Computerized assessment of background parenchymal enhancement on breast dynamic contrast-enhanced-MRI including electronic lesion removal.

Purpose: Current clinical assessment qualitatively describes background parenchymal enhancement (BPE) as minimal, mild, moderate, or marked based on the visually perceived volume and intensity of enhancement in normal fibroglandular breast tissue in dynamic contrast-enhanced (DCE)-MRI. Tumor enhancement may be included within the visual assessment of BPE, thus inflating BPE estimation due to angiogenesis within the tumor. Using a dataset of 426 MRIs, we developed an automated method to segment breasts, electronically remove lesions, and calculate scores to estimate BPE levels. Approach: A U-Net was trained for breast segmentation from DCE-MRI maximum intensity projection (MIP) images. Fuzzy c-means clustering was used to segment lesions; the lesion volume was removed prior to creating projections. U-Net outputs were applied to create projection images of both, affected, and unaffected breasts before and after lesion removal. BPE scores were calculated from various projection images, including MIPs or average intensity projections of first- or second postcontrast subtraction MRIs, to evaluate the effect of varying image parameters on automatic BPE assessment. Receiver operating characteristic analysis was performed to determine the predictive value of computed scores in BPE level classification tasks relative to radiologist ratings. Results: Statistically significant trends were found between radiologist BPE ratings and calculated BPE scores for all breast regions (Kendall correlation, p<0.001). Scores from all breast regions performed significantly better than guessing (p<0.025 from the z-test). Results failed to show a statistically significant difference in performance with and without lesion removal. BPE scores of the affected breast in the second postcontrast subtraction MIP after lesion removal performed statistically greater than random guessing across various viewing projections and DCE time points. Conclusions: Results demonstrate the potential for automatic BPE scoring to serve as a quantitative value for objective BPE level classification from breast DCE-MR without the influence of lesion enhancement.

U-Net breast lesion segmentations for breast dynamic contrast-enhanced magnetic resonance imaging.

Purpose: Given the dependence of radiomic-based computer-aided diagnosis artificial intelligence on accurate lesion segmentation, we assessed the performances of 2D and 3D U-Nets in breast lesion segmentation on dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) relative to fuzzy c-means (FCM) and radiologist segmentations. Approach: Using 994 unique breast lesions imaged with DCE-MRI, three segmentation algorithms (FCM clustering, 2D and 3D U-Net convolutional neural networks) were investigated. Center slice segmentations produced by FCM, 2D U-Net, and 3D U-Net were evaluated using radiologist segmentations as truth, and volumetric segmentations produced by 2D U-Net slices and 3D U-Net were compared using FCM as a surrogate reference standard. Fivefold cross-validation by lesion was conducted on the U-Nets; Dice similarity coefficient (DSC) and Hausdorff distance (HD) served as performance metrics. Segmentation performances were compared across different input image and lesion types. Results: 2D U-Net outperformed 3D U-Net for center slice (DSC, HD p<0.001) and volume segmentations (DSC, HD p<0.001). 2D U-Net outperformed FCM in center slice segmentation (DSC p<0.001). The use of second postcontrast subtraction images showed greater performance than first postcontrast subtraction images using the 2D and 3D U-Net (DSC p<0.05). Additionally, mass segmentation outperformed nonmass segmentation from first and second postcontrast subtraction images using 2D and 3D U-Nets (DSC, HD p<0.001). Conclusions: Results suggest that 2D U-Net is promising in segmenting mass and nonmass enhancing breast lesions from first and second postcontrast subtraction MRIs and thus could be an effective alternative to FCM or 3D U-Net.

Kaposi Sarcoma of the Gastrointestinal Tract in an Adolescent With AIDS.

Kaposi sarcoma (KS) of the gastrointestinal (GI) tract in a patient with acquired immunodeficiency syndrome (AIDS) has not been reported in an adolescent outside of Africa. We present a 16-year homosexual old male with AIDS, cutaneous KS, pulmonary KS, and gastrointestinal KS (GI-KS) lesions. Eighty percent of patients with GI-KS are asymptomatic, but our patient presented with a month-long history of dysphagia, abdominal pain, and hematochezia. Endoscopy with biopsies revealed multiple KS lesions within the stomach and lower GI tract. This novel case demonstrates the importance of considering early endoscopic screening in immunocompromised adolescents with cutaneous KS to improve morbidity and mortality.

Past, Present, and Future of Machine Learning and Artificial Intelligence for Breast Cancer Screening.

