Search

Separating and labeling each nuclear instance (instance-aware segmentation) is the key challenge in nuclear image segmentation. Deep Convolutional Neural Networks have been demonstrated to solve nuclear image segmentation tasks across different imaging modalities, but a systematic comparison on complex immunofluorescence images has not been performed. Deep learning based segmentation requires annotated datasets for training, but annotated fluorescence nuclear image datasets are rare and of limited size and complexity. In this work, we evaluate and compare the segmentation effectiveness of multiple deep learning architectures (U-Net, U-Net ResNet, Cellpose, Mask R-CNN, KG instance segmentation) and two conventional algorithms (Iterative h-min based watershed, Attributed relational graphs) on complex fluorescence nuclear images of various types. We propose and evaluate a novel strategy to create artificial images to extend the training set. Results show that instance-aware segmentation architectures and Cellpose outperform the U-Net architectures and conventional methods on complex images in terms of F1 scores, while the U-Net architectures achieve overall higher mean Dice scores. Training with additional artificially generated images improves recall and F1 scores for complex images, thereby leading to top F1 scores for three out of five sample preparation types. Mask R-CNN trained on artificial images achieves the overall highest F1 score on complex images of similar conditions to the training set images while Cellpose achieves the overall highest F1 score on complex images of new imaging conditions. We provide quantitative results demonstrating that images annotated by under-graduates are sufficient for training instance-aware segmentation architectures to efficiently segment complex fluorescence nuclear images.

Simple Summary: Tumor segmentation is a key step in oncologic imaging processing. We have recently developed a model to detect and segment neuroblastic tumors on MR images based on deep learning architecture nnU-Net. In this work, we performed an independent validation of the automatic segmentation tool with a large heterogeneous dataset. We reviewed the automatic segmentations and manually edited them when necessary. We were able to show that the automatic network was able to locate and segment the primary tumor on the T2 weighted images in the majority of cases, with an extremely high agreement between the automatic tool and the manually edited masks. The time needed for manual adjustment was very low. Objectives. To externally validate and assess the accuracy of a previously trained fully automatic nnU-Net CNN algorithm to identify and segment primary neuroblastoma tumors in MR images in a large children cohort. Methods. An international multicenter, multivendor imaging repository of patients with neuroblastic tumors was used to validate the performance of a trained Machine Learning (ML) tool to identify and delineate primary neuroblastoma tumors. The dataset was heterogeneous and completely independent from the one used to train and tune the model, consisting of 300 children with neuroblastic tumors having 535 MR T2-weighted sequences (486 sequences at diagnosis and 49 after finalization of the first phase of chemotherapy). The automatic segmentation algorithm was based on a nnU-Net architecture developed within the PRIMAGE project. For comparison, the segmentation masks were manually edited by an expert radiologist, and the time for the manual editing was recorded. Different overlaps and spatial metrics were calculated to compare both masks. Results. The median Dice Similarity Coefficient (DSC) was high 0.997; 0.944–1.000 (median; Q1–Q3). In 18 MR sequences (6%), the net was not able neither to identify nor segment the tumor. No differences were found regarding the MR magnetic field, type of T2 sequence, or tumor location. No significant differences in the performance of the net were found in patients with an MR performed after chemotherapy. The time for visual inspection of the generated masks was 7.9 ± 7.5 (mean ± Standard Deviation (SD)) seconds. Those cases where manual editing was needed (136 masks) required 124 ± 120 s. Conclusions. The automatic CNN was able to locate and segment the primary tumor on the T2-weighted images in 94% of cases. There was an extremely high agreement between the automatic tool and the manually edited masks. This is the first study to validate an automatic segmentation model for neuroblastic tumor identification and segmentation with body MR images. The semi-automatic approach with minor manual editing of the deep learning segmentation increases the radiologist's confidence in the solution with a minor workload for the radiologist. [ABSTRACT FROM AUTHOR]

Simple Summary: Tumor segmentation is a key step in oncologic imaging processing and is a time-consuming process usually performed manually by radiologists. To facilitate it, there is growing interest in applying deep-learning segmentation algorithms. Thus, we explore the variability between two observers performing manual segmentation and use the state-of-the-art deep learning architecture nnU-Net to develop a model to detect and segment neuroblastic tumors on MR images. We were able to show that the variability between nnU-Net and manual segmentation is similar to the inter-observer variability in manual segmentation. Furthermore, we compared the time needed to manually segment the tumors from scratch with the time required for the automatic model to segment the same cases, with posterior human validation with manual adjustment when needed. Tumor segmentation is one of the key steps in imaging processing. The goals of this study were to assess the inter-observer variability in manual segmentation of neuroblastic tumors and to analyze whether the state-of-the-art deep learning architecture nnU-Net can provide a robust solution to detect and segment tumors on MR images. A retrospective multicenter study of 132 patients with neuroblastic tumors was performed. Dice Similarity Coefficient (DSC) and Area Under the Receiver Operating Characteristic Curve (AUC ROC) were used to compare segmentation sets. Two more metrics were elaborated to understand the direction of the errors: the modified version of False Positive (FPRm) and False Negative (FNR) rates. Two radiologists manually segmented 46 tumors and a comparative study was performed. nnU-Net was trained-tuned with 106 cases divided into five balanced folds to perform cross-validation. The five resulting models were used as an ensemble solution to measure training (n = 106) and validation (n = 26) performance, independently. The time needed by the model to automatically segment 20 cases was compared to the time required for manual segmentation. The median DSC for manual segmentation sets was 0.969 (±0.032 IQR). The median DSC for the automatic tool was 0.965 (±0.018 IQR). The automatic segmentation model achieved a better performance regarding the FPRm. MR images segmentation variability is similar between radiologists and nnU-Net. Time leverage when using the automatic model with posterior visual validation and manual adjustment corresponds to 92.8%. [ABSTRACT FROM AUTHOR]

Clinical decision-making in cancer and other diseases relies on timely and cost-effective genome-wide testing. Classical bioinformatic algorithms, such as Rawcopy, can support genomic analysis by calling genomic breakpoints and copy-number variations (CNVs), but often require manual data curation, which is error prone, time-consuming, and thus substantially increasing costs of genomic testing and hampering timely delivery of test results to the treating physician. We aimed to investigate whether deep learning algorithms can be used to learn from genome-wide single-nucleotide polymorphism array (SNPa) data and improve state-of-the-art algorithms. We developed, applied, and validated a novel deep neural network (DNN), DeepSNP. A manually curated data set of 50 SNPa analyses was used as truth-set. We show that DeepSNP can learn from SNPa data and classify the presence or absence of genomic breakpoints within large genomic windows with high precision and recall. DeepSNP was compared with well-known neural network models as well as with Rawcopy. Moreover, the use of a localization unit indicates the ability to pinpoint genomic breakpoints despite their exact location not being provided while training. DeepSNP results demonstrate the potential of DNN architectures to learn from genomic SNPa data and encourage further adaptation for CNV detection in SNPa and other genomic data types. [ABSTRACT FROM AUTHOR]