Machine Learning in Nuclear Medicine: Part 2-Neural Networks and Clinical Aspects

Reporting guidelines in medical artificial intelligence: a systematic review and meta-analysis

BACKGROUND

The field of Artificial Intelligence (AI) holds transformative potential in medicine. However, the lack of universal reporting guidelines poses challenges in ensuring the validity and reproducibility of published research studies in this field.

METHODS

Based on a systematic review of academic publications and reporting standards demanded by both international consortia and regulatory stakeholders as well as leading journals in the fields of medicine and medical informatics, 26 reporting guidelines published between 2009 and 2023 were included in this analysis. Guidelines were stratified by breadth (general or specific to medical fields), underlying consensus quality, and target research phase (preclinical, translational, clinical) and subsequently analyzed regarding the overlap and variations in guideline items.

RESULTS

AI reporting guidelines for medical research vary with respect to the quality of the underlying consensus process, breadth, and target research phase. Some guideline items such as reporting of study design and model performance recur across guidelines, whereas other items are specific to particular fields and research stages.

CONCLUSIONS

Our analysis highlights the importance of reporting guidelines in clinical AI research and underscores the need for common standards that address the identified variations and gaps in current guidelines. Overall, this comprehensive overview could help researchers and public stakeholders reinforce quality standards for increased reliability, reproducibility, clinical validity, and public trust in AI research in healthcare. This could facilitate the safe, effective, and ethical translation of AI methods into clinical applications that will ultimately improve patient outcomes.

Fit of biokinetic data in molecular radiotherapy: a machine learning approach

BACKGROUND

In literature are reported different analytical methods (AM) to choose the proper fit model and to fit data of the time-activity curve (TAC). On the other hand, Machine Learning algorithms (ML) are increasingly used for both classification and regression tasks. The aim of this work was to investigate the possibility of employing ML both to classify the most appropriate fit model and to predict the area under the curve (τ).

METHODS

Two different ML systems have been developed for classifying the fit model and to predict the biokinetic parameters. The two systems were trained and tested with synthetic TACs simulating a whole-body Fraction Injected Activity for patients affected by metastatic Differentiated Thyroid Carcinoma, administered with [131I]I-NaI. Test performances, defined as classification accuracy (CA) and percentage difference between the actual and the estimated area under the curve (Δτ), were compared with those obtained using AM varying the number of points (N) of the TACs. A comparison between AM and ML were performed using data of 20 real patients.

RESULTS

As N varies, CA remains constant for ML (about 98%), while it improves for F-test (from 62 to 92%) and AICc (from 50 to 92%), as N increases. With AM, [Formula: see text] can reach down to - 67%, while using ML [Formula: see text] ranges within ± 25%. Using real TACs, there is a good agreement between τ obtained with ML system and AM.

CONCLUSIONS

The employing of ML systems may be feasible, having both a better classification and a better estimation of biokinetic parameters.

An Artificial Intelligence System for Optimizing Radioactive Iodine Therapy Dosimetry

Thyroid cancer, specifically differentiated thyroid carcinoma (DTC), is one of the most prevalent endocrine malignancies worldwide. Radioactive iodine therapy (RAIT) using I-131 has been a standard-of-care approach for DTC due to its ability to ablate remnant thyroid disease following surgery, thus reducing the risk of recurrence. It is also used for the treatment of iodine-avid metastases. RAIT dosimetry can be employed to determine the optimal treatment dose of I-131 to effectively treat cancer cells while safeguarding against undesirable radiation effects such as bone marrow toxicity or radiation pneumonitis. Conventional dosimetry protocols for RAIT, however, are complex and time-consuming, involving multiple days of imaging and blood sampling. This study explores the use of Artificial Intelligence (AI) in simplifying and optimizing RAIT. A retrospective analysis was conducted on 83 adult patients with DTC who underwent RAIT dosimetry at our institution between 1996 and 2023. The conventional MIRD-based dosimetry protocol involved imaging and blood sampling at 4, 24, 48, 72, and 96 h post-administration of a tracer activity of I-131. An AI system based on a deep-learning neural network was developed to predict the maximum permissible activity (MPA) for RAIT using only the data obtained from the initial 4, 24, and 48 h time points. The AI system predicted the MPA values with high accuracy, showing no significant difference compared to the results obtained from conventional MIRD-based analysis utilizing a paired t-test (p = 0.351, 95% CI). The developed AI system offers the potential to streamline the dosimetry process, reducing the number of imaging and blood sampling sessions while also optimizing resource allocation. Additionally, the AI approach can uncover underlying relationships in data that were previously unknown. Our findings suggest that AI-based dosimetry may be a promising method for patient-specific treatment planning in differentiated thyroid carcinoma, representing a step towards applying precision medicine for thyroid cancer. Further validation and implementation studies are warranted to assess the clinical applicability of the AI system.

