafted and deep learning-based radiomics approaches, it primarily focuses on the former as this field is more mature. This guideline will be updated once more studies and results have contributed to improved consensus regarding the application of deep learning methods for radiomics. Although methodological recommendations in the present document are valid for most medical image modalities, we focus here on nuclear medicine, and specific recommendations when necessary are made for PET/CT, PET/MR, and quantitative SPECT.

Validation of an Automatic Tagging System for Identifying Respiratory and Hemodynamic Deterioration Events in the Intensive Care Unit

Objectives

Predictive models for critical events in the intensive care unit (ICU) might help providers anticipate patient deterioration. At the heart of predictive model development lies the ability to accurately label significant events, thereby facilitating the use of machine learning and similar strategies. We conducted this study to establish the validity of an automated system for tagging respiratory and hemodynamic deterioration by comparing automatic tags to tagging by expert reviewers.

Methods

This retrospective cohort study included 72,650 unique patient stays collected from Electronic Medical Records of the University of Massachusetts’ eICU. An enriched subgroup of stays was manually tagged by expert reviewers. The tags generated by the reviewers were compared to those generated by an automated system.

Results

The automated system was able to rapidly and efficiently tag the complete database utilizing available clinical data. The overall agreement rate between the automated system and the clinicians for respiratory and hemodynamic deterioration tags was 89.4% and 87.1%, respectively. The automatic system did not add substantial variability beyond that seen among the reviewers.

Conclusions

We demonstrated that a simple rule-based tagging system could provide a rapid and accurate tool for mass tagging of a compound database. These types of tagging systems may replace human reviewers and save considerable resources when trying to create a validated, labeled database used to train artificial intelligence algorithms. The ability to harness the power of artificial intelligence depends on efficient clinical validation of targeted conditions; hence, these systems and the methodology used to validate them are crucial.

A plaster containing DHEP and heparin for mild to moderate contusions and sprains with haematoma: a double-blind randomized study

OBJECTIVE

This prospective, randomized, double-blind, three-arm study was performed to investigate the efficacy of a medicated plaster containing the combination of diclofenac epolamine (DHEP) 180 mg and heparin 5600 IU in the treatment of unilateral blunt soft tissue injuries involving the upper or lower limb, complicated by severe local haematoma.

RESEARCH DESIGN AND METHODS

Patients with mild-to-moderate injuries complicated by local haematoma (< or =140 cm(2)) were included and randomly treated once daily with plasters containing DHEP/heparin, DHEP only, or placebo. Plasters were applied for at least 12 hours daily for 10 consecutive days.

MAIN OUTCOME MEASURES

The time to complete haematoma dissolution was the primary efficacy endpoint; secondary endpoints were spontaneous pain reduction, pain on movement, muscle swelling and use of rescue analgesia.

RESULTS

A total of 185 patients (90 males and 95 females, aged 18-80 years) were evaluated for efficacy. Baseline clinical and demographic characteristics were similar across the treatment groups. The time to complete haematoma dissolution was significantly shorter with the DHEP/heparin plaster compared with both the DHEP and placebo plasters (p < 0.05). Patients in the DHEP/heparin group had a 60% probability of achieving complete haematoma dissolution within the 10-day treatment period compared with patients receiving either DHEP or placebo plasters. Patient-rated reductions in pain on movement were significantly (p < 0.05) greater in the two active treatment groups compared with placebo. Overall, the DHEP/heparin, DHEP and placebo plasters were well-tolerated. While a reliance on patient self-reporting had the potential to limit the usefulness of some data obtained in this study, the investigators accounted for this accordingly.

CONCLUSIONS

The plaster formulation combining DHEP and heparin relieves pain and induces faster dissolution of superficial haematomas, and may therefore contribute to a more rapid and complete recovery.

Development of an inactivated vaccine against infectious laryngotracheitis (ILT)--serological and protection studies

The strain of infectious laryngotracheitis (ILT virus utilised for these vaccine-development studies was isolated from an outbreak of the disease in Hungary. Inactivating agents tested included beta-propio-lactone, methyleneimine, ethyleneimine EI and formalin. ILT virus preparations inactivated with EI appeared to be the most antigenic when inoculated into chickens in the absence of adjuvant. For formulation of a trial oil-emulsion ILT vaccine for experimentation, ILT virus inactivated with 1200 mug/ml of EI was mixed with an equal volume of 50% incomplete Freund's adjuvant and then homogenised. Experimental vaccination of chickens with inactivated ILT vaccine elicited satisfactory serological response and protection to challenge both under laboratory and field conditions. Although only minor increases in antibody titres could be achieved by repeated vaccination with inactivated ILT vaccine at 2 to 5 weeks after primary vaccination at 10-weeks-old with attenuated or inactivated ILT vaccines, the protection conferred by vaccination with a single dose of the trial inactivated ILT vaccine appeared to be effective for at least 12 months. Hence, there would appear to be potential for inactivated-ILT vaccines in control of ILT, especially on sites that are regularly affected by this infection.

[The gastro-intestinal effects of portal hypertension. Role of highly selective vagotomy. Experimental study in the rat (author's transl)]

Portal hypertension was obtained by portal ligature in the rat by an original procedure. Hemodynamic and pathological studies were performed at the end of the 4th postoperative month. Portal hypertension causes macroscopic and histological lesions in particular in the stomach and small intestine. The lesions observed were superficial desquamation, interstitial oedema, submucosal fibrosis, ulcers, and superficial or total necrosis of the intestine. Splenic fibrosis with congestion of the medullary sinuses is usual. A collateral circulation towards the liver and caval system develops rapidly. We never observed oesophageal varices. The main cause of splanchnic modifications was vascular stasis to which should perhaps be added humoral changes. Highly selective vagotomy does not protect the splanchnic area against lesions induced by portal ligature.