In Frontiers in oncology

PURPOSE : Deep-learning effectively predicts dose distributions in knowledge-based radiotherapy planning. Using anatomical information that includes a structure map and computed tomography (CT) data as input has been proven to work well. The minimum distance from each voxel in normal structures to planning target volume (DPTV) closely affects each voxel's dose. In this study, we combined DPTV and anatomical information as input for a deep-learning-based dose-prediction network to improve performance.

MATERIALS AND METHODS : One hundred patients who underwent volumetric-modulated arc therapy for nasopharyngeal cancer were selected in this study. The prediction model based on a residual network had DPTV maps, structure maps, and CT as inputs and the corresponding dose distribution maps as outputs. The performances of the combined distance and anatomical information (COM) model and the traditional anatomical (ANAT) model with two-channel inputs (structure maps and CT) were compared. A 10-fold cross validation was performed to separately train and test the COM and ANAT models. The voxel-based mean error (ME), mean absolute error (MAE), dosimetric parameters, and dice similarity coefficient (DSC) of isodose volumes were used for modeling evaluation.

RESULTS : The mean MAE of the body volume of the COM model were 4.89 ± 1.35%, highly significantly lower than those for the ANAT model of 5.07 ± 1.37% (p<0.001). The ME values of the body for the 2-type models were similar (p >0.05). The mean DSC values of the isodose volumes in the range of 60 Gy were all better in the COM model (p<0.05), and there were highly significant differences between 10 Gy and 55 Gy (p<0.001). For most organs at risk, the ME, MAE, and dosimetric parameters predicted by both models were concurrent with the ground truth values except the MAE values of the pituitary and optic chiasm in the ANAT model and the average mean dose of the right parotid in the ANAT model.

CONCLUSIONS : The COM model outperformed the ANAT model and could improve automated planning with statistically highly significant differences.

Chen Xinyuan, Zhu Ji, Yang Bining, Chen Deqi, Men Kuo, Dai Jianrong

2023

anatomical information, deep-learning, dose-prediction, minimum distance, radiotherapy treatment planning

In Frontiers in oncology

OBJECTIVES : To develop and validate magnetic resonance imaging (MRI)-based pre-Radiomics and delta-Radiomics models for predicting the treatment response of local advanced rectal cancer (LARC) to neoadjuvant chemoradiotherapy (NCRT).

METHODS : Between October 2017 and August 2022, 105 LARC NCRT-naïve patients were enrolled in this study. After careful evaluation, data for 84 patients that met the inclusion criteria were used to develop and validate the NCRT response models. All patients received NCRT, and the post-treatment response was evaluated by pathological assessment. We manual segmented the volume of tumors and 105 radiomics features were extracted from three-dimensional MRIs. Then, the eXtreme Gradient Boosting algorithm was implemented for evaluating and incorporating important tumor features. The predictive performance of MRI sequences and Synthetic Minority Oversampling Technique (SMOTE) for NCRT response were compared. Finally, the optimal pre-Radiomics and delta-Radiomics models were established respectively. The predictive performance of the radionics model was confirmed using 5-fold cross-validation, 10-fold cross-validation, leave-one-out validation, and independent validation. The predictive accuracy of the model was based on the area under the receiver operator characteristic (ROC) curve (AUC).

RESULTS : There was no significant difference in clinical factors between patients with good and poor reactions. Integrating different MRI modes and the SMOTE method improved the performance of the radiomics model. The pre-Radiomics model (train AUC: 0.93 ± 0.06; test AUC: 0.79) and delta-Radiomcis model (train AUC: 0.96 ± 0.03; test AUC: 0.83) all have high NCRT response prediction performance by LARC. Overall, the delta-Radiomics model was superior to the pre-Radiomics model.

CONCLUSION : MRI-based pre-Radiomics model and delta-Radiomics model all have good potential to predict the post-treatment response of LARC to NCRT. Delta-Radiomics analysis has a huge potential for clinical application in facilitating the provision of personalized therapy.

