A multi-Task Learning based applicable AI model simultaneously predicts stage, histology, grade and LNM for cervical cancer before surgery.

PURPOSE: To build an Mult-Task Learning (MTL) based Artificial Intelligence(AI) model that can simultaneously predict clinical stage, histology, grade and LNM for cervical cancer before surgery. METHODS: This retrospective and prospective cohort study was conducted from January 2001 to March 2014 for the training set and from January 2018 to November 2021 for the validation set at Beijing Chaoyang Hospital, Capital Medical University. Preoperative clinical information of cervical cancer patients was used. An Artificial Neural Network (ANN) algorithm was used to build the MTL-based AI model. Accuracy and weighted F1 scores were calculated as evaluation indicators. The performance of the MTL model was compared with Single-Task Learning (STL) models. Additionally, a Turing test was performed by 20 gynecologists and compared with this AI model. RESULTS: A total of 223 cervical cancer cases were retrospectively enrolled into the training set, and 58 cases were prospectively collected as independent validation set. The accuracy of this cervical cancer AI model constructed with ANN algorithm in predicting stage, histology, grade and LNM were 75%, 95%, 86% and 76%, respectively. And the corresponding weighted F1 score were 70%, 94%, 86%, and 76%, respectively. The average time consumption of AI simultaneously predicting stage, histology, grade and LNM for cervical cancer was 0.01s (95%CI: 0.01-0.01) per 20 patients. The mean time consumption doctor and doctor with AI were 581.1s (95%CI: 300.0-900.0) per 20 patients and 534.8s (95%CI: 255.0-720.0) per 20 patients, respectively. Except for LNM, both the accuracy and F-score of the AI model were significantly better than STL AI, doctors and AI-assisted doctors in predicting stage, grade and histology. (P < 0.05) The time consumption of AI was significantly less than that of doctors' prediction and AI-assisted doctors' results. (P < 0.05 CONCLUSION: A multi-task learning AI model can simultaneously predict stage, histology, grade, and LNM for cervical cancer preoperatively with minimal time consumption. To improve the conditions and use of the beneficiaries, the model should be integrated into routine clinical workflows, offering a decision-support tool for gynecologists. Future studies should focus on refining the model for broader clinical applications, increasing the diversity of the training datasets, and enhancing its adaptability to various clinical settings. Additionally, continuous feedback from clinical practice should be incorporated to ensure the model's accuracy and reliability, ultimately improving personalized patient care and treatment outcomes.

Predicting axillary lymph node metastasis in breast cancer based on ultrasound radiofrequency time-series analysis.

BACKGROUND: The status of axillary lymph nodes (ALN) plays a critical role in the management of patients with breast cancer. It is an urgent demand to develop highly accurate, non-invasive methods for predicting ALN status. PURPOSE: To evaluate the efficacy of ultrasound radiofrequency (URF) time-series parameters, in combination with clinical data, in predicting ALN metastasis in patients with breast cancer. MATERIAL AND METHODS: We prospectively gathered clinicopathologic and ultrasonic data from patients diagnosed with breast cancer. Various machine-learning (ML) models were developed using all available features to determine the most efficient diagnostic model. Subsequently, distinct prediction models were created using the optimal ML model, and their diagnostic performances were evaluated and compared. RESULTS: The study encompassed 240 patients, of whom 88 had lymph node metastases. A leave-one-out cross-validation (LOOCV) method was used to split the entire dataset into training and testing subsets. The random forest ML model outperformed the other algorithms, with an area under the curve (AUC) of 0.92. Prediction models based on clinical, ultrasonic, URF parameters, clinical + ultrasonic, clinical + URF, and ultrasonic + URF parameters had AUCs of 0.56, 0.79, 0.78, 0.90, 0.80, and 0.84, respectively, in the testing set. The comprehensive diagnostic model (clinical + ultrasonic + URF parameters) demonstrated strong diagnostic capability, with an AUC of 0.94 in the testing set, exceeding any single prediction model. CONCLUSION: The combined model (clinical + ultrasonic + URF parameters) could be used preoperatively to predict lymph node status, offering valuable input for the design of individualized surgical approaches.

Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation.

