Prediction of Lung Nodule Progression with an Uncertainty-Aware Hierarchical Probabilistic Network.

Predicting whether a lung nodule will grow, remain stable or regress over time, especially early in its follow-up, would help doctors prescribe personalized treatments and better surgical planning. However, the multifactorial nature of lung tumour progression hampers the identification of growth patterns. In this work, we propose a deep hierarchical generative and probabilistic network that, given an initial image of the nodule, predicts whether it will grow, quantifies its future size and provides its expected semantic appearance at a future time. Unlike previous solutions, our approach also estimates the uncertainty in the predictions from the intrinsic noise in medical images and the inter-observer variability in the annotations. The evaluation of this method on an independent test set reported a future tumour growth size mean absolute error of 1.74 mm, a nodule segmentation Dice's coefficient of 78% and a tumour growth accuracy of 84% on predictions made up to 24 months ahead. Due to the lack of similar methods for providing future lung tumour growth predictions, along with their associated uncertainty, we adapted equivalent deterministic and alternative generative networks (i.e., probabilistic U-Net, Bayesian test dropout and Pix2Pix). Our method outperformed all these methods, corroborating the adequacy of our approach.

Hepatic Rupture as the Initial Presentation of an EGFR-Mutated Lung Adenocarcinoma: A Case Report.

Hepatic rupture is a rare complication of solid tumor malignancies, notably in lung adenocarcinomas, and carries an extremely poor overall prognosis. Epidermal growth factor receptor (EGFR) mutations in lung adenocarcinoma predict benefit with tyrosine kinase inhibitors (TKIs). This case report describes a female patient who presented with a metastatic hepatic rupture and was subsequently diagnosed with EGFR-mutated lung adenocarcinoma. The tumor had an impressive response to TKI inhibitor treatment, reversing her extremely poor, short-term prognosis. We believe this unique case sheds light on the treatment management of hepatic ruptures and supports the high response rate seen with TKIs in EGFR-mutated lung cancers, regardless of the patient's performance status.

Aggressive Pituitary Macroadenoma Treated With Capecitabine and Temozolomide Chemotherapy Combination in a Patient With Nelson's Syndrome: A Case Report.

Nelson's syndrome is considered a severe side effect that can occur after a total bilateral adrenalectomy in patients with Cushing's disease. It usually presents with clinical manifestations of an enlarging pituitary tumor including visual and cranial nerve alterations, and if not treated, can cause death through local brain compression or invasion. The first therapeutic option is surgery but in extreme cases of inaccessible or resistant aggressive pituitary tumors; the off-label use of chemotherapy with capecitabine and temozolomide can be considered. However, the use of this treatment is controversial due to adverse events, lack of complete response, and inability to predict results. We present the case of a 48-year-old man diagnosed with Nelson's syndrome with prolonged partial response and significant clinical benefit to treatment with capecitabine and temozolomide.

Re-Identification and growth detection of pulmonary nodules without image registration using 3D siamese neural networks.

Lung cancer follow-up is a complex, error prone, and time consuming task for clinical radiologists. Several lung CT scan images taken at different time points of a given patient need to be individually inspected, looking for possible cancerogenous nodules. Radiologists mainly focus their attention in nodule size, density, and growth to assess the existence of malignancy. In this study, we present a novel method based on a 3D siamese neural network, for the re-identification of nodules in a pair of CT scans of the same patient without the need for image registration. The network was integrated into a two-stage automatic pipeline to detect, match, and predict nodule growth given pairs of CT scans. Results on an independent test set reported a nodule detection sensitivity of 94.7%, an accuracy for temporal nodule matching of 88.8%, and a sensitivity of 92.0% with a precision of 88.4% for nodule growth detection.