The Milan criteria have been adopted by United Network for Organ Sharing (UNOS) to preoperatively assess outcome in patients with hepatocellular carcinoma (HCC) who receive orthotopic liver ...transplantation (OLT). These criteria rely solely on radiographic appearances of the tumor, providing no measure of tumor biology. Recurrence rates, therefore, remain around 20% for patients within the criteria. The neutrophil-lymphocyte ratio (NLR) is an indicator of inflammatory status previously established as a prognostic indicator in colorectal liver metastases. We aimed to determine whether NLR predicts outcome in patients undergoing OLT for HCC.
Analysis of patients undergoing OLT for HCC between 2001 and 2007 at our institution. A NLR > or =5 was considered to be elevated.
: A total of 150 patients were identified, with 13 patients having an elevated NLR. Of these, 62% developed recurrence compared with 14% with normal NLR (P < 0.0001). The disease-free survival for patients with high NLR was significantly worse than that for patients with normal NLR (1-, 3-, and 5-year survivals of 38%, 25%, and 25% vs. 92%, 85%, and 75%, P < 0.0001). Patients with high NLR also had poorer overall survival (5-year survival, 28% vs. 64%, P = 0.001). Patients within Milan with an elevated NLR had significantly poorer disease-free survival than those with normal NLR within Milan (5-year survival, 30% vs. 81%, P < 0.0001). On univariate analysis, 9 factors including an NLR > or =5 were significant predictors of poor disease-free survival. However, only a raised NLR remained significant on multivariate analysis (P = 0.005, HR: 19.98).
Elevated NLR significantly increases the risk for tumor recurrence and recipient death. Preoperative NLR measurement may provide a simple method of identifying patients with poorer prognosis and act as an adjunct to Milan in determining, which patients benefit most from OLT.
In this paper, a novel two-branch neural network model structure is proposed for multimodal emotion recognition, which consists of a time synchronous branch (TSB) and a time asynchronous branch ...(TAB). To capture correlations between each word and its acoustic realisation, the TSB combines speech and text modalities at each input window frame and then uses pooling across time to form a single embedding vector. The TAB, by contrast, provides cross-utterance information by integrating sentence text embeddings from a number of context utterances into another embedding vector. The final emotion classification uses both the TSB and the TAB embeddings. Experimental results on the IEMOCAP dataset demonstrate that the two-branch structure achieves state-of-the-art results in 4-way classification with all common test setups. When using automatic speech recognition (ASR) output instead of manually transcribed reference text, it is shown that the cross-utterance information considerably improves robustness against ASR errors. Furthermore, by incorporating an extra class for all the other emotions, the final 5-way classification system with ASR hypotheses can be viewed as a prototype for more realistic emotion recognition systems.
This paper investigates the use of parameterised sigmoid and rectified linear unit (ReLU) hidden activation functions in deep neural network (DNN) speaker adaptation. The sigmoid and ReLU ...parameterisation schemes from a previous study for speaker independent (SI) training are used. An adaptive linear factor associated with each sigmoid or ReLU hidden unit is used to scale the unit output value and create a speaker dependent (SD) model. Hence, DNN adaptation becomes re-weighting the importance of different hidden units for every speaker. This adaptation scheme is applied to both hybrid DNN acoustic modelling and DNN-based bottleneck (BN) feature extraction. Experiments using multi-genre British English television broadcast data show that the technique is effective in both directly adapting DNN acoustic models and the BN features, and combines well with other DNN adaptation techniques. Reductions in word error rate are consistently obtained using parameterised sigmoid and ReLU activation function for multiple hidden layer adaptation.
It is critical to balance waitlist mortality against posttransplant mortality.
Our objective was to devise a scoring system that predicts recipient survival at 3 months following liver ...transplantation to complement MELD‐predicted waitlist mortality.
Univariate and multivariate analysis on 21 673 liver transplant recipients identified independent recipient and donor risk factors for posttransplant mortality. A retrospective analysis conducted on 30 321 waitlisted candidates reevaluated the predictive ability of the Model for End‐Stage Liver Disease (MELD) score.
We identified 13 recipient factors, 4 donor factors and 2 operative factors (warm and cold ischemia) as significant predictors of recipient mortality following liver transplantation at 3 months. The Survival Outcomes Following Liver Transplant (SOFT) Score utilized 18 risk factors (excluding warm ischemia) to successfully predict 3‐month recipient survival following liver transplantation.
