Artificial intelligence solution to classify pulmonary nodules on CT.

PURPOSE: The purpose of this study was to create an algorithm to detect and classify pulmonary nodules in two categories based on their volume greater than 100 mm3 or not, using machine learning and deep learning techniques. MATERIALS AND METHOD: The dataset used to train the model was provided by the organization team of the SFR (French Radiological Society) Data Challenge 2019. An asynchronous and parallel 3-stages pipeline was developed to process all the data (a data "pre-processing" stage; a "nodule detection" stage; a "classifier" stage). Lung segmentation was achieved using 3D U-NET algorithm; nodule detection was done using 3D Retina-UNET and classifier stage with a support vector machine algorithm on selected features. Performances were assessed using area under receiver operating characteristics curve (AUROC). RESULTS: The pipeline showed good performance for pathological nodule detection and patient diagnosis. With the preparation dataset, an AUROC of 0.9058 (95% confidence interval [CI]: 0.8746-0.9362) was obtained, 87% yielding accuracy (95% CI: 84.83%-91.03%) for the "nodule detection" stage, corresponding to 86% specificity (95% CI: 82%-92%) and 89% sensitivity (95% CI: 84.83%-91.03%). CONCLUSION: A fully functional pipeline using 3D U-NET, 3D Retina-UNET and classifier stage with a support vector machine algorithm was developed, resulting in high capabilities for pulmonary nodule classification.

Artificial intelligence to predict clinical disability in patients with multiple sclerosis using FLAIR MRI.

PURPOSE: The purpose of this study was to create an algorithm that combines multiple machine-learning techniques to predict the expanded disability status scale (EDSS) score of patients with multiple sclerosis at two years solely based on age, sex and fluid attenuated inversion recovery (FLAIR) MRI data. MATERIALS AND METHODS: Our algorithm combined several complementary predictors: a pure deep learning predictor based on a convolutional neural network (CNN) that learns from the images, as well as classical machine-learning predictors based on random forest regressors and manifold learning trained using the location of lesion load with respect to white matter tracts. The aggregation of the predictors was done through a weighted average taking into account prediction errors for different EDSS ranges. The training dataset consisted of 971 multiple sclerosis patients from the "Observatoire français de la sclérose en plaques" (OFSEP) cohort with initial FLAIR MRI and corresponding EDSS score at two years. A test dataset (475 subjects) was provided without an EDSS score. Ten percent of the training dataset was used for validation. RESULTS: Our algorithm predicted EDSS score in patients with multiple sclerosis and achieved a MSE=2.2 with the validation dataset and a MSE=3 (mean EDSS error=1.7) with the test dataset. CONCLUSION: Our method predicts two-year clinical disability in patients with multiple sclerosis with a mean EDSS score error of 1.7, using FLAIR sequence and basic patient demographics. This supports the use of our model to predict EDSS score progression. These promising results should be further validated on an external validation cohort.

Abdominal musculature segmentation and surface prediction from CT using deep learning for sarcopenia assessment.

PURPOSE: The purpose of this study was to build and train a deep convolutional neural networks (CNN) algorithm to segment muscular body mass (MBM) to predict muscular surface from a two-dimensional axial computed tomography (CT) slice through L3 vertebra. MATERIALS AND METHODS: An ensemble of 15 deep learning models with a two-dimensional U-net architecture with a 4-level depth and 18 initial filters were trained to segment MBM. The muscular surface values were computed from the predicted masks and corrected with the algorithm's estimated bias. Resulting mask prediction and surface prediction were assessed using Dice similarity coefficient (DSC) and root mean squared error (RMSE) scores respectively using ground truth masks as standards of reference. RESULTS: A total of 1025 individual CT slices were used for training and validation and 500 additional axial CT slices were used for testing. The obtained mean DSC and RMSE on the test set were 0.97 and 3.7 cm2 respectively. CONCLUSION: Deep learning methods using convolutional neural networks algorithm enable a robust and automated extraction of CT derived MBM for sarcopenia assessment, which could be implemented in a clinical workflow.

