Search

Intraductal Papillary Mucinous Neoplasm (IPMN) cysts are pre-malignant pancreas lesions, and they can progress into pancreatic cancer. Therefore, detecting and stratifying their risk level is of ultimate importance for effective treatment planning and disease control. However, this is a highly challenging task because of the diverse and irregular shape, texture, and size of the IPMN cysts as well as the pancreas. In this study, we propose a novel computer-aided diagnosis pipeline for IPMN risk classification from multi-contrast MRI scans. Our proposed analysis framework includes an efficient volumetric self-adapting segmentation strategy for pancreas delineation, followed by a newly designed deep learning-based classification scheme with a radiomics-based predictive approach. We test our proposed decision-fusion model in multi-center data sets of 246 multi-contrast MRI scans and obtain superior performance to the state of the art (SOTA) in this field. Our ablation studies demonstrate the significance of both radiomics and deep learning modules for achieving the new SOTA performance compared to international guidelines and published studies (81.9% vs 61.3% in accuracy). Our findings have important implications for clinical decision-making. In a series of rigorous experiments on multi-center data sets (246 MRI scans from five centers), we achieved unprecedented performance (81.9% accuracy). The code is available upon publication.

Visual explanation methods have an important role in the prognosis of the patients where the annotated data is limited or unavailable. There have been several attempts to use gradient-based attribution methods to localize pathology from medical scans without using segmentation labels. This research direction has been impeded by the lack of robustness and reliability. These methods are highly sensitive to the network parameters. In this study, we introduce a robust visual explanation method to address this problem for medical applications. We provide an innovative visual explanation algorithm for general purpose and as an example application we demonstrate its effectiveness for quantifying lesions in the lungs caused by the Covid-19 with high accuracy and robustness without using dense segmentation labels. This approach overcomes the drawbacks of commonly used Grad-CAM and its extended versions. The premise behind our proposed strategy is that the information flow is minimized while ensuring the classifier prediction stays similar. Our findings indicate that the bottleneck condition provides a more stable severity estimation than the similar attribution methods. The source code will be publicly available upon publication.

We propose a novel 3D fully convolutional deep network for automated pancreas segmentation from both MRI and CT scans. More specifically, the proposed model consists of a 3D encoder that learns to extract volume features at different scales; features taken at different points of the encoder hierarchy are then sent to multiple 3D decoders that individually predict intermediate segmentation maps. Finally, all segmentation maps are combined to obtain a unique detailed segmentation mask. We test our model on both CT and MRI imaging data: the publicly available NIH Pancreas-CT dataset (consisting of 82 contrast-enhanced CTs) and a private MRI dataset (consisting of 40 MRI scans). Experimental results show that our model outperforms existing methods on CT pancreas segmentation, obtaining an average Dice score of about 88%, and yields promising segmentation performance on a very challenging MRI data set (average Dice score is about 77%). Additional control experiments demonstrate that the achieved performance is due to the combination of our 3D fully-convolutional deep network and the hierarchical representation decoding, thus substantiating our architectural design.

The kinetic mechanism of NADP-dependent malic enzyme purified from maize leaves was studied in the physiological direction. Product inhibition and substrate analogues studies with 3' aminopyridine dinucleotide phosphate and tartrate indicate that the enzyme reaction follows a sequential ordered Bi-Ter kinetic mechanism. NADP is the leading substrate followed by L-malate and the products are released in the order of CO2, pyruvate and NADPH. The enzyme also catalyzes a slow, magnesium-dependent decarboxylation of oxaloacetate and reduction of pyruvate and oxaloacetate in the presence of NADPH to produce L-lactate and L-malate, respectively.

The effect of structural analogues of L-malate was studied on NADP-malic enzyme purified from Zea mays L. leaves. Among the compounds tested, the organic acids behaved as more potent inhibitors at pH 7.0 than at pH 8.0, suggesting that the dimeric form was more susceptible to the inhibition than the tetrameric form of the enzyme.Oxalate, ketomalonate, hydroxymalonate, malonate, oxaloacetate, tartrate, α-hydroxybutyrate, α-ketobutyrate, α-ketoglutarate and α-hydroxyglutarate exhibited linear competitive inhibition with respect to the substrate L-malate at pH 8.0. On the other hand, glyoxylate and glycolate turned out to be non-competitive inhibitors, while glycolaldehyde, succinate, fumarate, maleate and β- and γ-hydroxybutyrate had no effect on the enzyme activity, at the concentrations assayed. These results suggest that the extent of inhibition was dependent on the size of the analogues and that the presence of an 1-carboxyl group along with a 2-hydroxyl or 2-keto group was important for binding of the substrate analogue to the enzyme.

Structural analogues of the NADP(+) were studied as potential coenzymes and inhibitors for NADP(+) dependent malic enzyme from Zea mays L. leaves. Results showed that 1, N(6)-etheno-nicotinamide adenine dinucleotide phosphate (∈ NADP(+)), 3-acetylpyridine-adenine dinucleotide phosphate (APADP(+)), nicotinamide-hypoxanthine dinucleotide phosphate (NHDP(+)) and β-nicotinamide adenine dinucleotide 2': 3'-cyclic monophosphate (2'3'NADPc(+)) act as alternate coenzymes for the enzyme and that there is little variation in the values of the Michaelis constants and only a threefold variation in Vmax for the five nucleotides. On the other hand, thionicotinamide-adenine dinucleotide phosphate (SNADP(+)), 3-aminopyridine-adenine dinucleotide phosphate (AADP(+)), adenosine 2'-monophosphate (2'AMP) and adenosine 2': 3'-cyclic monophosphate (2'3'AMPc) were competitive inhibitors with respect to NADP(+), while β-nicotinamide adenine dinucleotide 3'-phosphate (3'NADP(+)), NAD(+), adenosine 3'-monophosphate (3'AMP), adenosine 2': 5'-cyclic monophosphate (2'5'AMPc), 5'AMP, 5'ADP, 5'ATP and adenosine act as non-competitive inhibitors. These results, together with results of semiempirical self-consistent field-molecular orbitals calculations, suggest that the 2'-phosphate group is crucial for the nucleotide binding to the enzyme, whereas the charge density on the C4 atom of the pyridine ring is the major factor that governs the coenzyme activity.