Overlapping cytoplasms segmentation via constrained multi-shape evolution for cervical cancer screening.

Segmenting overlapping cytoplasms in cervical smear images is a clinically essential task for quantitatively measuring cell-level features to screen cervical cancer This task, however, remains rather challenging, mainly due to the deficiency of intensity (or color) information in the overlapping region Although shape prior-based models that compensate intensity deficiency by introducing prior shape information about cytoplasm are firmly established, they often yield visually implausible results, as they model shape priors only by limited shape hypotheses about cytoplasm, exploit cytoplasm-level shape priors alone, and impose no shape constraint on the resulting shape of the cytoplasm In this paper, we present an effective shape prior-based approach, called constrained multi-shape evolution, that segments all overlapping cytoplasms in the clump simultaneously by jointly evolving each cytoplasm's shape guided by the modeled shape priors We model local shape priors (cytoplasm-level) by an infinitely large shape hypothesis set which contains all possible shapes of the cytoplasm In the shape evolution, we compensate intensity deficiency for the segmentation by introducing not only the modeled local shape priors but also global shape priors (clump-level) modeled by considering mutual shape constraints of cytoplasms in the clump We also constrain the resulting shape in each evolution to be in the built shape hypothesis set for further reducing implausible segmentation results We evaluated the proposed method in two typical cervical smear datasets, and the extensive experimental results confirm its effectiveness.

Small Molecule-Drug Conjugates Emerge as a New Promising Approach for Cancer Treatment.

Antibody drug conjugates (ADCs) have emerged as a new promising class of anti- cancer agents. However, limitations such as higher costs and unavoidable immunogenicity due to their relatively large structures cannot be ignored. Therefore, the development of lightweight drugs such as small molecule-drug conjugates (SMDCs) based on the ADC design idea has become a new option for targeted therapy. SMDCs are derived from the coupling of small-molecule targeting ligands with cytotoxic drugs. They are composed of three parts: small-molecule targeting ligands, cytotoxic molecules, and linkers. Compared with ADCs, SMDCs can be more rapidly and evenly dispersed into tumor tissues, with low cost and no immunogenicity. In this article, we will give a comprehensive review of different types of SMDCs currently under clinical trials to provide ideas and inspirations for the development of clinically applicable SMDCs.

Advances, challenge and prospects in cell-mediated nanodrug delivery for cancer therapy: a review.

Nanomedicine offers considerable opportunities to improve drugability and reduce toxicity for tumour therapy. However, the application of nanomedicine has achieved little success in clinical trials due to multiple physiological barriers to drug delivery. Circulating cells are expected to improve the physical distribution of drugs and enhance the therapeutic effect by overcoming various biological barriers in collaboration with nano-drug delivery systems owing to excellent biocompatibility, low immunogenicity and a long-circulation time and strong binding specificity. Nonetheless, we have noticed some limitations in implementing tthe strategy. In this article, we intend to introduce the latest progress in research and application of circulating cell-mediated nano-drug delivery systems, describe the main cell-related drug delivery modes, sum up the relevant points of the transport systems in the process of loading, transport and release, and lastly discuss the advantages, challenges and future development trends in cell-mediated nano-drug delivery.

Modification of sodium aescinate into a safer, more stable and effective water-soluble drug by liposome-encapsulation: an in vitro and in vivo study.

Sodium aescinate (SA) is often used for intravenous (IV) injection owing to its anti-inflammatory, anti-exudative, increasing venous tension, improving blood circulation and reducing swelling activities. However, the clinical application of SA is limited by strong irritation, short half-life and low bioavailability. To overcome these defects, we intended to modify SA by encapsualing it with liposomes . SA was mixed with a proper amount of phospholipid and lyophilized to prepare the liposome of sodium aescinate for injection (SA-Lip-I). Its physical properties, cumulative release and dilution stability were evaluated in vitro. Its pharmacodynamic characteristics were evaluated. Safety of SA-Lip-I was evaluated in terms of hemolysis, IV irritation and acute toxicity. The mean particle size of SA-Lip-I was 117.33±0.95 nm, polydispersity index (PDI) was 0.140±0.017, Zeta potential was -30.34±0.23 mv, The cumulative release of SA-Lip at 12 h was more than 80%, which met the release requirements of nanoparticles. SA-Lip-I was well stable in the four mediators and met the clinical medication requirements. In addition, SA-Lip-I had better efficacy than the SA-I and has a significant difference. Furthermore, SA-Lip-I did not induce hemolysis at 37°C, and produced by far milder venous irritation as compared with SA-I. In addition, LD50 of SA-Lip-I was 2.12 fold that of the commercial SA-I, with no obvious side effects.The modified SA-Lip-I is a promising preparation which can reduce the irritation and toxic side effects, improve the treatment effect to a certain extent, but greatly alleviate pain of the patient during treatment, achieving the optimal curative effect.

