Backpropagation Neural Network for Processing of Missing Data in Breast Cancer Detection

BackgroundA complete dataset is essential for biomedical implementation. Due to the limitation of objective or subjective factors, missing data often occurs, which exerts uncertainty in the subsequent data processing. Commonly used methods of interpolation are interpolating substitute values that keep minimum error. Some applications of statistics are usually used for handling this problem.MethodsWe are trying to find a higher performance interpolation method compared with the usual statistic methods, by using artificial intelligence which is in full swing today. The prediction and classification of backpropagation neural network are used in this paper, describes a missing data interpolation method to propose the interpolation model that mines association rules in the data. In the experiment, depending on a multi-layer network structure, the model is trained and tested by sample data, constantly revises network weights and thresholds. The error function decreases along the negative gradient direction and approaches the expected real output. The model is validated on the breast cancer dataset, and we select real samples from the data set for validation, moreover, add four traditional methods as a control group.ResultsThe proposed method has great performance improvement in the interpolation of missing data. Experimental results show that the interpolation accuracy of our proposed method (84%) is higher than four traditional methods (1.33%, 74.67%, 73.33%, 77.33%) as mentioned in this paper, BPNN stays low in MSE evaluation. Finally, we analyze the performance of various methods in processing missing data.ConclusionsThe study in this paper has estimated missing data with high accuracy as much as possible to reduce the negative impact in the diagnosis of real life. At the same time, it can also assist in missing data processing in the biomedical field.     

Thermal boost combined with interstitial brachytherapy in breast conserving therapy – Assessment of early toxicity

Background

Hyperthermia (HT) causes a direct damage to cancerous cells and/or sensitize them to radiotherapy with usually minimal injury to normal tissues. Adjuvant HT is probably one of the most effective radiation sensitizers known and works best when delivered simultaneously with radiation. In breast conserving therapy, irradiation has to minimize the risk of local relapse within the treated breast, especially in an area of a tumor bed. Brachytherapy boost reduces 5-year local recurrence rate to mean 5,5%, so there still some place for further improvement. The investigated therapeutic option is an adjuvant single session of local HT (thermal boost) preceding standard CT-based multicatheter interstitial HDR brachytherapy boost in order to increase the probability of local cure.

Aim

To report the short-term results in regard to early toxicity of high-dose-rate (HDR) brachytherapy (BT) boost with or without interstitial microwave hyperthermia (MV HT) for early breast cancer patients treated with breast conserving therapy (BCT).

Materials and methods

Between February 2006 and December 2007, 57 stage IA–IIIA breast cancer patients received a 10 Gy HDR BT boost after conservative surgery and 42.5–50 Gy whole breast irradiation (WBI) ± adjuvant chemotherapy. 32 patients (56.1%) were treated with additional pre-BT single session of interstitial MW HT to a tumor bed (multi-catheter technique). Reference temperature was 43 °C and therapeutic time (TT) was 1 h. Incidence, severity and duration of radiodermatitis, skin oedema and skin erythema in groups with (I) or without HT (II) were assessed, significant p-value ≤ 0.05.

Results

Median follow-up was 40 months. Local control was 100% and distant metastasis free survival was 91.1%. HT sessions (median): reference temperature 42.2 °C, therapeutic time (TT) 61.4 min, total thermal dose 42 min and a gap between HT and BT 30 min. Radiodermatitis grades I and II occurred in 24 and 6 patients, respectively, differences between groups I and II were not significant. Skin oedema and erythema occurred in 48 (85.7%) and 36 (64.3%) cases, respectively, and were equally distributed between the groups. The incidence and duration of skin oedema differed between the subgroups treated with different fractionation protocols of WBI, p = 0.006. Skin oedema was present up to 12 months. No difference in pattern of oedema regression between groups I and II was observed, p = 0.933.

Conclusion

Additional thermal boost preceding standard HDR BT boost has a potential of further improvement in breast cancer local control in BCT. Pre-BT hyperthermia did not increase early toxicity in patients treated with BCT and was well tolerated. All side effects of combined treatment were transient and were present for up to 12 months. The increase in incidence of skin oedema was related to hypofractionated protocols of WBI. The study has to be randomized and continued on a larger group of breast cancer patients to verify the potential of local control improvement and to assess the profile of late toxicity.     

Sentinel node biopsy in breast cancer using infrared laser system first experience with PDE camera

Background

Sentinel node biopsy (SNB) is a gold standard in staging of early breast cancer. Nowadays, routine mapping of lymphatic tract is based on two tracers: human albumin with radioactive technetium, with or without blue dye. Recent years have seen a search for new tracers to examine sentinel node as well as lymphatic network. One of them is indocyanine green (ICG) visible in infrared light.

Aim

The aim of this study is to evaluate clinical usage of ICG in comparison with standard tracer, i.e. nanocoll, in SNB of breast cancer patients.

Materials and methods

In the 1st Department of Surgical Oncology and General Surgery, Greater Poland Cancer Centre, Poznań, 13 female breast cancer patients have benn operated since September 2010. All these patients had sentinel node biopsy with nanocoll (human albumin with radioactive technetium), and with indocyanine green. The feasibility of this new method was assessed in comparison with the standard nanocoll.

Results

A lymphatic network between the place of injection of ICG and sentinel node was seen in infrared light. An area where a sentinel node was possibly located was confirmed by gamma probe. Sensitivity of this method was 100%.

Conclusion

SNB using ICG is a new, promising diagnostics technique. This procedure is not without drawbacks; nevertheless it opens new horizons in lymphatic network diagnostics.     