Three artificial intelligence data challenges based on CT and MRI.

PURPOSE: The second edition of the artificial intelligence (AI) data challenge was organized by the French Society of Radiology with the aim to: (i), work on relevant public health issues; (ii), build large, multicentre, high quality databases; and (iii), include three-dimensional (3D) information and prognostic questions. MATERIALS AND METHODS: Relevant clinical questions were proposed by French subspecialty colleges of radiology. Their feasibility was assessed by experts in the field of AI. A dedicated platform was set up for inclusion centers to safely upload their anonymized examinations in compliance with general data protection regulation. The quality of the database was checked by experts weekly with annotations performed by radiologists. Multidisciplinary teams competed between September 11th and October 13th 2019. RESULTS: Three questions were selected using different imaging and evaluation modalities, including: pulmonary nodule detection and classification from 3D computed tomography (CT), prediction of expanded disability status scale in multiple sclerosis using 3D magnetic resonance imaging (MRI) and segmentation of muscular surface for sarcopenia estimation from two-dimensional CT. A total of 4347 examinations were gathered of which only 6% were excluded. Three independent databases from 24 individual centers were created. A total of 143 participants were split into 20 multidisciplinary teams. CONCLUSION: Three data challenges with over 1200 general data protection regulation compliant CT or MRI examinations each were organized. Future challenges should be made with more complex situations combining histopathological or genetic information to resemble real life situations faced by radiologists in routine practice.

Long-term recurrences of jaw osteoradionecrosis after apparent healing with the PENTOCLO protocol.

Osteoradionecrosis of the jaws (ORNJ) is a late complication of head and neck irradiation estimated at around 3% of irradiated patients. The PENTO protocol (Pentoxyfilline and Tocopherol), with the eventual adjunction of Clodronate (PENTOCLO), showed interesting results even in advanced ORNJ. The current literature does not describe the long-term outcomes and particularly after the completion of the protocol. The PENTO or PENTOCLO protocol should be prescribed as a life-long treatment or the outcome should be monitored at least as long as the duration of the protocol after its end.

Five simultaneous artificial intelligence data challenges on ultrasound, CT, and MRI.

PURPOSE: The goal of this data challenge was to create a structured dynamic with the following objectives: (1) teach radiologists the new rules of General Data Protection Regulation (GDPR), while building a large multicentric prospective database of ultrasound, computed tomography (CT) and MRI patient images; (2) build a network including radiologists, researchers, start-ups, large companies, and students from engineering schools, and; (3) provide all French stakeholders working together during 5 data challenges with a secured framework, offering a realistic picture of the benefits and concerns in October 2018. MATERIALS AND METHODS: Relevant clinical questions were chosen by the Société Francaise de Radiologie. The challenge was designed to respect all French ethical and data protection constraints. Multidisciplinary teams with at least one radiologist, one engineering student, and a company and/or research lab were gathered using different networks, and clinical databases were created accordingly. RESULTS: Five challenges were launched: detection of meniscal tears on MRI, segmentation of renal cortex on CT, detection and characterization of liver lesions on ultrasound, detection of breast lesions on MRI, and characterization of thyroid cartilage lesions on CT. A total of 5,170 images within 4 months were provided for the challenge by 46 radiology services. Twenty-six multidisciplinary teams with 181 contestants worked for one month on the challenges. Three challenges, meniscal tears, renal cortex, and liver lesions, resulted in an accuracy>90%. The fourth challenge (breast) reached 82% and the lastone (thyroid) 70%. CONCLUSION: Theses five challenges were able to gather a large community of radiologists, engineers, researchers, and companies in a very short period of time. The accurate results of three of the five modalities suggest that artificial intelligence is a promising tool in these radiology modalities.

Diagnosis of focal liver lesions from ultrasound using deep learning.