Wang Likun, Wu Xueliang, Tian Ruoxi, Ma Hongqing, Jiang Zekun, Zhao Weixin, Cui Guoqing, Li Meng, Hu Qinsheng, Yu Xiangyang, Xu Wengui

2023

MRI, machine learning, neoadjuvant chemoradiotherapy, radiomics, rectal adenocarcinoma

In The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland

INTRODUCTION : This study reviews the current state of robotic surgery training for surgeons, including the various curricula, training methods, and tools available, as well as the challenges and limitations of these.

METHODS : The authors carried out a literature search across PubMed, MEDLINE, and Google Scholar using keywords related to 'robotic surgery', 'computer-assisted surgery', 'simulation', 'virtual reality', 'surgical training', and 'surgical education'. Full text analysis was performed on 112 articles.

TRAINING PROGRAMMES : The training program for robotic surgery should focus on proficiency, deliberation, and distribution principles. The curricula can be broadly split up into pre-console and console-side training. Pre-Console and Console-Side Training: Simulation training is an important aspect of robotic surgery training to improve technical skill acquisition and reduce mental workload, which helps prepare trainees for live procedures.

OPERATIVE PERFORMANCE ASSESSMENT : The study also discusses the various validated assessment tools used for operative performance assessments.

FUTURE ADVANCES : Finally, the authors propose potential future directions for robotic surgery training, including the use of emerging technologies such as AI and machine learning for real-time feedback, remote mentoring, and augmented reality platforms like Proximie to reduce costs and overcome geographic limitations.

CONCLUSION : Standardisation in trainee performance assessment is needed. Each of the robotic curricula and platforms has strengths and weaknesses. The ERUS Robotic Curriculum represents an evidence-based example of how to implement training from novice to expert. Remote mentoring and augmented reality platforms can overcome the challenges of high equipment costs and limited access to experts. Emerging technologies offer promising advancements for real-time feedback and immersive training environments, improving patient outcomes.

Sinha Ankit, West Alexander, Vasdev Nikhil, Sooriakumaran Prasanna, Rane Abhay, Dasgupta Prokar, McKirdy Michael

2023-Mar-15

Education, Laparoscopic, Surgical training, Training & assessment

In American journal of preventive medicine ; h5-index 75.0

INTRODUCTION : Since 2005, female firearm suicide rates increased by 34%, outpacing the rise in male firearm suicide rates over the same period. The objective of this study was to develop and evaluate a natural language processing pipeline to identify a select set of common and important circumstances preceding female firearm suicide from coroner/medical examiner and law enforcement narratives.

METHODS : Unstructured information from coroner/medical examiner and law enforcement narratives were manually coded for 1,462 randomly selected cases from the National Violent Death Reporting System. Decedents were included from 40 states and Puerto Rico from 2014 to 2018. Naive Bayes, Random Forest, Support Vector Machine, and Gradient Boosting classifier models were tuned using 5-fold cross-validation. Model performance was assessed using sensitivity, specificity, positive predictive value, F1, and other metrics. Analyses were conducted from February to November 2022.

RESULTS : The natural language processing pipeline performed well in identifying recent interpersonal disputes, problems with intimate partners, acute/chronic pain, and intimate partners and immediate family at the scene. For example, the Support Vector Machine model had a mean of 98.1% specificity and 90.5% positive predictive value in classifying a recent interpersonal dispute before suicide. The Gradient Boosting model had a mean of 98.7% specificity and 93.2% positive predictive value in classifying a recent interpersonal dispute before suicide.

CONCLUSIONS : This study developed a natural language processing pipeline to classify 5 female firearm suicide antecedents using narrative reports from the National Violent Death Reporting System, which may improve the examination of these circumstances. Practitioners and researchers should weigh the efficiency of natural language processing pipeline development against conventional text mining and manual review.