Research exploring CycleGAN-based synthetic image generation has recently accelerated in the medical community due to its ability to leverage unpaired images effectively. However, a commonly established drawback of the CycleGAN, the introduction of artifacts in generated images, makes it unreliable for medical imaging use cases. In an attempt to address this, we explore the effect of structure losses on the CycleGAN and propose a generalized frequency-based loss that aims at preserving the content in the frequency domain. We apply this loss to the use-case of cone-beam computed tomography (CBCT) translation to computed tomography (CT)-like quality. Synthetic CT (sCT) images generated from our methods are compared against baseline CycleGAN along with other existing structure losses proposed in the literature. Our methods (MAE: 85.5, MSE: 20433, NMSE: 0.026, PSNR: 30.02, SSIM: 0.935) quantitatively and qualitatively improve over the baseline CycleGAN (MAE: 88.8, MSE: 24244, NMSE: 0.03, PSNR: 29.37, SSIM: 0.935) across all investigated metrics and are more robust than existing methods. Furthermore, no observable artifacts or loss in image quality were observed. Finally, we demonstrated that sCTs generated using our methods have superior performance compared to the original CBCT images on selected downstream tasks.

A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies.

OBJECTIVES: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. MATERIALS AND METHODS: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. RESULTS: The series included 225 patients (age range 21-90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85% (183/215, 95% CI: 82-91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65% (95% CI: 61-69) versus 88% (95% CI: 86-91, p<0.01). Reading time increased by 11% using CAD (296 s vs. 329 s; p<0.05). CONCLUSION: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. KEY POINTS: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.

Assessing the role of GPT-4 in thyroid ultrasound diagnosis and treatment recommendations: enhancing interpretability with a chain of thought approach.

Background: As artificial intelligence (AI) becomes increasingly prevalent in the medical field, the effectiveness of AI-generated medical reports in disease diagnosis remains to be evaluated. ChatGPT is a large language model developed by open AI with a notable capacity for text abstraction and comprehension. This study aimed to explore the capabilities, limitations, and potential of Generative Pre-trained Transformer (GPT)-4 in analyzing thyroid cancer ultrasound reports, providing diagnoses, and recommending treatment plans. Methods: Using 109 diverse thyroid cancer cases, we evaluated GPT-4's performance by comparing its generated reports to those from doctors with various levels of experience. We also conducted a Turing Test and a consistency analysis. To enhance the interpretability of the model, we applied the Chain of Thought (CoT) method to deconstruct the decision-making chain of the GPT model. Results: GPT-4 demonstrated proficiency in report structuring, professional terminology, and clarity of expression, but showed limitations in diagnostic accuracy. In addition, our consistency analysis highlighted certain discrepancies in the AI's performance. The CoT method effectively enhanced the interpretability of the AI's decision-making process. Conclusions: GPT-4 exhibits potential as a supplementary tool in healthcare, especially for generating thyroid gland diagnostic reports. Our proposed online platform, "ThyroAIGuide", alongside the CoT method, underscores the potential of AI to augment diagnostic processes, elevate healthcare accessibility, and advance patient education. However, the journey towards fully integrating AI into healthcare is ongoing, requiring continuous research, development, and careful monitoring by medical professionals to ensure patient safety and quality of care.

Preoperative prediction of high-grade osteosarcoma response to neoadjuvant therapy based on a plain CT radiomics model: A dual-center study.

Objective: To develop a model combining clinical and radiomics features from CT scans for a preoperative noninvasive evaluation of Huvos grading of neoadjuvant chemotherapy in patients with HOS. Methods: 183 patients from center A and 42 from center B were categorized into training and validation sets. Features derived from radiomics were obtained from unenhanced CT scans.Following dimensionality reduction, the most optimal features were selected and utilized in creating a radiomics model through logistic regression analysis. Integrating clinical features, a composite clinical radiomics model was developed, and a nomogram was constructed. Predictive performance of the model was evaluated using ROC curves and calibration curves. Additionally, decision curve analysis was conducted to assess practical utility of nomogram in clinical settings. Results: LASSO LR analysis was performed, and finally, three selected image omics features were obtained.Radiomics model yielded AUC values with a good diagnostic effect for both patient sets (AUCs: 0.69 and 0.68, respectively). Clinical models (including sex, age, pre-chemotherapy ALP and LDH levels, new lung metastases within 1 year after surgery, and incidence) performed well in terms of Huvos grade prediction, with an AUC of 0.74 for training set. The AUC for independent validation set stood at 0.70. Notably, the amalgamation of radiomics and clinical features exhibited commendable predictive prowess in training set, registering an AUC of 0.78. This robust performance was subsequently validated in the independent validation set, where the AUC remained high at 0.75. Calibration curves of nomogram showed that the predictions were in good agreement with actual observations. Conclusion: Combined model can be used for Huvos grading in patients with HOS after preoperative chemotherapy, which is helpful for adjuvant treatment decisions.