PURPOSE: The purpose of this study was to create an algorithm that simultaneously detects and characterizes (benign vs. malignant) focal liver lesion (FLL) using deep learning. MATERIALS AND METHODS: We trained our algorithm on a dataset proposed during a data challenge organized at the 2018 Journées Francophones de Radiologie. The dataset was composed of 367 two-dimensional ultrasound images from 367 individual livers, captured at various institutions. The algorithm was guided using an attention mechanism with annotations made by a radiologist. The algorithm was then tested on a new data set from 177 patients. RESULTS: The models reached mean ROC-AUC scores of 0.935 for FLL detection and 0.916 for FLL characterization over three shuffled three-fold cross-validations performed with the training data. On the new dataset of 177 patients, our models reached a weighted mean ROC-AUC scores of 0.891 for seven different tasks. CONCLUSION: This study that uses a supervised-attention mechanism focused on FLL detection and characterization from liver ultrasound images. This method could prove to be highly relevant for medical imaging once validated on a larger independent cohort.

Kidney cortex segmentation in 2D CT with U-Nets ensemble aggregation.

PURPOSE: This work presents our contribution to one of the data challenges organized by the French Radiology Society during the Journées Francophones de Radiologie. This challenge consisted in segmenting the kidney cortex from coronal computed tomography (CT) images, cropped around the cortex. MATERIALS AND METHODS: We chose to train an ensemble of fully-convolutional networks and to aggregate their prediction at test time to perform the segmentation. An image database was made available in 3 batches. A first training batch of 250 images with segmentation masks was provided by the challenge organizers one month before the conference. An additional training batch of 247 pairs was shared when the conference began. Participants were ranked using a Dice score. RESULTS: The segmentation results of our algorithm match the renal cortex with a good precision. Our strategy yielded a Dice score of 0.867, ranking us first in the data challenge. CONCLUSION: The proposed solution provides robust and accurate automatic segmentations of the renal cortex in CT images although the precision of the provided reference segmentations seemed to set a low upper bound on the numerical performance. However, this process should be applied in 3D to quantify the renal cortex volume, which would require a marked labelling effort to train the networks.

French updated recommendations in Stage I to III melanoma treatment and management.

As knowledge continues to develop, regular updates are necessary concerning recommendations for practice. The recommendations for the management of melanoma stages I to III were drawn up in 2005. At the request of the Société Française de Dermatologie, they have now been updated using the methodology for recommendations proposed by the Haute Autorité de Santé in France. In practice, the principal recommendations are as follows: for staging, it is recommended that the 7th edition of AJCC be used. The maximum excision margins have been reduced to 2 cm. Regarding adjuvant therapy, the place of interferon has been reduced and no validated emerging medication has yet been identified. Radiotherapy may be considered for patients in Stage III at high risk of relapse. The sentinel lymph node technique remains an option. Initial examination includes routine ultrasound as of Stage II, with other examinations being optional in stages IIC and III. A shorter strict follow-up period (3 years) is recommended for patients, but with greater emphasis on imaging.

[Update to the recommendations for management of melanoma stages I to III]. / Actualisation des recommandations de prise en charge du mélanome stades I à III.

As knowledge continues to develop, regular updates are necessary concerning recommendations for practice. The recommendations for the management of melanoma stages I to III were drawn up in 2005. At the request of the Société Française de Dermatologie, they have now been updated using the methodology for recommendations proposed by the Haute Autorité de Santé. In practice, the principal recommendations are as follows: for staging, it is recommended that the 7th edition of AJCC be used. The maximum excision margins have been reduced to 2cm. Regarding adjuvant therapy, the place of interferon has been reduced and no validated emerging medication has yet been identified. Radiotherapy may be considered for patients in stage III at high risk of relapse. The sentinel lymph node technique remains an option. Initial examination includes routine ultrasound as of stage II, with other examinations being optional in stages IIC and III. A shorter strict follow-up period (3years) is recommended for patients, but with greater emphasis on imaging.