Xiaosong Wang

Speech recognition was measured as a function of spectral resolution (number of spectral channels) and speech-to-noise ratio in normal-hearing (NH) and cochlear-implant (CI) listeners. Vowel, consonant, word, and sentence recognition were measured in five normal-hearing listeners, ten listeners with the Nucleus-22 cochlear implant, and nine listeners with the Advanced Bionics Clarion cochlear implant. Recognition was measured as a function of the number of spectral channels (noise bands or electrodes) at signal-to-noise ratios of + 15, + 10, +5, 0 dB, and in quiet. Performance with three different speech processing strategies (SPEAK, CIS, and SAS) was similar across all conditions, and improved as the number of electrodes increased (up to seven or eight) for all conditions. For all noise levels, vowel and consonant recognition with the SPEAK speech processor did not improve with more than seven electrodes, while for normal-hearing listeners, performance continued to increase up to at least 20 channels. Speech recognition on more difficult speech materials (word and sentence recognition) showed a marginally significant increase in Nucleus-22 listeners from seven to ten electrodes. The average implant score on all processing strategies was poorer than scores of NH listeners with similar processing. However, the best CI scores were similar to the normal-hearing scores for that condition (up to seven channels). CI listeners with the highest performance level increased in performance as the number of electrodes increased up to seven, while CI listeners with low levels of speech recognition did not increase in performance as the number of electrodes was increased beyond four. These results quantify the effect of number of spectral channels on speech recognition in noise and demonstrate that most CI subjects are not able to fully utilize the spectral information provided by the number of electrodes used in their implant.

The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.

Extracting, harvesting, and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. Meanwhile, vast amounts of clinical annotations have been collected and stored in hospitals' picture archiving and communication systems (PACS). These types of annotations, also known as bookmarks in PACS, are usually marked by radiologists during their daily workflow to highlight significant image findings that may serve as reference for later studies. We propose to mine and harvest these abundant retrospective medical data to build a large-scale lesion image dataset. Our process is scalable and requires minimum manual annotation effort. We mine bookmarks in our institute to develop DeepLesion, a dataset with 32,735 lesions in 32,120 CT slices from 10,594 studies of 4,427 unique patients. There are a variety of lesion types in this dataset, such as lung nodules, liver tumors, enlarged lymph nodes, and so on. It has the potential to be used in various medical image applications. Using DeepLesion, we train a universal lesion detector that can find all types of lesions with one unified framework. In this challenging task, the proposed lesion detector achieves a sensitivity of 81.1% with five false positives per image.

Chest X-rays are one of the most common radiological examinations in daily clinical routines. Reporting thorax diseases using chest X-rays is often an entry-level task for radiologist trainees. Yet, reading a chest X-ray image remains a challenging job for learning-oriented machine intelligence, due to (1) shortage of large-scale machine-learnable medical image datasets, and (2) lack of techniques that can mimic the high-level reasoning of human radiologists that requires years of knowledge accumulation and professional training. In this paper, we show the clinical free-text radiological reportscan be utilized as a priori knowledge for tackling these two key problems. We propose a novel Text-Image Embedding network (TieNet) for extracting the distinctive image and text representations. Multi-level attention models are integrated into an end-to-end trainable CNN-RNN architecture for highlighting the meaningful text words and image regions. We first apply TieNet to classify the chest X-rays by using both image features and text embeddings extracted from associated reports. The proposed auto-annotation framework achieves high accuracy (over 0.9 on average in AUCs) in assigning disease labels for our hand-label evaluation dataset. Furthermore, we transform the TieNet into a chest X-ray reporting system. It simulates the reporting process and can output disease classification and a preliminary report together. The classification results are significantly improved (6% increase on average in AUCs) compared to the state-of-the-art baseline on an unseen and hand-labeled dataset (OpenI).

BACKGROUND: Increasing studies have shown that circRNA is closely related to the carcinogenesis and development of many cancers. However, biological functions and the underlying molecular mechanism of circRNAs in triple-negative breast cancer (TNBC) remain largely unclear so far. METHODS: Here, we investigated the expression pattern of circRNAs in four pairs of TNBC tissues and paracancerous normal tissues using RNA-sequencing. The expression and prognostic significance of circSEPT9 were evaluated with qRT-PCR and in situ hybridization in two TNBC cohorts. The survival curves were drawn by the Kaplan-Meier method, and statistical significance was estimated with the log-rank test. A series of in vitro and in vivo functional experiments were executed to investigate the role of circSEPT9 in the carcinogenesis and development of TNBC. Mechanistically, we explored the potential regulatory effects of E2F1 and EIF4A3 on biogenesis of circSEPT9 with chromatin immunoprecipitation (ChIP), luciferase reporter and RNA immunoprecipitation (RIP) assays. Furthermore, fluorescent in situ hybridization (FISH), luciferase reporter and biotin-coupled RNA pull-down assays were implemented to verify the relationship between the circSEPT9 and miR-637 in TNBC. RESULTS: Increased expression of circSEPT9 was found in TNBC tissues, which was positively correlated with advanced clinical stage and poor prognosis. Knockdown of circSEPT9 significantly suppressed the proliferation, migration and invasion of TNBC cells, induced apoptosis and autophagy in TNBC cells as well as inhibited tumor growth and metastasis in vivo. Whereas up-regulation of circSEPT9 exerted opposite effects. Further mechanism research demonstrated that circSEPT9 could regulate the expression of Leukemia Inhibitory Factor (LIF) via sponging miR-637 and activate LIF/Stat3 signaling pathway involved in progression of TNBC. More importantly, we discovered that E2F1 and EIF4A3 might promote the biogenesis of circSEPT9. CONCLUSIONS: Our data reveal that the circSEPT9 mediated by E2F1 and EIF4A3 facilitates the carcinogenesis and development of triple-negative breast cancer through circSEPT9/miR-637/LIF axis. Therefore, circSEPT9 could be used as a potential prognostic marker and therapeutical target for TNBC.