Prediction of new-onset atrial fibrillation in patients with non-small cell lung cancer treated with curative-intent conventional radiotherapy.

BACKGROUND: Atrial fibrillation (AF) is an important side effect of thoracic Radiotherapy (RT), which may impair quality of life and survival. This study aimed to develop a prediction model for new-onset AF in patients with Non-Small Cell Lung Cancer (NSCLC) receiving RT alone or as a part of their multi-modal treatment. PATIENTS AND METHODS: Patients with stage I-IV NSCLC treated with curative-intent conventional photon RT were included. The baseline electrocardiogram (ECG) was compared with follow-up ECGs to identify the occurrence of new-onset AF. A wide range of potential clinical predictors and dose-volume measures on the whole heart and six automatically contoured cardiac substructures, including chambers and conduction nodes, were considered for statistical modeling. Internal validation with optimism-correction was performed. A nomogram was made. RESULTS: 374 patients (mean age 69 ±â€¯10 years, 57 % male) were included. At baseline, 9.1 % of patients had AF, and 42 (11.2 %) patients developed new-onset AF. The following parameters were predictive: older age (OR=1.04, 95 % CI: 1.013-1.068), being overweight or obese (OR=1.791, 95 % CI: 1.139-2.816), alcohol use (OR=4.052, 95 % CI: 2.445-6.715), history of cardiac procedures (OR=2.329, 95 % CI: 1.287-4.215), tumor located in the upper lobe (OR=2.571, 95 % CI: 1.518-4.355), higher forced expiratory volume in 1 s (OR=0.989, 95 % CI: 0.979-0.999), higher creatinine (OR=1.008, 95 % CI: 1.002-1.014), concurrent chemotherapy (OR=3.266, 95 % CI: 1.757 to 6.07) and left atrium Dmax (OR=1.022, 95 % CI: 1.012-1.032). The model showed good discrimination (area under the curve = 0.80, 95 % CI: 0.76-0.84), calibration and positive net benefits. CONCLUSION: This prediction model employs readily available predictors to identify patients at high risk of new-onset AF who could potentially benefit from active screening and timely management of post-RT AF.

Comparing the performance of a deep learning-based lung gross tumour volume segmentation algorithm before and after transfer learning in a new hospital.

Objectives: Radiation therapy for lung cancer requires a gross tumour volume (GTV) to be carefully outlined by a skilled radiation oncologist (RO) to accurately pinpoint high radiation dose to a malignant mass while simultaneously minimizing radiation damage to adjacent normal tissues. This is manually intensive and tedious however, it is feasible to train a deep learning (DL) neural network that could assist ROs to delineate the GTV. However, DL trained on large openly accessible data sets might not perform well when applied to a superficially similar task but in a different clinical setting. In this work, we tested the performance of DL automatic lung GTV segmentation model trained on open-access Dutch data when used on Indian patients from a large public tertiary hospital, and hypothesized that generic DL performance could be improved for a specific local clinical context, by means of modest transfer-learning on a small representative local subset. Methods: X-ray computed tomography (CT) series in a public data set called "NSCLC-Radiomics" from The Cancer Imaging Archive was first used to train a DL-based lung GTV segmentation model (Model 1). Its performance was assessed using a different open access data set (Interobserver1) of Dutch subjects plus a private Indian data set from a local tertiary hospital (Test Set 2). Another Indian data set (Retrain Set 1) was used to fine-tune the former DL model using a transfer learning method. The Indian data sets were taken from CT of a hybrid scanner based in nuclear medicine, but the GTV was drawn by skilled Indian ROs. The final (after fine-tuning) model (Model 2) was then re-evaluated in "Interobserver1" and "Test Set 2." Dice similarity coefficient (DSC), precision, and recall were used as geometric segmentation performance metrics. Results: Model 1 trained exclusively on Dutch scans showed a significant fall in performance when tested on "Test Set 2." However, the DSC of Model 2 recovered by 14 percentage points when evaluated in the same test set. Precision and recall showed a similar rebound of performance after transfer learning, in spite of using a comparatively small sample size. The performance of both models, before and after the fine-tuning, did not significantly change the segmentation performance in "Interobserver1." Conclusions: A large public open-access data set was used to train a generic DL model for lung GTV segmentation, but this did not perform well initially in the Indian clinical context. Using transfer learning methods, it was feasible to efficiently and easily fine-tune the generic model using only a small number of local examples from the Indian hospital. This led to a recovery of some of the geometric segmentation performance, but the tuning did not appear to affect the performance of the model in another open-access data set. Advances in knowledge: Caution is needed when using models trained on large volumes of international data in a local clinical setting, even when that training data set is of good quality. Minor differences in scan acquisition and clinician delineation preferences may result in an apparent drop in performance. However, DL models have the advantage of being efficiently "adapted" from a generic to a locally specific context, with only a small amount of fine-tuning by means of transfer learning on a small local institutional data set.