Brain PET and Cerebrovascular Disease

Cerebrovascular disease encompasses a broad spectrum of diseases such as stroke, hemorrhage, and cognitive decline associated with vascular narrowing, obstruction, rupture, and inflammation, among other issues. Recent advances in hardware and software have led to improvements in brain PET. Although still in its infancy, machine learning using convolutional neural networks is gaining traction in this area, often with a focus on providing high-quality images with reduced noise using a shorter acquisition time or less radiation exposure for the patient.

Automated Detection of Poor-Quality Scintigraphic Images Using Machine Learning

Objective  In the present study, we have used machine learning algorithm to accomplish the task of automated detection of poor-quality scintigraphic images. We have validated the accuracy of our machine learning algorithm on 99m Tc-methyl diphosphonate ( 99m Tc-MDP) bone scan images. Materials and Methods  Ninety-nine patients underwent 99mTC-MDP bone scan acquisition twice at two different acquisition speeds, one at low speed and another at double the speed of the first scan, with patient lying in the same position on the scan table. The low-speed acquisition resulted in good-quality images and the high-speed acquisition resulted in poor-quality images. The principal component analysis (PCA) of all the images was performed and the first 32 principal components (PCs) were retained as feature vectors of the image. These 32 feature vectors of each image were used for the classification of images into poor or good quality using machine learning algorithm (multivariate adaptive regression splines [MARS]). The data were split into two sets, that is, training set and test set in the ratio of 60:40. Hyperparameter tuning of the model was done in which five-fold cross-validation was performed. Receiver operator characteristic (ROC) analysis was used to select the optimal model using the largest value of area under the ROC curve. Sensitivity, specificity, and accuracy for the classification of poor- and good-quality images were taken as metrics for the performance of the algorithm. Result  Accuracy, sensitivity, and specificity of the model in classifying poor-quality and good-quality images were 93.22, 93.22, and 93.22%, respectively, for the training dataset and 86.88, 80, and 93.7%, respectively, for the test dataset. Conclusion  Machine learning algorithms can be used to classify poor- and good-quality images with good accuracy (86.88%) using 32 PCs as the feature vector and MARS as the classification model.

A role for artificial intelligence in molecular imaging of infection and inflammation

The detection of occult infections and low-grade inflammation in clinical practice remains challenging and much depending on readers’ expertise. Although molecular imaging, like [¹⁸F]FDG PET or radiolabeled leukocyte scintigraphy, offers quantitative and reproducible whole body data on inflammatory responses its interpretation is limited to visual analysis. This often leads to delayed diagnosis and treatment, as well as untapped areas of potential application. Artificial intelligence (AI) offers innovative approaches to mine the wealth of imaging data and has led to disruptive breakthroughs in other medical domains already. Here, we discuss how AI-based tools can improve the detection sensitivity of molecular imaging in infection and inflammation but also how AI might push the data analysis beyond current application toward predicting outcome and long-term risk assessment.

Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation

Artificial intelligence (AI) will change the face of nuclear medicine and molecular imaging as it will in everyday life. In this review, we focus on the potential applications of AI in the field, both from a physical (radiomics, underlying statistics, image reconstruction and data analysis) and a clinical (neurology, cardiology, oncology) perspective. Challenges for transferability from research to clinical practice are being discussed as is the concept of explainable AI. Finally, we focus on the fields where challenges should be set out to introduce AI in the field of nuclear medicine and molecular imaging in a reliable manner.

DblurDoseNet: A deep residual learning network for voxel radionuclide dosimetry compensating for single-photon emission computerized tomography imaging resolution

PURPOSE

Current methods for patient-specific voxel-level dosimetry in radionuclide therapy suffer from a trade-off between accuracy and computational efficiency. Monte Carlo (MC) radiation transport algorithms are considered the gold standard for voxel-level dosimetry but can be computationally expensive, whereas faster dose voxel kernel (DVK) convolution can be suboptimal in the presence of tissue heterogeneities. Furthermore, the accuracies of both these methods are limited by the spatial resolution of the reconstructed emission image. To overcome these limitations, this paper considers a single deep convolutional neural network (CNN) with residual learning (named DblurDoseNet) that learns to produce dose-rate maps while compensating for the limited resolution of SPECT images.

METHODS

We trained our CNN using MC-generated dose-rate maps that directly corresponded to the true activity maps in virtual patient phantoms. Residual learning was applied such that our CNN learned only the difference between the true dose-rate map and DVK dose-rate map with density scaling. Our CNN consists of a 3D depth feature extractor followed by a 2D U-Net, where the input was 11 slices (3.3 cm) of a given Lu-177 SPECT/CT image and density map, and the output was the dose-rate map corresponding to the center slice. The CNN was trained with nine virtual patient phantoms and tested on five different phantoms plus 42 SPECT/CT scans of patients who underwent Lu-177 DOTATATE therapy.