Down-regulation of kallikrein-related peptidase 5 (<Emphasis Type="Italic">KLK5</Emphasis>) expression in breast cancer patients: a biomarker for the differential diagnosis of breast lesions

Background  

Kallikrein-related peptidase 5 (KLK5) is a secreted trypsin-like protease of the KLK family, encoded by the KLK5 gene. KLK5 has been found to cleave various extracellular matrix components, as well as to activate several other KLK proteases, triggering the stimulation of tissue microenvironment proteolytic cascades.     

Down-regulation of Tripartite-motif containing 22 expression in breast cancer is associated with a lack of p53-mediated induction

Tripartite-motif containing 22 (TRIM22) is a direct p53 target gene and inhibits the clonogenic growth of leukemic cells. Its expression in Wilms tumors is negatively associated with disease relapse. This study addresses if TRIM22 expression is de-regulated in breast carcinoma. Western blotting analysis of a panel of 10 breast cancer cell lines and 3 non-malignant mammary epithelial cell lines with a well-characterized TRIM22 monoclonal antibody showed that TRIM22 protein is greatly under-expressed in breast cancer cells as compared to non-malignant cell lines. Similarly, TRIM22 protein is significantly down-regulated in breast tumors as compared to matched normal breast tissues. Study of cell lines with methylation inhibitor and bisulfite sequencing indicates that TRIM22 promoter hypermethylation may not be the cause for TRIM22 under-expression in breast cancer. Instead, we found that TRIM22 protein level correlates strongly (R = 0.79) with p53 protein level in normal breast tissue, but this correlation is markedly impaired (R = 0.48) in breast cancer tissue, suggesting that there is some defects in p53 regulation of TRIM22 gene in breast cancer. This notion is supported by cell line studies, which showed that TRIM22 was no longer inducible by p53-activating genotoxic drugs in breast cancer cell lines and in a p53 null cell line H1299 transfected with wild type p53. In conclusion, this study shows that TRIM22 is greatly under-expressed in breast cancer. p53 dysfunction may be one of the mechanisms for TRIM22 down-regulation.     

A New Signaling Pathway (JAK-Fes-phospholipase D) That Is Enhanced in Highly Proliferative Breast Cancer Cells

The products of the oncogene Fes and JAK3 are tyrosine kinases, whose expressions are elevated in tumor growth, angiogenesis, and metastasis. Phosphatidic acid, as synthesized by phospholipase D (PLD), enhances cancer cell survival. We report a new signaling pathway that integrates the two kinases with the lipase. A new JAK3-Fes-PLD2 axis is responsible for the highly proliferative phenotype of MDA-MB-231 breast cancer cells. Conversely, this pathway is maintained at a low rate of expression and activity levels in untransformed cells such as MCF10A. We also deciphered the inter-regulation that exists between the two kinases (JAK3 and the oncogene Fes) and between these two kinases and the lipase (PLD2). Whereas JAK3 and Fes marginally activate PLD2 in non-transformed cells, these kinases greatly enhance (>200%) PLD activity following protein-protein interaction through the SH2 domain and the Tyr-415 residue of PLD2. We also found that phosphatidic acid enhances Fes activity in MDA-MB-231 cells providing a positive activation loop between Fes and PLD2. In summary, the JAK3, Fes and PLD2 interactions in transformed cells maintain PLD2 at an enhanced level that leads to abnormal cell growth. Modulating this new JAK3-Fes-PLD2 pathway could be important to control the highly invasive phenotype of breast cancer cells.     

TNF inhibitor suppresses bone metastasis in a breast cancer cell line

In the evolution of cancer, tumor necrosis factor-alpha (TNF-α) plays a paradoxical role. High doses induce significant anticancer effects, but conversely, physiologic and pathologic levels of TNF-α may be involved in cancer promotion, tumor growth, and metastasis.Infliximab is a chimeric murine monoclonal antibody that binds with high affinity to soluble and membrane TNF-α and inhibits binding of TNF-α to its receptors. In the present study, we investigated the effect of infliximab, a TNF-α antagonist, on breast cancer aggressiveness and bone metastases.Infliximab greatly reduced cell motility and bone metastases in a metastatic breast cancer cell line, MDA-MB-231. The mechanism of bone metastasis inhibition involved decreased expression of CXC chemokine receptor 4 (CXCR4) and increased expression of decorin, which is the prototype of an expanding family of small leucine-rich proteoglycans. These results suggest a novel role for TNF-α inhibition in the reduction or prevention of bone metastases in this breast cancer model. Our study suggests that inhibition of TNF-α using infliximab may become a preventive therapeutic option for breast cancer.     

Technical challenges for FLASH proton therapy

There is growing interest in the radiotherapy community in the application of FLASH radiotherapy, wherein the dose is delivered to the entire treatment volume in less than a second. Early pre-clinical evidence suggests that these extremely high dose rates provide significant sparing of healthy tissue compared to conventional radiotherapy without reducing the damage to cancerous cells. This interest has been reflected in the proton therapy community, with early tests indicating that the FLASH effect is also present with high dose rate proton irradiation.In order to deliver clinically relevant doses at FLASH dose rates significant technical hurdles must be overcome in the accelerator technology before FLASH proton therapy can be realised. Of these challenges, increasing the average current from the present clinical range of 1–10 nA to in excess of 100 nA is at least feasible with existing technology, while the necessity for rapid energy adjustment on the order of a few milliseconds is much more challenging, particularly for synchrotron-based systems. However, the greatest challenge is to implement full pencil beam scanning, where scanning speeds 2 orders of magnitude faster than the existing state-of-the-art will be necessary, along with similar improvements in the speed and accuracy of associated dosimetry. Hybrid systems utilising 3D-printed patient specific range modulators present the most likely route to clinical delivery. However, to correctly adapt and develop existing technology to meet the challenges of FLASH, more pre-clinical studies are needed to properly establish the beam parameters that are necessary to produce the FLASH effect.