This analysis represents a study of waitlisted candidates and transplant recipients of liver allografts after the MELD score was implemented. Unlike MELD, the SOFT score can accurately predict 3‐month survival following liver transplantation. The most significant risk factors were previous transplantation and life support pretransplant. The SOFT score can help clinicians determine in real time which candidates should be transplanted with which allografts. Combined with MELD, SOFT can better quantify survival benefit for individual transplant procedures.
Unlike MELD, the SOFT score predicts 3‐month survival following liver transplantation, with the most significant factors being previous transplantation and life‐support pre‐transplant. See also editorial by Freeeman in this issue on page 2483.
Background and purpose:
Ifosfamide nephrotoxicity is a serious adverse effect for children undergoing cancer chemotherapy. Our recent in vitro studies have shown that the antioxidant N‐acetylcysteine ...(NAC), which is used extensively as an antidote for paracetamol (acetaminophen) poisoning in children, protects renal tubular cells from ifosfamide‐induced toxicity at a clinically relevant concentration. To further validate this observation, an animal model of ifosfamide‐induced nephrotoxicity was used to determine the protective effect of NAC.
Experimental approach:
Male Wistar albino rats were injected intraperitoneally with saline, ifosfamide (50 or 80 mg kg−1 daily for 5 days), NAC (1.2 g kg−1 daily for 6 days) or ifosfamide+NAC (for 6 days). Twenty‐four hours after the last injection, rats were killed and serum and urine were collected for biochemical analysis. Kidney tissues were obtained for analysis of glutathione, glutathione S‐transferase and lipid peroxide levels as well as histology analysis.
Key results:
NAC markedly reduces the severity of renal dysfunction induced by ifosfamide with a significant decrease in elevations of serum creatinine (57.8±2.3 vs 45.25±2.1 μmol l−1) as well as a reduced elevation of β2‐microglobulin excretion (25.44±3.3 vs 8.83±1.3 nmol l−1) and magnesium excretion (19.5±1.5 vs 11.16±1.5 mmol l−1). Moreover, NAC significantly improved the ifosfamide‐induced glutathione depletion and the decrease of glutathione S‐transferase activity, lowered the elevation of lipid peroxides and prevented typical morphological damages in renal tubules and glomeruli.
Conclusions and implications:
Our results suggest a potential therapeutic role for NAC in paediatric patients in preventing ifosfamide nephrotoxicity.
British Journal of Pharmacology (2008) 153, 1364–1372; doi:10.1038/bjp.2008.15; published online 18 February 2008
Significant progress has recently been made in speaker diarisation after the introduction of d-vectors as speaker embeddings extracted from neural network (NN) speaker classifiers for clustering ...speech segments. To extract better-performing and more robust speaker embeddings, this paper proposes a c-vector method by combining multiple sets of complementary d-vectors derived from systems with different NN components. Three structures are used to implement the c-vectors, namely 2D self-attentive, gated additive, and bilinear pooling structures, relying on attention mechanisms, a gating mechanism, and a low-rank bilinear pooling mechanism respectively. Furthermore, a neural-based single-pass speaker diarisation pipeline is also proposed in this paper, which uses NNs to achieve voice activity detection, speaker change point detection, and speaker embedding extraction. Experiments and detailed analyses are conducted on the challenging AMI and NIST RT05 datasets which consist of real meetings with 4–10 speakers and a wide range of acoustic conditions. For systems trained on the AMI training set, relative speaker error rate (SER) reductions of 13% and 29% are obtained by using c-vectors instead of d-vectors on the AMI dev and eval sets respectively, and a relative SER reduction of 15% in SER is observed on RT05, which shows the robustness of the proposed methods. By incorporating VoxCeleb data into the training set, the best c-vector system achieved 7%, 17% and 16% relative SER reduction compared to the d-vector on the AMI dev, eval and RT05 sets respectively.
•A complete single pass neural network-based diarisation pipeline•2D self-attentive, gated additive and bilinear pooling combination methods•Stacked combination using 2D self-attentive and a bilinear pooling structure•29% relative SER reductions on the AMI eval set using AMI training data•17% relative SER reductions on AMI eval set using additional VoxCeleb training data
BACKGROUND.Although short-term outcomes for liver transplantation have improved, patient and graft survival are limited by infection, cancer, and other complications of immunosuppression. Rapid ...induction of tolerance after liver transplantation would decrease these complications, improving survival and quality of life. Tolerance to kidneys, but not thoracic organs or islets, has been achieved in nonhuman primates and humans through the induction of transient donor chimerism. Since the liver is considered to be tolerogenic, we tested the hypothesis that the renal transplant transient chimerism protocol would induce liver tolerance.