Quantitative MRI-based radiomics analysis identifies blood flow feature associated to overall survival for rectal cancer patients.

Radiomics objectively quantifies image information through numerical metrics known as features. In this study, we investigated the stability of magnetic resonance imaging (MRI)-based radiomics features in rectal cancer using both anatomical MRI and quantitative MRI (qMRI), when different methods to define the tumor volume were used. Second, we evaluated the prognostic value of stable features associated to 5-year progression-free survival (PFS) and overall survival (OS). On a 1.5 T MRI scanner, 81 patients underwent diagnostic MRI, an extended diffusion-weighted sequence with calculation of the apparent diffusion coefficient (ADC) and a multiecho dynamic contrast sequence generating both dynamic contrast-enhanced and dynamic susceptibility contrast (DSC) MR, allowing quantification of Ktrans, blood flow (BF) and area under the DSC curve (AUC). Radiomic features were extracted from T2w images and from ADC, Ktrans, BF and AUC maps. Tumor volumes were defined with three methods; machine learning, deep learning and manual delineations. The interclass correlation coefficient (ICC) assessed the stability of features. Internal validation was performed on 1000 bootstrap resamples in terms of discrimination, calibration and decisional benefit. For each combination of image and volume definition, 94 features were extracted. Features from qMRI contained higher prognostic potential than features from anatomical MRI. When stable features (> 90% ICC) were compared with clinical parameters, qMRI features demonstrated the best prognostic potential. A feature extracted from the DSC MRI parameter BF was associated with both PFS (p = 0.004) and OS (p = 0.004). In summary, stable qMRI-based radiomics features was identified, in particular, a feature based on BF from DSC MRI was associated with both PFS and OS.

Predicting the risk of neurocognitive decline after brain irradiation in adult patients with a primary brain tumor.

BACKGROUND: Deterioration of neurocognitive function in adult patients with a primary brain tumor is the most concerning side effect of radiotherapy. This study aimed to develop and evaluate normal-tissue complication probability (NTCP) models using clinical and dose-volume measures for 6-month, 1-year, and 2-year Neurocognitive Decline (ND) postradiotherapy. METHODS: A total of 219 patients with a primary brain tumor treated with radical photon and/or proton radiotherapy (RT) between 2019 and 2022 were included. Controlled oral word association test, Hopkins verbal learning test-revised, and trail making test were used to objectively measure ND. A comprehensive set of potential clinical and dose-volume measures on several brain structures were considered for statistical modeling. Clinical, dose-volume and combined models were constructed and internally tested in terms of discrimination (area under the curve, AUC), calibration (mean absolute error, MAE), and net benefit. RESULTS: Fifty percent, 44.5%, and 42.7% of the patients developed ND at 6-month, 1-year, and 2-year time points, respectively. The following predictors were included in the combined model for 6-month ND: age at radiotherapy > 56 years (OR = 5.71), overweight (OR = 0.49), obesity (OR = 0.35), chemotherapy (OR = 2.23), brain V20 Gy ≥ 20% (OR = 3.53), brainstem volume ≥ 26 cc (OR = 0.39), and hypothalamus volume ≥ 0.5 cc (OR = 0.4). Decision curve analysis showed that the combined models had the highest net benefits at 6-month (AUC = 0.79, MAE = 0.021), 1-year (AUC = 0.72, MAE = 0.027), and 2-year (AUC = 0.69, MAE = 0.038) time points. CONCLUSIONS: The proposed NTCP models use easy-to-obtain predictors to identify patients at high risk of ND after brain RT. These models can potentially provide a base for RT-related decisions and post-therapy neurocognitive rehabilitation interventions.