Breast cancer screening has evolved substantially over the past few decades because of advancements in new image acquisition systems and novel artificial intelligence (AI) algorithms. This review provides a brief overview of the history, current state, and future of AI in breast cancer screening and diagnosis along with challenges involved in the development of AI systems. Although AI has been developing for interpretation tasks associated with breast cancer screening for decades, its potential to combat the subjective nature and improve the efficiency of human image interpretation is always expanding. The rapid advancement of computational power and deep learning has increased greatly in AI research, with promising performance in detection and classification tasks across imaging modalities. Most AI systems, based on human-engineered or deep learning methods, serve as concurrent or secondary readers, that is, as aids to radiologists for a specific, well-defined task. In the future, AI may be able to perform multiple integrated tasks, making decisions at the level of or surpassing the ability of humans. Artificial intelligence may also serve as a partial primary reader to streamline ancillary tasks, triaging cases or ruling out obvious normal cases. However, before AI is used as an independent, autonomous reader, various challenges need to be addressed, including explainability and interpretability, in addition to repeatability and generalizability, to ensure that AI will provide a significant clinical benefit to breast cancer screening across all populations.

A Next-Generation TRK Kinase Inhibitor Overcomes Acquired Resistance to Prior TRK Kinase Inhibition in Patients with TRK Fusion-Positive Solid Tumors.

Larotrectinib, a selective TRK tyrosine kinase inhibitor (TKI), has demonstrated histology-agnostic efficacy in patients with TRK fusion-positive cancers. Although responses to TRK inhibition can be dramatic and durable, duration of response may eventually be limited by acquired resistance. LOXO-195 is a selective TRK TKI designed to overcome acquired resistance mediated by recurrent kinase domain (solvent front and xDFG) mutations identified in multiple patients who have developed resistance to TRK TKIs. Activity against these acquired mutations was confirmed in enzyme and cell-based assays and in vivo tumor models. As clinical proof of concept, the first 2 patients with TRK fusion-positive cancers who developed acquired resistance mutations on larotrectinib were treated with LOXO-195 on a first-in-human basis, utilizing rapid dose titration guided by pharmacokinetic assessments. This approach led to rapid tumor responses and extended the overall duration of disease control achieved with TRK inhibition in both patients.Significance: LOXO-195 abrogated resistance in TRK fusion-positive cancers that acquired kinase domain mutations, a shared liability with all existing TRK TKIs. This establishes a role for sequential treatment by demonstrating continued TRK dependence and validates a paradigm for the accelerated development of next-generation inhibitors against validated oncogenic targets. Cancer Discov; 7(9); 963-72. ©2017 AACR.See related commentary by Parikh and Corcoran, p. 934This article is highlighted in the In This Issue feature, p. 920.

High-resolution chromosome ideogram representation of recognized genes for bipolar disorder.

Bipolar disorder (BPD) is genetically heterogeneous with a growing list of BPD associated genes reported in recent years resulting from increased genetic testing using advanced genetic technology, expanded genomic databases, and better awareness of the disorder. We compiled a master list of recognized susceptibility and genes associated with BPD identified from peer-reviewed medical literature sources using PubMed and by searching online databases, such as OMIM. Searched keywords were related to bipolar disorder and genetics. Our compiled list consisted of 290 genes with gene names arranged in alphabetical order in tabular form with source documents and their chromosome location and gene symbols plotted on high-resolution human chromosome ideograms. The identified genes impacted a broad range of biological pathways and processes including cellular signaling pathways particularly cAMP and calcium (e.g., CACNA1C, CAMK2A, CAMK2D, ADCY1, ADCY2); glutamatergic (e.g., GRIK1, GRM3, GRM7), dopaminergic (e.g., DRD2, DRD4, COMT, MAOA) and serotonergic (e.g., HTR1A, HTR2A, HTR3B) neurotransmission; molecular transporters (e.g., SLC39A3, SLC6A3, SLC8A1); and neuronal growth (e.g., BDNF, IGFBP1, NRG1, NRG3). The increasing prevalence of BPD calls for better understanding of the genetic etiology of this disorder and associations between the observed BPD phenotype and genes. Visual representation of genes for bipolar disorder becomes a tool enabling clinical and laboratory geneticists, genetic counselors, and other health care providers and researchers easy access to the location and distribution of currently recognized BPD associated genes. Our study may also help inform diagnosis and advance treatment developments for those affected with this disorder and improve genetic counseling for families.