Artificial intelligence (AI), the wide spectrum of technologies aiming to give machines or computers the ability to perform human-like cognitive functions, began in the 1940s with the first abstract models of intelligent machines. Soon after, in the 1950s and 1960s, machine learning algorithms such as neural networks and decision trees ignited significant enthusiasm. More recent advancements include the refinement of learning algorithms, the development of convolutional neural networks to efficiently analyze images, and methods to synthesize new images. This renewed enthusiasm was also due to the increase in computational power with graphical processing units and the availability of large digital databases to be mined by neural networks. AI soon began to be applied in medicine, first through expert systems designed to support the clinician’s decision and later with neural networks for the detection, classification, or segmentation of malignant lesions in medical images. A recent prospective clinical trial demonstrated the non-inferiority of AI alone compared with a double reading by two radiologists on screening mammography. Natural language processing, recurrent neural networks, transformers, and generative models have both improved the capabilities of making an automated reading of medical images and moved AI to new domains, including the text analysis of electronic health records, image self-labeling, and self-reporting. The availability of open-source and free libraries, as well as powerful computing resources, has greatly facilitated the adoption of deep learning by researchers and clinicians. Key concerns surrounding AI in healthcare include the need for clinical trials to demonstrate efficacy, the perception of AI tools as ‘black boxes’ that require greater interpretability and explainability, and ethical issues related to ensuring fairness and trustworthiness in AI systems. Thanks to its versatility and impressive results, AI is one of the most promising resources for frontier research and applications in medicine, in particular for oncological applications.

Purpose: When autocontouring based on artificial intelligence (AI) is used in the radiotherapy (RT) workflow, the contours are reviewed and eventually adjusted by a radiation oncologist before an RT treatment plan is generated, with the purpose of improving dosimetry and reducing both interobserver variability and time for contouring. The purpose of this study was to evaluate the results of application of a commercial AI-based autocontouring for RT, assessing both geometric accuracies and the influence on optimized dose from automatically generated contours after review by human operator. Materials and Methods: A commercial autocontouring system was applied to a retrospective database of 40 patients, of which 20 were treated with radiotherapy for prostate cancer (PCa) and 20 for head and neck cancer (HNC). Contours resulting from AI were compared against AI contours reviewed by human operator and human-only contours using Dice similarity coefficient (DSC), Hausdorff distance (HD), and relative volume difference (RVD). Dosimetric indices such as D_mean, D_0.03cc, and normalized plan quality metrics were used to compare dose distributions from RT plans generated from structure sets contoured by humans assisted by AI against plans from manual contours. The reduction in contouring time obtained by using automated tools was also assessed. A Wilcoxon rank sum test was computed to assess the significance of differences. Interobserver variability of the comparison of manual vs. AI-assisted contours was also assessed among two radiation oncologists for PCa. Results: For PCa, AI-assisted segmentation showed good agreement with expert radiation oncologist structures with average DSC among patients ≥ 0.7 for all structures, and minimal radiation oncology adjustment of structures (DSC of adjusted versus AI structures ≥ 0.91). For HNC, results of comparison between manual and AI contouring varied considerably e.g., 0.77 for oral cavity and 0.11–0.13 for brachial plexus, but again, adjustment was generally minimal (DSC of adjusted against AI contours 0.97 for oral cavity, 0.92–0.93 for brachial plexus). The difference in dose for the target and organs at risk were not statistically significant between human and AI-assisted, with the only exceptions of D_0.03cc to the anal canal and D_mean to the brachial plexus. The observed average differences in plan quality for PCa and HNC cases were 8% and 6.7%, respectively. The dose parameter changes due to interobserver variability in PCa were small, with the exception of the anal canal, where large dose variations were observed. The reduction in time required for contouring was 72% for PCa and 84% for HNC. Conclusions: When an autocontouring system is used in combination with human review, the time of the RT workflow is significantly reduced without affecting dose distribution and plan quality.