METHODS.Seven cynomolgus macaques received immune conditioning followed by simultaneous donor bone marrow and liver transplantation. The more extensive liver surgery required minor adaptations of the kidney protocol to decrease complications. All immunosuppression was discontinued on postoperative day (POD) 28. Peripheral blood chimerism, recipient immune reconstitution, liver function tests, and graft survival were determined.
RESULTS.The level and duration of chimerism in liver recipients were comparable to those previously reported in renal transplant recipients. However, unlike in the kidney model, the liver was rejected soon after immunosuppression withdrawal. Rejection was associated with proliferation of recipient CD8 T effector cells in the periphery and liver, increased serum interleukin (IL)-6 and IL-2, but peripheral regulatory T cell (Treg) numbers did not increase. Antidonor antibody was also detected.
CONCLUSIONS.These data show the transient chimerism protocol does not induce tolerance to livers, likely due to greater CD8 T cell responses than in the kidney model. Successful tolerance induction may depend on greater control or deletion of CD8 T cells in this model.
A significant cost in obtaining acoustic training data is the generation of accurate transcriptions. When no transcription is available,
unsupervised training techniques must be used. Furthermore, ...the use of discriminative training has become a standard feature of state-of-the-art large vocabulary continuous speech recognition (LVCSR) system. In unsupervised training, unlabelled data are recognised using a seed model and the hypotheses from the recognition system are used as transcriptions for training. In contrast to maximum likelihood training, the performance of discriminative training is more sensitive to the quality of the transcriptions. One approach to deal with this issue is data selection, where only well recognised data are selected for training. More effectively, as the key contribution of this work, an active learning technique,
directed manual transcription, can be used. Here a relatively small amount of poorly recognised data is manually transcribed to supplement the automatic transcriptions. Experiments show that using the data selection approach for discriminative training yields disappointing performance improvement on the data which is mismatched to the training data type of the seed model. However, using the directed manual transcription approach can yield significant improvements in recognition accuracy on all types of data.
This paper describes, and evaluates on a large scale, the lattice based framework for discriminative training of large vocabulary speech recognition systems based on Gaussian mixture hidden Markov ...models (HMMs). This paper concentrates on the maximum mutual information estimation (MMIE) criterion which has been used to train HMM systems for conversational telephone speech transcription using up to 265 hours of training data. These experiments represent the largest-scale application of discriminative training techniques for speech recognition of which the authors are aware. Details are given of the MMIE lattice-based implementation used with the extended Baum-Welch algorithm, which makes training of such large systems computationally feasible. Techniques for improving generalization using acoustic scaling and weakened language models are discussed. The overall technique has allowed the estimation of triphone and quinphone HMM parameters which has led to significant reductions in word error rate for the transcription of conversational telephone speech relative to our best systems trained using maximum likelihood estimation (MLE). This is in contrast to some previous studies, which have concluded that there is little benefit in using discriminative training for the most difficult large vocabulary speech recognition tasks. The lattice MMIE-based discriminative training scheme is also shown to out-perform the frame discrimination technique. Various properties of the lattice-based MMIE training scheme are investigated including comparisons of different lattice processing strategies (full search and exact-match) and the effect of lattice size on performance. Furthermore a scheme based on the linear interpolation of the MMIE and MLE objective functions is shown to reduce the danger of over-training. It is shown that HMMs trained with MMIE benefit as much as MLE-trained HMMs from applying model adaptation using maximum likelihood linear regression (MLLR). This has allowed the straightforward integration of MMIE-trained HMMs into complex multi-pass systems for transcription of conversational telephone speech and has contributed to our MMIE-trained systems giving the lowest word error rates in both the 2000 and 2001 NIST Hub5 evaluations.
Mandarin Chinese is based on characters which are syllabic in nature and morphological in meaning. All spoken languages have syllabiotactic rules which govern the construction of syllables and their ...allowed sequences. These constraints are not as restrictive as those learned from word sequences, but they can provide additional useful linguistic information. Hence, it is possible to improve speech recognition performance by appropriately combining these two types of constraints. For the Chinese language considered in this paper, character level language models (LMs) can be used as a first level approximation to allowed syllable sequences. To test this idea, word and character level n-gram LMs were trained on 2.8 billion words (equivalent to 4.3 billion characters) of texts from a wide collection of text sources. Both hypothesis and model based combination techniques were investigated to combine word and character level LMs. Significant character error rate reductions up to 7.3% relative were obtained on a state-of-the-art Mandarin Chinese broadcast audio recognition task using an adapted history dependent multi-level LM that performs a log-linearly combination of character and word level LMs. This supports the hypothesis that character or syllable sequence models are useful for improving Mandarin speech recognition performance.