Goldstein Evan V, Mooney Stephen J, Takagi-Stewart Julian, Agnew Brianna F, Morgan Erin R, Haviland Miriam J, Zhou Weipeng, Prater Laura C

2023-Mar-16

In Frontiers in health services

INTRODUCTION : Artificial intelligence (AI) is widely seen as critical for tackling fundamental challenges faced by health systems. However, research is scant on the factors that influence the implementation and routine use of AI in healthcare, how AI may interact with the context in which it is implemented, and how it can contribute to wider health system goals. We propose that AI development can benefit from knowledge generated in four scientific fields: intervention, innovation, implementation and improvement sciences.

AIM : The aim of this paper is to briefly describe the four fields and to identify potentially relevant knowledge from these fields that can be utilized for understanding and/or facilitating the use of AI in healthcare. The paper is based on the authors' experience and expertise in intervention, innovation, implementation, and improvement sciences, and a selective literature review.

UTILIZING KNOWLEDGE FROM THE FOUR FIELDS : The four fields have generated a wealth of often-overlapping knowledge, some of which we propose has considerable relevance for understanding and/or facilitating the use of AI in healthcare.

CONCLUSION : Knowledge derived from intervention, innovation, implementation, and improvement sciences provides a head start for research on the use of AI in healthcare, yet the extent to which this knowledge can be repurposed in AI studies cannot be taken for granted. Thus, when taking advantage of insights in the four fields, it is important to also be explorative and use inductive research approaches to generate knowledge that can contribute toward realizing the potential of AI in healthcare.

Nilsen Per, Reed Julie, Nair Monika, Savage Carl, Macrae Carl, Barlow James, Svedberg Petra, Larsson Ingrid, Lundgren Lina, Nygren Jens

2022

artificial intelligence, implementation, improvement, innovation, intervention

In Mayo Clinic proceedings

OBJECTIVE : To evaluate the performance of an internally developed and previously validated artificial intelligence (AI) algorithm for magnetic resonance (MR)-derived total kidney volume (TKV) in autosomal dominant polycystic kidney disease (ADPKD) when implemented in clinical practice.

PATIENTS AND METHODS : The study included adult patients with ADPKD seen by a nephrologist at our institution between November 2019 and January 2021 and undergoing an MR imaging examination as part of standard clinical care. Thirty-three nephrologists ordered MR imaging, requesting AI-based TKV calculation for 170 cases in these 161 unique patients. We tracked implementation and performance of the algorithm over 1 year. A radiologist and a radiology technologist reviewed all cases (N=170) for quality and accuracy. Manual editing of algorithm output occurred at radiology or radiology technologist discretion. Performance was assessed by comparing AI-based and manually edited segmentations via measures of similarity and dissimilarity to ensure expected performance. We analyzed ADPKD severity class assignment of algorithm-derived vs manually edited TKV to assess impact.

RESULTS : Clinical implementation was successful. Artificial intelligence algorithm-based segmentation showed high levels of agreement and was noninferior to interobserver variability and other methods for determining TKV. Of manually edited cases (n=84), the AI-algorithm TKV output showed a small mean volume difference of -3.3%. Agreement for disease class between AI-based and manually edited segmentation was high (five cases differed).

CONCLUSION : Performance of an AI algorithm in real-life clinical practice can be preserved if there is careful development and validation and if the implementation environment closely matches the development conditions.

Potretzke Theodora A, Korfiatis Panagiotis, Blezek Daniel J, Edwards Marie E, Klug Jason R, Cook Cole J, Gregory Adriana V, Harris Peter C, Chebib Fouad T, Hogan Marie C, Torres Vicente E, Bolan Candice W, Sandrasegaran Kumaresan, Kawashima Akira, Collins Jeremy D, Takahashi Naoki, Hartman Robert P, Williamson Eric E, King Bernard F, Callstrom Matthew R, Erickson Bradley J, Kline Timothy L

2023-Mar-15