A PET/CT radiomics model for predicting distant metastasis in early-stage non-small cell lung cancer patients treated with stereotactic body radiotherapy: a multicentric study.

OBJECTIVES: Stereotactic body radiotherapy (SBRT) is a treatment option for patients with early-stage non-small cell lung cancer (NSCLC) who are unfit for surgery. Some patients may experience distant metastasis. This study aimed to develop and validate a radiomics model for predicting distant metastasis in patients with early-stage NSCLC treated with SBRT. METHODS: Patients at five institutions were enrolled in this study. Radiomics features were extracted based on the PET/CT images. After feature selection in the training set (from Tianjin), CT-based and PET-based radiomics signatures were built. Models based on CT and PET signatures were built and validated using external datasets (from Zhejiang, Zhengzhou, Shandong, and Shanghai). An integrated model that included CT and PET radiomic signatures was developed. The performance of the proposed model was evaluated in terms of its discrimination, calibration, and clinical utility. Multivariate logistic regression was used to calculate the probability of distant metastases. The cutoff value was obtained using the receiver operator characteristic curve (ROC), and the patients were divided into high- and low-risk groups. Kaplan-Meier analysis was used to evaluate the distant metastasis-free survival (DMFS) of different risk groups. RESULTS: In total, 228 patients were enrolled. The median follow-up time was 31.4 (2.0-111.4) months. The model based on CT radiomics signatures had an area under the curve (AUC) of 0.819 in the training set (n = 139) and 0.786 in the external dataset (n = 89). The PET radiomics model had an AUC of 0.763 for the training set and 0.804 for the external dataset. The model combining CT and PET radiomics had an AUC of 0.835 for the training set and 0.819 for the external dataset. The combined model showed a moderate calibration and a positive net benefit. When the probability of distant metastasis was greater than 0.19, the patient was considered to be at high risk. The DMFS of patients with high- and low-risk was significantly stratified (P < 0.001). CONCLUSIONS: The proposed PET/CT radiomics model can be used to predict distant metastasis in patients with early-stage NSCLC treated with SBRT and provide a reference for clinical decision-making. In this study, the model was established by combining CT and PET radiomics signatures in a moderate-quantity training cohort of early-stage NSCLC patients treated with SBRT and was successfully validated in independent cohorts. Physicians could use this easy-to-use model to assess the risk of distant metastasis after SBRT. Identifying subgroups of patients with different risk factors for distant metastasis is useful for guiding personalized treatment approaches.

Developing PRISM: A Pragmatic Institutional Survey and Bench Marking Tool to Measure Digital Research Maturity of Cancer Centers.

BACKGROUND: Multicenter precision oncology real-world evidence requires a substantial long-term investment by hospitals to prepare their data and align on common Clinical Research processes and medical definitions. Our team has developed a self-assessment framework to support hospitals and hospital networks to measure their digital maturity and better plan and coordinate those investments. From that framework, we developed PRISM for Cancer Outcomes: PR: agmatic I: nstitutional S: urvey and benchM: arking. OBJECTIVES: The primary objective was to develop PRISM as a tool for self-assessment of digital maturity in oncology hospitals and research networks; a secondary objective was to create an initial benchmarking cohort of >25 hospitals using the tool as input for future development. METHODS: PRISM is a 25-question semiquantitative self-assessment survey developed iteratively from expert knowledge in oncology real-world study delivery. It covers four digital maturity dimensions: (1) Precision oncology, (2) Clinical digital data, (3) Routine outcomes, and (4) Information governance and delivery. These reflect the four main data types and critical enablers for precision oncology research from routine electronic health records. RESULTS: During piloting with 26 hospitals from 19 European countries, PRISM was found to be easy to use and its semiquantitative questions to be understood in a wide diversity of hospitals. Results within the initial benchmarking cohort aligned well with internal perspectives. We found statistically significant differences in digital maturity, with Precision oncology being the most mature dimension, and Information governance and delivery the least mature. CONCLUSION: PRISM is a light footprint benchmarking tool to support the planning of large-scale real-world research networks. It can be used to (i) help an individual hospital identify areas most in need of investment and improvement, (ii) help a network of hospitals identify sources of best practice and expertise, and (iii) help research networks plan research. With further testing, policymakers could use PRISM to better plan digital investments around the Cancer Mission and European Digital Health Space.

METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII.

PURPOSE: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies. METHODS: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated. RESULT: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community. CONCLUSION: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers. CRITICAL RELEVANCE STATEMENT: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning. KEY POINTS: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score ( https://metricsscore.github.io/metrics/METRICS.html ) and a repository created to collect feedback from the radiomics community ( https://github.com/metricsscore/metrics ).

The role of artificial intelligence in radiotherapy clinical practice.

This review article visits the current state of artificial intelligence (AI) in radiotherapy clinical practice. We will discuss how AI has a place in the modern radiotherapy workflow at the level of automatic segmentation and planning, two applications which have seen real-work implementation. A special emphasis will be placed on the role AI can play in online adaptive radiotherapy, such as performed at MR-linacs, where online plan adaptation is a procedure which could benefit from automation to reduce on-couch time for patients. Pseudo-CT generation and AI for motion tracking will be introduced in the scope of online adaptive radiotherapy as well. We further discuss the use of AI for decision-making and response assessment, for example for personalized prescription and treatment selection, risk stratification for outcomes and toxicities, and AI for quantitative imaging and response assessment. Finally, the challenges of generalizability and ethical aspects will be covered. With this, we provide a comprehensive overview of the current and future applications of AI in radiotherapy.

Computed tomography and radiation dose images-based deep-learning model for predicting radiation pneumonitis in lung cancer patients after radiation therapy.

PURPOSE: To develop a deep learning model that combines CT and radiation dose (RD) images to predict the occurrence of radiation pneumonitis (RP) in lung cancer patients who received radical (chemo)radiotherapy. METHODS: CT, RD images and clinical parameters were obtained from 314 retrospectively-collected patients (training set) and 35 prospectively-collected patients (test-set-1) who were diagnosed with lung cancer and received radical radiotherapy in the dose range of 50 Gy and 70 Gy. Another 194 (60 Gy group, test-set-2) and 158 (74 Gy group, test-set-3) patients from the clinical trial RTOG 0617 were used for external validation. A ResNet architecture was used to develop a prediction model that combines CT and RD features. Thereafter, the CT and RD weights were adjusted by using 40 patients from test-set-2 or 3 to accommodate cohorts with different clinical settings or dose delivery patterns. Visual interpretation was implemented using a gradient-weighted class activation map (grad-CAM) to observe the area of model attention during the prediction process. To improve the usability, ready-to-use online software was developed. RESULTS: The discriminative ability of a baseline trained model had an AUC of 0.83 for test-set-1, 0.55 for test-set-2, and 0.63 for test-set-3. After adjusting CT and RD weights of the model using a subset of the RTOG-0617 subjects, the discriminatory power of test-set-2 and 3 improved to AUC 0.65 and AUC 0.70, respectively. Grad-CAM showed the regions of interest to the model that contribute to the prediction of RP. CONCLUSION: A novel deep learning approach combining CT and RD images can effectively and accurately predict the occurrence of RP, and this model can be adjusted easily to fit new cohorts.

Interpretable artificial intelligence in radiology and radiation oncology.

Artificial intelligence has been introduced to clinical practice, especially radiology and radiation oncology, from image segmentation, diagnosis, treatment planning and prognosis. It is not only crucial to have an accurate artificial intelligence model, but also to understand the internal logic and gain the trust of the experts. This review is intended to provide some insights into core concepts of the interpretability, the state-of-the-art methods for understanding the machine learning models, the evaluation of these methods, identifying some challenges and limits of them, and gives some examples of medical applications.

Emerging role of quantitative imaging (radiomics) and artificial intelligence in precision oncology.