Artificial intelligence (AI), the wide spectrum of technologies aiming to give machines or computers the ability to perform human-like cognitive functions, began in the 40s with the first abstract models of intelligent machines. Soon later in the 50s and 60s machine learning algorithms such as neural networks and decision trees ignited large enthusiasm. More recent advancements include the refinement of learning algorithms, the development of convolutional neural networks to efficiently analyze images, and methods to synthesize new images. The renewed enthusiasm was also due to the increase in computational power with graphical processing units and the availability of large digital databases to be mined by neural networks. AI soon began to be applied in medicine, first through expert systems designed to support the clinician’s decision, and later with neural networks for the detection or classification of malignant lesions in medical images. More recently, the use of natural language processing, recurrent neural networks, transformers and generative models has both improved the capabilities of making an automated reading of medical images and moved AI to new domains, including text analysis of electronic health records, image self-labelling and self-reporting. Thanks to its versatility and impressive results and fueled by the availability of powerful computing resources and open-source libraries, AI is one of the most promising resources for frontier research and applications in medicine.

The aim of this study is to predict local failure after partial prostate re-irradiation for the treatment of isolated locally recurrent prostate cancer by using a machine learning classifier based on radiomic features from pre-treatment computed tomography (CT), positron-emission tomography (PET) and biological effective dose distribution (BED) of the radiotherapy plan. The analysis was conducted on a monocentric dataset of 43 patients with evidence of isolated intraprostatic recurrence of prostate cancer after primary external beam radiotherapy. All patients received partial prostate re-irradiation delivered by volumetric modulated arc therapy. The gross tumor volume (GTV) of each patient was manually contoured from planning CT, choline-PET and dose maps. An ensemble machine learning pipeline including unbalanced data correction and feature selection was trained using the radiomic and dosiomic features as input for predicting occurrence of local failure. The model performance was assessed using sensitivity, specificity, accuracy and area under receiver operating characteristic curves of the score function in 10-fold cross validation repeated 100 times. Local failure was observed in 13 patients (30%), with a median time to recurrence of 36.7 months (range = 6.1–102.4 months). A four variables ensemble machine learning model resulted in accuracy of 0.62 and AUC 0.65. According to our results, a dosiomic machine learning classifier can predict local failure after partial prostate re-irradiation.

Purpose: to predict eligibility for deep inspiration breath-hold (DIBH) radiotherapy (RT) treatment of patients with left breast cancer from analysis of respiratory signal, using Deep Bidirectional Long Short-Term Memory (BLSTM) recurrent neural networks. Methods: The respiratory traces from 36 patients who underwent DIBH RT were collected. The patients’ RT treatment plans were generated for both DIBH and free-breathing (FB) modalities. The patients were divided into two classes (patient eligible or not), based on the decrease of maximum dose to the left anterior descending (LAD) artery achieved with DIBH, compared to that achieved with FB and ΔD_L. Patients with ΔD_L > median value of ΔD_L within the patient cohort were assumed to be those selected for DIBH. A BLSTM-RNN was trained for classification of patients eligible for DIBH by analysis of their respiratory signals, as acquired during acquisition of the pre-treatment computed tomography (CT), for selecting the window for DIBH. The dataset was split into training (60%) and test groups (40%), and the hyper-parameters, including the number of hidden layers, the optimizer, the learning rate, and the number of epochs, were selected for optimising model performance. The BLSTM included 2 layers of 100 neural units, each followed by a dropout layer with 20% dropout, and was trained in 35 epochs using the Adam optimizer, with an initial learning rate of 0.0003. Results: The system achieved accuracy, specificity, and sensitivity of, F1 score and area under the receiving operating characteristic curve (AUC) of 71.4%, 66.7%, 80.1%, 72.4%, and 69.4% in the test dataset, respectively. Conclusions: The proposed BLSTM-RNN classified patients in the test set eligible for DIBH with good accuracy. These results look promising for building an accurate and robust decision system to provide automated assistance to the radiotherapy team in assigning patients to DIBH.