No description available.

No description available.

Object detection on natural images has become a single-stage end-to-end process thanks to recent breakthroughs on deep neural networks. By contrast, automated pulmonary nodule detection is usually a three steps method: lung segmentation, generation of nodule candidates and false positive reduction. This project tackles the nodule detection problem with a single stage modelusing a deep neural network. Pulmonary nodules have unique shapes and characteristics which are not present outside of the lungs. We expect the model to capture these characteristics and to only focus on elements inside the lungs when working on raw CT scans (without the segmentation). Nodules are small, distributed and infrequent. We show that a well trained deep neural network can spot relevantfeatures and keep a low number of region proposals without any extra preprocessing or post-processing. Due to the visual nature of the task, we designed a three-dimensional convolutional neural network with residual connections. It was inspired by the region proposal network of the Faster R-CNN detection framework. The evaluation is performed on the LUNA16 dataset. The final score is 0.826 which is the average sensitivity at 0.125, 0.25, 0.5, 1, 2, 4, and 8 false positives per scan. It can be considered as an average score compared to other submissions to the challenge. However, the solution described here was trained end-to-end and has fewer trainable parameters. / Objektdetektering i naturliga bilder har reducerates till en enstegs process tack vare genombrott i djupa neurala nätverk. Automatisk detektering av pulmonella nodulärer är vanligtvis ett trestegsproblem: segmentering av lunga, generering av nodulärkandidater och reducering av falska positiva utfall. Det här projektet tar sig an nodulärdetektering med en enstegsmodell med hjälp av ett djupt neuralt nätverk. Pulmonella nodulärer har unika karaktärsdrag som inte finns utanför lungorna. Modellen förväntas fånga dessa drag och enbart fokusera på element inuti lungorna när den arbetar med datortomografibilder. Nodulärer är små och glest föredelade. Vi visar att ett vältränat nätverk kan finna relevanta särdrag samt föreslå ett lågt antal intresseregioner utan extra för- eller efter- behandling. På grund av den visuella karaktären av det här problemet så designade vi ett tredimensionellt s.k. convolutional neural network med residualkopplingar. Projektet inspirerades av Faster R-CNN, ett nätverk som utmärker sig i sin förmåga att detektera intresseregioner. Nätverket utvärderades på ett dataset vid namn LUNA16. Det slutgiltiga nätverket testade 0.826, vilket är genomsnittlig sensitivitet vid 0.125, 0.25, 0.5, 1, 2, 4, och 8 falska positiva per utvärdering. Detta kan anses vara genomsnittligt jämfört med andra deltagande i tävlingen, men lösningen som föreslås här är en enstegslösning som utför detektering från början till slut och har färre träningsbara parametrar. / La détection d’objets sur les images naturelles est devenue au fil du temps un processus réalisé de bout en bout en une seule étape grâce aux évolutions récentes des architectures de neurones artificiels profonds. En revanche, la détection automatique de nodules pulmonaires est généralement un processus en trois étapes : la segmentation des poumons (pré-traitement), la génération de zones d’intérêt (modèle) et la réduction des faux positifs (post-traitement). Ce projet s’attaque à la détection des nodules pulmonaires en une seule étape avec un réseau profond de neurones artificiels. Les nodules pulmonaires ont des formes et des structures uniques qui ne sont pas présentes en dehors de cet organe. Nous nous attendons à ce qu’un modèle soit capable de capturer ces caractéristiques et de se focaliser uniquement sur les éléments à l’intérieur des poumons alors même qu’il reçoit des images brutes (sans segmentation des poumons). Les nodules sont petits, peu fréquents et répartis aléatoirement. Nous montrons qu’un modèle correctement entraîné peut repérer les éléments caractéristiques des nodules et générer peu de localisations sans pré-traitement ni post-traitement. Du fait de la nature visuelle de la tâche, nous avons développé un réseau neuronal convolutif tridimensionnel. L’architecture utilisée est inspirée du méta-algorithme de détection Faster R-CNN. L’évaluation est réalisée avec le jeu de données du challenge LUNA16. Le score final est de 0.826 qui représente la sensibilité moyenne pour les valeurs de 0.125, 0.25, 0.5, 1, 2, 4 et 8 faux positifs par scanner. Il peut être considéré comme un score moyen comparé aux autres contributions du challenge. Cependant, la solution décrite montre la faisabilité d’un modèle en une seule étape, entraîné de bout en bout. Le réseau comporte moins de paramètres que la majorité des solutions.

No description available.

京都大学 / 新制・課程博士 / 博士(医学) / 甲第24879号 / 医博第5013号 / 新制||医||1068(附属図書館) / 京都大学大学院医学研究科医学専攻 / (主査)教授 後藤 慎平, 教授 渡邊 直樹, 教授 平井 豊博 / 学位規則第4条第1項該当 / Doctor of Medical Science / Kyoto University / DFAM

Lung cancer is one of the main causes of death worldwide, with most patients suffering from an advanced unresectable or metastatic non-small cell lung cancer. The mortality trends are mostly related to patterns of tobacco use, specifically from cigarettes. Tobacco is the basic etiological agent found as a consequence of the inhalation of tobacco smoke. Published data show the use of interferons (IFNs) in the treatment of lung tumours due to their potential in displaying antiproliferative, anti-angiogenic, immunoregulatory, and proapoptotic effects. Type1 IFNs have been employed as treatments for many types of cancer, both for haematological cancers and solid tumours. The IFN-γ (naked) functions as an anticancer agent against various forms of cancer. Hence, this study aimed to investigate the genoprotective and genotoxic effects of IFN-γ liposome (nano) on 42 blood samples from lung cancer patients, compared to the same sample size from healthy individuals. The effectiveness of IFN- γ liposome against oxidative stress was also evaluated in this study. A concentration of 100U/ml of IFN-γ liposome was used to treat the lymphocytes in: Comet and micronucleus assays, Comet repair, Western blotting and real-time polymerase chain reaction (qPCR) were based on a preliminary test for the optimal dose. The lymphocytes from lung cancer patients presented with higher DNA damage levels than those of healthy individuals. IFN-γ liposome was not found to induce any DNA damage in the lymphocytes. Also, it caused a significant reduction in DNA damage in the lymphocytes from lung cancer patients in; Comet, Comet repair and micronucleus assays. Furthermore, the 100U/ml of IFN-γ liposome significantly reduced the oxidative stress caused by H2O2 and appeared to be effective in both groups using the Comet and micronucleus assays. Results from; Comet, Comet repair and micronucleus assays were consistent. The data obtained indicated that IFN-γ in both forms (naked INF-γ and INF-γ nano-liposome) may potentially be effective for the treatment of lung cancer and showed the ability of IFN-γ liposome to reduce the DNA damage more than the naked form. The IFN-γ in both forms has also shown anti-cancer potential in the lymphocytes from lung cancer patients by regulating the expression of p53, p21, Bcl-2 at mRNA and protein levels by up-regulating the p53 and p21 to mediate cell cycle arrest and DNA repair in lung cancer patients. The findings of this study are consistent with the view that the naked IFN-γ and liposome could have a significant role in cancer treatment, including lung cancer. / Mutah University in Jordan

No description available.

No description available.

No description available.

No description available.