Cancer is a fatal disease and the second most cause of death worldwide. Treatment of cancer is a complex process and requires a multi-modality-based approach. Cancer detection and treatment starts with screening/diagnosis and continues till the patient is alive. Screening/diagnosis of the disease is the beginning of cancer management and continued with the staging of the disease, planning and delivery of treatment, treatment monitoring, and ongoing monitoring and follow-up. Imaging plays an important role in all stages of cancer management. Conventional oncology practice considers that all patients are similar in a disease type, whereas biomarkers subgroup the patients in a disease type which leads to the development of precision oncology. The utilization of the radiomic process has facilitated the advancement of diverse imaging biomarkers that find application in precision oncology. The role of imaging biomarkers and artificial intelligence (AI) in oncology has been investigated by many researchers in the past. The existing literature is suggestive of the increasing role of imaging biomarkers and AI in oncology. However, the stability of radiomic features has also been questioned. The radiomic community has recognized that the instability of radiomic features poses a danger to the global generalization of radiomic-based prediction models. In order to establish radiomic-based imaging biomarkers in oncology, the robustness of radiomic features needs to be established on a priority basis. This is because radiomic models developed in one institution frequently perform poorly in other institutions, most likely due to radiomic feature instability. To generalize radiomic-based prediction models in oncology, a number of initiatives, including Quantitative Imaging Network (QIN), Quantitative Imaging Biomarkers Alliance (QIBA), and Image Biomarker Standardisation Initiative (IBSI), have been launched to stabilize the radiomic features.

Computed tomography-based radiomics for the differential diagnosis of pneumonitis in stage IV non-small cell lung cancer patients treated with immune checkpoint inhibitors.

INTRODUCTION: Immunotherapy-induced pneumonitis (IIP) is a serious side-effect which requires accurate diagnosis and management with high-dose corticosteroids. The differential diagnosis between IIP and other types of pneumonitis (OTP) remains challenging due to similar radiological patterns. This study was aimed to develop a prediction model to differentiate IIP from OTP in patients with stage IV non-small cell lung cancer (NSCLC) who developed pneumonitis during immunotherapy. METHODS: Consecutive patients with metastatic NSCLC treated with immunotherapy in six centres in the Netherlands and Belgium from 2017 to 2020 were reviewed and cause-specific pneumonitis events were identified. Seven regions of interest (segmented lungs and spheroidal/cubical regions surrounding the inflammation) were examined to extract the most predictive radiomic features from the chest computed tomography images obtained at pneumonitis manifestation. Models were internally tested regarding discrimination, calibration and decisional benefit. To evaluate the clinical application of the models, predicted labels were compared with the separate clinical and radiological judgements. RESULTS: A total of 556 patients were reviewed; 31 patients (5.6%) developed IIP and 41 patients developed OTP (7.4%). The line of immunotherapy was the only predictive factor in the clinical model (2nd versus 1st odds ratio = 0.08, 95% confidence interval:0.01-0.77). The best radiomic model was achieved using a 75-mm spheroidal region of interest which showed an optimism-corrected area under the receiver operating characteristic curve of 0.83 (95% confidence interval:0.77-0.95) with negative and positive predictive values of 80% and 79%, respectively. Good calibration and net benefits were achieved for the radiomic model across the entire range of probabilities. A correct diagnosis was provided by the radiomic model in 10 out of 12 cases with non-conclusive radiological judgements. CONCLUSION: Radiomic biomarkers applied to computed tomography imaging may support clinicians making the differential diagnosis of pneumonitis in patients with NSCLC receiving immunotherapy, especially when the radiologic assessment is non-conclusive.

Real-time auto-segmentation of the ureter in video sequences of gynaecological laparoscopic surgery.

BACKGROUND: Ureteral injury is common during gynaecological laparoscopic surgery. Real-time auto-segmentation can assist gynaecologists in identifying the ureter and reduce intraoperative injury risk. METHODS: A deep learning segmentation model was crafted for ureter recognition in surgical videos, utilising 3368 frames from 11 laparoscopic surgeries. Class activation maps enhanced the model's interpretability, showing its areas. The model's clinical relevance was validated through an End-User Turing test and verified by three gynaecological surgeons. RESULTS: The model registered a Dice score of 0.86, a Hausdorff 95 distance of 22.60, and processed images in 0.008 s on average. In complex surgeries, it pinpointed the ureter's position in real-time. Fifty five surgeons across eight institutions found the model's accuracy, specificity, and sensitivity comparable to human performance. Yet, artificial intelligence experience influenced some subjective ratings. CONCLUSIONS: The model offers precise real-time ureter segmentation in laparoscopic surgery and can be a significant tool for gynaecologists to mitigate ureteral injuries.