Preparation and characterization of paclitaxel palmitate albumin nanoparticles with high loading efficacy: an in vitro and in vivo anti-tumor study in mouse models.

BACKGROUND: Combination of the prodrug technique with an albumin nano drug-loaded system is a novel promising approach for cancer treatment. However, the long-lasting and far-reaching challenge for the treatment of cancers lies in how to construct the albumin nanometer drug delivery system with lead compounds and their derivatives. METHODS: In this study, we reported the preparation of injectable albumin nanoparticles (NPs) with a high and quantitative drug loading system based on the NabTM technology of paclitaxel palmitate (PTX-PA). RESULTS: Our experimental study on drug tissue distribution in vivo demonstrated that the paclitaxel palmitate albumin nanoparticles (Nab-PTX-PA) remained in the tumor for a longer time post-injection. Compared with saline and paclitaxel albumin nanoparticles (Abraxane®), intravenous injection of Nab-PTX-PA not only reduced the toxicity of the drug in normal organs, and increased the body weight of the animals but maintained sustained release of paclitaxel (PTX) in the tumor, thereby displaying an excellent antitumor activity. Blood routine analysis showed that Nab-PTX-PA had fewer adverse effects or less toxicity to the normal organs, and it inhibited tumor cell proliferation more effectively as compared with commercial paclitaxel albumin nanoparticles. CONCLUSIONS: This carrier strategy for small molecule drugs is based on naturally evolved interactions between long-chain fatty acids (LCFAs) and Human Serum Albumin (HSA), demonstrated here for PTX. Nab-PTX-PA shows higher antitumor efficacy in vivo in breast cancer models. On the whole, this novel injectable Nab-PTX-PA has great potential as an effective drug delivery system in the treatment of breast cancer.

Quantitative analysis of patients with celiac disease by video capsule endoscopy: A deep learning method.

BACKGROUND: Celiac disease is one of the most common diseases in the world. Capsule endoscopy is an alternative way to visualize the entire small intestine without invasiveness to the patient. It is useful to characterize celiac disease, but hours are need to manually analyze the retrospective data of a single patient. Computer-aided quantitative analysis by a deep learning method helps in alleviating the workload during analysis of the retrospective videos. METHOD: Capsule endoscopy clips from 6 celiac disease patients and 5 controls were preprocessed for training. The frames with a large field of opaque extraluminal fluid or air bubbles were removed automatically by using a pre-selection algorithm. Then the frames were cropped and the intensity was corrected prior to frame rotation in the proposed new method. The GoogLeNet is trained with these frames. Then, the clips of capsule endoscopy from 5 additional celiac disease patients and 5 additional control patients are used for testing. The trained GoogLeNet was able to distinguish the frames from capsule endoscopy clips of celiac disease patients vs controls. Quantitative measurement with evaluation of the confidence was developed to assess the severity level of pathology in the subjects. RESULTS: Relying on the evaluation confidence, the GoogLeNet achieved 100% sensitivity and specificity for the testing set. The t-test confirmed the evaluation confidence is significant to distinguish celiac disease patients from controls. Furthermore, it is found that the evaluation confidence may also relate to the severity level of small bowel mucosal lesions. CONCLUSIONS: A deep convolutional neural network was established for quantitative measurement of the existence and degree of pathology throughout the small intestine, which may improve computer-aided clinical techniques to assess mucosal atrophy and other etiologies in real-time with videocapsule endoscopy.