The current diagnostic procedure for men suspected of prostate cancer is a standard extended-sextant biopsy (ie, standard biopsy). Unlike many other solid tumors for which image-guided biopsy is common, prostate cancer has traditionally been detected by randomly sampling the entire organ. However, the recent introduction of multiparametric magnetic resonance imaging (MP-MRI) now allows for imaging-based identification of prostate cancer, which may improve diagnostic accuracy for higher-risk tumors.^1-5

Image-guided tumor ablation has become a well-established hallmark of local cancer therapy. The breadth of options available in this growing field increases the need for standardization of terminology and reporting criteria to facilitate effective communication of ideas and appropriate comparison among treatments that use different technologies, such as chemical (eg, ethanol or acetic acid) ablation, thermal therapies (eg, radiofrequency, laser, microwave, focused ultrasound, and cryoablation) and newer ablative modalities such as irreversible electroporation. This updated consensus document provides a framework that will facilitate the clearest communication among investigators regarding ablative technologies. An appropriate vehicle is proposed for reporting the various aspects of image-guided ablation therapy including classification of therapies, procedure terms, descriptors of imaging guidance, and terminology for imaging and pathologic findings. Methods are addressed for standardizing reporting of technique, follow-up, complications, and clinical results. As noted in the original document from 2003, adherence to the recommendations will improve the precision of communications in this field, leading to more accurate comparison of technologies and results, and ultimately to improved patient outcomes.

Cellular diversity in tumors is a key factor for therapeutic failures and lethal outcomes of solid malignancies. Here, we determined the single-cell transcriptomic landscape of liver cancer biospecimens from 19 patients. We found varying degrees of heterogeneity in malignant cells within and between tumors and diverse landscapes of tumor microenvironment (TME). Strikingly, tumors with higher transcriptomic diversity were associated with patient's worse overall survival. We found a link between hypoxia-dependent vascular endothelial growth factor expression in tumor diversity and TME polarization. Moreover, T cells from higher heterogeneous tumors showed lower cytolytic activities. Consistent results were found using bulk genomic and transcriptomic profiles of 765 liver tumors. Our results offer insight into the diverse ecosystem of liver cancer and its impact on patient prognosis.

The use of 12-core systematic prostate biopsy is associated with diagnostic inaccuracy that contributes to both overdiagnosis and underdiagnosis of prostate cancer. Biopsies performed with magnetic resonance imaging (MRI) targeting may reduce the misclassification of prostate cancer in men with MRI-visible lesions.

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of ${n}$ stacked transformations are applied to each image during network training. The underlying assumption is that the “expected” domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented “big” data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with ${n}={9}$ transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than “shallower” stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.