RESULTS

When testing on virtual patient phantoms, the lesion/organ mean dose-rate error and the normalized root mean square error (NRMSE) relative to the ground truth of the CNN method was consistently lower than DVK and MC, when applied to SPECT images. Compared to DVK/MC, the average improvement for the CNN in mean dose-rate error was 55%/53% and 66%/56%; and in NRMSE was 18%/17% and 10%/11% for lesion and kidney regions, respectively. Line profiles and dose-volume histograms demonstrated compensation for SPECT resolution effects in the CNN-generated dose-rate maps. The ensemble noise standard deviation, determined from multiple Poisson realizations, was improved by 21%/27% compared to DVK/MC. In patients, potential improvements from CNN dose-rate maps compared to DVK/MC were illustrated qualitatively, due to the absence of ground truth. The trained residual CNN took about 30 s on a single GPU (Tesla V100) to generate a 512 × 512 × 130 dose-rate map for a patient.

CONCLUSION

The proposed residual CNN, trained using phantoms generated from patient images, has potential for real-time patient-specific dosimetry in clinical treatment planning due to its demonstrated improvement in accuracy, resolution, noise, and speed over the DVK/MC approaches.

Evidence-Based Artificial Intelligence in Medical Imaging

Artificial intelligence (AI) in medical imaging is in its infancy. However, ongoing advances in hardware and software as well as increasing access to ever-expanding datasets for training, validation, and testing purposes are likely to make AI an increasingly prevalent and powerful tool. Of course issues, such as the need to protect the privacy of sensitive health data, remain; nevertheless, it is likely the average imager will need to develop an evidence-based approach to assessing AI in medical imaging. We hope this article will provide insight into just how this can be conducted by applying 5 simple questions, specifically: (1) Who was in the training sample, (2) How was the model trained, (3) How reliable is the algorithm, (4) How was the model validated, and (5) How useable is the algorithm.

Clinical Applications of Artificial Intelligence in Positron Emission Tomography of Lung Cancer

The ability of a computer to perform tasks normally requiring human intelligence or artificial intelligence (AI) is not new. However, until recently, practical applications in medical imaging were limited, especially in the clinic. With advances in theory, microelectronic circuits, and computer architecture as well as our ability to acquire and access large amounts of data, AI is becoming increasingly ubiquitous in medical imaging. Of particular interest to our community, radiomics tries to identify imaging features of specific pathology that can represent, for example, the texture or shape of a region in the image. This is conducted based on a review of mathematical patterns and pattern combinations. The difficulty is often finding sufficient data to span the spectrum of disease heterogeneity because many features change with pathology as well as over time and, among other issues, data acquisition is expensive. Although we are currently in the early days of the practical application of AI to medical imaging, research is ongoing to integrate imaging, molecular pathobiology, genetic make-up, and clinical manifestations to classify patients into subgroups for the purpose of precision medicine, or in other words, predicting a priori treatment response and outcome. Lung cancer is a functionally and morphologically heterogeneous disease. Positron emission tomography (PET) is an imaging technique with an important role in the precision medicine of patients with lung cancer that helps predict early response to therapy and guides the selection of appropriate treatment. Although still in its infancy, early results suggest that the use of AI in PET of lung cancer has promise for the detection, segmentation, and characterization of disease as well as for outcome prediction.

Exploratory Assessment of K-means Clustering to Classify 18F-Flutemetamol Brain PET as Positive or Negative

RATIONALE

We evaluated K-means clustering to classify amyloid brain PETs as positive or negative.

PATIENTS AND METHODS

Sixty-six participants (31 men, 35 women; age range, 52-81 years) were recruited through a multicenter observational study: 19 cognitively normal, 25 mild cognitive impairment, and 22 dementia (11 Alzheimer disease, 3 subcortical vascular cognitive impairment, and 8 Parkinson-Lewy Body spectrum disorder). As part of the neurocognitive and imaging evaluation, each participant had an 18F-flutemetamol (Vizamyl, GE Healthcare) brain PET. All studies were processed using Cortex ID software (General Electric Company, Boston, MA) to calculate SUV ratios in 19 regions of interest and clinically interpreted by 2 dual-certified radiologists/nuclear medicine physicians, using MIM software (MIM Software Inc, Cleveland, OH), blinded to the quantitative analysis, with final interpretation based on consensus. K-means clustering was retrospectively used to classify the studies from the quantitative data.

RESULTS

Based on clinical interpretation, 46 brain PETs were negative and 20 were positive for amyloid deposition. Of 19 cognitively normal participants, 1 (5%) had a positive 18F-flutemetamol brain PET. Of 25 participants with mild cognitive impairment, 9 (36%) had a positive 18F-flutemetamol brain PET. Of 22 participants with dementia, 10 (45%) had a positive 18F-flutemetamol brain PET; 7 of 11 participants with Alzheimer disease (64%), 1 of 3 participants with vascular cognitive impairment (33%), and 2 of 8 participants with Parkinson-Lewy Body spectrum disorder (25%) had a positive 18F-flutemetamol brain PET. Using clinical interpretation as the criterion standard, K-means clustering (K = 2) gave sensitivity of 95%, specificity of 98%, and accuracy of 97%.

CONCLUSIONS

K-means clustering may be a powerful algorithm for classifying amyloid brain PET.